Data Center World is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Real-Time Resilience: Continuous and Coordinated Captures for Facility-Wide Power Quality Insights

Karimulla Shaikh  (CTO, Volta Insite, Inc.)

Pass Type: AFCOM Solution Provider, All Access Conference, Industry Conference, Standard Conference - Get your pass now!

Track: Power Sourcing & Sustainability

Session Type: Session

Vault Recording: TBD

Audience Level: All Audiences

Traditional electrical signature analysis in data centers is typically done periodically on individual pieces of equipment, but that may not indicate site-wide power quality issues. ESA applied at a facility level can enable quick troubleshooting of power distribution and transients, but how does one do that?

The solution is to analyze multiple continuous captures that are time-synchronized across the facility with milli-second precision. Mission-critical software can process these multiple captures to rapidly identify an issue with the internal power distribution or with an individual piece of equipment, localizing the risk for immediate action. It can also identify potential issues outside the facility such as the quality of power from a feeder substation.

Identifying and responding to these risks in real-time improves the reliability of the affected equipment. Cloud-based remote analysis and management can provide additional insights for strategic decisions. Ultimately, this helps data centers run their power infrastructure more efficiently, extends the life of the equipment and contributing to sustainable data center operation.

Takeaway

Appreciate the value of continuous coordinated data captures with correlating events across multiple pieces of electrical equipment in a data center

Understand the application of AI-driven models to detect anomalies from these captures that traditional predictive models may not identify reliably