# The Living Forecast: Evolving Day-Ahead Predictions into Intraday Reality

arXiv: https://arxiv.org/abs/2510.12271 · HTML: https://mlsanity.com/paper/2510.12271/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 7 of 7)

- [Flexible Model Aggregation for Quantile Regression](https://mlsanity.com/paper/2103.00083/) (2021)
- [Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systems](https://mlsanity.com/paper/2409.07637/) (2024)
- [Bayesian Hierarchical Probabilistic Forecasting of Intraday Electricity Prices](https://mlsanity.com/paper/2403.05441/) (2024)
- [GUIDE-VAE: Advancing Data Generation with User Information and Pattern Dictionaries](https://mlsanity.com/paper/2411.03936/) (2024)
- [Operating Dynamic Reserve Dimensioning Using Probabilistic Forecasts](https://mlsanity.com/paper/2108.09362/) (2021)
- [Probabilistic Load Forecasting of Distribution Power Systems based on Empirical Copulas](https://mlsanity.com/paper/2310.03657/) (2023)
- [One Model to Forecast Them All and in Entity Distributions Bind Them](https://mlsanity.com/paper/2501.15499/) (2025)

## Abstract (arXiv)

Accurate intraday forecasts are essential for power system operations, complementing day-ahead forecasts that gradually lose relevance as new information becomes available. This paper introduces a Bayesian updating mechanism that converts fully probabilistic day-ahead forecasts into intraday forecasts without retraining or re-inference. The approach conditions the Gaussian mixture output of a conditional variational autoencoder-based forecaster on observed measurements, yielding an updated distribution for the remaining horizon that preserves its probabilistic structure. This enables consistent point, quantile, and ensemble forecasts while remaining computationally efficient and suitable for real-time applications. Experiments on household electricity consumption and photovoltaic generation datasets demonstrate that the proposed method improves forecast accuracy up to 25% across likelihood-, sample-, quantile-, and point-based metrics. The largest gains occur in time steps with strong temporal correlation to observed data, and the use of pattern dictionary-based covariance structures further enhances performance. The results highlight a theoretically grounded framework for intraday forecasting in modern power systems.