Task planning-driven adaptive slices

1 . A method of operating a first network node in a communication network, the method comprising:

receiving a plan indicating a plurality of tasks to be performed by at least one second network node operating in the communication network, information associated with each task of the plurality of tasks, and a sequence in which to perform the plurality of tasks, the information comprising at least one of:

a criticality of each task of the plurality of tasks; and

an indication of concurrent actions of each task of the plurality of tasks;

determining a network slice schedule based on the plurality of tasks to be performed by the at least one second network node operating in the communication network and the sequence in which to perform the plurality of tasks; and

providing the network slice schedule to a network slice orchestrator operating in the communication network.

2 . The method of claim 1 , further comprising:

receiving information associated with a task of the plurality of tasks,

wherein determining the network slice schedule comprises determining a slice configuration associated with a portion of the network slice schedule corresponding to the task based on the information.

3 . The method of claim 1 , where receiving the plan comprises receiving an annotated plan that comprises:

indication of the plurality of tasks to be performed by the at least one second network node operating in the communication network;

indication of the sequence in which to perform the plurality of tasks; and

the information associated with each task of the plurality of tasks.

4 . The method of claim 1 , wherein the information comprises the criticality of each task of the plurality of tasks.

5 . The method of claim 1 , wherein determining the network slice schedule comprises:

determining a latency requirement and a bandwidth requirement associated with a first task of the plurality of tasks to be performed by a third network node of the at least one second network node based on a portion of information that is associated with the first task of the plurality of tasks;

determining a network resource allocation associated with performing the first task of the plurality of tasks based on the latency requirement and the bandwidth requirement;

determining that the network slice schedule comprises an existing slice associated with an earlier task of the plurality of tasks, the earlier task being scheduled to occur prior to the first task; and

responsive to determining that the network slice schedule comprises the existing network slice associated with the earlier task of the plurality of tasks, determining whether to reconfigure the existing network slice associated with the earlier task of the plurality of tasks at a start of the first task to provide the network resource allocation to the third network node during performance of the first task based on the information.

6 . The method of claim 5 , wherein determining whether to reconfigure the existing network slice associated with the earlier task of the plurality of tasks comprises:

determining a resource cost of reconfiguring the existing network slice to be a new network slice;

determining a resource savings of using the new network slice during the first task rather than the existing network slice during the first task;

responsive to the resource cost of reconfiguring the existing network slice to be new network slice being greater than the resource savings of using the new network slice, determining to maintain the existing network slice during the first task; and

responsive to the resource savings of using the new network slice being greater than the resource cost of reconfiguring the existing network slice to be new network slice, determining to reconfigure the existing network slice into the new slice.

7 . The method of claim 6 , wherein determining the resource cost of reconfiguring the existing network slice to be the new network slice comprises determining an amount of time required to reconfigure the existing network slice into the new network slice, and

wherein determining the resource savings of using the new network slice during the first task rather than the existing network slice during the first task comprises determining a difference in network resource allocation between using the new network slice during the first task and using the existing network slice during the first task.

8 . The method of claim 1 , wherein determining the network slice schedule comprises:

determining, for a plurality of time intervals, whether to add a new network slice, remove an existing network slice, reconfigure the existing network slice, merge the existing network slice with another network slice, or maintain the existing network slice.

9 . The method of claim 1 , wherein determining the network slice schedule comprises:

generating a data structure of possible network slice actions, times associated with the possible network slice actions, resource cost of performing each of the possible network slice actions, and constraints associated with each task of the plurality of tasks, the possible network slice actions including at least one of: reconfiguring an existing network slice, maintaining the existing network slice, removing the existing network slice, merging existing network slices, and adding a new network slice;

searching the data structure for a minimum cost set of the possible network slice actions to complete the plurality of tasks while meeting the constraints associated with each task of the plurality of tasks; and

determining the network slice schedule based on the minimum cost set of the possible network slice actions, and

wherein the data structure is a tree structure.

10 . The method of claim 1 , wherein determining the network slice schedule comprises:

determining that an existing network slice is scheduled to exist when a new task of the plurality of tasks is scheduled to start;

responsive to determining that the existing network slice is scheduled to already exist when the new task of the plurality of tasks is scheduled to start, determining whether it is more efficient to maintain the network slice or reconfigure the network slice;

responsive to determining that it is more efficient to maintain the network slice, generating the network slice schedule to include the network slice being maintained when the new task of the plurality of tasks is scheduled to start; and

responsive to determining that it is more efficient to reconfigure the network slice, generating the network slice schedule to include reconfiguring the network slice when the new task of the plurality of tasks is scheduled to start.

