Kernel-Based Learning for Smart Inverter Control

TL;DR

This paper proposes a kernel-based nonlinear control policy for smart inverters in distribution grids, improving voltage regulation and loss minimization by leveraging multi-task learning and real-world data.

Contribution

It introduces a novel nonlinear control approach for smart inverters using kernel regression, outperforming traditional affine rules.

Findings

Nonlinear control rules achieve near-optimal performance.

Few non-local readings suffice for effective control.

Kernel-based methods outperform affine control rules.

Abstract

Distribution grids are currently challenged by frequent voltage excursions induced by intermittent solar generation. Smart inverters have been advocated as a fast-responding means to regulate voltage and minimize ohmic losses. Since optimal inverter coordination may be computationally challenging and preset local control rules are subpar, the approach of customized control rules designed in a quasi-static fashion features as a golden middle. Departing from affine control rules, this work puts forth non-linear inverter control policies. Drawing analogies to multi-task learning, reactive control is posed as a kernel-based regression task. Leveraging a linearized grid model and given anticipated data scenarios, inverter rules are jointly designed at the feeder level to minimize a convex combination of voltage deviations and ohmic losses via a linearly-constrained quadratic program. Numerical tests using real-world data on a benchmark feeder demonstrate that nonlinear control rules driven also by a few non-local readings can attain near-optimal performance.