About us

scopelab image

We are a research group directed by Prof. Abhishek Dubey at Institute for Software Integrated Systems, Vanderbilt University working on design and operation of Cyber-physical Systems (CPS) with Artificial Intelligence (AI) based components (AI-CPS). Our applications domains include public transit systems, emergency response systems and power grid. For these systems we investigate principled design, operation and optimization methods that not only consider the system operations, but also consider resilience, performance and assurance. Our research is part of the broad research into smart and connected communities (SCC) and Cyber-Physical Systems (CPS). Both of these research areas are being enabled by the rapid and transformational changes driven by innovations in smart sensors, such as cameras and air quality monitors, which are now embedded in almost every physical device and system we use, from watches and smartphones to automobiles, homes, roads, and workplaces. Coupled with emerging new modes of networking, new algorithms for data analytics, and new paradigms of distributed computing like fog computing, these sensors create an “Internet of Things” (IoT) that provide endless opportunities for innovation and improving the quality of life, such as improved transportation with reduced congestion and more efficient use of energy and water. The effect of these innovations can be seen in a number of diverse domains, such as transportation, energy, emergency response, and health care, including the work done by our team in that area.Read more at the National Science Foundation page.

Recent Updates

Research Horizontals

Assurance of CPS with AI components

The motivation for this horizontal focused research area is resilience. In recent years, AI based components are being heavily used in CPS, including in our work. Despite their impressive capability, using them in safety critical applications is challenging because (1) they learn from training data, and subtle changes in the images during testing could cause these components to predict erroneously, (2) testing and verifying these components is complex and sometimes not possible, and (3) safety and assurance case development of systems using these components is complicated. A popular example of such a system is NVIDIA’s DAVE-II car that used an end-to-end learning LEC, which took in a forward facing camera image to predict the steering control action. While such autonomous systems have shown exceptional progress at different levels of autonomous driving, fatal incidents like Tesla’s autopilot crash and Uber self-driving car crash have shown these systems to be fragile and susceptible to operational context shifts (popularly known as OOD), or faults in sensors and actuators. The susceptibility to these faults complicates the safety assurance and certification process, and thus hinders their wide-spread utilization.

Resilient Design and Operation of Complex Cyber-Physical Systems

Cyber-Physical Systems encompass all modern engineered systems, including smart transit, smart emergency response, smart grid. The big issue in these systems is the construction and operation of the system in a safe and efficient manner. There have been many different approaches taken by the research community over the years. The approach of this lab has been to focus on component-based software engineering (CBSE) efforts for these systems. The guiding principles of CBSE are interfaces with well defined execution models, compositional semantics and analysis. However, there are a number of challenges that have to be resolved (a) performance management, (b) modularization and adaptation of the system as the requirements and environment changes and (c) safe and secure design of the system itself and ensuring that new design and component additions can be compositionally analyzed and operated during the life cycle of the system.

Blockchains and Multi Stakeholder systems

One of our fundamental focus of research is the use of Blockchain for decentralization of operation in large scale distributed systems. Examples of this type of system include smart cities, transactive energy, and IoT. The current form of these systems allows large scale stakeholders to participate, for example in the case of power systems bulk energy markets between power plants and power distribution companies, and in the case of IoT the various internet providers make agreements with each other to allow access to each other’s networks. Blockchains are interesting for creating decentralized systems because they enable participants to reach a consensus on any state variable in the system without relying on a trusted third party or trusting each other. Distributed consensus not only solves the trust issue, but also provides fault-tolerance since consensus is always reached on the correct state as long as the number of faulty nodes is below a threshold. Further, blockchains enable performing computation in a distributed and trustworthy manner in the form of smart contracts.

Application Domains

Emergency Response Systems (ERS)

Planning and preparation in anticipation of urban emergency incidents are critical because of the alarming extent of the damage such incidents cause as well as the sheer frequency of their occurrence. Incident response is typically optimized as part of designing ERS pipelines but can have a high variance depending upon the location of the first responders, other incidents in the call chain, the severity of the call, traffic conditions, and weather conditions. Our research on algorithmic approaches to ERS spanning the past six years has developed proactive stationing and principled dispatch strategies to reduce the overall response times. The system depends upon incident data, temporal data (weather and traffic), and static roadway data and has to contend with changes in incident distributions and communication failures.

