CN117693035A

CN117693035A - Channel aggregation method and device

Info

Publication number: CN117693035A
Application number: CN202211066591.3A
Authority: CN
Inventors: 舒同欣; 刘鹏; 郭子阳; 罗嘉俊; 杨讯; 颜敏
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2022-08-31
Filing date: 2022-08-31
Publication date: 2024-03-12
Also published as: WO2024046286A1

Abstract

The application relates to the technical field of communication, and discloses a channel aggregation method and a device for making optimal channel aggregation decisions so as to solve the problems of small channel aggregation throughput and large time delay. The method comprises the following steps: the method comprises the steps that a first terminal device receives a load report, wherein the load report comprises load information of each channel in M channels of a network device in a t-th time period, and the M channels comprise 1 main channel and M-1 secondary channels corresponding to the first terminal device; inputting channel environment information of a t-th time period into a channel aggregation model for processing to obtain a t-th channel aggregation indicated value, wherein the channel environment information of the t-th time period comprises load information of each secondary channel in a main channel and M-1 secondary channels in the t-th time period, and the t-th channel aggregation indicated value is used for indicating N secondary channels in the M-1 secondary channels to aggregate with the main channel; and transmitting the data packet through the channel aggregated by the main channel and the N secondary channels in the t+1th time period.

Description

Channel aggregation method and device

Technical Field

The present disclosure relates to the field of communications technologies, and in particular, to a channel aggregation method and apparatus.

Background

To cope with the problems of shortage of spectrum resources and increase in traffic flow, channel aggregation technology is introduced in communication standards established by the institute of electrical and electronics engineers (institute of electrical and electronics engineers, IEEE). Specific channel aggregation techniques may aggregate a primary channel with secondary channels adjacent to the primary channel based on the primary channel to support a greater channel bandwidth, thereby increasing the data transmission rate.

Currently, channel aggregation methods are mainly classified into two types of channel aggregation methods, i.e., static (static) channel aggregation and dynamic (dynamic) channel aggregation. The main idea of static channel aggregation is: on the premise that the main channel is idle, all secondary channels need to wait for the idle channel to be aggregated. The main idea of dynamic channel aggregation is: when the main channel is idle, if the secondary channel is idle, the main channel and the idle secondary channel can be aggregated.

However, when the channel aggregation method is adopted, when a plurality of terminal devices compete for channel resources, the problems of low channel aggregation throughput and long time delay caused by high collision rate of data packets sent by each terminal device and multiple times of entering a reverse window by the terminal devices to wait for sending the data packets exist.

Disclosure of Invention

The embodiment of the application provides a channel aggregation method and device, which aim to make an optimal channel aggregation decision and solve the problems of small channel aggregation throughput and large time delay.

In a first aspect, an embodiment of the present application provides a channel aggregation method, where the method may be performed by a first terminal device, or may be performed by a component (for example, a processor, a chip, or a chip system) of the first terminal device, or may be implemented by a logic module or software that can implement all or part of the functions of the first terminal device. The method is described below by taking the first terminal device as an example, where the method includes: the method comprises the steps that a first terminal device receives a load report from a network device, wherein the load report comprises load information of each channel in M channels of the network device in a t-th time period, the M channels comprise 1 main channel and M-1 secondary channels corresponding to the first terminal device, M is an integer greater than or equal to 2, and t is an integer greater than or equal to 2; the method comprises the steps that channel environment information of a t-th time period is input into a channel aggregation model by a first terminal device to be processed to obtain a t-th channel aggregation indicated value, the channel environment information of the t-th time period comprises load information of each secondary channel in the t-th time period in a main channel and M-1 secondary channels, and channel state monitoring information obtained by monitoring channel states of the main channel and the M-1 secondary channels in the t-th time period by the first terminal device, and the t-th channel aggregation indicated value is used for indicating N secondary channels in the M-1 secondary channels to aggregate with the main channel, wherein N is an integer which is greater than or equal to 0 and smaller than or equal to M-1; the first terminal device performs channel aggregation on the main channel and the N secondary channels, that is, the terminal device may send a data packet through the channel aggregated by the main channel and the N secondary channels in the t+1th time period, where the t+1th time period is a time period after the t time period.

Optionally, the load report may further include an expiration of the t-th period.

By adopting the method, the first terminal equipment can acquire accurate load information of each channel from the network equipment side, and combine channel state monitoring information (such as information of data packets sent by the first terminal equipment in each channel) obtained by channel state monitoring, based on real-time load and channel state of the channel, the optimal channel aggregation decision is made by utilizing artificial intelligence (artificial intelligence, AI), namely the prediction capability of a channel aggregation model, so that collision probability of the aggregated channel sending data of the first terminal equipment and the data packets sent by other terminal equipment is reduced, transmission performance of the aggregated channel is improved, and the problems of small channel aggregation throughput and long time delay are solved.

In one possible design, the channel state monitoring information obtained by the first terminal device performing channel state monitoring on the primary channel and the M-1 secondary channels in the t-th time period may, but is not limited to, include one or more of the following: the first terminal equipment monitors the busy state of each sub-channel in the main channel and M-1 sub-channels in the t time period in each time unit; the data packet sending state of each time unit of the first terminal equipment on each secondary channel in the primary channel and M-1 secondary channels, which is monitored by the first terminal equipment in the t-th time period; the first terminal device monitors the number of time units of which the data packet sending state and the busy/idle state of the channel are kept unchanged and continuous on each secondary channel in the primary channel and the M-1 secondary channels in the t-th time period.

In the design, the first terminal equipment can monitor the channel state of each channel from the angles of busy state of each channel, self data packet sending condition of each channel and the like, is favorable for making an optimal channel aggregation decision through a channel aggregation model based on the real-time load and the channel state of the channel, and therefore improves the transmission performance of the aggregated channel.

