A Meta-learning based Distribution System Load Forecasting Model Selection Framework

TL;DR

This paper introduces a meta-learning framework for automatic selection of load forecasting models in distribution systems, improving accuracy across diverse tasks through a multi-step process.

Contribution

It develops a novel meta-learning based framework that automates load forecast model selection, enhancing adaptability and accuracy for various distribution system scenarios.

Findings

Framework achieves high accuracy in seen tasks

Performs well on unseen forecasting tasks

Effective in heterogeneous load forecasting scenarios

Abstract

This paper presents a meta-learning based, automatic distribution system load forecasting model selection framework. The framework includes the following processes: feature extraction, candidate model labeling, offline training, and online model recommendation. Using user load forecasting needs as input features, multiple meta-learners are used to rank the available load forecast models based on their forecasting accuracy. Then, a scoring-voting mechanism weights recommendations from each meta-leaner to make the final recommendations. Heterogeneous load forecasting tasks with different temporal and technical requirements at different load aggregation levels are set up to train, validate, and test the performance of the proposed framework. Simulation results demonstrate that the performance of the meta-learning based approach is satisfactory in both seen and unseen forecasting tasks.