HARNESSING POTENTIALS OF SOLAR RADIATION IN LIBERIA USING ARTIFICIAL NEURAL NETWORK

Abstract

The current state of energy supply in Liberia is a combination of fossil fuel and hydroelectric power generation and the cost of generating, maintaining, and distributing energy is high. On the other hand, Liberia lies within a suitable zone for solar energy utilisation for photovoltaic applications, as its climate is relatively hot all year round. This paper investigates the use of the artificial neural network to model the reliability of solar radiation in a study area in Liberia, as a necessary prerequisite for alternative power generation. Seven variables (longitude, latitude, elevation, average temperature, precipitation, wind speed and relative humidity) were used as input data (causal variables) and one parameter/factor (solar radiation) was used as output (response variable) for 2000-2018. The obtained results showed that the employed model explains all the variabilities of the response data around the mean with an overall regression value of 0.93. It was found through visualised maps that the study area is in a suitable spot for the utilisation of solar energy potentials.