变拓扑人工神经网络负荷预报

提出变拓扑人工神经网络(ANN)预报电力系统负荷的方法。所提出的模型能较 全面地反映影响负荷变化的各种因素。ANN在BP算法的学习中，需用的数 据窗最短。通过人机会话，可灵活地实现不同预报期限的负荷预报。算例表明 ，方法是有效的，预报精度比常规方法高，收敛性好，计算速度快，适于在线 应用。

CHANGING TOPOLOGICAL ARTIFICIAL NEURAL NETWORK FOR LOAD FORECASTING

The paper presents a method of changing topological artificial neural network (ANN) to forecast the load of power system. The model is almost an all - round reflection of various factors which affect the changing of load. The data window which ANN needs in the learning of BP algorithm is the shortest. Through man -machine dialog, the load forecasting of various forecasting terms can be flexibly realized. The calculations show that the method is efficient. The forecasting accuracy is more accurate than that of conventional methods. It has satisfied convergency and high computing speed, which is suitable for on-line application.