M$^2$OE$^2$-GL: A Family of Probabilistic Load Forecasters That Scales to Massive Customers

TL;DR

This paper introduces M2OE2-GL, a scalable probabilistic load forecasting method that combines global pretraining with lightweight local fine-tuning, effectively handling heterogeneity across large customer datasets.

Contribution

It presents a novel global-to-local extension of the M2OE2 forecaster, enabling scalable and accurate load predictions across thousands of customers.

Findings

Substantial error reductions achieved

Scales effectively to very large load datasets

Maintains computational efficiency

Abstract

Probabilistic load forecasting is widely studied and underpins power system planning, operation, and risk-aware decision making. Deep learning forecasters have shown strong ability to capture complex temporal and contextual patterns, achieving substantial accuracy gains. However, at the scale of thousands or even hundreds of thousands of loads in large distribution feeders, a deployment dilemma emerges: training and maintaining one model per customer is computationally and storage intensive, while using a single global model ignores distributional shifts across customer types, locations, and phases. Prior work typically focuses on single-load forecasters, global models across multiple loads, or adaptive/personalized models for relatively small settings, and rarely addresses the combined challenges of heterogeneity and scalability in large feeders. We propose M2OE2-GL, a global-to-local extension of the M2OE2 probabilistic forecaster. We first pretrain a single global M2OE2 base model across all feeder loads, then apply lightweight fine-tuning to derive a compact family of group-specific forecasters. Evaluated on realistic utility data, M2OE2-GL yields substantial error reductions while remaining scalable to very large numbers of loads.