In one possible design, the method further comprises: the first terminal equipment determines a reward value for obtaining a t-1 channel aggregation indicated value based on a channel aggregation model according to the load information of each secondary channel in the t-1 time period in the main channel and N 'secondary channels, wherein the t-1 channel aggregation indicated value is used for indicating the aggregation of the N' secondary channels in the M-1 secondary channels and the main channel; the first terminal equipment determines a first state action value of a channel aggregation mode corresponding to the t-1 channel aggregation indicated value based on the channel environment information of the t-1 time period according to the channel environment information of the t-1 time period, the t-1 channel aggregation indicated value and the set state action value function; the first terminal equipment receives the channel environment information of the t-1 time period, and 2 corresponding to the primary channel and M-1 secondary channels ^M-1 -1 candidate channel aggregate indicator value and set state action value function, determining a second state action value, 2 ^M-1 -1 candidate channel aggregate indicator value corresponds to 2 of primary channel and M-1 secondary channels ^M-1 -1 candidate channel aggregation, the second state action value is 2 based on the channel environment information of the t-1 time period ^M-1 -1 candidate channel aggregationThe maximum state action value in the state action values of the candidate channel aggregation modes corresponding to the indicated values; the first terminal equipment determines the loss of the channel aggregation model according to the first state action value, the second state action value and the rewarding value of the t-1 channel aggregation indicated value; the first terminal equipment carries out training update on the channel aggregation model according to the loss of the channel aggregation model; wherein N' is the same as or different from N, and the t-1 th time period is a time period before the t-th time period.

In the above design, after the channel aggregation model makes a channel aggregation decision (i.e. outputs a channel aggregation indication value), the first terminal device may test whether a data packet sent on an aggregated channel collides with a data packet sent by another terminal device, and according to the channel aggregation decision and the condition of the data packet sent on the aggregated channel, different rewards are given to the channel aggregation decision made by the channel aggregation model in combination with the load condition of each channel, so as to guide the channel aggregation model to learn according to the load condition on each channel, so as to output an optimal channel aggregation decision through the channel aggregation model.

In one possible design, the method further comprises: the method comprises the steps that a first terminal device determines a reward value of a t-1 th channel aggregation indicated value based on a channel aggregation model according to load information of each secondary channel in a t-1 th time period in a main channel and N ' secondary channels, wherein the t-1 th channel aggregation indicated value is used for indicating N ' secondary channels in the M-1 th secondary channels to aggregate with the main channel, N ' is the same as N or different from N, and the t-1 th time period is a time period before the t-1 th time period;

the first terminal device inputs channel environment information of a t-th time period into a channel aggregation model for processing to obtain a t-th channel aggregation indicated value, and the method comprises the following steps: the first terminal equipment inputs the channel environment information of the t time period and the rewarding value of the t-1 channel aggregation indicated value into a channel aggregation model for processing to obtain the t channel aggregation indicated value.

By adopting the method, different rewards can be given to the channel aggregation decision (namely the output channel aggregation indicated value) made by the channel aggregation model by setting the rewarding strategy, and the given rewards value is also used as an influence factor for the channel aggregation model to make the channel aggregation decision of the user demand next time.

Optionally, the first terminal device determines, according to load information of each secondary channel in the main channel and the N' secondary channels in the t-1 th time period, a reward value for obtaining the t-1 th channel aggregation indication value based on the channel aggregation model, where the reward value may include the following cases, where each case may be combined or may be used independently, and the application does not limit a combined case of each case:

when the channel transmission data packet aggregated by the primary channel and N 'secondary channels of the first terminal device is not collided with the transmission data packet of other terminal devices and N' is not zero, the first terminal device performs the following stepsDetermining a reward value of a t-1 channel aggregation indicated value based on the channel aggregation model;

when the first terminal equipment does not collide with the other terminal equipment transmitting data packets in the channel transmitting data packets aggregated by the main channel and the N 'secondary channels and N' is zero, the first terminal equipment performs the following stepsDetermining a reward value of a t-1 channel aggregation indicated value based on the channel aggregation model;

when the first terminal device collides with the other terminal device transmitting data packet in the channel transmitting data packet aggregated by the main channel and the N 'secondary channels and N' is not zero, the first terminal device performs the following steps Determining a reward value of a t-1 channel aggregation indicated value based on the channel aggregation model;

when the first terminal device collides with the other terminal device transmitting data packet in the channel transmitting data packet aggregated by the main channel and the N 'secondary channels and N' is zero, the first terminal device performs the following stepsDetermining a reward value of a t-1 channel aggregation indicated value based on the channel aggregation model;

in each of the above cases, R _t Represents a reward value for deriving a t-1 channel aggregate indicator value based on a channel aggregate model, K represents a kth secondary channel of the N 'secondary channels, k=1, 2, …, N',load information indicating the kth secondary channel in the t-1 time period, +.>Load information indicating the primary channel in the t-1 th time period.

In a second aspect, an embodiment of the present application provides a communications device, where the communications device has a function for implementing the method in the first aspect, where the function may be implemented by hardware, or may be implemented by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above, including for example an interface unit and a processing unit.

In one possible design, the device may be a chip or an integrated circuit.

In one possible design, the apparatus includes a memory and a processor, the memory storing instructions for execution by the processor, the apparatus being capable of performing the method of the first aspect described above when the instructions are executed by the processor.

In one possible design, the apparatus may be a first terminal device.

In a third aspect, embodiments of the present application provide a communication device including an interface circuit and a processor, the processor and the interface circuit being coupled to each other. The processor is configured to implement the method of the first aspect described above by logic circuitry or executing instructions. The interface circuit is used for receiving signals from other communication devices except the communication device and transmitting the signals to the processor or sending the signals from the processor to the other communication devices except the communication device. It will be appreciated that the interface circuit may be a transceiver or input output interface.

Optionally, the communication device may further comprise a memory for storing instructions executed by the processor or for storing input data required by the processor to execute the instructions or for storing data generated after the processor executes the instructions. The memory may be a physically separate unit or may be coupled to the processor, or the processor may include the memory.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium, in which a computer program or instructions are stored, which when executed, can implement the method of the first aspect.

In a fifth aspect, embodiments of the present application also provide a computer program product comprising a computer program or instructions which, when executed, implement the method of the first aspect described above.

In a sixth aspect, embodiments of the present application further provide a chip, where the chip is coupled to the memory, and is configured to read and execute a program or an instruction stored in the memory, to implement the method of the first aspect.

The technical effects achieved by the second aspect to the sixth aspect are referred to the technical effects achieved by the first aspect, and the detailed description is not repeated here.

