A Framework for Analyzing Resource Allocation Policies for Multi-Access Edge Computing

Multi-Access Edge Computing (MEC) is a promising new paradigm enabling low-latency access to services deployed on edge servers. This helps to avert network latencies often encountered in accessing cloud services. The cornerstone of a MEC environment is a resource allocation policy used to partition and allocate computational resources such as bandwidth, memory available on the edge server to user service invocations availing such services. In this work, we propose a generic data-driven framework to model and analyze such MEC resource allocation policies. We model a MEC system as a Turn-Based Stochastic Multi-Player Game and use Probabilistic Model Checking to derive quantitative guarantees on resource allocation policies against requirements expressed in Probabilistic Alternating-Time Temporal Logic with Rewards. We present results on state-of-the-art MEC resource allocation policies to demonstrate the effectiveness of our framework.