• Journal of KIISE:Software and Applications
• /
• v.37 no.7
• /
• pp.503-517
• /
• 2010

Service-oriented computing, the effective paradigm for developing service applications by using reusable services, becomes popular. In service-oriented computing, service consumer has no responsibility for managing services, just invokes services what service providers are producing. On the other hand, service providers should manage any resources and data for service consumers can use the service anytime and anywhere. However, it is hard service providers manage the quality of the services because an unspecified number of service consumers. Therefore, service scalability for providing services with higher quality of services specified in a service level agreement becomes a potential problem in service-oriented computing. There have been many researches for scalability in network, database, and distributed computing area. But a research about a definition of service scalability and metrics of measuring service scalability is still not mature in service engineering area. In this paper, we construct a service network which connects multiple service nodes, and integrate all the resources to manage it. And we also present a service scalability framework for managing service scalability by using a mechanism of service migration or replication. In section 3, we, firstly, present the structure of the scalability management framework and basic functionalities. In section 4, we propose scalability enhancement mechanism which is needed to release functionality of the framework. In section 5, we design and implement the framework by using proposed mechanism. In section 6, we demonstrate the result of our case study which dynamically manages services in multi-nodes environment by applying our framework. Through the case study, we show the applicability of our scalability management framework and mechanism.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.3
• /
• pp.73-82
• /
• 2022

Auto-scaling is one of the most important functions for cloud computing technology. Even if the number of users or service requests is explosively increased or decreased, system resources and service instances can be appropriately expanded or reduced to provide services suitable for the situation and it can improves stability and cost-effectiveness. However, since the policy is performed based on a single metric data at the time of monitoring a specific system resource, there is a problem that the service is already affected or the service instance that is actually needed cannot be managed in detail. To solve this problem, in this paper, we propose a method to predict system resource and service response time using a multivariate time series analysis model and establish an auto-scaling policy based on this. To verify this, implement it as a custom scheduler in the Kubernetes environment and compare it with the Kubernetes default auto-scaling method through experiments. The proposed method utilizes predictive data based on the impact between system resources and response time to preemptively execute auto-scaling for expected situations, thereby securing system stability and providing as much as necessary within the scope of not degrading service quality. It shows results that allow you to manage instances in detail.