Public Transit

Transit Agencies struggle to maintain transit accessibility with reduced resources, changing ridership patterns, vehicle capacity constraints. We have been working for the last several years to design AI-based scheduling systems to solve the problem of allocating vehicles and drivers to transit services, scheduling vehicle maintenance, and electric-vehicle charging, proactive stationing, and dispatch of vehicles for fixed-line service to mitigate unscheduled maintenance and unmet transit demand, aggregating on-demand transit requests, and dispatching and routing on-demand vehicles. Similar to the incident response, the decision support systems face key challenges - environments are non-stationary and difficult to predict due to human factors and complex processes affecting transit demand and traffic as well as unscheduled maintenance and accidents; simulations are expensive and complex as city-scale simulations need to consider millions of individuals and vehicles.

Power Grids

Resilience, scalability and safety of operations is critical for power grid. Ensuring that the system operates resiliently while handling the challenges of both component failures, environmental uncertainty and adversarial attacks is not easy. The challenge in this domain include data corruption, failure and misoperation of protection equipment, and the possibility of misclassification of a fault by the AI system. System integration and operation of the grid remains open challenges. Further, the emerging trend in this domain is networked microgrids that can island or be connected together to respond to adversities. However, dynamic formation of networked microgrids for heterogeneous components is not a solved problem. System integrators must often put together a microgrid from available components that communicate different information, at different rates, using different protocols. Due to variations in the microgrid architectures and their generation and load mix, each microgrid solution is customized and site-specific.

Active Projects

Addressing Transit Accessibility and Public Health Challenges due to COVID-19

The COVID-19 pandemic has not only disrupted the lives of millions but also created exigent operational and scheduling challenges for public transit agencies. Agencies are struggling to maintain transit accessibility with reduced resources, changing ridership patterns, vehicle capacity constraints due to social distancing, and reduced services due to driver unavailability. A number of transit agencies have also begun to help the local food banks deliver food to shelters, which further strains the available resources if not planned optimally. At the same time, the lack of situational information is creating a challenge for riders who need to understand what seating is available on the vehicles to ensure sufficient distancing. We are designing integrated transit operational optimization algorithms, which will provide proactive scheduling and allocation of vehicles to transit and cargo trips, considering exigent vehicle maintenance requirements (i.e., disinfection). A key component of the research is the design of privacy-preserving camera-based ridership detection methods that can help provide commuters with real-time information on available seats considering social-distancing constraints.

Augmenting and Advancing Cognitive Performance of Control Room Operators for Power Grid Resiliency

The goal of the project is to investigate the mechanisms required to integrate recent advances from cognitive neuroscience, artificial intelligence, machine learning, data science, cybersecurity, and power engineering to augment power grid operators for better performance. Two key parameters influencing human performance from the dynamic attentional control (DAC) framework are working memory (WM) capacity, the ability to maintain information in the focus of attention, and cognitive flexibility (CF), the ability to use feedback to redirect decision making given fast changing system scenarios. We are building a new set of algorithms for data-driven event detection, anomaly flag processing, root cause analysis and decision support using Tree Augmented naive Bayesian Net (TAN) structure, Minimum Weighted Spanning Tree (MWST) using the Mutual Information (MI) metric, and unsupervised learning improved for online learning and decision making.

CHARIOT

The CHARIOT (Cyber-pHysical Application aRchItecture with Objective-based reconfiguraTion) project, aims to address the challenges stemming from the need to resolve various challenges within extensible CPS found in smart Cities. CHARIOT is an application architecture that enables design, analysis, deployment, and maintenance of extensible CPS by using a novel design-time modeling tool and run-time computation infrastructure. In addition to physical properties, timing properties and resource requirements, CHARIOT also considers heterogeneity and resilience of these systems. The CHARIOT design environment follows a modular objective decomposition approach for developing and managing the system. Each objective is mapped to one or more data workflows implemented by different software components. This function to component association enables us to assess the impact of individual failures on the system objectives. The runtime architecture of CHARIOT provides a universal cyber-physical component model that allows distributed CPS applications to be constructed using software components and hardware devices without being tied down to any specific platform or middleware. It extends the principles of health management, software fault tolerance and goal based design.

