Generative Probabilistic Time Series Forecasting and Applications in Grid Operations

arXiv:2402.13870v1 Announce Type: new
Abstract: Generative probabilistic forecasting produces future time series samples according to the conditional probability distribution given past time series observations. Such techniques are essential in risk-based decision-making and planning under uncertainty with broad applications in grid operations, including electricity price forecasting, risk-based economic dispatch, and stochastic optimizations. Inspired by Wiener and Kallianpur's innovation representation, we propose a weak innovation autoencoder architecture and a learning algorithm to extract independent and identically distributed innovation sequences from nonparametric stationary …

abstract applications arxiv cs.lg decision distribution economic eess.sp electricity forecasting future generative grid making operations planning price probability risk samples series stat.ap stochastic time series time series forecasting type uncertainty