Day-Ahead Electricity Market Price Forecasting Considering the Components of the Electricity Market Price; Using Demand Decomposition, Fuel Cost, and the Kernel Density Estimation
Abstract
:1. Introduction
2. Proposed Algorithm
2.1. Overview of the Methodology
2.2. Feature Generation of the Labels
2.2.1. Kernel Density Estimation
2.2.2. Feature Generation of the Labels and Post-Processing
2.3. Decomposition
2.4. Feature Selection
2.4.1. Information Gain
2.4.2. SHAP
2.4.3. Average of the Rank of Each Feature Importance
2.5. XGBoost
3. Case Study
3.1. Simulation Environment
3.1.1. Database
3.1.2. The Case Studies
- Forecasting and with or without decomposition data, and each of the four combinations contain the independent feature selection process.
- Forecasting and with the same feature set that was used for the forecast with decomposed demand.
- Forecasting and using the same feature set as above.
3.1.3. Features and Parameters
- forecasting with decomposed demand
- forecasting without decomposed demand
- forecasting with decomposed demand
- forecasting without decomposed demand
3.2. Performance Indices
3.2.1. Error Metric
3.2.2. Statistical Test: Diebold-Mariano Test
3.2.3. Dynamic Time Warping (DTW) Distance
3.3. Simulation Results
- The forecasting can be significantly improved by using decomposed data of the previous demand as a feature.
- Combining the use of decomposed data and the use of fuel cost per unit improves forecasting significantly compared to each case.
- Using fuel cost per unit improves forecasting significantly for all periods.
- For forecasting at the beginning of the month, using fuel cost per unit resulted in the most accurate but not significant forecasting. However, when using the argument of PDF calculated by KDE together, the forecasting was significantly improved.
- For forecasting the rest of the month, using kdeargmax improves the forecasting significantly compared to other methods.
4. Discussion and Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Gao, C.; Bompard, E.; Napoli, R.; Wan, Q.; Zhou, J. Bidding Strategy with Forecast Technology Based on Support Vector Machine in the Electricity Market. Phys. A Stat. Mech. Its Appl. 2008, 387, 3874–3881. [Google Scholar] [CrossRef] [Green Version]
- Weron, R. Electricity Price Forecasting: A Review of the State-of-the-Art with a Look into the Future. Int. J. Forecast. 2014, 30, 1030–1081. [Google Scholar] [CrossRef] [Green Version]
- Stoft, S. Power System Economics: Designing Markets for Electricity; IEEE Press: New York, NY, USA, 2002. [Google Scholar]
- Kirschen, D.S.; Strbac, G. Fundamentals of Power System Economics, 2nd ed.; Wiley: Hoboken, NJ, USA, 2018. [Google Scholar]
- Petropoulos, F.; Apiletti, D.; Assimakopoulos, V.; Babai, M.Z.; Barrow, D.K.; ben Taieb, S.; Bergmeir, C.; Bessa, R.J.; Bijak, J.; Boylan, J.E.; et al. Forecasting: Theory and Practice. Int. J. Forecast. 2022, 38, 705–871. [Google Scholar] [CrossRef]
