MLMC-based Resource Adequacy Assessment with Active Learning Trained Surrogate Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ruiqi, Tindemans, Simon H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909712004415488
author Zhang, Ruiqi
Tindemans, Simon H.
author_facet Zhang, Ruiqi
Tindemans, Simon H.
contents Multilevel Monte Carlo (MLMC) is a flexible and effective variance reduction technique for accelerating reliability assessments of complex power system. Recently, data-driven surrogate models have been proposed as lower-level models in the MLMC framework due to their high correlation and negligible execution time once trained. However, in resource adequacy assessments, pre-labeled datasets are typically unavailable. For large-scale systems, the efficiency gains from surrogate models are often offset by the substantial time required for labeling training data. Therefore, this paper introduces a speed metric that accounts for training time in evaluating MLMC efficiency. Considering the total time budget is limited, a vote-by-committee active learning approach is proposed to reduce the required labeling calls. A case study demonstrates that, within a given computational budget, active learning in combination with MLMC can result in a substantial reduction variance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20930
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MLMC-based Resource Adequacy Assessment with Active Learning Trained Surrogate Models
Zhang, Ruiqi
Tindemans, Simon H.
Machine Learning
Multilevel Monte Carlo (MLMC) is a flexible and effective variance reduction technique for accelerating reliability assessments of complex power system. Recently, data-driven surrogate models have been proposed as lower-level models in the MLMC framework due to their high correlation and negligible execution time once trained. However, in resource adequacy assessments, pre-labeled datasets are typically unavailable. For large-scale systems, the efficiency gains from surrogate models are often offset by the substantial time required for labeling training data. Therefore, this paper introduces a speed metric that accounts for training time in evaluating MLMC efficiency. Considering the total time budget is limited, a vote-by-committee active learning approach is proposed to reduce the required labeling calls. A case study demonstrates that, within a given computational budget, active learning in combination with MLMC can result in a substantial reduction variance.
title MLMC-based Resource Adequacy Assessment with Active Learning Trained Surrogate Models
topic Machine Learning
url https://arxiv.org/abs/2505.20930