Overview

Mobility load balancing is a 3GPP Release 17 AI/ML for NG RAN Use Case. It involves transferring load from overloaded cells to under-loaded neighboring cells, for optimizing network performance and user experience.


Concept

  • Default Association: In NetSim, the default user equipment (UE) association is based on Maximum signal strength (SS-RSRP)
  • Load Balancing Goal: Modify the association/Handover criteria to distribute network load efficiently across available cells.

NetSim provides a flexible framework for users to develop and test load balancing algorithms:

  • NetSim passes 'measurements' to the user algorithm
  • The algorithm processes data and returns 'controls or actions'
  • NetSim adjusts the simulation based on algorithm output
  • NetSim then provides performance metrics (KPIs) back to the algorithm
  • These steps occur in a continuous loop, allowing for run-time adjustments.


Example Load Balancing Algorithm

Inputs

  • Number of RRC connected UEs at each gNB
  • DL and UL CQIs of each UE
  • Time averaged PRB utilization (DL and UL) at each gNB

Possible Outputs

  • UE to gNB associations
  • Cell Individual Offsets: A positive CIO value artificially increases the perceived signal strength of the cell from the UE’s perspective, while a negative CIO reduces it  

User Algorithm 

  • Algorithms can be written in high-level languages like Python
  • No need for deep knowledge of NetSim internals

Example Scenario

  • 3 sectors per cell, 3 carriers per sector. Total (3*3) 9 gNBs. NetSim models each sector-carrier as 1 gNB.
  • 1500 UEs
  • Dynamic variables: Cell load, traffic characteristics, distribution of devices 
  • Load balancing using Cell individual offset (CIO)


Results


The cell individual offset (CIO) values were adjusted for the 9 gNBs. 


1. UE - gNB association

  • Each colored dot represents a UE, and different colors represent connections to different gNBs operating at various frequencies (1.5 GHz, 2.6 GHz, and 3.5 GHz). 
  • In the initial association (left image), UEs are concentrated more heavily in certain gNBs (note the denser clusters of certain colors). This creates an uneven load distribution across the network.
  • After load balancing handovers (right image), the distribution of colors appears are evenly spread, indicating that some UEs have been handed over to different gNBs to achieve better load distribution across the network 


2. PRB Utilization at the gNBs before and after load balancing

  • These graphs show resource (PRB) usage of different 5G base stations over time, comparing scenarios with and without load balancing.
  • Without load balancing (top): Some base stations (gNB2 & 3) are overloaded at ~100% while others are underused at 20-40%.
  • With load balancing (bottom): Resource usage is more evenly distributed across all base stations, with peaks around 80-90% and most stations operating at 30-70%.

Additional Considerations

To create more sophisticated traffic steering solutions, users could consider the following:

  • PRB utilization between GBR (Guaranteed Bit Rate) and Non-GBR users
  • Time-varying network traffic patterns
  • UE mobility 

Useful Links

1. NetSim 5G overview: https://tetcos.com/5g.html