Zero-Shot Load Forecasting with Large Language Models

TL;DR

This paper introduces Chronos, a zero-shot load forecasting model based on large language models, which achieves high accuracy in data-scarce scenarios without additional training, outperforming traditional models across multiple datasets.

Contribution

Proposes a novel zero-shot load forecasting approach using an advanced LLM framework, demonstrating its effectiveness without dataset-specific training.

Findings

Chronos significantly reduces forecasting errors compared to baseline models.

The model performs well across various forecast horizons and datasets.

It outperforms nine popular baseline models in deterministic and probabilistic load forecasting.

Abstract

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.