This paper proposed an algorithm for fault tolerant distributed computation in a grid by the means of meta-heuristic Ant Colony Optimization (ACO) technique and Check-Pointing. Load Balancing is the process of distributing the workload among the nodes in a grid. The load can be CPU cycles, memory capacity or network load. Due to the emerging computing methodology of grid computing over the heterogeneous environment there is a need of hybrid fault tolerant load balancing technique which takes into account the grid scenario including computer heterogeneity, network bandwidth and communication delay. General TermsAlgorithms Used: ACO Algorithm for Load Balancing, Check-Point Setter Algorithm and Fault Index Update Algorithm as fault tolerance mechanisms.

Cloud computing is a business oriented IT-technology, which is composed of multiple computing technologies accessed via internet. With the rapid increase in cloud usage, it becomes a challenge to deliver the cloud services effectively and efficiently to the cloud consumers on the pay-per usage basis. In this concern Balancing of load has become one of the essential components for the cloud computing environment to perform the effective operations. Scheduling of virtual machines or data centers has to be done properly by using an appropriate load balancing technique. Hence, several algorithms have been developed to process the client's request towards the cloud nodes.. In this present work, a hybridized swarm intelligence technique is proposed to evenly distribute the incoming task requests among the virtual machines or server. Additionally, the performance analysis has been performed using the CloudAnalyst simulator. This paper gives a comprehensive performance analysis of the proposed approach and compares its results with existing Round Robin (RR), Equally Spread Current Execution (ESCE) and ant colony optimization (ACO) techniques. Simulation results have demonstrated that the proposed technique shows a significant outcome in terms of response time, data center processing time and total cost in cloud computing.

No abstract

No abstract