The paper "On the Joint Design of Microservice Deployment and Routing in Cloud Data Centers" addresses the challenges of transitioning from traditional monolithic to microservice architecture in internet enterprises. The authors propose a comprehensive solution that optimizes both microservice deployment and request routing to enhance system performance. Key contributions include: 1. **Performance Analysis Model**: A model is developed using Open Jackson queuing network theory to analyze queuing delay, processing time, and data communication, introducing a delay minimization objective function. 2. **Hybrid Genetic and Local Search-Based Deployment Algorithm (HELAS)**: This algorithm optimizes service deployment and request routing by using $m/m/c$ queues. It involves multiple iterations of deployment and routing processes, refined through crossover and local search operations. 3. **Probabilistic Forwarding-Based Routing Algorithm (PORA)**: This algorithm selects routing paths based on instance location and computing resources to improve system performance. The paper demonstrates that the proposed scheme significantly reduces average response latency by 37%-67% and enhances request success rates by 8%-115% compared to baseline algorithms. The joint optimization problem is complex, combining aspects of capable facility location and category-constrained multiple knapsack problems, which are NP-hard. The authors' heuristic approach leverages genetic and local search techniques to address this challenge effectively.The paper "On the Joint Design of Microservice Deployment and Routing in Cloud Data Centers" addresses the challenges of transitioning from traditional monolithic to microservice architecture in internet enterprises. The authors propose a comprehensive solution that optimizes both microservice deployment and request routing to enhance system performance. Key contributions include: 1. **Performance Analysis Model**: A model is developed using Open Jackson queuing network theory to analyze queuing delay, processing time, and data communication, introducing a delay minimization objective function. 2. **Hybrid Genetic and Local Search-Based Deployment Algorithm (HELAS)**: This algorithm optimizes service deployment and request routing by using $m/m/c$ queues. It involves multiple iterations of deployment and routing processes, refined through crossover and local search operations. 3. **Probabilistic Forwarding-Based Routing Algorithm (PORA)**: This algorithm selects routing paths based on instance location and computing resources to improve system performance. The paper demonstrates that the proposed scheme significantly reduces average response latency by 37%-67% and enhances request success rates by 8%-115% compared to baseline algorithms. The joint optimization problem is complex, combining aspects of capable facility location and category-constrained multiple knapsack problems, which are NP-hard. The authors' heuristic approach leverages genetic and local search techniques to address this challenge effectively.