Ensemble models for solar power forecasting—a weather classification approach

P. A. G. M. Amarasinghe; N. S. Abeygunawardana; T. N. Jayasekara; E. A. J. P. Edirisinghe; S. K. Abeygunawardane; P. A. G. M. Amarasinghe; N. S. Abeygunawardana; T. N. Jayasekara; E. A. J. P. Edirisinghe; S. K. Abeygunawardane

doi:10.3934/energy.2020.2.252

AIMS Energy

2020, Volume 8, Issue 2: 252-271. doi: 10.3934/energy.2020.2.252

Previous Article Next Article

Research article Topical Sections

Ensemble models for solar power forecasting—a weather classification approach

Department of Electrical Engineering, University of Moratuwa, Sri Lanka

Received: 04 November 2019 Accepted: 11 March 2020 Published: 23 March 2020

Solar power integration has shown a significant growth in many power systems during the last decade. The intermittent nature of solar irradiance tends to vary the amount of solar power in the system and an accurate solar power forecasting method can be used to tackle this in power system planning and operation. In this paper, authors have proposed a generalized ensemble model integrating deep learning techniques to generate accurate solar power forecasts for 21 solar photovoltaic facilities located in Germany. Most important weather parameters for solar power generation are selected through a feature selection process. In addition, a weather classification approach is used to cluster the dataset and for each cluster, a separate ensemble algorithm is assigned. Finally, considering the prediction errors in each cluster, a novel ensemble model is developed. The proposed models are evaluated using root mean square error and results are compared with single machine learning techniques and available forecasting models in the literature. Compared to deep belief network, support vector regression and random forest regression models, the proposed ensemble model with cloud classification reduces RMSE error by 10.49%, 7.78%, and 7.95% respectively. Results show that the weather classification approach reduces the forecasting error by a considerable margin and the proposed ensemble model provides a better forecasting accuracy than single machine learning methods.
- deep learning,
- ensemble models,
- solar PV,
- solar power forecasting,
- weather classification
Citation: P. A. G. M. Amarasinghe, N. S. Abeygunawardana, T. N. Jayasekara, E. A. J. P. Edirisinghe, S. K. Abeygunawardane. Ensemble models for solar power forecasting—a weather classification approach[J]. AIMS Energy, 2020, 8(2): 252-271. doi: 10.3934/energy.2020.2.252

Related Papers:

Abstract

Solar power integration has shown a significant growth in many power systems during the last decade. The intermittent nature of solar irradiance tends to vary the amount of solar power in the system and an accurate solar power forecasting method can be used to tackle this in power system planning and operation. In this paper, authors have proposed a generalized ensemble model integrating deep learning techniques to generate accurate solar power forecasts for 21 solar photovoltaic facilities located in Germany. Most important weather parameters for solar power generation are selected through a feature selection process. In addition, a weather classification approach is used to cluster the dataset and for each cluster, a separate ensemble algorithm is assigned. Finally, considering the prediction errors in each cluster, a novel ensemble model is developed. The proposed models are evaluated using root mean square error and results are compared with single machine learning techniques and available forecasting models in the literature. Compared to deep belief network, support vector regression and random forest regression models, the proposed ensemble model with cloud classification reduces RMSE error by 10.49%, 7.78%, and 7.95% respectively. Results show that the weather classification approach reduces the forecasting error by a considerable margin and the proposed ensemble model provides a better forecasting accuracy than single machine learning methods.

