MSc Thesis: Predicting weather-related transmission line failures using machine learning

Roddy Akeel successfully defends his master's thesis


REYKJAVIK, July 15 - After conducting his studies, Roddy Akeel successfully defended his master's thesis where he attempted to improve reliability assessments by developing an informational tool that predicts weather-related transmission line failures. Roddy's work was supervised by Ragnar Kristjánsson from Reykjavik University, and Samuel Perkin from Landsnet.


Power outages can negatively impact society and the economy. Cutting off electricity supply can reduce the availability of clean water, limit communication and reduce normal hospital functions. The average lifestyle of individuals and societies as a whole depend on electricity and therefore depend on the stable and reliable transmission of electricity from its generation location to where it is consumed.

Roddy defines power system reliability as the overall stability and security of an entire transmission system including the reliability of each component in the power system. As different methods for improving power system operator decision making, Roddy looked to implement machine learning to link meteorological conditions to transmission line failure. He used different feed-forward neural networks and different preprocessing methods to extract base weather parameters before training the algorithms. The preprocessing methods he used were seasonal classification, k-means classification, and a custom risk parameter flag. 

Three cases including low, medium, and high-risk scenarios were conducted using the best performing algorithms. Though Roddy acknowledges that data quality impacted the overall performance of the different neural networks, machine learning can benefit the prediction and preparation of weather-related transmission line promises. He suggests additional weather stations collecting data be added to improve results in future studies.

To read more about using machine learning to predict weather-related power outages in a transmission system click here.

Congratulations Roddy on an excellent thesis!


About Iceland School of Energy

By bringing together the best from industry and academia, Iceland School of Energy provides a unique, and comprehensive training for its students. A wide range of courses taught by the very best in their field open a broad spectrum of possibilities for students and allow for individual study designs. Focus is put on close collaboration with industry experts while maintaining high academic quality of the work.

Full-time graduate studies

Short programmes and professional development