Hour-ahead Forecasting of Photovoltaic Power Output based on Hidden Markov Model and Genetic Algorithm

Victor Eniola, Tawat Suriwong, Chatchai Sirisamphanwong, Kasamsuk Ungchittrakool

Abstract


It is well known that the variability in PV power output is primarily owing to fluctuations in radiation received by the solar panels. With short-term forecasting, intermittency problem associated with PV based power production as well as power quality issues can be addressed. Forecasting in the short-term horizon particularly is very crucial to power quality and power schedules such as load drop or gain, and power dispatch planning. This study details an innovative method based on ordinary model (Hidden Markov Model, HMM) and HMM optimized with Genetic Algorithm (GA) for hour-ahead forecasting of the power output (Po) of a 1.2 kW PV system. Solar irradiance (Gs), module temperature (Tm) acquired by mathematical modelling and wind speed (w) were used as initial forecast data. The forecast data was preprocessed and split into two quotas. The first was used in training the model developed based on HMM. To improve the performance of the forecasting model, GA was integrated. Secondly, the data was deployed to test and validate the proposed scheme. The model testing and validation was built on the computation of normalized Root Mean Square Error (nRMSE). As the results, GA-optimized HMM (HMM+GA) is able to forecast Po an hour-ahead with low nRMSE than HMM under clear sky day (CSD) condition. However, the abnormalities of the forecasting model resulting from instantaneous fluctuations in solar irradiance under cloudy day (CD) condition were decreased with correction factor (x). It was deduced that if the average change in the absolute value of solar irradiance is more than 128% and 90% in the morning and evening times respectively, the GA-optimized forecasting model with or without x presents average nRMSE of 2.33%. Therefore, HMM+GA gives more accurate Po forecast for CSDs whereas HMM+GA+x presents the best Po for CDs, supporting the consideration of the proposed forecast model as a good technique for hour-ahead power output forecasting of PV system.


Keywords


Forecasting; Photovoltaic; Power; Hidden Markov Model; Genetic Algorithm

Full Text:

PDF

References


R. Al-Hajj, A. Assi, and M.M. Fouad. "A predictive evaluation of global solar radiation using recurrent neural models and weather data", 2017 IEEE 6th International Conference on Renewable Energy Research and Applications (ICRERA), DOI: 10.1109/ICRERA.2017.8191265, p. 195-199, 2017.

A. Alzahrani, P. Shamsi, M. Ferdowsi, and C. Dagli. "Solar irradiance forecasting using deep recurrent neural networks", 2017 IEEE 6th International Conference on Renewable Energy Research and Applications (ICRERA), DOI: 10.1109/ICRERA.2017.8191206, p. 988-994, 2017.

H. Wang, H. Yi, J. Peng, G. Wang, Y. Liu, H. Jiang, and W. Liu, "Deterministic and probabilistic forecasting of photovoltaic power based on deep convolutional neural network", Energy Conversion and Management, 153: p. 409-422, 2017.

M. Yesilbudak, M. Çolak, and R. Bayindir. "A review of data mining and solar power prediction", 2016 IEEE International Conference on Renewable Energy Research and Applications (ICRERA), DOI: 10.1109/ICRERA.2016.7884507, p. 1117-1121, 2016.

M. Yesilbudak, M. Colak, R. Bayindir, and H.I. Bulbul. "Very-short term modeling of global solar radiation and air temperature data using curve fitting methods", 2017 IEEE 6th International Conference on Renewable Energy Research and Applications (ICRERA), DOI: 10.1109/ICRERA.2017.8191233, p. 1144-1148, 2017.

M. Omar, A. Dolara, G. Magistrati, M. Mussetta, E. Ogliari, and F. Viola. "Day-ahead forecasting for photovoltaic power using artificial neural networks ensembles", 2016 IEEE International Conference on Renewable Energy Research and Applications (ICRERA), DOI: 10.1109/ICRERA.2016.7884513, p. 1152-1157, 2016.

M. Yesilbudak, M. Colak, and R. Bayindir, "What are the Current Status and Future Prospects in Solar Irradiance and Solar Power Forecasting?", International Journal of Renewable Energy Research, 8(1), 2018.

A. Lahouar, A. Mejri, and J.B.H. Slama. "Importance based selection method for day-ahead photovoltaic power forecast using random forests", 2017 International Conference on Green Energy Conversion Systems (GECS), DOI: 10.1109/GECS.2017.8066171, p. 1-7, 2017.

E. Ogliari, A. Dolara, G. Manzolini, and S. Leva, "Physical and hybrid methods comparison for the day ahead PV output power forecast", Renewable Energy, 113: p. 11-21, 2017.

