Abstract
With the deepening of China’s electricity spot market construction, spot market price prediction is the basis for making reasonable quotation strategies. This paper proposes a day-ahead spot market price forecast based on a hybrid extreme learning machine technology. Firstly, the trading center’s information is examined using the Spearman correlation coefficient to eliminate characteristics that have a weak link with the price of power. Secondly, a similar day-screening model with weighted grey correlation degree is constructed based on the grey correlation theory (GRA) to exclude superfluous samples. Thirdly, the regularized limit learning machine (RELM) is tuned using the Marine Predators Algorithm (MPA) to increase RELM parameter accuracy. Finally, the proposed forecasting model is applied to the Shanxi spot market, and other forecasting models and error computation methodologies are compared. The results demonstrate that the model suggested in this paper has a specific forecasting effect for power price forecasting technology.
Subject
Management, Monitoring, Policy and Law,Renewable Energy, Sustainability and the Environment,Geography, Planning and Development,Building and Construction
Reference62 articles.
1. Particle swarm optimization GM(1,2) short-term electricity price prediction method with error correction;Wang;Power Syst. Prot. and Contr.,2011
2. A new method of ARIMA electricity price forecast with error forecast correction;Zhou;Chin. J. Elec. Eng.,2004
3. Short-Term Electricity Prices Forecasting Using Functional Time Series Analysis
4. Prediction of spot electricity price based on ARIMA-GARCH model;Liu;Energy Technol. Econ.,2012
5. Forecasting electricity prices with expert, linear, and nonlinear models
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献