Drawings

Fig. 1 is a schematic diagram of a communication system architecture according to an embodiment of the present application;

fig. 2 is a schematic diagram of a fully-connected neural network according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a neuron according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of an adjacent multi-channel aggregation according to an embodiment of the present application;

fig. 5 is a schematic diagram of preamble puncturing transmission according to an embodiment of the present application;

fig. 6 is a schematic diagram of a channel aggregation method according to an embodiment of the present application;

fig. 7 is one of schematic diagrams of indication information of load information of a channel according to an embodiment of the present application;

fig. 8 is a second schematic diagram of indication information of load information of a channel according to an embodiment of the present disclosure;

fig. 9A is a schematic diagram of a structure of a channel aggregation model according to an embodiment of the present application;

FIG. 9B is a schematic diagram of a reinforcement learning process according to an embodiment of the present application;

fig. 10 is a schematic diagram of a communication device according to an embodiment of the present application;

FIG. 11 is a second schematic diagram of a communication device according to an embodiment of the present disclosure;

fig. 12 is a schematic view of a device structure according to an embodiment of the present application.

Detailed Description

The technical solution of the embodiment of the application can be applied to various communication systems, for example: the communication systems such as the 5G system, the LTE system, the long term evolution advanced (LTE-a) system, etc. may also be extended to related cellular systems such as wireless fidelity (wireless fidelity, wiFi), worldwide interoperability for microwave access (worldwide interoperability for microwave access, wimax), and 3GPP, etc., and future communication systems such as 6G systems, etc. Specifically, the architecture of the communication system applied in the embodiments of the present application may be shown in fig. 1, and includes a network device and a plurality of terminal devices, where three terminal devices are taken as an example in fig. 1. The terminal device 1-the terminal device 3 may send data (or data packets) to the network device separately or simultaneously, and it should be noted that the number of terminal devices and network devices in the communication system shown in fig. 1 is not limited in the embodiment of the present application.

The terminal device may also be referred to as a terminal (terminal), a User Equipment (UE), a Mobile Station (MS), a mobile terminal, or the like. Terminal devices may be widely used in various scenarios, such as device-to-device (D2D) communication, vehicle-to-everything (vehicle to everything, V2X) communication, machine-type communication, MTC), internet of things (internet of things, ioT), virtual reality, augmented reality, industrial control, autopilot, telemedicine, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal device may be a cell phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, unmanned aerial vehicle, helicopter, airplane, ship, robot, mechanical arm, smart home device, vehicle-mounted terminal, ioT terminal, wearable device, station (STA) in WiFi system, etc. The embodiment of the application does not limit the specific technology and the specific equipment form adopted by the terminal equipment.

The network device may also be referred to as AN Access Network (AN) device, or a radio access network (radio access network, RAN) device. May be a base station (base station), an evolved NodeB (eNodeB), a transceiver point (transmitter and receiver point, TRP), an integrated access and backhaul (integrated access and backhauling, IAB) node, a next generation base station (gNB) in a fifth generation (5th generation,5G) mobile communication system, a base station in a sixth generation (6th generation,6G) mobile communication system, a base station in other future mobile communication systems, a home base station (e.g., home evolved nodeB, or home node B, HNB), an Access Point (AP) in a WiFi system, a wireless relay node, a wireless backhaul node, and so on.

Before describing embodiments of the present application, some of the terms in the present application are explained first to facilitate understanding by those skilled in the art.

1) Neural Networks (NNs) are a machine learning technique that simulates a human brain neural network in an effort to be able to implement artificial-like intelligence. The neural network comprises at least 3 layers, an input layer, an intermediate layer (also called hidden layer) and an output layer. A deeper neural network may contain more hidden layers between the input layer and the output layer. Taking the simplest neural network as an example, the internal structure and implementation will be described, referring to the schematic diagram of the fully-connected neural network including 3 layers shown in fig. 2. As shown in fig. 2, the neural network includes 3 layers, which are an input layer, a hidden layer, and an output layer, respectively, wherein each circle in fig. 2 represents one neuron, the input layer has 3 neurons, the hidden layer has 4 neurons, the output layer has 2 neurons, and each layer of neurons is fully connected with the next layer of neurons. Each link between neurons corresponds to a weight that can be updated by training. Each neuron of the hidden layer and the output layer may also correspond to a bias, which may also be updated by training. Updating the neural network refers to updating these weights and biases. The structure of the neural network, namely the number of neurons contained in each layer of the neural network and the connection relation among the neurons, and the parameters of the neural network, namely the weight corresponding to each connecting line among the neurons and the bias corresponding to each neuron are known, so that all the information of the neural network is known.

As can be seen from fig. 2, there may be multiple input connections per neuron, with each neuron calculating an output based on the inputs. Referring to fig. 3, fig. 3 is a schematic diagram of a neuron calculating an output based on an input. As shown in fig. 3, one neuron includes 3 inputs, 1 output, and 2 calculation functions, and the calculation formula (1-1) of the output can be expressed as:

output = activation function (input 1 x weight 1+ input 2 x weight 2+ input 3 x weight 3+ bias) (1-1);

where "×" denotes a mathematical operation "multiply" or "multiply", where the activation function may employ an S-type function (sigmoid function), hyperbolic function, rectifying function (rectification function, reLu), etc.

Each neuron may have multiple output connections, with the output of one neuron being the input to the next neuron. It should be understood that the input layer has only output links, each neuron of the input layer is a value of the input neural network, and the output value of each neuron is directly input as all output links. The output layer has only input connection, and the output is calculated by adopting the calculation mode of the formula (1-1). Alternatively, the output layer may have no calculation of the activation function, that is, the aforementioned equation (1-1) may be transformed into: output = input 1 x weight 1+ input 2 x weight 2+ input 3 x weight 3+ bias.

For example, a k-layer neural network may be represented as:

y＝fk(fk-1(…(f1(w1*x+b1)))(1-2)；

where x represents the input of the neural network, y represents the output of the neural network, wi represents the weight of the i-th layer neural network, bi represents the bias of the i-th layer neural network, fi represents the activation function of the i-th layer neural network, i=1, 2, …, k.

