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

2025/11/12 by Abhinav Das, Das, Abhinav, Stephan Schlüter +1
Engineering · #Electric Power System Optimization #Energy Load and Power Forecasting #FOS: Computer and information sciences #G.3 #Machine Learning (cs.LG) #Smart Grid Energy Management

paper · pdf · doi:10.48550/arxiv.2511.11701

openalex publication_date 2025/11/12 · openalex created_date 2025/11/19 · openalex updated_date 2026/07/29

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.

Citations

• Electricity Price Prediction Using Multi-Kernel Gaussian Process Regression Combined with Kernel-Based Support Vector Regression
• Probabilistic electric load forecasting: A tutorial review
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Related

• Learning the Probability Distributions of Day-Ahead Electricity Prices
• Analyzing Uncertainty Quantification in Statistical and Deep Learning Models for Probabilistic Electricity Price Forecasting
• Neural networks in day-ahead electricity price forecasting: Single vs.\n multiple outputs
• Regime-Aware Conditional Neural Processes with Multi-Criteria Decision Support for Operational Electricity Price Forecasting
• Probabilistic intraday electricity price forecasting using generative machine learning