结合神经元网络和模糊专家系统进行电力短期负荷预测

结合人工神经元网络（ＡＮＮ）和模糊专家系统进行负荷预测．给出了径向基函数（ＲＢＦ）网络的结构，并采用正交最小平方法（ＯＬＳ）选取ＲＢＦ中心．先用ＡＮＮ进行基本负荷预测，然后考虑天气变化和假日因素所引起的负荷变化，利用模糊专家系统进行负荷调整．文中还把日期划分为５类．测试结果表明，该方法具有较高的精度和较快的速度．

Electric ShortTerm Load Forecasting Using Artificial Neural Networks and Fuzzy Expert System

This paper presents a hybrid model for short term load forecasting that integrates artificial neural networks (ANN) and fuzzy expert system. Radical basis function(RBF) network is introduced and an orthogonal least square alogorithm (OLS) is used to determine RBF function centers. The initial load is forecasted by the trained RBF networks, and then, the fuzzy expert systems modify the initial load considering the possibility of load variation due to changes in temperature and the load behavior of holiday. Day types are divided into five classes in this paper. Test results show that the hybrid model can forecast load with a higher accuracy and a faster speed.