Abstract

In the next generation of Cloud computing systems, it is expected that multiple Cloud Service Providers (CSPs) will cooperate together to advertise their services and prices to their end users, which may choose the one that best meets their budgetary and technical needs. Despite this benefit of having multiple CSPs to select from, several issues may arise. For instance, how does an IT entrepreneur select a CSP to offload his/her service request? How does the underlying Inter-Cloud system handle this service request? To address these questions, this thesis proposes a novel Optimal Cloud Broker design for Inter-Cloud Systems in the form of a Semi-Markov Decision Process (SMDP) based model. Under the long-run expected average cost criterion, the optimal policy is derived, which aim at maximizing the overall virtual machine utilization while giving the end users the best possible prices. The effectiveness of the proposed Broker design is validated by numerical results.

Highlights

  • 1.1 Context and MotivationCloud computing is an emerging technology in which computing resources such as memory, processing and storage are managed through the Internet

  • For a system, to work efficiently, the load balancing policy distributes the load in such a way that the minimum number of Cloud Service Providers (CSPs) are used and each CSP is utilized to a maximum extent

  • We consider an Inter-Cloud system with two Cloud Centers, a private and a public. This might be a typical scenario of a mobile service provider that has its private CSP, and a service level agreement (SLA) with a public Cloud service provider to handle the limitation of a CSP specially when the peak demand exceeds the CSP’s capacity

Read more

Summary

Context and Motivation

Cloud computing is an emerging technology in which computing resources such as memory, processing and storage are managed through the Internet. Designing a resource allocation model in inter-cloud environment is a challenging task For this purpose, a component of the inter-cloud architecture, referred to as broker, has been introduced, with a goal to reduce the request processing time, maximizing the rewards [6], [7]. A component of the inter-cloud architecture, referred to as broker, has been introduced, with a goal to reduce the request processing time, maximizing the rewards [6], [7] Such entity is meant to work with the individual CSPs in order to manage their identity, access and delivery of requests between them, and to ensure that the availability and performance requirements from both the users and the CSP are achieved in a timely and effective manner. We proposed an Semi-Markov Decision Process(SMDP)-based resource allocation scheme that assigns the resources from the cloud, and selects the best cloud among the available ones from which the resources have to be allocated to satisfy the user’s incoming requests

Research Problem
Proposed Approach
Thesis Contributions
Thesis Outline
Background and Related Works
Resource Allocation in Inter-Cloud Computing
Related Work
System Model
Optimal Control Problem
System State and State Space
Decision Epochs and Actions
Transition probabilities
Policy, Optimality Criterion, Cost Function, and Value Iteration Algorithm
Simulation Setup
Performance Metrics
Impact of
Impact of Bandwidth Requirement of Service Class 1 on the Optimal Cost
Analysis of the Optimal Structure
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call