NORMA eResearch @NCI Library

Mid Term Forecasting of Solar Power Generation in India: A Statistical Approach

Gupta, Garima (2020) Mid Term Forecasting of Solar Power Generation in India: A Statistical Approach. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


As a developing country, the electricity demand in India is increasing rapidly, but the generation using existing resources lacks in fulfilling the demand. The primary source of electricity generation is nonrenewable resources that are environmentally unfriendly and costly. Renewable resources such as solar power, wind power, hydropower, etc could solve this problem, due to the fact of its abundant availability, cost-effective and environment-friendly nature. Installation of solar photovoltaic plants can help in minimizing this energy crisis, but the intermittency in power generation can cause fluctuations at the supply end. This issue can be addressed using an accurate forecasting system that can handle seasonalities. Various machine learning techniques ARIMA, SES, DHR, Neural Network, TBATS, and Prophet have been implemented on historical data of Rajasthan and Andhra Pradesh and the main focus of this research project was forecasting solar power generation with the help of the best model among these by evaluating the performance using evaluation metrics RMSE, MAE, and MAPE. TBATS model has given the best performance over applied models with an RMSE of 3.395737 for Rajasthan data and ARIMA with an RMSE of 1.9261 was the best performing model for Andhra Pradesh time series data.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 22 Jan 2021 12:59
Last Modified: 22 Jan 2021 12:59

Actions (login required)

View Item View Item