用贝叶斯更新将日间预测转为实时电力预测，无需重新训练。
The Living Forecast: Evolving Day-Ahead Predictions into Intraday Reality
- 基于变分自编码器的预测结果，用观测数据动态修正概率分布。
- 在多个指标上提升最高达25%的准确率，尤其在相关性强的时间段。
- 适合电力系统实时调度，保持计算效率与概率结构一致性。
精确的日内预测对电力系统运行至关重要，可弥补日间预测随新信息出现而逐渐失效的问题。本文提出一种贝叶斯更新机制，无需重新训练或推理，即可将全概率化的日间预测转化为日内预测。该方法以观测数据为条件，对基于条件变分自编码器的高斯混合输出进行修正，得到剩余时段的更新概率分布，同时保持其概率结构。该方法支持一致的点预测、分位数预测与集合预测，在计算效率上适合实时应用。在家庭用电与光伏发电数据集上的实验表明，所提方法在似然、采样、分位数和点预测指标上，准确率最高提升25%。性能增益在与观测数据强时间相关的时段最为显著，引入基于模式字典的协方差结构进一步提升效果。结果验证了该方法在现代电力系统中的理论合理性与实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。