Dipper Throated Optimization with Convolutional Neural Network Based Task Scheduling and Resource Allocation in the Cloud Computing

The progress in the recent technology has shown wide application of cloud computing due to its extensive range of assistances for the users. The functioning of schedule task and allocate the resources in the cloud is affected due to enormous multiple task request. The existing methods tried to overcome the problem of multiple user requests to balance the cloud load but failed to reach the estimated outcome due to limited space searching ability. To overwhelm the existing problem an improved Dipper Throated Optimization with Convolutional Neural Network (DTO-CNN) method is introduced to increase the functioning of task scheduling and resource allocation in the cloud atmosphere. The CNN algorithm was used to predict the task scheduling in the cloud based on their previous history. The DTO algorithm was used for improving space searching ability of the CNN model that improved the schedule task and allocate the resources in the cloud atmosphere. The functioning of the proposed DTO-CNN algorithm is evaluated using throughput, reliability and response time. The developed DTO-CNN has obtained throughput of 307ms, reliability of 0.895 and response time of 991ms for 500 number of tasks compared to the existing FFARS-MSO model.