Cloud Computing (CC) environments face the challenge of ensuring optimal Quality of Service (QoS) by improving multiple parameters simultaneously. In this paper, we propose the integration of Smart Message Passing Interface Approach (SMPIA) with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithms for task scheduling and resource allocation in a Cloud environment. These algorithms—PSO-SMPIA and GA-SMPIA—are designed to reduce make-span and total execution time while enhancing resource utilization. The key contribution of this study is the introduction of a new multipurpose function to calculate the maximum cost for each transaction flow, which has been overlooked in previous works. This function factors in flow load amount, make-span, Virtual Machine (VM) capacity, and execution speed. Additionally, we categorize telecommunication deals and tenders based on flow types, and develop an efficient transaction flow allocation matrix to distribute the load across VMs. By sending transaction flows to selected VMs according to the matrix, the algorithms aim to optimize resource utilization. The results demonstrate that PSO-SMPIA outperforms Optimized-SMPIA (O-SMPIA), Fuzzy SMPIA (FSMPIA), and GA-SMPIA in terms of average resource utilization. However, FSMPIA and O-SMPIA exhibit superior performance in reducing make-span and execution time, respectively. Ultimately, GA-SMPIA delivers enhanced QoS by simultaneously reducing make-span and execution time while optimizing resource usage. The implementation is designed on a MERN stack to facilitate scalable, real-time cloud-based task scheduling and resource management.

Keywords: Cloud Computing (CC), Quality of Service (QoS), Task Scheduling, MERN Stack, Optimization Algorithms