USER CONTEXT MIGRATION BASED ON COMPUTATION GRAPH IN ARTIFICIAL INTELLIGENCE APPLICATION EXECUTING IN EDGE COMPUTING ENVIRONMENT
In an information processing system with at least a first node and a second node separated from the first node, and each of the first node and the second node configured to execute an application in accordance with at least one entity that moves from a proximity of the first node to a proximity of the second node, a method maintains, as part of a context at the first node, a set of status indicators for a set of computations associated with a computation graph representing at least a portion of the execution of the application at the first node. Further, the method causes the transfer of the context from the first node to the second node to enable the second node to continue execution of the application using the transferred context from the first node.
1 . A method, comprising:
in an information processing system with at least a first node and a second node separated from the first node, and each of the first node and the second node configured to execute an application in accordance with at least one entity that moves from a proximity of the first node to a proximity of the second node;
maintaining, as part of a context at the first node, a set of status indicators for a set of computations associated with a computation graph representing at least a portion of the execution of the application at the first node; and
causing the transfer of the context from the first node to the second node to enable the second node to continue execution of the application using the transferred context from the first node;
wherein the first node comprises at least one processor and at least one memory storing computer program instructions wherein, when the at least one processor executes the computer program instructions, the first node performs the above steps.
2 . The method of claim 1 , wherein the maintaining step further comprises setting each of the set of status indicators for the set of computations to one of a plurality of statuses based on an execution state of each of the computations.
3 . The method of claim 2 , wherein a first status of the plurality of statuses represents that the given computation is completed.
4 . The method of claim 3 , wherein a second status of the plurality of statuses represents that the given computation has started but not yet completed.
5 . The method of claim 3 , wherein a third status of the plurality of statuses represents that the given computation has not yet started.
6 . The method of claim 5 , wherein the context is transferred from the first node to the second node after each computation with the second status is completed.
7 . The method of claim 5 , wherein the context transferred to the second node includes one or more computations with the third status.
8 . The method of claim 5 , wherein the maintaining step further comprises changing one or more computations with the second status to the third status prior to the one or more computations being completed, based on a timing demand associated with the context transfer step.
9 . The method of claim 5 , wherein the transferred context further comprises parameters associated with the set of computations.
10 . The method of claim 9 , wherein the parameters for a given computation comprise at least one of model parameters for the given computation and outputs from other computations.
11 . The method of claim 10 , wherein parameters that are outputs of other computations that serve as inputs to computations with the third status are transferred as part of the context.
12 . The method of claim 9 , wherein, when the application comprises an artificial intelligence model used for inference, no model parameters are necessarily part of the transferred context.
13 . The method of claim 9 , wherein, when the application comprises an artificial intelligence model used for training, model parameters of at least computations with the first status and the third status are part of the transferred context.
14 . The method of claim 1 , wherein the information processing system comprises an edge computing environment and the first node and second node respectively comprise two edge nodes of the edge computing environment, and the at least one entity comprises cellular-based user equipment that moves from a proximity of the first edge node to a proximity of the second edge node.
15 . An apparatus, comprising:
at least one processor and at least one memory storing computer program instructions wherein, when the at least one processor executes the computer program instructions, the apparatus is configured as a first node in an information processing system with at least the first node and a second node separated from the first node, and each of the first node and the second node are configured to execute an application in accordance with at least one entity that moves from a proximity of the first node to a proximity of the second node, wherein the first node performs operations comprising:
maintaining, as part of a context at the first node, a set of status indicators for a set of computations associated with a computation graph representing at least a portion of the execution of the application at the first node; and
causing the transfer of the context from the first node to the second node to enable the second node to continue execution of the application using the transferred context from the first node.
16 . The apparatus of claim 15 , wherein the maintaining operation further comprises setting each of the set of status indicators for the set of computations to one of a plurality of statuses based on an execution state of each of the computations.
17 . The apparatus of claim 16 , wherein a first status of the plurality of statuses represents that the given computation is completed, a second status of the plurality of statuses represents that the given computation has started but not yet completed, and a third status of the plurality of statuses represents that the given computation has not yet started.
18 . A computer program product stored on a non-transitory computer-readable medium and comprising machine executable instructions, the machine executable instructions, when executed, causing a processing device to perform steps of a first node in an information processing system with at least the first node and a second node separated from the first node, and each of the first node and the second node configured to execute an application in accordance with at least one entity that moves from a proximity of the first node to a proximity of the second node, wherein the first node performs steps comprising:
maintaining, as part of a context at the first node, a set of status indicators for a set of computations associated with a computation graph representing at least a portion of the execution of the application at the first node; and
causing the transfer of the context from the first node to the second node to enable the second node to continue execution of the application using the transferred context from the first node.
19 . The computer program product of claim 18 , wherein the maintaining step further comprises setting each of the set of status indicators for the set of computations to one of a plurality of statuses based on an execution state of each of the computations.
20 . The computer program product of claim 19 , wherein a first status of the plurality of statuses represents that the given computation is completed, a second status of the plurality of statuses represents that the given computation has started but not yet completed, and a third status of the plurality of statuses represents that the given computation has not yet started.