Transactive energy management of a microgrid with distributed energy resources

• Main Author: Cao, Wenhai
• Other Authors: Xu Yan
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering; Transactive energy management system; Deep reinforcement learning; Radial basis function; Nonlinear optimization
• Online Access: https://hdl.handle.net/10356/175711
• Institution: Nanyang Technological University

This dissertation delves into the intricacies of Transactive Energy Management (TEM) systems within microgrids, focusing particularly on the application and innovation in managing Distributed Energy Resources (DERs). By providing a comprehensive analysis of the global energy demand transition and the increasing reliance on renewable energy sources, the dissertation unveils the pivotal role of microgrid systems in the modern energy transformation. Specifically, integrating distributed energy resources such as solar, wind, and battery storage, enhance not only the stability and economic efficiency of power supply but also promote environmental sustainability. The document further highlights the significant application of Internet of Things (IoT) and data analytics in optimizing microgrid Transactive Energy Management Systems (TEMS). It emphasizes the critical importance of these advanced technologies in improving energy distribution efficiency and overall system performance. Moreover, through discussing the effectiveness of Deep Reinforcement Learning (DRL) and Radial Basis Function (RBF) networks in addressing high-dimensional and continuous action space optimization challenges, the dissertation showcases the immense potential of AI-assisted optimization tools. In exploring nonlinear optimization methods within microgrids, the dissertation comprehensively describes the operational models and constraints of battery energy storage systems, photovoltaic, and wind energy systems, underscoring the central role of the power flow model in achieving economic and environmental objectives of microgrids. Through precise mathematical modeling and innovative optimization strategies, microgrids can achieve more efficient energy management, thereby fulfilling the dual purpose of cost reduction and increased utilization of renewable resources. In conclusion, this dissertation not only analyzes the configuration and design of microgrid Transactive Energy Management Systems in depth but also elucidates the significant role of AI and nonlinear optimization technologies in advancing microgrid development. With the application of these cutting-edge technologies, microgrids are poised to become a key force in the future energy system transformation, offering strong support for achieving a more sustainable and efficient energy utilization.