Grasshopper Optimized Tuning of Support Vector Regression for Day a Head Prognostic Problem

Recently, the scenario behind the power system operation and control is not even because of the fluctuating power demands. The ultimate reason for this fluctuation is climatic variables. It is highly recommended to identify the method which produces precise forecasting. This article brings an approach that utilizes Support Vector Regression and tuning parameters of Support vector using an enhanced Grasshopper optimization algorithm for predicting the future demand by analyzing the influence of weather parameters for a North East India data. The parameter tuning still improves the accuracy of SVR. Further the parameters that were tuned by GOA was examined, by giving it to a Support vector regression for a building energy consumption data on a JMP Pro 16 environment.