An Explainable Framework for Machine learning-Based Reactive Power Optimization of Distribution Network

TL;DR

This paper introduces an explainable machine learning framework for reactive power optimization in distribution networks, utilizing Shapley explanations to enhance interpretability and reduce computational costs.

Contribution

It develops a model-agnostic explanation method using Shapley values to interpret machine learning-based reactive power optimization solutions.

Findings

The framework accurately explains reactive power solutions visually.

It reduces computational burden compared to direct Shapley calculations.

Applicable to various machine learning models like neural networks.

Abstract

To reduce the heavy computational burden of reactive power optimization of distribution networks, machine learning models are receiving increasing attention. However, most machine learning models (e.g., neural networks) are usually considered as black boxes, making it challenging for power system operators to identify and comprehend potential biases or errors in the decision-making process of machine learning models. To address this issue, an explainable machine-learning framework is proposed to optimize the reactive power in distribution networks. Firstly, a Shapley additive explanation framework is presented to measure the contribution of each input feature to the solution of reactive power optimizations generated from machine learning models. Secondly, a model-agnostic approximation method is developed to estimate Shapley values, so as to avoid the heavy computational burden associated with direct calculations of Shapley values. The simulation results show that the proposed explainable framework can accurately explain the solution of the machine learning model-based reactive power optimization by using visual analytics, from both global and instance perspectives. Moreover, the proposed explainable framework is model-agnostic, and thus applicable to various models (e.g., neural networks).