References

[1]	World Energy Council, World energy perspectives: renewable integrations 2016. World Energy Council, 2016. Available from: https://www.worldenergy.org/assets/images/imported/2016/10/World-Energy-Resources-Full-report-2016.10.03.pdf.
[2]	Singh M, Keswani S, Chitkara P, et al. (2017) 100% electricity generation through renewable energy by 2050- Assessment of Sri Lanka's Power Sector. Asian Development Bank and the United Nations Development Programme, 2017. Available from: adb.org/publications/electricity-generation-renewable-energy-2050-sri-lanka
[3]	International Energy Agency, Global Energy & CO2 Status Report 2017. International Energy Agency, 2017. Available from: https://www.iea.org/publications/freepublications/publication/GECO2017.pdf.
[4]	Wahlquist C, South Australia's Tesla battery on track to make back a third of cost in a year. Guardian News & Media Limited, 2018. Available from: https://www.theguardian.com/technology/2018/sep/27/south-australias-tesla-battery-on-track-to-make-back-a-third-of-cost-in-a-year.
[5]	Mohammed AA, Aung Z (2016) Ensemble learning approach for probabilistic forecasting of solar power generation. Energies 9: 1017. doi: 10.3390/en9121017
[6]	Shi J, Lee WJ, Liu Y, et al. (2011) Forecasting power output of photovoltaic systems based on weather classification and support vector machines. In proceedings of the 2011 IEEE Industry Applications Society Annual Meeting, 1-6.
[7]	De Leone R, Pietrini M, Giovannelli A (2015) Photovoltaic energy production forecast using support vector regression. Neural Comput Appl 26: 1955-1962. doi: 10.1007/s00521-015-1842-y
[8]	Yang HT, Huang CM, Huang YC, et al. (2014) A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output. IEEE Trans Sustainable Energy 5: 917-926. doi: 10.1109/TSTE.2014.2313600
[9]	Li Z, Rahman SM, Vega R, et al. (2016) A hierarchical approach using machine learning methods in solar photovoltaic energy production forecasting. Energies 9: 55. doi: 10.3390/en9010055
[10]	Abuella M, Chowdhury B (2016) Solar Power Forecasting Using Support Vector Regression. In proceedings of the 2016 American Society for Engineering Management Annual Conference.
[11]	Fentis A, Bahatti L, Mestari M, et al. (2017) Short-term solar power forecasting using Support Vector Regression and feed-forward NN. In proceedings of the 2017 IEEE 15th International New Circuits and Systems Conference: 405-408.
[12]	Das UK, Tey KS, Seyedmahmoudian M, et al. (2017) SVR-based model to forecast PV power generation under different weather conditions. Energies 10: 876. doi: 10.3390/en10070876
[13]	Bouzerdoum M, Mellit A, Massi PA (2013) A hybrid model (SARIMA-SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant. Sol Energy 98: 226-235. doi: 10.1016/j.solener.2013.10.002
[14]	Eseye AT, Zhang J, Zheng D (2018) Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information. Renewable Energy 118: 357-367. doi: 10.1016/j.renene.2017.11.011
[15]	Abedinia O, Raisz D, Amjady N (2017) Effective prediction model for Hungarian small-scale solar power output. IET Renewable Power Gener11: 1648-1658.
[16]	Abuella M, Chowdhury B (2015) Solar power forecasting using artificial neural networks. In proceedings of the 2015 North American Power Symposium (NAPS): 1-5.
[17]	Asrari A, Wu TX, Ramos B (2017) A hybrid algorithm for Short-Term Solar power prediction-sunshine state case study. IEEE Trans Sustainable Energy 8: 582-591. doi: 10.1109/TSTE.2016.2613962
[18]	Burianek T, Stuchly J, Misak S (2015) Solar power production forecasting based on recurrent neural network. In Advances in Intelligent Systems and Computing, Proceedings of the Second International Afro-European Conference for Industrial Advancement AECIA: 195-204.
[19]	Chen C, Duan S, Cai T, et al. (2011) Online 24-h solar power forecasting based on weather type classification using artificial neural network. Sol Energy 85: 2856-2870. doi: 10.1016/j.solener.2011.08.027
[20]	Ciaramella A, Staiano A, Cervone G, et al. (2016) A bayesian-based neural network model for solar photovoltaic power forecasting. Advances in Neural Networks, Cham: Springer, 169-177.
[21]	Muhammad ER, Simon SP, Venkateswaran PR (2017) Day-ahead forecasting of solar photovoltaic output power using multilayer perceptron. Neural Comput Appl 28: 3981-3992. doi: 10.1007/s00521-016-2310-z
[22]	Gensler A, Henze J, Sick B, et al. (2016) Deep Learning for solar power forecasting-An approach using Auto-Encoder and LSTM Neural Networks. In proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC): 2858-2865.
[23]	Nitisanon S, Hoonchareon N (2017) Solar power forecast with weather classification using self-organized map. In proceedings of the IEEE Power & Energy Society General Meeting: 1-5.
[24]	Rana M, Koprinska I, Agelidis VG (2016) Solar power forecasting using weather type clustering and ensembles of neural networks. In proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN): 4962-4969.
[25]	Singh VP, Vijay V, Bhatt MS, et al. (2013) Generalized neural network methodology for short term solar power forecasting. In proceedings of the 13th International Conference on Environment and Electrical Engineering (EEEIC): 58-62.
[26]	Behera MK, Majumder I, Nayak N, (2018) Solar photovoltaic power forecasting using optimized modified extreme learning machine technique. Eng Sci Technol, Int J 21: 428-438. doi: 10.1016/j.jestch.2018.04.013
[27]	Fernandez-Jimenez LA, Muñoz-Jimenez A, Falces A, et al. (2012) Short-term power forecasting system for photovoltaic plants. Renewable Energy 44: 311-317. doi: 10.1016/j.renene.2012.01.108
