Scribd
Upload
8 views3 pages

Smart Queue Management in Cloud Networks

This document proposes a Smart Scheduling and Pricing algorithm to jointly optimize scheduling and pricing decisions for delay-tolerant batch services in wireless cloud networks. The algorithm aims to maximize the service provider's long-term profit without needing to predict future information. Simulation results show the algorithm achieves near-optimal profit while bounding job queue lengths in the data center, outperforming existing algorithms that do not consider queue lengths or cooling energy costs. The algorithm can be implemented online using current information and extended to multiple service classes.

Uploaded by

dhasdj
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
8 views3 pages

Smart Queue Management in Cloud Networks

This document proposes a Smart Scheduling and Pricing algorithm to jointly optimize scheduling and pricing decisions for delay-tolerant batch services in wireless cloud networks. The algorithm aims to maximize the service provider's long-term profit without needing to predict future information. Simulation results show the algorithm achieves near-optimal profit while bounding job queue lengths in the data center, outperforming existing algorithms that do not consider queue lengths or cooling energy costs. The algorithm can be implemented online using current information and extended to multiple service classes.

Uploaded by

dhasdj
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Smart Scheduling and Pricing for Wireless Cloud Networks

ABSTRACT: This proposed system gives a clear picture about wireless cloud computing system where the wireless service provider leverage a data center providing cloud services to its subscribers at a much attractive prices. To maximize the service providers profit on a long run, we propose a joint optimization of scheduling and pricing decisions for delay-tolerant batch services. While the existing algorithm on jointly scheduling and pricing focuses on static or asymptotic analysis, we develop a proven Smart Scheduling and Pricing algorithm that can be applied to an arbitrarily random environment, which without the necessity of predicting the future information, may follow an arbitrary path over period of time.

When comparing the optimal offline algorithm with future information, we prove that Smart Scheduling and Pricing Algorithm produce a close-to-optimal return while bounding the job queue length in the data center. Alongside, there has been a trace-based simulation study conducted to validate this Smart Scheduling and Pricing Algorithm. Based on analytical and numerical studies, we prove that tuning the control parameter appropriately can lead to a desired tradeoff between the profit and queuing delay. Also, our deeper research with respect to the existing algorithms which neglect cooling system energy consumption, demand-side management, and/or the queue length information, revealed that Smart Scheduling and Pricing algorithm achieves maximum profit while incurring the same average queuing delay, approximately.

EXISTING SYSTEM: The existing algorithms for joint optimization of scheduling and pricing can work for limited capacity or a static game-theoritic setting for demand response in the smart grid and also to develop efficient online algorithm is a nontrivial task. PROPOSED SYSTEM: The proposed system ( Smart Scheduling and Pricing ) can be extended to multiple service classes and provide differentiated QoS in terms of the average delay. We proposed a provably-efficient online scheduling and pricing algorithm, which can be implemented based on the currently available information. We proved that, compared to the optimal offline algorithm with future information, Smart Scheduling and Pricing algorithm produces a close-to- optimal long-term profit while bounding the job queue length in the data center.

SYSTEM REQUIREMENTS:
SOFTWARE REQUIREMENTS:
Front End Environment Back End Operating System : : : : [Link] Visual Studio 2008 or 2010 SQL Server 2005 Windows XP

HARDWARE REQUIREMENTS:
Processor RAM : : Pentium IV 512 MB

Hard Disk

80 GB

You might also like