Data-Driven Incident Detection in Power Distribution Systems

TL;DR

This paper introduces a data-driven method for detecting incidents in power distribution systems with energy storage, leveraging sensor data relationships without needing system models, effective even with limited sensing.

Contribution

It presents a novel incident detection approach that uses causal relationships in sensor data and includes data augmentation to handle scarce sensing scenarios.

Findings

Effective detection of ESS-related incidents demonstrated in case studies.

Method works without prior system knowledge or parameters.

Robust performance with limited sensor data.

Abstract

In a power distribution network with energy storage systems (ESS) and advanced controls, traditional monitoring and protection schemes are not well suited for detecting anomalies such as malfunction of controllable devices. In this work, we propose a data-driven technique for the detection of incidents relevant to the operation of ESS in distribution grids. This approach leverages the causal relationship observed among sensor data streams, and does not require prior knowledge of the system model or parameters. Our methodology includes a data augmentation step which allows for the detection of incidents even when sensing is scarce. The effectiveness of our technique is illustrated through case studies which consider active power dispatch and reactive power control of ESS.