Real-time digital twin machine learning-based cost minimization model for renewable-based microgrids considering uncertainty. (15th January 2023)

• Record Type: Journal Article
• Authors: Pan, Mingyu; Xing, Qijing; Chai, Zhichao; Zhao, He; Sun, Qinfei; Duan, Dapeng
• Is Part Of: Solar energy. Volume 250(2023)
• Page Start: 355
• Page End: 367
• Publication Date: 2023-01-15
• Subjects: Reinforcement learning -- Energy management -- Markov chain scheme -- Renewable-based microgrid -- Digital twin; Solar energy -- Periodicals; Solar engines -- Periodicals; 621.47
• DOI: 10.1016/j.solener.2023.01.006
• Languages: English
• ISSNs: 0038-092X

Abstract

Highlights: This paper examines a reinforcement learning (RL) method that uses 2steps-ahead to schedule the batteries and PV. Develop an essential architecture to make multi-criteria decisions via an individual user. Increase the battery's usage at peak times and increase the wind turbine's and PVs usage for local consumption. Reinforcement learning algorithms modeling in digital twin to select the optimum battery planning measures based on forecasts of wind power and photovoltaic availability. Abstract: This research study aims to investigate the microgrid operation for distributing energy including of a local user, a wind turbine, 5 photovoltaics (PV), and a battery, which is linked by a transformer to the external network. This paper examines a reinforcement learning (RL) method that uses 2steps-ahead to schedule the batteries, which is essential for achieving the objective of the users. There is an essential architecture to make multi-criteria decisions via an individual user to increase the battery's usage at peak times and increase the wind turbine's usage for local consumption. RL algorithms select the optimum battery planning measures based on forecasts of wind power and photovoltaic availability. Through the suggested learning, the user can better understand the optimum battery planning measures for various time-varying environment factors. By using the proposed architecture, smart users are capable of learning the uncertain environment and selecting optimum energy management measures based on their experiences.