Toward high-resolution projection of electricity prices: A machine learning approach to quantifying the effects of high fuel and CO2 prices

被引:4
作者
Madadkhani, Shiva [1 ,3 ]
Ikonnikova, Svetlana [2 ,3 ]
机构
[1] Munich Data Sci Inst MDSI, Walther von Dyck Str 10, D-85748 Garching, Germany
[2] Univ Texas Austin, Ctr Energy Econ, Bur Econ Geol, 10100 Burnet Ra, Bldg 130, Austin, TX 78758 USA
[3] Tech Univ Munich, Ctr Energy Markets, TUM Sch Management, Arcissstr 21, D-80333 Munich, Germany
关键词
Electricity price forecasting; Machine learning; Feature selection; Scenario analysis; VARIABLE IMPORTANCE; BIG DATA; SELECTION; REGRESSION; ECONOMETRICS; GENERATION; MODELS; IMPACT; STATE; CLASSIFICATION;
D O I
10.1016/j.eneco.2023.107241
中图分类号
F [经济];
学科分类号
02 ;
摘要
The growing share of renewables, the retirement of coal generation, and the increasing significance (and price) of carbon emissions continue to reshape electricity market dynamics. Ongoing power sector transformations, along with recurrent energy price shocks, bring new challenges to electricity price prediction and projection. Adept at capturing nonlinear and time-varying dynamics of the power market, machine learning (ML) methods can significantly enhance modeling and projection capabilities. This paper leverages ML modeling to (1) analyze the day-ahead electricity price dynamics and (2) develop future price projections under varying market conditions. First, we offer a methodology for identifying and ranking the factors determining day-ahead power price behavior. Guided by the understanding of power price drivers, we then develop an ensemble ML model for highresolution (i.e., for each day of the next year) electricity price projection. Hence, the first part of our analysis helps relate fundamental modeling approaches to ML studies, and the second part extends the existing literature, which is limited to high aggregation level (e.g., yearly basis) projections. High-resolution projections provide valuable insights into within-year price dynamics and help answer highly debated questions raised by the growing share of renewables and the current energy market turmoil. We demonstrate our methodology on the German power market, using data on 80 explanatory variables from 2015 to 2021. We identify the most critical power price drivers and develop an ML model to study the within-year impact of high fuel and carbon prices. Our findings indicate that the often-neglected interaction variables may significantly impact price projections and should be included in day-ahead electricity price modeling. We confirm the efficacy of our approach with a forecasting exercise based on day-ahead electricity prices in the first two quarters of 2022.
引用
收藏
页数:18
相关论文
共 50 条
[21]   Unravelling CO2 Reduction Reaction Intermediates on High Entropy Alloy Catalysts: An Interpretable Machine Learning Approach To Establish Scaling Relations [J].
Roy, Diptendu ;
Mandal, Shyama Charan ;
Das, Amitabha ;
Pathak, Biswarup .
CHEMISTRY-A EUROPEAN JOURNAL, 2024, 30 (06)
[22]   High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model [J].
Bai, Xuefeng ;
Li, Yi ;
Xie, Yabo ;
Chen, Qiancheng ;
Zhang, Xin ;
Li, Jian-Rong .
GREEN ENERGY & ENVIRONMENT, 2025, 10 (01) :132-138
[23]   High-Resolution Vegetation Mapping in Japan by Combining Sentinel-2 and Landsat 8 Based Multi-Temporal Datasets through Machine Learning and Cross-Validation Approach [J].
Sharma, Ram C. ;
Hara, Keitarou ;
Tateishi, Ryutaro .
LAND, 2017, 6 (03)
[24]   Reconstructing the exit wave of 2D materials in high-resolution transmission electron microscopy using machine learning [J].
Larsen, Matthew Helmi Leth ;
Dahl, Frederik ;
Hansen, Lars P. ;
Barton, Bastian ;
Kisielowski, Christian ;
Helveg, Stig ;
Winther, Ole ;
Hansen, Thomas W. ;
Schiotz, Jakob .
ULTRAMICROSCOPY, 2023, 243
[25]   Capturing the net ecosystem CO2 exchange dynamics of tidal wetlands with high spatiotemporal resolution by integrating process-based and machine learning estimations [J].
Lu, Yuqiu ;
Huang, Ying ;
Jia, Qingyu ;
Xie, Yebing .
AGRICULTURAL AND FOREST METEOROLOGY, 2024, 352
[26]   Identification of on-road vehicle CO2 emission pattern in China: A study based on a high-resolution emission inventory [J].
Xu, Yanling ;
Liu, Zeyuan ;
Xue, Wenbo ;
Yan, Gang ;
Shi, Xurong ;
Zhao, Dadi ;
Zhang, Yu ;
Lei, Yu ;
Wang, Jinnan .
RESOURCES CONSERVATION AND RECYCLING, 2021, 175
[27]   Defect Dynamics in 2-D MoS2 Probed by Using Machine Learning, Atomistic Simulations, and High-Resolution Microscopy [J].
Patra, Tarak K. ;
Zhang, Fu ;
Schulman, Daniel S. ;
Chan, Henry ;
Cherukara, Mathew J. ;
Terrones, Mauricio ;
Das, Saptarshi ;
Narayanan, Badri ;
Sankaranarayanan, Subramanian K. R. S. .
ACS NANO, 2018, 12 (08) :8006-8016
[28]   A High-Resolution Earth Observations and Machine Learning-Based Approach to Forecast Waterborne Disease Risk in Post-Disaster Settings [J].
Nusrat, Farah ;
Haque, Musad ;
Rollend, Derek ;
Christie, Gordon ;
Akanda, Ali S. .
CLIMATE, 2022, 10 (04)
[29]   Machine Learning Approach to Assess Rubber Plant Health Through Canopy Density Mapping Using Very High-Resolution Aerial Photographs [J].
Ayu, Farida ;
Manessa, Masita Dwi Mandini ;
Stevanus, Charlos Togi ;
Efriana, Anisya Feby .
EIGHTH GEOINFORMATION SCIENCE SYMPOSIUM 2023: GEOINFORMATION SCIENCE FOR SUSTAINABLE PLANET, 2024, 12977
[30]   An extensive investigation on leveraging machine learning techniques for high-precision predictive modeling of CO2 emission [J].
Nguyen, Van Giao ;
Duong, Xuan Quang ;
Nguyen, Lan Huong ;
Nguyen, Phuoc Quy Phong ;
Priya, Jayabal Chandra ;
Truong, Thanh Hai ;
Le, Huu Cuong ;
Pham, Nguyen Dang Khoa ;
Nguyen, Xuan Phuong .
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2023, 45 (03) :9149-9177