基于基因表达式编程的中长期电力负荷预测挖掘

Mid-Long Term Load Forecasting Model Mining Based on Gene Expression Programming

准确、及时的中长期负荷预测对于制定经济合理的电力分配方案具有十分重要的意义。传统基于统计和人工智能的电力负荷预测算法存在计算效率低、预测准确率不高的问题。文章结合基因表达式编程的思想,提出基于基因表达式编程的中长期电力负荷预测算法(Mid-long Term Load Forecasting Model Mining based on Gene Expression Programming,LFMM-GEP)。在标准EUNITE数据集上的仿真实验结果表明,文章提出的LFMM-GEP算法在MAE和MAPE以及预测精度上,要优于传统的其他人工智能和统计方法。

Accurate,timely mid-long term load forecasting is of great significance for formulating economical and reasonable power distribution schemes.Traditional power load forecasting algorithms based on statistics and artificial intelligence have low calculation efficiency and low prediction accuracy.This paper proposes a mid-long term load forecasting model mining algorithm based on gene expression programming(LFMM-GEP).Experimental results on the standard EUNITE dataset show that the proposed LFMM-GEP algorithm is superior to other traditional artificial intelligence and statistical methods in terms of MAE,MAPE and prediction accuracy.