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 50 条
  • [1] Electricity price forecasting on the day-ahead market using machine learning
    Tschora, Leonard
    Pierre, Erwan
    Plantevit, Marc
    Robardet, Celine
    APPLIED ENERGY, 2022, 313
  • [2] Day-ahead price forecasting based on hybrid prediction model
    Olamaee, Javad
    Mohammadi, Mohsen
    Noruzi, Alireza
    Hosseini, Seyed Mohammad Hassan
    COMPLEXITY, 2016, 21 (S2) : 156 - 164
  • [3] Day-Ahead Forecasting for the Tropics with Numerical Weather Prediction and Machine Learning
    Ng, Nigel Yuan Yun
    Gopalan, Harish
    Raghavan, Venugopalan S. G.
    Ooi, Chin Chun
    2022 17TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV), 2022, : 125 - 130
  • [4] Day-Ahead Prediction of Microgrid Electricity Demand Using a Hybrid Artificial Intelligence Model
    Ma, Yuan-Jia
    Zhai, Ming-Yue
    PROCESSES, 2019, 7 (06):
  • [5] An adaptive hybrid model for day-ahead photovoltaic output power prediction
    Zhang, Jinliang
    Tan, Zhongfu
    Wei, Yiming
    JOURNAL OF CLEANER PRODUCTION, 2020, 244
  • [6] An integrated machine learning model for day-ahead electricity price forecasting
    Fan, Shu
    Liao, James R.
    Kaneko, Kazuhiro
    Chen, Luonan
    2006 IEEE/PES POWER SYSTEMS CONFERENCE AND EXPOSITION. VOLS 1-5, 2006, : 1643 - +
  • [7] Electric vehicles load forecasting for day-ahead market participation using machine and deep learning methods
    Bampos, Zafeirios N.
    Laitsos, Vasilis M.
    Afentoulis, Konstantinos D.
    Vagropoulos, Stylianos I.
    Biskas, Pantelis N.
    APPLIED ENERGY, 2024, 360
  • [8] Forecasting Day-ahead Solar Radiation Using Machine Learning Approach
    Hassan, M. Z.
    Ali, K. M. E.
    Ali, A. B. M. Shawkat
    Kumar, Jashnil
    2017 4TH ASIA-PACIFIC WORLD CONGRESS ON COMPUTER SCIENCE AND ENGINEERING (APWCONCSE 2017), 2017, : 252 - 258
  • [9] A Hybrid Model for Day-Ahead Price Forecasting
    Wu, Lei
    Shahidehpour, Mohammad
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2010, 25 (03) : 1519 - 1530
  • [10] Day-Ahead Spot Market Price Forecast Based on a Hybrid Extreme Learning Machine Technique: A Case Study in China
    Dong, Jun
    Dou, Xihao
    Bao, Aruhan
    Zhang, Yaoyu
    Liu, Dongran
    SUSTAINABILITY, 2022, 14 (13)