Performance assessment based on stochastic differential equation and effort data for edge computing. (15th February 2021)

• Record Type: Journal Article
• Authors: Tamura, Yoshinobu; Yamada, Shigeru
• Is Part Of: Software testing, verification & reliability. Volume 31:Number 6(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-02-15
• Subjects: edge computing -- effort control -- open‐source project -- stochastic differential equation; Computer software -- Testing -- Periodicals; Computer software -- Verification -- Periodicals; Computer software -- Reliability -- Periodicals; 005.14
• DOI: 10.1002/stvr.1766
• Languages: English
• ISSNs: 0960-0833

Abstract

Summary: Many open‐source software are included in commercial software. Also, several open‐source software are used in the cloud service such as OpenStack and Eucalyptus from standpoint of the unified management, cost reduction and maintainability. In particular, the operation phase of cloud service has a unique feature with uncertainty such as big data and network connectivity, because the operation phase of cloud service changes depending on many external factors. On the other hand, the effective methods of performance assessments for cloud service have only a few presented. Recently, edge computing is the focus of attention because of the problems of connection and processing delay in case of cloud computing. It is known as that cloud computing treats big data. On the other hand, edge computing operates on instant data. We focus on the performance assessments based on the relationship between the cloud and edge services operated by using several open‐source software. Then we propose a two‐dimensional stochastic differential equation model considering the unique features with uncertainty from big data under the operation of cloud and edge services. Also, we analyse actual data to show numerical examples of performance assessments considering the network connectivity as characteristics of cloud and edge services. Moreover, we compare the noise terms of the proposed model for actual data. Abstract : We propose the method of performance assessment for edge computing. Then, a two‐dimensional stochastic differential equation model considering the unique features with uncertainty from big data under the operation of cloud and edge services has been proposed. This paper has shown several numerical examples of performance assessments considering the network connectivity as characteristics of cloud and edge services. Moreover, this paper compares the noise terms of the proposed model for actual data.