From grid fault diagnosis to vehicle-to-building optimization — building energy systems that are secure, adaptive, and resilient.
Modern power grids are under pressure from every direction. Renewable generation peaks when demand is lowest, creating supply-demand mismatches that stress infrastructure. A single fifteen-minute demand spike can determine an entire month’s commercial electricity bill. Data center electricity demand is projected to triple by 2030. And as cities electrify their transit fleets, thousands of new high-power loads are connecting to grids that were never designed for them.
At the same time, these grids face growing threats — from cyberattacks that can manipulate protection systems to wildfires that force rapid reconfiguration of transmission networks. The traditional approach of overbuilding capacity and relying on manual intervention cannot scale to meet these challenges.
The SCOPE Lab has built a research program that spans the full arc of energy system intelligence: from diagnosing faults and detecting anomalies, through securing decentralized energy markets, to turning electric vehicle fleets into mobile energy assets that stabilize the grid. Each piece of work builds on what came before, creating a coherent path from monitoring through control through optimization.
Reliable grid operation starts with knowing the state of the system — and knowing when something has gone wrong. In collaboration with Saqib Hasan and the Vanderbilt Institute for Software Integrated Systems, we developed hierarchical fault diagnosis methods that use temporal causal diagrams to reason about cascading failures in cyber-physical energy systems. When a fault occurs in a power grid, its effects propagate through both the physical network (voltage drops, frequency deviations) and the cyber infrastructure (sensor failures, communication delays). Our approach models these coupled propagation paths and reasons backward from observed symptoms to root causes — enabling operators to identify not just that something failed, but where and why.
We built simulation testbeds that allow researchers to study how cascading failures propagate through realistic grid topologies, and developed systematic methods for identifying optimal load control actions that can arrest a cascade before it reaches a blackout. More recently, WENFlow (ICCPS 2026) applies wavelet-enhanced normalizing flows for real-time anomaly detection across city-wide sensor networks — detecting irregular behavior in power grid measurements, traffic sensors, and other CPS infrastructure with the speed needed for operational response.
Power grids are attractive targets for cyberattack because the physical consequences are immediate and widespread. An attacker who compromises protection relays or manipulates sensor readings can trigger cascading failures that affect millions of people.
We developed a game-theoretic framework for defending power systems against dynamic cyber-attacks, where an attacker and defender interact over multiple rounds — the attacker probing for vulnerabilities, the defender adapting protection strategies. This work, led by Saqib Hasan, moves beyond static vulnerability analysis to model the strategic interaction between sophisticated adversaries and resource-constrained defenders. We also built Power-Attack, a comprehensive tool-chain for modeling and simulating attacks in power systems, giving researchers a controlled environment to evaluate defense strategies before deploying them on real infrastructure.
As energy systems become more decentralized — with microgrids, prosumers, and peer-to-peer trading — new attack surfaces emerge. Our work on cyber-attacks in blockchain-based transactive energy systems identified vulnerabilities specific to decentralized energy markets and developed mitigation strategies that maintain market integrity even under adversarial conditions.
The traditional grid is centrally controlled, but the future grid will be decentralized — with distributed generation, local storage, and peer-to-peer energy trading. This transition requires new market mechanisms and middleware platforms.
TRANSAX is a blockchain-based decentralized forward-trading energy exchange we developed for transactive microgrids. Prosumers — participants who both produce and consume energy — can trade energy futures with each other through smart contracts, without relying on a central market operator. The platform preserves privacy and safety through cryptographic commitments and formal verification of smart contracts via VeriSolid, ensuring that trades are executed correctly by construction. We also explored broader questions about blockchains for transactive energy systems — the opportunities they create for decentralized coordination and the challenges they introduce around scalability, latency, and governance.
The middleware that makes this possible is RIAPS — the Resilient Information Architecture Platform for Smart Systems — which provides the fault-tolerant, real-time distributed computing foundation that decentralized grid applications need. RIAPS manages the complexity of coordinating multiple interacting agents (solar inverters, battery controllers, load managers) across unreliable communication networks, and has been deployed in microgrid testbeds for both transactive energy and distributed control applications.
MODiCuM extended these ideas beyond energy to general decentralized computation — a blockchain-based marketplace for outsourcing computation with verifiable execution guarantees.
Grid resilience is tested most severely during extreme events, when operators must make rapid reconfiguration decisions under uncertainty. Wildfires present a particularly difficult case: as fire spreads, transmission lines must be de-energized to prevent ignition, but every line taken offline changes power flows across the entire network.
We developed a reinforcement-learning-based proactive control system that learns to reconfigure the grid ahead of advancing wildfire, de-energizing threatened lines while maintaining power delivery to as many customers as possible. The RL agent is trained on realistic wildfire spread models — informed by WildfireDB, an open-source dataset connecting wildfire spread with terrain, weather, and vegetation determinants that we released at NeurIPS 2021. This work demonstrates that learned policies can outperform rule-based heuristics for grid reconfiguration under the kind of spatially-evolving, uncertain threats that climate change is making more frequent.
All of the challenges above — monitoring, security, decentralized control, resilience — converge when electric vehicles connect to the grid. EVs are not just loads; with bidirectional charging, they become mobile batteries that can absorb excess generation, shave demand peaks, and provide emergency power during outages. A modern EV carries 55–78 kWh of storage — enough to power a typical home for multiple days. And vehicles sit parked roughly 95% of the time.
But realizing this potential is hard. The optimization problem is enormous: with just 10 chargers and 10 charging rate options, the action space reaches 10 billion possibilities per time step, multiplied by 96 steps per day, over 30-day billing cycles. Decisions must be made without knowing future EV arrivals, departure times, desired charge levels, or electricity prices. And demand charges — which depend on a single highest fifteen-minute peak over an entire month — mean that one missed spike erases weeks of careful optimization.
Our vehicle-grid work began with CARTA’s electric transit fleet in Chattanooga. Working with Rishav Sen and the DOE-funded smart transportation projects, we built E-Transit-Bench — a co-simulation platform integrating transit operations (via SUMO) with power grid modeling (via GridLAB-D) to analyze how bus electrification affects grid stability. This platform revealed that strategic charging scheduling can significantly reduce grid stress while maintaining transit service — but that the optimization problem requires understanding both the transportation and energy domains simultaneously.
This insight led to our partnership with Nissan Advanced Technology Center, focused on vehicle-to-building (V2B) optimization — using parked EVs to shave building demand peaks and reduce electricity costs. The research has progressed through five publications at top venues over two years, each addressing a limitation of the previous approach:
OPTIMUS (SmartComp 2024) established the simulation foundation — a discrete-event platform built on real Nissan operational data that provides a shared benchmark for comparing V2B algorithms. OPTIMUS includes generative models trained on real EV arrival and building load data, modular policy engines, and a web dashboard for non-technical users.
RL-V2B (AAMAS 2025, Best Paper Nominated) tackled the learning challenge. Standard reinforcement learning struggles with V2B because rewards are sparse — the demand charge that determines the monthly bill is only known at the end of the billing period. Our enhanced DDPG framework uses action masking to enforce feasible charger states and MILP-driven policy guidance to accelerate training. Validated on nine months of real Nissan data, RL-V2B achieved over 4% cost savings compared to heuristic baselines while meeting 100% of EV charging requirements.
