Smart cities require supporting multiple concurrent applications with different computational requirements (real-time, near real-time, and batch) on shared infrastructure. CHARIOT innovates by providing a unified computation model that accommodates heterogeneous application types through tasklets and transport abstractions, enabling efficient resource sharing while preserving quality-of-service requirements.
This paper addresses generic computation models for smart city platforms supporting cyber-physical systems with heterogeneous application types. The CHARIOT computation model represents distributed computations as task graphs supporting diverse timing requirements and data processing patterns. The model enables mapping of time-driven, batch, and stream processing onto common computation abstractions.
The paper demonstrates how CHARIOT maps to existing computation patterns and scales across multiple edge and cloud computing nodes. It shows successful integration of control applications, edge analytics, and data processing workflows within a single platform. The validation using transactive energy and traffic control scenarios confirms the model's ability to support diverse smart city applications.
@inproceedings{Pradhan2016d,
author = {Pradhan}, S. and Dubey, Abhishek and {Neema}, S. and {Gokhale}, A.},
booktitle = {2016 1st International Workshop on Science of Smart City Operations and Platforms Engineering (SCOPE) in partnership with Global City Teams Challenge (GCTC) (SCOPE - GCTC)},
title = {Towards a generic computation model for smart city platforms},
year = {2016},
month = {apr},
pages = {1-6},
abstract = {Smart emergency response systems, smart transportation systems, smart parking spaces are some examples of multi-domain smart city systems that require large-scale, open platforms for integration and execution. These platforms illustrate high degree of heterogeneity. In this paper, we focus on software heterogeneity arising from different types of applications. The source of variability among applications stems from (a) timing requirements, (b) rate and volume of data they interact with, and (c) behavior depending on whether they are stateful or stateless. These variations result in applications with different computation models. However, a smart city system can comprise multi-domain applications with different types and therefore computation models. As such, a key challenge that arises is that of integration; we require some mechanism to facilitate integration and interaction between applications that use different computation models. In this paper, we first identify computation models based on different application types. Second, we present a generic computation model and explain how it can map to previously identified computation models. Finally, we briefly describe how the generic computation model fits in our overall smart city platform architecture.},
category = {workshop},
contribution = {colab},
doi = {10.1109/SCOPE.2016.7515059},
file = {:Pradhan2016d-Towards_a_Generic_Computation_Model_for_Smart_City_Platforms.pdf:PDF},
issn = {null},
keywords = {smart city, cyber-physical systems, computation models, edge computing, task graphs, distributed systems, resource management},
tag = {platform},
month_numeric = {4}
}