- Ollech, D. Seasonal Adjustment of Daily Time Series. Dtsch. Bundesbank Discuss. Pap. 2018, 41. [Google Scholar] [CrossRef]
- Bandara, K.; Hyndman, R.J.; Bergmeir, C. MSTL: A Seasonal-Trend Decomposition Algorithm for Time Series with Multiple Seasonal Patterns. Int. J. Oper. Res. 2021. [Google Scholar] [CrossRef]
- Cleveland, R.B.; Cleveland, W.S.; McRae, J.E.; Terpenning, I. STL: A Seasonal-Trend Decomposition Procedure Based on Loess. Off. Stat. 1990, 6, 3–73. [Google Scholar]
- Gao, T.; Niu, D.; Ji, Z.; Sun, L. Mid-Term Electricity Demand Forecasting Using Improved Variational Mode De-composition and Extreme Learning Machine Optimized by Sparrow Search Algorithm. Energy 2022, 261, 125328. [Google Scholar] [CrossRef]
- Bandara, K.; Bergmeir, C.; Hewamalage, H. LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns. IEEE Trans. Neural. Netw. Learn. Syst. 2021, 32, 1586–1599. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Jurgen, A. Doornik Autometrics. In The Methodology and Practice of Econometrics; Castle, J., Shephard, N., Eds.; Oxford University Press: Oxford, UK, 2009; pp. 88–121. [Google Scholar] [CrossRef]
- Zou, H.; Hastie, T. Regression Shrinkage and Selection via the Elastic Net. R. Stat. Society. Ser. B (Stat. Methodol.) 2005, 67, 301–320. [Google Scholar] [CrossRef] [Green Version]
- Tibshirani, R. Regression Shrinkage and Selection via the Lasso; Wiley: Hoboken, NJ, USA, 1996; Volume 58. [Google Scholar]
- Elliott, G.; Gargano, A.; Timmermann, A. Complete Subset Regressions. J. Econom. 2013, 177, 357–373. [Google Scholar] [CrossRef] [Green Version]
- Aue, A.; Norinho, D.D.; Hörmann, S. On the Prediction of Stationary Functional Time Series. J. Am. Stat. Assoc. 2015, 110, 378–392. [Google Scholar] [CrossRef] [Green Version]
- Kelly, B.; Pruitt, S. Market Expectations in the Cross-Section of Present Values. J. Financ. 2013, 68, 1721–1756. [Google Scholar] [CrossRef]
- Box, G.E.P.; Cox, D.R. An Analysis of Transformations. Source J. R. Stat. Society. Ser. B (Methodol.) 1964, 26, 211–252. [Google Scholar] [CrossRef]
- Effrosynidis, D.; Arampatzis, A. An Evaluation of Feature Selection Methods for Environmental Data. Ecol. Inform. 2021, 61, 101224. [Google Scholar] [CrossRef]
- Zhang, R.; Nie, F.; Li, X.; Wei, X. Feature Selection with Multi-View Data: A Survey. Inf. Fusion 2019, 50, 158–167. [Google Scholar] [CrossRef]
- Passalis, N.; Tefas, A.; Kanniainen, J.; Gabbouj, M.; Iosifidis, A. Deep Adaptive Input Normalization for Time Series Forecasting. IEEE Trans. Neural. Netw. Learn. Syst. 2020, 31, 3760–3765. [Google Scholar] [CrossRef] [Green Version]
- Ogasawara, E.; Martinez, L.C.; De Oliveira, D.; Zimbrão, G.; Pappa, G.L.; Mattoso, M. Adaptive Normalization: A Novel Data Normalization Approach for Non-Stationary Time Series. In Proceedings of the International Joint Conference on Neural Networks, Barcelona, Spain, 18–23 July 2010. [Google Scholar]
