Department of Electrical Engineering and Computer Science
Permanent URI for this collection
Browse
Browsing Department of Electrical Engineering and Computer Science by Author "Srikantha, P."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Decentralized Topology Reconfiguration in Multiphase Distribution Networks(IEEE Transactions on Signal and Information Processing over Networks, 2019-02) Srikantha, P.; Liu, J.The cyber-physical nature of the modern power grid allows active power entities to exchange information signals with one another to make intelligent local actuation decisions. Exacting effective coordination amongst these cyber-enabled entities by way of strategic signal exchanges is essential for accommodating highly fluctuating power components (e.g., renewables, electric vehicles, etc.) that are becoming prevalent in today's electric grid. As such, in this paper, we present a novel decentralized topology reconfiguration algorithm for the distribution network (DN) that allows the system to adapt in real time to unexpected perturbations and/or congestions to restore balance in loads across the feeder and improve the DN voltage profile. For this, individual agents residing in DN buses iteratively exchange signals with neighbouring nodes to infer the current state (e.g., power balance and voltage) of the system and utilize this information to make local line switching decisions. Strong convergence properties and optimality conditions of the proposed algorithm are established via theoretical studies evoking potential games and discrete concavity. Comparative simulation studies conducted on realistic DNs showcase the practical properties of the proposed algorithm.Item Open Access Stealthy Black-box Attacks on Deep Learning Non-intrusive Load Monitoring Models(IEEE Transactions on Smart Grid, 2021-03) Srikantha, P.; Wang, J.With the advent of the advanced metering infrastructure, electricity usage data is being continuously generated at large volumes by smart meters vastly deployed across the modern power grid. Electric power utility companies and third party entities such as smart home management solution providers gain significant insights into these datasets via machine learning (ML) models. These are then utilized to perform active/passive power demand management that fosters economical and sustainable electricity usage. Although ML models are powerful, these remain vulnerable to adversarial attacks. A novel stealthy black-box attack construction model is proposed that targets deep learning models utilized to perform non-intrusive load monitoring based on smart meter data. These attacks are practical as there is no assumption of the knowledge of training data, internal parameters, and architecture of the targeted ML model. The profound impact of the proposed stealthy attack constructions on energy analytics and decision-making processes is shown through comprehensive theoretical, practical, and comparative analysis. This work sheds light on vulnerabilities of ML models in the smart grid context and provides valuable insights for securely accommodating increasing prevalence of artificial intelligence in the modern power grid.