Artificial Intelligence

The research within the Artificial Intelligence group conduct research focused on all aspects of algorithms and methods in respect to Artificial Intelligence. This includes probabilistic and biologically inspired methods, big data, data mining, machine learning, search, information integration, and semantic web as well as applications in bioinformatics, engineering informatics, social informatics, and related areas.

The AI the research group is focusing on reasoning, knowledge, planning, learning, natural language processing, image analysis, prediction, perception and the ability to move and manipulate objects in addition to statistical methods, computational intelligence, and traditional symbolic AI.


  • Bernt Arild Bremdal, Professor
  • Asbjørn Danielsen, Associate Professor
  • Hans Olofsen, Associate Professor
  • Børre Bang, Professor
  • Rune Dalmo, Associate Professor
  • Arne Lakså, Professor
  • Tatiana Kravetc, Associate Professor
  • Helge Fredriksen, Associate Professor
  • Øivin H. Thuv, Senior Lecturer
  • Arthur Schuchter, Researcher
  • Marin H. Skjelvareid, Associate Professor

PhD students:

  • Kristoffer Tangrand
  • Andreas Dyrøy Jansson
  • Shayan Dadman
  • Halldor Arnason

Recent publications:

  • Ilieva, Iliana; Bremdal, Bernt Arild. Flexibility-Enhancing Charging Station to Support the Integration of Electric Vehicles. World Electric Vehicle Journal 2021. ISSN 2032-6653.s doi: 10.3390/wevj12020053.
  • Ilieva, Iliana; Bremdal, Bernt Arild. Utilizing Local Flexibility Resources to Mitigate Grid Challenges at Electric Vehicle Charging Stations. Energies 2021. ISSN 1996-1073.s doi: 10.3390/en14123506
  • Bremdal, Bernt Arild; Farahmand, Hossein; Lloret-Gallego, Pau; Ottesen, Stig Ødegaard; Puranik, Sanket; Pellerin, Bryan; Waage, Dagfinn. Towards a Reference Architecture for Cloud Based Flexibility Services in the Electricity Domain. CIRED Conference Proceedings 2020. ISSN 2032-9644.
  • Ilieva, Iliana; Bremdal, Bernt Arild. Implementing local flexibility markets and the uptake of electric vehicles – the case for Norway. IEEE 2020 ISBN 978-1-7281-2956-3.
  • Sánchez de la Nieta López, Agustın; Ilieva, Iliana; Gibescu, Madeleine; Bremdal, Bernt Arild; Simonsen, Stig; Gramme, Eivind. Optimal midterm peak shaving cost in an electricity management system using behind customers’ smart meter configuration. Applied Energy 2020. ISSN 0306-2619.s doi: 10.1016/j.apenergy.2020.116282.
  • B. Bremdal, K. Tangrand, A. Danielsen, E. Gramme: The E-Regio project: for a distributed local energy market. The Innovation Platform ISSUE 2,, p. 85-86
  • Tangrand, Kristoffer and Bremdal, Bernt. (2020). Using Deep Learning Methods to Monitor Non-Observable States in a Building. Proceedings of the Northern Lights Deep Learning Workshop. 1. 6. 10.7557/18.5159.

  • Tangrand, Kristoffer; Bremdal, Bernt Arild. The FlexNett Simulator. IOP Conference Series: Earth and Environmental Science (EES) 2019; Volum 352:012005. ISSN 1755-1307.p 1 - 9.

    Bremdal, Bernt Arild; Ilieva, Iliana. Micro Markets in Microgrids. John Wiley & Sons 2019 ISBN 9781119434542.s 97 - 164.

  • Ilieva, Iliana; Bremdal, Bernt Arild; de la Nieta Lopez, A.A.S.; Simonsen, S.H.. Local energy markets as a solution for increased energy efficiency and flexibility. IOP Conference Series: Earth and Environmental Science (EES) 2019; Volum 352 (012036). ISSN 1755-1307.s

  • Olivella-Rosell, Pol; Lloret-Gallego, Pau; Munne-Collado, Ingrid; Villafafila-Robles, Roberto; Sumper, Andreas; Ottesen, Stig Ødegaard; Rajasekharan, Jayaprakash; Bremdal, Bernt Arild. Local Flexibility Market Design for Aggregators Providing Multiple Flexibility Services at Distribution Network Level. Energies 2018; Volum 11 (4). ISSN 1996-1073.

  • Jansson, Andreas Dyrøy; Bremdal, Bernt Arild. Genetic Algorithm for Adaptable Design using Crowdsourced Learning as Fitness Measure. IEEE conference proceedings 2018 ISBN 978-1-5386-7189-4.

  • Asbjørn Danielsen: Increasing fall risk awareness using wearables: A fall risk awareness protocol. Journal of Biomedical Informatics, 2016 DOI: 10.1016/j.jbi.2016.08.016

  • Danielsen, Asbjørn and Tørresen, Jim. Recognizing Bedside Events Using Thermal and Ultrasonic Readings. Sensors (Basel). 2017;17(6):1342. Published 2017 Jun 9. doi:10.3390/s17061342

  • Danielsen, Asbjørn and Bremdal, Bernt. (2017). Predicting Bedside Falls using Current Context. 10.1109/SSCI.2017.8280988.

  • Asbjørn Danielsen: Non-intrusive Bedside Event Recognition Using Infrared Array and Ultrasonic Sensor, Published in: Ubiquitous Computing and Ambient Intelligence, 2016


AI and Robotics Lab cooperate on innovative cyber-physical systems

The AI and Robotics Lab at Campus Narvik have initiated cooperative efforts on a new type of cyber-physical systems for the industry.  The experiences from the AI group's work on grid control for the electricity system, especially related to stategic operations of microgrids and charging stations is being merged with the Industry 4.0 initiatives in logistics and manufacturing.


New members of the AI Group

The AI Group is extended with new members and heavy expertise in AI bringing activities across campuses tighter together.


The Smart Charge Project has started

October 2019: The Interreg funded project has started. Smart Charge is a cooperation between the Computer Science and Computational Engineering Department of UiT and The Lapland University of Applied Sciences in Rovaniemi in Finland


Work at UiT Narvik hits international front pages

Technology developed at UiT Narvik reaches the front page of Innovation News Network in June.The Innovation News Network promotes work that was done in the E-Regio project together with Smart Innovation Norway in Halden and Skagerak, the energy company, in Porsgrunn, Norway. UiT was engaged due to its earlier work on multi-agent systems and simulations on energy markets.  This technology was further developed in the Interreg funded project, Smart Charge.  E-Regio created a chance for the AI group to test the technology beyond a simulated world and has been used to manage a local energy market at Skagerak soccer stadium. Here a giant facility for local energy production based on solar panels and 1000 kWh of storage has been built.  An agent represents a device such as a battery, PV panel or the grid.  Based on predictions made on future supply and consumption as well as storage level the agents engage in internal trade that seeks to improve local self-consumption and cut costs and improve profits for the players involved in this market.  Several R&D initiatives have explored similar concepts before, but with the Skagerak case UiT Narvik shows that it is possible to employ these type of agents in real-world settings too.