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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Haoran, Cheng, Zhe, Guo, Muhao, Weng, Yang, Sun, Yannan, Tran, Victor, Chainaranont, John
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912724263370752
author Li, Haoran
Cheng, Zhe
Guo, Muhao
Weng, Yang
Sun, Yannan
Tran, Victor
Chainaranont, John
author_facet Li, Haoran
Cheng, Zhe
Guo, Muhao
Weng, Yang
Sun, Yannan
Tran, Victor
Chainaranont, John
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17623
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M$^2$OE$^2$-GL: A Family of Probabilistic Load Forecasters That Scales to Massive Customers
Li, Haoran
Cheng, Zhe
Guo, Muhao
Weng, Yang
Sun, Yannan
Tran, Victor
Chainaranont, John
Machine Learning
Artificial Intelligence
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.
title M$^2$OE$^2$-GL: A Family of Probabilistic Load Forecasters That Scales to Massive Customers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.17623