Mobile Communications Research

Self-Organized Networks (SON):

  • AI based SON functions
  • Focus on mobility and inter-cell optimization functions like: Mobility Robust Optimization (MRO), Mobility Load Balancing (MLB), Inter-Cell Interference Coordination (ICIC) and Coverage and Capacity Optimization (CCO)
  • Implicit coordination to solve conflict management between SON functions
  • Radio resource management (RRM) for Ultra reliable low latency communication (URLLC) applications

Machine learning (ML):

  • Zero-touch ML framework for 4G/5G simulations
  • Machine learning based on Recommendation Systems, Neural Networks, etc.
  • Federated learning for added security
  • Trust in ML through Explainable-AI
  • Computational offloading for edge and cloud computing in campus networks
  • Cognitive Network Management of radio resources to achieve higher spectral efficiency while maintaining the QoS requirements of the applications


  • Active member of Open Networking Foundation (ONF) Community
  • Machine learning based xApps for SON/RRM
  • Adapted SON functions of MRO, MLB, CCO and ICIC
  • Solutions for effective network management

Radio Resource Management:

  • Radio resource management with a special focus on URLLC applications, for the selection of multi numerology, mini-slots, radio resources, MCS mapping etc.
  • The hierarchical radio resource allocation, i.e. D2D (Device-to-device) sub-granting scheme, is seen as a solution to overcome the incurred inefficient radio resource utilization in overlay D2D communications.
  • D2D Reuse SON solution that minimizes the impact of URLLC applications on network capacity is based on allowing the sharing of the cellular network’s radio resources with multiple device-to-device (D2D) users.
  • Autonomous D2D resource selection protocols for reduced latency and increased spectral efficiency in an out-of-coverage scenario
  • Slice management and packet scheduling based on machine learning and other optimization solutions