Decision-Oriented Learning for Future Power System Decision-Making under Uncertainty

TL;DR

This paper discusses decision-oriented learning (DOL) as an innovative approach that improves decision-making in power systems under uncertainty by replacing traditional statistical loss with decision-focused loss functions.

Contribution

It explains the mismatch between forecast accuracy and decision quality in power systems, reviews DOL techniques, and discusses challenges and future directions for DOL adoption.

Findings

DOL aligns model training with decision quality rather than statistical accuracy.

Traditional statistical learning may lead to suboptimal decisions despite accurate forecasts.

DOL techniques have specific advantages and limitations in power system applications.

Abstract

Better forecasts may not lead to better decision-making. To address this challenge, decision-oriented learning (DOL) has been proposed as a new branch of machine learning that replaces traditional statistical loss with a decision loss to form an end-to-end model. Applications of DOL in power systems have been developed in recent years. For renewable-rich power systems, uncertainties propagate through sequential tasks, where traditional statistical-based approaches focus on minimizing statistical errors at intermediate stages but may fail to provide optimal decisions at the final stage. This paper first elaborates on the mismatch between more accurate forecasts and more optimal decisions in the power system caused by statistical-based learning (SBL) and explains how DOL resolves this problem. Secondly, this paper extensively reviews DOL techniques and their applications in power systems while highlighting their pros and cons in relation to SBL. Finally, this paper identifies the challenges to adopt DOL in the energy sector and presents future research directions.