Skip to main content
ENE-03 · Energy & Utilities

Grid Event Intelligence

Outcome​

Help control-room operators cut through alarm storms by correlating SCADA events with network topology, weather, and field work into a ranked probable-cause narrative, while every switching action stays an operator decision.

Portfolio attributeValue
Primary personaControl-room operator
Primary aggregateGridEvent
Cosmos DB containers1
Grounding dataSCADA alerts, topology, weather, work logs
Development estimateUSD 60-220 monthly dev estimate
Runtime optionsPython FastAPI and C# ASP.NET Core

Productivity hypothesis​

These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.

Impact typeMeasureConservative internal assumptionCustomer measurement
ProductivityEvent brief preparation time8-12% reduction(baseline median brief-preparation minutes - assisted median minutes) / baseline median minutes * 100
Quality or riskCorrected or reissued briefs3-6% reduction(baseline corrected or reissued brief rate - assisted rate) / baseline rate * 100

Important: Conservative internal pilot assumptions only; not public benchmarks, commitments, or expected customer results. Validate against a comparable baseline or matched control cohort with mandatory human review.

Rationale: Incident, topology, weather, and work-log evidence can accelerate situation synthesis without automating grid control.

Pilot guardrail: Operators retain authority for switching, warnings, escalation, and resource commitments.

Customer validation plan​

  1. Baseline the current workflow with representative users and tasks.
  2. Run the accelerator on the same task mix with human review retained.
  3. Measure event brief preparation time and corrected or reissued briefs with the documented formulas.
  4. Replace internal assumptions with customer-observed results before a business case.

Why Azure Cosmos DB​

This AI solution needs an operational data plane, not only a vector index:

  • Hybrid vector and full-text retrieval combines semantic recall with exact identifiers, codes, names, and domain language.
  • Hierarchical partition keys and metadata predicates keep tenant and domain boundaries in the normal query path.
  • Operational JSON, source chunks, workflow and agent state, feedback, and audit records remain together for low-latency reads and governed writes.
  • Change feed reacts to source and operational updates without polling.
  • Autoscale throughput, configurable consistency, and multi-region distribution support variable demand and enterprise availability.

Domain workflow​

Domain workflow

StageActorInput → outputApproval
1. Ingest alarms and protection operationsSCADA integration serviceAlarm stream with device points and quality flags → Time-ordered alarm set for the control areaPolicy controlled
2. Correlate alarms into a single grid eventCorrelation agentAlarms, topology snapshot, and timing windows → GridEvent with the affected network elementPolicy controlled
3. Rank probable causes with contextCause ranking agentWeather, field work logs, and asset history → Ranked hypotheses such as lightning, vegetation, or crew switchingPolicy controlled
4. Propose restoration switchingRestoration agentTopology and load estimates → OperatorActionProposal with predicted impactPolicy controlled
5. Execute operator-approved switchingControl-room operatorProposal with risk notes → Executed switching order and updated event dispositionHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
gridEvents/tenantId, /controlAreaIdGridEvent, ScadaAlarm, NetworkTopologySnapshot, WeatherObservation, FieldWorkLogEntry, OperatorActionProposal/activityNarrativeVectorEmbedding, /riskNotesVectorEmbedding, /activityNarrativeVector, /riskNotesVector

Query contract​

QueryContainerScopePurpose
Event correlation windowgridEventssingle-partitionRead alarms and topology for the control area within the correlation window in one partition query.
Storm attribution checkgridEventssingle-partitionTest whether lightning or wind in the same grid cell explains the event timing.
Planned work overlapgridEventssingle-partitionRule out alarms caused by crews performing planned switching.
High-impact open eventsgridEventssingle-partitionPrioritize unresolved events by customers affected for the operator console.

Python and C# services route each document type to its declared container and hierarchical partition key. ETag-based writes protect mutable aggregates, while append-only records and bounded cross-partition queries preserve scale.

Azure deployment​

Azure deployment

Clone the source repository, authenticate with Azure, and run:

Set-Location accelerators/energy-utilities/grid-event-intelligence
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators