Institut für Technik der Informationsverarbeitung (ITIV)

Implementation of a machine learning algorithm of an overhead line congestion monitoring based on data from distributed sensor nodes

Implementation of a machine learning algorithm of an overhead line congestion monitoring based on data from distributed sensor nodes

.
.

Background

The real-time thermal line rating of an overhead transmission line (OTL) is the maximum permissible level of power flow that can pass through the line safely and reliably under prevailing weather conditions. The current-carrying capacity of an OTL is conventionally limited to a static line rating (SLR)  which is derived from a maximum allowable conductor temperature and a conservative set of weather conditions for a particular season based on a thermal model of overhead conductors. Real-time thermal line rating promises to provide additional ampacity thus may serve to mitigate blackout due to overload during peak demand in congestion network. This will serve as optional remedy for investment as upgrading requires huge investment.

The developments in sensors and the Internet of Things (IoT) technologies to capture and preprocess data along with meteorological weather data using Machine learning algorithm to forecast current carrying capacity of transmission line.

 

Tasks

  • Literature Review
  • To develop machine learning algorithm.
  • To implement with dataset.

 

Required skills

  • Student of informatics or electrical engineering.
  • Programming experience (Python, C/C++).