ABSTRACT
Forecasting models are used to produce Energy Planning Models (EPMs) in developing renewable energy farms. One such application is the forecasting of daily global solar radiation, which is the energy being converted into PV power. In this study, results show that Gaussian process regression (GPR) and nonlinear autoregressive network with exogenous inputs (NARX) are equally proficient forecasting models for daily global solar radiation in Dumaguete, Philippines using only a relatively small dataset. A long short-term memory (LSTM) network was also trained to forecast global solar radiation. Combining the two produced a NARX-LSTM hybrid with a root mean square error (RMSE) of approximately 0.10. The global solar radiation forecast from this study could be used in calculating the amount of energy the PV cells from solar energy farms can harness in a day. Furthermore, the forecasting model can be used in the further development and improvement of energy planning models.
- U.T. Jesus Tamang Director, E.A. Carmencita Bariso, M.O. Sinocruz, Philippine Energy Plan 2012-2030, n.d.Google Scholar
- Department of Energy. 2019. 2019 Power StatisticsGoogle Scholar
- H. Wang, Y. Liu, B. Zhou, C. Li, G. Cao, N. Voropai, E. Barakhtenko. 2020. Taxonomy research of artificial intelligence for deterministic solar power forecasting, Energy Convers Manag.. https://doi.org/10.1016/j.enconman.2020.112909.Google ScholarCross Ref
- K.B. Debnath, M. Mourshed, Forecasting methods in energy planning models, Renew Sustain Energy Rev. 88 (2018) 297–325. https://doi.org/10.1016/j.rser.2018.02.002.Google ScholarCross Ref
- M. Massaoudi, I. Chihi, L. Sidhom, M. Trabelsi, S.S. Refaat, F.S. Oueslati. 2019. A Novel Approach Based Deep RNN Using Hybrid NARX-LSTM Model For Solar Power Forecasting. 1–9. http://arxiv.org/abs/1910.10064.Google Scholar
- J. Schmidhuber, EVOLINO, (2008). http://people.idsia.ch/∼juergen/evolino.html.Google Scholar
- E. Gordo, N. Khalaf, T. Strangeowl. 2015. Factors Affecting Solar Power PRODUCTION EFFICIENCY,1–18.Google Scholar
- K. Vidyanandan. 2017. An Overview of Factors Affecting the Performance of Solar PV Systems, Energy Scan. 27, 2–8.Google Scholar
- C.M.S. Creayla, F.C.C. Garcia, E.Q.B. Macabebe, 2017. Next Day Power Forecast Model Using Smart Hybrid Energy Monitoring System and Meteorological Data.Google Scholar
- J. Zheng, H. Zhang, Y. Dai, B. Wang, T. Zheng, Q. Liao, Y. Liang, F. Zhang, X. Song. 2020. Time series prediction for output of multi-region solar power plants, Appl Energy. https://doi.org/10.1016/j.apenergy.2019.114001.Google ScholarCross Ref
- F. Rodríguez, A. Fleetwood, A. Galarza, L. Fontán. 2018. Predicting solar energy generation through artificial neural networks using weather forecasts for microgrid control, Renew Energy.. https://doi.org/10.1016/j.renene.2018.03.070.Google ScholarCross Ref
- K. Li, T. Wang, M. Shi, Z. Xuan, Z. Zhen, F. Wang, A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework, (n.d.).Google Scholar
- T. Cai, S. Duan, C. Chen. 2010. Forecasting power output for grid-connected photovoltaic power system without using solar radiation measurement, 2nd Int Symp Power Electron Distrib Gener Syst PEDG 2010. https://doi.org/10.1109/PEDG.2010.5545754.Google ScholarCross Ref
- M. Louzazni, H. Mosalam, A. Khouya, A non-linear auto-regressive exogenous method to forecast the photovoltaic power output, Sustain Energy Technol Assessments. 38 (2020). https://doi.org/10.1016/j.seta.2020.100670.Google ScholarCross Ref
- Data Source: Climate and Agrometeorological Data Section (CADS), Philippine Atmospheric, Geophysical and Astronomical Services Administration (PAGASA).Google Scholar
- Data Source: National Solar Radiation Center, Philippine Atmospheric, Geophysical and Astronomical Services Administration (PAGASA).Google Scholar
- Gaussian Processes, not quite for dummies, (n.d.). https://thegradient.pub/gaussian-process-not-quite-for-dummies/ (accessed June 7, 2021).Google Scholar
Index Terms
- Forecasting of daily global solar radiation in Dumaguete, Philippines using NARX-LSTM Hybrid Network
Recommendations
Wind speed forecasting using the NARX model, case: La Mata, Oaxaca, México
This study presents the generation of a nonlinear autoregressive exogenous model (NARX) for wind speed forecasting in a 1 h, in advance horizon. A sample of meteorological data of hourly measurements taken during a year was used for the generation of ...
Numerical Weather Prediction Data Free Solar Power Forecasting with Neural Networks
e-Energy '18: Proceedings of the Ninth International Conference on Future Energy SystemsThe worldwide increase in renewable energy penetration levels has made accuracy, availability, and affordability of wind and solar energy forecasting systems an integral part of the modern power grids. The present paper describes an approach to ...
Forecasting of solar radiation using different machine learning approaches
AbstractIn this study, monthly solar radiation (SR) estimation was performed using five different machine learning-based approaches. The models used are support vector machine regression (SVMR), long short-term memory (LSTM), Gaussian process regression (...
Comments