Short Term Load Forecasting using SVM Models

For the planning, operation, and control of power system, load forecasting plays a vital role. It is necessary to forecast the electrical load accurately for the efficient working of distribution systems. Besides these, it is also essential for security analysis, unit commitment, fuel purchase scheduling and maintenance schedule. To minimize the errors in forecasting, the paper uses Support Vector Machines (SVM) and Artificial Neural Networks (ANN) as machine learning models for the load forecasting. Real measurements collected in Indian Institute of Technology Kanpur (IITK) substation arc used to validate the study. The data used in the modeling of Feed Forward Neural Network (FFNN) arc hourly electricity load and historical temperature data. The hourly load data of IITK substation from April-2017 to June-2017 is used for training of FFNN model and SVM models, and testing was done on test data for next week. It can be seen from the simulation results that hourly load forecast using proposed SVM models are more accurate than FFNN model.