Channel access method and related apparatus
In the method, an access point AP receives action information separately reported by N stations STAs, where N pieces of action information are used to determine a training result of a first neural network of each STA, and N is a positive integer. The AP determines the training result of the first neural network of each STA based on the N pieces of action information, and sends the training result of the first neural network of each STA to the corresponding STA. The training result of the first neural network of each STA is determined based on the action information reported by the N STAs, instead of only the action information of the STA. This can improve a prediction capability of the first neural network, help improve a capability of each STA to predict channel access behavior of another STA, and improve a system throughput and reduce a communication latency.
1 . A method of channel access by an access point (AP), the method comprising:
receiving, by the AP, action information separately reported by N stations (STAs), wherein N pieces of action information are used to determine a training result of a first neural network of each STA, and N is a positive integer;
determining, by the AP, the training result of the first neural network of each STA based on the N pieces of action information; and
sending, by the AP, the training result of the first neural network of each STA to the corresponding STA, wherein the training result allows the corresponding STA to update the first neural network and access a channel when the corresponding STA has sensed that the channel is idle based on the updated first neural network and current status information of the STA.
2 . The method according to claim 1 , wherein the action information indicates an action of a period of time, and the action is sending or skipping sending.
3 . The method according to claim 1 , wherein the method further comprises:
receiving, by the AP, carrier sense result information or packet transmission result information separately reported by the N STAs; and
the determining, by the AP, the training result of the first neural network of each STA based on the N pieces of action information comprises:
determining, by the AP, the training result of the first neural network of each STA based on the N pieces of action information and the N pieces of carrier sense result information; or
determining, by the AP, the training result of the first neural network of each STA based on the N pieces of action information and the N pieces of packet transmission result information.
4 . The method according to claim 1 , wherein the training result is a neural network parameter or a gradient, and the neural network parameter or gradient is used by the STA to update the first neural network.
5 . The method according to claim 1 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time indication subfield, and a data 1 subfield to a data T subfield, wherein T is a positive integer;
the time indication subfield indicates a moment at which the STA successfully receives first response information last time, and the first response information is response information sent when the AP successfully receives action information sent by the STA;
the data 1 subfield indicates an action performed in a first slot after the STA successfully receives the first response information last time; and
the data T subfield indicates an action performed in a T th slot after the STA successfully receives the first response information last time.
6 . The method according to claim 1 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time indication subfield, an action 1 subfield, a time 1 subfield, an action P subfield, and a time P subfield, wherein P is a positive integer;
the time indication subfield indicates a moment at which the STA successfully receives first response information last time, and the first response information is response information sent when the AP successfully receives action information sent by the STA;
the action 1 subfield indicates a first action after the STA successfully receives the first response information last time, and the time 1 subfield indicates duration of the action 1 or end time of the action 1; and
the action P subfield indicates a P th action between a moment at which the STA successfully receives the first response information last time and a current moment, and the time P subfield indicates duration of the action P or end time of the action P.
7 . The method according to claim 1 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time 1 indication subfield, an action 1 subfield, a time P indication subfield, and an action P subfield, wherein P is a positive integer;
the time 1 indication subfield indicates start time of an action 1, the action 1 subfield indicates a first action after the STA successfully receives first response information last time, and the first response information is response information sent when the AP successfully receives action information sent by the STA; and
the time P indication subfield indicates start time of an action P, and the action P subfield indicates a P th action between a moment at which the STA successfully receives the first response information last time and a current moment.
8 . A method of channel access by a station (STA), the method comprising:
reporting, by the STA, action information to an access point (AP), wherein the action information is used to determine a training result of a first neural network of the STA;
receiving, by the STA, the training result of the first neural network from the AP, wherein the training result of the first neural network is used to update the first neural network, to determine whether the STA accesses a channel;
updating, by the STA, the first neural network based on the training result of the first neural network;
sensing that the channel is idle; and
determining, based on an updated first neural network and current status information of the STA, whether to access the channel.
9 . The method according to claim 8 , wherein the action information indicates an action of a period of time, and the action is sending or skipping sending.
10 . The method according to claim 8 , wherein the method further comprises:
reporting, by the STA, carrier sense result information or packet transmission result information to the AP, wherein the carrier sense result information or the packet transmission result information is used to determine the training result of the first neural network of the STA.