DG-MCTS (ICCPS 2025) addressed the need for online, non-myopic decision-making under uncertainty. Rather than learning a fixed policy, DG-MCTS uses domain-guided Monte Carlo Tree Search to plan at each time step — sampling possible future EV arrivals and building loads, pruning the action space with domain heuristics, and evaluating candidate actions through simulation rollouts. DG-MCTS achieved the lowest costs in six of eight test months, roughly 3% cheaper than RL, with better robustness under high uncertainty.
P-V2B (ICCPS 2026) introduced a key insight: employees return to the same workplace daily, creating persistence that can be exploited for multi-day coordination. The neuro-symbolic framework combines a Monte Carlo MPC layer for short-horizon symbolic optimization with a neural value function that predicts monthly peak power based on daily overcharging patterns. This enables cross-day coordination — proactively overcharging during low-demand periods to enable deeper discharge during peaks — that provably achieves lower or equal cost than any daily-decomposed policy.
CONSENT (AAMAS 2026) moved beyond pure optimization to human-centered negotiation. Real V2B systems involve real people who need their cars charged by specific times. CONSENT explicitly models user flexibility — departure times, desired charge levels — and generates personalized pricing options that incentivize flexibility. The mechanism is strategy-proof (users cannot game it), budget-feasible (incentives are capped at expected savings), and voluntary (every participant benefits). In testing, operator costs dropped roughly 6%, user costs dropped roughly 22%, and approximately 78% of users chose to participate.
Our energy research is converging toward multi-site, multi-region coordination. The next step is inter-building energy trading — coordinating V2B across multiple buildings on a campus with shared EV fleets. Beyond that, we are working toward regional VGI coordination across geographically distributed sites, integration with demand response signals from distribution system operators, and the use of second-life EV batteries as stationary reserve storage for neighborhood-scale microgrid resilience.
The common thread across all of this work — from fault diagnosis through blockchain markets through V2B optimization — is that energy systems are cyber-physical systems, and making them intelligent requires the same principled approach to uncertainty, real-time decision-making, and human-system interaction that defines the SCOPE Lab’s research across all domains.
This work reflects collaboration across institutions and industry. Our partners include Nissan Advanced Technology Center, CARTA, the Vanderbilt Center for Sustainability, Energy and Climate (VSEC), Penn State University, and Banaras Hindu University. Grid security and diagnosis work has been conducted in collaboration with Saqib Hasan and Xenofon Koutsoukos at Vanderbilt, and grid resilience work with Anurag Srivastava at West Virginia University.
Funding has been provided by the Department of Energy, Nissan, National Science Foundation, Vanderbilt VSEC, and DARPA.
Selected Publications:
@inproceedings{iccps2026_pv2b,
author = {Sen, Rishav and Liu, Fangqi and Talusan, Jose Paolo and Pettet, Ava and Suzue, Yoshinori and Mukhopadhyay, Ayan and Dubey, Abhishek},
title = {Persistent Vehicle-to-Building Integration via Neuro-Symbolic Control},
year = {2026},
booktitle = {Proceedings of the HSCC/ICCPS 2026: 29th ACM International Conference on Hybrid Systems: Computation and Control and 17th ACM/IEEE International Conference on Cyber-Physical Systems},
location = {Saint Malo, France},
keywords = {vehicle-to-building, EV charging, demand charge management, user persistence, neuro-symbolic control, Monte Carlo tree search, model predictive control},
note = {Acceptance rate: 28\%; Regular Paper; Track: Systems and Applications},
series = {HSCC/ICCPS '26},
what = {P-V2B introduces a neuro-symbolic framework for vehicle-to-building charging that incorporates user persistence information alongside technical optimization. The work addresses the persistent user problem where electric vehicles exhibit recurring arrival patterns over time at buildings, enabling buildings to anticipate charging demand and schedule charging strategically. The approach combines a neuro-symbolic control framework integrating Monte Carlo Model Predictive Control with a learned value function to handle both short-horizon feasibility and long-horizon demand-charge prediction, accounting for user behavior patterns while managing real-time constraints.},
why = {Vehicle-to-building systems present a complex control challenge combining real-time physical constraints with long-horizon stochastic effects of user behavior, where traditional decomposition approaches fail to capture crucial dependencies. The innovation lies in explicitly leveraging user persistence—the observation that EV users exhibit recurring patterns—as a key input alongside technical constraints, enabling more intelligent demand charge management. This bridges control theory and behavioral modeling, providing a principled way to incorporate user behavioral patterns into cyber-physical system optimization.},
results = {Evaluation on real EV fleet data from a major California manufacturer demonstrates substantial improvements in demand charge reduction and total operating costs compared to both heuristic baselines and prior work that ignore user persistence. The neuro-symbolic framework achieves significant cost savings while ensuring feasibility and full compliance with user charging requirements, validating the effectiveness of persistence-aware control strategies.},
project_tags = {energy, CPS, planning}
}
Vehicle-to-Building (V2B) integration is a cyber–physical system (CPS) where Electric Vehicles (EVs) enhance building resilience by serving as mobile storage for peak shaving, reducing monthly peak-power demand charges, supporting grid stability, and lowering electricity costs. We introduce the Persistent Vehicle-to-Building (P-V2B) problem, a long-horizon formulation that incorporates user-level persistence, where each EV corresponds to a consistent user identity across days. This structure captures recurring arrival patterns and travel-related external energy use, common in employee-based facilities with regular commuting behavior. Persistence enables multi-day strategies that are unattainable in single-day formulations, such as over-charging on low-demand days to support discharging during future high-demand periods. Real-time decision making in this CPS setting presents three key challenges: (i) uncertainty in long-term EV behavior and building load forecasts, which causes traditional control and heuristic methods to degrade under stochastic conditions; (ii) inter-day coupling of decisions and rewards, where early actions affect downstream feasible charging and discharging opportunities, complicating long-horizon optimization; and (iii) high-dimensional continuous action spaces, which exacerbate the curse of dimensionality in reinforcement learning (RL) and search-based approaches. To address these challenges, we propose a neuro-symbolic framework that integrates a constraint-based Monte Carlo Model Predictive Control (MC-MPC) layer with a learned Value Function (VF). The MC–MPC enforces physical feasibility and manages environmental uncertainty, while the VF provides long-term strategic foresight. Evaluations using real building and EV fleet data from an EV manufacturer in California demonstrate that the hybrid framework substantially outperforms state-of-the-art baselines, significantly reducing demand charge and total energy costs, while ensuring feasibility and full compliance with user charging requirements.
