Abstract
Sustainability of software architectures is largely dependent on cost-effective evolution and modular architecture. Careful modularization, characterizing proper design of complex system is cognitive and challenging task for insuring improved sustainability. Moreover, failure to modularize the software sys-tems during its evolution phases often results in requiring extra effort towards managing design deterioration and solving unfore-seen inter-dependencies. In this paper, we present an empirical perspective of package-level modularization metrics proposed by Sarkar, Kak and Rama to characterize modularization quality through packages. In particular, we explore impact of these design based modularization metrics on other well known mod-ularity metrics and software quality metrics. Our experimental examination over open source java software systems illustrates that package-level modularization metrics significantly correlate with architectural sustainability measures and quality metrics of software systems.
Highlights
In recent times, conventional conjectures of experimental research and theory have been joined by computational and data-intensive methodologies [1], [2]
We explored Sarkar et al.’s package-level modularization metrics for automated optimization of module structure and determine their correlation strength with the metrics related to testing efforts, deficit produced in design of software and overall maintainability
Our results show that package level modularization metrics bear considerably significant relationship with modularization metrics studied in different engineering domains
Summary
Conventional conjectures of experimental research and theory have been joined by computational and data-intensive methodologies [1], [2]. Software architectures metrics help developers to determine maintenance objectives, testing effort and overall design decisions. It is worth mentioning that Sarkar et al.’s study provided experimental validation of proposed architectural metrics to an extent They introduced comparative analysis on modularity achievement between human based development effort and randomized modularization. We explored Sarkar et al.’s package-level modularization metrics for automated optimization of module structure and determine their correlation strength with the metrics related to testing efforts, deficit produced in design of software and overall maintainability. Significant statistical correlation was witnessed with metrics quantifying maintainability, design deficit and testing effort These findings help to evaluate software sustainability in terms of architecture.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have