Forecasting the Generation of Wind Power in the Western and Southern Regions of India: Comparative Approach

Das, Saptarshi (2020) Forecasting the Generation of Wind Power in the Western and Southern Regions of India: Comparative Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

With the increasing power demand, driven by the rising population and the push towards cleaner energy, India has grown interested in the production of wind-energy due to its renewable nature and high inhouse generation rate. Currently, the states of Tamil Nadu and Maharashtra have been producing the highest amounts of wind-energy. However, to make an informed decision regarding the maximum power output, the generated wind power needs to be predicted beforehand. Intriguingly, wind power forecasting can be generally viewed as a univariate time series analysis problem requiring the usage of complex variable like wind speed, keeping the turbine constant into consideration. Therefore, it can be challenging to model wind speed patterns using standard time series models like ARIMA. In this context, machine learning and neural network-based algorithms have been shown to successfully overcome these limitations. Still, the practicability of simpler yet powerful parsimonious models including Facebook, Inc's Prophet has not been tested in the purview of this specific domain. In this work, five timeseries forecasting models (ARIMA, Dynamic Harmonic Regression, Neural Network, Prophet, Simple Exponential Smoothing) have been implemented for predicting the wind speed (later converted to wind power) in both Tamil Nadu and Maharashtra. The evaluation results indicate that the neural network approach worked best for the given datasets. Nevertheless, the forecasts from the Prophet model were also promising and can be improved as part of future work. Moreover, these research findings can be incorporated into projects involving the site-suitability analysis for developing wind farms across different Indian states.

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 T Technology > TD Environmental technology. Sanitary engineering
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	10 Jun 2020 17:23
Last Modified:	10 Jun 2020 17:23
URI:	https://norma.ncirl.ie/id/eprint/4267

Actions (login required)

View Item