基于改进遗传算法的BP神经网络短期电力负荷预测

BP neural network short-term power load forecasting based on improved genetic algorithm

有效且准确的短期电力负荷预测有助于工业生产的预报评估和发电成本的降低。针对传统的遗传算法优化的BP神经网络局部寻优能力不足,预测精度不高的缺陷,提出模拟退火算法改进的遗传算法,来优化BP神经网络的初始权值阈值,建立改进遗传算法的BP神经网络预测模型对实际短期电力负荷数据进行预测。通过MATLAB仿真研究表明,改进后的预测模型比改进前的预测模型预测精度更高,对短期负荷预测更有实用价值。

Effective and accurate short-term power load forecasting is helpful to the prediction and evaluation of industrial production and the reduction of power generation cost. In view of the shortcomings of the traditional genetic algorithm optimized BP neural network with insufficient local optimization ability and low prediction precision, the improved genetic algorithm of simulated annealing algorithm is proposed to optimize the initial weight threshold of the BP neural network, and to set up the BP neural network prediction model of improved genetic algorithm to predict the actual short-term power load data. The MATLAB simulation results show that the improved prediction model is more accurate than the improved prediction model, and has more practical value for short-term load forecasting.