Utility-driven virtual machine allocation in edge cloud environments using a partheno-genetic algorithm

Abstract Mobile Edge Computing alleviates network congestion and reduces latency by offloading tasks to the network edge. However, fluctuating Quality of Service (QoS) and service compositions significantly challenge service reliability and utility optimization. To address these challenges, this paper proposes a novel virtual machine allocation framework designed to maximize the utility of edge cloud service provisioning under QoS constraints. First, the task processing mechanism is modeled as an M/M/m queuing system, with service loss and revenue functions defined to quantify the quality and profitability of edge services. Next, the framework dynamically reallocates virtual machines across sub-service centers, based on task arrival rates and varying QoS requirements, to optimize overall service utility. Finally, we develop a partheno-genetic algorithm based on integer coding to solve the service utility maximization (SOPGA) to determine the optimal virtual machine allocation strategy. Simulation results demonstrate that the proposed virtual machine allocation algorithm improves service utility by more than 20% compared to other virtual machine allocation algorithms, significantly enhancing service utility in edge cloud environments while maintaining robust QoS guarantees.