- Uniejewski, B.; Weron, R.; Ziel, F. Variance Stabilizing Transformations for Electricity Spot Price Forecasting. IEEE Trans. Power Syst. 2018, 33, 2219–2229. [Google Scholar] [CrossRef] [Green Version]
- Nayak, S.C.; Misra, B.B.; Behera, H.S. Impact of Data Normalization on Stock Index Forecasting. Int. J. Comput. Inf. Syst. Ind. Manag. Appl. 2014, 6, 257–269. [Google Scholar]
- Guo, J.J.; Luh, P.B. Selecting Input Factors for Clusters of Gaussian Radial Basis Function Networks to Improve Market Clearing Price Prediction. IEEE Trans. Power Syst. 2003, 18, 665–672. [Google Scholar] [CrossRef]
- Aliamiri, A.; Stalnaker, J.; Miller, E.L. Statistical Classification of Buried Unexploded Ordnance Using Nonpara-metric Prior Models. IEEE Trans. Geosci. Remote Sens. 2007, 45, 2794–2806. [Google Scholar] [CrossRef] [Green Version]
- Van Hulle, M.M. Density-Based Clustering with Topographic Maps. IEEE Trans. Neural. Netw. 1999, 10, 204–207. [Google Scholar] [CrossRef] [PubMed]
- Tangirala, S. Evaluating the Impact of GINI Index and Information Gain on Classification Using Decision Tree Classifier Algorithm. Int. J. Adv. Comput. Sci. Appl. 2020, 11, 612–619. [Google Scholar] [CrossRef] [Green Version]
- Lundberg, S.M.; Allen, P.G.; Lee, S.-I. A Unified Approach to Interpreting Model Predictions. Adv. Neural Inf. Process. Syst. 2017, 30, 4768–4777. [Google Scholar]
- Natekin, A.; Knoll, A. Gradient Boosting Machines, a Tutorial. Front. Neurorobot. 2013, 7, 21. [Google Scholar] [CrossRef] [Green Version]
- Freund, Y.; Schapire, R.E. Experiments with a New Boosting Algorithm DRAFT-PLEASE DO NOT DISTRIBUTE. Experiments with a new boosting algorithm. icmi 1996, 96, 148–156. [Google Scholar]
- Chen, T.; Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; Association for Computing Machinery: New York, NY, USA, 2016; pp. 785–794. [Google Scholar]
- Prokhorenkova, L.; Gusev, G.; Vorobev, A.; Dorogush, A.V.; Gulin, A. CatBoost: Unbiased Boosting with Categor-ical Features. Adv. Neural Inf. Process. Syst. 2018, 31, 6638–6648. [Google Scholar]
- Kwon, B.S.; Park, R.J.; Song, K. Bin Short-Term Load Forecasting Based on Deep Neural Networks Using LSTM Layer. J. Electr. Eng. Technol. 2020, 15, 1501–1509. [Google Scholar] [CrossRef]
- Misiorek, A.; Trueck, S.; Weron, R. Point and Interval Forecasting of Spot Electricity Prices: Linear vs. Non-Linear Time Series Models. Stud. Nonlinear Dyn. Econom. 2006, 10, 3. [Google Scholar] [CrossRef] [Green Version]
- Diebold, F.X.; Mariano, R.S. Comparing Predictive Accuracy. J. Bus. Econ. Stat. 2002, 20, 134–144. [Google Scholar] [CrossRef]
- Harvey, D.; Leybourne, S.; Newbold, P. Testing the Equality of Prediction Mean Squared Errors. Int. J. Forecast. 1997, 13, 281–291. [Google Scholar] [CrossRef]
- Senin, P. Dynamic Time Warping Algorithm Review; Information and Computer Science Department, University of Hawaii: Honolulu, HI, USA, 2008. [Google Scholar]