Computational Processing at Edge

Developing an edge cloud is one of the big concerns for cyber-physical systems because latency to the cloud is a big issue. Under DOE and ARPA-E funding we have been developing a middleware that can support edge cloud called RIAPS. It is built upon a lot of our prior work in the area of componentized software frameworks for real-time systems and provides solutions for security, fault isolation, fault recovery, device abstractions, time synchronization and correct-by construction design. Recently, we have been extending this work to create a computational outsourcing market called MODICUM for edge systems. It is 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.

DataScience and STEM

This project aims to help the incorporation of data science concepts and skill development in undergraduate courses in biology, computer science, engineering, and environmental science. Through a collaboration between Virginia Tech, Vanderbilt University, and North Carolina Agricultural and Technical State University, we are developing interdisciplinary learning modules based on high frequency, real-time data from water and traffic monitoring systems. These topics will facilitate incorporation of real-world data sets to enhance the student learning experience and they are broad enough that they can incorporate other data sets in the future. Such expertise will better prepare students to enter the STEM workforce, especially those STEM professions that focus on smart and connected computing. The project will investigate how and in what ways the modules support student learning of data science.

Edgenet - An online Edge Computing Based Generative Anomaly Detection and Prognostics Solution

Anomaly detection, prognostication and automated mitigation are very critical for data center management. Most of these approaches can be divided into two categories - model-based and data-driven. While model-based techniques rely on physics guided models that can explain and predict the expected progression of parameters such as temperature and voltage in electronics, the data-driven approach is suitable for complex scenarios where a suitable physics based model is unavailable. The data-driven approaches can be further divided into supervised and unsupervised methods. While supervised methods rely on prior labels, unsupervised methods are more suited for cases where the prior failure data might be unavailable or where the failure trends change over time. This is precisely the problem that exists in modern data-centers where the network devices and models change over time and the prior labels are absent. The precise problem therefore is to develop unique anomaly scoring functions that can identify whether the various components in a complex device are failing or not. Note that unlike the prior art it is crucial to not only identify anomalies, but identify the sub-components at the silicon level which are failing in the devices.

Energy Efficiency of Transit Operations

We are developing models to analyze and optimize the cost of transit operations by focusing on the energy impact of the vehicles. For this purpose, we are developing real-time data sets containing information about engine telemetry, including engine speed, GPS position, fuel usage, and state of charge (electrical vehicles) from all vehicles in addition to traffic congestion, current events in the city, and the braking and acceleration patterns. These high-dimensional datasets allow us to train accurate data-driven predictors using deep neural networks, for energy consumption given various routes and schedules. Having these predictors combined with traffic congestion information obtained from external sources will enable the agencies to identify and mitigate energy efficiency bottlenecks within each specific mode of operation such as electric bus and electric car. To make this possible, the project is also developing new distributed computing and machine learning algorithms that can handle data at such a rate and scale.

Integrated Microgrid Control Platform

Dynamic formation of networked microgrids for heterogeneous components is not a solved problem. System integrators must often put together a microgrid from available components that communicate different information, at different rates, using different protocols. Due to variations in the microgrid architectures and their generation and load mix, each microgrid solution is customized and site-specific. Building on the Resilient Information Architecture Platform for Smart Grid, the goal of this project is to demonstrate a technology for microgrid integration and control based on distributed computing techniques, advanced software engineering methods, and state-of-the-art control algorithms that provides a scalable and reusable solution yielding a highly configurable Integrated Microgrid Control Platform (IMCP) . Our solution addresses the heterogeneity problem by encapsulating the specific details of protocols into reusable device software components with common interfaces, and the dynamic grid management and reconfiguration problem with advanced distributed algorithms that form the foundation for a decentralized and expandable microgrid controller. Investigators Prof. Gabor Karsai (PI), Prof. Abhishek Dubey (Co-PI) and Prof. Srdjan Lukic (Co-PI).

MIDAS

The goal of the project to develop a new approach to evolutionary software development and deployment that extends the results of model-based software engineering and provides an integrated, end-to-end framework for building software that is focused on growth and adaptation. The envisioned technology is based on the concept of a ‘Model Design Language’ (MDL) that supports the expression of the developer’s objectives (the ‘what’), intentions (the ‘how’), and constraints (the ‘limitations’) related to the software artifacts to be produced. The ‘models’ represented in this language are called the ‘design models’ for the software artifact(s) and they encompass more than what we express today in software models. We consider software development as a continuous process, as in the DevOps paradigm, where the software is undergoing continuous change, improvement, and extension; and our goal is to build the tools to support this. The main idea is that changes in the requirements will result in the designer/developer making changes in the ‘design model’ that will result in changes in the generated artifacts, or changes in the target system, at run-time, as needed.

