Deducing queueing from transactional data: the queue inference engine, revisited
Operations Research - Supplement to Operations Research: stochastic processes
Estimating disperse network queues: The Queue inference engine
ACM SIGCOMM Computer Communication Review
The Impact of Duplicate Orders on Demand Estimation and Capacity Investment
Management Science
New approaches for inference of unobservable queues
Proceedings of the 40th Conference on Winter Simulation
Manufacturing & Service Operations Management
Analysis of an unobservable queue using arrival and departure times
Computers and Industrial Engineering
Queue inference from periodic reporting data
Operations Research Letters
Hi-index | 0.00 |
We are motivated by queueing networks in which queues are difficult to observe but services are easy to record. Our goal is to estimate the queues from service data. More specifically, we consider an open queueing network with Poisson external arrivals, multi-server stations, general service times and Markovian switches of customers between stations. Customers’ transitions between stations may be either immediate or of exponentially distributed durations. Each customer is supplied with an Identification Number (ID) upon entering the network. Operational data is collected which includes transaction times (starts and terminations of services) and ID’s of served customers. Our objective is to estimate the evolution of the queues in the network, given the collected data. We cover estimation at both end of busy periods and in real time. The applicability of the theory is demonstrated by analyzing a service operation.