Dynamic Service Placement in Geographically Distributed Clouds

Abstract

Edge computing has emerged as a new paradigm to bring cloud applications closer to users for increased performance. ISPs have the opportunity to deploy private edge-clouds in their infrastructure to generate additional revenue by providing ultra-low latency applications to local users. We envision a rapid increase in the number of such applications for "edge" networks in the near future with virtual/augmented reality (VR/AR), networked gaming, wearable cognitive assistance, autonomous driving and IoT analytics having already been proposed for edge-clouds instead of the central clouds to improve performance. This raises new challenges as the complexity of the resource allocation problem for multiple services with latency deadlines (i.e., which service to place at which node of the edge-cloud in order to satisfy the latency constraints) becomes significant. In this paper, we propose a set of practical, uncoordinated strategies for service placement in edge-clouds. Through extensive simulations using both synthetic and real-world trace data, we demonstrate that uncoordinated strategies can perform comparatively well with the optimal placement solution, which satisfies the maximum amount of user requests.

Service placement for latency reduction in the internet of things

“…For example, Zhang et al [11] aim at optimizing hosting costs, while Huang et al [12] focus at optimizing energy costs. Ooi et al [13] target the optimization of the availability of the services when resources fail, and Ghaznavi et.…”

Replica Placement in Cloud through Simple Stochastic Model Predictive Control

“…Multiplicity of hosts are Ω = [9, 10, 10, 9, 10, 7] T . The speed factors for the hosts are = [1, 1.2, 0.9, 1.1, 0.8, 1.2] T The service demand for the services are d = [5,4,2,8,1,2,5,8,6,8,4,5,6,5] * 10 −3 . The random cost coefficients are σ * s,h = rand H,1 * 1 1,S + 10.…”

“…In a PaaS environment, where the PaaS controller can make decisions about placement of its services on physical machines, the amount of physical hardware required to meet the Quality of Service (QoS) is fulfilled by the deployment of replicas on available hardware and by choosing the ratio of the workload each replica handles. An Optimal Service Placement (OSP) [1] problem is concerned with minimizing the infrastructure cost through resource sharing, while meeting the promised QoS mentioned in Service Level Agreement (SLA) through optimal placement of service replicas over time. In general, the near optimal steady-state solution to OSP for a set of Ntier software systems can be found by iterative improvement algorithms such as the one introduced in [2].…”

Faces in the Clouds: Long-Duration, Multi-User, Cloud-Assisted Video Conferencing

“…Airlift seeks to optimise throughput for users within a given delay bound. In [24], the authors model service placement between geographically-distributed clouds. They focus on dynamic pricing, moving instance placements according to price fluctuations.…”