2) Channel aggregation, in the IEEE 802.11ac standard, a channel aggregation technology is introduced for the first time, allowing a plurality of adjacent 20MHz sub-channels (secondary channel) to be aggregated into a channel with a bandwidth of 40MHz, 80MHz or 160MHz for transmission based on one 20 megahertz (MHz) main channel, thereby improving transmission efficiency. FIG. 4 is a schematic diagram of adjacent multi-channel aggregation, and referring to FIG. 4, it can be seen that a 20MHz primary channel and a 20MHz secondary channel may be aggregated into a 40MHz bandwidth channel; the 40MHz primary channel and the 40MHz secondary channel may be aggregated into a channel with a bandwidth of 80 MHz; the primary channel of 8MHz and the secondary channel of 80MHz may be aggregated into a channel with a bandwidth of 160 MHz.

In the next generation standard of the 802.11ac standard, i.e., the 802.11ax standard, channel aggregation is allowed to be performed between non-adjacent 20MHz channels based on the techniques such as preamble puncturing (preamble puncturing), so that more flexibility is provided for channel aggregation and more possibility is provided for further improving the transmission throughput. As shown in fig. 5, fig. 5 is a schematic diagram of preamble puncturing transmission. Here, TX means transmission (transport), CH means channel (channel), each channel (CH 1, CH2, CH3, CH 4) has a bandwidth of 20MHz, and transmission bandwidths of frame 1 (frame 1), frame 2 (frame 2), and frame 3 (frame 3) are all 80MHz, and when frame 1 is transmitted, the secondary 20MHz channel (S20) is busy (busy), so S20 is punctured, and the actual bandwidth of frame 1 is 60MHz. Similarly, the actual bandwidth of frame 2 is 60MHz and the actual bandwidth of frame 3 is 40MHz.

3) The current channel aggregation method is mainly divided into two types of channel aggregation methods, namely static channel aggregation and dynamic channel aggregation. The main idea of static channel aggregation is: on the premise that the main channel is idle, all secondary channels need to wait for the idle channel to be aggregated. The main idea of dynamic channel aggregation is: when the main channel is idle, if the secondary channel is idle, the main channel and the idle secondary channel can be aggregated.

As can be seen from the above channel aggregation method, the main idea of the current channel aggregation method is to aggregate the main channel with the idle secondary channel when the main channel is idle. However, when there are multiple terminal devices competing for channel resources, there may be some or all overlapping channels after aggregation applied by the multiple terminal devices, where the collision rate of data packets sent by each terminal device is high, and the terminal device enters the backoff window multiple times to wait for sending data packets, so that the problem of small channel aggregation throughput and large time delay is caused.

Based on the above, the application provides a channel aggregation method, which aims to make a preferable channel aggregation decision to improve the transmission performance of the aggregated channel by utilizing the prediction capability of artificial intelligence (artificial intelligence, AI) based on the real-time state of the channel and the transmission requirement of the service, and solve the problems of small channel aggregation throughput and large time delay. Embodiments of the present application will now be described in detail with reference to the drawings, wherein the broken lines in the drawings represent optional steps or components.

In addition, it should be understood that the ordinal terms such as "first," "second," and the like in the embodiments of the present application are used for distinguishing a plurality of objects, and are not used for limiting the size, content, sequence, timing, priority, importance, and the like of the plurality of objects. For example, the t-th period and the t+1th period do not represent the difference in priority or importance level or the like corresponding to the two periods.

In the embodiments of the present application, the number of nouns, unless otherwise indicated, means "a singular noun or a plural noun", i.e. "one or more". "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. For example, A/B, means: a or B. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c, represents: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, c may be single or plural.

Fig. 6 is a schematic diagram of a channel aggregation method according to an embodiment of the present application, where the method includes:

s601: the first terminal device receives a load report from the network device, the load report including load information of each of M channels of the network device in a t-th time period, M being an integer greater than or equal to 2, t being an integer greater than or equal to 2.

In this embodiment of the present application, the network device may acquire, according to a set acquisition period, load information of each of M channels of the network device in a period (for example, a t-th period) corresponding to the acquisition period in a carrier sensing (carrier sensing) manner or the like. The load information of the channel in a certain period (such as the t-th period) can be represented by a load value, where the load value represents the ratio of the busy time (i.e. the time when the data packet is transmitted) of the channel in the period to the total time ratio.

As an example: for a certain period (such as the t-th period), the network device may obtain, through carrier sensing, whether each of M channels of the network device has data packet transmission in each time unit in the period, and determine load information (such as a load value) of each channel in the period according to whether each channel has data packet transmission in each time unit in the period. The time units may be resources with different time granularities, such as subframes, slots (slots), mini slots, or symbols, and one or more time units may be included in one time period.

For example: a certain period (e.g., the t-th period) includes 50 time domain units, and the network device obtains, through carrier sensing, transmission of a data packet in 30 time domain units in the period, so that it can determine that load information (e.g., a load value) of the channel a in the period is 30/50×100% =60%. Alternatively, the load value may be quantized (scale) to 0-255, for example, the load value of channel a during the period is 60%,60% 255=153, and the load value of channel a during the period may be represented by 153 as 60%.

For the t-th time period, after the network device obtains the load information of each of the M channels in the t-th time period, a load report (load report) including the load information of each of the M channels in the t-th time period may be sent to the terminal device by broadcasting, multicasting, and so on, for example: and the information is transmitted to one or more terminal devices in the service range of the network device in a broadcasting mode.

The indication information in the load report for indicating the load information of each channel may be as shown in fig. 7, where a channel number (channel number) field is used to indicate the number (or index) of the channel, and occupies one 8 bits (octet); the channel load (channel load) field is used to indicate the load value corresponding to the channel, and occupies one otte. For the loading information of each of the M channels in the t-th time period, the loading report generates a total of m×16 bits of overhead.

In one possible implementation, the indication information for indicating the load information of each channel may further include a regulatory class (regulatory class) field and an actual measurement stop time (actual measurement stop time) field as shown in fig. 8. Wherein the supervision class field may indicate a set of types, occupying one ottet, which may contain: one or more of information such as operating frequency band, channel bandwidth, channel set, upper limit of transmission power, set emission limit (emissions limits set), behavior limit set (behavior limits set), etc. For example: the type set corresponding to the supervision type field with the value of 55 indicates that the channel bandwidth is 20MHz in the 5 gigahertz (GHz) frequency band, the channel numbers (or indexes) of the channels included in the channel set are 149, 153, 157, 161 and 165, and the transmission power is 1000mW,emissions limits set and 4,behavior limits set and 10; the supervision class set corresponding to the value 12 of the supervision class field indicates that the channel bandwidth is 25MHz in the 2.407GHz band, the channel number (or index) of the channel included in the belonging channel set is 1-11, the transmission power is 1000mW,emissions limits sets and behavior limits set is 10. The actual measurement stop time field occupies 8 hotets and is used for indicating the time for completing the load measurement, and the actual measurement stop time field can be used for ensuring the time consistency of the load report issued to each terminal device, for example, the network device performs the load measurement on the channel through carrier sensing in the t-th time period, and the time for completing the load measurement is the cut-off time of the t-th time period.

