Categories
Cohort 2

Advanced analytics for wind energy systems

Cohort 2

Project summary

This project aims to unlock the untapped potential of wind energy data by applying advanced analytics to improve modelling, performance, and decision-making across the entire wind energy lifecycle.

The wind energy data lifecycle spans multiple stages:

  • Pre-construction: meteorological mast data, LiDAR measurements, wind climate and energy yield modelling, environmental impact assessments.
  • Operational phases: SCADA data, energy yield records, condition monitoring system data, nacelle LiDAR readings, maintenance logs.
  • Decommissioning: data on structural integrity and end-of-life processes.

Although the wind energy sector has achieved remarkable success in data collection, much of this data remains underutilised. Extracting greater value from these datasets could transform how wind farms are designed, operated, and maintained.

The project will apply advanced analytics techniques – including machine learning, digital twin modelling, time series and spectral analysis, and feature extraction – to enhance data utilisation and improve existing models or develop new ones for wind energy systems. The research will focus broadly on advanced analytics of wind energy data, with specific directions and research questions developed in collaboration with Natural Power.

Meet the researcher

Hi, I’m Aidan. I studied Aeronautical Engineering in Glasgow, and obtained a Master’s focussing on experimental aerodynamics.

After a two-year stint in gas turbine engineering, and a year as a Wind Engineer, I felt the call of academia and decided to return to Glasgow.

My research utilises data science to study the nature of the wind resource, ultimately aiming to reduce uncertainty and aid the development of the wind industry.

Research in the field of wind energy is rewarding and exciting due to the industry’s clear virtues and the multitude of unanswered questions related to the environment and its interaction with mechanical systems.