@inproceedings{sen2026negotiations,
author = {Sen, Rishav and Liu, Fangqi and Talusan, Jose Paolo and Pettet, Ava and Suzue, Yoshinori and Bailey, Mark and Mukhopadhyay, Ayan and Dubey, Abhishek},
title = {CONSENT: A Negotiation Framework for Leveraging User Flexibility in Vehicle-to-Building Charging under Uncertainty},
booktitle = {Proceedings of the 24th Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2026)},
year = {2026},
note = {Acceptance rate: 25\%},
location = {Paphos, Cyprus},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
series = {AAMAS '26},
keywords = {vehicle-to-building, energy management, negotiation, demand response, incentive design, semi-Markov decision processes, user flexibility},
what = {CONSENT is a negotiation framework that enables coordination between EV owners and smart buildings under uncertainty in vehicle-to-building charging systems. The work formulates the V2B charging problem as a semi-Markov decision process with negotiation between buildings and users. The system offers personalized charging options based on user flexibility constraints, building energy efficiency goals, and uncertainty in EV arrival patterns, allowing users to express preferences through bounded SoC and departure time adjustments while buildings optimize charging schedules.},
why = {Vehicle-to-building energy coordination creates a fundamental conflict: buildings want to minimize peak demand costs while users want convenient, low-cost charging. Existing approaches either assume full system control or fail to capture real-world incentive-based coordination where users voluntarily participate. CONSENT is innovative because it explicitly bridges technical control with behavioral negotiation, using formal constraint handling and incentive design to enable mutually beneficial cooperation without requiring users to fully comply with building preferences.},
results = {Simulation and user study evaluation demonstrates that CONSENT generates mutually beneficial outcomes: buildings achieve 23% cost reductions compared to baseline approaches while users maintain satisfaction with their charging requirements through negotiated flexibility options. The framework proves effective at aligning disparate objectives through structured negotiation, significantly reducing operational costs while ensuring user voluntary participation.},
project_tags = {energy, CPS, planning}
}
The growth of Electric Vehicles (EVs) creates a conflict in vehicle-to-building (V2B) settings between building operators, who face high energy costs from uncoordinated charging, and drivers, who prioritize convenience and a full charge. To resolve this, we propose a negotiation-based framework that, by design, guarantees voluntary participation, strategy-proofness, and budget feasibility. It transforms EV charging into a strategic resource by offering drivers a range of incentive-backed options for modest flexibility in their departure time or requested state of charge (SoC). Our framework is calibrated with user survey data and validated using real operational data from a commercial building and an EV manufacturer. Simulations show that our negotiation protocol creates a mutually beneficial outcome: lowering the building operator’s costs by over 3.5% compared to an optimized, non-negotiating smart charging policy, while simultaneously reducing user charging expenses by 22% below the utility’s retail energy rate. By aligning operator and EV user objectives, our framework provides a strategic bridge between energy and mobility systems, transforming EV charging from a source of operational friction into a platform for collaboration and shared savings.
@inproceedings{sen2025iccps,
author = {Sen, Rishav and Zhang, Yunuo and Liu, Fangqi and Talusan, Jose Paolo and Pettet, Ava and Suzue, Yoshinori and Mukhopadhyay, Ayan and Dubey, Abhishek},
booktitle = {Proceedings of the ACM/IEEE 16th International Conference on Cyber-Physical Systems (ICCPS)},
title = {Online Decision-Making Under Uncertainty for Vehicle-to-Building Systems},
year = {2025},
address = {New York, NY, USA},
publisher = {Association for Computing Machinery},
series = {ICCPS '25},
acceptance = {28.4},
category = {selective},
contribution = {lead},
location = {California, USA},
numpages = {10},
ranking = {rank1},
what = {This work formulates and solves the vehicle-to-building charging problem as a Markov decision process, emphasizing the challenge of real-time decision-making under uncertainty. The research models the problem using online MCTS-based approaches to handle dynamic electricity pricing, heterogeneous EV chargers, and stochastic EV arrivals. The work integrates domain-knowledge guided exploration with Monte Carlo tree search to enable efficient decision-making that balances immediate operational constraints with long-term energy cost minimization.},
why = {Vehicle-to-building systems present a unique control challenge where centralized optimization traditionally assumes full system knowledge, yet real deployment requires online decision-making under uncertainty in EV arrivals, pricing, and building loads. This work is innovative because it explicitly models the online decision-making nature of V2B coordination, demonstrating how MCTS-based planning can provide near-optimal decisions in high-dimensional, uncertain environments without requiring expensive offline computation.},
results = {Evaluation using real EV data and building information demonstrates that the online MCTS approach achieves significant improvements in total electricity costs while meeting all user charging requirements. The framework shows that principled online decision-making substantially outperforms greedy heuristics and provides better real-world applicability than offline optimization.},
keywords = {vehicle-to-building, EV charging, online optimization, Monte Carlo tree search, stochastic decision-making, demand charge management},
project_tags = {energy, CPS, planning}
}
Vehicle-to-building (V2B) systems combine physical infrastructure such as smart buildings and electric vehicles (EVs) connected to chargers at the building, with digital control mechanisms to manage energy use. By utilizing EVs as flexible energy reservoirs, buildings can dynamically charge and discharge EVs to effectively manage energy usage, and reduce costs under time-variable pricing and demand charge policies. This setup leads to the V2B optimization problem, where buildings coordinate EV charging and discharging to minimize total electricity costs while meeting users’ charging requirements. However, the V2B optimization problem is difficult due to: 1) fluctuating electricity pricing, which includes both energy charges (/kWh) and demand charges (/kW); 2) long planning horizons (usually over 30 days); 3) heterogeneous chargers with differing charging rates, controllability, and directionality (unidirectional or bidirectional); and 4) user-specific battery levels at departure to ensure user requirements are met. While existing approaches often model this setting as a single-shot combinatorial optimization problem, we highlight critical limitations in prior work and instead model the V2B optimization problem as a Markov decision process, i.e., a stochastic control process. Solving the resulting MDP is challenging due to the large state and action spaces. To address the challenges of the large state space, we leverage online search, and we counter the action space by using domain-specific heuristics to prune unpromising actions. We validate our approach in collaboration with an EV manufacturer and a smart building operator in California, United States, showing that the proposed framework significantly outperforms state-of-the-art methods.