Y. Liu, L. Ye, H. Qin, X. Hong, J. Ye, and X. Yin, "Monthly streamflow forecasting based on hidden Markov model and Gaussian Mixture Regression", Journal of Hydrology, 561: p. 146-159, 2018.

L.R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition", Proceedings of the IEEE, 77(2): p. 257-286, 1989.

S. Leva, A. Dolara, F. Grimaccia, M. Mussetta, and E. Ogliari, "Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power", Mathematics and Computers in Simulation, 131: p. 88-100, 2017.

V. Sharma, D. Yang, W. Walsh, and T. Reindl, "Short term solar irradiance forecasting using a mixed wavelet neural network", Renewable Energy, 90: p. 481-492, 2016.

Y. Yang and L. Dong. "Short-Term PV Generation System Direct Power Prediction Model on Wavelet Neural Network and Weather Type Clustering", 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, DOI: 10.1109/IHMSC.2013.56, p. 207-211, 2013.

Y.z. Li, R. Luan, and J.c. Niu. "Forecast of power generation for grid-connected photovoltaic system based on grey model and Markov chain", 2008 3rd IEEE Conference on Industrial Electronics and Applications, DOI: 10.1109/ICIEA.2008.4582816, p. 1729-1733, 2008.

Z. Zhong, C. Yang, W. Cao, and C. Yan, "Short-Term Photovoltaic Power Generation Forecasting Based on Multivariable Grey Theory Model with Parameter Optimization", Mathematical Problems in Engineering, 2017: p. 9, 2017.

F. Barbieri, S. Rajakaruna, and A. Ghosh, "Very short-term photovoltaic power forecasting with cloud modeling: A review", Renewable and Sustainable Energy Reviews, 75: p. 242-263, 2017.

W. Zhang, X. Zheng, X.S.J. Geng, Q.N.J. Li, and C. Bao. "Short-term photovoltaic output forecasting based on correlation of meteorological data", IEEE Conference on Energy Internet and Energy System Integration (EI2), DOI: 10.1109/EI2.2017.8245285, p. 1-5, 2017.

L. Fen, L. Chunyang, Y. Yong, Y. Quanquan, Z. Jinbin, and W. Lijuan, "Short-term photovoltaic power probability forecasting based on OLPP-GPR and modified clearness index", The Journal of Engineering, 2017(13): p. 1625-1628, 2017.

M.G. De Giorgi, P.M. Congedo, M. Malvoni, and D. Laforgia, "Error analysis of hybrid photovoltaic power forecasting models: A case study of mediterranean climate", Energy Conversion and Management, 100: p. 117-130, 2015.

A.T. Eseye, J. Zhang, and D. Zheng, "Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information", Renewable Energy, 118: p. 357-367, 2018.

J. Li, J.K. Ward, J. Tong, L. Collins, and G. Platt, "Machine learning for solar irradiance forecasting of photovoltaic system", Renewable Energy, 90: p. 542-553, 2016.

S. Dubey, J.N. Sarvaiya, and B. Seshadri, "Temperature Dependent Photovoltaic (PV) Efficiency and Its Effect on PV Production in the World – A Review", Energy Procedia, 33: p. 311-321, 2013.

N. Savvakis and T. Tsoutsos, "Performance assessment of a thin film photovoltaic system under actual Mediterranean climate conditions in the island of Crete", Energy, 90: p. 1435-1455, 2015.

J. Joshi, K. Tankeshwar, and S. Srivastava, "Hidden Markov Model for Quantitative Prediction of Snowfall and Analysis of Hazardous Snowfall Events over Indian Himalaya", Journal of Earth System Science: p. 126: 033, 2017.

J. Wang, R. Ran, and Y. Zhou, "A Short-Term Photovoltaic Power Prediction Model Based on an FOS-ELM Algorithm", Applied Sciences, 7: p. 423, 2017.

M.Q. Raza, M. Nadarajah, and C. Ekanayake. "A multivariate ensemble framework for short term solar photovoltaic output power forecast", 2017 IEEE Power & Energy Society General Meeting, DOI: 10.1109/PESGM.2017.8274676, p. 1-5, 2017.




DOI (PDF): https://doi.org/10.20508/ijrer.v9i2.9348.g7659

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is cited in SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics);

IJRER has been cited in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2025; 

h=35,

Average citation per item=6.59

Last three Years Impact Factor=(1947+1753+1586)/(146+201+78)=5286/425=12.43

Category Quartile:Q4