- Hsu, H.H.; Yang, A.C.; Lu, M. Da KNN-DTW Based Missing Value Imputation for Microarray Time Series Data. J. Comput. 2011, 6, 418–425. [Google Scholar] [CrossRef] [Green Version]
- Shen, S.K.; Liu, W.; Zhang, T. Load Pattern Recognition and Prediction Based on DTW K-Mediods Clustering and Markov Model. In Proceedings of the IEEE International Conference on Energy Internet, ICEI 2019, Nanjing, China, 27–31 May 2019; Institute of Electrical and Electronics Engineers Inc.: Piscataway, NJ, USA, 2019; pp. 403–408. [Google Scholar]
- Laperre, B.; Amaya, J.; Lapenta, G. Dynamic Time Warping as a New Evaluation for Dst Forecast With Machine Learning. Front. Astron. Space Sci. 2020, 7, 39. [Google Scholar] [CrossRef]
Feature Categories | Time Points for Using | Features | Feature Name | |
---|---|---|---|---|
Decomposed demand [MWh] | h 2-24, h-25, h-48, h-72, h-168 |
|
| |
Previous price [₩/kWh] | h-24, h-25, h-48, h-72, h-168 |
| (original)
| (scaled)
|
Calendar (integer) | h |
|
| |
Fuel cost [₩/kWh] Capacity [MWh] | h |
|
|
|
Weighted average weather | h |
|
| |
price [₩/kWh] 1 | h |
Categorical | Numerical | Decomposed | Past SMP | |||
---|---|---|---|---|---|---|
Decomposition | (a) | ‘day_week’, ‘day’ | ‘price_coal’ | ‘demand_h-168’, ‘demand_wd-168’, ‘demand_trend-168’,’demand_trend-72 | ‘hpn-24’, ‘hpn-25’, ‘hpn-168 | |
- | (b) | ‘day_week’, ‘day’, ‘month | ‘wind_speed’ | ‘demand_h-168’, ‘demand_h-48’ | ‘hpn-24’, ‘hpn-25’, ’hpn-72’, ‘hpn-168 | |
Decomposition | (c) | ‘day_week’, ‘day’ | ‘price_coal’, ‘price_lng’ | ‘demand_h-168’, ‘demand_trend-72’ | ‘h-24’,’h-25’, ‘h-72’,’h-168’ | |
- | (d) | ‘day_week’, ‘day’ | ‘price_coal’, ‘price_lng’, ‘price_gap’, | ‘demand_h-168’ | ‘h-24’,’h-25’, ‘h-72’,’h-168’ |
Parameters |
---|
scale_pos_weight = 0.1, n_estimators = 1000, colsample_bytree = 0.9, learning_rate = 0.01, alpha = 0, gamma = 0.001, max_depth = 15, min_child_weight = 3, objective = ‘reg:squarederror’,subsample = 0.8 |
(No Decomposition) | (No Decomposition) | |||
---|---|---|---|---|
Mean of RMSE | 7.1544 | 7.5764 | 8.0916 | 8.3355 |
Mean of MAPE | 3.8308 | 4.1759 | 4.5900 | 4.7564 |
D-M test statistic [p-value] | - | −4.4899 [8.2567 ] | −5.0678 [5.0842 ] | −5.8951 [5.6803 ] |
5.0678 [5.0842 ] | 2.8786 [4.1096 ] | - | −5.1268 [3.7627 ] | |
Mean of MDE | 3.4016 | 3.7335 | 4.1780 | 4.1841 |
Mean of DTW | 91.4516 | 97.7729 | 118.8496 | 122.1072 |
Test Dates: 12.01–12.31 | ||||||
---|---|---|---|---|---|---|
Mean of RMSE | 7.7059 | 7.3693 | 7.0126 | 7.1544 | 6.9925 | 6.4846 |
Mean of MAPE | 4.4054 | 4.1295 | 3.8200 | 3.8308 | 3.8681 | 3.4855 |
D-M test statistic [p-value] | −1.6959 [0.0903] | - | 5.3007 [1.5225 ] | 2.2326 [2.5875 ] | 4.4798 [8.6467 ] | 7.3816 [4.1985 ] |
−3.8738 [1.1660 ] | −5.3007 [1.5225 ] | - | −0.0884 [0.9296] | −1.1494 [0.2508] | 6.3962 [2.8154 ] | |
−3.7154 [2.1810 ] | −2.2326 [2.5875 ] | 0.0884 [0.9296] | - | −0.3469 [0.7288] | 3.2639 [1.1491 ] | |
