Regularization for electricity price forecasting

• Autorzy: UNIEJEWSKI Bartosz
• Języki publikacji: EN

Abstrakty

EN

The most commonly used form of regularization typically involves defining the penalty function as a ℓ1 or ℓ2 norm. However, numerous alternative approaches remain untested in practical applications. In this study, we apply ten different penalty functions to predict electricity prices and evaluate their performance under two different model structures and in two distinct electricity markets. The study reveals that LQ and elastic net consistently produce more accurate forecasts compared to other regularization types. In particular, they were the only types of penalty functions that consistently produced more accurate forecasts than the most commonly used LASSO. Furthermore, the results suggest that cross-validation outperforms Bayesian information criteria for parameter optimization, and performs as well as models with ex-post parameter selection.

Słowa kluczowe

EN

electricity price forecasting regularization; power market; convex regularization; LQ regularization; elastic net

• Wydawca: Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Operations Research and Decisions
• Rocznik: 2024
• Tom: 34
• Numer: 3
• Strony: 267-286

Twórcy

autor

UNIEJEWSKI Bartosz

• Department of Operations Research and Business Intelligence, Wroclaw University of Science and Technology, Wroclaw, Poland,

Bibliografia

• Agrawal, R. K., Muchahary, F., and Tripathi, M. M. Ensemble of relevance vector machines and boosted trees for electricity price forecasting. Applied Energy 250 (2019), 540–548.
• Antoniadis, A., and Fan, J. Regularization of wavelet approximations. Journal of the American Statistical Association 96, 455 (2001), 939–967.
• Barnes, A. K., and Balda, J. C. Sizing and economic assessment of energy storage with real-time pricing and ancillary services. In 2013 4th IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG) (Rogers, AR, USA, 2013), IEEE, pp. 1-7.
• Ciarreta, A., Muniain, P., and Zarraga, A. Do jumps and cojumps matter for electricity price forecasting? Evidence from the German-Austrian day-ahead market. Electric Power Systems Research 212 (2022), 108144.
• Efron, B., Hastie, T., Johnstone, I., and Tibshirani, R. Least angle regression. The Annals of Statistics 32, 2 (2004), 407–499.
• Fan, J., and Li, R. Variable selection via nonconcave penalized likelihood and its oracle properties. Journal of the American Statistical Association 96, 456 (2001), 1348–1360.
• Gaillard, P., Goude, Y., and Nedellec, R. Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting. International Journal of Forecasting 32, 3 (2016), 1038–1050.
• Grasmair, M., Haltmeier, M., and Scherzer, O. Sparse regularization with lq penalty term. Inverse Problems 24, 5 (2008), 055020.
• Hastie, T., Tibshirani, R., and Wainwright, M. Statistical Learning with Sparsity: The Lasso and Generalizations. CRC Press, 2015.
• Hoerl, A. E., and Kennard, R. W. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 12, 1 (1970), 55–67.
• Hubicka, K., Marcjasz, G., and Weron, R. A note on averaging day-ahead electricity price forecasts across calibration windows. IEEE Transactions on Sustainable Energy 10, 1 (2019), 321–323.
• Janczura, J., and Wójcik, E. Dynamic short-term risk management strategies for the choice ofelectricity market based on probabilistic forecasts of profit and risk measures. The German and the Polish market case study. Energy Economics 110 (2022), 106015.
• Kath, C., and Ziel, F. The value of forecasts: Quantifying the economic gains of accurate quarter-hourly electricity price forecasts. Energy Economics 76 (2018), 411–423.
• Lago, J., Marcjasz, G., De Schutter, B., and Weron, R. Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark. Applied Energy 293 (2021), 116983.
• Ludwig, N., Feuerriegel, S., and Neumann, D. Putting big data analytics to work: Feature selection for forecasting electricity prices using the LASSO and random forests. Journal of Decision Systems 24, 1 (2015), 19–36.