11 . The method according to claim 8 , wherein the training result is a neural network parameter or a gradient; and
the neural network parameter or gradient is used by the STA to update the first neural network.
12 . The method according to claim 8 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time indication subfield, and a data 1 subfield to a data T subfield, wherein T is a positive integer;
the time indication subfield indicates a moment at which the STA successfully receives first response information last time, and the first response information is response information sent when the AP successfully receives action information sent by the STA;
the data 1 subfield indicates an action performed in a first slot after the STA successfully receives the first response information last time; and
the data T subfield indicates an action performed in a T th slot after the STA successfully receives the first response information last time.
13 . The method according to claim 8 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time indication subfield, an action 1 subfield, a time 1 subfield, an action P subfield, and a time P subfield, wherein P is a positive integer;
the time indication subfield indicates a moment at which the STA successfully receives first response information last time, and the first response information is response information sent when the AP successfully receives action information sent by the STA;
the action 1 subfield indicates a first action after the STA successfully receives the first response information last time, and the time 1 subfield indicates duration of the action 1 or end time of the action 1; and
the action P subfield indicates a P th action between a moment at which the STA successfully receives the first response information last time and a current moment, and the time P subfield indicates duration of the action P or end time of the action P.
14 . The method according to claim 8 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time 1 indication subfield, an action 1 subfield, a time P indication subfield, and an action P subfield, wherein P is a positive integer;
the time 1 indication subfield indicates start time of an action 1, the action 1 subfield indicates a first action after the STA successfully receives first response information last time, and the first response information is response information sent when the AP successfully receives action information sent by the STA; and
the time P indication subfield indicates start time of an action P, and the action P subfield indicates a P th action between a moment at which the STA successfully receives the first response information last time and a current moment.
15 . A communication apparatus of an access point (AP), wherein the communication apparatus comprises:
a communication unit, configured to receive action information separately reported by N stations (STAs), wherein N pieces of action information are used to determine a training result of a first neural network of each STA, and N is a positive integer; and
a processing unit, configured to determine the training result of the first neural network of each STA based on the N pieces of action information, wherein
the communication unit is further configured to send the training result of the first neural network of each STA to the corresponding STA, wherein the training result allows the corresponding STA to update the first neural network and access a channel when the corresponding STA has sensed that the channel is idle based on the updated first neural network and current status information of the STA.
16 . The apparatus according to claim 15 , wherein the action information indicates an action of a period of time, and the action is sending or skipping sending.
17 . The apparatus according to claim 15 , wherein
the communication unit is further configured to receive carrier sense result information or packet transmission result information separately reported by the N STAs; and
when determining the training result of the first neural network of each STA based on the N pieces of action information, the processing unit is specifically configured to:
determine the training result of the first neural network of each STA based on the N pieces of action information and the N pieces of carrier sense result information; or
determine the training result of the first neural network of each STA based on the N pieces of action information and the N pieces of packet transmission result information.
18 . The apparatus according to claim 15 , wherein the training result is a neural network parameter or a gradient, and the neural network parameter or gradient is used by the STA to update the first neural network.
19 . The apparatus according to claim 15 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time indication subfield, and a data 1 subfield to a data T subfield, wherein T is a positive integer;
the time indication subfield indicates a moment at which the STA successfully receives first response information last time, and the first response information is response information sent when an AP successfully receives action information sent by the STA;
the data 1 subfield indicates an action performed in a first slot after the STA successfully receives the first response information last time; and
the data T subfield indicates an action performed in a T th slot after the STA successfully receives the first response information last time.
20 . The apparatus according to claim 15 , wherein the action information is carried in an action details field of a first frame reported by the STA;
the action details field comprises a time indication subfield, an action 1 subfield, a time 1 subfield, an action P subfield, and a time P subfield, wherein P is a positive integer;
the time indication subfield indicates a moment at which the STA successfully receives first response information last time, and the first response information is response information sent when an AP successfully receives action information sent by the STA;
the action 1 subfield indicates a first action after the STA successfully receives the first response information last time, and the time 1 subfield indicates duration of the action 1 or end time of the action 1; and
the action P subfield indicates a P th action between a moment at which the STA successfully receives the first response information last time and a current moment, and the time P subfield indicates duration of the action P or end time of the action P.