High-Fidelity Machine Learning Approximations of Large-Scale Optimal Power Flow

2020/06/29 by Minas Chatzos, Chatzos, Minas, Ferdinando Fioretto +5 · 42 citations
Computer Science · Engineering · Mathematics · #Artificial intelligence #Artificial neural network #Computer science #Electric power system #Engineering #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Mathematics #Fidelity #Generator (circuit theory) #High fidelity #Key (lock) #Machine Learning (cs.LG) #Mathematical optimization #Mathematics #Optimal Power Flow Distribution #Optimization and Control (math.OC) #Power (physics) #Power System Optimization and Stability #Power System Reliability and Maintenance #Power flow #Scale (ratio) #Signal Processing (eess.SP) #cs.LG #eess.SP #electronic engineering #information engineering #math.OC

paper · pdf · doi:10.48550/arxiv.2006.16356

published in arXiv (Cornell University) (Cornell University)

arxiv created 2020/06/29 · openalex publication_date 2020/06/29 · arxiv updated 2020/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The AC Optimal Power Flow (AC-OPF) is a key building block in many power system applications. It determines generator setpoints at minimal cost that meet the power demands while satisfying the underlying physical and operational constraints. It is non-convex and NP-hard, and computationally challenging for large-scale power systems. Motivated by the increased stochasticity in generation schedules and increasing penetration of renewable sources, this paper explores a deep learning approach to deliver highly efficient and accurate approximations to the AC-OPF. In particular, the paper proposes an integration of deep neural networks and Lagrangian duality to capture the physical and operational constraints. The resulting model, called OPF-DNN, is evaluated on real case studies from the French transmission system, with up to 3,400 buses and 4,500 lines. Computational results show that OPF-DNN produces highly accurate AC-OPF approximations whose costs are within 0.01% of optimality. OPF-DNN generates, in milliseconds, solutions that capture the problem constraints with high fidelity.

Citations

• Multiplier and gradient methods
• On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming
• Phase Transitions for Optimality Gaps in Optimal Power Flows A Study on the French Transmission Network

Cited by

• Towards Generalization of Graph Neural Networks for AC Optimal Power Flow
• Learning-Accelerated ADMM for Distributed Optimal Power Flow
• Quantum Hardware-in-the-Loop for Optimal Power Flow in Renewable-Integrated Power Systems
• Sobolev Training of End-to-End Optimization Proxies

Related

• DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow Problems
• Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods
• Towards Understanding the Unreasonable Effectiveness of Learning AC-OPF Solutions
• Machine Learning for AC Optimal Power Flow
• Beyond the Neural Fog: Interpretable Learning for AC Optimal Power Flow