From the Utility Management edition of November 5, 2026
Cherryland Electric Cooperative uses InsightAI on AMI data to find voltage anomalies and failing equipment
Cherryland Electric Cooperative · Electric cooperative, AMI and grid analytics · Northwest Lower Michigan (US)
- Publisher
- T&D World
- Original publication
- T&D World, 18 Aug 2026
- Source retrieved
- 2026-11-06
What happened
After fully deploying about 40,000 second-generation Sensus AMI meters across 3,400 miles of line, Cherryland invested in Xylem Data Lake's InsightAI, an AI-driven analytics assistant that helps staff write prompts/SQL to analyse meter data without deep data-science skills. The co-op used it to segment three-phase commercial voltage interval data into ranges, flag readings outside ANSI 5% limits, and find bad or failing transformers and faulty secondary connections. Last-gasp outage reporting also speeds OMS restoration. No quantified SAIDI/SAIFI or dollar savings are published.
Why it matters
A US rural electric co-op turning AMI interval data into AI-assisted voltage anomaly workflows is a concrete metering/operations pattern for other co-ops and municipal utilities with thin analytics benches.
Evidence and measured results
T&D World feature dated 18 Aug 2026 based on metering supervisor interviews. Qualitative equipment finds; no measured reliability or cost outcomes. Older than last run but not previously archived.
Limitations and uncertainty
Trade feature; self-reported finds; no independent evaluation; August publication date.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-11-05; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- AMI data exists but staff cannot manually review system-wide voltage anomalies.
- Stakeholders
- Metering supervisor
- Lineworkers
- OMS operator
- IT/data platform owner
- Discovery questions
- Do meters report interval voltage?
- Is there a data lake or MDM analytics tier?
- What ANSI limits do you enforce?
- Value hypothesis
- AI-assisted querying can surface failing transformers sooner; reliability impact is unmeasured here.
- Potential engagement
- AMI analytics use-case design and threshold pilot.
- Unsupported claims
- SAIDI/SAIFI improvement
- Dollar savings
- InsightAI unique necessity
Pre-sales engineering
Role takeaway
- Fit
- Co-ops/munis with AMI interval voltage and limited data-science staff.
- Architecture and integration
- AMI head-end to data lake; InsightAI or similar over SQL; OMS consuming last-gasp events.
- Prerequisites
- AMI coverage
- Interval voltage
- Query governance
- Constraints
- Small staff
- Vendor lake dependency
- August case age
- Security
- Govern who can query member/interval data; audit exported reports.
- Proof of value
- Confirmed equipment finds from flags
- False flags per 100 meters
- Time from flag to repair
Delivery
Role takeaway
- Work
- Stand up lake/assistant, define voltage bands, pilot on commercial three-phase, feed line crews.
- Dependencies
- AMI vendor
- Data-lake vendor
- Field crews
- Ownership
- Metering supervisor.
- Skills and adoption
- Train staff to review AI-assisted SQL before acting.
- Governance checkpoints
- Approve voltage thresholds
- Quarterly false-flag review
- Acceptance criteria
- Proposed: written ANSI band rules
- Proposed: sample of confirmed finds logged
- Proposed: access-control list for lake queries
- Risks
- False voltage flags
- Unreviewed AI SQL
- Member-data exposure
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
AMI last-gasp into OMS plus a cloud data lake with an AI SQL/reporting assistant over 15-minute voltage intervals.
Governance
Who approves, reviews and stays accountable for outcomes?
Analytics used to set meter alert thresholds; implies need for documented ANSI-based rules and review of AI-generated queries.
Security and privacy
What data, permissions and controls need testing?
Member usage/voltage data in a vendor data lake; article does not detail access controls or retention.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Lets metering staff without data-science backgrounds query system-wide data; lineworkers consume voltage insights in the field.
Procurement
What should contracts, pricing and exit terms secure?
AMI upgrade plus Xylem Data Lake/InsightAI subscription on top of Sensus meters.
Operating model
Which teams own the service once it runs?
Moves from one-meter-at-a-time review to system-wide anomaly hunting and proactive transformer/secondary repairs.
Publication history
- 2026-11-05Utility Management · Issue 087 resources
Stable resource ID: cherryland-insightai-ami-voltage-anomaly-detection-2026