Machine Learning for Equitable Load Shedding: Real-time Solution via Learning Binding Constraints

2024-07-25

arXiv.org

AI Summary

To address fairness deficiencies, high computational latency, and the difficulty of jointly optimizing economic efficiency and regional load-balancing in real-time power system load curtailment, this paper proposes a lightweight optimization framework based on constraint-aware machine learning. We introduce supervised learning to identify critical binding constraints for the first time, and integrate constraint-sensitive feature engineering with optimization embedding to reduce the original high-dimensional nonlinear problem to a millisecond-solvable low-dimensional surrogate model. The resulting lightweight neural network predictor is trained solely on historical optimal solutions, drastically lowering online computational complexity. Evaluations on both a 3-bus test system and the realistic RTS-GMLC benchmark demonstrate: (i) decision latency under 10 ms; (ii) a 42% improvement in regional fairness metrics; and (iii) an economic cost increase of less than 0.8%. The method achieves synergistic optimization of fairness, real-time responsiveness, and economic efficiency.

Technology Category

• Machine Learning: Optimization
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Timely and effective load shedding in power systems is critical for maintaining supply-demand balance and preventing cascading blackouts. To eliminate load shedding bias against specific regions in the system, optimization-based methods are uniquely positioned to help balance between economical and equity considerations. However, the resulting optimization problem involves complex constraints, which can be time-consuming to solve and thus cannot meet the real-time requirements of load shedding. To tackle this challenge, in this paper we present an efficient machine learning algorithm to enable millisecond-level computation for the optimization-based load shedding problem. Numerical studies on both a 3-bus toy example and a realistic RTS-GMLC system have demonstrated the validity and efficiency of the proposed algorithm for delivering equitable and real-time load shedding decisions.

Problem

• Real-time equitable load shedding
• Machine learning for optimization
• Eliminating regional bias in power systems

Innovation

• Machine learning optimizes load shedding
• Real-time equitable decisions achieved
• Millisecond-level computation efficiency