摘要
根据电力负荷的主要影响因素,考虑时间和天气,建立了基于遗传算法和反向传播神经网络(BP)的短期负荷预测.从BP神经网络的理论入手,采用遗传算法优化BP神经网络的初始权值和隐层节点数,从而避免了神经网络结构确定和初始权值选择的盲目性,提高了神经网络用于电力系统短期负荷预测的效率和精度使得负荷预测在更加合理的网络结构上进行.
With the main influential factors on electric power load, the weekday and weather considered, a load forecasting model based on genetic algorithm and BP is constructed. Considering that the number of nevre cells in hidder layer,initial weight and unit＇s bias value are the most important acftors factors to the foercasti percision of ANN,genetic algoritbm is used to choose a more reasonable frame of ANN. Genetic algorithm is good for deci- ding the proper fabric of net, and helping the ANN to conquer its disfigurement.
基金
安徽省高校自然科学基金资助项目(2003kj036)
