Jim Lee, Cimetrics
Many organizations have IT infrastructure that is both centralized (data centers) and distributed (telecommunications/server rooms). Although energy efficiency is sometimes considered, especially during construction, the real value propositions that matter to the IT departmentare reliability and risk mitigation (ensuring uptime). The reliability of the infrastructure depends on a number of factors including environmental conditions, power quality, and IT equipment performance. Fault detection and diagnostics (FDD) can be applied to the reliability problem, but it requires the fusion of data from disparate sources such as HVAC, power metering, electrical switchgear, uninterruptable power supplies, backup generators, servers, routers and switches. Data is collected via SNMP, Modbus, BACnet, and proprietary protocols. Today's servers can provide management data, including internal temperatures and computational workload metrics, which are also useful inputs to an FDD system. For IT, the benefits of FDD are to predict equipment failures before they occur and to provide insight into the cause of failures that do occur. This requires that FDD analytics operate at the system level as well as at the equipment level.