A Survey of Load Balancing and Implementation of Clustering-Based Approach for Clouds

Background: Generally, it is observed that there is not a single algorithm that classifies the task using Quality of Service (QoS) parameters requested by the task but instead focuses on classifying resources and balancing the task's using the availability of resources. In past literature, authors divided the load balancing solutions in three main parts workload estimation, decision making, task transferring. Workload estimation deals with identifying requirements for the incoming tasks on the system. Decision making is done to analyze that whether or not load balancing should be performed for the given node. If the decision for load balancing has been made then third step deals with transferring task to appropriate node to reach a saturation point where the system will be in the stable state. Objective: To address this issue, our approach is more focused upon on workload estimation and its main objective is to cluster the incoming heterogeneous task into generic groups. Another issue for this approach is that the client demand varies for the number of tasks. Thus, some attributes may be much more critical to a user then the others and this demand changes from user to user. Methods: This paper classify the tasks using QoS parameters and focused on work-load estimation. The main objective is to cluster the incoming heterogeneous task into generic groups. For this, KMedoid based clustering approach for cloud computing is devised and implemented. This approach is then compared with its different iterations to analyses the workload execution more deeply. Results: The analysis of our approach is computed using cloudsim simulator. Results and computations shows that the data is very uneven in initial times, as some clusters have only four elements and others are having much more elements. Whereas after the 20^th iteration data observed is more normally balanced, so the clusters formed after 20^th iteration were more stable than clusters formed initially i.e. 1st iteration. The number of iterations is also minimized to do unnecessary clustering as after a few steps the changes in medoids are very less. Conclusion: A brief survey of various load balancing techniques in cloud computing is discussed. These approaches are meta-heuristic in nature and have complex behavior and can be implemented in cloud computing. In our paper, K-Medoid based clustering approach for identifying the task into similar groups has also been implemented. Implementation is done on cloudsim simulation package provided by Cloud Labs, which is a java based open source package. The results obtained in our approach are limited to classi fication of tasks into various clusters. It would also useful where new task arrives and simply assign it to a VM that was created for some other element of that class. In future, this work can be expanded to create an effective clustering based model for load balancing.