US 12,137,057 B2
Method and system for allocating computation resources for latency sensitive services over a communication network
Dhananjay Lal, Englewood, CO (US)
Assigned to Adeia Guides Inc., San Jose, CA (US)
Filed by Adeia Guides Inc., San Jose, CA (US)
Filed on Jul. 25, 2022, as Appl. No. 17/872,758.
Prior Publication US 2024/0031306 A1, Jan. 25, 2024
Int. Cl. H04L 47/80 (2022.01); H04L 47/78 (2022.01)
CPC H04L 47/805 (2013.01) [H04L 47/781 (2013.01); H04L 47/803 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a network compute orchestrator (NCO), a request for service from a requester device;
determining, by the NCO, that the service requested by the requester device is a first type of service of a plurality of service types;
accessing, by the NCO, a first data structure that stores for each service type of the plurality of service types:
(a) a compute grade required for a respective service type of the plurality service types, and
(b) a maximum acceptable latency for the respective service type of the plurality of service types;
determining, by the NCO, according to the accessing of the first data structure:
(a) a required compute grade requirement for the first type of service, and
(b) a maximum acceptable latency for the first type of service;
accessing, by the NCO, a second data structure that stores for each network device of a network arrangement of network devices:
(a) a number and a type of available compute units, and
(b) an estimated or measured latency of communication from the respective network device of the network arrangement of network devices to the requester device;
selecting, by the NCO, a selected network device of the network arrangement of network devices, based at least in part on determining that the second data structure indicates that:
(a) the selected network device has an available compute unit meeting the required compute grade requirement for the first type of service, and
(b) the selected network device has the estimated or measured latency of communication from the respective network device of the network arrangement of network devices to the requester device that is lower than the maximum acceptable latency for the first type of service; and
causing the selected network device of the network arrangement of network devices to perform the requested service for the requester device.