Resilient Information Architecture Platform for the Smart Grid

The future of the Smart Grid for electrical power depends on computer software that has to be robust, reliable, effective, and secure. This software will continuously grow and evolve, while operating and controlling a complex physical system that modern life and economy depends on. The project aims at engineering and constructing the foundation for such software; a ‘platform’ that provides core services for building effective and powerful apps, not unlike apps on smartphones. The platform is designed by using and advancing state-of-the-art results from electrical, computer, and software engineering, will be documented as an open standard, and will be prototyped as an open source implementation.

Secure and Trustworthy Middleware for Integrated Energy and Mobility in Smart Connected Communities

The rapid evolution of data-driven analytics, Internet of things (IoT) and cyber-physical systems (CPS) are fueling a growing set of Smart and Connected Communities (SCC) applications, including for smart transportation and smart energy. However, the deployment of such technological solutions without proper security mechanisms makes them susceptible to data integrity and privacy attacks, as observed in a large number of recent incidents. The goal of this project is to develop a framework to ensure data privacy, data integrity, and trustworthiness in smart and connected communities. The innovativeness of the project lies in the collaborative effort between team of researchers from US and Japan together. As part of the project the research team is developing privacy-preserving algorithms and models for anomaly detection, trust and reputation scoring used by application providers for data integrity and information assurance. Towards that goal, we are also studing trade-offs between security, privacy, trust levels, resources, and performance using two exemplar applications in smart mobility and smart energy exchange in communities.

Statistical Optimization and Analytics for Community Emergency Management

The goal of this project is to improve emergency response systems using proactive resource management that minimizes time and maximizes the effectiveness of the response. With road accidents accounting for 1.25 million deaths globally and 240 million emergency medical services (EMS) calls in the U.S. each year, there is a critical need for a proactive and effective response to these emergencies. Furthermore, a timely response to these incidents is crucial and life-saving for severe incidents. The process of managing emergencies requires full integration of planning and response data and models and their implementation in a dynamic and uncertain environment to support real-time decisions of dispatching emergency response resources. However, the current state-of-the-art research has mainly focused on advances that target individual aspects of emergency response (e.g., prediction, optimization) when different components of an Emergency Response Management (ERM) system are highly interconnected. Additionally, the current practice of ERM workflow in the U.S. is reactive, resulting in a large variance in response times.

Transactive Energy Systems

Transactive energy systems 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. In the last five years, we have used this research vertical to drive our research in the area of resilient decentralized CPS and have developed a novel middleware platform called TRANSAX by enabling 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. It 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.

Transit System Optimization

We are developing algorithms to perform system-wide optimization, (the microtransit, fixed line and paratransit) focusing on three objectives - minimizing energy per passenger per mile, minimizing total energy consumed, and maximizing the percentage of daily trips served by public transit. While it is possible to optimize these decisions separately as prior work has done, integrated optimization can lead to significantly better service (e.g., synchronizing flexible courtesy stops with microtransit dispatch for easy transfer). However, this is hard due to uncertainty of future demand, traffic conditions etc. We address these challenges using state-of-the-art artificial intelligence, machine learning, and data-driven optimization techniques. Deep reinforcement learning (DRL) and Monte-Carlo tree search form the core of our operational optimization, which is supported by data-driven optimization for offline planning and by machine learning techniques for predicting demand, maintenance requirements, and traffic conditions. A key aspect of this research area is the development of techniques to preserve privacy across multimodal datasets, while also providing sufficient information for analysis and scheduling. The outcome of the project will be a deployment-ready software system that can be used to design and operate a micro-transit service effectively.

