Spectrum access optimization including for 5g or other next generation user equipment

Abstract

The disclosed technology is directed towards a (5G) spectrum access engine that operates to achieve 5G spectrum optimization. The 5G spectrum access engine provides optimized spectrum access in low-bands, mid-bands, and high-bands based on energy detection algorithms, data analytics, and/or a deep learning architecture. The 5G spectrum access engine can reallocate spectrum to user equipment (UEs), including to allocate Sub-6 frequencies to a user equipment when, based on energy sensing, the user equipment is experiencing poor signal quality with millimeter wave communications.

What is claimed is: 
     
         1 . A method, comprising:
 obtaining, by a spectrum access engine of network equipment comprising a processor, historical spectrum usage data associated with a communications network;   generating, by the spectrum access engine, predicted spectrum access and allocation requests based on the historical spectrum usage data; and   allocating, by the spectrum access engine, channels in the spectrum based on the predicted spectrum access and allocation requests.   
     
     
         2 . The method of  claim 1 , wherein allocating the channels comprises allocating a first group of channels, and further comprising:
 processing, by the spectrum access engine, the historical spectrum usage data to determine a prescriptive remedy to adjust for spectrum access and allocation based on network conditions, and   allocating, by the spectrum access engine, a second group of channels in the spectrum based on the prescriptive remedy.   
     
     
         3 . The method of  claim 1 , further comprising:
 determining, by the spectrum access engine, that a user equipment communicating in a first portion of the spectrum sensed signal strength is experiencing low signal quality according to a low signal quality threshold, and   in response to the determining:
 selecting, by the spectrum access engine, a second, different portion of the spectrum for the user equipment, and 
 instructing, by the spectrum access engine, the user equipment and other network equipment associated with the communications network, other than the network equipment, to communicate via two frequency division duplex channels in the second, different portion of the spectrum. 
   
     
     
         4 . The method of  claim 1 , wherein obtaining the historical spectrum usage data comprises communicating, by the spectrum access engine, with a machine learning engine and a data analytics engine. 
     
     
         5 . The method of  claim 1 , wherein generating the predicted spectrum access and allocation requests is further based on in-field spectrum access request load. 
     
     
         6 . The method of  claim 1 , wherein the allocating the channels comprises, in response to determining a reduction in signal strength in the spectrum below a threshold, allocating the channels in a Sub-6-GHz spectrum based on the predicted spectrum access and allocation requests. 
     
     
         7 . The method of  claim 6 , wherein allocating the channels further comprises, in response to determining that the Sub-6-GHz spectrum is not available, allocating the channels in a fourth generation long term evolution spectrum based on the predicted spectrum access and allocation requests. 
     
     
         8 . Network equipment, comprising:
 a processor; and   a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
 determining, via a spectrum access engine, historical spectrum usage data associated with a communications network; 
 predicting, via the spectrum access engine, a future spectrum loading based on the historical spectrum usage data; and 
 allocating, via the spectrum access engine, channels in the spectrum based on the future spectrum loading. 
   
     
     
         9 . The network equipment of  claim 8 , wherein allocating the channels comprises allocating a first group of channels, and wherein the operations further comprise:
 processing, via the spectrum access engine, the historical spectrum usage data to determine a prescriptive remedy to adjust for spectrum loads based on network conditions, and   allocating, via the spectrum access engine, a second group of channels in the spectrum based on the prescriptive remedy.   
     
     
         10 . The network equipment of  claim 8 , wherein the operations further comprise:
 determining, via the spectrum access engine, that a user equipment communicating in a first portion of the spectrum sensed signal strength is experiencing low signal quality according to a low signal quality criterion, and   in response to the determining:
 selecting, via the spectrum access engine, a second, different portion of the spectrum for the user equipment, and 
 instructing, via the spectrum access engine, the user equipment and other network equipment associated with the communications network to communicate via two frequency division duplex channels in the second, different portion of the spectrum. 
   
     
     
         11 . The network equipment of  claim 8 , wherein determining the historical spectrum usage data comprises communicating, by the spectrum access engine, with a machine learning engine. 
     
     
         12 . The network equipment of  claim 8 , wherein generating the predicted spectrum access and allocation requests is further based on in-field spectrum access request load. 
     
     
         13 . The network equipment of  claim 8 , wherein allocating the channels comprises, in response to determining a reduction in signal strength in the spectrum below a threshold, allocating the channels in a Sub-6-GHz spectrum based on the future spectrum loading. 
     
     
         14 . The network equipment of  claim 13 , wherein allocating the channels further comprises, in response to determining that the Sub-6-GHz spectrum is not available, allocating the channels in a fourth generation long term evolution spectrum based on the future spectrum loading. 
     
     
         15 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor of network equipment, facilitate performance of operations, comprising:
 acquiring, via a spectrum access engine, historical spectrum usage data associated with a communications network;   determining, via the spectrum access engine, predicted spectrum access and allocation requests based on the historical spectrum usage data; and   assigning, via the spectrum access engine, channels in the spectrum based on the predicted spectrum access and allocation requests.   
     
     
         16 . The non-transitory machine-readable medium of  claim 15 , wherein allocating the channels comprises allocating a first group of channels, and wherein the operations further comprise:
 processing, via the spectrum access engine, the historical spectrum usage data to determine a prescriptive remedy to adjust for spectrum access and allocation based on network conditions, and   assigning, via the spectrum access engine, a second group of channels in the spectrum based on the prescriptive remedy.   
     
     
         17 . The non-transitory machine-readable medium of  claim 15 , wherein the operations further comprise:
 determining, via the spectrum access engine, that a user equipment communicating in a first portion of the spectrum sensed signal strength is experiencing low signal quality, and   in response to the determining:
 selecting, via the spectrum access engine, a second, different portion of the spectrum for the user equipment, and 
 instructing, via the spectrum access engine, the user equipment and the communications network to communicate via two frequency division duplex channels in the second, different portion of the spectrum. 
   
     
     
         18 . The non-transitory machine-readable medium of  claim 15 , wherein obtaining the historical spectrum usage data comprises communicating, by the spectrum access engine, with a machine learning engine and a data analytics engine. 
     
     
         19 . The non-transitory machine-readable medium of  claim 15 , wherein generating the predicted spectrum access and allocation requests is further based on in-field spectrum access request load. 
     
     
         20 . The non-transitory machine-readable medium of  claim 15 , wherein assigning the channels comprises, in response to determining a reduction in signal strength in the spectrum below a threshold, assigning the channels in a Sub-6-GHz spectrum based on the predicted spectrum access and allocation requests.