一种复合算法在短期负荷预测中的应用

Application of A Complex Algorithm to Short-term Load Forecasting

为提高电力系统短期负荷预测精度,文中提出一种基于改进遗传算法优化的径向基函数神经网络短期电力负荷预测模型,该模型采用改进的选择策略、自适应交叉和变异概率防止出现早熟现象;将自适应交叉和变异操作的改进遗传算法与梯度下降法混合交互运算,作为径向基函数神经网络的学习算法,将上述模型和算法应用于某地区电网的短期负荷预测,取得良好的预测效果。

In order to improve short term load forecasting accuracy,this paper presents a improved genetic algorithm based on improved radial basis function neural network short term load forecasting model.This model uses an improved selection strategy,adaptive crossover and mutation to prevent premature;the adaptive crossover and mutation of the improved genetic algorithm and gradient descent mixed interactive operation,as the radial basis function neural network learning algorithm.The above model and the algorithm applied to a regional power in the short-term load forecast,and made a good prediction.