@inproceedings{liu2024reinforcement,
author = {Liu, Fangqi and Sen, Rishav and Talusan, Jose and Pettet, Ava and Kandel, Aaron and Suzue, Yoshinori and Mukhopadhyay, Ayan and Dubey, Abhishek},
booktitle = {Proceedings of the 23rd Conference on Autonomous Agents and MultiAgent Systems, {AAMAS} 2025, Detroit, Michigan},
title = {Reinforcement Learning-based Approach for Vehicle-to-Building Charging with Heterogeneous Agents and Long Term Rewards},
year = {2025},
address = {Richland, SC},
note = {nominated for best paper},
organization = {International Conference on Autonomous Agents and Multi-Agent Systems},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
series = {AAMAS '25},
acceptance = {24.5},
category = {selective},
contribution = {lead},
location = {Detroit, Michigan},
what = {This work proposes a reinforcement learning-based approach for vehicle-to-building charging that combines Deep Deterministic Policy Gradient with action masking and policy guidance. The framework models V2B as a Markov decision process with continuous action spaces and constraints, using action masking to ensure feasibility and policy guidance to improve learning efficiency. The approach incorporates domain-specific knowledge about charging physics, building loads, and grid constraints while maintaining flexibility to adapt to new operational scenarios.},
why = {Vehicle-to-building energy management presents a high-dimensional, continuous control problem under uncertainty where traditional optimization methods struggle with real-time responsiveness and scalability. This work is innovative because it combines modern deep reinforcement learning with domain-specific constraints and knowledge, enabling scalable learning of near-optimal charging policies that naturally adapt to building dynamics and user behavior without requiring explicit model calibration.},
results = {Evaluation on real EV fleet data from a major manufacturer demonstrates significant cost savings while meeting all user charging requirements and grid constraints. The learned policies achieve substantial improvements in demand charge reduction and total operating costs compared to both heuristic baselines and model-predictive control approaches.},
keywords = {electric vehicle charging, reinforcement learning, deep deterministic policy gradient, building energy management, demand response, stochastic control},
project_tags = {energy, planning, ML for CPS}
}
Strategic aggregation of electric vehicle batteries as energy reservoirs can optimize power grid demand, benefiting smart and connected communities, especially large office buildings that offer workplace charging. This involves optimizing charging and discharging to reduce peak energy costs and net peak demand, monitored over extended periods (e.g., a month), which involves making sequential decisions under uncertainty and delayed and sparse rewards, a continuous action space, and the complexity of ensuring generalization across diverse conditions. Existing algorithmic approaches, e.g., heuristic-based strategies, fall short in addressing real-time decision-making under dynamic conditions, and traditional reinforcement learning (RL) models struggle with large stateaction spaces, multi-agent settings, and the need for long-term reward optimization. To address these challenges, we introduce a novel RL framework that combines the Deep Deterministic Policy Gradient approach (DDPG) with action masking and efficient MILP-driven policy guidance. Our approach balances the exploration of continuous action spaces to meet user charging demands. Using real-world data from a major electric vehicle manufacturer, we show that our approach comprehensively outperforms many well-established baselines and several scalable heuristic approaches, achieving significant cost savings while meeting all charging requirements. Our results show that the proposed approach is one of the first scalable and general approaches to solving the V2B energy management challenge.
@inproceedings{talusan2024smartcomp,
author = {Talusan, Jose Paolo and Sen, Rishav and Ava Pettet, Aaron Kandel and Suzue, Yoshinori and Pedersen, Liam and Mukhopadhyay, Ayan and Dubey, Abhishek},
booktitle = {2024 IEEE International Conference on Smart Computing (SMARTCOMP)},
title = {OPTIMUS: Discrete Event Simulator for Vehicle-to-Building Charging Optimization},
year = {2024},
month = jun,
acceptance = {32.9},
contribution = {lead},
what = {OPTIMUS is a discrete event simulator for vehicle-to-building charging optimization that combines real-world EV data with flexible policy evaluation. The platform integrates generative models for EV arrivals, building loads, and demand charges with configurable optimization algorithms including greedy heuristics, mixed-integer linear programming, and reinforcement learning. OPTIMUS enables building owners and EV manufacturers to test charging policies under diverse scenarios while accounting for realistic uncertainty in EV arrivals and building operations.},
why = {Deploying V2B charging systems requires understanding how different control policies perform under real-world conditions with diverse uncertainties, yet existing tools either focus on specific optimization techniques or lack the flexibility to accommodate varied operational scenarios. OPTIMUS is innovative because it provides a comprehensive, modular simulation platform that enables practical policy development and evaluation by combining real-world data streams with configurable solution algorithms.},
results = {The platform enables evaluation of diverse V2B charging policies on real building and EV data, supporting policy development through extensive scenario analysis. Results demonstrate the ability to predict policy performance under various conditions including different arrival patterns, building loads, and grid events.},
keywords = {vehicle-to-building, EV charging, discrete event simulation, policy evaluation, optimization, charging management},
project_tags = {energy, CPS, planning}
}
The increasing popularity of electronic vehicles has spurred a demand for EV charging infrastructure. In the United States alone, over 160,000 public and private charging ports have been installed. This has stoked fear of potential grid issues in the future. Meanwhile, companies, specifically building owners are also seeing the opportunity to leverage EV batteries as energy stores to serve as buffers against the electric grid. The main idea is to influence and control charging behavior to provide a certain level of energy resiliency and demand responsiveness to the building from grid events while ensuring that they meet the demands of EV users. However, managing and co-optimizing energy requirements of EVs and cost-saving measures of building owners is a difficult task. First, user behavior and grid uncertainty contribute greatly to the potential effectiveness of different policies. Second, different charger configurations can have drastically different effects on the cost. Therefore, we propose a complete end-to-end discrete event simulator for vehicle-to-building charging optimization. This software is aimed at building owners and EV manufacturers such as Nissan, looking to deploy their charging stations with state-of-the-art optimization algorithms. We provide a complete solution that allows the owners to train, evaluate, introduce uncertainty, and benchmark policies on their datasets. Lastly, we discuss the potential for extending our work with other vehicle-to-grid deployments.
@article{proactivewildfire,
author = {Kadir, Salah Uddin and Majumder, Subir and Srivastava, Anurag K. and Chhokra, Ajay Dev and Neema, Himanshu and Dubey, Abhishek and Laszka, Aron},
journal = {IEEE Transactions on Industrial Informatics},
title = {Reinforcement-Learning-Based Proactive Control for Enabling Power Grid Resilience to Wildfire},
year = {2024},
issn = {1941-0050},
month = jan,
number = {1},
pages = {795-805},
volume = {20},
contribution = {colab},
doi = {10.1109/TII.2023.3263500},
keywords = {power grid resilience, reinforcement learning, wildfire propagation, proactive control, critical infrastructure, machine learning, emergency response, optimization},
what = {This work develops a reinforcement learning-based proactive control approach for power grid resilience during wildfire events. The researchers model the power system and wildfire propagation using a detailed integrated testbed that captures both the spatial dynamics of fire spread across a geographical grid and the operational constraints of the power network. A deep reinforcement learning agent is trained to make real-time decisions about generator control and load management during extreme weather events, coordinating with multiple microgrids and transmission systems to minimize load shedding and outages.},
why = {Traditional power system operations rely on myopic load dispatch and post-event remedial actions, which are insufficient for managing cascading failures during wildfires. This work is innovative because it combines machine learning with physics-based wildfire propagation models to enable proactive, anticipatory decision-making. Rather than reacting after failures occur, the approach allows operators to preemptively adjust power flows and resources, representing a significant advance in how autonomous systems can handle extreme events in critical infrastructure.},
results = {The proposed approach successfully reduces power loss through increased power flow rerouting during wildfire events compared to baseline myopic control policies. The integrated testbed demonstrates that the RL-based controller can provide decision support to operators while maintaining computational tractability. Testing on a realistic IEEE power system mapped to geographical terrain shows that proactive control achieves substantial improvements in reducing load outages and providing resilience, with the ability to be deployed in real-time alongside human operators.},
project_tags = {energy, emergency, scalable AI, CPS, ML for CPS}
}
Industrial electric power grid operation subject to an extreme event requires decision making by human operators under stressful conditions. Decision making using system data informatics under adverse dynamic events, especially if forecasted, should be supplemented by intelligent proactive control. Power transmission system operation during wildfires requires resiliency-driven proactive control for load shedding, line switching, and resource allocation considering the dynamics of the wildfire and failure propagation to minimize the impact on the system. However, the possible number of line and load switching in an extensive industrial system during an event make the traditional prediction-driven and stochastic approaches computationally intractable, leading operators to often use preplanned or greedy algorithms. In this article, we model and solve the proactive control problem as a Markov decision process (MDP) and introduce an integrated testbed for spatiotemporal wildfire propagation and proactive power-system operation. Our approach allows the controller to provide setpoints for all generation fleets in the power grid. We evaluate our approach utilizing the IEEE test system mapped onto a hypothetical terrain. Our results show that the proposed approach can help the operator to reduce load outage during an extreme event. It reduces power flow through lines that are to be de-energized and adjusts the load demand by increasing power flow through other lines.
