基于Copula函数与多目标进化算法的负荷区间预测

Interval prediction of load based on Copula function and multi-objective evolutionary algorithm

与点预测相比,负荷区间预测可提供预测上界与下界,更有助于电力系统的稳定运行。针对未充分利用相邻负荷序列之间的相关关系而导致预测精度较低的问题,提出一种基于Copula函数与分解的多目标进化算法(MOEA/D)的负荷区间预测方法。该方法通过建立Copula函数,挖掘相邻负荷序列之间的相关性,利用MOEA/D寻找Pareto最优解集,并通过熵权法与优劣解距离法(TOPSIS),得到最优的预测模型参数与预测结果。最后,将该方法应用于某地区的负荷预测,并与常用的区间预测方法进行对比,结果表明该方法具有更好的预测效果。

Compared with the point prediction,the load interval prediction can provide the upper and lower bounds of the prediction value,which is more conducive to the stable operation of the power system.Aiming at the problem that the correlation between adjacent load sequences is not fully utilized,thereby reducing the prediction accuracy,a load interval prediction method based on Copula function and the multi-objective evolutionary algorithm based on decomposition(MOEA/D)is proposed.This method makes full use of the correlation between adjacent load sequences by establishing a Copula function.The MOEA/D multi-objective optimization algorithm is used to find the Pareto optimal solution set,and through entropy weight method and technique for order preference by similarity to ideal solution(TOPSIS),the optimal prediction model parameters and the prediction results are obtained.Finally,this method is applied to load forecasting for a certain area,and compared with commonly used interval forecasting methods.The results show that this method has better forecasting effect.