Compute-aware resource configurations for a radio access network

Abstract

Aspects of the present disclosure relate to allocating RAN resources among RAN slices using a machine learning model. In examples, the machine learning model may determine an optimal RAN resource configuration based on compute power needs. As a result, RAN resource allocation generation and compute power requirements may improve, even in instances with changing or unknown network conditions. In examples, a prediction engine may receive communication parameters and/or requirements associated with service-level agreements (SLAs) for applications executing at least partially at a device in communication with the RAN. The RAN may generate one or more RAN resource configuration for implementation among RAN slices. Upon a change in network conditions or SLA requirements, an optimal RAN configuration may be determined in terms of required compute power.

What is claimed is: 
     
         1 . A system comprising:
 at least one processor; and   memory storing instructions that, when executed by the at least one processor, causes the system to perform a set of operations, the set of operations comprising:
 receiving communication requirements from a plurality of service level agreements (SLAs); 
 retrieving a model that predicts an amount of compute resources needed to implement resource allocation configurations of a radio access network (RAN), the model being trained on training data mapping changes in RAN resource configurations to compute resources needed at one or more stages in a physical layer software processing pipeline; 
 generating, using the retrieved model, a resource allocation configuration for a set of resources of the RAN based on the received communication requirements; and 
 implementing the resource allocation by forming a first RAN slice comprising a first set of logical resources and a second RAN slice comprising a second set of logical resources. 
   
     
     
         2 . The system of  claim 1 , wherein the set of resources of the RAN comprises a local scheduler of the first RAN slice to allocate the first set of logical resources among a set of devices associated with the first RAN slice. 
     
     
         3 . The system of  claim 1 , wherein the generated resource allocation configuration for the set of resources of the RAN based on the received communication requirements is a resource allocation configuration having a lowest amount of compute required. 
     
     
         4 . The system of  claim 1 , wherein generating the resource allocation configuration for the set of resources of a RAN includes:
 receiving communication requirements for a plurality of different SLAs;   generating, using the retrieved model, a second resource allocation configuration for the set of resources of the RAN based on the received communication requirements for the plurality of different SLAs; and   implementing the second resource allocation by forming a different first RAN slice comprising a third set of logical resources and a different second RAN slice comprising a fourth set of logical resources.   
     
     
         5 . The system of  claim 4 , wherein the resource allocation is for a first frame of the RAN and the second resource allocation is for a frame after the first frame. 
     
     
         6 . The system of  claim 5 , wherein the first RAN slice is a low-latency network and the second RAN slice is a mobile broadband network. 
     
     
         7 . The system of  claim 1 , wherein first resource allocation comprises an indication of at least one of:
 a resource block allocation;   a time slot allocation;   a numerology allocation; or   
       a multiple-input and multiple-output (MIMO) layer allocation. 
     
     
         8 . A method for allocating resources of a radio access network (RAN), the method comprising:
 receiving communication requirements from a plurality of service level agreements (SLAs);   retrieving a model that predicts an amount of compute resources needed to implement resource allocation configurations of a radio access network (RAN), the model being trained on training data mapping changes in RAN resource configurations to compute resources needed at one or more stages in a physical layer software processing pipeline;   generating, using the retrieved model, a resource allocation configuration for a set of resources of the RAN based on the received communication requirements; and   implementing the resource allocation by forming a first RAN slice comprising a first set of logical resources and a second RAN slice comprising a second set of logical resources.   
     
     
         9 . The method of  claim 8 , wherein the set of resources of the RAN comprises a local scheduler of the first RAN slice to allocate the first set of logical resources among a set of devices associated with the first RAN slice. 
     
     
         10 . The method of  claim 8 , wherein the generated resource allocation configuration for the set of resources of the RAN based on the received communication requirements is a resource allocation configuration having a lowest amount of compute required. 
     
     
         11 . The method of  claim 8 , wherein generating the resource allocation configuration for the set of resources of a RAN includes:
 receiving communication requirements for a plurality of different SLAs;   generating, using the retrieved model, a second resource allocation configuration for the set of resources of the RAN based on the received communication requirements for the plurality of different SLAs; and   implementing the second resource allocation by forming a different first RAN slice comprising a third set of logical resources and a different second RAN slice comprising a fourth set of logical resources.   
     
     
         12 . The method of  claim 11 , wherein the resource allocation is for a first frame of the RAN and the second resource allocation is for a frame after the first frame. 
     
     
         13 . The method of  claim 11 , wherein the second resource allocation comprises an indication of at least one of:
 a resource block allocation;   a time slot allocation;   a numerology allocation; or   a multiple-input and multiple-output (MIMO) layer allocation.   
     
     
         14 . The method of  claim 8 , further comprising:
 receiving an indication that network conditions of the RAN have changed; and   generating a second resource allocation configuration for the set of resources of the RAN based on the received communication requirements.   
     
     
         15 . A method for allocating resources of a radio access network (RAN) to form a first RAN slice and a second RAN slice, the method comprising:
 receiving communication requirements from a plurality of service level agreements (SLAs);   retrieving a model that predicts an amount of compute resources needed to implement resource allocation configurations of a radio access network (RAN), the model being based on data mapping changes in RAN resource configurations to compute resources needed at one or more stages in a physical layer software processing pipeline;   receiving channel state information associated with a device in communication with the RAN;   generating, using the retrieved model, a resource allocation configuration for a set of resources of the RAN based on the received communication requirements and the channel state information; and   implementing the resource allocation, thereby forming the first RAN slice comprising a first set of logical resources and the second RAN slice comprising a second set of logical resources.   
     
     
         16 . The method of  claim 15 , wherein the generated resource allocation configuration for the set of resources of the RAN based on the received communication requirements and the channel state information is a resource allocation configuration having a lowest amount of compute required. 
     
     
         17 . The method  claim 15 , wherein generating the resource allocation configuration for the set of resources of a RAN includes:
 receiving communication requirements for a plurality of different SLAs;   generating, using the model, a second resource allocation configuration for the set of resources of the RAN based on the received communication requirements for the plurality of different SLAs; and   implementing the second resource allocation, thereby forming a different first RAN slice comprising a third set of logical resources and a different second RAN slice comprising a fourth set of logical resources.   
     
     
         18 . The method of  claim 17 , wherein the resource allocation comprises an indication of at least one of:
 a resource block allocation;   a time slot allocation;   a numerology allocation; or   a multiple-input and multiple-output (MIMO) layer allocation.   
     
     
         19 . The method of  claim 17 , wherein the resource allocation is for a first frame of the RAN and the second resource allocation is for a frame after the first frame. 
     
     
         20 . The method of  claim 15 , wherein the first RAN slice is a low-latency network and the second RAN slice is a mobile broadband network.