journal article·2020-07-02Open access

Hybrid Load Forecasting Using Gaussian Process Regression and Novel Residual Prediction

Cosmin Darab, Turcu Antoniu, Horia Gheorghe Beleiu, Sorin Pavel, Iulian Birou, Dan Doru Micu, Stefan Ungureanu, Stefan Dragos Cirstea

Applied Sciences· Volume 10· Issue 13

Abstract

Short-term electricity load forecasting has attracted considerable attention as a result of the crucial role that it plays in power systems and electricity markets. This paper presents a novel hybrid forecasting method that combines an autoregressive model with Gaussian process regression. Mixed-user, hourly, historical data are used to train, validate, and evaluate the model. The empirical wavelet transform was used to preprocess the data. Among the perturbing factors, the most influential predictors that were recorded were the weather factors and day type. The developed methodology is upgraded using a novel closed-loop algorithm that uses the forecasting values and influential factors to predict the residuals. Most performance indicators that are computed indicate that forecasting the residuals actually improves the method’s precision, decreasing the mean absolute percentage error from 5.04% to 4.28%. Measured data are used to validate the effectiveness of the presented approach, making it a suitable tool for use in load forecasting by utility companies.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Energy Load and Power Forecasting · Solar Radiation and Photovoltaics · Smart Grid Energy Management

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Electrical Engineering, Technical University of Cluj-Napoca, 28 Memorandumului Street, 400114 Cluj-Napoca, Romania

Department of Electric Machines and Drives, Faculty of Electrical Engineering, Technical University of Cluj-Napoca, 28 Memorandumului Street, 400114 Cluj-Napoca, Romania

Department of Electrotechnics and Measurements, Faculty of Electrical Engineering, Technical University of Cluj-Napoca, 28 Memorandumului Street, 400114 Cluj-Napoca, Romania

References (34)

Show source-provided references
1. T.I.E. Agency (2020, May 01). Global Energy & CO2 Status Report. Available online: https://www.iea.org/.
2. A hybrid forecasting model based on date-framework strategy and improved feature selection technology for short term load forecasting10.1016/j.energy.2016.11.034 ↗
3. Utility companies strategy for short-term energy demand forecasting using machine learning based models10.1016/j.scs.2018.03.002 ↗
4. An interval optimization based day-ahead scheduling scheme for renewable energy management in smart distribution systems10.1016/j.enconman.2015.10.014 ↗
5. Wang, H., Lei, Z., Zhang, X., Zhou, B., and Peng, J. (2019). A review of deep learning for renewable energy forecasting. Energy Convers. Manag., 198.10.1016/j.enconman.2019.111799 ↗
6. Deterministic and probabilistic forecasting of photovoltaic power based on deep convolutional neural network10.1016/j.enconman.2017.10.008 ↗
7. Multi-period flexibility forecast for low voltage prosumers10.1016/j.energy.2017.11.142 ↗
8. Mak, S.T. (2015). Advanced Metering and Demand Response Applications in New Technologies for Smart Grid Operation, IOP Publishing.10.1088/978-0-7503-1158-8 ↗
9. Big Data Analytics for Dynamic Energy Management in Smart Grids10.1016/j.bdr.2015.03.003 ↗
10. Imperialist competitive algorithm combined with refined high-order weighted fuzzy time series (RHWFTS–ICA) for short term load forecasting10.1016/j.enconman.2013.08.039 ↗
11. Short-term power load probability density forecasting based on Yeo-Johnson transformation quantile regression and Gaussian kernel function10.1016/j.energy.2018.04.072 ↗
12. Takeda, H., Tamura, Y., and Sato, S. (2016). Using the ensemble Kalman filter for electricity load forecasting and analysis. Energy, 104.10.1016/j.energy.2016.03.070 ↗
13. Lynch, C., O’Mahony, M.J., and Guinee, R.A. (July, January 29). Accurate day ahead temperature prediction using a 24 hour Kalman filter estimator. Proceedings of the 2015 11th Conference on Ph.D. Research in Microelectronics and Electronics (PRIME), Glasgow, UK.10.1109/PRIME.2015.7251354 ↗
14. Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information10.1016/j.renene.2017.11.011 ↗
15. Forecasting U.S. shale gas monthly production using a hybrid ARIMA and metabolic nonlinear grey model10.1016/j.energy.2018.07.047 ↗
16. Forecasting daily urban electric load profiles using artificial neural networks10.1016/j.enconman.2004.01.006 ↗
17. Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market10.1016/j.enconman.2005.12.008 ↗
18. Day-ahead price forecasting of electricity markets by a new feature selection algorithm and cascaded neural network technique10.1016/j.enconman.2009.07.016 ↗
19. Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting10.1016/j.renene.2019.01.031 ↗
20. Very short term load forecasting of a distribution system with high PV penetration10.1016/j.renene.2017.01.019 ↗
21. Innovative Second-Generation Wavelets Construction with Recurrent Neural Networks for Solar Radiation Forecasting10.1109/TNNLS.2012.2216546 ↗
22. PV power forecasting using an integrated GA-PSO-ANFIS approach and Gaussian process regression based feature selection strategy10.17775/CSEEJPES.2016.01920 ↗
23. Short-term electricity load forecasting based on feature selection and Least Squares Support Vector Machines10.1016/j.knosys.2018.08.027 ↗
24. A SARIMA-RVFL hybrid model assisted by wavelet decomposition for very short-term solar PV power generation forecast10.1016/j.renene.2019.03.020 ↗
25. A Short-Term and High-Resolution Distribution System Load Forecasting Approach Using Support Vector Regression With Hybrid Parameters Optimization10.1109/TSG.2016.2628061 ↗
26. Improving Load Forecasting Process for a Power Distribution Network Using Hybrid AI and Deep Learning Algorithms10.1109/ACCESS.2019.2923796 ↗
27. A Gaussian process regression based hybrid approach for short-term wind speed prediction10.1016/j.enconman.2016.08.086 ↗
28. (2020, May 01). Transelectrica. Available online: http://transelectrica.ro/en/web/tel/despre-noi1.
29. R. P. Ltd (2020, May 01). Weather_in_the_World. Available online: https://rp5.ru/Weather_archive_in_Bucharest,_Filaret.
30. Empirical wavelet transform10.1109/TSP.2013.2265222 ↗
31. Deep belief network based electricity load forecasting: An analysis of Macedonian case10.1016/j.energy.2016.07.090 ↗
32. Jin, Y. (2006). Multi-Objective Machine Learning, Springer Science & Business Media.10.1007/11399346 ↗
33. Rasmussen, C.E., and Williams, C.K.I. (2006). Gaussian Processes for Machine Learning, MIT Press. Available online: www.GaussianProcess.org/gpml.10.7551/mitpress/3206.001.0001 ↗
34. Combining Probabilistic Load Forecasts10.1109/TSG.2018.2833869 ↗