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

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.

References in corpus (18)

• A Survey of Contextual Optimization Methods for Decision Making under Uncertainty
• Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities
• Optimizing Rank-based Metrics with Blackbox Differentiation
• DC3: A learning method for optimization with hard constraints
• Learning with Differentiable Perturbed Optimizers
• Interior Point Solving for LP-based prediction+optimisation
• A Contextual Bandit Approach for Value-oriented Prediction Interval Forecasting
• Prescribing net demand for two-stage electricity generation scheduling
• Decision-Focused Learning: Through the Lens of Learning to Rank
• Backpropagation through Combinatorial Algorithms: Identity with Projection Works
• Backpropagation of Unrolled Solvers with Folded Optimization
• Application-Driven Learning: A Closed-Loop Prediction and Optimization Approach Applied to Dynamic Reserves and Demand Forecasting
• Active Learning For Contextual Linear Optimization: A Margin-Based Approach
• A Solver-Free Framework for Scalable Learning in Neural ILP Architectures
• Decision-Focused Learning without Differentiable Optimization: Learning Locally Optimized Decision Losses
• Towards Improving Unit Commitment Economics: An Add-On Tailor for Renewable Energy and Reserve Predictions
• Task-Aware Machine Unlearning and Its Application in Load Forecasting
• Load Data Valuation in Multi-Energy Systems: An End-to-End Approach