António Corte Real , G. Pontes Luz , J.M.C. Sousa , M.C. Brito , S.M. Vieira
{"title":"Optimization of a photovoltaic-battery system using deep reinforcement learning and load forecasting","authors":"António Corte Real , G. Pontes Luz , J.M.C. Sousa , M.C. Brito , S.M. Vieira","doi":"10.1016/j.egyai.2024.100347","DOIUrl":null,"url":null,"abstract":"<div><p>Home Energy Management Systems (HEMS) are increasingly relevant for demand-side management at the residential level by collecting data (energy, weather, electricity prices) and controlling home appliances or storage systems. This control can be performed with classical models that find optimal solutions, with high real-time computational cost, or data-driven approaches, like Reinforcement Learning, that find good and flexible solutions, but depend on the availability of load and generation data and demand high computational resources for training. In this work, a novel HEMS is proposed for the optimization of an electric battery operation in a real, online and data-driven environment that integrates state-of-the-art load forecasting combining CNN and LSTM neural networks to increase the robustness of decisions. Several Reinforcement Learning agents are trained with different algorithms (Double DQN, Dueling DQN, Rainbow and Proximal Policy Optimization) in order to minimize the cost of electricity purchase and to maximize photovoltaic self-consumption for a PV-Battery residential system. Results show that the best Reinforcement Learning agent achieves a 35% reduction in total cost when compared with an optimization-based agent.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"16 ","pages":"Article 100347"},"PeriodicalIF":9.6000,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000132/pdfft?md5=801e90a3cad6681c711e85effe347670&pid=1-s2.0-S2666546824000132-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy and AI","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666546824000132","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Home Energy Management Systems (HEMS) are increasingly relevant for demand-side management at the residential level by collecting data (energy, weather, electricity prices) and controlling home appliances or storage systems. This control can be performed with classical models that find optimal solutions, with high real-time computational cost, or data-driven approaches, like Reinforcement Learning, that find good and flexible solutions, but depend on the availability of load and generation data and demand high computational resources for training. In this work, a novel HEMS is proposed for the optimization of an electric battery operation in a real, online and data-driven environment that integrates state-of-the-art load forecasting combining CNN and LSTM neural networks to increase the robustness of decisions. Several Reinforcement Learning agents are trained with different algorithms (Double DQN, Dueling DQN, Rainbow and Proximal Policy Optimization) in order to minimize the cost of electricity purchase and to maximize photovoltaic self-consumption for a PV-Battery residential system. Results show that the best Reinforcement Learning agent achieves a 35% reduction in total cost when compared with an optimization-based agent.