Stochastic Model Driven Performance and Availability Planning for a Mobile Edge Computing System

Mobile Edge Computing (MEC) has emerged as a promising network computing paradigm associated with mobile devices at local areas to diminish latency under the employment and utilization of cloud/edge resources. In that context, MEC solutions are required dynamically allocate requests close possible their Moreover, power resource capacity server machines can directly impact performance operational availability apps services. The systems practitioners must understand trade off between in design stages. analytical models suited such an objective. Therefore, this paper proposes Stochastic Petri Net (SPN) evaluate both environments. Different previous work, our proposal includes unique metrics discard probability sensitivity analysis guides evaluation decisions. highly flexible by considering fourteen transitions base model twenty-five extended model. was validated real experiment, result which indicated equality experiment p-value equal 0.684 t-Test. Regarding availability, results model, different from always remain above 99%, since it presents redundancy components were impacting A numerical is performed comprehensive manner, output study serve practical guide designing system architectures making trade-off Mean Response Time (MRT) utilization.