Contention-Aware Microservice Deployment in Collaborative Mobile Edge Networks

TL;DR

The paper tackles contention among microservices deployed across collaborative mobile edge computing (MEC) nodes by optimizing a weighted latency objective, $\min \sum_{k=1}^{|\mathcal{A}|} \gamma_{a_k} T_{a_k}$, under CPU and memory constraints. It introduces CAMD, a Block Coordinate Descent–based framework that decomposes the deployment into per-microservice subproblems solved with Simulated Annealing, followed by migration to ensure feasibility. By accounting for application priorities, microservice dependencies, and cross-server data transfers, CAMD achieves substantial latency reductions compared to greedy, multi-objective evolutionary, and solver-based baselines in both simulation and a Kubernetes testbed. The approach provides a practical, scalable strategy for latency-sensitive multi-application workloads in heterogeneous MEC environments, highlighting the importance of resource contention awareness in edge orchestration.

Abstract

As an emerging computing paradigm, mobile edge computing (MEC) provides processing capabilities at the network edge, aiming to reduce latency and improve user experience. Meanwhile, the advancement of containerization technology facilitates the deployment of microservice-based applications via edge node collaboration, ensuring highly efficient service delivery. However, existing research overlooks the resource contention among microservices in MEC. This neglect potentially results in inadequate resources for microservices constituting latency-sensitive applications, leading to increased response time and ultimately compromising quality of service (QoS). To solve this problem, we propose the Contention-Aware Multi-Application Microservice Deployment (CAMD) algorithm for collaborative MEC, balancing rapid response for applications with low-latency requirements and overall processing efficiency. The CAMD algorithm decomposes the overall deployment problem into manageable sub-problems, each focusing on a single microservice, then employs a heuristic approach to optimize these sub-problems, and ultimately arrives at an optimized deployment scheme through an iterative process. Finally, the superiority of the proposed algorithm is evidenced through intensive experiments and comparison with baseline algorithms.

Figures (6)

• Figure 1: System model.
• Figure 2: Response latency under various request sizes.
• Figure 3: Response latency under various server numbers.
• Figure 4: Response latency under various numbers of microservices composed of an application.
• Figure 5: Collaborative MEC testbed for microservice deployment.