Generalized Neural Network Approach for Global Solar Energy Estimation in India

Abstract

In India, large areas of land are barren and sparsely populated, making these areas suitable as locations for large central power stations based on solar energy. India is located in the equatorial sun belt of the earth, thereby receiving abundant radiant energy from the sun. Estimating solar energy accurately is a big task to exploit the solar potential for power generation. A number of conventional and intelligent models are available; how- ever, the results are not satisfactory due to extreme simplicity of their parameterization. In this paper, application of generalized neural network (GNN), a modified approach of artificial neural network (ANN), is proposed to estimate solar energy to overcome the problems of ANN such as a large number of neurons and layers required for complex function approximation, which do not affect the training time only but also the fault tolerant capabilities of the ANN. The mean relative error in the estimation of global solar energy is found around 4% whereas the same using fuzzy logic is 6% approximately. Therefore, it is concluded that the GNN technique is found more accurate for the estimation of global solar energy.