Adaptive Evolutionary Optimization for Resource Allocation in Cloud Microservices
S Saivardhan, Sufian Ali, V Kethan Reddy, Sivasankara Rao S
1B. Tech IV Year(21WJ1A05V3), Department of CSE, Guru Nanak Institutions Technical Campus, Hyderabad.
2B. Tech IV Year(21WJ1A0529), Department of CSE, Guru Nanak Institutions Technical Campus, Hyderabad.
3B. Tech IV Year(21WJ1A05X7), Department of CSE, Guru Nanak Institutions Technical Campus, Hyderabad.
Associate Professor, Department of CSE, Guru Nanak Institutions Technical Campus, Hyderabad.
Abstract: Efficient resource allocation for microservice management in heterogeneous cloud environments remains a critical challenge due to dynamic workload variations and network constraints. This paper presents an optimized framework, the Multi-Objective Microservice Allocation (MOMA) algorithm, which formulates resource management as a constrained optimization problem. The proposed approach prioritizes two key factors resource utilization and network communication overhead—to ensure efficient microservice deployment and system performance. By intelligently distributing workloads and minimizing transmission delays, the framework simplifies cloud service orchestration and enhances real-time workload monitoring. A comparative evaluation against existing algorithms using real-world datasets highlights significant improvements in resource balancing, network efficiency, and overall system reliability. Experimental results confirm that the MOMA algorithm effectively enhances resource utilization, reduces network congestion, and improves cloud service stability, making it a promising solution for modern cloud computing environments.
Keywords: Resource allocation, genetic algorithm, container-based heterogeneous cloud, multi-objective optimization, microservice.
