SCAREY: Location-Aware Service Lifecycle Management
Kurt Horvath, Dragi Kimovski, Radu Prodan
TL;DR
SCAREY introduces a location-aware service lifecycle framework for the computing continuum that unifies discovery, provisioning, placement, and monitoring via a finite state machine to adapt service instances to demand. The approach combines a scalable deployment and dynamic scaling algorithm, latency-aware service placement using network measurements across Edge, Fog, and Cloud, and selective resource acquisition with MESDD-driven discovery to reduce idle resources and emissions. Real-world–style evaluations show SCAREY improves service discovery and acquisition times by over 73%, cuts operating costs by about 45%, and reduces power consumption and CO2 emissions by over 57% compared to COLAP and PIES. The work demonstrates significant practical impact for scalable, energy-conscious orchestration in distributed computing environments and suggests avenues for extending QoS metrics and security in future work.
Abstract
Scheduling services within the computing continuum is complex due to the dynamic interplay of the Edge, Fog, and Cloud resources, each offering distinct computational and networking advantages. This paper introduces SCAREY, a user location-aided service lifecycle management framework based on state machines. SCAREY addresses critical service discovery, provisioning, placement, and monitoring challenges by providing unified dynamic state machine-based lifecycle management, allowing instances to transition between discoverable and non-discoverable states based on demand. It incorporates a scalable service deployment algorithm to adjust the number of instances and employs network measurements to optimize service placement, ensuring minimal latency and enhancing sustainability. Real-world evaluations demonstrate a 73% improvement in service discovery and acquisition times, 45% cheaper operating costs and over 57% less power consumption and lower CO2 emissions compared to existing related methods.