Bayesian Neural Networks with Monte Carlo Dropout for Probabilistic Electricity Price Forecasting

TL;DR

This paper introduces a probabilistic electricity price forecasting method using Bayesian neural networks with Monte Carlo dropout, outperforming traditional models in accuracy and uncertainty quantification.

Contribution

It presents a novel framework applying Bayesian neural networks with MC dropout for hourly electricity price prediction, capturing uncertainties effectively.

Findings

Proposed model outperforms GARCHX and LEAR in point and interval predictions.

Separate models for each hour capture diurnal price patterns.

Framework enhances risk management in electricity markets.

Abstract

Accurate electricity price forecasting is critical for strategic decision-making in deregulated electricity markets, where volatility stems from complex supply-demand dynamics and external factors. Traditional point forecasts often fail to capture inherent uncertainties, limiting their utility for risk management. This work presents a framework for probabilistic electricity price forecasting using Bayesian neural networks (BNNs) with Monte Carlo (MC) dropout, training separate models for each hour of the day to capture diurnal patterns. A critical assessment and comparison with the benchmark model, namely: generalized autoregressive conditional heteroskedasticity with exogenous variable (GARCHX) model and the LASSO estimated auto-regressive model (LEAR), highlights that the proposed model outperforms the benchmark models in terms of point prediction and intervals. This work serves as a reference for leveraging probabilistic neural models in energy market predictions.