Department of Electrical Engineering and Computer Science
Permanent URI for this collection
Browse
Browsing Department of Electrical Engineering and Computer Science by Subject "smart grids"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Open Access A Data-Driven Approach for Generating Synthetic Load Patterns and Usage Habits(IEEE Transactions on Smart Grid, 2020-07) Pirathayini, Srikantha; S.E. KababjiToday's electricity grid is rapidly evolving to become highly connected and automated. These advancements have been mainly attributed to the ubiquitous communication/computational capabilities in the grid and the Internet of Things paradigm that is steadily permeating modern society. Another trend is the recent resurgence of machine learning which is especially timely for smart grid applications. However, a major deterrent in effectively utilizing machine learning algorithms is the lack of labelled training data. We overcome this issue in the specific context of smart meter data by proposing a flexible framework for generating synthetic labelled load (e.g., appliance) patterns and usage habits via a non-intrusive novel data-driven approach. We leverage on recent developments in generative adversarial networks (GAN) and kernel density estimators (KDE) to eliminate model-based assumptions that otherwise result in biases. The ensuing synthetic datasets resemble real datasets and lend to rich and diverse training/testing platforms for developing effective machine learning algorithms pertaining to consumer-side energy applications. Theoretical and practical studies presented in this paper highlight the viability and superior performance of the proposed framework.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 Hierarchical Signal Processing for Tractable Power Flow Management in Electric Grid Networks(IEEE Transactions on Signal and Information Processing over Networks, 2018-07) srikantha, P.; Kundur, D.Rapid advancements in smart grid technologies have brought about the proliferation of intelligent and actuating power system components such as distributed generation, storage, and smart appliance units. Capitalizing fully on the potential benefits of these systems for sustainable and economical power generation, management, and delivery is currently a significant challenge due to issues of scalability, intermittency, and heterogeneity of the associated networks. In particular, vertically integrated and centralized power system management is no longer tractable for optimally coordinating these diverse devices at large scale while also accounting for the underlying complex physical grid constraints. To address these challenges, we propose a hierarchical signal processing framework for optimal power flow management whereby the cyber-physical network relationships of the modern grid are leveraged to enable intelligent decision-making by individual devices based on local constraints and external information. Decentralized and distributed techniques based on convex optimization and game theoretic constructs are employed for information exchanges and decision-making at each tier of the proposed framework. It is shown via theoretical and simulation studies that our technique allows for the seamless integration of power components into the grid with low computational and communication overhead while maintaining optimal, sustainable, and feasible grid operations.