Power Generation Forecasting of Dual-Axis Solar Tracked PV System Based on Averaging and Simple Weighting Ensemble Neural Networks

  • Budiman Putra Asma'ur Rohman Research Center for Electronics and Telecommunication, Indonesian Institute of Sciences (PPET-LIPI)
  • Catur Hilman Department of Engineering Physics, ITS
  • Erik Tridianto Politeknik Elektronika Negeri Surabaya
  • Teguh Hady Ariwibowo Politeknik Elektronika Negeri Surabaya
Keywords: photovoltaic, power output, solar tracking, forecasting, ensemble neural network

Abstract

Solar power is a renewable energy interest many researchers around the world to be explored for human life beneficial especially for electric power generation. Photovoltaic (PV) is one of technology developed massively to exploit the solar power for this purpose. However, its performance is very sensitive to environmental condition such as solar irradiance, weather, and climatic behavior. Thus, the hybrid power generation systems are developed to solve this output uncertainty problem. To support this such hybrid system, this paper proposes an ensemble neural network based forecaster of the power output of PV systems which will lead an efficient power management. The object of this research is the PV systems equipped with two axes automated solar tracking with peak power 10Wp. The proposed ensemble forecaster model employs four multi-layer perceptron neural networks with two hidden layers as base forecasters while the input number of historical data is varied in order to exploit the forecaster diversity. The final prediction is calculated both by conventional averaging and simple weighting optimized by the least square fitting technique. According to the research results, the both proposed approaches provide low error rate. Moreover, in term of comparison, the ensemble model with averaging combining technique gives the highest accuracy comparing to the other ensemble and conventional neural network structures.

Downloads

Download data is not yet available.

Author Biographies

Budiman Putra Asma'ur Rohman, Research Center for Electronics and Telecommunication, Indonesian Institute of Sciences (PPET-LIPI)
Kampus LIPI Gd.20, Lt.4, Jalan Sangkuriang, Bandung, IndonesiaKampus LIPI Gd.20, Lt.4, Jalan Sangkuriang, Bandung, Indonesia
Erik Tridianto, Politeknik Elektronika Negeri Surabaya
Politeknik Elektronika Negeri Surabaya

References

Häberlin, Heinrich, Photovoltaics system design and practice,John Wiley & Sons, 2012.

Yona, Atsushi, et al., Application of neural network to one-day-ahead 24 hours generating power forecasting for photovoltaic system,Intelligent Systems Applications to Power Systems, 2007. ISAP 2007. International Conference on. IEEE, 2007.

Shi, Jie, et al.,Forecasting power output of photovoltaic systems based on weather classification and support vector machines,IEEE Transactions on Industry Applications 48.3, pp 1064-1069, 2012.

Su, Yan, et al.,Real-time prediction models for output power and efficiency of grid-connected solar photovoltaic systems. Applied Energy 93,pp 319-326, 2012.

Li, Yanting, Yan Su, and Lianjie Shu, An ARMAX model for forecasting the power output of a grid connected photovoltaic system,Renewable Energy 66, pp 78-89, 2014.

Yang, Hong-Tzer, et al, A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output,IEEE transactions on sustainable energy 5.3,pp 917-926, 2014.

Dolara, Alberto, et al,A physical hybrid artificial neural network for short term forecasting of PV plant power output,Energies 8.2,pp 1138-1153, 2015.

Larson, David P., Lukas Nonnenmacher, and Carlos FM Coimbra,Day-ahead forecasting of solar power output from photovoltaic plants in the American Southwest,Renewable Energy 91, pp 11-20, 2016.

Rokach, Lior,Ensemble-based classifiers, Artificial Intelligence Review, 33.1-2, pp 1-39, 2010.

L. K. Hansen and P. Salamon, Neural Network Ensembles, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, pp. 993-1001, 1990.

Rahman, Akhlaqur, and Sumaira Tasnim,Ensemble Classifiers and Their Applications: A Review, arXiv preprint arXiv:1404.4088, 2014.

Maqsood, Imran, Muhammad Riaz Khan, and Ajith Abraham, An ensemble of neural networks for weather forecasting. Neural Computing and Applications, 13.2, pp 112-122.13, 2004.

Y. Li, S. Gao, and S. Chen, Ensemble feature weighting based on local learning and diversity, 26th AAAI Conf. Artificial Intelligence, pp. 1019–1025. 14, 2012.

Mc Leod, Peter, and Brijesh Verma,Variable Hidden Neuron Ensemble for Mass Classification in Digital Mammograms. IEEE Computational Intelligence Magazine, 8.1, pp. 68-76. 15, 2013.

Barrow, Devon K., and Sven F. Crone, Crogging (cross-validation aggregation) for forecasting - A novel algorithm of neural network ensembles on time series subsamples. Neural Networks (IJCNN), The 2013 International Joint Conference on. IEEE, 2013.

Pulido, Martha, and Patricia Melin, Ensemble Neural Network Optimization Using the Particle Swarm Algorithm with Type-1 and Type-2 Fuzzy Integration for Time Series Prediction. Recent Advances on Hybrid Approaches for Designing Intelligent Systems. Springer International Publishing, 99-112 17, 2014.

Hilman, Catur, E. Tridianto, TH Ariwibowo, Budiman PA Rohman, Forecasting of Power Output of 2-Axis Solar Tracked PV Systems using Ensemble Neural Network, International Electronics Symposium (IES) IEEE, 2017.

Hilman, Catur and Ali Musyafa, Rancang Bangun Dual-Axis PV Solar Tracker System MenggunakanInterval Type-2 Fuzzy Logic Controller, Seminar Nasional Pascasarjana XIV – ITS, 2015.

Naftaly, Ury, Nathan Intrator, and David Horn, Optimal ensemble averaging of neural networks. Network: Computation in Neural Systems. 8.3, pp. 283-296. 12, 1997.

Rahman, Akhlaqur, and Sumaira Tasnim, Ensemble Classifiers and Their Applications: A Review, arXiv preprint arXiv:1404.4088, 2014.

Hagan, Martin T., and Mohammad B. Menhaj, Training feedforward networks with the Marquardt algorithm, Neural Networks, IEEE Transactions on 5.6, pp. 989-993, 1994.

Jiang, Yingni, Prediction of monthly mean daily diffuse solar radiation using artificial neural networks and comparison with other empirical models, Energy policy,Vol.36,n10,pp.3833-3837, 2008.

Simon Haykin, Neural Networks. A Comprehensive Foundation, 2ndEdition, Prentice Hall, 1999.

Published
2018-12-29
How to Cite
Rohman, B. P. A., Hilman, C., Tridianto, E., & Ariwibowo, T. H. (2018). Power Generation Forecasting of Dual-Axis Solar Tracked PV System Based on Averaging and Simple Weighting Ensemble Neural Networks. EMITTER International Journal of Engineering Technology, 6(2), 275-288. https://doi.org/10.24003/emitter.v6i2.341
Section
Articles