Department of Electrical Engineering and Computer Science
Permanent URI for this collection
Browse
Browsing Department of Electrical Engineering and Computer Science by Subject "power system management"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Hidden Convexities in Decentralized Coordination for the Distribution Networks(IEEE Transactions on Power Systems, 2020-05) Srikantha, Pirathayini; M. MallickThe modern power grid is undergoing unprecedented levels of transformations due to the rising prevalence of diverse power entities, cyber-enablement of grid components and energy deregulations. In this paper, we focus on distribution networks (DNs) to enable the seamless plug-and-play coordination of actuating cyber-enabled power entities for cost-effective and feasible system operations. The proposed distributed algorithm empowers individual cyber-physical agents residing in active power nodes with the ability to iteratively compute local actuation setpoints by exchanging information with neighbouring entities. The main contribution of this work is the identification of hidden convexities in the original non-convex optimal power flow (OPF) formulation for the DN via strategic decomposition and strong duality principles. These eliminate the need for OPF relaxations/approximations. Strong convergence and feasibility results are presented via theoretical analysis and practical simulation studies conducted on realistic systems.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.