Load Rebalancing in Cloud Computing Environment Anagha Meher Bidisha Roy Rajkumar Shende Department of Computer Engineering Department of Computer Engineering Department of Computer Engineering St. Francis Institute of Technology St. Francis Institute of Technology St. Francis Institute of Technology Mumbai, India Mumbai, India Mumbai, India Abstract—Cloud computing is distributed computing over a network and it means the ability to run a program on many connected computers at the same time.Large scale distributed systems such as cloud computing applications are becoming very common. These applications come with increasing challenges on how to transfer and where to store and compute data. Load balancing is the one of the challenging task. Load balancing is the process of reassigning the total loads to the individual nodes of the collective system to make the best response time and also good utilization of the resources and to remove the situation where some nodes are over loaded and some other are under loaded. To decrease the total number of heavy nodes (servers) in the system by moving load from heavy nodes (servers) to light nodes (servers) is the main aim of balancing the load. Our objective is to allocate the files as uniformly as possible among the nodes such that no node manages an excessive number of loads. In this paper we present K-means algorithm, Min-Min and Max-Min algorithm for load balancing on cloud. Keywords— Load balance, clouds, K-means algorithms, Min- Min algorithm, Max-Min algorithm I. INTRODUCTION The concept of Cloud computing has significantly changed the field of parallel and distributed computing systems today. Cloud Computing (or cloud for short) is a compelling technology. In clouds, clients can dynamically allocate their resources on-demand without sophisticated deployment and management of resources [1]."Cloud" simplifies the many network connections and computer systems involved in online services. Cloud Computing is a technology, which connects so many nodes together for allocating resources dynamically [2].Cloud computing is a internet based development and use of computer technology. It is a style of computing in which dynamically scalable and often virtualized resources are provided as a service over the internet. Different types of technologies are used in clouds such as Map Reduce programming paradigm, distributed file systems, virtualization. These kinds of technologies are scalable which can add or delete new nodes or systems making it reliable [2].In large cloud we can connect hundreds or thousands of node together. By shifting of workload (processes) among the processor (servers), it is a process of load balancing for improving the performance of the system. Load balancing is a methodology to distribute workload across multiple computers, or other resources over the network links to achieve optimal resource utilization, maximize throughput, minimum response time, and avoid overload. This project is based on simulation technique. When analyzing the existing system, clouds rely on central nodes to balance the loads of storage nodes, there comes the performance bottleneck because the failure of central nodes leads to the failure of whole system and it will leads to many technical and functional difficulties. The term which is generally used in reference to internet is called as cloud computing. The cloud is changing the worldwide network of computer into largest single computer. Resource sharing increases the load on single machine. Therefore overall performance decreases and this problem are called as load balancing. Load balancing is one of the major issues now days. It is a process of reassigning the total load to the individual nodes of the collective system to make resource utilization effective and to improve the response time of the job, simultaneously removing a condition in which some of the nodes are over loaded while some others are under loaded. Load balancing is one of the central issue in cloud computing. It is a mechanism that distributes the dynamic local workload evenly across all the nodes in the whole cloud to avoid a situation where some nodes are heavily loaded while others are idle or doing little work. It helps to achieve a high user satisfaction and resource utilization ratio, hence improving the overall performance and resource utility of the system. Load balancing simultaneously removing a condition in which some of the nodes are over loaded while some others are under loaded. II. RELATED WORK In [1], The chunks can be distributed to the system evenly for reducing movement cost as much as possible it is a design to reallocate file chunks in load rebalancing algorithm. Number of chunks migrated to balance the loads of the chunk servers it is define as movement cost. To reduce demanded movement cost and to balance the loads of nodes these are the advantages of this paper. Physical network locality and node heterogeneity these advantages are taken in this paper. Existing centralized approaches are comparable with this proposal. The load imbalance factor, movement cost, and algorithmic overhead these terms are considerably outperform in prior distributed algorithm. In [5], Distributed hash tables are shown to become a useful building block for a variety of distributed applications. To International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 www.ijert.org IJERTV4IS080672 (This work is licensed under a Creative Commons Attribution 4.0 International License.) Vol. 4 Issue 08, August-2015 734