EXIN CDCE key terms

A four-level scheme describing data centre availability and fault tolerance, from a single path with no redundancy to fully fault-tolerant systems with concurrently maintainable site infrastructure. It is used when specifying resilience and comparing design options.

The property of site infrastructure allowing any planned maintenance activity on a component to be performed without shutting down the IT load. It requires redundant capacity paths and careful isolation procedures.

Provision of extra capacity beyond the minimum needed to carry the load. N+1 adds one spare unit; 2N duplicates the entire capacity path so either side can carry full load alone.

Any component whose failure causes the whole system or a protected load to stop. Identifying and eliminating such components is central to resilient design reviews.

The ability of infrastructure to keep serving the IT load despite a failure of any single component, without interruption. It typically requires fully duplicated paths and automatic transfer.

A system that supplies conditioned power from batteries or another stored source during a mains failure or disturbance, bridging the gap until generators start or load is shut down cleanly.

The ratio of total facility energy consumption to the energy delivered to IT equipment. A value near 1.0 indicates efficient operation; it is used to benchmark and track efficiency improvements.

The total heat that must be removed from the data centre to maintain acceptable conditions, comprising IT heat plus heat from lighting, people, and envelope gains. It drives cooling capacity sizing.

A layout and physical enclosure strategy that separates cold supply air from hot exhaust air, preventing mixing. It improves cooling efficiency and allows higher supply temperatures.

The practice of directing cooled air to where equipment needs it and returning hot air to cooling units, using blanking panels, seals, raised floors, and containment to reduce bypass and recirculation.

The electrical load per rack, usually expressed in kilowatts. It determines cooling method, power distribution design, and whether traditional or high-density cooling approaches are required.

A device that distributes electrical power to racks or equipment, often with metering and switching. Rack PDUs provide outlet-level power delivery and monitoring inside cabinets.

A modular overhead or underfloor power distribution system of enclosed conductors with tap-off points. It allows circuits to be added or relocated without new cable runs.

An automatic device that switches a load between two power sources within milliseconds using semiconductor devices, supporting fault tolerance and source maintenance without load interruption.

An engine-driven generator providing backup power during prolonged mains outages. Its rating, fuel autonomy, start time, and testing regime are key design and operational parameters.

Deliberately applying an artificial electrical load to a generator or UPS to verify capacity and reliability under realistic conditions, often required for commissioning and periodic maintenance.

The structured process of verifying that installed systems meet design intent and operate correctly, including component, system, and integrated systems testing before handover to operations.

A full-scale test demonstrating that all systems work together under simulated failure conditions, such as a utility outage, before a data centre is accepted for live operation.

A structured method for identifying how components or processes can fail, assessing the severity and likelihood of effects, and prioritizing mitigation actions. It is used in design and operational risk reviews.

Scheduled, planned servicing of equipment to reduce failure probability and extend life, based on manufacturer guidance, condition data, or time intervals. It is documented and tracked against a maintenance plan.

Using sensors and trend data, such as temperature, vibration, or current, to decide when maintenance is needed rather than relying on fixed schedules. It supports predictive maintenance decisions.

Software that records assets, work orders, maintenance schedules, and spares, providing an auditable history of maintenance activity and supporting planning and compliance reporting.

A controlled process for planning, reviewing, approving, implementing, and documenting changes to the data centre, reducing the risk of outages caused by uncoordinated modifications.

A written, step-by-step document describing how a specific change or maintenance task will be performed, including prerequisites, verification steps, and rollback actions. It is reviewed before execution.

A documented routine instruction for performing a recurring operational task consistently and safely, such as a generator test or a guided equipment inspection.

A predefined response document for handling abnormal events, such as cooling loss or power failure, specifying actions, roles, and escalation to limit impact on services.

The process of detecting, recording, responding to, and resolving unplanned service disruptions, restoring normal operation quickly and capturing lessons for improvement.

Software that consolidates asset, power, cooling, and capacity data to give visibility across the facility. It supports planning, efficiency analysis, and informed operational decisions.

A repository recording configuration items and their relationships, such as servers, circuits, and dependencies. It underpins change planning and impact analysis.

Planning and monitoring space, power, cooling, and network resources to ensure current and forecast demand can be met without over-provisioning or risking constraints.

A formal agreement defining expected service levels, such as availability, response times, and remedies for shortfalls, between a data centre provider and its customers.

The proportion of time a service is operational and accessible, often expressed as a percentage of agreed service time. It is calculated from uptime and downtime and tied to SLA commitments.

Documented arrangements for keeping critical business functions running during and after disruption, covering people, processes, and technology dependencies beyond the data centre itself.

A documented set of procedures for restoring IT systems and data after a major disruption, including roles, recovery sequences, and alternate site arrangements. It is tested periodically.

The maximum acceptable duration to restore a service after disruption. It drives architecture choices such as redundancy, standby sites, and recovery automation.

The maximum acceptable amount of data loss measured in time, determining how frequently data must be replicated or backed up to meet business expectations.

Layered measures such as perimeter fencing, access control, visitor management, CCTV, and intrusion detection that protect the facility and equipment from unauthorized access and harm.

Restricting entry to authorized individuals using credentials such as badges, biometrics, or PINs, often combined, with logging and zone-based permissions to enforce least privilege.

Continuous sensing of temperature, humidity, water leakage, smoke, and power conditions, with alerting to detect abnormal conditions before they damage equipment or cause outages.

An international standard specifying requirements for an information security management system, including risk assessment, controls, and continual improvement. Certification demonstrates audited compliance.

A series of international standards covering data centre facilities and infrastructures, addressing classification, availability, security, energy efficiency, and related design and operation topics.

Records, logs, test results, and certificates that demonstrate conformity with standards, regulations, and internal policies during internal or external audits.

Laws and rules affecting data centre operation, such as data protection, environmental permitting, fire safety, electrical safety, and employment obligations, which must be identified and met.