One-Shot Price Forecasting with Covariate-Guided Experts under Privacy Constraints

TL;DR

This paper introduces a MoE Encoder module that enhances pre-trained multivariate time series forecasting models by enabling expert-guided univariate transformation and federated training, improving accuracy while respecting privacy constraints.

Contribution

The paper proposes a novel MoE Encoder layer that improves zero-shot domain adaptation and privacy-preserving federated learning for time series forecasting.

Findings

MoE-Encoder significantly outperforms strong baselines in accuracy.

Federated transfer of MoE-Encoder parameters enables efficient adaptation.

The approach maintains high performance with minimal data sharing.

Abstract

Forecasting in power systems often involves multivariate time series with complex dependencies and strict privacy constraints across regions. Traditional forecasting methods require significant expert knowledge and struggle to generalize across diverse deployment scenarios. Recent advancements in pre-trained time series models offer new opportunities, but their zero-shot performance on domain-specific tasks remains limited. To address these challenges, we propose a novel MoE Encoder module that augments pretrained forecasting models by injecting a sparse mixture-of-experts layer between tokenization and encoding. This design enables two key capabilities: (1) trans forming multivariate forecasting into an expert-guided univariate task, allowing the model to effectively capture inter-variable relations, and (2) supporting localized training and lightweight parameter sharing in federated settings where raw data cannot be exchanged. Extensive experiments on public multivariate datasets demonstrate that MoE-Encoder significantly improves forecasting accuracy compared to strong baselines. We further simulate federated environments and show that transferring only MoE-Encoder parameters allows efficient adaptation to new regions, with minimal performance degradation. Our findings suggest that MoE-Encoder provides a scalable and privacy-aware extension to foundation time series models.