A Hyper-Heuristic Approach for Quality of Experience Aware Service Placement Scheme in 5G Mobile Edge Computing

The 5^{th} Generation (5G) Mobile Edge Computing (MEC) addresses the problem of high end-to-end delay experienced by traditional cloud computing users by ensuring fast accessible and reliable computing resources. However, the deployment of service instances in MEC resources requires migration due to user mobility. While Proactive Migration of service instances at multiple MECs increases users' Quality-of-Experience (QoE), Reactive Migration might reduce the deployment cost at the expense of user QoE. In this paper, we have developed a framework, that distributes service instances proactively among the Edge Nodes depending on user movement trajectories to ensure faster migration of the service instances and deliver higher QoE within minimum VNF deployment cost considering users' budgets. The aforementioned Proactive Service Placement (PSP) problem is formulated as a Multi-Objective Linear Programming (MOLP) that brings a trade-off between these two conflicting objectives, maximizing user QoE and lowering VNF deployment cost. For large networks, the PSP problem is proven to be an NP-hard problem. Thus, we have developed an artificial intelligence-based Hyper-heuristic algorithm for PSP, called HPSP, which can provide a high-performing solution within polynomial time. The HPSP exploits Tabu Search Optimization as a high-level meta-heuristic algorithm that selects one of the three lower-level meta-heuristic algorithms- Golden Eagle Optimizer, Sine Cosine Optimization, and Jellyfish Search Optimization depending on the situation. The results of numerical analysis describe that the HPSP system outperforms the other state-of-the-art works in terms of user QoE, cost, and the ratio of proactive to reactive service placements.