Power systems
[Closed]
Work description
- The key aim of this project is to provide: i) new fundamental FL risk models to characterise the uncertainty of network outages, ii) a much higher time granularity in fault-level forecasting to suppress the need for complex and extensive fault-level monitoring in networks. - Development through simulation of a new fault level (FL) assessment framework to reduce uncertainty from the wide range of MV/LV distribution network topologies and demand. - Deliver a new probabilistic solution in the form of fault-level risk models/algorithms to capture the uncertainty of outages affecting the extensive number of system assets and demands. This solution is encouraged to be Machine Learning based, i.e. reinforcement learning, robust optimization, or other methods are envisaged. - Validation of a wide range of realistic network scenarios using the algorithms developed into a fault level (FL) hardware demonstrator at INESC TEC laboratory and pilot system.
Minimum profile required
- Previous academic background in power systems or similar- Proven experience in power system protection and automation project and test
Preference factors
- Knowledge of power system protection and automation - Knowledge of self-healing strategies and algorithms - Knowledge regarding the implementation of standards in MV/LV distribution substations and networks - Knowledge of programming (and Machine Learning basics)
Application Period
Since 15 Feb 2024 to 15 Mar 2024
[Closed]
Centre
Power and Energy Systems