A Neural Network-based Time-Series Model for Predicting Global Solar Radiations

Abstract

Global solar radiation is variable in nature, hence its forecasting is very important. This paper aims to predict the global solar radiations using real experimental data collected over time by developing time series based neural networks in MATLAB. In this research work three models are developed, one for the daily prediction of global solar radiations and two for the hourly (with and without night times) prediction of the global solar radiations. The results obtained are evaluated using statistical analysis which confirmed that nonlinear autoregressive models are a good choice for predicting the global solar radiations. The regression coefficient was found high in the case of hourly prediction (including night hours) followed by hourly prediction (excluding night hours) and daily prediction (after averaging) respectively. The value of the best validation performance for hourly prediction (including night hours) was found 0.060887 with a regression coefficient of 0.96481. To further validate the applicability of the proposed algorithm, the model was compared with four time-series models developed in Waikato Environment for Knowledge Analysis. The results confirmed the high efficiency of our proposed models among others, based on the performance parameters root mean square error and mean Absolute error. The root mean square error for our proposed model came 1.28 which is the lowest as compared to other time series models. Also, the accuracy of the hourly prediction model was found higher as compared to daily prediction models. Further, the critical analysis of our method with various available methods in the literature is also discussed.

KEYWORDS:

• Artificial neural networks
• Global solar radiations
• Photovoltaics
• Regression
• Solar energy
• Time series

ACKNOWLEDGEMENTS

The authors would like to acknowledge the support provided by the National Institute of Technology Hamirpur (H.P) and Baba Ghulam Shah Badshah University Rajouri (J&K) in the successful completion of this research work. The support was provided in terms of the use of laboratory infrastructure and library.

Additional information

Funding

The funding was provided through TEQIP-III by NPIU in the form of a Research Grant with sanction number:BGSBU/TEQIP-III/RGS/014.

Notes on contributors

Shafqat Nabi Mughal

Shafqat Nabi Mughal is working as an assistant professor in the Department of Electrical Engineering, Baba Ghulam Shah Badshah University Rajouri (J&K). He has more than 10 years of teaching & research experience. He has published more than 40 research publications. His research interests include renewable energy technologies, deregulation, machine learning, etc. He is the recipient of the top 50 distinguished researcher award by Green Thinkerz. He is a member of IEEE, IEI and ISTE. Corresponding author. Email: [email protected]

Yog Raj Sood

Yog Raj Sood, former director, NIT Puducherry, obtained his BE degree in electrical engineering and ME in power systems from PEC Chandigarh, India in 1984 and 1987, respectively. He was awarded a PhD degree from the Indian Institute of Technology, Roorkee. He has more than 30 years of teaching, research, and administrative experience. He is presently working as a professor (HAG) with the Department of Electrical Engineering, NIT Hamirpur. His research interests include deregulation of power systems, condition monitoring of power transformer, and non-conventional sources of energy. Email: [email protected]

R.K. Jarial

R K Jarial is working as associate professor in the Electrical Engineering Department, National Institute of Technology, Hamirpur, India. He has completed his BSc Engineering (Electrical) and MTech (Power Systems) from Regional Engineering College, Kurukshetra (now, National Institute of Technology, Kurukshetra) in 1989 and 1991, respectively. He completed his PhD in 2007 from the University of Rajasthan through MNIT Jaipur (Raj.) He joined NIT Hamirpur in 1994 and has been involved in the development of the High Voltage Lab in the Electrical Engineering Department since 1995. He has played a prominent role in creating an industry sponsored center (TIFAC CORE) on “Power Transformer Diagnostics” wef 2000. This center has been jointly funded by the Department of Science & Technology, through TIFAC Delhi, HP State Electricity Board Ltd., Shimla, and NIT Hamirpur, respectively. Dr Jarial has authored many professional publications in key journals and conferences. His research interests include power electronics drives, diagnostic analysis of power transformers, and high voltage systems. He is a life member of ISTE, Associate Member (IE), Calcutta, IEEE DEIS Society, IEEE Power Electronics. Email: [email protected]