It is to be understood that the supervision type field and the actual measurement stop time field are optional, and whether or not the supervision type field and the actual measurement stop time field exist may be indicated by the first 2 bits of the indication information. For example: 00 indicates that there are no these two fields, 01 indicates that there is an actual measurement stop time field, 10 indicates that there is a regulatory class field, and 11 indicates that both the regulatory class field and the actual measurement stop time field are present.

In addition, it should be understood that the M channels include 1 primary channel and M-1 secondary channels corresponding to the first terminal device, where among the M channels, the 1 primary channel corresponding to the first terminal device may be indicated to the first terminal device by the network device through a radio resource control (radio resource control, RRC) message or the like, or may be determined by the first terminal device according to load information of the M channels (for example, a channel with a minimum load value is selected as a primary channel), which is not limited in this application.

S602: the first terminal equipment inputs the channel environment information of the t-th time period into a channel aggregation model for processing to obtain a t-th channel aggregation indicated value.

The channel environment information of the t-th time period comprises load information of each secondary channel in the t-th time period of the main channel and the M-1 secondary channels, and channel state monitoring information obtained by the first terminal equipment in the t-th time period of channel state monitoring of the main channel and the M-1 secondary channels, wherein the channel aggregation indicated value is used for indicating N secondary channels in the M-1 secondary channels to aggregate with the main channel, and N is an integer which is greater than or equal to 0 and less than or equal to M-1.

In the embodiment of the present application, the first terminal device may further monitor channel states of the primary channel and the M-1 secondary channels in a time period corresponding to each acquisition period, so as to obtain channel state monitoring information. Taking the t time period as an example, the channel state monitoring information obtained by the first terminal device performing channel state monitoring on the primary channel and the M-1 secondary channels in the t time period may include: the first terminal equipment monitors the busy state of each sub-channel in the main channel and M-1 sub-channels in the t time period in each time unit; the data packet sending state of each time unit of the first terminal equipment on each secondary channel in the primary channel and M-1 secondary channels, which is monitored by the first terminal equipment in the t-th time period; and the first terminal equipment monitors one or more of the data packet sending state and the busy/idle state of the channel on each secondary channel in the primary channel and the M-1 secondary channels in the t-th time period, and keeps the number of time units unchanged and continuous.

Wherein for the busy state of each time unit of the primary channel and each of the M-1 secondary channels monitored by the first terminal device in the t-th time period, the busy state of each time unit can be used Denoted i=1, 2, 3, …, M, i (hereinafter referred to as channel i) among the primary channel and M-1 secondary channels (M channels in total), and->The number of the elements contained in the element is equal to the number of the time units contained in the t-th time period, the value of the element is 1, which represents that the busy/idle state of the channel i in the time unit corresponding to the element is busy (namely, the transmission of the data packet is possible, the transmission of the data packet of the first terminal equipment is possible, the transmission of the data packet of other terminal equipment is also possible), the value of the element is 0, which represents that the busy/idle state of the channel i in the time unit corresponding to the element is idle (namely, the transmission of the data packet is not available), the value of the element is-1, which represents that the first terminal equipment does not monitor the busy/idle state of the channel i in the time unit corresponding to the element (for example, because the first terminal equipment sends the data packet in other channels outside the channel i in the time unit corresponding to the element, and the busy/idle state of the channel i in the time unit corresponding to the element cannot be monitored). Such as->The busy/idle state of the first 9 time units in the t-th time period is idle, and the busy/idle state of the 10 th time unit is busy.

The data packet transmission state of each time unit on each of the primary channel and the M-1 secondary channels for the first terminal device monitored by the first terminal device in the t-th time period can be used Denoted i=1, 2, 3, …, M, i (hereinafter referred to as channel i) among the primary channel and M-1 secondary channels (M channels in total), and->The number of the elements contained in the channel i is equal to the number of the time units contained in the t time period, the value of the element is 1, which represents that the first terminal equipment of the channel i has data packet transmission in the time unit corresponding to the element, and the value of the element is 0, which represents that the first terminal equipment of the channel i has no data packet transmission in the time unit corresponding to the element. Such as->Indicating that the first terminal device has a data packet to transmit on channel i in the first 3 time units and the 10 th time units of the t-th time period, and has no data packet to transmit on channel i in the 4 th to 9 th time units.

For the first terminal device to monitor the data packet transmitting state and busy state of the channel on each of the main channel and M-1 secondary channels in the t-th time period, the number of time units which keep invariable and continuous simultaneously can be usedAnd (3) representing. To->And->For example, in the first time unit of the t-th time period, the first terminal device may be able to add ∈>The value of (2) is set to an initial value of 0; a second time unit in the t-th time period, >And->The values of the elements corresponding to the second time unit are all the same as the values of the elements corresponding to the first time unit,/-or%>Value +1 (")>1); a third time unit in the t-th time period,>and->The values of the elements corresponding to the third time unit are all the same as the values of the elements corresponding to the second time unit,/->Value +1 (")>2); in the fourth time unit of the t-th time period, there is +.>The value of the element corresponding to the fourth time unit is different from the value of the element corresponding to the third time unit,/->The value of (2) is reset to 0; in the fifth time unit of the t-th time period, there is +.>The value of the element corresponding to the fifth time unit is different from the value of the element corresponding to the fourth time unit, ">The value of (2) is reset to 0; a sixth time unit in the t-th time period,>and->The values of the elements corresponding to the sixth time unit are all the same as the values of the elements corresponding to the fifth time unit, ">Value +1 (")>1); …; tenth time unit in the t-th time period,/->And->The values of the elements corresponding to the tenth time unit are all the same as the values of the elements corresponding to the ninth time unit, ">Value +1 (")>5); finally obtain5.

