基于改进随机森林算法的短期负荷预测研究  

Study on Short-term Load Forecasting Based on Improved Random Forest Algorithm

作　　者：陈逸飞 薛军伟 邱俊 Chen Yifei;Xue Junwei;Qiu Jun(School of Electrical and Control Engineering,Liaoning Technical University,Huludao Liaoning 125000,China)

机构地区：[1]辽宁工程技术大学电气与控制工程学院,辽宁葫芦岛125000

出　　处：《现代工业经济和信息化》2024年第4期218-220,225,共4页Modern Industrial Economy and Informationization

摘　　要：针对电力系统短期负荷预测精度低的特点,提出了一种基于麻雀优化算法的改进随机森林回归预测模型。利用SSA优化算法不断迭代优化RFR的决策树数量和节点分列等相关参数,提高RFR的预测性能,得到SSA-RFR回归预测模型。为验证模型在预测精度上的优良性,利用中国某地区电力负荷历史数据进行数据仿真,将未改进的模型与改进后的模型的预测结果进行对比。对比结果表明,提出的改进模型具有更优良的预测精度,与实际值更为接近。Aiming at the low accuracy of short-term load forecasting in the power system,an improved Random Forest Regression Forecasting(RFRF)model based on the Sparrow Optimisation Algorithm is proposed.Firstly,the SSA optimization algorithm is used to iteratively optimize the relevant parameters such as the number of decision trees and node disaggregation of RFR to improve the forecasting performance of RFR,and the SSA-RFR regression forecasting model is obtained.In order to verify the model's excellence in prediction accuracy,data simulation is carried out using historical data of power load in a region of China,and the prediction results of the unimproved model are compared with those of the improved model,and the results show that the improved model proposed in this paper has a much better prediction accuracy,which is closer to the actual value.

关 键 词：电力系统 短期负荷预测 随机森林 麻雀优化算法 迭代优化 

分 类 号：TM715[电气工程—电力系统及自动化]