基于ISSA优化EEMD的用户侧电力负荷预测方法  

User side power load forecasting method based on ISSA optimized EEMD

作　　者：石文娟 凌凡 张俊权 宋振世 李力 SHI Wen-juan;LING Fan;ZHANG Jun-quan;SONG Zhen-shi;LI Li(Beijing China-Power Information Technology Company Limited,Beijing 100085,China)

机构地区：[1]北京中电普华信息技术有限公司,北京100085

出　　处：《信息技术》2025年第2期97-103,共7页Information Technology

摘　　要：为减少负荷预测结果误差,提出基于混合改进麻雀搜索算法(ISSA)优化集合经验模态分解(EEMD)的电力负荷预测方法。获取用户历史用电信息,通过奇异值分解算法去除噪声数据,并利用差分自回归滑动平均模型完成平滑处理。针对集合经验模态分解所需的参数建立优化目标函数,依托于ISSA算法求出最优参数组合。通过分析历史电力负荷数据,将其输入基于广义回归神经网络的预测模型,输出电力负荷预测值。实验结果表明:所提方法预测结果的相对误差控制在0.1以下,可满足用户侧电力负荷预测要求。To reduce the error of load forecasting results,a power load forecasting method based on the hybrid Improved Sparrow Search Algorithm(ISSA)optimized Ensemble Empirical Mode Decomposition(EEMD)is proposed.User historical electricity consumption information is obtained,and the noise data is removed through singular value decomposition algorithm,and the differential autoregressive moving average model is used to complete smoothing processing.An optimization objective function is established for the parameters required for ensemble empirical mode decomposition,and based on the ISSA algorithm,the optimal parameter combination is found.Historical power load data is analyzed,which is inputted it into a prediction model based on generalized regression neural network,and output power load prediction values.The experiment results show that the relative error of the proposed method’s prediction results is controlled below 0.1,which meets the requirements of user side power load prediction.

关 键 词：ISSA 集合经验模态分解 用户侧 负荷 参数优化 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]