Cloud computing is a new archetype that provides dynamic computing servicesto cloud users through the support of datacenters that employs the services ofdatacenter brokers which discover resources and assign them Virtually. Thefocus of this research is to efficiently optimize resource allocation in thecloud by exploiting the Max-Min scheduling algorithm and enhancing it toincrease efficiency in terms of completion time (makespan). This is key toenhancing the performance of cloud scheduling and narrowing the performance gapbetween cloud service providers and cloud resources consumers/users. Thecurrent Max-Min algorithm selects tasks with maximum execution time on a fasteravailable machine or resource that is capable of giving minimum completiontime. The concern of this algorithm is to give priority to tasks with maximumexecution time first before assigning those with the minimum execution time forthe purpose of minimizing makespan. The drawback of this algorithm is that, theexecution of tasks with maximum execution time first may increase the makespan,and leads to a delay in executing tasks with minimum execution time if thenumber of tasks with maximum execution time exceeds that of tasks with minimumexecution time, hence the need to improve it to mitigate the delay in executingtasks with minimum execution time. CloudSim is used to compare theeffectiveness of the improved Max-Min algorithm with the traditional one. Theexperimented results show that the improved algorithm is efficient and canproduce better makespan than Max-Min and DataAware.
展开▼
