2N
Redundancy where the entire power/cooling system is fully mirrored, so any single path can fail with zero impact.
Current numbers
~50% / 2–3%battery-capacity cut and double-conversion-loss cut from distributed BBU + supercaps vs central 2N
secondsloss-of-cooling thermal-trip window for 1 kW+ GPUs — UPS-backed pumps + N+1/2N rejection mandatory
+30–50%MEP construction-cost swing of 2N over N+1; 2N strands ~50% of capacity idle