System and methods for distributed GPU using Multi-access Edge Compute services

A network device comprising:

• a processor configured to:
• receive, from an application, a service request for multi-access edge compute (MEC)-based virtual graphic processing unit (vGPU) services;
• receive real-time utilization data from multiple MEC clusters in different MEC network locations;
• combine the real-time utilization data from the different MEC clusters;
• forward the combined real-time utilization data in separate redundant data pipelines;
• generate, based on processing of the combined real-time utilization data, a utilization view of the multiple MEC clusters in the different MEC network locations;
• select, based on the utilization view, one of the different MEC network locations to provide the MEC-based vGPU services;
• and
• instruct a MEC cluster of the multiple MEC clusters in the one of the different MEC network locations to perform provisioning for the MEC-based vGPU services.

A non-transitory computer-readable storage medium storing instructions executable by a processor of a device, which when executed cause the device to:

• receive, from an application, a service request for multi-access edge compute (MEC)-based virtual graphic processing unit (vGPU) services;
• receive real-time utilization data from multiple MEC clusters in different MEC network locations;
• combine the real-time utilization data from the different MEC clusters;
• forward the combined real-time utilization data in separate redundant data pipelines;
• generate, based on processing of the combined real-time utilization data, a utilization view of the multiple MEC clusters in the different MEC network locations;
• select, based on the utilization view, one of the different MEC network locations to provide the MEC-based vGPU services;
• and
• instruct a MEC cluster of the multiple MEC clusters in the one of the different MEC network locations to perform provisioning for the MEC-based vGPU services.