基于粒子群算法的配电台区售电量精准预测方法

Precise Prediction Method of Electricity Sales in Distribution Station Area Based on Particle Swarm Algorithm

针对不同时段和不同模态下,售电量预测准确性较低的问题,设计一个基于粒子群算法的配电台区售电量精准预测方法。建立灰色模型挖掘数据,输入电力负荷数据,并进行归一化处理,提取容量利用特征,通过网格法将配电台区数据拆分,准变预测问题表现形式,建立售电量增长趋势模型,计算曲线拟合问题,采用粒子群算法设计配电台区售电量精准预测过程,优化权重变换函数和粒子权值,更新期望容量的长度与突变点处增长率变化参数,优化节假日趋势模型和售电量季节趋势模型求解结果,完成配电台区售电量精准预测。实验结果表明,该方法在一个月内售电量、一年内售电量、低频模态预测与高频模态预测上,都具有较高的准确性,满足配电台区售电量精准预测需求。

Aiming at the problem of low accuracy of electricity sales forecast in different periods and different modes,an accurate forecasting method of electricity sales in distribution stations based on particle swarm optimization algorithm is designed.The grey model is established to mine data,input power load data,conduct normalization processing,extract capacity utilization characteristics,split the data of distribution station area through grid method,form the quasi variable prediction problem,establish the growth trend model of electricity sales,calculate the curve fitting problem,use particle swarm optimization algorithm to design the accurate prediction process of electricity sales in distribution station area,and optimize the weight transformation function and particle weight value,update the length of the expected capacity and the change parameters of the growth rate at the sudden change point,optimize the solution results of the holiday trend model and the seasonal trend model of electricity sales,and complete the accurate prediction of electricity sales in the distribution station area.The experimental results show that the method has high accuracy in electricity sales within one month,electricity sales within one year,low-frequency modal prediction and high-frequency modal prediction,and meets the demand for accurate prediction of electricity sales in distribution stations.