Application of Extreme Learning Machine- Autoencoder to Medium Term Electricity Price Forecasting

被引:4
作者
Najafi, Arsalan [1 ]
Homaee, Omid [1 ]
Golshan, Mehdi [2 ]
Jasinski, Michal [1 ,3 ]
Leonowicz, Zbigniew [1 ,3 ]
机构
[1] Wroclaw Univ Sci & Technol, Fac Elect Engn, Dept Elect Engn Fundamentals, PL-50370 Wroclaw, Poland
[2] Islamic Azad Univ, Dept Comp Engn, Sepidan Branch, Sepidan 1477893855, Iran
[3] VSB Tech Univ Ostrava, Fac Elect Engn & Comp Sci, Dept Elect Power Engn, Ostrava 70800, Czech Republic
关键词
Forecasting; electricity price; extreme learning machine; autoencoder; electricity market;
D O I
10.1109/TIA.2023.3303866
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Electricity market prices are highly volatile, highly frequent, non-linear, and non-stationary which makes forecasting very complicated. Although accurate forecasting plays a crucial role in the electricity market for traders, retailers, large consumers as well as generation companies in terms of economic efficiency and power systems safety. Hence, this article proposes a new forecasting approach for medium-term electricity market prices based on an extreme learning machine-autoencoder (ELM-AE). The main idea behind this is to use trained weights for hidden layers instead of randomly generated weights. The input hidden layer weights are obtained by solving a network with the same input outputs by the autoencoder method. Then, the obtained output weights are used again as the input weights for a new ELM network. To do so, a data-set is created using input data, where the ahead 24 hours are forecasted based on the previous 168 data. The simulations have been performed on New York Independent System Operator prices and compared with the classic ELM demonstrating the high accuracy of the proposed method in both training and testing.
引用
收藏
页码:7214 / 7223
页数:10
相关论文
共 34 条
  • [1] Afrasiabi M., 2022, Electric Power Syst. Res., V213
  • [2] Day-ahead price forecasting of electricity markets by a new fuzzy neural network
    Amjady, N
    [J]. IEEE TRANSACTIONS ON POWER SYSTEMS, 2006, 21 (02) : 887 - 896
  • [3] Electricity Price Forecasting for Operational Scheduling of Behind-the-Meter Storage Systems
    Chitsaz, Hamed
    Zamani-Dehkordi, Payam
    Zareipour, Hamidreza
    Parikh, Palak P.
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2018, 9 (06) : 6612 - 6622
  • [4] Do jumps and cojumps matter for electricity price forecasting? Evidence from the German-Austrian day-ahead market
    Ciarreta, Aitor
    Muniain, Peru
    Zarraga, Ainhoa
    [J]. ELECTRIC POWER SYSTEMS RESEARCH, 2022, 212
  • [5] Forecasting electricity prices for a day-ahead pool-based electric energy market
    Conejo, AJ
    Contreras, J
    Espínola, R
    Plazas, MA
    [J]. INTERNATIONAL JOURNAL OF FORECASTING, 2005, 21 (03) : 435 - 462
  • [6] Conejo AJ, 2010, INT SER OPER RES MAN, V153, P1, DOI 10.1007/978-1-4419-7421-1
  • [7] Short-term electricity price forecast based on the improved hybrid model
    Dong, Yao
    Wang, Jianzhou
    Jiang, He
    Wu, Jie
    [J]. ENERGY CONVERSION AND MANAGEMENT, 2011, 52 (8-9) : 2987 - 2995
  • [8] Hybrid Local General Regression Neural Network and Harmony Search Algorithm for Electricity Price Forecasting
    Elattar, Ehab E.
    Elsayed, Salah K.
    Farrag, Tamer Ahmed
    [J]. IEEE ACCESS, 2021, 9 : 2044 - 2054
  • [9] Mid-term electricity demand forecasting using improved variational mode decomposition and extreme learning machine optimized by sparrow search algorithm
    Gao, Tian
    Niu, Dongxiao
    Ji, Zhengsen
    Sun, Lijie
    [J]. ENERGY, 2022, 261
  • [10] Brain tumour detection in magnetic resonance imaging using Levenberg-Marquardt backpropagation neural network
    Ghahramani, Marzieh
    Shiri, Nabiollah
    [J]. IET IMAGE PROCESSING, 2023, 17 (01) : 88 - 103