基于Tent-ASO-BP的短期电力负荷预测模型  

Short⁃term power load forecasting model based on Tent⁃ASO⁃BP

作　　者：邓磊刚 赵号 孙宗阳 DENG Leigang;ZHAO Hao;SUN Zongyang(Aviation Industry Corporation of China Xi’an Aviation Computing Technology Research Institute,Xi’an 710076,China)

机构地区：[1]中国航空工业集团公司西安航空计算技术研究所,陕西西安710076

出　　处：《电子设计工程》2024年第11期164-168,共5页Electronic Design Engineering

基　　金：陕西省自然科学基金研究计划项目(2022JQ-564)。

摘　　要：针对短期电力负荷预测精度低与可靠性差的问题,设计一种基于Tent-ASO-BP的电力短期负荷预测模型。该模型利用了Tent混沌映射的方法,设计了一种原子种群初始化方法,其在保证个体的同时选出适应度最优的个体,增强原子种群在分布空间的均匀性,进而加快ASO算法的收敛;同时引入自适应,增加该算法的局部探索和开发能力;将改进的ASO算法应用于BP神经网络参数优化,搭建了Tent-ASO-BP预测模型对短期电力负荷进行预测。使用Matlab工具进行仿真,通过对Tent-ASO-BP、ASO-BP和BP三种算法进行实验对比,结果表明,Tent-ASO-BP网络预测模型的RMSE、MAE和MAPE分别为32.736 MW,51.783 MW和6.623%,相比于ASO-BP和BP网络预测模型有明显减少,得出该模型具有更强的迭代能力和更强的局部寻优能力,为电力系统短期电力负荷预测提供依据,具有普遍的指导意义。Aiming at the problem of low accuracy and poor reliability of short⁃term power load forecasting,a short⁃term power load forecasting model based on Tent⁃ASO⁃BP is designed.This model uses the method of Tent chaos mapping to design an atomic population initialization method,which ensures individuals and selects individuals with the best fitness to enhance the uniformity of atomic populations in the distribution space,thereby accelerating the convergence of ASO algorithm.At the same time,adaptive is introduced to increase the local exploration and development capabilities of the algorithm.The improved ASO algorithm is applied to BP neural network parameter optimization,and the Tent⁃ASO⁃BP prediction model is built to predict short⁃term power load.Using Matlab tools for simulation,through experimental comparison of Tent⁃ASO⁃BP,ASO⁃BP and BP algorithms,the results show that the RMSE,MAE and MAPE of Tent⁃ASO⁃BP network prediction model are 32.736 MW,51.783 MW and 6.623%,respectively,which are significantly reduced compared with ASO⁃BP and BP network prediction models,and the model has stronger iterative ability and stronger local optimization ability.It provides a basis for short⁃term power load prediction of power system and has general guiding significance.

关 键 词：短期电力预测 Tent混沌映射 原子搜索算法Tent-ASO-BP 自适应 MATLAB仿真 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]