LEVIATHAN SYSTEMS
← Back to Glossary

What Is Power Distribution Unit (PDU)?_

A PDU distributes electrical power from a facility circuit to the equipment within a rack. Data center PDUs come in basic (power strip), metered (with monitoring), monitored (per-outlet metering), and switched (remote outlet control) variants. GPU racks typically require high-amperage PDUs supporting 3-phase power at 208V or 415V, with dual-feed redundancy.

Technical Details

PDU selection for GPU racks depends on total rack power draw, outlet configuration, and monitoring requirements. An H100 rack at 40–80 kW typically uses dual high-amperage PDUs with C19/C20 outlets for server power connections and C13/C14 outlets for switches and accessories. For GB200/GB300 NVL72 racks at 120 kW, power delivery may use 415V 3-phase with dedicated circuit breakers and high-gauge power whips. PDU types progress in capability: basic (power distribution only), metered (total load monitoring), monitored (per-outlet current/voltage monitoring), and switched (remote on/off control per outlet). Intelligent PDUs with network connectivity enable remote monitoring of power consumption, environmental conditions, and outlet status.

How Leviathan Systems Works with Power Distribution Unit (PDU)

Leviathan Systems mounts and wires PDUs as part of GPU rack assembly, selecting appropriate configurations for the power density and monitoring requirements of each deployment.

Appears In

UPS & Battery Energy Storage for AI Halls: Ride-Through for Spiky GPU LoadsGetting Ready for Rubin / VR200: Deployment-Readiness Planning NowRFP & SOW Checklist for a GPU Build: Scope It So Nothing Falls ThroughRack PDU Selection & Metering for GPU Racks: Outlet Count, Phase, TelemetryThe Power-On Walkdown: A Step-by-Step Energization ProcedurePower-On Sequencing for a GPU Hall: Inrush, Soft-Start, and Staged EnergizationScaling from Pilot to Production GPU Cluster: What Breaks and What to PlanCoordinating a Multi-Site GPU Rollout: Standardize Once, Deploy EverywhereMEP Coordination for AI Data Halls: Where Mechanical, Electrical, and IT CollideHow to Choose a GPU Deployment Partner: A Buyer's ChecklistHarmonics & Power Quality at GPU Density: Taming the Switch-Mode LoadH200 Deployment Guide: What's Different from H100 on the FloorH100 / HGX H100 Deployment Checklist: Power, Cooling, and Cabling DemandsThe GPU Deployment Site Survey: What to Measure Before You CommitGPU Data Center Deployment in Northern Virginia: Who Does It and How to HireDe-Racking & Decommissioning a GPU Cluster for MigrationHow to Size a CDU for a GPU Cluster: Heat Load, Flow, Approach TempBusway vs Whip: Choosing Power Distribution for GPU RacksBreaker Coordination & Selective Tripping in GPU Power SystemsB300 Deployment Guide: The Physical-Layer Step Up from B200B200 / HGX B200 Deployment Guide: Power, Thermal, and Rack DemandsArmored vs Standard Fiber in the GPU Data Hall: When Ruggedization PaysWriting an Acceptance Test Plan (ATP) for a GPU Cluster415V vs 480V Distribution in AI Halls: The High-Density Power Decision2N vs N+1 Power Redundancy for AI Clusters: What's Worth Paying ForCable Pathways & Containment for GPU Rooms: Overhead Tray, Ladder, Fiber RunnerNVIDIA B200 vs GB200: HGX vs Rack-Scale, and What Changes to DeployAMD MI300X vs NVIDIA H100: Infrastructure & Deployment DifferencesNVIDIA GB300 NVL72 Explained: Specs, Power, and What It Takes to DeployData Center Migration for AI Infrastructure: A Practical Field GuideNVIDIA H100 vs H200 vs B200: What Changes for DeploymentGoogle TPU vs NVIDIA GPU: What It Means for Your AI Infrastructure BuildData Center Rack-and-Stack Services for GPU Builds: What's IncludedLiquid Cooling vs Air Cooling in the Data Center: When the Crossover HappensCommon GPU Deployment Mistakes — and How to Avoid ThemHow Long Does GPU Cluster Deployment Take?GPU Commissioning & Acceptance: What to Demand Before You Sign OffSite Readiness Before the GPUs Arrive: Power, Cooling, Floor, PathwaysGPU Rack Assembly: What Drives the CostPre-Power Inspection: The Walkdown Before Energizing a GPU HallGB300 NVL72 Deployment: Power, Cooling, and the Cable PlantGB200 vs GB300 NVL72: What Changes for DeploymentHigh-Density Rack PDU Install & Power-On: 415V Three-Phase Done RightGPU Rack Receiving, Staging & Lift Plan: Moving ~1,360 kg Racks Without DamageOverhead Busway Installation for 100kW+ GPU Rack Drops