在实时电价环境下基于RBF神经网络和自适应神经模糊系统相结合的电力短期负荷预测方法.pdfVIP

25 卷 22 期 中 国 电 机 工 程 学 报 Vol.25 No.22 Nov. 2005 2005 年11 月 Proceedings of the CSEE 2005 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2005) 07-0078-05 中图分类号：TM715 文献标识码：A 学科分类号：47040 基于径向基神经网络和自适应神经模糊 系统的电力短期负荷预测方法 雷绍兰, 孙才新, 周 湶, 张晓星, 程其云 （重庆大学高电压与电工新技术教育部重点实验室, 重庆市 沙坪坝区 400030 ） SHORT-TERM LOAD FORECASTING METHOD BASED ON RBF NEURAL NETWORK AND ANFIS SYSTEM LEI Shao-lan , SUN Cai-xin, ZHOU Quan, ZHANG Xiao-xing, CHENG Qiyun (The Key Laboratory of High Voltage Engineering and Electrical New Technology，Ministry of Education，Chongqing University, Shapingba District, Chongqing 400030, China) ABSTRACT: To counter the influence of real-time electric 网络；自适应神经模糊系统 price on short-term load, a model for forecasting the short-term 1 引言 load is set up by combining Radial Basis Function (RBF)neural 电力短期负荷预测是电力系统安全调度和经 network with Adaptive Neural Fuzzy Inference System (ANFIS). The model first draws on the nonlinear approaching 济运行的重要依据。在电力市场环境下，各电力公 capacity of the RBF network to forecast the load on the 司若要制定合理的经济模型和具有竞争力的实时电 prediction day which takes no account of the factor of electric [1] 价，则需依赖于准确和快速的负荷预测 。长期以 price, and then, based on the recent changes of real-time price, 来，人们致力于短期负荷预测方法的研究，并提出 uses the ANFIS system to modify the results of load forecasting [2-11] 了许多负荷预测算法 ，其中广泛应用于实时电 obtained by using the RBF network so as to improve the