Short Term Load Forecasting Using Sliding-Window LSTM in DKI Jakarta Power Subsystems

Abstract

Subsystem-level short-term load forecasting is important not only for capturing heterogeneous load characteristics, but also for maintaining system reliability and supporting accurate operational decision-making. While many existing studies focus on aggregated system-level forecasting, such approaches may may fail to capture localized load dynamics localized load dynamics in large interconnected systems. This paper proposes a validation-driven, subsystem-aware multi-horizon Stacked LSTM framework for seven power subsystems in DKI Jakarta using two years of 30-minute resolution operational data (August 2023-July 2025). The proposed framework integrates validation-driven sliding window optimization, architecture tuning, and weather feature evaluation within a structured experimental pipeline. A strict chronological split is applied, and final performance is evaluated on a fully unseen operational month (July 2025) to ensure outof-sample generalization. Across the seven subsystems, the optimized models achieve test MAPE values ranging from 3.34% to 9.24%, demonstrating reliable forecasting performance under heterogeneous load dynamics. Weather feature evaluation revealed subsystem-dependent responses. A Wilcoxon signed-rank test indicates no statistically significant difference between the Baseline and All-Weather configurations p-value 0.43, despite subsystem-dependent responses to meteorological variables. The results indicate that subsystemspecific parameter configurations, determined through validation, are essential for accurate subsystem-level short-term load forecasting in heterogeneous smart grid systems, while weather information should be incorporated selectively according to subsystem characteristics.