Infrastructure · Software component
Edge Fleet Manager
Software componentInfrastructureInfrastructurearc:EdgeFleetManager
A cloud-hosted management plane that holds the desired application, model and configuration state of every edge AI site and continuously reconciles sites toward it over secure tunnels.
Responsibility. Centrally enforces consistent desired state across a fleet of edge locations.
Also known as: Fleet Command cloud management plane, Hybrid-cloud edge orchestrator
Relationships
is configured by structural
invokes dependency
reads dependency
- GPU Partition Layout abstract Ch4.6
receives telemetry from dynamic
sends data to dynamic
has access controlled by control
Design guidance
- SHOULD manage edge sites as declaratively configured resources grouped by location group, allowing controlled per-site exceptions.
- SHOULD adopt centralized edge fleet management for 50+ geographically distributed sites without local technical staff; avoid for <10 locations, cloud-only workloads or rarely updated static models.
Quantitative guidance
As stated by the sources; verify before use.
- Configuration drift incidents fell from 15-20% of locations within 6 months to <1% (Ch4.6 retail example).
- Outage response 5-15 minutes remotely vs 4-24 hours via technician dispatch (Ch4.6).
Classification
- Patterns
- Declarative desired-state reconciliationCentralized control with edge autonomyHierarchical location groups
- Technologies
- NVIDIA Fleet Command
- Quality attributes
- Maintainability (ISO/IEC 25010)Performance efficiency (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
- Risks mitigated
- Configuration drift across edge locationsVersion inconsistenciesPhysical site visits for remediation
Sources
- Ch4.6: T. Nguyen, "TensorRT-LLM and NVIDIA Fleet Command," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.6. ISBN: 9798244538229.