Adaptive Multi-task Learning for Probabilistic Load Forecasting

TL;DR

This paper introduces an adaptive multi-task learning approach for probabilistic load forecasting that dynamically adjusts to changing consumption patterns and correlations among multiple entities, improving prediction accuracy and uncertainty estimation.

Contribution

It proposes a novel adaptive multi-task learning method based on vector-valued hidden Markov models that updates in real-time, addressing limitations of offline methods in load forecasting.

Findings

Outperforms existing load forecasting methods in accuracy.

Provides reliable probabilistic load predictions and uncertainty assessments.

Effectively adapts to dynamic consumption pattern changes.

Abstract

Simultaneous load forecasting across multiple entities (e.g., regions, buildings) is crucial for the efficient, reliable, and cost-effective operation of power systems. Accurate load forecasting is a challenging problem due to the inherent uncertainties in load demand, dynamic changes in consumption patterns, and correlations among entities. Multi-task learning has emerged as a powerful machine learning approach that enables the simultaneous learning across multiple related problems. However, its application to load forecasting remains underexplored and is limited to offline learning methods, which cannot capture changes in consumption patterns. This paper presents an adaptive multi-task learning method for probabilistic load forecasting. The proposed method can dynamically adapt to changes in consumption patterns and correlations among entities. In addition, the techniques presented provide reliable probabilistic predictions for loads of multiple entities and assess load uncertainties. Specifically, the method is based on vectorvalued hidden Markov models and uses a recursive process to update the model parameters and provide predictions with the most recent parameters. The performance of the proposed method is evaluated using datasets that contain the load demand of multiple entities and exhibit diverse and dynamic consumption patterns. The experimental results show that the presented techniques outperform existing methods both in terms of forecasting performance and uncertainty assessment.