Machine Learning Approach For System Reconfiguration Considering Profit-Driven Security Market. (May 2022)

• Record Type: Journal Article
• Authors: Li, Xiaolei; Zhang, Qi
• Is Part Of: Computers & electrical engineering. Volume 100(2022)
• Publication Date: 2022-05
• Subjects: Risk-measure -- grey wolf optimization -- Time-varying acceleration coefficients -- scheme generation -- smart microgrid; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.107891
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Develop optimum daily planning for RSMGs based on risk Maximizing the profits of MG operators through the reduction of them. Model the uncertain parameters of cost for selling and buying the energy and the speed of the wind. Develop the scheme generation and grey wolf optimization (GWO) algorithms to simulate variables and determine the optimum solution. Develop a novel restriction to restrict the number of topologies that can be obtained throughout the day. Calculate the RSMG operator profit after hourly configuration based on the price and incomes for the RSMG and risk evaluation. Abstract: The reconfigurable smart microgrids (RSMGs) represent the novel form for Microgrid (MG) that is worthy of further research. The present study examines a daily risk-based optimal scheduling of RSMG using a wind turbine in order to maximize the profit of the MG operator. A simulation on the basis of the Autoregressive Moving Average model is performed by considering the wind speed, selling energy cost, and buying energy cost as uncertain parameters. The grey wolf optimization algorithm has been developed to determine the optimal combination of MG switches every hour. Additionally, the condition value-at-risk has been employed to formulate a risk measure. According to the simulation outcomes, by evaluating the risk, the predicted gain for the optimum planning issue would increase, and RSMG would be able to generate more revenue through selling energy to the upstream grid over long periods. Graphical abstract: Image, graphical abstract