Dealing with Anomalies in Day-Ahead Market Prediction Using Machine Learning Hybrid Model

被引:0
作者
Pilot, Karol [1 ]
Ganczarek-Gamrot, Alicja [1 ]
Kania, Krzysztof [1 ]
机构
[1] Univ Econ Katowice, Fac Informat & Commun, PL-40287 Katowice, Poland
关键词
prediction; energy market; anomalies; hybrid models; ELECTRICITY PRICES; RANDOM FOREST; JUMP-DIFFUSION; FORECAST; SPIKES; LOAD; MANAGEMENT; ERROR;
D O I
10.3390/en17174436
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Forecasting the electricity market, even in the short term, is a difficult task, due to the nature of this commodity, the lack of storage capacity, and the multiplicity and volatility of factors that influence its price. The sensitivity of the market results in the appearance of anomalies in the market, during which forecasting models often break down. The aim of this paper is to present the possibility of using hybrid machine learning models to forecast the price of electricity, especially when such events occur. It includes the automatic detection of anomalies using three different switch types and two independent forecasting models, one for use during periods of stable markets and the other during periods of anomalies. The results of empirical tests conducted on data from the Polish energy market showed that the proposed solution improves the overall quality of prediction compared to using each model separately and significantly improves the quality of prediction during anomaly periods.
引用
收藏
页数:20
相关论文
共 89 条
  • [1] A novel hybrid model to forecast seasonal and chaotic time series
    Abbasimehr, Hossein
    Behboodi, Amirreza
    Bahrini, Aram
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 239
  • [2] Global factors, uncertainty, weather conditions and energy prices: On the drivers of the duration of commodity price cycle phases
    Agnello, Luca
    Castro, Vitor
    Hammoudeh, Shawkat
    Sousa, Ricardo M.
    [J]. ENERGY ECONOMICS, 2020, 90
  • [3] Best-Practice Recommendations for Defining, Identifying, and Handling Outliers
    Aguinis, Herman
    Gottfredson, Ryan K.
    Joo, Harry
    [J]. ORGANIZATIONAL RESEARCH METHODS, 2013, 16 (02) : 270 - 301
  • [4] Nonlinear autoregressive and random forest approaches to forecasting electricity load for utility energy management systems
    Ahmad, Tanveer
    Chen, Huanxin
    [J]. SUSTAINABLE CITIES AND SOCIETY, 2019, 45 : 460 - 473
  • [5] Aimal Syeda, 2019, Web, Artificial Intelligence and Network Applications. Proceedings of the Workshops of the 33rd International Conference on Advanced Information Networking and Applications (WAINA-2019). Advances in Intelligent Systems and Computing (AISC 927), P592, DOI 10.1007/978-3-030-15035-8_57
  • [6] Ali M, 2019, PAL CIBFR ST ISLAM F, P79, DOI [10.1109/ITT48889.2019.9075063, 10.1007/978-3-319-96613-7_7]
  • [7] Amjady N., 2017, Electric Power Systems: Advanced Forecasting Techniques and Optimal Generation Scheduling
  • [8] Day ahead price forecasting of electricity markets by a mixed data model and hybrid forecast method
    Amjady, Nima
    Keynia, Farshid
    [J]. INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2008, 30 (09) : 533 - 546
  • [9] A Multi-Stage Price Forecasting Model for Day-Ahead Electricity Markets
    Angamuthu Chinnathambi, Radhakrishnan
    Mukherjee, Anupam
    Campion, Mitch
    Salehfar, Hossein
    Hansen, Timothy M.
    Lin, Jeremy
    Ranganathan, Prakash
    [J]. FORECASTING, 2019, 1 (01): : 26 - 46
  • [10] [Anonymous], 2021, Energy Price Rise Since