基于WPA-Prophet模型的区域用电量预测
Prediction of Regional Electricity Consumption Based on WPA-Prophet Model
谭曾盛 1王志兵1
作者信息
- 1. 湖南工业大学 计算机学院,湖南 株洲 412007
- 折叠
摘要
为了获得精度更高的用电量预测模型,采用狼群算法对Prophet模型的关键参数进行寻优,构建基于WPA优化Prophet的用电量预测模型.实验数据为澳大利亚维多利亚州 2015-2019 年五年的日用电量,使用前四年作为测试集,最后一年验证预测结果的准确性,预测结果的评价指标采用均方根误差和平均绝对百分比误差.实验结果表明,通过WPA优化后的Prophet模型预测精度得到了有效提升,为提升区域用电量预测精度提供了参考.
Abstract
In order to obtain a more accurate electricity consumption prediction model,Wolf Pack Algorithm(WPA)is used to optimize key parameters of the Prophet model,and an optimized electricity consumption prediction model is built based on WPA.The experimental data is the daily electricity consumption of Victoria,Australia from 2015 to 2019.The data of first four years are used as the test set,and the accuracy of the prediction results is verified in the last year.The evaluation indexes of the prediction results are Root-Mean-Square Error and Mean Absolute Percentage Error.The experimental results show that the prediction accuracy of Prophet model optimized by WPA algorithm has been effectively improved,which provides a reference for improving the prediction accuracy of regional electricity consumption.
关键词
Prophet模型/狼群算法/用电量预测/时间序列Key words
Prophet model/Wolf Pack Algorithm/electricity consumption prediction/time series引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据