Zero-Shot Load Forecasting with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Wenlong, Yang, Zhe, Jia, Mengshuo, Rehtanz, Christian, Fang, Jiannong, Porté-Agel, Fernando
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917840490070016
author Liao, Wenlong
Yang, Zhe
Jia, Mengshuo
Rehtanz, Christian
Fang, Jiannong
Porté-Agel, Fernando
author_facet Liao, Wenlong
Yang, Zhe
Jia, Mengshuo
Rehtanz, Christian
Fang, Jiannong
Porté-Agel, Fernando
contents Deep learning models have shown strong performance in load forecasting, but they generally require large amounts of data for model training before being applied to new scenarios, which limits their effectiveness in data-scarce scenarios. Inspired by the great success of pre-trained language models (LLMs) in natural language processing, this paper proposes a zero-shot load forecasting approach using an advanced LLM framework denoted as the Chronos model. By utilizing its extensive pre-trained knowledge, the Chronos model enables accurate load forecasting in data-scarce scenarios without the need for extensive data-specific training. Simulation results across five real-world datasets demonstrate that the Chronos model significantly outperforms nine popular baseline models for both deterministic and probabilistic load forecasting with various forecast horizons (e.g., 1 to 48 hours), even though the Chronos model is neither tailored nor fine-tuned to these specific load datasets. Notably, Chronos reduces root mean squared error (RMSE), continuous ranked probability score (CRPS), and quantile score (QS) by approximately 7.34%-84.30%, 19.63%-60.06%, and 22.83%-54.49%, respectively, compared to baseline models. These results highlight the superiority and flexibility of the Chronos model, positioning it as an effective solution in data-scarce scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11350
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-Shot Load Forecasting with Large Language Models
Liao, Wenlong
Yang, Zhe
Jia, Mengshuo
Rehtanz, Christian
Fang, Jiannong
Porté-Agel, Fernando
Machine Learning
Signal Processing
Deep learning models have shown strong performance in load forecasting, but they generally require large amounts of data for model training before being applied to new scenarios, which limits their effectiveness in data-scarce scenarios. Inspired by the great success of pre-trained language models (LLMs) in natural language processing, this paper proposes a zero-shot load forecasting approach using an advanced LLM framework denoted as the Chronos model. By utilizing its extensive pre-trained knowledge, the Chronos model enables accurate load forecasting in data-scarce scenarios without the need for extensive data-specific training. Simulation results across five real-world datasets demonstrate that the Chronos model significantly outperforms nine popular baseline models for both deterministic and probabilistic load forecasting with various forecast horizons (e.g., 1 to 48 hours), even though the Chronos model is neither tailored nor fine-tuned to these specific load datasets. Notably, Chronos reduces root mean squared error (RMSE), continuous ranked probability score (CRPS), and quantile score (QS) by approximately 7.34%-84.30%, 19.63%-60.06%, and 22.83%-54.49%, respectively, compared to baseline models. These results highlight the superiority and flexibility of the Chronos model, positioning it as an effective solution in data-scarce scenarios.
title Zero-Shot Load Forecasting with Large Language Models
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2411.11350