基于启发式动态规划方法发电商最优竞价策略.pdfVIP

第 33 卷 第 11 期 电 网 技 术 Vol. 33 No. 11 2009 年 6 月 Power System Technology Jun. 2009 文章编号：1000-3673 （2009 ）11-0071-05 中图分类号：F416.2 文献标志码：A 学科代码：790·625 基于启发式动态规划方法的发电商最优竞价策略 张志刚，马光文，王黎 （四川大学水电学院，四川省 成都市 610065 ） Optimal Bidding Strategy of Generation Companies Based on Heuristic Dynamic Programming ZHANG Zhi-gang ，MA Guang-wen ，WANG Li （Institute of Hydroelectric Engineering，Sichuan University，Chengdu 610065，Sichuan Province，China ） ABSTRACT: The bidding strategy for electricity purchase and 关键词：电力市场；启发式动态规划；近似动态规划； sale in electricity market environment is a complex dynamic 智能体 problem that is especially prominent in the duration of 0 引言 medium- and long-term transaction, so it is hard for traditional mathematical analysis method to analyze and calculate such a 电力市场环境下，发电、输电和配电服务的分 problem. An optimal power flow based learning model for 离为电力工业的发展带来了更多的机遇，同时也带 two-layer medium- and long-term optimal bidding strategy is 来了很多不确定因素。在这样的环境下，各电力市 proposed. Using heuristic dynamic programming method, the 场成员可通过采用策略性的投标来获取最大利润， strategic behavior of dynamic programming and iteration of 每个市场成员在确定其投标策略时，主要考虑其他 reward and penalty factors are regarded as agent and the 市场竞争对象的竞价策略、潮流约束、燃料费用的 external uncertain factors as the external environment of the 变化等。由于这些不确定因素的影响，若采用传统 agent. Under this condition, through the assessment and 的数值解法，各市场成员很难得到理想的竞价策 judgment on environment, the agent chooses feasible strategic 略。此外，由于单个市场成员的利润函数一般呈现 scheme guides itself to attain optimal production revenue by