• Yogita Mohanrao Shinde
• Prof.Dipak Gupta

The rapid increase in solar power plant installed capacity leads to considerable difficulties in terms of power system operation and control, resulting from highly stochastic nature of solar energy harvesting. The paper considers the problem of day- ahead solar power plant output forecasting, based on the meteorological data. The improvement of solar power plant output prediction will significantly simplify power system operation mode planning taking into market procedures and active power generation reserves allocation. As a case study the authors use meteorological data for a real operated solar power plant. As a results of regression modelling the statistical significance of the meteorological parameters was analyzed. The optimal mathematical formulation of regression model was provided. In addition, the paper gives the idea of empirical cauterization approach, providing significant improvement of prediction accuracy. The results of the verification on real data allow deciding on the applicability of the proposed methods in industrial operation.

Time series Analysis, Regression Analysis, Clustering, Forecasting of electricity generation, solar power plants, Machine Learning.

"Implementation on Solar Forecasting Analysis using ML", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 8, page no.813-818, August-2020, Available :http://www.jetir.org/papers/JETIR2008106.pdf

"Implementation on Solar Forecasting Analysis using ML", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 8, page no. pp813-818, August-2020, Available at : http://www.jetir.org/papers/JETIR2008106.pdf