Optimising Makespan Minimization and Performance at the Same Time with a Dynamic Cloud Task Scheduling Comparative Study of MOSOS and PSO

The practice of allocating available resources, such as personnel, money, time, or materials, to different tasks, projects, or activities is known as resource allocation. Effective resource allocation is crucial for optimizing productivity, achieving goals, and maximizing efficiency within an organization or project. Resource allocation in cloud computing can face several challenges. These include over-allocation, where resources are provisioned excessively, leading to increased cost, and under-allocation, which can result in performance bottlenecks. Cloud environments often have to support a variety of different workloads, each with its own resource requirements. This can make it difficult to allocate resources efficiently whilst maintaining the Quality of Service (QoS). Tackling such issues, our paper demonstrates the workings of the MOSOS (multi-objective symbiotic organism search) algorithm to optimize the performance and cut down on makespan and cost. We simulate MOSOS alongside the Particle Swarm Optimization Algorithm (PSO) to understand whether PSO outperforms MOSOS or whether MOSOS accomplishes similar results to PSO. The results back up MOSOS in terms of makespan but fail when compared against PSO's execution times. We find that PSO uses a lesser number of parameters and makes fewer function calls as opposed to MOSOS. Thus, we can argue that in dynamic cloud environments where time is essential, PSO may perform better as compared to MOSOS.