Two-Stage Load Forecasting for Residual Reduction and Economic Dispatch Using PJM Datasets

摘要

This paper discusses preliminary results obtained using auto-regressive integrated moving average (ARIMA), and exponential smoothing (ES) forecasting methods for loads in 11 regions of PJM Interconnection. The datasets used to predict day-ahead loads include demand values in both 24-hour and 30-day format for 2016 calendar year for multiple (e.g., 11 regions) areas. The accuracy of forecasting is evaluated using Mean Absolute Percentage Error (MAPE) and Mean Absolute Deviation (MAD) parameters. An economic dispatch was then carried using a linear programming formulation in Algebraic Mathematical Programming Language (AMPL) environment. The preliminary results indicate ARIMA outperforms ES for both 24-hour and 30-day to predict day-ahead forecasting.