Task scheduling with enhanced VM migration using SM-PCCTSA with SKD-RBM

Recently, Cloud Computing (CC) and virtualization are the approaches developed for Task Scheduling (TS) in the Cloud Data Centre (CDC). Energy Consumption (EC), which maximizes the cost of cloud users, is one of the key issues faced by the CDC. Thus, by employing Scramble Mutation-centric Pearson Correlation Coefficient Tree Search Algorithm(SM-PCCTSA) with Solomon Kullback Divergence-centric Restricted Boltzmann Machine (SKD-RBM), a Multi Optimized TS Framework for Virtual Machines (VMs) with enhanced migration is proposed in this paper. Primarily, the request is sent to the CDC by the users and the information on the tasks is extracted. Then, by deploying the Standard Deviation-based Minkowski Distance K-Means (SD-MDKM), the tasks are prioritized. Next, the time slot is generated to execute the tasks. Moreover, the tasks are scheduled using SM-PCCTSA grounded on the time slot. A similar process is undergone by the newincoming tasks. In the case of VM unavailability, VM Migration (VMM) is done by employing SKD-RBM and then the High-Priority (HP) tasks are scheduled. In the end, by utilizing the Entropy-centric Binomial Distribution Fuzzy (EBD-Fuzzy) Algorithm, the VM attributes are extracted for VM monitoring. Incomplete tasks are scheduled centered on the status of the VMs. The experimental analysis outcomes stated the robustness of the proposed system by attaining 96.10% accuracy, 96.23% precision, and 95.71% f-measure. For 100 tasks, the clustering, response, throughput, processing, latency, and average waiting times of the proposed system are 216 ms, 3784 ms, 2945 ms, 2671 ms, 874 ms, and 896 ms, respectively. According tothe experiential investigation, the proposed technique is analogized with the conventional methodology and iscomparatively more effectual.