Evolution Of New Load Balancing Model For Cloud Computing

Abstract— Load balancing is one of the central issues in cloud computing. Since millions of users are accessing the cloud every moment, the concept of load balancing has an important impact on the performance of cloud computing. When the environment is very large and complex, the divisions simplify the load balancing. This paper implements two efficient algorithms for performing a better load balance model for the public cloud based on the cloud partitioning concept with a switch mechanism to choose different strategies for different situations. The algorithm applies an improved round robin technique and game theory to the load balancing strategy to improve the efficiency in the Cloud Simulator.

This algorithm is based on the nature of honey bees of finding and reaping food. The forager bees is a class of bees which forage for food sources and on finding one, they come back to the beehive to tell about this using waggle dance. This dance gives an idea about the quality or quantity of food and also its distance from the beehive. Scout bees then follow the forager bees to the location and then began to reap the food. Then they return to the beehive and do a waggle dance, which gives an idea of how much food is left resulting in further exploitation of the food sources. In load balancing ,as the demand for webservers changes(increases or decreases), dynamically the services are assigned to regulate the changing demands .

of the job, the availability-state of the VMs and their associated prices. In subsection 4.1, we give the

Cloud computing can be viewed as one of the most rapidly growing and evolving paradigm.Webmail,online storage and online documents are most famous examples in which customers can access their data via web browsers on the internet. The original idea of the cloud computing was delivered by J.C.R Licklider in sixties (Mohamed 2009). Cloud computing has developed since then and started to server the publics after internet offered a significant bandwidth in the nineties (Mohamed 2009). Cloud computing has been through many different phases and is still rapidly evolving.

Cloud Computing provide enterprises and users with varieties of capabilities for store and process data in the data centers of third-party. It depends on resources sharing to carry out accordance and economies of scale, like a utility over a network. The basic of Cloud Computing is the extended concept of sharing services and aggregate infrastructure. It is the product of evolution and using current exponents and technologies.

The Important of Cloud Computing is increasing and it is receiving a growing attention in Scientific & Industrial Communities. Cloud computing is one of the top 10 most important technologies and has a greater possibility in successive years by companies and organizations. Cloud computing implement everywhere, favourable, on demand network access to a shared pool of configurable computing resources (e.g. networks, servers, storage, applications and servers) that can be immediately supply and released with minimal management effort.

Abstract-The excessive demand of pay per usage Cloud Computing model, considerably raise the need to balance the load in datacenter. Load balancing guarantees the availability of services without degrading the performance to users. Downtime observed by users is a big issue which leads to violation of quality of services (QoS) and requirements for users in time. Solution to this problem lies in improvement of response time.

IT departments and infrastructure providers are under increasing pressure to provide computing infrastructure at the lowest possible cost. In order to do this, the concepts of resource pooling, virtualization, dynamic provisioning, utility and commodity computing must be leveraged to create a public or private cloud that meets these needs. Cloud computing is a general term for anything that involves delivering hosted services over the Internet. This provides the smaller

Cloud computing is an ever expanding part of the IT industry, it is quickly being adopted by more ICT businesses due to it’s

Cloud based application workloads are very dynamic [1] and distinctive in nature, and the resources of the Cloud environments should exploit their native properties such as rapid elasticity, resource sharing, instant scaling etc, in such a way to handle the incoming workloads in an efficient way. Cloud datacenters are facing more commercial and interactive workloads at higher frequencies unlike the traditional

The scarcity of computing resources can lead to slowdown or delay in processing job requests. In some cases, it leads to the rejection of job request. However, the emergence of Cloud computing gives the illusion of infinite computing resources. These resources are made available on demand and can be provisioned rapidly and automatically in any amount of quantity to process users’ job requests. In the Cloud, it is possible to add up resources for provisioning when there is an increase in application load (Scale up). On the other hand, when there is a decrease in application load, resources can be released. (Scale down). This feature of the Cloud that dynamically scales the amount of the resources it provides to clients as their workloads increase or decrease is called elasticity [41]. In this work, the number of resources in the private Cloud are considered to be static (not elastic). However, based on the characteristics of the incoming jobs of users, extra public Cloud compute resources can be rented or released [1][42].

For cloud computing systems to function optimally, the individual components of the network of computing resources must function optimally. Thus, the importance of keeping track of the performance of these components is apparent. In addition to this, the providers of the cloud service need to

(Joshi and Sivalingam 2013) [7] Cloud is exposed to malicious entries. Preservation of data hence is compulsory. In order to reduce the impact of server failures on the VDCs hosted in the data center, we present a new load balancing scheme based on clustering that efficiently allocates the VDCs on the data center.

We live in a digital world where everything is internet and server based applications to make our lives easy. There is a drastic development of technology from time to time where we have travelled from typical data server with one application on a server to several shared applications in a single server. Increase of redundancy by making data and applications highly available to help disaster recovery. AWS provides features of modern data center with a GUI to establish different applications.

As each server machine can host multiple application so it is important that application should be stateless for the reason that every application store their position information in backend storage servers, so that is repeated safely but it may cause storage servers becomes overloaded but the focus of proposed work is on application tire presenting a architecture is representative of a huge place of internet services hosted in the cloud computing environment even through providing infinite capacity on demand.