Simulation01
Discrete events
Arrivals and service completions move the system forward. A shared waiting line feeds the first available service channel.
Designed & builtJavaScript · operations analytics
AN INTERACTIVE LABORATORY FOR THE SCIENCE OF WAITING
Queue Lab
See how variability and service capacity shape a waiting line. Change the inputs, watch customers arrive and leave, and connect the live simulation to queueing theory.
Recorded app demo · GIFConfigure → simulate → compare
1–10parallel service channels
Live simulationcustomers, queues, and service
Finite or unlimitedwaiting-room capacity
Simulation + theorycompare observed and expected results
01 / PRODUCT OVERVIEW
Turn a formula into a system you can see.
Why can a line grow even when average capacity seems sufficient? What changes when you add a server or reduce variability?
Queue Lab puts those questions into a browser experiment. A discrete-event simulation drives the customer animation and empirical distributions, while analytical reference values make the connection between the experiment and operations-management concepts visible.
My roleProduct Designer · DeveloperInteractive learning workflow, simulation controls, queue visualization, and analytical comparison.
02 / USER WORKFLOW
Change one assumption. See what follows.
- 01
Choose the variability
Select Poisson, exponential, normal, or constant arrival and service settings. Adjust rates and the spread of normal times.
- 02
Set service capacity
Choose one to ten service channels and an unlimited or finite waiting room. Try café, bank, call-center, steady-service, or overloaded presets.
- 03
Watch the system evolve
Run the animated queue, pause, advance one event, change speed, or fast-forward through 2,000 customers.
- 04
Compare and explain
Read live performance measures, distributions, and theory. Compare parallel channels with a single faster channel of equal total capacity.
03 / SIMULATION & ANALYTICAL LOGIC
Observe the queue. Inspect the explanation.
The laboratory displays queue length, customers in service, throughput, and turnaways alongside distributions and simulated-versus-theoretical performance.
Exact references02
M/M/1 & M/M/s
Single-server formulas and Erlang C provide reference values for stable systems with exponential interarrival and service times.
Capacity limits03
Finite waiting rooms
A birth–death calculation handles limited line capacity and the probability that an arriving customer is turned away.
Other distributions04
Approximate comparisons
For general or constant times with unlimited waiting space, the app uses an Allen–Cunneen approximation. Interface labels distinguish approximations and reference values.
04 / TEACHING & EXPERIMENTATION
A small experiment for a practical operations question.
Make capacity decisions visible
Compare a café with one service channel, a bank with several tellers, or a call center with limited waiting capacity. Observe the relationship between utilization, congestion, and customer experience.
Connect evidence and theory
Explore how changing variability affects waiting times, examine simulated distributions, and compare one fast server with multiple parallel servers at equal total capacity.
05 / TRY THE APPLICATION
Run your own queue experiment.
Queue Lab runs directly in your browser with no account or API key. Start with a preset, adjust one input, and compare the resulting behavior. The app is an educational simulation; theoretical comparisons depend on the assumptions shown in the interface.