Selected Activities

Deep NN Car with SafetyManager

Transax-Blockchain and Transactive Energy

Presentation by Afiya Ayman at IEEE SMARTCOMP 2020

Mobility Application Built by Students in the Smart Cities Class

Recent paper on the impact of COVID-19 on transit

CHARIOT Demonstration

Incident Analytics and Response Management Dashboard

Project presentation given at the DoE Annual Merit Review

Providing Information to Commuters

Energy Consumption Dashboard

Modular Mobility Application

Multi-Modal Mobility Workshops organized in 2018

Poster at TDEC workshop in Knoxville in 2019

Resilient Information Architecture Platform Demonstration

Occupancy Analysis Dashboard for CARTA

Modular Computing Platform for Public Transit

Occupancy Analysis Dashboard for WeGo Nashville

The Team

Dr. Abhishek Dubey

Lead

Dr. Abhishek Dubey is an Assistant Professor of Electrical Engineering and Computer Science at Vanderbilt University and a Senior Research Scientist at the Institute for Software-Integrated Systems. Abhishek directs the SCOPE lab (Smart and resilient COmputing for Physical Environment) at the Institute for Software Integrated Systems and is the co-lead of Vanderbilt Initiative for Smart Cities Operation and Research (VISOR). His broad research interest lies in the resilient system design of cyber physical systems. He is specially interested in performance management, online failure detection, isolation and recovery in smart and connected cyber-physical systems, with a focus on transportation networks and smart grid. His key contributions include the development and deployment of resilience decision support systems for Metropolitan Transit Authority in Nashville, a robust incident prediction and dispatch system developed for Nashville Fire Department and a privacy-preserving decentralized system for peer-to-peer energy exchange. His other contributions include middleware for online fault-detection and recovery in software intensive distributed systems and a robust software model for building cyber-physical applications, along with spatial and temporal separation among different system components, which guarantees fault isolation. Recently, this work has been adapted for fault detection and isolation in breaker assemblies in power transmission lines. His work has been funded by the National Science Foundation, NASA, DOE, ARPA-E. AFRL, DARPA, Siemens, Cisco and IBM. Abhishek completed his PhD in Electrical Engineering from Vanderbilt University in 2009 in the area of fault detection and isolation for large computing clusters. He received his M.S. in Electrical Engineering from Vanderbilt University in August 2005 and completed his undergraduate studies in Electrical Engineering from the Indian Institute of Technology, Banaras Hindu University, India in May 2001.

Dr. Ayan Mukhopadhyay

Research Scientist

Dr. Ayan Mukhopadhyay is a Research Scientist in the Department of Electrical Engineering and Computer Science at Vanderbilt University, USA. Prior to this, he was a Post-Doctoral Research Fellow at the Stanford Intelligent Systems Lab at Stanford University, USA. He was awarded the 2019 CARS post-doctoral fellowship by the Center of Automotive Research at Stanford (CARS). Before joining Stanford, he completed his Ph.D. at Vanderbilt University’s Computational Economics Research Lab, and his doctoral thesis was nominated for the Victor Lesser Distinguished Dissertation Award 2020. His research interests include multi-agent systems, robust machine learning, and decision-making under uncertainty applied to the intersection of CPS and smart cities. His work has been published in several top-tier AI and CPS conferences like AAMAS, UAI, and ICCPS. His work on creating proactive emergency response pipelines has been covered in the government technology magazine, won the best paper award at ICLR’s AI for Social Good Workshop, and covered in multiple smart city symposiums.

Geoffrey Pettet

Graduate Research Assistant

Geoffrey Pettet is a graduate student in the Department of Computer Science and Computer Engineering at Vanderbilt University, and works as a research assistant at the Institute for Software Integrated Systems. He completed his undergraduate studies in computer science at Vanderbilt University in May 2016.

Nithin Guruswamy

Graduate Research Assistant

Nithin is a PhD student at Scope Lab. He has over 16 years professional experience, working in various companies like Cisco ,Honeywell and GE transportation and have extensive knowledge on embedded software and iOS development across industry verticals like Mobile Communication, Avionics, Railroad and Computer Networking. Previously before joining to Vanderbilt University, he was working as a Software Engineer 4 at Cisco Systems Ltd, where he was responsible for debugging support and developing new features for five switch fabric modules of Cisco’s NCS6K core router and application of machine learning on Cisco routers for hardware failure prediction.

Dr. Sayyed Mohsen Vazirizade

PostDoc

Sayyed Mohsen Vazirizade is a Post Doctoral Research Fellow in the Department of Computer Science and Computer Engineering at Vanderbilt University. Sayyed earned his PhD from the University of Arizona in Dec. 2019.