@article{eisele2020Safe,
author = {Eisele, Scott and Eghtesad, Taha and Campanelli, Keegan and Agrawal, Prakhar and Laszka, Aron and Dubey, Abhishek},
journal = {ACM Trans. Cyber-Phys. Syst.},
title = {Safe and Private Forward-Trading Platform for Transactive Microgrids},
year = {2021},
issn = {2378-962X},
month = jan,
number = {1},
volume = {5},
address = {New York, NY, USA},
articleno = {8},
contribution = {lead},
doi = {10.1145/3403711},
issue_date = {January 2021},
keywords = {blockchain, distributed energy, transactive energy, privacy, smart contracts, microgrids},
numpages = {29},
publisher = {Association for Computing Machinery},
tag = {decentralization, power},
url = {https://doi.org/10.1145/3403711},
what = {This paper introduces TRANSAX, a blockchain-based decentralized energy trading platform for transactive microgrids that simultaneously addresses efficiency, safety, and privacy requirements. The system uses smart contracts for transparent trading while employing cryptographic mixing protocols for anonymization. The architecture leverages distributed ledgers and resilient information architecture to enable peer-to-peer energy trading.},
why = {Decentralized energy trading in microgrids offers significant efficiency benefits but must simultaneously satisfy conflicting requirements for efficiency, safety, and privacy. This work is innovative because it demonstrates how blockchain and cryptographic techniques can be combined to achieve all three properties without requiring a centralized authority. The approach enables local energy trading while preventing exploitation of trading activity.},
results = {The TRANSAX platform was evaluated through testbed experiments and demonstrated feasibility of private blockchain-based energy trading. The system successfully maintained energy safety constraints while preserving privacy of trading activities. The hybrid solver architecture proved effective for solving complex energy allocation problems while distributing computation across resilient ledger nodes.},
project_tags = {energy, middleware, CPS}
}
Transactive microgrids have emerged as a transformative solution for the problems faced by distribution system operators due to an increase in the use of distributed energy resources and rapid growth in renewable energy generation. Transactive microgrids are tightly coupled cyber and physical systems, which require resilient and robust financial markets where transactions can be submitted and cleared, while ensuring that erroneous or malicious transactions cannot destabilize the grid. In this paper, we introduce TRANSAX, a novel decentralized platform for transactive microgrids. TRANSAX enables participants to trade in an energy futures market, which improves efficiency by finding feasible matches for energy trades, reducing the load on the distribution system operator. TRANSAX provides privacy to participants by anonymizing their trading activity using a distributed mixing service, while also enforcing constraints that limit trading activity based on safety requirements, such as keeping power flow below line capacity. We show that TRANSAX can satisfy the seemingly conflicting requirements of efficiency, safety, and privacy, and we demonstrate its performance using simulation results.
@inproceedings{Laszka2018,
author = {Laszka, Aron and Eisele, Scott and Dubey, Abhishek and Karsai, Gabor and Kvaternik, Karla},
booktitle = {24th {IEEE} International Conference on Parallel and Distributed Systems, {ICPADS} 2018, Singapore, December 11-13, 2018},
title = {{TRANSAX:} {A} Blockchain-Based Decentralized Forward-Trading Energy Exchanged for Transactive Microgrids},
year = {2018},
pages = {918--927},
acceptance = {37.7},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/icpads/LaszkaEDKK18},
category = {selectiveconference},
contribution = {lead},
doi = {10.1109/PADSW.2018.8645001},
file = {:Laszka2018-TRANSAX_A_Blockchain-Based_Decentralized_Forward-Trading_Energy_Exchanged_for_Transactive_Microgrids.pdf:PDF},
keywords = {transactive energy, blockchain, smart contracts, energy trading, microgrids},
project = {transactive-energy,cps-blockchains},
tag = {decentralization,power},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
url = {https://doi.org/10.1109/PADSW.2018.8645001},
what = {This paper presents TRANSAX, a blockchain-based decentralized energy trading platform for transactive microgrids that addresses three key challenges: privacy protection through encrypted transactions, resilience through distributed ledgers, and efficient resource allocation using smart contracts and linear programming. The system enables individual prosumers to autonomously trade energy with neighbors while maintaining system safety constraints and grid stability.},
why = {Transactive energy systems require mechanisms for distributed market participants to coordinate energy production and consumption without centralized control, but face challenges with privacy, reliability, and fair resource allocation. TRANSAX is innovative because it combines blockchain-based distributed ledgers for trust and transparency with optimization algorithms for efficient matching, enabling scalable transactive energy markets suitable for microgrids.},
results = {TRANSAX successfully enabled forward energy trading among distributed participants with multiple time horizons and flexible resource constraints. The platform maintained system stability by enforcing feeder capacity constraints while maximizing total energy traded. Smart contracts verified transaction feasibility before blockchain execution, and the hybrid solver architecture solved large-scale resource allocation problems efficiently.},
project_tags = {energy, planning}
}
Power grids are undergoing major changes due to rapid growth in renewable energy and improvements in battery technology. Prompted by the increasing complexity of power systems, decentralized IoT solutions are emerging, which arrange local communities into transactive microgrids. The core functionality of these solutions is to provide mechanisms for matching producers with consumers while ensuring system safety. However, there are multiple challenges that these solutions still face: privacy, trust, and resilience. The privacy challenge arises because the time series of production and consumption data for each participant is sensitive and may be used to infer personal information. Trust is an issue because a producer or consumer can renege on the promised energy transfer. Providing resilience is challenging due to the possibility of failures in the infrastructure that is required to support these market based solutions. In this paper, we develop a rigorous solution for transactive microgrids that addresses all three challenges by providing an innovative combination of MILP solvers, smart contracts, and publish-subscribe middleware within a framework of a novel distributed application platform, called Resilient Information Architecture Platform for Smart Grid. Towards this purpose, we describe the key architectural concepts, including fault tolerance, and show the trade-off between market efficiency and resource requirements.
