June 17 Grid Analytics Community – Bayesian Deep Learning for Photovoltaic Power Forecasting: A Probabilistic Framework for Uncertainty Quantification and Grid Reliability Optimization

Join the Grid Analytics Community on Wednesday, June 17 at 1:00 PM CT for a presentation with Q&A/open discussion on “Bayesian Deep Learning for Photovoltaic Power Forecasting: A Probabilistic Framework for Uncertainty Quantification and Grid Reliability Optimization” led by Pablo Bustamante, Data Science and Business Intelligence Analyst at El Paso Electric.

Session Description:

This presentation investigates solar photovoltaic (PV) power forecasting under uncertainty using machine learning, Bayesian deep learning, and decision-theoretic modeling to improve grid reliability and operational planning. Traditional forecasting methods such as linear regression, random forests, and neural networks are first evaluated using utility-scale solar and weather data, followed by the development of a Bayesian deep learning framework combining CNNs, LSTMs, and Transformer models to produce probabilistic forecasts that capture both aleatoric and epistemic uncertainty. The presentation then connects these uncertainty-aware forecasts to operational decision-making through reserve allocation and reliability assessment, demonstrating that probabilistic forecasting frameworks provide improved reliability and economic efficiency compared to traditional deterministic approaches while offering a practical pathway for renewable energy integration into modern grid operations.

*UAI Utility Members can register and access all nine of our Analytics Communities via our Community Page. Not a part of the Grid Analytics Community and want to join this session? Please use our direct link here to request access. You will find the Teams meeting credentials to the upcoming meeting at the top of the feed on this page. If you have any questions or run into any issues, please contact us at info@utilityanalytics.com.