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

2026-01-17

AI Summary

This work addresses the challenges of generalizing multivariate time series forecasting in power systems under cross-regional privacy constraints and heavy reliance on expert knowledge. To this end, we propose a pretraining-based temporal prediction framework that integrates sparse Mixture-of-Experts (MoE) with federated learning. By inserting an MoE module between tokenization and encoding, our approach decouples multivariate forecasting into expert-guided univariate tasks, marking the first application of MoE architecture to enhance pretrained time series models. This design enables effective modeling of inter-variable relationships and efficient cross-regional knowledge transfer while preserving data privacy. Experimental results on public datasets demonstrate that our method significantly outperforms strong baselines. In federated simulations, sharing only lightweight MoE parameters allows rapid adaptation to new regions with minimal performance degradation.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• price forecasting
• privacy constraints
• multivariate time series
• federated learning
• power systems

Innovation

• Mixture-of-Experts
• federated learning
• time series forecasting
• privacy-preserving
• pretrained models