−3.6879 [2.4260 ] | −4.4798 [8.6467 ] | 1.1494 [0.2508] | 0.3469 [0.7288] | - | 8.5620 [6.3485 ] | |
−6.1395 [1.3485 ] | −7.3816 [4.1985 ] | −6.3962 [2.8154 ] | −3.2639 [1.1491 ] | −8.5620 [6.3485 ] | - | |
Mean of MDE | 4.0419 | 3.7479 | 3.4451 | 3.4016 | 3.4896 | 3.1148 |
Mean of DTW | 117.2682 | 110.8884 | 100.7169 | 91.4516 | 100.3044 | 88.5130 |
12.01–12.07 | ||||||
Mean of RMSE | 9.6569 | 11.6741 | 11.0114 | 9.2406 | 10.2170 | 8.9655 |
Mean of MAPE | 5.4366 | 6.7260 | 6.1647 | 5.0623 | 5.7129 | 4.8689 |
D-M test statistic [p-value] | 3.3877 [8.7907 ] | - | 3.0695 [2.5028 ] | 4.8458 [2.8631 ] | −4.6920 [5.6043 ] | 6.3787 [1.6863 ] |
2.3822 [1.8336 ] | −3.0695 [2.5028 ] | - | 4.2597 [3.4098 ] | 4.4040 [1.8920 ] | 7.0852 [3.7051 ] | |
−1.4907 [0.1379] | −4.8458 [2.8631 ] | −4.2597 [3.4098 ] | - | −3.3772 [9.1084 ] | 0.7559 [0.4508] | |
0.8637 [0.3890] | 4.6920 [5.6043 ] | −4.4040 [1.8920 ] | 3.3772 [9.1084 ] | - | 7.5808 [2.2594 ] | |
−2.2433 [2.6191 ] | −6.3787 [1.6863 ] | −7.0852 [3.7051 ] | 0.7559 [0.4508] | −7.5808 [2.2594 ] | - | |
Mean of MDE | 4.8351 | 6.0611 | 5.5053 | 4.4443 | 5.0602 | 4.2253 |
Mean of DTW | 150.9208 | 191.8587 | 169.6297 | 114.5523 | 150.8459 | 122.3397 |
12.08–12.31 | ||||||
Mean of RMSE | 7.4111 | 6.3271 | 6.0976 | 6.8896 | 6.3271 | 6.0976 |
Mean of MAPE | 4.2184 | 3.4493 | 3.2428 | 3.6474 | 3.4493 | 3.2428 |
D-M test statistic [p-value] | −4.6369 [4.3802 ] | - | 5.0688 [5.4061 ] | −1.7033 [0.0896] | 1.1100 [0.2675] | 5.0688 [5.4061 ] |
−5.7786 [1.2351 ] | −5.0688 [5.4061 ] | - | −3.2329 [1.2954 ] | −5.0688 [5.4061 ] | −0.0522 [0.9584] | |
−3.4886 [5.2278 ] | 1.7033 [0.0896] | 3.2329 [1.2954 ] | - | 1.7033 0.0891] | 3.2329 [1.2954 ] | |
−4.6370 [4.3802 ] | −1.1100 [0.2675] | 5.0688 [5.4061 ] | −1.7033 0.0891] | 5.0688 [5.4061 ] | ||
−5.7786 [1.2351 ] | −5.0688 [5.4061 ] | 0.0522 [0.9584] | 3.2329 [1.2954 ] | −5.0688 [5.4061 ] | - | |
Mean of MDE | 3.8849 | 3.1118 | 2.9115 | 3.2313 | 3.1118 | 2.9115 |
Mean of DTW | 109.6864 | 88.4524 | 82.9930 | 90.0540 | 88.4524 | 82.9930 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jin, A.; Lee, D.; Park, J.-B.; Roh, J.H. Day-Ahead Electricity Market Price Forecasting Considering the Components of the Electricity Market Price; Using Demand Decomposition, Fuel Cost, and the Kernel Density Estimation. Energies 2023, 16, 3222. https://doi.org/10.3390/en16073222
Jin A, Lee D, Park J-B, Roh JH. Day-Ahead Electricity Market Price Forecasting Considering the Components of the Electricity Market Price; Using Demand Decomposition, Fuel Cost, and the Kernel Density Estimation. Energies. 2023; 16(7):3222. https://doi.org/10.3390/en16073222
Chicago/Turabian StyleJin, Arim, Dahan Lee, Jong-Bae Park, and Jae Hyung Roh. 2023. "Day-Ahead Electricity Market Price Forecasting Considering the Components of the Electricity Market Price; Using Demand Decomposition, Fuel Cost, and the Kernel Density Estimation" Energies 16, no. 7: 3222. https://doi.org/10.3390/en16073222