Demand response decision optimization method considering long-term income

• Main Authors: WANG DUNDONG, GU YINKAI, GAO YANQING, XU BINGYIN, BI XIAOMING, WAN MINGYU, LIU PINGPING, LU MIN
• Format: Patent
• Language: Chinese; English
• Published: 29.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention belongs to the technical field of demand side management of a power system, and provides a demand response decision optimization method considering long-term income, which comprises the following steps: (1) constructing an electricity seller demand response optimization model; (2) constructing a demand response optimization mechanism; and (3) solving a demand response decision. According to the optimization method disclosed by the invention, demand response optimization scheduling considering long-term benefits is realized by utilizing a deep reinforcement learning algorithm based on a competitive deep network architecture, so that the long-term benefits of the electricity sellers are maximized. 本发明属于电力系统的需求侧管理技术领域，提供一种计及长期收益的需求响应决策的优化方法，包括：(1)售电商需求响应优化模型构建；(2)需求响应优化机制构建；(3)需求响应决策求解。本发明优化方法利用基于竞争深度网络架构的深度强化学习算法实现计及长期收益的需求响应优化调度，以实现售电商长期利益的最大化。