SCALING SOCIAL MEDIA APPLICATIONS INTO GEO-DISTRIBUTED CLOUDS

ABSTRACT:

Federation of geo-distributed cloud services is a trend in cloud computing that, by spanning multiple data centers at different geographical locations, can provide a cloud platform with much larger capacities. Such a geo-distributed cloud is ideal for supporting large-scale social media applications with dynamic contents and demands. Although promising, its realization presents challenges on how to efficiently store and migrate contents among different cloud sites and how to distribute user requests to the appropriate sites for timely responses at modest costs. These challenges escalate when we consider the persistently increasing contents and volatile user behaviors in a social media application. By exploiting social influences among users, this paper proposes efficient proactive algorithms for dynamic, optimal scaling of a social media application in a geo-distributed cloud. Our key contribution is an online content migration and request distribution algorithm with the following features: 1) future demand prediction by novelly characterizing social influences among the users in a simple but effective epidemic model; 2) one-shot optimal content migration and request distribution based on efficient optimization algorithms to address the predicted demand; and 3) a -step look-ahead mechanism to adjust the one-shot optimization results toward the offline optimum. We verify the effectiveness of our online algorithm by solid theoretical analysis, as well as thorough comparisons to ready algorithms including the ideal offline optimum, using large-scale experiments with dynamic realistic settings on Amazon Elastic Compute Cloud (EC2).

AIM

The aims of this paper how to efficiently store and migrate contents among different cloud sites and how to distribute user requests to the appropriate sites for timely responses at modest costs.

SCOPE

 The Scope of this paper tends to verify the effectiveness of our online algorithm by solid theoretical analysis, as well as thorough comparisons to ready algorithms including the ideal offline optimum, using large-scale experiments with dynamic realistic settings on Amazon Elastic Compute Cloud (EC2).

EXISTING SYSTEM

Most existing cloud systems—e.g., Amazon Elastic Compute Cloud (EC2) and Simple Storage Service (S3), Microsoft Azure, Google App Engine—organize their shared pool of servers from one or a few data centers and serve their users using different virtualization technologies. The services provided by one individual cloud provider are typically deployed to one or a few geographic regions, prohibiting it from serving application demands equally well from all over the globe. To truly fulfill the promise of cloud computing, a rising trend is to federate disparate cloud services (in separate data centers) from different providers, i.e., interconnecting them based on common standards and policies to provide a universal environment for cloud computing. The aggregate capabilities of a federated cloud would appear to be limitless and can serve a wide range of demands over a much larger geographic span

DISADVANTAGES:

1. Aiming at operational cost minimization with service delay
2. An  optimal content migration and request distribution problem, with longtime and one-shot flavors

PROPOSED SYSTEM

This project proposes such an online algorithm for dynamic, optimal scaling of a social media application in a geo-distributed cloud. First, we enable proactive content migration by predicting future demand based on social influence among the users and correlation across videos. More specifically, a simple but effective epidemic model is built to capture propagation of video views along both social connections (i.e., people view the videos posted or retweeted by their friends) and interest correlations Second, to serve the predicted demands, we decide on the one-shot optimal content migration and request distribution strategy by formulating the problem as a mixed integer program. Third, a -step look-ahead mechanism is proposed to adjust the one-shot optimization results toward the offline optimality, which gives rise to the online algorithm. We prove the effectiveness of the algorithm using solid theoretical analysis and demonstrate how the algorithm can be practically implemented in a real-world geo-distributed cloud with low costs. We also design an efficient optimal offline algorithm that derives the offline optimum of the long-term optimization problem, as a benchmark to evaluate performance of our online algorithm

ADVANTAGES

1. A novel -step look-ahead mechanism is designed with guarantees to adjust the one-shot optimum to the offline optimum
2. One -shot  optimal content migration and request distribution based on efficient optimization algorithms to address the predicted demand

 SYSTEM ARCHITECTURE:

 SYSTEM CONFIGURATION

HARDWARE REQUIREMENTS:-

·              Processor         -   Pentium –III

·                Speed                -    1.1 Ghz

·                RAM                 -    256 MB(min)

·                Hard Disk         -   20 GB

·                Floppy Drive    -    1.44 MB

·                Key Board        -    Standard Windows Keyboard

·                Mouse               -    Two or Three Button Mouse

·                Monitor             -    SVGA

SOFTWARE REQUIREMENTS:-

·                Operating System              : Windows  7                                       

·                Front End                  : JSP AND SERVLET

·                Database                  : MYSQL

·                Tool                           :NETBEANS

REFERENCE:

Chuan Wu , Bo Li,  Linquan Zhang. “Scaling Social Media Applications Into Geo-Distributed Clouds”, IEEE/ACM Transactions on Networking, Volume  23, Issue 3 MARCH 2014.