Select the most relevant input parameters usingWEKA for models forecast Solar radiation based onArtificial Neural Networks

Forecasting solar radiation is important for manyapplications in research related to renewable energy.Solar radiation is forecasted by solar radiation forecastmodels including the traditional models and artificialneural network (ANN) based model. There aregeographical and meteorological variables that affect thesolar radiation, thus identifying the appropriate variablesto forecast solar radiation correctly is an important issuein the research area. Accordingly Waikato Environmentfor Knowledge Analysis (WEKA) Software was used in11 points in Guilan based on different weather conditionsto find the most effective input parameters to forecastsolar radiation in different ANN models. Inputparameters include latitude, longitude, maximum windspeed, average temperatures in each month, the averagemaximum air temperature, average minimum airtemperature, sunshine, monthly rainfall, maximumrainfall in a day for different cities of Gilan. In order tocheck the reliability of the forecasts by knownparameters, three ANN models have developed (ANN-1,ANN-2 and ANN-3). The maximum MAPE for ANN-1,ANN-2 and ANN-3 equals 22.15%, 20.29% and 22.14%,respectively indicating 1.86% improvement in theaccuracy in the prediction of ANN-2.

Select the most relevant input parameters usingWEKA for models forecast Solar radiation based onArtificial Neural Networks Keywords:

Neural Network , Data Mining , WEKA