A Data-Driven Real-Time Optimal Power Flow Algorithm Using Local Feedback

2025-02-21

AI Summary

Real-time AC optimal power flow (OPF) becomes computationally intractable under high penetration of distributed energy resources (DERs). Method: This paper proposes a fully distributed optimization framework relying solely on local measurements. It introduces a novel OPF paradigm based on learnable local feedback functions, recasting the time-varying optimization problem as neural network parameter training. A gradient-free stochastic primal-dual update scheme is designed to circumvent the computational bottleneck of computing gradients from nonlinear power flow models. Contribution/Results: Theoretical convergence is guaranteed via the universal approximation theorem. Experiments on the IEEE 37-bus system demonstrate that the method significantly outperforms state-of-the-art benchmarks in both solution accuracy and dynamic tracking speed. Moreover, it achieves lightweight communication overhead, high computational efficiency, and flexible deployment—making it particularly suitable for edge-constrained DER-rich distribution networks.

Technology Category

• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The increasing penetration of distributed energy resources (DERs) adds variability as well as fast control capabilities to power networks. Dispatching the DERs based on local information to provide real-time optimal network operation is the desideratum. In this paper, we propose a data-driven real-time algorithm that uses only the local measurements to solve time-varying AC optimal power flow (OPF). Specifically, we design a learnable function that takes the local feedback as input in the algorithm. The learnable function, under certain conditions, will result in a unique stationary point of the algorithm, which in turn transfers the OPF problems to be optimized over the parameters of the function. We then develop a stochastic primal-dual update to solve the variant of the OPF problems based on a deep neural network (DNN) parametrization of the learnable function, which is referred to as the training stage. We also design a gradient-free alternative to bypass the cumbersome gradient calculation of the nonlinear power flow model. The OPF solution-tracking error bound is established in the sense of universal approximation of DNN. Numerical results on the IEEE 37-bus test feeder show that the proposed method can track the time-varying OPF solutions with higher accuracy and faster computation compared to benchmark methods.

Problem

• Solves real-time optimal power flow using local feedback.
• Addresses variability from distributed energy resources.
• Bypasses gradient calculation in nonlinear power flow models.

Innovation

• Data-driven real-time OPF algorithm
• Local feedback-based control
• Deep neural network parametrization