Hypervolume Sen Task Scheduilng and Multi Objective Deep Auto Encoder based Resource Allocation in Cloud

Cloud Computing (CC) environment has restructured the Information Age by empowering on demand dispensing of resources a pay-per-use base. Resource Scheduling and allocation is an approach ascertaining schedule which tasks should be carried out. Owing to heterogeneity nature resources, scheduling in CC considered as intricate task. Allocating best resource for cloud request remains complicated task issue identifying – pair according user requirements optimization issue. Therefore main objective Server allocating optimal manner. In this work optimized scheduled model designed effectively address large numbers arriving from users, while maintaining enhanced Quality Service (QoS). The requests are mapped manner resources. process out using proposed Multi-objective Auto-encoder Deep Neural Network-based (MA-DNN) method combination Sen’s functions Network model. First performed applying Hypervolume-based programming With this, multi-objective (i.e., cost time during tasks) means programming. Second, with that turn allocate utilizing Jensen–Shannon divergence function. function advantage minimizing energy consumption only higher results, mapping performed, therefore improving greater extent. Finally, corresponding Kronecker Delta improves makespan significantly. To show efficiency between environment, we also perform thorough experiments basis realistic traces derived Personal Datasets. experimental results compared RAA-PI-NSGAII DRL, MA-DNN not significantly accelerates efficiency, but reduces usage considerably.