A multi-objective approach to model-driven performance bottlenecks mitigation

Software performance engineering (spe) evaluates the key performancefactors such as response time and utilization in the entire life cycle of software development.one of the important issues of software performance is bottlenecks that have not beeninvestigated much till now in the process of spe. meanwhile, bottleneck detection andmitigation in software modeling stage is quality-centered and cost eective. layeredbottleneck is a type of bottleneck that occurs in systems with layered services and aects itsutilization more than at bottlenecks. the presented approach in this paper has selectedlayered queening network (lqn) as an appropriate performance model to present andanalyze the layered bottlenecks. the process of spe from software model to performancemodel has been automatically implemented. also, an optimization stage is added to ndthe best specication of software model in a way that the strength of the bottleneck, theresponse time and the cost will be minimized. to assess the proposed solution, two recentlyproposed multi-objective gravitational search algorithms are employed. to evaluate theeectiveness of the applied algorithms, two well-known multi-objective algorithms: nsgaiiand mopso are also applied to a case study, and a comprehensive comparison ispresented.