Application Scenarios

Visual Product Inspections

Traditional approaches in industrial manufacturing relied on naked eyes to detect product defects. This method was inefficient and often failed to detect flaws and even ejected products without defects from the pool of qualified products, causing losses in revenue and brand image. IEF combines cloud modeling and edge decision-making to achieve automatic visual inspection, moving away from traditional manual visual inspections.

Advantages

High efficiency: Edge-side deployment of visual models trained in the cloud enables real-time product prediction, improving detection efficiency and product quality.
Excellent models: Model training in the cloud, data processing at the edge, and incremental model training optimization achieve excellent models.
Unified control: IEF delivers models and monitors node status in a unified manner.

Figure 1 Visual product inspections

CDN Node Management

Unified management of CDN nodes deployed across the country helps users implement automatic application scheduling, auto scaling, and O&M of edge nodes and applications.

Advantages

Auto scaling: IEF automatically adapts the amount of computing resources to fluctuating service load according to custom auto-scaling policies. To scale computing resources at the cluster level, IEF adds or reduces cloud servers. To scale computing resources at the workload level, IEF adds or reduces containers.
Intelligent scheduling: Inter-node and inter-application affinity scheduling is supported.
Dimensional O&M: Service status and edge node status are monitored in real time to ensure stable running of applications.
Local autonomy: Services can run properly even when edge nodes are disconnected from cloud center networks.

Figure 2 CDN node management