In this embodiment of the present application, the input of the channel aggregation model may be channel environment information S of a certain period (for example, the t-th period), and the channel aggregation model is output as a channel aggregation instruction value Y. Taking the t-th time period as an example, the channel environment information S of the t-th time period _t Load information including the primary channel at the t-th time periodAnd the load information of M-1 secondary channels in the t-th time period +.>Where j=1, 2, 3, …, M-1, represents the j-th of M-1 secondary channels. And channel state monitoring information obtained by the first terminal device performing channel state monitoring on the main channel and the M-1 secondary channels in the t-th time period, such as the +.>One or more of the following. Y may beIs 0 to 2 ^M-1 -1, each of which is mapped to a specific channel aggregation manner including the primary channel, e.g., y=0 represents that channel aggregation is not performed, y=1 represents that channel aggregation is performed between the primary channel and a first secondary channel of the M-1 secondary channels, y=2 represents that channel aggregation is performed between the primary channel and a second secondary channel of the M-1 secondary channels, …, y=m-1 represents that channel aggregation is performed between the primary channel and the M-1 secondary channels, y=m represents that channel aggregation is performed between the primary channel and the first secondary channel and the second secondary channel of the M-1 secondary channels, and so on.

For parameters of each layer of neurons in the channel aggregation model (i.e., the neural network corresponding to the channel aggregation model), parameters can be configured for each layer of neurons in the channel aggregation model by a random initialization mode. Or a plurality of channel environment information samples marked with target channel aggregation indication values corresponding to the channel aggregation mode in the sample library can be adopted for training by training equipment. In one possible implementation, the plurality of channel environment information samples in the sample library may obtain channel environment information corresponding to each of the plurality of time periods by the first terminal device, and manually determine, according to the channel environment information corresponding to the next time period of the time period, a preferred channel aggregation mode corresponding to the channel environment information corresponding to the time period, and then label, for the channel environment information corresponding to the time period, a target channel aggregation instruction value corresponding to the preferred channel aggregation mode. When the channel aggregation model is trained, training equipment (such as first terminal equipment or network equipment) can input channel environment information samples in a sample library into the channel aggregation model to obtain channel aggregation indicated values output by the channel aggregation model, the training equipment can calculate loss (loss) of the channel aggregation model according to the channel aggregation indicated values output by the channel aggregation model and target channel aggregation indicated values corresponding to the channel environment information samples through loss function (loss function), the higher the loss is, the larger the difference between the channel aggregation indicated values output by the channel aggregation model and the target channel aggregation indicated values is, the channel aggregation model adjusts parameters of neurons in the channel aggregation model according to the loss, and if the parameters of the neurons in the channel aggregation model are updated through a random gradient descent method, the training process of the channel aggregation model becomes a process of reducing the loss as much as possible. And continuously training the channel aggregation model through the channel environment information samples in the sample set, and obtaining the channel aggregation model after training when the loss is reduced to a preset range.

As an example, the structure of the channel aggregation model in the embodiment of the present application may be shown in fig. 9A, where each block in fig. 9A represents a fully connected layer, the channel aggregation model may be formed by 7 fully connected layers, where the 7 fully connected layers sequentially include 1 input layer, 5 hidden layers, and 1 output layer from left to right, where the activation function of each layer may use a rectification function (rectification function, reLu), the input (inputs) of the input layer is channel environment information S of a certain period (e.g., the first period), the output h1 of the input layer is the input of the hidden layer 1, the output h2 of the hidden layer 1 is the input of the hidden layer 2, the output h3 of the hidden layer 2 is the input of the hidden layer 3, the exclusive or operation result of the output h4 of the hidden layer 3 and the output h2 of the hidden layer 1 is the input of the hidden layer 4, the exclusive or operation result of the output h6 of the hidden layer 5 and the output h4 of the hidden layer 3 is the input of the output layer, and the output layer output h1 is the channel aggregation indication value Y. The training process of the channel aggregation model is a process of continuously adjusting parameters of neurons of each layer in the channel aggregation model.

It should be understood that the training device may be a first terminal device, or may be a network device, or may be other devices such as a server, a computer, or the like, where when the training device is not the first terminal device, the training device may determine parameters of neurons of each layer in the channel aggregation model and send the parameters to the first terminal device.

In some implementations, as shown in FIG. 9B, the channel aggregation model is based on channel environment information for a certain time period (e.g., the t-1 th time period) (S) _t-1 ) After outputting the channel aggregation indicator (e.g., t-1 channel aggregation indicator), the first terminal device may further test whether the data packet transmitted on the aggregated channel collides with the data packet transmitted by other terminal devices, and according to the channel aggregation indicatorThe channel aggregation method indicated by the indication value and the condition of transmitting data packets on the aggregated channels are combined with the load condition of each channel in the time period, and a reward value (such as R is given to the channel aggregation indication value output based on the channel aggregation model _t ) And takes the prize value as input to the channel aggregation model for the next time period (e.g., the t-th time period). And learning according to the load condition on each channel by using the guide channel aggregation model so as to output an optimal channel aggregation decision through the channel aggregation model. Alternatively, the channel aggregation model may also output the channel aggregation indication value (e.g., t-1) based on the channel environment information of a certain time period (e.g., t-1) as an input of the channel aggregation model of a next time period (e.g., t-1).

In one possible implementation, the first terminal device may determine the prize value of the channel aggregation indicator value obtained based on the channel aggregation model, that is, determine the prize value of the first terminal device for performing the decision action obtained based on the channel aggregation model (i.e., the channel aggregation mode corresponding to the channel aggregation indicator value). The time period is taken as the t time period, and the rewarding value of the channel aggregation indicated value is obtained based on the channel aggregation model to be R _t+1 The following description is given for the sake of example:

when the channel transmission data packet aggregated by the primary channel and the N secondary channels of the first terminal device is not collided with the transmission data packet of other terminal devices and N is not zero, the first terminal device performs the following stepsDetermining a reward value of a t-th channel aggregation indicated value based on the channel aggregation model;

when the channel transmission data packet aggregated by the primary channel and the N secondary channels of the first terminal device is not collided with the transmission data packet of other terminal devices and N is zero, the first terminal device performs the following stepsDetermining a reward value of a t-th channel aggregation indicated value based on the channel aggregation model;

when the first terminal device collides with the other terminal device transmitting data packets in the channel transmitting data packet aggregated by the main channel and the N secondary channels and N is not zero, the first terminal device performs the following steps Determining a reward value of a t-th channel aggregation indicated value based on the channel aggregation model;

when the first terminal device collides with the other terminal device transmitting data packet in the channel transmitting data packet aggregated by the main channel and the N secondary channels and N is zero, the first terminal device performs the following stepsDetermining a reward value for obtaining a t-th channel aggregation indicated value based on the channel aggregation model.

