Adaptive multi-objective swarm intelligence for containerized microservice deployment

Abstract

Container-based microservice architecture is essential for modern applications. However, optimizing deployment remains critically challenging due to complex interdependencies among microservices. In this paper, we propose a formalized deployment model by systematically analyzing the interdependencies within Service Function Chains (SFCs). To achieve this, we design a novel swarm intelligence optimization algorithm, named Multi-objective Sand Cat Swarm Optimization with Hybrid Strategies (MSCSO-HS), for multi-objective optimization in microservice deployment. Our algorithm effectively optimizes inter-microservice communication costs and enhances container aggregation density to improve application reliability and maximize resource utilization. Extensive experiments demonstrate that MASCSO outperforms state-of-the-art algorithms for all optimization metrics. Our model achieves improvements of 23.76% in communication latency, 47.51% in deployment density, 38.70% in failure rate, 58.50% in CPU utilization, and 53.81% in RAM usage. The MASCSO framework not only enhances microservice performance and reliability but also provides a robust solution for resource scheduling in cloud environments for microservice deployment.