Abstract
Day-ahead prediction of electricity market price is a key for market participants to make a bidding strategy. While numerous methods for day-ahead market price (DMP) forecasting have been developed and applied, those lack interpretable models for DMP forecasting. This study provides a new hybrid model for DMP forecasting, centered on eXtreme Gradient Boosting (XGBoost). The suggested proposal uses neural networks (NNs) with entity embedding (EE) to preprocess categorical feature data and applying Shapley Additive exPlanations (SHAP) to select optimal features. In addition, the weights of NNs and SHAP are interpretability methods. The embedding weights from NNs can reveal the distribution of categorical features in the multi-dimensional space by t-distributed Stochastic Neighbor Embedding (t-SNE). SHAP can explain the impact of input features on the forecast result by assessing the importance of global and local features. The proposed model has been proven to be high accuracy, interpretability and outperforms other models on the test set accuracy, including support vector machine, artificial neural works, classification and regression trees, and random forest). Furthermore, the study found that those load/capacity ratios, the historical clearing prices, penetration of renewable energy, month, hour, weekdays, and weekends have a substantial impact on the prediction of the DMP.
Similar content being viewed by others
Data Availability
All relevant data are available through this manuscript.
References
Xie K (2017) Electricity market, operation and regulation: US practical. China Electric Power Press, Beijing
Li G, Liu CC, Mattson C, Lawarrée J (2007) Day-ahead electricity price forecasting in a grid environment. IEEE Trans Power Syst 22(1):266–274. https://doi.org/10.1109/TPWRS.2006.887893
Yonghua S, Minglei B, Yi D, Changzheng S, Nan S (2020) Review of Chinese electricity spot market key Issues and its suggestions under the new round of Chinese power system reform. Zhongguo Dianji Gongcheng Xuebao/Proc Chin Soc Electr Eng 40(10):3172–3187. https://doi.org/10.13334/j.0258-8013.pcsee.191251
Kostrzewski M, Kostrzewska J (2019) Probabilistic electricity price forecasting with Bayesian stochastic volatility models. Energy Economics 80:610–620. https://doi.org/10.1016/j.eneco.2019.02.004
Uniejewski B, Marcjasz G, Weron R (2019) On the importance of the long-term seasonal component in day-ahead electricity price forecasting: part II—probabilistic forecasting. Energy Econ 79:171–182. https://doi.org/10.1016/j.eneco.2018.02.007
Lago J, De Ridder F, De Schutter B (2018) Forecasting spot electricity prices: deep learning approaches and empirical comparison of traditional algorithms. Appl Energy 221:386–405. https://doi.org/10.1016/j.apenergy.2018.02.069
Nowotarski J, Weron R (2018) Recent advances in electricity price forecasting: a review of probabilistic forecasting. Renew Sustain Energy Rev 81:1548–1568. https://doi.org/10.1016/j.rser.2017.05.234
Weron R (2014) Electricity price forecasting: A review of the state-of-the-art with a look into the future 30(4):1030–1081. https://doi.org/10.1016/j.ijforecast.2014.08.008
Lago J, De Ridder F, Vrancx P, De Schutter B (2018) Forecasting day-ahead electricity prices in Europe: the importance of considering market integration. Appl Energy 211:890–903. https://doi.org/10.1016/j.apenergy.2017.11.098
Lago J, Marcjasz G, De Schutter B, Weron R (2021) Forecasting day-ahead electricity prices: a review of state-of-the-art algorithms, best practices and an open-access benchmark. Appl Energy 293:116983. https://doi.org/10.1016/j.apenergy.2021.116983