Dr. Scott Eisele

Senior Engineer

Dr. Scott Eisele is a senior Engineer at Institute for Software Integrated Systems His research interests are in cyber-physical systems, and distributed computing. He completed an undergraduate degree in Mechanical Engineering at Brigham Young University in 2013 and received PhD in Electrical Engineering in 2020.

Shreyas Ramakrishna

Graduate Research Assistant

Shreyas Ramakrishna is a graduate student in the Department of Electrical Engineering at Vanderbilt University, and works as a research assistant at the Institute for Software Integrated Systems. He received his M.S. degree in Electrical Engineering from Technical University Kaiserslautern (Germany) in June 2015 and completed his undergraduate studies in Electrical engineering from Visvesvaraya Technological University, India in 2012.

Michael Wilbur

Graduate Research Assistant

Michael Wilbur is a graduate student in the Department of Electrical Engineering and Computer Science at Vanderbilt University and works as a research assistant at the Institute for Software Integrated Systems. He received his M.S. degree in Structural Engineering from Northwestern University in December 2018 and his Bachelor’s degree in Civil Engineering from The University of Notre Dame in 2012.

Selected Publications

  1. S. Eisele, T. Eghtesad, N. Troutman, A. Laszka, and A. Dubey, Mechanisms for Outsourcing Computation via a Decentralized Market, in 14TH ACM International Conference on Distributed and Event Based Systems, 2020.
  2. S. Eisele, T. Eghtesad, K. Campanelli, P. Agrawal, A. Laszka, and A. Dubey, Safe and Private Forward-Trading Platform for Transactive Microgrids, Transactions on Cyber-Physical Systems, 2020.
  3. S. Ramakrishna, C. Hartsell, M. P. Burruss, G. Karsai, and A. Dubey, Dynamic-Weighted Simplex Strategy for Learning Enabled Cyber Physical Systems, Special Issue on the 2019 IEEE Symposium on Real-time Computing ISORC, 2020.
  4. G. Pettet, A. Mukhopadhyay, M. Kochenderfer, Y. Vorobeychik, and A. Dubey, On Algorithmic Decision Procedures in Emergency Response Systems in Smart and Connected Communities, in Proceedings of the 19th Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2020, Auckland, New Zealand, 2020.
  5. S. Hasan, A. Dubey, G. Karsai, and X. Koutsoukos, A game-theoretic approach for power systems defense against dynamic cyber-attacks, International Journal of Electrical Power & Energy Systems, vol. 115, 2020.
  6. C. Hartsell et al., CPS Design with Learning-Enabled Components: A Case Study, in Proceedings of the 30th International Workshop on Rapid System Prototyping, RSP 2019, New York, NY, USA, October 17-18, 2019, 2019, pp. 57–63.
  7. F. Sun, A. Dubey, J. White, and A. Gokhale, Transit-hub: a smart public transportation decision support system with multi-timescale analytical services, Cluster Computing, vol. 22, no. Suppl 1, pp. 2239–2254, Jan. 2019.
  8. Garcı́a-Valls Marisol, A. Dubey, and V. J. Botti, Introducing the new paradigm of Social Dispersed Computing: Applications, Technologies and Challenges, Journal of Systems Architecture - Embedded Systems Design, vol. 91, pp. 83–102, 2018.
  9. S. Pradhan et al., CHARIOT: Goal-Driven Orchestration Middleware for Resilient IoT Systems, TCPS, vol. 2, no. 3, pp. 16:1–16:37, 2018.
  10. D. Balasubramanian et al., DREMS ML: A wide spectrum architecture design language for distributed computing platforms, Sci. Comput. Program., vol. 106, pp. 3–29, 2015.
  11. T. Levendovszky et al., Distributed Real-Time Managed Systems: A Model-Driven Distributed Secure Information Architecture Platform for Managed Embedded Systems, IEEE Software, vol. 31, no. 2, pp. 62–69, 2014.
  12. N. Mahadevan, A. Dubey, and G. Karsai, Application of software health management techniques, in 2011 ICSE Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS 2011, Waikiki, Honolulu , HI, USA, May 23-24, 2011, 2011, pp. 1–10.
  13. N. Roy, A. Dubey, and A. S. Gokhale, Efficient Autoscaling in the Cloud Using Predictive Models for Workload Forecasting, in IEEE International Conference on Cloud Computing, CLOUD 2011, Washington, DC, USA, 4-9 July, 2011, 2011, pp. 500–507.
All Publications