@inproceedings{eisele2020mechanisms,
author = {Eisele, Scott and Eghtesad, Taha and Troutman, Nicholas and Laszka, Aron and Dubey, Abhishek},
booktitle = {14TH ACM International Conference on Distributed and Event Based Systems},
title = {Mechanisms for Outsourcing Computation via a Decentralized Market},
year = {2020},
acceptance = {25.5},
category = {selectiveconference},
contribution = {lead},
keywords = {blockchain, decentralized computation, smart contracts, job scheduling, distributed ledger, computation verification},
tag = {platform,decentralization},
what = {This paper introduces MODiCUM, a blockchain-based distributed ledger system for outsourcing computation with mechanisms to address misbehavior and verify results. The work presents a smart contract-based protocol for job outsourcing that enables verification of computation correctness while keeping verification costs low. The system addresses challenges in decentralized computation by implementing dispute resolution mechanisms and ensuring that resource providers receive payment only for correct results.},
why = {Outsourcing computation to distributed resources could enable efficient use of idle computing capacity, but requires mechanisms to verify that results are correct without trusting individual participants. Traditional centralized approaches suffer from single points of failure and may not capture all available computing resources. This work is innovative because it provides a decentralized approach to computation outsourcing using blockchain smart contracts, enabling trustless verification and fair compensation while maintaining computational efficiency.},
results = {MODiCUM successfully demonstrates a working decentralized computation marketplace where jobs are posted, matched with resource providers, and results are verified using smart contracts. The system enables efficient verification through random sampling of results and maintains fairness through mechanisms that prevent collusion. Results show that the approach can support computation outsourcing with reasonable efficiency while ensuring that dishonest participants face consequences.},
project_tags = {middleware, CPS}
}
As the number of personal computing and IoT devices grows rapidly, so does the amount of computational power that is available at the edge. Since many of these devices are often idle, there is a vast amount of computational power that is currently untapped, and which could be used for outsourcing computation. Existing solutions for harnessing this power, such as volunteer computing (e.g., BOINC), are centralized platforms in which a single organization or company can control participation and pricing. By contrast, an open market of computational resources, where resource owners and resource users trade directly with each other, could lead to greater participation and more competitive pricing. To provide an open market, we introduce MODiCuM, a decentralized system for outsourcing computation. MODiCuM deters participants from misbehaving-which is a key problem in decentralized systems-by resolving disputes via dedicated mediators and by imposing enforceable fines. However, unlike other decentralized outsourcing solutions, MODiCuM minimizes computational overhead since it does not require global trust in mediation results. We provide analytical results proving that MODiCuM can deter misbehavior, and we evaluate the overhead of MODiCuM using experimental results based on an implementation of our platform.
@article{Hasan2020,
author = {Hasan, Saqib and Dubey, Abhishek and Karsai, Gabor and Koutsoukos, Xenofon},
journal = {International Journal of Electrical Power \& Energy Systems},
title = {A game-theoretic approach for power systems defense against dynamic cyber-attacks},
year = {2020},
issn = {0142-0615},
volume = {115},
contribution = {colab},
doi = {https://doi.org/10.1016/j.ijepes.2019.105432},
file = {:Hasan2020-A_Game_Theoretic_Approach_for_Power_Systems_Defense_against_Dynamic_Cyber_Attacks.pdf:PDF},
keywords = {power systems, cybersecurity, game theory, dynamic attacks, resilience, critical infrastructure protection},
project = {cps-reliability},
tag = {platform,power},
url = {http://www.sciencedirect.com/science/article/pii/S0142061519302807},
what = {This paper presents a game-theoretic approach for power system defense against dynamic cyber-attacks where attackers can target multiple substations at different times. The work develops both static and dynamic attack models and provides efficient algorithms for identifying worst-case attacks and optimal defense strategies. The methodology uses game theory to model the interaction between attackers and defenders, enabling strategic identification of critical substations to protect.},
why = {Power systems face emerging threats from dynamic cyber-attacks that can target multiple components at different times to maximize damage while remaining within resource constraints. Static defense approaches are insufficient for protecting against strategically sequenced attacks. This work is innovative because it applies game-theoretic analysis to power system cybersecurity, enabling defenders to anticipate worst-case attack scenarios and identify optimal protection strategies that minimize overall system damage.},
results = {The game-theoretic analysis identifies worst-case dynamic attacks and optimal defense strategies for IEEE test systems. Results show that dynamic attacks can cause greater damage than static attacks through strategic timing and component selection. The work provides algorithms for defenders to identify critical substations to protect based on attack budget constraints, enabling more strategic allocation of limited security resources.},
project_tags = {energy, CPS, planning}
}
Technological advancements in today’s electrical grids give rise to new vulnerabilities and increase the potential attack surface for cyber-attacks that can severely affect the resilience of the grid. Cyber-attacks are increasing both in number as well as sophistication and these attacks can be strategically organized in chronological order (dynamic attacks), where they can be instantiated at different time instants. The chronological order of attacks enables us to uncover those attack combinations that can cause severe system damage but this concept remained unexplored due to the lack of dynamic attack models. Motivated by the idea, we consider a game-theoretic approach to design a new attacker-defender model for power systems. Here, the attacker can strategically identify the chronological order in which the critical substations and their protection assemblies can be attacked in order to maximize the overall system damage. However, the defender can intelligently identify the critical substations to protect such that the system damage can be minimized. We apply the developed algorithms to the IEEE-39 and 57 bus systems with finite attacker/defender budgets. Our results show the effectiveness of these models in improving the system resilience under dynamic attacks.
@inproceedings{ajay2021powerattack,
author = {Chhokra, Ajay and Barreto, Carlos and Dubey, Abhishek and Karsai, Gabor and Koutsoukos, Xenofon},
booktitle = {9th Workshop on Modeling and Simulation of Cyber-Physical Energy Systems, MSCPES@CPSIoTWeek},
title = {Power-Attack: A comprehensive tool-chain for modeling and simulating attacks in power systems},
year = {2021},
category = {workshop},
contribution = {colab},
keywords = {power systems, cyber security, attack simulation, domain-specific language, protection systems},
project = {cps-reliability},
tag = {platform,power},
what = {This paper presents Power-Attack, a comprehensive tool-chain for modeling and simulating cyber attacks in power systems. The system includes a domain-specific language for defining attack scenarios and a scalable simulation engine that models both physical layer dynamics and protection system components. The framework enables evaluation of protection relay responses and overall system behavior under various attack conditions.},
why = {As power systems become increasingly vulnerable to cyber attacks, developing tools for attack simulation and mitigation analysis is critical for system security. This work is innovative because it provides an integrated tool-chain combining high-level domain-specific languages with detailed physical layer simulation. The approach enables security analysts to quickly specify complex attack scenarios and evaluate system responses.},
results = {The Power-Attack framework was evaluated on IEEE 39 bus systems and demonstrated effectiveness in simulating various cyber attack scenarios. The tool-chain successfully modeled both device attacks and data attacks on protection systems. The simulation results demonstrated how different attacks affect frequency stability and identified specific vulnerabilities in protection system configurations.},
project_tags = {CPS, emergency, Explainable AI}
}
Due to the increased deployment of novel communication, control and protection functions, the grid has become vulnerable to a variety of attacks. Designing robust machine learning based attack detection and mitigation algorithms require large amounts of data that rely heavily on a representative environment, where different attacks can be simulated. This paper presents a comprehensive tool-chain for modeling and simulating attacks in power systems. The paper makes the following contributions, first, we present a probabilistic domain specific language to define multiple attack scenarios and simulation configuration parameters. Secondly, we extend the PyPower-dynamics simulator with protection system components to simulate cyber attacks in control and protection layers of power system. In the end, we demonstrate multiple attack scenarios with a case study based on IEEE 39 bus system.
