Assessing Electricity Demand Forecasting with Exogenous Data in Time Series Foundation Models

TL;DR

This study evaluates the effectiveness of time-series foundation models for electricity demand forecasting with exogenous data, revealing variable performance influenced by model architecture and geographic climate, and emphasizing domain-specific approaches.

Contribution

It provides an empirical comparison of foundation models against a baseline in electricity demand forecasting, highlighting architecture and climate as key factors affecting performance.

Findings

Chronos-2 performs best among foundation models in zero-shot settings.

Baseline often outperforms foundation models in stable climates for short-term forecasts.

Model architecture and geographic context significantly influence forecasting effectiveness.

Abstract

Time-series foundation models have emerged as a new paradigm for forecasting, yet their ability to effectively leverage exogenous features -- critical for electricity demand forecasting -- remains unclear. This paper empirically evaluates foundation models capable of modeling cross-channel correlations against a baseline LSTM with reversible instance normalization across Singaporean and Australian electricity markets at hourly and daily granularities. We systematically assess MOIRAI, MOMENT, TinyTimeMixers, ChronosX, and Chronos-2 under three feature configurations: all features, selected features, and target-only. Our findings reveal highly variable effectiveness: while Chronos-2 achieves the best performance among foundation models (in zero-shot settings), the simple baseline frequently outperforms all foundation models in Singapore's stable climate, particularly for short-term horizons. Model architecture proves critical, with synergistic architectural implementations (TTM's channel-mixing, Chronos-2's grouped attention) consistently leveraging exogenous features, while other approaches show inconsistent benefits. Geographic context emerges as equally important, with foundation models demonstrating advantages primarily in variable climates. These results challenge assumptions about universal foundation model superiority and highlight the need for domain-specific models, specifically in the energy domain.