Mousa SR, Bakhit PR, Ishak S (2019) An extreme gradient boosting method for identifying the factors contributing to crash/near-crash events: a naturalistic driving study. Can J Civ Eng. https://doi.org/10.1139/cjce-2018-0117
Agrawal RK, Muchahary F, Tripathi MM (2019) Ensemble of relevance vector machines and boosted trees for electricity price forecasting. Appl Energy 250:540–548. https://doi.org/10.1016/j.apenergy.2019.05.062
Guo C, Berkhahn F (2016) Entity embeddings of categorical variables. https://arxiv.org/abs/1604.06737
Ziel F, Steinert R, Husmann S (2015) Forecasting day ahead electricity spot prices: the impact of the EXAA to other European electricity markets. Energy Econ 51:430–444. https://doi.org/10.1016/j.eneco.2015.08.005
Yang Z, Ce L, Lian L (2017) Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods. Appl Energy 190:291–305. https://doi.org/10.1016/j.apenergy.2016.12.130
Diongue AK, Guégan D, Vignal B (2009) Forecasting electricity spot market prices with a k-factor GIGARCH process. Appl Energy 86(4):505–510. https://doi.org/10.1016/j.apenergy.2008.07.005
Nowotarski J, Weron R (2016) On the importance of the long-term seasonal component in day-ahead electricity price forecasting. Energy Econ 57:228–235. https://doi.org/10.1016/j.eneco.2016.05.009
Uniejewski B, Weron R, Ziel F (2018) Variance stabilizing transformations for electricity spot price forecasting. IEEE Trans Power Syst 33(2):2219–2229. https://doi.org/10.1109/TPWRS.2017.2734563
Weron R, Misiorek A (2008) Forecasting spot electricity prices: a comparison of parametric and semiparametric time series models. Int J Forecast 24(4):744–763. https://doi.org/10.1016/j.ijforecast.2008.08.004
Díaz G, Coto J, Gómez-Aleixandre J (2019) Prediction and explanation of the formation of the Spanish day-ahead electricity price through machine learning regression. Appl Energy 239:610–625. https://doi.org/10.1016/j.apenergy.2019.01.213
Yang Y, Dong Y, Chen Y, Li C (2014) Intelligent optimized combined model based on GARCH and SVM for forecasting electricity price of New South Wales, Australia. Abstr Appl Anal 2014:1–9. https://doi.org/10.1155/2014/504064
Shayeghi H, Ghasemi A, Moradzadeh M, Nooshyar M (2017) Day-ahead electricity price forecasting using WPT, GMI and modified LSSVM-based S-OLABC algorithm. Soft Comput 21(2):525–541. https://doi.org/10.1007/s00500-015-1807-1
Catalão JPS, Mariano SJPS, Mendes VMF, Ferreira LAFM (2007) Short-term electricity prices forecasting in a competitive market: a neural network approach. Electric Power Syst Res 77(10):1297–1304. https://doi.org/10.1016/j.epsr.2006.09.022
Cerjan M, Matijaš M, Delimar M (2014) Dynamic hybrid model for short-term electricity price forecasting. Energies. https://doi.org/10.3390/en7053304
Shrivastava NA, Panigrahi BK (2014) A hybrid wavelet-ELM based short term price forecasting for electricity markets. Int J Electr Power Energy Syst 55:41–50. https://doi.org/10.1016/j.ijepes.2013.08.023
Chen J, Li H, Yi Q, Wang J (2014) Application of BP Neural Networks based on genetic simulated annealing algorithm for shortterm electricity price forecasting
Chinnathambi RA, Plathottam SJ, Hossen T, Nair AS, Ranganathan P (2018) Deep neural networks (DNN) for day-ahead electricity price markets, pp 1–6. https://doi.org/10.1109/EPEC.2018.8598327
Wang B, Shaaban K, Kim I (2019) Reveal the hidden layer via entity embedding in traffic prediction. Procedia Comput Sci 151:163–170. https://doi.org/10.1016/j.procs.2019.04.025
Naz A, Javed MU, Javaid N, Saba T, Alhussein M, Aurangzeb K (2019) Short-term electric load and price forecasting using enhanced extreme learning machine optimization in smart grids. Energies. https://doi.org/10.3390/en12050866
