About the project
This project aims to develop a criticality ranking system for power grid assets using data-driven approaches. By applying machine learning and statistical models, it prioritizes high-risk assets, enabling proactive decisions, optimised resource allocation, enhanced maintenance efficiency, and improved grid reliability.
Effective asset management in power grids is essential for ensuring operational reliability, minimising downtime, and optimising maintenance costs. However, traditional asset management approaches often lack a structured mechanism for prioritising critical assets, leading to inefficient resource allocation. This project addresses this challenge by proposing a holistic ranking system to assess asset criticality based on operational data, test results as well as the cost of associated consequences.
As part of the Doctoral Centre for Advanced Electrical Power Engineering, the project’s objectives include:
- analysing collected data to extract insights
- developing a criticality ranking model based on key parameters such as failure frequency and downtime impact
- implementing predictive risk assessment using machine learning techniques.
The goal is to enable strategic maintenance planning and proactive decision-making to enhance grid stability. The methodology involves aggregating and preprocessing historical performance data, defining ranking criteria like failure frequency and system dependency, and applying machine learning and statistical models to classify and rank assets by risk.
Expected outcomes include a systematic ranking framework for critical power assets, enhanced maintenance efficiency by focusing on high-risk assets, and a significant reduction in failures and operational disruptions. By leveraging historical data, this project empowers power utilities to make informed, data-driven decisions, ensuring improved grid stability, optimised maintenance strategies, and cost savings.
You will join an interdisciplinary and diverse academic team in the Electrical Power Engineering research group that will support you in expanding your transferrable skills, such as critical review of the literature, academic writing and publishing, as well as collaborating with your team members and organising activities. You will acquire hands-on experience with testing facilities and operate advanced equipment in the Tony Davies High Voltage Laboratory as part of your experimental research.
