Beyond the Neural Fog: Interpretable Learning for AC Optimal Power Flow

2024-07-30

arXiv.org

AI Summary

Solving the non-convex AC optimal power flow (AC-OPF) problem remains challenging; conventional DC-OPF approximations lack accuracy, while neural network (NN)-based approaches suffer from opacity, heavy data dependency, and frequent violation of physical feasibility. Method: This paper proposes a physics-informed, interpretable learning framework that explicitly embeds AC power flow constraints, employs a sparse linear model architecture, and utilizes lightweight supervised learning—avoiding end-to-end deep networks. Contribution/Results: The method requires no large-scale labeled datasets, guarantees physical feasibility of all solutions (strictly satisfying AC power flow equations), and ensures decision transparency. Evaluated across multiple benchmark power systems of varying scales, it achieves accuracy comparable to or superior to state-of-the-art NN methods—particularly excelling in low-data regimes. All generated OPF solutions are provably feasible and interpretable, bridging the gap between data-driven efficiency and first-principles reliability in power system optimization.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

The AC optimal power flow (AC-OPF) problem is essential for power system operations, but its non-convex nature makes it challenging to solve. A widely used simplification is the linearized DC optimal power flow (DC-OPF) problem, which can be solved to global optimality, but whose optimal solution is always infeasible in the original AC-OPF problem. Recently, neural networks (NN) have been introduced for solving the AC-OPF problem at significantly faster computation times. However, these methods necessitate extensive datasets, are difficult to train, and are often viewed as black boxes, leading to resistance from operators who prefer more transparent and interpretable solutions. In this paper, we introduce a novel learning-based approach that merges simplicity and interpretability, providing a bridge between traditional approximation methods and black-box learning techniques. Our approach not only provides transparency for operators but also achieves competitive accuracy. Numerical results across various power networks demonstrate that our method provides accuracy comparable to, and often surpassing, that of neural networks, particularly when training datasets are limited.

Problem

• AC-OPF Complexity
• DC-OPF Limitations
• Neural Network Interpretability

Innovation

• Interpretable Method
• AC-OPF Solution
• Data Efficiency