US2022416921A1PendingUtilityA1

Frequency spectrum management device, system, method and computer readable storage medium

Assignee: SONY GROUP CORPPriority: Feb 28, 2018Filed: Jul 11, 2022Published: Dec 29, 2022
Est. expiryFeb 28, 2038(~11.6 yrs left)· nominal 20-yr term from priority
H04B 17/373H04B 17/345G06N 3/084G06N 20/00H04W 52/243H04W 16/14H04W 72/541G06N 3/044H04W 72/51H04B 17/382G06N 3/08H04W 72/048H04W 72/082G06N 3/0445G06N 3/09G06N 3/0499
66
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

A frequency spectrum management device includes a processing circuit configured to acquire, with regard to a position of a primary user sample, a plurality pieces of sample information, each of the plurality pieces of sample information comprising information of a plurality of secondary user samples, and an aggregate interference generated by the plurality of secondary users on the primary user sample; and training a neural network model by taking the information of the plurality of secondary user samples as an input of the neural network model and taking the aggregate interference generated by the plurality of secondary user samples on the primary user sample as an output of the neural network model, so as to determine a parameter set of the neural network model corresponding to the position of the primary user sample.

Claims

exact text as granted — not AI-modified
1 . A spectrum management apparatus, comprising processing circuitry configured to:
 acquire a plurality of pieces of sample information with respect to a position of a sample first electronic device, each of the plurality of pieces of sample information comprising information of a plurality of sample second electronic devices and aggregate interference produced by the plurality of sample second electronic devices to the sample first electronic device; and   train a neural network model by using the information of the plurality of sample second electronic devices as an input to the neural network model and using the aggregate interference produced by the plurality of sample second electronic devices to the sample first electronic device as an output of the neural network model, to determine a parameter set of a neural network model corresponding to the position of the sample first electronic device, wherein   the information of the plurality of sample second electronic devices comprises one or more of: position information of each sample second electronic device of the plurality of sample second electronic devices; information related to a radio propagation environment between each sample second electronic device and the sample first electronic device; power information of each sample second electronic device; and antenna radiation direction information of each sample second electronic device.   
     
     
         2 . The spectrum management apparatus according to  claim 1 , wherein the processing circuitry is further configured to:
 acquire information of a plurality of current second electronic devices with respect to a position of a current first electronic device;   acquire a parameter set of a neural network model corresponding to the position of the current first electronic device; and   predict aggregate interference produced by the plurality of current second electronic devices to the current first electronic device, by using the information of the plurality of current second electronic devices as an input to the neural network model corresponding to the position of the current first electronic device.   
     
     
         3 . The spectrum management apparatus according to  claim 1 , wherein the processing circuitry is further configured to:
 send the parameter set of the neural network model corresponding to the position of the sample first electronic device to another spectrum management apparatus than the spectrum management apparatus, for the another spectrum management apparatus to predict, using the neural network model, aggregate interference produced at the position of the sample first electronic device.   
     
     
         4 . The spectrum management apparatus according to  claim 1 , wherein the information of the plurality of current second electronic devices comprises position information of each current second electronic device of the plurality of current second electronic devices. 
     
     
         5 . The spectrum management apparatus according to  claim 4 , wherein the information of the plurality of current second electronic devices further comprises one or more of: information related to a radio propagation environment between each current second electronic device and the current first electronic device; power information of each current second electronic device; and antenna radiation direction information of each current second electronic device. 
     
     
         6 . The spectrum management apparatus according to  claim 1 , wherein the processing circuitry is further configured to: divide the plurality of current second electronic devices into a plurality of clusters, and
 wherein the information of the plurality of current second electronic devices comprises: position information of a cluster center of each cluster of the plurality of clusters, information related to a radio propagation environment between the cluster center of each cluster and the current first electronic device, and/or a superposition value of power of all current second electronic devices in each cluster.   
     
     
         7 . The spectrum management apparatus according to  claim 1 , wherein the plurality of current second electronic devices are current second electronic devices producing interference to the current first electronic device determined according to a electronic device type and an interference threshold of the current first electronic device. 
     
     
         8 . The spectrum management apparatus according to  claim 1 , wherein the processing circuitry is further configured to:
 determine, according to the position of the current first electronic device, whether or not the parameter set of the neural network model corresponding to the position of the current first electronic device is stored; and   use the position of the current first electronic device as the position of the sample first electronic device to acquire the plurality of pieces of sample information, in a case where the parameter set of the neural network model corresponding to the position of the current first electronic device is not stored.   
     
     
         9 . The spectrum management apparatus according to  claim 1 , wherein the processing circuitry is further configured to:
 perform spectrum management on the plurality of current second electronic devices according to the predicted aggregate interference produced by the plurality of current second electronic devices to the current first electronic device.   
     
