短期电力负荷预测的自适应混合遗传优化BP算法

Short-Term Load Forecasting with Adaptive Hybrid Genetic Optimization BP Neural Network Algorithm

基于遗传算法具有很强的全局搜索能力和BP神经网络具有精确的局部搜索能力的特点,提出对电力短期负荷预测的自适应的混合算法。将训练样本随机地分为训练集和测试集。应用该算法对澳大利亚悉尼的短期电力负荷进行了预测。仿真计算表明,该算法达到了提高预测精度和改善网络性能的要求。

The paper proposed an adaptive hybrid genetic BP neural network algorithm, which use genetic algorithm to optimize the BP network initial weight first, then use the BP neural network to learn by itself according to the data given, to acquire an excellent load forecasting system. In the training of neural network, the over-fitting often appears which affects the result of forecasting. To prevent this problem, the entire data set is divided into training set and validation set randomly. This algorithm was used to predict the load of Sydney. Simulation results indicate that the algorithm improve the forecast accuracy and the performance of the network.