Abstract
An application based on a microservice architecture with a set of independent, fine-grained modular services is desirable, due to its low management cost, simple deployment, and high portability. This type of container technology has been widely used in cloud computing. Several methods have been applied to container-based microservice scheduling, but they come with significant disadvantages, such as high network transmission overhead, ineffective load balancing, and low service reliability. In order to overcome these disadvantages, in this study, we present a multi-objective optimization problem for container-based microservice scheduling. Our approach is based on the particle swarm optimization algorithm, combined parallel computing, and Pareto-optimal theory. The particle swarm optimization algorithm has fast convergence speed, fewer parameters, and many other advantages. First, we detail the various resources of the physical nodes, cluster, local load balancing, failure rate, and other aspects. Then, we discuss our improvement with respect to the relevant parameters. Second, we create a multi-objective optimization model and use a multi-objective optimization parallel particle swarm optimization algorithm for container-based microservice scheduling (MOPPSO-CMS). This algorithm is based on user needs and can effectively balance the performance of the cluster. After comparative experiments, we found that the algorithm can achieve good results, in terms of load balancing, network transmission overhead, and optimization speed.
Highlights
Pareto theory is a decent framework that can be used to deal with multi-objective optimization problems; we use an algorithm that combines the particle swarm optimization algorithm and the Pareto frontier, using Pareto theory to evaluate the quality of the function solution
We compared the performance of the four algorithms considering six different aspects: network transmission overhead, local load balancing, standard deviation of cluster resources, global load balancing, service reliability, and algorithm running speed
Network transmission takes into account the number of requests, transmission data size, transmission distance, transmission time, and other factors in the process of network transmission, and so network transmission overhead is one of the indicators we used to measure the performance of the algorithm
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Considered the specific quality of service (QoS) trade-offs and proposed an innovative capillary computing architecture These methods can solve the container-based microservice scheduling problem, to some extent; most of them can only achieve cluster load balancing, and cannot achieve local load balancing. These methods are prone to uneven use of resources within the node, resulting in unreasonable container allocation, which leads to increased transmission overhead and reduced reliability. We establish three new optimization target models for the container-based microservice scheduling problem: the network transmission cost model between microservices, the global and local load balancing model, and the service reliability model.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
