Task Scheduling in Cloud Computing using Mean Ant Colony Optimization

In the context of cloud computing, the scheduling of tasks has been a very crucial component. Numerous guidelines can be subjected as a memorandum of understanding between cloud consumers and organizations that must be obeyed to remedy the task scheduling problem. This agreement indicates the level of service the user expects from the stakeholders. Given the enormous number of tasks co-occurring at the provider’s end, providers must deliver good Quality of Service(QoS) to consumers by the agreement. To sustain good goals for tasks, one could think of the challenges of task scheduling as the search or discovery of an optimal mapping having a set of subtasks consisting of various functions over a range of resources. The approach termed Ant Colony optimization (ACO), which stands for “random optimization search”, is used to spread incoming jobs across virtualized resources. In the research that is being presented, a solution to the issue of job scheduling in cloud computing is proposed in the form of mean ant colony optimization(MACO) method. This MACO shortens the amount of time required to complete the study as a whole by estimating the rate of evaporation along with improvement in the pheromone update function. With the simulation tool CloudSim, the objectives like response time and total time of the proposed method are assessed and compared with other existing algorithms like FCFS, SJF, RR, and PSO. In terms of expenses, resources required, scheduling time, energy consumption, makespan, and degree of imbalance, we aim to build a strategy that can perform at a greater level than the traditional ACO algorithm.