PERBANDINGAN AKURASI PREDIKSI KONSUMSI BIAYA LISTRIK RUMAH TANGGA MENGGUNAKAN METODE SINGLE EXPONENTIAL SMOOTHING DAN SINGLE MOVING AVERAG

Abstract

Abstract

Forecasting household electricity consumption is important in energy planning and management. The accuracy

of this forecasting can help make decisions regarding generating capacity, energy distribution and electricity

tariffs. This research aims to compare the accuracy of household electricity consumption predictions using two

statistical methods, namely Single Exponential Smoothing (SES) and Single Moving Average (SMA). The data used

was taken from household electricity consumption from January 2023 to September 2024. The SES method was

applied with adjusted smoothing parameters, while SMA was used to capture more dynamic consumption patterns.

The analysis results show that the SES method is more accurate with lower MAE and RMSE values. The predicted

price of household electricity consumption for October 2024 is IDR 62987.7 using the SES method, while using

the SMA method the prediction is IDR 56365.3. This study concludes that SES is more effective for predicting

household electricity consumption and recommends this method in future energy planning