Probabilistic electric load forecasting through Bayesian Mixture Density Networks

TL;DR

This paper introduces a Bayesian Mixture Density Network approach for probabilistic electric load forecasting, effectively capturing uncertainties and providing robust predictions for smart energy grid management.

Contribution

The paper presents a novel Bayesian Mixture Density Network framework that models both aleatoric and epistemic uncertainties in load forecasting, integrating variational inference and deep ensembles.

Findings

Achieves robust probabilistic load forecasts in household settings

Effectively captures both types of predictive uncertainties

Demonstrates scalability and reliability across different conditions

Abstract

Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. Neural networks are widely considered to achieve improved prediction performances, supporting highly flexible mappings of complex relationships between the target and the conditioning variables set. However, obtaining comprehensive predictive uncertainties from such black-box models is still a challenging and unsolved problem. In this work, we propose a novel PLF approach, framed on Bayesian Mixture Density Networks. Both aleatoric and epistemic uncertainty sources are encompassed within the model predictions, inferring general conditional densities, depending on the input features, within an end-to-end training framework. To achieve reliable and computationally scalable estimators of the posterior distributions, both Mean Field variational inference and deep ensembles are integrated. Experiments have been performed on household short-term load forecasting tasks, showing the capability of the proposed method to achieve robust performances in different operating conditions.