A novel algorithm for fault tolerant job Scheduling and load balancing in grid computing environment

A load balancing algorithm which considers the different characteristics of the grid computing environment is needed as grid computing is emerging all over the Internet. Therefore, this research presents a Novel fault tolerant job Scheduling and load balancing strategy named as NovelAlg_FLB, which focuses on grid architecture, computer heterogeneity, communication delay, network bandwidth, resource availability, unpredictability and job characteristics. NovelAlg_FLB culminates the strength of neighbor and cluster based load balancing algorithms. The main goal of this research is to arrive at job tasks that will deliver in minimal response time and optimal utilization of computing nodes. Lower complexity of the above mentioned method and extreme reduction of number of additional communications caused due to load balancing are the major achievements conquered. Grid Simulation Toolkit (GridSim) is used to conduct a simulation of the proposed method. It is proven through experimental results that the above mentioned algorithm performs extremely well in a huge grid environment.