Multi-task Online Learning for Probabilistic Load Forecasting

2025-02-06

AI Summary

Existing multi-task load forecasting methods for power systems struggle to characterize load uncertainty and adapt to dynamically evolving consumption patterns. This paper proposes a dynamic graph neural network framework that integrates online learning with multi-task learning, enabling— for the first time—the real-time modeling of time-varying inter-regional and inter-building load similarities. The framework incorporates quantile regression to produce calibrated probabilistic forecasts. By jointly addressing uncertainty quantification and time-varying structural modeling, it achieves significant improvements in both point prediction accuracy and probabilistic calibration across diverse real-world datasets, including scenarios involving abrupt changes, periodic drifts, and heterogeneity. Compared to state-of-the-art multi-task approaches, it reduces the Continuous Ranked Probability Score (CRPS) by 12.7%.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Load forecasting is essential for the efficient, reliable, and cost-effective management of power systems. Load forecasting performance can be improved by learning the similarities among multiple entities (e.g., regions, buildings). Techniques based on multi-task learning obtain predictions by leveraging consumption patterns from the historical load demand of multiple entities and their relationships. However, existing techniques cannot effectively assess inherent uncertainties in load demand or account for dynamic changes in consumption patterns. This paper proposes a multi-task learning technique for online and probabilistic load forecasting. This technique provides accurate probabilistic predictions for the loads of multiple entities by leveraging their dynamic similarities. The method's performance is evaluated using datasets that register the load demand of multiple entities and contain diverse and dynamic consumption patterns. The experimental results show that the proposed method can significantly enhance the effectiveness of current multi-task learning approaches across a wide variety of load consumption scenarios.

Problem

• improves load forecasting accuracy
• assesses load demand uncertainties
• handles dynamic consumption patterns

Innovation

• Multi-task online learning
• Probabilistic load forecasting
• Dynamic similarity leveraging