Novel Four-Layered Software Defined 5G Architecture for AI-based Load Balancing and QoS Provisioning

Software defined 5G network (SD-5G) is an evolving networking technology. The integration of SDN and 5G brings scalability, and efficiency. However, Quality of Service (QoS) provision is still challenging in SD-5G due to improper load balancing, traffic unawareness and so on. To overwhelm these issues this paper designs a novel load balancing scheme using Artificial Intelligence (AI) techniques. Firstly, novel four-layered SD-5G network is designed with user plane, smart data plane, load balancing plane, and distributed control plane. In the context to 5G, the data transmission rate must satisfy the QoS constraints based on the traffic type such as text, audio, video etc. Thus, the data from the user plane is classified by Smart Traffic Analyzer in the data plane. For traffic analysis, Enriched Neuro-Fuzzy (ENF) classifier is proposed. In the load balancing plane, Primary Load balancer and Secondary Load Balancer are deployed. This plane is responsible for balancing the load among controllers. For controller load balancing, switch migration is presented. Overloaded controller is predicted by Entropy function. Then decision for migration is made by Fitness-based Reinforcement Learning (F-RL) algorithm. Finally, the four-layered SD-5G network is modeled in the NS-3.26. The observations shows that the proposed work improves the SD-5G network in terms of Loss Rate, Packet Delivery Rate, Delay, and round trip time.