Microservice Composition Deployment and Scheduling Method under Multi-objective Optimization

Abstract

The invention discloses a microservice combination deployment and scheduling method under multi-objective optimization, including acquiring resource center-related data, microservice-related data and user-related data; establishing a multi-objective optimization model for microservice combination deployment and scheduling; Algorithm NSGA‑III solves the multi-objective optimization model; calculates the microservice quantity vector that each resource center needs to start; deploys and schedules the microservices in the resource center according to the microservice quantity vector. The present invention builds a detailed multi-objective optimization model for the combined scheduling problem of microservices, solves the model through the improved NSGA-III algorithm, and decodes the solution results to obtain the combined deployment strategy of microservices. Experiments prove the effectiveness of the method of the present invention Compared with the traditional deployment strategy, the microservice combination deployment strategy has greatly improved the computing and storage resources of the resource center, the load balancing rate, and the actual utilization rate of the service.

Description

technical field [0001] The invention belongs to the field of high-performance cloud computing services, and in particular relates to a microservice combination deployment and scheduling method under multi-objective optimization. Background technique [0002] Microservices are the product of SOA architecture development and cloud technology development and application to a certain mature stage. There are many shortcomings in the traditional single application, especially for the concurrent conditions of a large number of users distributed in different regions and with different business needs. Scalability, fault tolerance, stability, and invulnerability are obviously unable to meet the concurrency requirements of large-scale distributed users in the mobile Internet. Microservices split traditional monolithic applications into services, and decompose them horizontally or vertically into mutually independent microservices according to business and functional requirements. Each...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a microservice combination deployment and scheduling method under multi-objective optimization, which is used to solve the problem of the deployment and scheduling process of microservices, involving many objective functions, complex constraints, strong real-time requirements for the calculation of results, and The problem with high performance indicators

Images