ARLOS: Adaptive Forecasting and Risk-Calibrated Load Operation in Distribution Substations Under Distribution Shift

Forecast accuracy alone is an incomplete proxy for operational value when load distributions change. This paper presents ARLOS, an auditable forecast–uncertainty–decision framework that combines static and adaptive XGBoost forecasts, rolling performance monitoring, residual-bootstrap uncertainty, and explicit fixed-margin, quantile, and risk-target operating rules. The evaluation uses 2021 for ex ante training and capacity-proxy definition and 2022–2023 for strictly sequential testing on two Ecuadorian distribution substations under a measured baseline, smooth growth, and intraday structural shift. Under the four shifted station–scenario cases, adaptive fixed-margin operation reduced the weighted operational objective by 24.8–46.0% relative to the static fixed-margin baseline; baseline-regime changes ranged from −2.5 to 11.2%, showing that adaptation is valuable primarily when mismatch is present rather than universally. A 2×2 ablation further shows that adaptation and uncertainty are distinct, non-additive sources of operational value: aggregate normalized cost changes from 0.987 for static/fixed operation to 0.650 for adaptive/fixed, 0.515 for static/quantile, and 0.546 for adaptive/quantile. Realized one-sided exceedance, computed from observed load rather than from the bootstrap sample itself, remains within 0.0039–0.0111 of the target across the controlled cases, while nominal 10–90% interval coverage ranges from 78.0% to 78.6%. A nine-substation deployment check corroborates the calibration and identifies a measured drift episode in which adaptation limits, but does not eliminate, forecast degradation. The results support ARLOS as a transparent framework for studying how adaptation and uncertainty propagate into operational consequences under distribution shift.These contributions align with Sustainable Development Goal 7 (Affordable and Clean Energy) and Sustainable Development Goal 9 (Industry, Innovation and Infrastructure) by supporting more reliable, efficient, and intelligent operation of electricity distribution infrastructure.