Day-Ahead Electricity Price Forecasting Strategy Based on Machine Learning and Optimization Algorithm

被引:0
作者
Sun, Caixin [1 ]
Pan, Xiaofeng [1 ]
Li, Gang [2 ]
Li, Pengfei [3 ]
Gao, Guoqing [4 ]
Tian, Ye [2 ]
Xu, Gesheng [5 ]
机构
[1] Huaneng Clean Energy Res Inst, Beijing, Peoples R China
[2] Huaneng Grp Co Ltd, Shanxi Branch, Taiyuan, Peoples R China
[3] Huaneng Shanxi Power Supply Co Ltd, Taiyuan, Peoples R China
[4] Huaneng Shanghai Renewable Corp Co Ltd, Shanghai, Peoples R China
[5] Xian FPA Energy Technol Co Ltd, Xian, Peoples R China
来源
2022 4TH ASIA ENERGY AND ELECTRICAL ENGINEERING SYMPOSIUM (AEEES 2022) | 2022年
关键词
system load rate; electricity price forecast; machine learning; optimization algorithm; REGRESSION;
D O I
10.1109/AEEES54426.2022.9759695
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Electric power marketization is the product of the continuous development of the current electric power system. Day-ahead electricity price plays an important role in power market, so the prediction of day-ahead electricity price becomes very important. In this paper, the load rate of the system is introduced, and the machine learning algorithm is adopted. In addition, the improvement and expansion of the machine learning algorithm are realized by combining the tuning advantage of the bionic optimization algorithm, and then the accurate prediction of day-ahead electricity price is realized. The results show that this strategy algorithm can greatly improve the accuracy of day-ahead electricity price forecasting.
引用
收藏
页码:254 / 259
页数:6
相关论文
共 13 条
[1]   Day-ahead industrial load forecasting for electric RTG cranes [J].
Alasali, Feras ;
Haben, Stephen ;
Becerra, Victor ;
Holderbaum, William .
JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, 2018, 6 (02) :223-234
[2]   Application of a new hybrid neuro-evolutionary system for day-ahead price forecasting of electricity markets [J].
Amjady, Nima ;
Keynia, Farshid .
APPLIED SOFT COMPUTING, 2010, 10 (03) :784-792
[3]   Day-ahead price forecasting of electricity markets by a new feature selection algorithm and cascaded neural network technique [J].
Amjady, Nima ;
Keynia, Farshid .
ENERGY CONVERSION AND MANAGEMENT, 2009, 50 (12) :2976-2982
[4]  
Jun D, 2008, J CENT SOUTH UNIV T, V15, P316
[5]   Month ahead average daily electricity price profile forecasting based on a hybrid nonlinear regression and SVM model: an ERCOT case study [J].
Ma, Ziming ;
Zhong, Haiwang ;
Xie, Le ;
Xia, Qing ;
Kang, Chongqing .
JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, 2018, 6 (02) :281-291
[6]   Electricity price forecasting using generalized regression neural network based on principal components analysis [J].
Niu Dong-xiao ;
Liu Da ;
Xing Mian .
JOURNAL OF CENTRAL SOUTH UNIVERSITY OF TECHNOLOGY, 2008, 15 (Suppl 2) :316-320
[7]  
Song H., 2012, J GREY SYST-UK, V14, P351
[8]   Electricity price short-term forecasting using artificial neural networks [J].
Szkuta, BR ;
Sanabria, LA ;
Dillon, TS .
IEEE TRANSACTIONS ON POWER SYSTEMS, 1999, 14 (03) :851-857
[9]  
Tan Z., 2010, J CHINAS ELECTRICITY, V30, P103
[10]  
Wang R., 2018, P 4 INT C SOCIAL SCI, V181