•  
  •  
 

Abstract

This paper presents a means for the short term load forecasting (STLF) of electricity. The forthcoming Integrated-Single Electricity Market (I-SEM) diverges from the current market structure (the Single Electricity Market or SEM), with significant impacts on Irish supply companies, creating a need for these companies to be able to accurately forecast their customers’ load in the Day Ahead. Using a Double Seasonal Exponential Smoothing variation of the Holt-Winters method that factors in an error correction, data from the Irish market was trained and used to forecast a supply company’s demand resulting in an average daily MAPE (Mean Absolute Percentage Error) of 2.99% over a period of nearly four weeks. The suite of formulas used employs daily and weekly seasonal components to forecast a full day’s (48 half-hour periods) demand.

DOI

10.21427/D75G90

Share

COinS