Learning Provably Stable Local Volt/Var Controllers for Efficient Network Operation

Abstract

This paper develops a data-driven framework to synthesize local Volt/Var control strategies for distributed energy resources (DERs) in power distribution networks (DNs). Aiming to improve DN operational efficiency, as quantified by a generic optimal reactive power flow (ORPF) problem, we propose a two-stage approach. The first stage involves learning the manifold of optimal operating points determined by an ORPF instance. To synthesize local Volt/Var controllers, the learning task is partitioned into learning local surrogates (one per DER) of the optimal manifold with voltage input and reactive power output. Since these surrogates characterize efficient DN operating points, in the second stage, we develop local control schemes that steer the DN to these operating points. We identify the conditions on the surrogates and control parameters to ensure that the locally acting controllers collectively converge, in a global asymptotic sense, to a DN operating point agreeing with the local surrogates. We use neural networks to model the surrogates and enforce the identified conditions in the training phase. AC power flow simulations on the IEEE 37-bus network empirically bolster the theoretical stability guarantees obtained under linearized power flow assumptions. The tests further highlight the optimality improvement compared to prevalent benchmark methods.

References in corpus (9)

• Convex Relaxation of Optimal Power Flow, Part I: Formulations and Equivalence
• Options for Control of Reactive Power by Distributed Photovoltaic Generators
• Distributed Optimal Power Flow for Smart Microgrids
• Data-driven Local Control Design using Optimization and Machine Learning Techniques
• Optimal Distributed Feedback Voltage Control under Limited Reactive Power
• A New Voltage Stability-Constrained Optimal Power Flow Model: Sufficient Condition, SOCP Representation, and Relaxation
• Reverse and Forward Engineering of Local Voltage Control in Distribution Networks
• On the Properties of the Compound Nodal Admittance Matrix of Polyphase Power Systems
• Optimal Design of Volt/VAR Control Rules of Inverters using Deep Learning

Cited by in corpus (6)

• Bridging Transient and Steady-State Performance in Voltage Control: A Reinforcement Learning Approach with Safe Gradient Flow
• Unsupervised Learning for Equitable DER Control
• Distributed Online Feedback Optimization for Real-time Distribution System Voltage Regulation
• Constraints on OPF Surrogates for Learning Stable Local Volt/Var Controllers
• Optimal Control in Both Steady State and Transient Process with Unknown Disturbances
• From droop to optimality: The potential of volt/var control for power distribution grid enhancement