Scheduling Multi-Component Applications Across Federated Edge Clusters With Phare
Open Access
- 18 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 5, 1814-1826
Abstract
has also resulted in increased complexity for Cloud orchestration tools. Traditional tools were designed for centralized data centers and are ineffective for locating microservices in geographically-distributed edge-like infrastructures. This paper presents Phare, a decentralized scheduling algorithm designed to optimize the placement of microservices by satisfying their computing and communication demands while minimizing deployment costs. Phare employs a heuristic-based approach to solve the NP-Hard scheduling problem, prioritizing the microservices with the more stringent requirements and placing them on the most convenient computing facilities, based on the concept of affinity, contributing to the field by providing a more holistic approach to resource scheduling in edge computing. We validate our approach against Firmament, the state-of-the-art workload scheduling algorithm for component-based applications, on simulated edge infrastructures with hundreds of clusters. Phare achieves up to a 10× reduction in terms of deployment costs compared to Firmament while providing a much lower scheduling latency.Keywords
Funding Information
- European Union’s Horizon Europe Research and Innovation Programme Project FLUIDOS (101070473)
- TIM S.p.A. through the Ph.D. scholarship
This publication has 34 references indexed in Scilit:
- Impact of etcd deployment on Kubernetes, Istio, and application performanceSoftware: Practice and Experience, 2020
- Geo-distributed efficient deployment of containers with KubernetesComputer Communications, 2020
- Topology-Aware Resource Allocation for IoT Services in CloudsIEEE Access, 2018
- Optimal Task Assignment in Mobile Cloud Computing by Queue Based Ant-Bee AlgorithmWireless Personal Communications, 2018
- Fast and efficient network service embedding method with adaptive offloading to the edge2018
- On Uncoordinated Service Placement in Edge-Clouds2017
- Phoenix: A Constraint-Aware Scheduler for Heterogeneous Datacenters2017
- Network-aware resource management strategy in cloud computing environments2016
- A Network-Aware Optimization for VM Placement2015
- A complete anytime algorithm for number partitioningArtificial Intelligence, 1998