In each of the above cases, R _t+1 Represents a prize value for deriving a t-th channel aggregate indicator value based on a channel aggregate model, K represents a kth secondary channel of the N secondary channels, k=1, 2, …, N,load information indicating the kth secondary channel in the t-th time period,/for the K-th secondary channel>Load information indicating a primary channel in a t-th period.

In other implementations, the first terminal device also determines the reward value R for obtaining the t-th channel aggregation indicator value based on the channel aggregation model according to the average value of the load information (such as the load value) of the main channel and the N secondary channels in the t-th time period _t+1 . For example: when the first terminal device collides with the data packets sent by other terminal devices in the channel after the aggregation of the main channel and the N secondary channels, the product of the average value of the load information (such as the load value) of the main channel and the N channels in the (t+1) th time period and-1 is used as the rewarding value R _t+1 The method comprises the steps of carrying out a first treatment on the surface of the When the first terminal device is not set with other terminals in the channel transmission data packet aggregated by the main channel and the N secondary channelsWhen the data packet to be transmitted collides, the average value of the load information (such as load value) of the main channel and N channels in the (t+1) th time period is taken as a reward value R _t+1 。

The time period is the t time period, and the rewarding value obtained by obtaining the t channel aggregation indicated value based on the channel aggregation model is determined as R _t+1 For illustration, it will be appreciated that for other time periods, such as the t-1 th time period (the time period t-1 is the time period before the t-1 th time period), the first terminal device may also determine the prize value R for obtaining the t-1 th channel aggregation indication value based on the channel aggregation model based on the load information of the primary channel and each of the N' secondary channels in the t-1 th time period _t The t-1 th channel aggregation indicator value is used for indicating that N 'secondary channels in M-1 secondary channels are aggregated with the main channel, and N' is the same as or different from N.

Such as: when the channel transmission data packet aggregated by the primary channel and N 'secondary channels of the first terminal device is not collided with the transmission data packet of other terminal devices and N' is not zero, the first terminal device performs the following steps Determining a reward value for obtaining a t-1 channel aggregation indication value based on the channel aggregation model.

When the first terminal equipment does not collide with the other terminal equipment transmitting data packets in the channel transmitting data packets aggregated by the main channel and the N 'secondary channels and N' is zero, the first terminal equipment performs the following stepsDetermining a reward value for obtaining a t-1 channel aggregation indication value based on the channel aggregation model.

When the first terminal device collides with the other terminal device transmitting data packet in the channel transmitting data packet aggregated by the main channel and the N 'secondary channels and N' is not zero, the first terminal device performs the following stepsDetermination based on channel aggregationThe model obtains the rewarding value of the t-1 channel aggregation indicating value.

When the first terminal device collides with the other terminal device transmitting data packet in the channel transmitting data packet aggregated by the main channel and the N 'secondary channels and N' is zero, the first terminal device performs the following stepsDetermining a reward value for obtaining a t-1 channel aggregation indication value based on the channel aggregation model.

In each of the above cases, R _t Represents a reward value for deriving a t-1 channel aggregate indicator value based on a channel aggregate model, K represents a kth secondary channel of the N 'secondary channels, k=1, 2, …, N', Load information indicating the kth secondary channel in the t-1 time period, +.>Load information indicating the primary channel in the t-1 th time period.

S603: and the first terminal equipment transmits the data packet through the channel aggregated by the main channel and the N secondary channels in the t+1th time period. The (t+1) th time period is a time period after the (t) th time period.

The first terminal equipment inputs channel environment information of a t time period into a channel aggregation model for processing, after a t channel aggregation indicated value is obtained, the M-1 secondary channels and the main channel can be aggregated according to N secondary channels and the main channel in the M-1 secondary channels indicated by the t channel aggregation indicated value, and data packets are sent to the network equipment through the aggregated channels in a t+1th time period after the t time period.

In some implementations, in order to make the channel aggregation decision (i.e., the channel aggregation indication value) made by the channel aggregation model conform to the expectation of the user, the user may also be preconfigured with a state action value function Q for evaluating different decision actions a (i.e., the channel aggregation modes corresponding to different channel aggregation indication values Y) made based on various channel environment information S, and perform state action value evaluation on the decision actions a (i.e., the channel aggregation modes corresponding to the output channel aggregation indication values Y) output by the channel aggregation model based on the channel environment information S in a certain period of time, so as to obtain a first state action value; and all possible decision actions corresponding to the channel environment information S in the time period (namely, all possible channel aggregation modes corresponding to the channel aggregation indicated values Y) can be evaluated respectively through the state action value function Q to obtain a plurality of state action values, and the maximum value in the state action values is selected as a second state action value. And determining the loss of the channel aggregation model according to the second state action value, the first state action value and the rewarding value, and training and updating the channel aggregation model, for example, adopting a random gradient descent method to update the parameters of neurons in the channel aggregation model according to the loss.

Taking the t-th time period as an example, the following expected square prize value function (which may also be referred to as a loss function) may be used to determine the loss of the channel aggregation model.

L(θ)＝E[R _t+1 +γmax _a′ Q(s _t ′,a′,θ ^* )-Q(s _t ,a _t ；θ)] ²

Wherein L () represents a desired square prize value function, L (θ) represents a loss of the channel aggregation model, Q () represents a set state action value function, γ represents a discount factor (the value may be 0.9 or the like), θ represents a current parameter of the channel aggregation model, R _t+1 Representing decision action a based on channel aggregation model _t (namely, the obtained channel aggregation mode corresponding to the t-th channel aggregation indicated value); q(s) _t ,a _t ；θ)]Representing channel environment information s based on the t-th time period _t Making decision action a _t (i.e., the channel aggregation mode corresponding to the output t-th channel aggregation instruction value); max (max) _a ′Q(s _t ′,a′,θ ^* ) Representing channel environment information s based on the t-th time period _t All selectable decision actions a (2 ^M-1 -candidate channel aggregation mode corresponding to each of the 1 candidate channel aggregation instruction values)A' represents a decision action corresponding to the second state action value, θ ^* The parameters representing the target channel aggregation model, that is, the parameters of the channel aggregation model when the decision action a '(channel aggregation instruction value corresponding to a') of the second state action value is output.