Wei Q, Chen S, Huang W, Ma G, Tao C (2021) Forecasting method of clearing price in spot market by random forest regression. Zhongguo Dianji Gongcheng Xuebao/Proc Chin Soc Electr Eng 41(4):1360–1367. https://doi.org/10.13334/j.0258-8013.pcsee.191904
Du M, Liu N, Hu X (2019) Techniques for interpretable machine learning. Commun ACM 63(1):68–77. https://doi.org/10.1145/3359786
Molnar C (2019) Interpretable machine learning. A guide for making black box models explainable. https://christophm.github.io/interpretable-ml-book/. Accessed on 15 June 2021
Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, Katz R, Himmelfarb J, Bansal N, Lee S-I (2020) From local explanations to global understanding with explainable AI for trees. Nat Mach Intell 2(1):56–67. https://doi.org/10.1038/s42256-019-0138-9
Lundberg SM, Lee S-I (2017).A unified approach to interpreting model predictions. Advances in neural information processing systems, Long Beach, CA. Neural information processing systems foundation. pp 4766–4775. Advances in neural information processing systems. https://arxiv.org/abs/1705.07874
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785–794. https://doi.org/10.1145/2939672.2939785
Mokbal FMM, Dan W, Xiaoxi W, Wenbin Z, Lihua F (2021) XGBXSS: an extreme gradient boosting detection framework for cross-site scripting attacks based on hybrid feature selection approach and parameters optimization. J Inf Secur Appl 58:102813. https://doi.org/10.1016/j.jisa.2021.102813
Panapakidis IP, Dagoumas AS (2016) Day-ahead electricity price forecasting via the application of artificial neural network based models. Appl Energy 172:132–151. https://doi.org/10.1016/j.apenergy.2016.03.089
Sánchez de la Nieta AA, Contreras J (2020) Quantifying the effect of renewable generation on day–ahead electricity market prices: the Spanish case. Energy Econ 90:104841. https://doi.org/10.1016/j.eneco.2020.104841
Visser L, AlSkaif T, Sark Wv (2020) The importance of predictor variables and feature selection in day-ahead electricity price forecasting, pp 1–6. https://doi.org/10.1109/SEST48500.2020.9203273
Parsa AB, Movahedi A, Taghipour H, Derrible S, Mohammadian A (2020) Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accid Anal Prev. https://doi.org/10.1016/j.aap.2019.105405
Ji C, Zhou T, Xiang T, Huang H (2014) Application of support vector machine based on grid search and cross validation in implicit stochastic dispatch of cascaded hydropower stations. Dianli Zidonghua Shebei/Electric Power Autom Equip 34(3):125–131. https://doi.org/10.3969/j.issn.1006-6047.2014.03.021
Budiman F (2019) SVM-RBF parameters testing optimization using cross validation and grid search to improve multiclass classification. Sci Vis 11(1):80–90. https://doi.org/10.26583/sv.11.1.07
PJM Markets & operations data directory. http://dataminer2.pjm.com/feed/ancillary_services/definition
Liyan L, Xiaoyan Z (2016) Comparison of GARCH model in electricity price forecasting. Dianli Xitong Baohu yu Kongzhi/Power Syst Prot Control 44(04):57–63. https://doi.org/10.7667/PSPC150775
Acknowledgements
This paper is supported by the National Natural Science Foundation of China (52039006), the National Key Research & Development Program (2018YFB0905204), and the Research project entrusted by Power China Hydropower Development Group Co., Ltd (SD-2020/S-04).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of Interest
All authors decline that there is no conflict of interest related to this manuscript.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xie, H., Chen, S., Lai, C. et al. Forecasting the clearing price in the day-ahead spot market using eXtreme Gradient Boosting. Electr Eng 104, 1607–1621 (2022). https://doi.org/10.1007/s00202-021-01410-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-021-01410-6