Photovoltaic Power Prediction for Solar Car Park Lighting Office Energy Management

Abstract

Abstract The photovoltaic energy is widely used in modern power network due to its environmental and economic benefits. Solar car park is one of the solar photovoltaic system applications. The photovoltaic energy has disadvantages of intermittence and weather's variation. Thus, photovoltaic power prediction is very necessary to guarantee a balance between the produced energy and the solar car park requirements. The prediction of the photovoltaic energy is related to solar irradiation and ambient temperature forecasting. The aim of this study was to evaluate various methodologies for weather data estimation, namely, the empirical models, the multilayer perceptron neural network (MLPNN), and the adaptive neuro-fuzzy inference system (ANFIS). The simulation results show that the ANFIS model can be successfully used to forecast the photovoltaic power. The forecasted photovoltaic energy was used for the solar car park lighting office management algorithm.