Supply Restoration in Power Distribution Systems - A Case Study in Integrating Model-Based Diagnosis and Repair Planning

TL;DR

This paper discusses the integration of diagnosis and repair planning in power distribution systems, addressing partial observability and stochastic repair actions through a pragmatic approach.

Contribution

It analyzes challenges in applying existing diagnosis and repair planning methods to real-world power supply restoration problems and proposes a practical solution.

Findings

Identifies key difficulties in integrating diagnosis and repair in power systems.

Highlights the importance of handling partial observability and stochastic actions.

Proposes a pragmatic approach tailored to real-world constraints.

Abstract

Integrating diagnosis and repair is particularly crucial when gaining sufficient information to discriminate between several candidate diagnoses requires carrying out some repair actions. A typical case is supply restoration in a faulty power distribution system. This problem, which is a major concern for electricity distributors, features partial observability, and stochastic repair actions which are more elaborate than simple replacement of components. This paper analyses the difficulties in applying existing work on integrating model-based diagnosis and repair and on planning in partially observable stochastic domains to this real-world problem, and describes the pragmatic approach we have retained so far.