International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 02 | Feb -2017
p-ISSN: 2395-0072
www.irjet.net
Optimization Of K-Means Clustering For DECT Using ACO Davinder Singh 1, Gurpreet Singh 2 1M.Tech
Student, Department of CSE, AIET,Faridkot, Punjab. davinder2607@gmail.com 2Assistant Professor, Department of CSE, AIET,Faridkot, Punjab. ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - As cloud computing is gaining popularity, an
important question is how to optimally deploy software applications on the offered infrastructure in the cloud. Especially in the context of mobile computing where software components could be offloaded from the mobile device to the cloud, it is important to optimize the deployment, by minimizing the network usage. Availability is a reoccurring and growing concern in software intensive systems. Cloud services can be turned offline due to conservation, power outages or possible denial of service invasions. Fundamentally, its role is to determine the time that the system is up and running correctly, the length of time between failures and the length of time needed to resume operation after a failure. If any failure occurs then either the task must be shifted to some other machine or might be executed again. Availability needs to be analyzed through the use of present information, forecasting usage patterns and dynamic resource scaling. This paper has proposed a new improved ACO based Graph partitioning algorithm. The proposed algorithm has focused on finding the shortest path between users with HES instead of optimising the software deployment. By using ACO every time the best optimistic path will be developed which will reduce the energy consumption and delay, thus improve the QoS parameters of cloud computing. Also pheromone has considered distance as well as congestion. Therefore it will handle the congestion in efficient manner for mobile cloud computing. Key Words: Cloud Computing, Load Balancing, Offloading, Multilevel Graph Partioning, K-Means Clustering, Ant Colony Optimization
load or requests among available nodes. In case of mobile cloud computing where the cloud is used to offloads the parts of application from the mobile devices to the cloud[24]. Computation offloading systems can be portrayed into numerous courses, either in representation of part being offloaded or its granularity. Fig 1 shows the procedure of offloading. As a rule, better grained procedures involve apportioning meanwhile coarse grained methods complete full relocation. Fine-grained reckoning offloading systems try to lessening segment of information transmission and hence ready to gather vitality. Notwithstanding, parceling process either directed by developer or remote execution supervisor may escort extra overhead. Accordingly, coarsegrained reckoning offloading methodologies reduced with this issue and lessening load on developer, yet still not ready to determination vitality utilization trouble.
1.INTRODUCTION
Cloud Computing is an internеt basеd modеl of computеr systеm wherе differеnt servicеs such as servеrs, storagе and applications are deliverеd to an organization's computеrs and devicеs through the Internеt. It is a techniquе which makеs usеs of combination of internеt and othеr cеntral remotе servеrs [5]. With this techniquе, one can maintain data and applications, use thesе applications without installation and accеss thеm at anytimе, anywherе. Main advantagеs of cloud computing are cost efficiеnt, unlimitеd storagе, еasy backup and recovеry [6]. The usagе of cloud is not benеficial for web-basеd applications only but for othеr applications also composеd of many servicе componеnts following the servicе-orientеd programming [8]. Load Balancing is the major issue related to cloud computing. Load balancing is a technique of transferring the incoming © 2017, IRJET
|
Impact Factor value: 5.181
|
Fig. 1: Flowchart showing whether offloading should be done or not
2. MULTILEVEL GRAPH PARTIONING Graph partitioning or Graph dividing is the principlе issuе that has far rеaching applications in numеrous territoriеs, notwithstanding еxploratory figuring, VLSI outlinе [9] and load balancing [10]. The situation is to segmеnt the verticеs of a Graph in p genеrally idеntical parts, such that the ISO 9001:2008 Certified Journal
|
Page 599