Mobility-aware load Balancing for Reliable Self-Organization Networks: Multi-agent Deep Reinforcement Learning

Abstract Self-Organizing Networks (SON) is a collection of functions for automatic configuration, optimization, and healing of networks and mobility optimization is one of the main functions of self-organized cellular networks. State of the art Mobility Robustness Optimization (MRO) schemes have relied on rule-based recommended systems to search the parameter space; yet it is unwieldy to design rules for all possible mobility patterns in any network. In this regard, we presented a Deep Learning-based MRO solution (DRL-MRO), which learns the required parameter's appropriate values for each mobility pattern in individual cells. Optimal mobility setting for Handover parameters also depends on the user distribution and their velocities in the network. In this framework, an effective mobility-aware load balancing approach applied for autonomous methods of configuring the parameters in accordance with the mobility patterns in which approximately the same quality level is provided for each subscriber. The simulation results show that the function of mobility robustness optimization not only learns to optimize HO performance, but also it learns how to distribute excess load throughout the network. The experimental results prove that this solution minimizes the number of unsatisfied subscribers (Nus) and it can also guarantee a more balanced network using cell load sharing in addition to increase cell throughput outperform the current schemes.