摘要
为了提高电力系统短期负荷预测的准确性,本文提出了基于改进随机森林算法的电力系统短期负荷预测模型。改进随机森林算法是将随机森林算法中的决策树数量和分裂特征数等参数采用粒子群进行优化,通过比较每组参数对应的随机森林袋外数据误差,获取参数最优值,使随机森林算法的性能得到最优,并采用山东省某城市电网的历史负荷数据进行仿真分析。仿真结果表明,与基于传统随机森林算法的预测模型相比,本文所提出的预测模型的平均绝对误差降低0.81%,最大相对误差降低1.89%,说明本文所提出的基于改进随机森林算法的短期负荷预测模型具有更好的预测性能。该研究具有一定的工程实用性。
In order to improve the accuracy of power system short-term load forecasting,this paper proposes a short-term load forecasting model based on improved random forest algorithm.The improved random forest algorithm is to optimize the parameters such as the number of decision trees and the number of splitting features in the random forest algorithm by using particle swarm optimization.By comparing the errors of the data outside the bag corresponding to each group of parameters,the optimal values of parameters are obtained,so that the performance of the random forest algorithm is optimized,and the historical load data of a city power grid in Shandong Province is used for simulation analysis.The simulation results show that the average absolute error and the maximum relative error of the forecasting model proposed in this paper are reduced by 0.81%and 1.89%respectively,compared with the traditional random forest algorithm,which shows that the short-term load forecasting model based on the improved random forest algorithm proposed in this paper has better forecasting performance.The model has certain engineering practicability.
作者
邢书豪
孙文慧
颜勇
张智晟
XING Shuhao;SUN Wenhui;YAN Yong;ZHANG Zhisheng(College of Electrical Engineering,Qingdao University,Qingdao 266071,China;Qingdao Metro Group Co.,Ltd.,Qingdao 266000,China;State Grid Shandong Integrated Energy Service Co.,Ltd.,Jinan 255000,China)
出处
《青岛大学学报（工程技术版）》
CAS
2019年第3期7-10,38,共5页
Journal of Qingdao University(Engineering & Technology Edition)
基金
国家自然科学基金资助项目(51477078)
智能电网教育部重点实验室开放研究基金(2018)
关键词
改进随机森林算法
粒子群优化算法
短期负荷预测
电力系统
improved random forest algorithm
particle swarm optimization
short-term load forecasting
power system
