Predicting Solar Irradiance With SVM Regression

12 Pages Posted: 2 Jan 2019 Last revised: 14 Jan 2019

Date Written: November 24, 2018

Abstract

This paper describes using manifold learning for dimensionality reduction along with support vector machines for regression to predict the solar irradiance given historical weather data. A critical struggle in the renewable energy industry is combining the unpredictable renewable energy sources with pre-existing energy sources in an efficient way to minimize cost and pollution. By using machine learning, we are able to achieve high accuracy in prediction which can be very useful in controlling the output of fossil fuel output, yet maintaining a constant flow of energy to consumers. The synchronization of solar and non-renewable energy is explored from both a deterministic and stochastic approach, with the stochastic formulation showing promise.

Keywords: Support Vector Machines, Manifold Learning, Solar Energy, Grid Integration

Suggested Citation

Palaniappan, Vivek, Predicting Solar Irradiance With SVM Regression (November 24, 2018). Available at SSRN: https://ssrn.com/abstract=3302155 or http://dx.doi.org/10.2139/ssrn.3302155

Vivek Palaniappan (Contact Author)

University of Cambridge ( email )

Cambridge
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
90
Abstract Views
503
rank
336,838
PlumX Metrics