Capacity Planning Model for a Black-Friday Traffic Surge
Overview
What this challenge is about.
Pull 18 months of per-service request rate + utilization from Prometheus. Forecast BFCM traffic per service using a baseline + multiplicative seasonal model (Prophet or statsmodels SARIMA). Compute required capacity per service from the forecast + headroom + per-service utilization-to-capacity curves (load test if not already known). Design an autoscaling policy: warm-pool size, scale-out triggers, scale-in cooldowns. Build a pre-warm calendar (T-7 days, T-2 days, T-1 day). Validate against 3 prior BFCMs — would your model have over- or under-provisioned? Deliver Python forecasting code, autoscaling configs, pre-warm calendar, and a 7-page proposal.
The Brief
What you'll do, and what you'll demonstrate.
Replace 60 percent over-provisioning with a forecast-driven capacity-planning model validated against 3 prior BFCMs, including autoscaling + pre-warm playbook.
Earning criteria — what you'll demonstrate
- Apply seasonal forecasting (Prophet / SARIMA) to operational traffic data
- Derive per-service capacity from utilization curves and headroom policy
- Design autoscaling that respects warm-up time and scale-in safety
- Validate capacity models against prior peak events
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career mappings coming soon.