This paper presents a novel generative probabilistic forecasting approach
derived from the Wiener-Kallianpur innovation representation of nonparametric
time series. Under the paradigm of generative artificial intelligence, the
proposed forecasting architecture includes an autoencoder that transforms
nonparametric multivariate random processes into canonical innovation
sequences, from which future time series samples are generated according to
their probability distributions conditioned on past samples. A novel
deep-learning algorithm is proposed that constrains the latent process to be an
independent and identically distributed sequence with matching autoencoder
input-output conditional probability distributions. Asymptotic optimality and
structural convergence properties of the proposed generative forecasting
approach are established. Three applications involving highly dynamic and
volatile time series in real-time market operations are considered: (i)
locational marginal price forecasting for merchant storage participants, {(ii)
interregional price spread forecasting for interchange markets,} and (iii) area
control error forecasting for frequency regulations. Numerical studies based on
market data from multiple independent system operators demonstrate superior
performance against leading traditional and machine learning-based forecasting
techniques under both probabilistic and point forecast metrics.

本文提出了一种新颖的生成式概率预测方法，基于非参数时间序列的 Wiener-Kallianpur 创新表示。在生成人工智能的范式下，提出的预测架构包括一个自编码器，将非参数多变量随机过程转化为规范化的创新序列，根据过去样本的条件概率分布生成未来时间序列样本。提出了一种新颖的深度学习算法，使潜在过程成为具有匹配自编码器输入 - 输出条件概率分布的独立同分布序列。该生成式预测方法具有渐近最优性和结构收敛性质。研究了三个应用领域，包括实时市场操作中的高动态和高波动时间序列：(i) 商业储能参与者的位置边际价格预测，(ii) 互联市场的区域价格差预测，以及 (iii) 频率调节的区域控制误差预测。基于多个独立系统运营商的市场数据的数值研究表明，在概率和点预测指标下，与传统的和基于机器学习的预测技术相比，该方法具有更优越的性能。