@article{Chhokra2018a,
author = {Chhokra, Ajay and Dubey, Abhishek and Mahadevan, Nagabhushan and Karsai, Gabor and Balasubramanian, Daniel and Hasan, Saqib},
journal = {International Journal of Prognostics and Health Management},
title = {Hierarchical Reasoning about Faults in Cyber-Physical Energy Systems using Temporal Causal Diagrams},
year = {2018},
month = feb,
number = {1},
volume = {9},
attachments = {https://www.isis.vanderbilt.edu/sites/default/files/ijphm_18_001_0.pdf},
contribution = {colab},
file = {:Chhokra2018a-Hierarchical_Reasoning_about_Faults_in_Cyber-Physical_Energy_Systems_using_Temporal_Causal_Diagrams.pdf:PDF},
keywords = {fault diagnosis, temporal causal diagrams, power systems, fault propagation, cyber-physical systems},
tag = {platform,power},
type = {Journal Article},
url = {https://www.phmsociety.org/node/2290},
what = {This paper presents hierarchical reasoning about faults in cyber-physical energy systems using Temporal Causal Diagrams that augment failure models with discrete and continuous dynamics. The approach models fault propagation across physical and cyber components by tracking how anomalies detected by protection devices lead to state changes and behavioral effects. The system uses local observers and a reasoning engine to generate system-level hypotheses explaining observed anomalies without requiring global perspective.},
why = {Cyber-physical systems like power grids present complex fault scenarios where failures in one component cascade through the system via protection device interactions. Traditional fault diagnosis approaches fail because they ignore how protection devices themselves can cause secondary failures. This work is innovative because it models fault propagation as behavioral changes in cyber-physical components, enabling diagnosis systems to explain cascading failures and identify root causes.},
results = {The approach successfully diagnosed cascading failures in power systems by tracking fault propagation through protection devices and actuators. Temporal Causal Diagram models accurately predicted failure modes and discrepancies under various system conditions. The reasoning engine generated correct system-level hypotheses consistent with observed anomalies without missing any dangerous contingencies.},
project_tags = {CPS, Explainable AI}
}
The resiliency and reliability of critical cyber physical systems like electrical power grids are of paramount importance. These systems are often equipped with specialized protection devices to detect anomalies and isolate faults in order to arrest failure propagation and protect the healthy parts of the system. However, due to the limited situational awareness and hidden failures the protection devices themselves, through their operation (or mis-operation) may cause overloading and the disconnection of parts of an otherwise healthy system. This can result in cascading failures that lead to a blackout. Diagnosis of failures in such systems is extremely challenging because of the need to account for faults in both the physical systems as well as the protection devices, and the failure-effect propagation across the system. Our approach for diagnosing such cyber-physical systems is based on the concept of Temporal Causal Diagrams (TCD-s) that capture the timed discrete models of protection devices and their interactions with a system failure propagation graph. In this paper we present a refinement of the TCD language with a layer of independent local observers that aid in diagnosis. We describe a hierarchical two-tier failure diagnosis approach and showcase the results for 4 different scenarios involving both cyber and physical faults in a standard Western System Coordinating Council (WSCC) 9 bus system.
@article{GHOSH2020101759,
author = {Ghosh, Purboday and Eisele, Scott and Dubey, Abhishek and Metelko, Mary and Madari, Istvan and Volgyesi, Peter and Karsai, Gabor},
journal = {Journal of Systems Architecture},
title = {Designing a decentralized fault-tolerant software framework for smart grids and its applications},
year = {2020},
issn = {1383-7621},
pages = {101759},
volume = {109},
contribution = {minor},
doi = {https://doi.org/10.1016/j.sysarc.2020.101759},
keywords = {Component, Fault tolerance, Distributed systems, Smart grid},
tag = {platform},
url = {http://www.sciencedirect.com/science/article/pii/S1383762120300539}
}
The vision of the ‘Smart Grid’ anticipates a distributed real-time embedded system that implements various monitoring and control functions. As the reliability of the power grid is critical to modern society, the software supporting the grid must support fault tolerance and resilience of the resulting cyber-physical system. This paper describes the fault-tolerance features of a software framework called Resilient Information Architecture Platform for Smart Grid (RIAPS). The framework supports various mechanisms for fault detection and mitigation and works in concert with the applications that implement the grid-specific functions. The paper discusses the design philosophy for and the implementation of the fault tolerance features and presents an application example to show how it can be used to build highly resilient systems.
@inproceedings{iccps2026_wenflow,
author = {Buckelew, Jacob and Talusan, Jose Paolo and Sivaramakrishnan, Vasavi and Mukhopadhyay, Ayan and Srivastava, Anurag and Dubey, Abhishek},
title = {WENFlow: Wavelet-Enhanced Normalizing Flows for Real-Time Anomaly Detection in CPS},
year = {2026},
booktitle = {Proceedings of the HSCC/ICCPS 2026: 29th ACM International Conference on Hybrid Systems: Computation and Control and 17th ACM/IEEE International Conference on Cyber-Physical Systems},
location = {Saint Malo, France},
keywords = {anomaly detection, cyber-physical systems, wavelet transforms, normalizing flows, spatiotemporal analysis, unsupervised learning, interpretability},
note = {Acceptance rate: 28\%; Regular Paper; Track: Foundations},
series = {HSCC/ICCPS '26},
what = {WENFlow proposes a wavelet-enabled normalizing flow framework for unsupervised anomaly detection in high-dimensional cyber-physical systems. The work addresses the challenge of detecting subtle anomalies in systems like power grids and water networks that exhibit complex spatiotemporal patterns. WENFlow combines discrete wavelet transform for multi-scale temporal feature extraction with gated selective self-attention to identify critical sensors, conditional density estimation for likelihood-based anomaly scoring, and interpretable analysis through log-density and feature importance.},
why = {Real-time anomaly detection in complex infrastructure systems requires capturing both slow operational trends and fast localized disruptions, with scalable robustness to contaminated training data and high dimensionality. Existing methods struggle with spatiotemporal dependencies and contamination from unlogged maintenance events. WENFlow is innovative because it achieves linear complexity scaling with sensor dimensionality through wavelet decomposition and feature-wise attention, providing both accurate anomaly detection and interpretable explanations of which sensors and temporal patterns indicate anomalies.},
results = {Extensive evaluation on power grid and water treatment benchmarks demonstrates WENFlow achieves superior anomaly detection performance compared to state-of-the-art methods including transformers and density-based approaches, while maintaining linear scaling with system dimensionality and robustness to contaminated training data. The framework provides interpretable analysis through feature importance scores and temporal pattern visualization.},
project_tags = {CPS, ML for CPS, Explainable AI}
}
Real-time anomaly detection in high-dimensional data is crucial for ensuring the security of cyber-physical systems (CPS) such as power grids and water distribution networks. Such data commonly take the form of multivariate time series, often unlabeled and necessitating the need for unsupervised detection methods. However, many unsupervised deep learning methods make assumptions about the normality of training data, which is unrealistic in real-world CPS where training data often contain anomalies or rare patterns. Furthermore, these methods rely on inefficient mechanisms to learn spatiotemporal dependencies in the data and scale quadratically with the number of system features. To address these problems, we propose Wavelet-Enhanced Normalizing Flows (WENFlow), an unsupervised deep learning model that identifies anomalies in low-density regions of the data distribution and does not assume access to anomaly-free training data. Notably, WENFlow leverages a scalable Gated Selective Self-Attention mechanism for capturing the most critical spatial dependencies between features. Compared to existing models, WENFlow scales linearly with respect to the number of system features and meets real-time inference requirements for anomaly detection. In our experiments, WENFlow achieves superior AUC scores against baseline methods across datasets with varying anomaly ratios, showcasing its robustness against contaminated training data. We evaluate WENFlow on 2 real-world benchmark datasets and a simulated phasor measurement unit dataset collected from a power grid testbed.
