<![CDATA[The increasing electricity demand and the growing complexity of distribution networks require PLN to employ accurate load forecasting to ensure system reliability. This challenge is evident in the SG 06 Feeder of ULP Meureudu, which exhibits highly fluctuating load patterns, significant disparities between average and peak loads, and a relatively low load factor. These characteristics reduce the effectiveness of conventional forecasting methods and highlight the need for a model capable of accurately capturing temporal patterns. This study develops a short-term load forecasting model based on a Gated Recurrent Unit (GRU) architecture, utilizing time-based features as the sole input variables. The research process includes historical data collection, preprocessing, time-series windowing, model training, and performance evaluation using RMSE, MAE, and MAPE. The results show that the GRU model is able to generate stable and accurate predictions for both daily and weekly load patterns of the SG 06 Feeder, outperforming the simple statistical and time-based reference models used for comparison. The proposed model provides a reliable solution to support operational decision-making and enhance the reliability of the 20 kV distribution network managed by ULP Meureudu.]]>
Copyrights © 2026
