Embedded Files
One of the most important political and scientific endeavours of today is the ongoing energy transition that aims to transform the global energy sector into a zero-carbon scenario by the second half of this century.
One of the most important political and scientific endeavours of today is the ongoing energy transition that aims to transform the global energy sector into a zero-carbon scenario by the second half of this century.
The energy transition will rely on policy frameworks and market instruments, but also on advances in information technology – where machine learning will be a key enabling methodology.
The energy transition will rely on policy frameworks and market instruments, but also on advances in information technology – where machine learning will be a key enabling methodology.
The role of machine learning can be illustrated by its impact on the power sector transformation: The energy transition will have a profound effect on the power system, including the transmission (high voltage) and distribution (low voltage) grid. Data-driven power grid analysis and optimisation have attracted wide attention in recent years and machine learning has been used in studies of load forecasting, power flow calculation, grid stability and security, integration of distributed generation (renewable energy sources) and optimisation of flexibility assets such as batteries. Based on historical records of consumption, weather data and grid response, and guided by knowledge of the physics of power networks, machine learning algorithms can provide decision support in the design, management and maintenance of power systems and thus improve their economic efficiency and security.
The role of machine learning can be illustrated by its impact on the power sector transformation: The energy transition will have a profound effect on the power system, including the transmission (high voltage) and distribution (low voltage) grid. Data-driven power grid analysis and optimisation have attracted wide attention in recent years and machine learning has been used in studies of load forecasting, power flow calculation, grid stability and security, integration of distributed generation (renewable energy sources) and optimisation of flexibility assets such as batteries. Based on historical records of consumption, weather data and grid response, and guided by knowledge of the physics of power networks, machine learning algorithms can provide decision support in the design, management and maintenance of power systems and thus improve their economic efficiency and security.
The UiT Machine Learning Group’s energy analytics initiative builds on our expertise in machine learning and supplements this with the domain knowledge of partners in UiT’s Arctic Centre for Sustainable Energy (ARC) and external collaborators in industry, research institutes and academia.
The UiT Machine Learning Group’s energy analytics initiative builds on our expertise in machine learning and supplements this with the domain knowledge of partners in UiT’s Arctic Centre for Sustainable Energy (ARC) and external collaborators in industry, research institutes and academia.
Major Projects
Major Projects
Highlighted Publications
Highlighted Publications
- Changkyu Choi, Filippo Maria Bianchi, Michael Kampffmeyer, and Robert Jenssen.
- Bilal Babar, Luigi Tommaso Luppino, Tobias Boström, and Stian Normann Anfinsen.
Google Sites
Report abuse