@inproceedings{rishav2022eEnergy,
author = {Sen, Rishav and Bharati, Alok Kumar and Khaleghian, Seyedmehdi and Ghosal, Malini and Wilbur, Michael and Tran, Toan and Pugliese, Philip and Sartipi, Mina and Neema, Himanshu and Dubey, Abhishek},
booktitle = {Proceedings of the Thirteenth ACM International Conference on Future Energy Systems},
title = {E-Transit-Bench: Simulation Platform for Analyzing Electric Public Transit Bus Fleet Operations},
year = {2022},
address = {New York, NY, USA},
pages = {532–541},
publisher = {Association for Computing Machinery},
series = {e-Energy '22},
contribution = {lead},
doi = {10.1145/3538637.3539586},
isbn = {9781450393973},
keywords = {electric vehicles, power grid, transit simulation, charging optimization, grid impact analysis},
location = {Virtual Event},
numpages = {10},
url = {https://doi.org/10.1145/3538637.3539586},
what = {This paper presents E-TRANSIT-BENCH, a simulation platform for analyzing the impact of electric vehicle charging on power grid operations in public transit systems. The framework integrates transit simulation with power grid modeling using SUMO and GridLAB-D co-simulation. The system enables detailed analysis of how bus electrification affects grid stability, load distribution, and charging infrastructure requirements.},
why = {As public transit agencies transition to electric buses, understanding the impact on power infrastructure is critical for cost-effective planning and grid stability. This work is significant because it provides an integrated modeling framework that captures complex interactions between transit operations and grid dynamics. The co-simulation approach enables analysis of various electrification strategies and their grid impacts.},
results = {The simulation platform demonstrated how different charging strategies significantly affect grid load profiles and voltage stability. The analysis identified optimal charging station locations that minimize grid stress while supporting transit schedules. The framework enabled evaluation of various battery capacities, charging rates, and scheduling strategies to inform infrastructure planning decisions.},
project_tags = {energy, transit, CPS}
}
When electrified transit systems make grid aware choices, improved social welfare is achieved by reducing grid stress, reducing system loss, and minimizing power quality issues. Electrifying transit fleet has numerous challenges like non availability of buses during charging, varying charging costs and so on, that are related the electric grid behavior. However, transit systems do not have access to the information about the co-evolution of the grid’s power flow and therefore cannot account for the power grid’s needs in its day-to-day operation. In this paper we propose a framework of transportation-grid co-simulation, analyzing the spatio-temporal interaction between the transit operations with electric buses and the power distribution grid. Real-world data for a day’s traffic from Chattanooga city’s transit system is simulated in SUMO and integrated with a realistic distribution grid simulation (using GridLAB-D) to understand the grid impact due to transit electrification. Charging information is obtained from the transportation simulation to feed into grid simulation to assess the impact of charging. We also discuss the impact to the grid with higher degree of transit electrification that further necessitates such an integrated transportation-grid co-simulation to operate the integrated system optimally. Our future work includes extending the platform for optimizing the charging and trip assignment operations.
@inproceedings{barretocyber2020,
author = {Barreto, Carlos and Eghtesad, Taha and Eisele, Scott and Laszka, Aron and Dubey, Abhishek and Koutsoukos, Xenofon},
booktitle = {3rd IEEE International Conference on IndustrialCyber-Physical Systems (ICPS 2020)},
title = {Cyber-Attacks and Mitigation in Blockchain Based Transactive Energy Systems},
year = {2020},
category = {selectiveconference},
contribution = {colab},
keywords = {blockchain, transactive energy systems, cybersecurity, smart contracts, distributed energy resources, market mechanisms, cyberattacks},
project = {cps-reliability},
tag = {decentralization,power},
what = {This paper addresses cyber-attacks and mitigation strategies in blockchain-based transactive energy systems where distributed energy resources participate in peer-to-peer electricity trading. The work identifies vulnerabilities in blockchain-based market mechanisms and proposes attack scenarios that could disrupt market operations. The analysis considers scenarios where attackers can compromise gateway nodes, delay trading bids, and disrupt the blockchain consensus mechanism.},
why = {Blockchain-based transactive energy systems enable decentralized energy trading but introduce new security vulnerabilities and operational risks. Understanding how attackers could exploit these systems is essential for designing robust mechanisms that maintain market integrity even under adversarial conditions. This work is innovative because it systematically analyzes attack vectors specific to blockchain-based energy markets and demonstrates the importance of considering cybersecurity alongside operational efficiency in decentralized energy systems.},
results = {The analysis identifies critical vulnerabilities in blockchain-based transactive energy systems and demonstrates how delays in trading bids and gateway compromise could affect market equilibrium. Results show that certain attack scenarios can increase generator profits while reducing overall market efficiency. The work highlights the need for additional security mechanisms and careful system design to ensure that blockchain-based energy markets remain robust against cyber threats.},
project_tags = {energy, CPS}
}
Power grids are undergoing major changes due to the rapid adoption of intermittent renewable energy resources and the increased availability of energy storage devices. These trends drive smart-grid operators to envision a future where peer-to-peer energy trading occurs within microgrids, leading to the development of Transactive Energy Systems. Blockchains have garnered significant interest from both academia and industry for their potential application in decentralized TES, in large part due to their high level of resilience. In this paper, we introduce a novel class of attacks against blockchain based TES, which target the gateways that connect market participants to the system. We introduce a general model of blockchain based TES and study multiple threat models and attack strategies. We also demonstrate the impact of these attacks using a testbed based on GridLAB-D and a private Ethereum network. Finally, we study how to mitigate these attack.