Optimized Management of Virtual Power Plants for Frequency Support Using Deep Reinforcement Learning

• Grant number: 24/18735-1
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: March 01, 2025
• End date: February 29, 2028
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Denis Vinicius Coury
• Grantee: Pedro Inácio de Nascimento e Barbalho
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Growing initiatives to reduce greenhouse gas emissions have motivated academia and industry to develop and disseminate Distributed Energy Resources (DERs) based on renewable sources such as wind turbines and photovoltaic panels. Additionally, the integration of energy storage systems is increasing, as they compensate during energy surplus and shortage due to the intermittency of these sources. These DER technologies are usually connected to the grid through DC-AC converters, also known as inverters. Inverter-Based Resources (IBRs), when deployed on a large scale, can impact the grid's equivalent inertia and generate reverse power flows. In this context, Virtual Power Plants (VPPs) emerge as a viable solution to aggregate DERs, maximizing the benefits of distributed generation. Studies on VPPs primarily focused on optimization strategies for DER dispatch to minimize operational costs, without adequately addressing stability issues associated with the operation of IBRs. Moreover, the complexity of variables and scenarios involved in optimization requires the use of advanced algorithms, such as Deep Reinforcement Learning (DRL). Considering this, the main objectives of this postdoctoral research project are to propose indicators for diagnosing stability in networks with high IBR penetration; to develop a DRL-based approach for optimizing the dispatch of IBRs in VPPs by adjusting the grid's equivalent inertia; and to analyze the impact of the proposed approach on the operation of protection devices.