摘要：Load balancing is one of the major issues in cloud computing which allocates a task into VMs with various length and completion time. Hence maintaining load in VMs is a challenging task during task scheduling and allocating. In this paper, we proposed resource aware dynamic task scheduling and secure load balancing using intelligent schemes in cloud environment. The proposed work has following process: (1). Real-Time and Non-Real Time tasks-oriented clustering by using Human Mental Search (HMS) algorithm, in this stage the tasks are clustered into four types such as real-time and short, real-time, and long, non- real time and short and non-real time and long. (2).Energy and Delay aware Clustered Tasks Scheduling, based on the task clustering scheduling is performed and tasks are scheduled in the order of priority which done by using fuzzy VIKOR approach. (3).Security Risks aware VM Clustering, which is done by using Hierarchical Agglomerative Clustering algorithm, this VM clustering process has three entities such as VM’s information collector which collects the information about VMs, second entity is load monitor which manage the whole datacenter and third entity is decision maker which performs task allocation by selecting optimal VM. (4).Co-Resident attacks resisted optimum VM selection which is selected by using continuous-Actor-Critic-Algorithm(C-ACAL). The simulation is conducted by using Cloud Sim that evaluate the performance in terms of response time, latency, resource utilization, throughput, energy consumption and task execution success rate.
