SUN Yue,HONG Yicheng,LIU Xin,et al.Application of SARIMA - SVR hybrid model in electricity revenue forecasting[J].Journal of Yanbian University,2021,47(04):324-328.
SARIMA - SVR混合模型在电费收入预测中的应用
- Title:
- Application of SARIMA - SVR hybrid model in electricity revenue forecasting
- 文章编号:
- 1004-4353(2021)04-0324-05
- 关键词:
- 电费收入预测; SARIMA - SVR; 混合模型; 支持向量机; 残差分析
- Keywords:
- electricity revenue forecast; SARIMA - SVR; hybrid model; support vector machine; residual analysis
- 分类号:
- N32
- 文献标志码:
- A
- 摘要:
- 针对SARIMA模型和SVR模型在预测电费收入数据时因存在线性因素和非线性因素所产生的难以精准预测的问题,提出一种将SARIMA和SVR相结合的SARIMA - SVR混合模型.利用延边供电公司的月电费收入数据对SARIMA - SVR混合模型的有效性进行验证显示, SARIMA - SVR混合模型的平均绝对百分比误差比SARIMA模型和SVR模型分别低了13.50%和73.75%.该结果表明SARIMA - SVR混合模型对电费收入数据具有较好的预测效果.
- Abstract:
- Aiming at the difficulty of accurate prediction caused by linear and nonlinear factors when SARIMA model and SVR model forecast electricity revenue data, a SARIMA - SVR hybrid model combining SARIMA and SVR was proposed.The validity of the SARIMA - SVR hybrid model was verified by using the monthly electricity revenue data of Yanbian Power Supply Company.The results show that the average absolute percentage error of SARIMA - SVR model is 13.50% lower than that of SARIMA model and 73.75% lower than that of SVR model.The results show that SARIMA - SVR hybrid model has a good prediction effect on electricity income data.
参考文献/References:
[1] 曹家伟.供电企业电费回收管理方法研究[D].青岛:青岛大学,2016.
[2] 刘东东,胡少柔,陈荣腾.基于大数据技术的电费回收研究[J].江苏科技信息,2016(27):55 - 56.
[3] MEMARZADEH G, KEYNIA F.Short - term electricity load and price forecasting by a new optimal LSTM - NN based prediction algorithm[J].Electric Power Systems Research, 2021,192:106995.
[4] 胡泽月.基于ARIMA模型的企业自由现金流预测研究[D].石家庄:河北经贸大学,2021.
[5] 范恒瑞,任黎秀.ARIMA与指数平滑法在江苏省GDP预测中的应用[J].江西农业学报,2011,23(2):187 - 189.
[6] 刘松,张帅.运用ARIMA模型对股价预测的实证研究[J].经济研究导刊,2021(25):76 - 78.
[7] AL - MUSAYLH M S, DEO R C, ADAMOWSKI J F, et al.Short - term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia[J].Advanced Engineering Informatics, 2018,35:1 - 16.
[8] 张远汀,龚伟伟,叶钰,等.应用机器学习技术预测强雨雪天气过程中的积雪[J].科学技术与工程,2019,19(15):58 - 69.
[9] LI W, BECKER D M.Day - ahead electricity price prediction applying hybrid models of LSTM - based deep learning methods and feature selection algorithms under consideration of market coupling[J].Energy, 2021,237:121543.
[10] 王振,高茂庭.基于卷积神经网络的图像识别算法设计与实现[J].现代计算机(专业版),2015(20):61 - 66.
[11] 王燕.应用时间序列分析[M].北京:中国人民大学出版社,2015.
[12] 周志华.机器学习[M].北京:清华大学出版社,2016.
备注/Memo
收稿日期: 2021-09-17
基金项目: 延边大学横向项目(20210051)
第一作者: 孙越(1997—),女,在读硕士,研究方向为应用统计.
通信作者: 郑雪燕(1989—),女,硕士,讲师,研究方向为时间系列分析、数据挖掘.