Abstract: Aspects of the present invention monitor at least one microservice within a container module for a failure; collect logged data in response to the at least one microservice having the failure; check the logged data to determine that an existing tree is not built for the logged data; perform telemetry tracing on the at least one microservice in response to the existing tree not being built for the logged data; collect logged tracing data based on performing the telemetry tracing on the at least one microservice; visualize an actual flow of the collected logged tracing data; and fix the at least one microservice based on the visualized actual flow the collected logged tracing data.

Abstract: Deploying energy-rated deep neural network models on energy-scored edge devices is provided. An overall energy efficiency rating is assigned to a deep neural network model based on utilizing software optimization and hardware accelerators during training of the deep neural network model. Energy scores are assigned to respective edge devices in an edge inference computing environment based on properties of each respective edge device. Particular edge devices are selected that have a corresponding energy score within a defined edge device energy score range for the overall energy efficiency rating that corresponds to the deep neural network model. The deep neural network model is deployed to the particular edge devices that have a corresponding energy score within the defined edge device energy score range for the overall energy efficiency rating that corresponds to the deep neural network model.

Abstract: A processor may identify that there is a disruption in an environment. The processor may converge a group of two or more devices. The group of two or more devices may be converged in a geofenced area. The processor may limit the usage of the group of the two or more devices to the usage of one of the two or more devices at a time.

Abstract: Deploying energy-rated deep neural network models on energy-scored edge devices is provided. An overall energy efficiency rating is assigned to a deep neural network model based on utilizing software optimization and hardware accelerators during training of the deep neural network model. Energy scores are assigned to respective edge devices in an edge inference computing environment based on properties of each respective edge device. Particular edge devices are selected that have a corresponding energy score within a defined edge device energy score range for the overall energy efficiency rating that corresponds to the deep neural network model. The deep neural network model is deployed to the particular edge devices that have a corresponding energy score within the defined edge device energy score range for the overall energy efficiency rating that corresponds to the deep neural network model.