Analysis of Solar Power Variability Due to Seasonal Variation and its Forecasting for Jodhpur Region Using Artificial Neural Network

##plugins.themes.academic_pro.article.main##

Vikas Pratap Singh
Vivek Vijay
S. H. Gaurishankar
D. K. Chaturvedi
N. Rajkumar

Abstract

In 21st century solar power variability is an important issue due to grid integration. In these days grid integration is very popular because of heavy load. So solar power, wind power and conventional power are basic sources of grid integration. Solar power is playing a key role in grid integration. The main objective of this paper is to analyse solar power variability due to seasonal variation in Jodhpur. Jodhpur is known as sun-city for an average 320 sunny days in a year. Average solar insolation available in Jodhpur city is 5.7-6.0 kWh/m>sup<2>/sup< per day. This is second highest insolation in the world. In this paper, the Solar power variability analysis is carried out based on the data collected from a typical 43 kW amorphous silicon solar photovoltaic system installed in Jodhpur. Mansoon, winter and summer seasons are used for analysis of variation in Photovoltaic Generation due to change of solar insolation. Output of solar photovoltaic system depends on solar insolation and in this paper we have analysed the variation in solar power according to rainy, winter and summer seasons and used artificial neural network to predict the power output from PV system. The paper showed that proposed ANN model is more accurate and study of variability in solar power can help in plant operation, power scheduling and dispatchability.

##plugins.themes.academic_pro.article.details##

How to Cite
Singh, V. P., Vijay, V., Gaurishankar, S. H., Chaturvedi, D. K., & Rajkumar, N. (2013). Analysis of Solar Power Variability Due to Seasonal Variation and its Forecasting for Jodhpur Region Using Artificial Neural Network. Power Research - A Journal of CPRI, 423–430. Retrieved from https://node6473.myfcloud.com/~geosocin/CPRI/index.php/pr/article/view/883

References

  1. M. Osborne, “Gartner posts long range forecast for photovoltaic’s industry,” March 2009, http://www.pvtech.org/news/a/gartner posts long range forecast for photovoltaic industry.
  2. Yoo S, Lee E, Lee K. Buildingintegrated photovoltaics: a Korean case study.Solar Energy 1998;64:151–61.
  3. Amit Konar: Artificial intelligence and soft computing: behavioral and cognitive modeling of the human brain –CRC press 2000.
  4. Chaturvedi, D.K., Satsangi, P.S. & Kalra, P.K, Fuzzified Neural Network Approach for Load Forecasting Problems, Int. J. on Engineering Intelligent Systems, CRL Publishing, U.K., Vol. 9, No. 1, March 2001, pp.3-9.
  5. EI Desouky, A.A. and M.M. EI Kateb, 2000. Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA, IEE. Proceedings, Gener. Trans. Distrib., 147: 213-217.
  6. Khotanzad, A.; Enwang Zhou; Elragal, H.; “A Neuro-Fuzzy Approach to Short Term Load Forecasting in a Price-Sensitive Environment”, IEEE Transactions on Power Systems, Vol.17, pp. 1273 – 1282, 2002.
  7. Chaturvedi, D.K., Mohan, M., and Kalra, P.K., Development of flexible neural network, Journal of the Institution of Engineers (India), CP, 83: 1–5, 2002.
  8. Devendra K. Chaturvedi: Soft computing Techniques and its Applications in Electrical Engineering - Springer- Verlag Berlin Heidelberg, 2008.
  9. Arbib, M.A. Handbook of Brain Theory and Neural Networks, 2nd edn. MIT Press, Cambridge, MA, 2003.
  10. Ricardo Marquez, Hugo T.C. Pedro, Carlos F.M. Coimbra, 2013. “Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs” Solar Energy 86 (7), 2017–2028.

Similar Articles

<< < 1 2 3 > >> 

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)

1 2 > >>