Publication

Abstract : Weather forecasting is the application of science and technology to soothsay the state of the atmosphere for a future time at a given location. It is carried out by amassing quantitative data about the current state of the atmosphere and past and/or present experiences. A neural network can learn intricate mapping from inputs to outputs, predicated solely on samples. In this paper, a neural network-predicated algorithm for soothsaying the wind velocity is presented. The Neural Networks package fortifies variants of training or learning algorithms. One such algorithm is Back Propagation Neural Network (BPN) technique. This method is more efficient than numerical differentiation. The results showed that this model could be applied to weather prognostication quandaries. The performance evaluation of the model carried out on the substructure of Root Mean Square Error (RMSE) showed that the BPN model yielded good results with a lower prognostication error. The energy engendered is calculated utilizing the forecasted value of wind velocity and the tolerance values are calculated according to the distinguishment between genuine and presaged values. Assuming the average load at a place is taken constant, calculation of the battery reserve for a particular day with the avail of OPTIM tool is done.