A Statistical Learning Approach to Reactive Power Control in Distribution Systems

TL;DR

This paper proposes a deep neural network-based statistical learning method for real-time reactive power control in distribution systems, offering a computationally efficient and robust alternative to traditional optimization methods amid renewable energy variability.

Contribution

It introduces a novel deep learning approach to approximate optimal reactive power control, reducing computational complexity and enhancing robustness in distribution system management.

Findings

Neural network-based control achieves near-optimal power loss reduction.

Method demonstrates high computational efficiency in real-time applications.

Robustness to input perturbations verified through numerical tests.

Abstract

Pronounced variability due to the growth of renewable energy sources, flexible loads, and distributed generation is challenging residential distribution systems. This context, motivates well fast, efficient, and robust reactive power control. Real-time optimal reactive power control is possible in theory by solving a non-convex optimization problem based on the exact model of distribution flow. However, lack of high-precision instrumentation and reliable communications, as well as the heavy computational burden of non-convex optimization solvers render computing and implementing the optimal control challenging in practice. Taking a statistical learning viewpoint, the input-output relationship between each grid state and the corresponding optimal reactive power control is parameterized in the present work by a deep neural network, whose unknown weights are learned offline by minimizing the power loss over a number of historical and simulated training pairs. In the inference phase, one just feeds the real-time state vector into the learned neural network to obtain the `optimal' reactive power control with only several matrix-vector multiplications. The merits of this novel statistical learning approach are computational efficiency as well as robustness to random input perturbations. Numerical tests on a 47-bus distribution network using real data corroborate these practical merits.