11 . The method of claim 1 , wherein determining the network slice schedule comprises:

determining that a portion of a first task of the plurality of tasks and a portion of a second task of the plurality of tasks are scheduled to occur at the same time;

responsive to determining that the portion of the first task of the plurality of tasks and the portion of the second task of the plurality of tasks are scheduled to occur at the same time, determining that a single network slice will not meet requirements for completing both the first task and the second task;

responsive to determining that the single network slice will not meet the requirements for completing both the first task and the second task, determining whether it is more efficient to reconfigure the single network slice to provide sufficient resources to meet the requirements for completing both the first task and the second task or more efficient to add a new network slice;

responsive to determining that it is more efficient to reconfigure the single network slice, generating the network slice schedule to include reconfiguring the single network slice to provide sufficient resources to meet the requirements for completing both the first task and the second task when the first task or the second task is scheduled to start; and

responsive to determining that it is more efficient to add the new network slice, generating the network slice schedule to include adding the new network slice when the first task or the second task is scheduled to start.

12 . The method of claim 1 , wherein determining the network slice schedule comprises:

determining that a portion of a first task of the plurality of tasks and a portion of a second task of the plurality of tasks are scheduled to occur at the same time;

responsive to determining that the portion of the first task of the plurality of tasks and the portion of the second task of the plurality of tasks are scheduled to occur at the same time, determining that the first task is scheduled to be completed prior to the second task; and

responsive to determining that the first task is scheduled to be completed prior to the second task, generating the network slice schedule to include merging a first network slice associated with the first task with a second network slice associated with the second task when the first task is be completed, and

wherein being more efficient comprises at least one of:

using less energy;

improving performance; and

using less network resources.

13 . The method of claim 1 , wherein determining the network slice schedule comprises using artificial intelligence (“AI”) planning to autonomously derive a set of initial network slices and network slice reconfigurations to use to configure the communication network during completion of the plurality of tasks.

14 . The method of claim 1 , wherein determining the network slice schedule comprises determining a service level agreement (“SLA”) for each task of the plurality of tasks, and

wherein a SLA of a first task of the plurality of tasks is different than a SLA of a second task of the plurality of tasks.

15 . The method of claim 1 , wherein determining the network slice schedule comprises determining at least one variable network slice associated with one or more tasks of the plurality of tasks, the at least one variable network slice being scheduled to be reconfigured during completion of the plurality of tasks.

16 . The method of claim 1 , wherein the first network node is a network slice scheduler, the second network node is a terminal device, and the communication network is a new radio (“NR”) network.

17 . The method of claim 1 , wherein providing the network slice schedule to the network slice orchestrator operating in the communication network comprises transmitting the network slice schedule as an input to the network slice orchestrator to cause the network slice orchestrator to reconfigure variable network slices of the communication network during completion of the plan, the network slice schedule indicating when and how to reconfigure the variable network slices.

18 . The method of claim 1 , wherein the first network node is the network slice orchestrator and is configured to allocate network resources among the at least one second network node during performance of the plurality of tasks based on the network slice schedule.

19 . A first network node operating in a communication network, the first network node comprising:

processing circuitry; and

memory coupled to the processing circuitry and having instructions stored therein that are executable by the processing circuitry to cause the first network node to perform operations, the operations comprising:

receiving a plan indicating a plurality of tasks to be performed by at least one second network node operating in the communication network, information associated with each task of the plurality of tasks, and a sequence in which to perform the plurality of tasks, the information comprising at least one of:

a criticality of each task of the plurality of tasks; and

an indication of concurrent actions of each task of the plurality of tasks;

determining a network slice schedule based on the plurality of tasks to be performed by the at least one second network node operating in the communication network and the sequence in which to perform the plurality of tasks; and

providing the network slice schedule to a network slice orchestrator operating in the communication network.

20 . A non-transitory computer readable medium having instructions stored therein that are executable by processing circuitry of a first network node operating in a communication network to cause the first network node to perform operations comprising:

receiving a plan indicating a plurality of tasks to be performed by at least one second network node operating in the communication network, information associated with each task of the plurality of tasks, and a sequence in which to perform the plurality of tasks, the information comprising at least one of:

a criticality of each task of the plurality of tasks; and

an indication of concurrent actions of each task of the plurality of tasks;

determining a network slice schedule based on the plurality of tasks to be performed by the at least one second network node operating in the communication network and the sequence in which to perform the plurality of tasks; and

providing the network slice schedule to a network slice orchestrator operating in the communication network.