The Definitive Guide toAI Data Centers
Ask the GuideAboutAccount
Calculators › Redundancy options

Redundancy options

Size N, N+1, 2N, 2(N+1) and the distributed 3N/2 and 4N/3 options for one load from equal modules: installed modules and their multiple of N, the load on each module, whether each option rides through a module failure or can be serviced live, and modelled annual downtime from your failure and repair rates. It names the option with the fewest modules that meets your requirements.

ScenarioNVIDIA GB300 NVL72 · 56 active / 72 installed GPUs · 1 racks · 0.14 MW IT · $9M programguide defaults (as of 2026-09)Edit your project assumptions →

Redundancy options compared

3N/2 meets your requirements with the fewest modules: 6, 1.5× N

N = 800 kW ÷ 200 kW, rounded up = 4 modules.

Each option sized for this load
OptionModules× NLoad per moduleRides through a module failureService a module liveService a path liveSurvives losing a pathSurvives a failure during serviceModelled downtime
N41×100%nonononono140 h a year
N+151.25×80%yesyesnonono2.8 h a year
2N82×50%yesyesyesyesno2.2 h a year
2(N+1)102.5×40%yesyesyesyesyes3 s a year
3N/261.5×67%yesyesyesyesno1.7 h a year
4N/382×50%yesyesyesyesno3.3 h a year

Concurrent maintainability means you can service any module or path with the load held; it needs a second path, so N+1 on one shared path does not qualify (losing that bus drops the load) → Ch 0.5. Module count tracks equipment cost only: distribution, transfer switches and controls are extra, and 3N/2 and 4N/3 need more of them → Ch 12.1. The downtime column is a screening model: modules fail independently at your rate, each path or block has one repair crew, the paths share nothing and every transfer works. Shared buses, controls and common causes usually set real downtime, so read these hours as a floor → Ch 12.5.

Worked decision — stated assumptions

All ledger inputs are assumed teaching values chosen to exercise this chapter’s method; they are not market quotes, OEM performance claims or operating records. Arithmetic uses the full entered precision.

Assumed inputs
InputValue
Load to protect800 kW
Module size200 kW
Failures per module per year4.38 per yr
Repair time per failure8 h
Distribution paths for N and N+1one
Concurrent maintainability required?yes
Ride through one module failure?yes

Decide how much plant to buy for an 800 kW load from 200 kW modules when the owner wants both concurrent maintainability and ride-through of one module failure. N is 800 ÷ 200 = 4 modules. With one shared distribution path, N+1 rides through a module failure but cannot keep the load up while that path is serviced, so it fails the maintainability requirement. Of the options that meet both, 3N/2 needs the fewest modules: three blocks of two, 6 modules or 1.5× N, each module 67% loaded. 2N needs 8 and 2(N+1) needs 10. At Chapter 12.5's illustrative power-path rates (one failure per 2,000 hours, 8 h repair), 3N/2 models about 1.7 hours of downtime a year before shared causes.

Add a standby distribution path for maintenance: N+1 now meets both requirements with 5 modules, 1.25× N. The trade is a second path and its transfer equipment against one fewer module, so price both before you choose, and prove the transfer works in commissioning.

Guide derivation. Method and handoff: Chapter 0.5 — Reliability, Redundancy & Availability: The Design-Basis Primer.

These are transparent screening estimates, not final designs, financial advice, or project approvals. Replace every default with current project data and have the responsible project authorities validate the result. You can save, share a permalink, or export to CSV; see the full calculator suite.