A queuing theory model for fog computing

Under many scenarios where resources may be scarce or a good Quality of Service is a requirement, appropriately sizing components and devices is one of the main challenges. New scenarios, such as IoT, mobile cloud computing, mobile edge computing or fog computing, have emerged recently. The ability to design, model and simulate those infrastructures is critical to dimension them correctly. Queuing theory models provide a good approach to understanding how a given architecture would behave for a given set of parameters, thus helping to detect possible bottlenecks and performance issues in advance. This work presents a fog-computing modelling framework based on queuing theory. The proposed framework was used to simulate a given scenario allowing the possibility of adjusting the system by means of user-defined parameters. The results show that the proposed model is a good tool for designing optimal fog architectures regarding QoS requirements. It can also be used to fine-tune the designs to detect possible bottlenecks or improve the performance parameters of the overall environment.