Optimal Selection of Weather Stations for Electric Load Forecasting

For the proper planning and operation of any electric power system, it is essential to have a reliable software tool that allows for accurate short-term forecasting consumption. Temperature one most important drivers energy consumption selecting appropriate weather station or combination stations crucial improving accuracy. In this study, we propose an algorithm determine optimal selection based on (i) initial reduction in problem complexity, which drastically decreases computational cost, (ii) posterior incremental search algorithm. The proposed methodology, identifies number locations be used their specific geographical locations, exhaustively tested using three insightful case studies real data from Spanish mainland grid two different forecast databases, denoting significant errors. developed method currently use by transmission system operator (Red Eléctrica de Espa na, REE) make hourly forecasts.