QoS-aware Autonomic Adaptation of Microservices Placement on Edge Devices

Abstract

Given the widespread availability of cheap computing and storage devices, as well as the increasing popularity of high speed network connections (e.g., Fiber To The Home (FTTH)), it is feasible for groups of users to share their own resources to build a service hosting platform. In such use-case, the response-time of the service is critical for the quality of experience. We describe a solution to optimize the response-time in the case of an application based on microservices. This solution leverages the flexibility of microservices to dynamically adapt the placement of the application workloads on edge devices. We validate this solution on a production edge infrastructure and discuss possible strategies for the decision rules.

Towards a participatory cloud infrastructure for hosting services: QoS-aware dynamic orchestration of microservices

“…This section focuses on exploring how dynamic adjustments to the placement of microservices can be employed to maintain acceptable application performance. We detailled our proposed solution in [13].…”

An Enhanced Lightweight Security Gateway Protocol for the Edge Layer

“…However, maintaining the dependency relationship within the µs is complex in a large IIoT system, as a large amount of data needs to be transferred among the adjacent µs [33]. In a µs-based system, every service request and response should have a unique identifier, i.e., a correlation ID [34]. Managing and coordinating these unique request processing identifiers requires additional computational resources.…”

Self-organizing Fog Support Services for Responsive Edge Computing

“…Similarly, a study by Hosseinzadeh et al [12] provides an overview of various multi-objective optimization algorithms in service networks, but in the context of selecting optimal services rather than deploying them in optimal locations. Stévant, Pazat and Blanc [13] propose a framework which monitors and optimizes service placement to minimize QoS requirements, represented by response time in their evaluation. The difference with the approach in this article is that SoSwirly attempts to balance QoS requirements versus total used resources.…”