Development of Photovoltaic Power Generation Prediction Model using ANFIS

Abstract

Prediction of photovoltaic (PV) performance is important for energy management practices. The power produced from renewable energy sources is uncertain in nature as it is subjected to continuous changing weather conditions. Hence accurate prediction of output power from these sources is difficult task. In this paper Adaptive Neuro-Fuzzy Inference System (ANFIS) based forecast model for predicting the PV power generation is developed. The proposed model is based on back propagation hybrid learning algorithm of ANFIS with four inputs and one output. Experimentally measured input data of 20 KW. PV system installed at Nashik, Maharashtra, India is used for developing prediction model. The inputs are solar radiation (Rad), ambient temperature (Temp), relative humidity (Hum) and day of year for measurement. Photovoltaic power generation is the output of the model. This data is utilized in the training and testing of the proposed model. Results obtained confirm the ability of the developed ANFIS model for assessing the power produced with reasonable accuracy. A comparative study has done between regression analysis and ANFIS. This shows that the ANFIS-model performs much better than regression. The advantage of the ANFIS model is that they do not need more parameters or complicate calculations unlike implicit models. The developed model could be used to forecast the profile of the produced power in uncertain whether conditions. The error due to ANFIS prediction model for energy produced from the given system considered in this research is 6.14 % which is much better when compared with regression analysis whose error is 16 %. The results indicate that this model can potentially be used to estimate and predict PV solar output power.