كنفرانس بين المللی مهندسی صنايع و سيستم ها

صفحه اصلی / دوازدهمین كنفرانس بين المللی مهندسی صنايع و سيستم ها

A hybrid analytical framework integrating heavy-traffic queuing and service composition in cloud manufacturing

نویسندگان :

Mina Ravanesh¹ Emad Roghanian²

1- دانشگاه صنعتی خواجه نصیرالدین طوسی 2- دانشگاه صنعتی خواجه نصیرالدین طوسی

کلمات کلیدی :

Cloud Manufacturing،Heavy Traffic Queuing Theory،Service Composition،Resource Scheduling،Quality of Service،hybrid framework

چکیده :

Cloud Manufacturing (CMfg) enables on-demand sharing of distributed manufacturing resources, yet efficient scheduling remains a critical challenge, particularly in determining the optimal number of operational machines under varying load conditions. Traditional queuing models based on heavy-traffic limits effectively calculate resource requirements for specific Quality-of-Service (QoS) classes but overlook the potential of service composition capabilities. Conversely, empirical studies on Manufacturing-as-a-Service (Maas) have demonstrated the operational benefits of service composition without providing a rigorous mathematical model for resource sizing. To bridge this gap, this paper proposes a hybrid analytical framework that integrates QoS-classified heavy-traffic queuing theory with a quantitative Service Composition (SC) capability index. The SC index is introduced as a multiplier to enhance the effective service rate, directly impacting the traffic intensity and consequently, the minimum number of machines required to maintain stability. A comprehensive numerical study is conducted for four QoS classes (ZWT, MWT, BWT and PWT) at a traffic intensity of ρ=0.8. The results demonstrate that improving the SC index from 0 to 1 consistently reduces the required number of machines by 28% across all classes. The most significant absolute reductions are observed in the stringent ZWT and MWT classes, with decreases of 280 and 8.4 machines, respectively, while the BWT and PWT classes show reductions of 4.2 and 21 machines, respectively. These findings indicate that investments in service composition yield higher returns in environments with strict quality requirements, helping industrial managers achieve an optimal balance between physical resource investments and software infrastructure in cloud manufacturing.