Efficient Resources Allocation for Different Jobs in Cloud
Cloud Computing is an emerging technique in recent years that provides computing as a services. In order to maximize resources utilization, many scheduling algorithms were analyzed and implemented. Job scheduling using Berger model is one of the algorithm for scheduling jobs. The combination of Berger model and Neural Network would overcome the disadvantage of Berger Model i.e., incompletion of task when tasks-resources match is not achieved. In this paper, the submitted jobs are classified based on different parameters like bandwidth, memory, Completion time and Resources Utilization. The classified user tasks are passed to the neural network. Neural network consists of input layer, hidden layer and output layer. With the help of hidden layer, the jobs are matched with the resources by adjusting weight.