24 August 2021 3 5K Report

Suppose we have a system designed to deliver services to customers arriving during weekdays. The arrival process is modeled as a Poisson process with an Arrival rate of λ, also we use agent-based modeling with NetLogo to study the behavior of customers. After multiple Observation and replication of the model, the first 8 hours was selected as the warm-up period and the remaining time as the steady-state. If we consider the average length of stay (ALOS) as the crucial output data, how should we handle the initialization bias in this case?

As a workaround, is removing those data sufficient if we take into account the effects of the warm-up period on the ALOS?

More F. Ge's questions See All
Similar questions and discussions