• Maciejowska, K. Portfolio management of a small RES utility with a structural vector autoregressive model of electricity markets in Germany. Operations Research and Decisions 32, 4 (2022), 75–90.
• Mayer, K., and Trück, S. Electricity markets around the world. Journal of Commodity Markets 9 (2018), 77–100.
• Mazumder, R., Friedman, J. H., and Hastie, T. SparseNet: Coordinate descent with nonconvex penalties. Journal of the American Statistical Association 106, 495 (2011), 1125–1138.
• McIlhagga, W. penalized: A MATLAB toolbox for fitting generalized linear models with penalties. Journal of Statistical Software 72, 6 (2016), 1–21.
• Mirakyan, A., Meyer-Renschhausen, M., and Koch, A. Composite forecasting approach, application for next-day electricity price forecasting. Energy Economics 66 (2017), 228 – 237.
• Muniain, P., and Ziel, F. Probabilistic forecasting in day-ahead electricity markets: Simulating peak and off-peak prices. International Journal of Forecasting 36, 4 (2020), 1193–1210.
• Narajewski, M., and Ziel, F. Ensemble forecasting for intraday electricity prices: Simulating trajectories. Applied Energy 279 (2020), 115801.
• Narajewski, M., and Ziel, F. Optimal bidding in hourly and quarter-hourly electricity price auctions: Trading large volumes of power with market impact and transaction costs. Energy Economics 110 (2022), 105974.
• Nikolova, M. Local strong homogeneity of a regularized estimator. SIAM Journal on Applied Mathematics 61, 2 (2000), 633–658.
• Nitka, W., and Weron, R. Combining predictive distributions of electricity prices. Does minimizing the CRPS lead to optimal decisions in day-ahead bidding? Operations Research and Decisions 33, 3 (2023), 105–118.
• Park, M. Y., and Hastie, T. L1-Regularization path algorithm for generalized linear models. Journal of the Royal Statistical Society. Series B: Statistical Methodology 69, 4 (2007), 659–677.
• Radchenko, P., and James, G. M. Improved variable selection with Forward-Lasso adaptive shrinkage. The Annals of Applied Statistics 5, 1 (2011), 427–448.
• Schmidt, M., Fung, G., and Rosales, R. Optimization Methods for L1-Regularization. Technical Report No. 19, University of British Columbia, 2009.
• Serafin, T., Uniejewski, B., and Weron, R. Averaging predictive distributions across calibration windows for day-ahead electricity price forecasting. Energies 12, 13 (2019), 2561.
• Tibshirani, R. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B: Statistical Methodology 58, 1 (1996), 267–288.
• Uniejewski, B., Nowotarski, J., and Weron, R. Automated variable selection and shrinkage for day-ahead electricity price forecasting. Energies 9, 8 (2016), 621.
• Uniejewski, B., Weron, R., and Ziel, F. Variance stabilizing transformations for electricity spot price forecasting. IEEE Transactions on Power Systems 33 (2018), 2219–2229.
• Weron, R. Electricity price forecasting: A review of the state-of-the-art with a look into the future. International Journal of Forecasting 30, 4 (2014), 1030–1081.
• Zhang, C.-H. Nearly unbiased variable selection under minimax concave penalty. The Annals of Statistics 38, 2 (2010), 894–942.
• Ziel, F. Forecasting electricity spot prices using LASSO: On capturing the autoregressive intraday structure. IEEE Transactions on Power Systems 31, 6 (2016), 4977–4987.
• Ziel, F. Iteratively reweighted adaptive lasso for conditional heteroscedastic time series with applications to AR-ARCH type processes. Computational Statistics and Data Analysis 100 (2016), 773–793.
• Ziel, F., Steinert, R., and Husmann, S. Efficient modeling and forecasting of electricity spot prices. Energy Economics 47 (2015), 98–111.
• Ziel, F., and Weron, R. Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks. Energy Economics 70 (2018), 396–420.
• Zou, H. The adaptive lasso and its oracle properties. Journal of the American Statistical Association 101, 476 (2006), 1418–1429.
• Zou, H., and Hastie, T. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society. Series B: Statistical Methodology 67, 2 (2005), 301–320.

Identyfikatory

DOI

10.37190/ord240314