[28]	Dolara A, Grimaccia F, Leva S, et al. (2015) A physical hybrid artificial neural network for short term forecasting of PV plant power output. Energies 8: 1138-1153. doi: 10.3390/en8021138
[29]	Yona A, Senjyu T, Funabashi T (2007) Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system. In Proceedings of the 2007 IEEE Power Engineering Society General Meeting: 1-6.
[30]	Mandal P, Madhira STS, Ul HA, et al. (2012) Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques. Procedia Comput Sci 12: 332-337. doi: 10.1016/j.procs.2012.09.080
[31]	Ding M, Wang L, Bi R (2011) An ANN-based approach for forecasting the power output of photovoltaic system. Procedia Environ Sci 11: 1308-1315. doi: 10.1016/j.proenv.2011.12.196
[32]	Liu J, Fang W, Zhang X, et al. (2015) An improved photovoltaic power forecasting model with the assistance of aerosol index data. IEEE Trans Sustainable Energy 6: 434-442. doi: 10.1109/TSTE.2014.2381224
[33]	Mellit A, Massi PA, Lughi V (2014) Short-term forecasting of power production in a large-scale photovoltaic plant. Sol Energy 105: 401-413. doi: 10.1016/j.solener.2014.03.018
[34]	Chow SKH, Lee EWM, Li DHW (2012) Short-term prediction of photovoltaic energy generation by intelligent approach. Energy Build 55: 660-667. doi: 10.1016/j.enbuild.2012.08.011
[35]	Al-Dahidi S, Ayadi O, Adeeb J, et al. (2018) Extreme learning machines for solar photovoltaic power predictions. Energies 11: 2725. doi: 10.3390/en11102725
[36]	Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14: 1771-1800. doi: 10.1162/089976602760128018
[37]	Zhang Y, Beaudin M, Taheri R, et al. (2015) Day-Ahead power output forecasting for small-scale solar photovoltaic electricity generators. IEEE Trans Smart Grid 6: 2253-2262. doi: 10.1109/TSG.2015.2397003
[38]	Gensler A, Sick B, Pankraz V (2016) An analog ensemble-based similarity search technique for solar power forecasting. In Proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC): 2850-2857.
[39]	Monteiro C, Santos T, Fernandez-Jimenez LA, et al. (2013) Short-term power forecasting model for photovoltaic plants based on historical similarity. Energies 6: 2624-2643. doi: 10.3390/en6052624
[40]	Wu YK, Chen CR, Abdul RH (2014) A novel hybrid model for short-term forecasting in PV power generation. Int J Photoenergy 2014: ID-569249.
[41]	Raza MQ, Nadarajah M, Ekanayake C (2017) A multivariate ensemble framework for short term solar photovoltaic output power forecast. In Proceedings of the 2017 IEEE Power & Energy Society General Meeting: 1-5.
[42]	Omar M, Dolara A, Magistrati G, et al. (2016) Day-ahead forecasting for photovoltaic power using artificial neural networks ensembles. In Proceedings of the 2016 IEEE International Conference on Renewable Energy Research and Applications: 1152-1157.
[43]	Cervone G, Clemente HL, Alessandrini S, et al. (2017) Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble. Renewable Energy 108: 274-286. doi: 10.1016/j.renene.2017.02.052
[44]	Haque AU, Nehrir MH, Mandal P (2013) Solar PV power generation forecast using a hybrid intelligent approach. In Proceedings of the IEEE Power and Energy Society General Meeting: 1-5.
[45]	Abuella M, Chowdhury B (2017) Random forest ensemble of support vector regression models for solar power forecasting. In Proceedings of the 2017 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference: 1-5.
[46]	Sanjari MJ, Gooi HB (2016) Probabilistic forecast of PV power generation based on higher order markov chain. IEEE Trans Power Syst 32: 2942-2952.
[47]	Bracale A, Caramia P, Carpinelli G, et al. (2013) A bayesian method for Short-Term probabilistic forecasting of photovoltaic generation in smart grid operation and control. Energies 6: 733-747. doi: 10.3390/en6020733
[48]	Gulnar P, Rizwan M, Nidhi GN (2018) Intelligent model for solar energy forecasting and its implementation for solar photovoltaic applications. J Renewable Sustainable Energy 10: 063702. doi: 10.1063/1.5027824
[49]	Pereira S, Canhoto P, Salgado R, et al. (2019) Development of an ANN based corrective algorithm of the operational ECMWF global horizontal irradiation forecasts. Sol Energy 185: 387-405. doi: 10.1016/j.solener.2019.04.070
[50]	Wan C, Zhao J, Song Y, et al. (2015) Photovoltaic and solar power forecasting for smart grid energy management. CSEE J Power Energy Syst 1: 38-46. doi: 10.17775/CSEEJPES.2015.00046
[51]	Das UK, Tey KS, Seyedmahmoudian M, et al. (2018) Forecasting of photovoltaic power generation and model optimization: A review. Renewable Sustainable Energy Rev 81: 912-928. doi: 10.1016/j.rser.2017.08.017
[52]	Amarasinghe PAGM, Abeygunawardane SK, (2018) Application of Machine Learning Algorithms for Solar Power Forecasting in Sri Lanka. In proceedings of the 2nd International Conference on Electrical Engineering (EECon): 87-92.
[53]	Corne D, Dissanayake M, Peacock A, et al. (2015) Accurate localized short term weather prediction for renewables planning. In Proceedings of the IEEE Symposium on Computational Intelligence Applications in Smart Grid: 1-8.
[54]	Kursa MB, Rudnicki WR (2010) Feature Selection with the Boruta Package. J Stat Software 36: 1-13.
[55]	Coimbra CF, Kleissl J, Marquez R (2013) Overview of solar-forecasting methods and a metric for accuracy evaluation. Solar Energy Forecasting and Resource Assessment, Boston: Academic Press, 171-194.

Reader Comments

Your name:*

Email:*
© 2020 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)