     
         10 . The spectrum management apparatus according to  claim 1 , wherein the processing circuitry is further configured to: divide the plurality of sample second electronic devices into a plurality of clusters, and
 wherein the information of the plurality of sample second electronic devices comprises: position information of a cluster center of each cluster of the plurality of clusters, information related to a radio propagation environment between the cluster center of each cluster and the sample first electronic device, and/or a superposition value of power of all sample second electronic devices in each cluster.   
     
     
         11 . The spectrum management apparatus according to  claim 1 , wherein the plurality of sample second electronic devices are sample second electronic devices producing interference to the sample first electronic device determined according to a electronic device type and an interference threshold of the sample first electronic device. 
     
     
         12 . The spectrum management apparatus according to  claim 1 , wherein the processing circuitry is further configured to:
 acquire, from a network side apparatus for managing first electronic devices, aggregate interference produced by the plurality of sample second electronic devices to the sample first electronic device.   
     
     
         13 . The spectrum management apparatus according to  claim 1 , wherein the parameter set of the neural network model corresponding to the position of the sample first electronic device comprises: node numbers of an input layer, an output layer and an implicit layer of the neural network model; and weight coefficient information of the neural network model. 
     
     
         14 . The spectrum management apparatus according to  claim 1 , wherein the spectrum management apparatus comprises a Spectrum Access System SAS or a Coexistence Manager CxM. 
     
     
         15 . A spectrum management system, comprising:
 one or more network side apparatuses for managing second electronic devices, configured to send information of sample second electronic devices to a spectrum management apparatus;   one or more network side apparatuses for managing first electronic devices, configured to send existence information of a sample first electronic device to the spectrum management apparatus; and   the spectrum management apparatus configured to:   acquire a plurality of pieces of sample information with respect to a position of the sample first electronic device, each of the plurality of pieces of sample information comprising information of a plurality of sample second electronic devices and aggregate interference produced by the plurality of sample second electronic devices to the sample first electronic device; and   train a neural network model by using the information of the plurality of sample second electronic devices as an input to the neural network model and using the aggregate interference produced by the plurality of sample second electronic devices to the sample first electronic device as an output of the neural network model, to determine a parameter set of a neural network model corresponding to the position of the sample first electronic device, wherein   the information of the plurality of sample second electronic devices comprises one or more of: position information of each sample second electronic device of the plurality of sample second electronic devices; information related to a radio propagation environment between each sample second electronic device and the sample first electronic device; power information of each sample second electronic device; and antenna radiation direction information of each sample second electronic device.   
     
     
         16 . The spectrum management system according to  claim 15 , wherein:
 the network side apparatus for managing second electronic devices is further configured to send information of a plurality of current second electronic devices to the spectrum management apparatus,   the network side apparatus for managing first electronic devices is further configured to send existence information of a current first electronic device to the spectrum management apparatus, and   the spectrum management apparatus is further configured to: acquire information of the plurality of current second electronic devices with respect to a position of the current first electronic device; acquire a parameter set of a neural network model corresponding to the position of the current first electronic device; and predict aggregate interference produced by the plurality of current second electronic devices to the current first electronic device, by using the information of the plurality of current second electronic devices as an input to the neural network model corresponding to the position of the current first electronic device.   
     
     
         17 . The spectrum management system according to  claim 15 , wherein the spectrum management apparatus is further configured to:
 perform spectrum management on the plurality of current second electronic devices according to the predicted aggregate interference produced by the plurality of current second electronic devices to the current first electronic device.   
     
     
         18 . The spectrum management system according to  claim 15 , wherein the network side apparatus for managing second electronic devices comprises a Citizens Broadband Radio Service Device CBSD, the network side apparatus for managing first electronic devices comprises an Environmental Sensing Capability ESC device or a CBSD with sensing capability, the spectrum management apparatus comprises a Spectrum Access System SAS or a Coexistence Manager CxM. 
     
     
         19 . A radio communication method performed by a spectrum management apparatus, comprising:
 acquiring a plurality of pieces of sample information with respect to a position of a sample first electronic device, each of the plurality of pieces of sample information comprising information of a plurality of sample second electronic devices and aggregate interference produced by the plurality of sample second electronic devices to the sample first electronic device; and   training a neural network model by using the information of the plurality of sample second electronic devices as an input to the neural network model and using the aggregate interference produced by the plurality of sample second electronic devices to the sample first electronic device as an output of the neural network model, to determine a parameter set of a neural network model corresponding to the position of the sample first electronic device, wherein   
       the information of the plurality of sample second electronic devices comprises one or more of: position information of each sample second electronic device of the plurality of sample second electronic devices; information related to a radio propagation environment between each sample second electronic device and the sample first electronic device; power information of each sample second electronic device; and antenna radiation direction information of each sample second electronic device.

Join the waitlist — get patent alerts

Track US2022416921A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.