电力市场中发电企业竞价行为的RePast仿真  

Study on RePast-based simulation for power generation companies'bidding behavior in electric market

作　　者：黄仙[1] 刘旭东[1] 

机构地区：[1]华北电力大学控制科学与工程学院,北京102206

出　　处：《计算机工程与应用》2010年第5期208-210,228,共4页Computer Engineering and Applications

摘　　要：不完全信息,寡头垄断的电力市场中,发电企业竞价上网,面临的关键是如何采用最优的申报策略以获得最大的发电收益。基于多主体的建模思路和方法,将复杂适应系统理论与博弈理论相结合,利用RePast平台对发电企业的竞价过程进行了建模仿真研究。模型考虑了发电企业群体成员的自学习性及个体之间的交互行为。仿真过程中,各参与主体在各次竞价中积累知识,不断修正各自的预测函数,以达到最优收益。仿真结果验证了该方法的有效性。As incomplete information and monopolistic electric market,power generation companies sell electric power to grid by bidding price.It is quite important for them to get maximum income by taking the optimal bidding strategy.In this paper,these companies＇bidding behavior is modeled and simulated on Repast platform with an idea of multi-agent which combines both theories of game and complex adaptive system.Self-learning ability and alternating behavior of the population of power generation companies are both taken into account.The abilities that each agent can accumulate experience gained during competition bidding and can modify its predict function at every bidding are simulated so as to get the maximal payoff.The simulation results show the presented method is effective.

关 键 词：电力市场 竞价 复杂适应系统 主体 仿真 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]