While the foregoing describes the determination of the loss of the channel aggregation model by taking the time period as the t time period, it is understood that, for other time periods (such as the t-1 time period), the loss of the channel aggregation model corresponding to the t-1 time period can be determined by replacing the reward value, the first state action value and the second state action value corresponding to the t-1 time period with the reward value, the first state action value and the second state action value corresponding to the t-1 time period, and training and updating the channel aggregation model of the t-1 time period.

In addition, it should be understood that, the foregoing is that the channel aggregation model is on the first terminal device side, the first terminal device processes the input channel environment information of the t-th time period based on the channel aggregation model to obtain a channel aggregation indicated value, and the first terminal device performs channel aggregation at the t+1th time period based on the channel aggregation mode indicated by the channel aggregation indicated value for illustration. In some implementations, the channel aggregation model may be further deployed in a network device, where the network device side obtains channel environment information corresponding to the t-th time period of the first terminal device and inputs the channel aggregation model, processes the input channel environment information of the t-th time period to obtain a channel aggregation indication value, and the network device sends the channel aggregation indication value or a channel aggregation mode indicated by the channel aggregation indication value to the first terminal device, where the first terminal device performs channel aggregation according to the channel aggregation indication value from the network device or the channel aggregation mode indicated by the channel aggregation indication value.

It will be appreciated that, in order to implement the functions in the above embodiments, the first terminal device includes a corresponding hardware structure and/or software module for performing each function. Those of skill in the art will readily appreciate that the elements and method steps of the examples described in connection with the embodiments disclosed herein may be implemented as hardware or a combination of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application scenario and design constraints imposed on the solution.

Fig. 10 and 11 are schematic structural diagrams of a possible communication device according to an embodiment of the present application. These communication devices may be used to implement the functions of the first terminal device in the above method embodiments, so that the beneficial effects of the above method embodiments may also be implemented. In one possible implementation, the communication device may be the first terminal device, and may also be a module (e.g. a chip) applied to the first terminal device.

As shown in fig. 10, the communication device 1000 includes a processing unit 1010 and an interface unit 1020, where the interface unit 1020 may also be a transceiver unit or an input-output interface. The communication device 1000 may be used to implement the functionality of the first terminal device in the method embodiment shown in fig. 6 described above.

When the communication apparatus 1000 is used to implement the functionality of the first terminal device in the method embodiment shown in fig. 6:

an interface unit 1020, configured to receive a load report from a network device, where the load report includes load information of each of M channels of the network device in a t-th time period, where the M channels include 1 primary channel and M-1 secondary channels corresponding to a first terminal device, M is an integer greater than or equal to 2, and t is an integer greater than or equal to 2; a processing unit 1010, configured to input channel environment information in a t-th time period into a channel aggregation model for processing, to obtain a t-th channel aggregation instruction value, where the channel environment information in the t-th time period includes load information of each of a main channel and M-1 secondary channels in the t-th time period, and channel state monitoring information obtained by monitoring channel states of the main channel and M-1 secondary channels in the t-th time period, and the t-th channel aggregation instruction value is used to instruct N secondary channels in the M-1 secondary channels to aggregate with the main channel, where N is an integer greater than or equal to 0 and less than or equal to M-1; and channel aggregation is carried out on the main channel and the N secondary channels. Optionally, the load report further comprises an expiration of the t-th period.

In one possible design, the channel state monitoring information obtained by the processing unit 1010 performing channel state monitoring on the primary channel and the M-1 secondary channels in the t-th time period includes one or more of the following: the busy state of each of the primary channel and M-1 secondary channels monitored by the processing unit 1010 during the t-th time period for each time unit; the processing unit 1010 monitors the data packet transmission status of the communication device in each time unit on each of the primary channel and M-1 secondary channels during the t-th time period; the processing unit 1010 monitors the number of time units during the t-th time period in which the communication device keeps constant the data packet transmission status and the busy/idle status of the channel on each of the primary channel and the M-1 secondary channels.

In one possible design, the processing unit 1010 is further configured to determine, according to load information of each of the primary channel and the N 'secondary channels in the t-1 th time period, a reward value based on a channel aggregation model to obtain a t-1 th channel aggregation indicator value, where the t-1 th channel aggregation indicator value is used to indicate that the N' secondary channels in the M-1 secondary channels are aggregated with the primary channel; according to the channel environment information of the t-1 time period, the t-1 channel aggregation indicated value and the set state action value function, determining a first state action value of a channel aggregation mode corresponding to the t-1 channel aggregation indicated value based on the channel environment information of the t-1 time period; 2 of the primary channel corresponding to M-1 secondary channels according to channel environment information of t-1 time period ^M-1 -1 candidate channel aggregate indicator value and set state action value function, determining a second state action value, 2 ^M-1 -1 candidate channel aggregate indicator value corresponds to 2 of primary channel and M-1 secondary channels ^M-1 -1 candidate channel aggregation, the second state action value is 2 based on the channel environment information of the t-1 time period ^M-1 -a maximum state action value of state action values of candidate channel aggregation modes corresponding to the 1 candidate channel aggregation instruction values; determining loss of the channel aggregation model according to the first state action value, the second state action value and the rewarding value of the t-1 channel aggregation indicated valueLoss of function; training and updating the channel aggregation model according to the loss of the channel aggregation model; wherein N' is the same as or different from N, and the t-1 th time period is a time period before the t-th time period.

In one possible design, the processing unit 1010 is further configured to determine, according to load information of each of the primary channel and the N ' secondary channels in a t-1 th time period, a reward value for obtaining a t-1 th channel aggregation indicator value based on a channel aggregation model, where the t-1 th channel aggregation indicator value is used to indicate that N ' secondary channels in the M-1 secondary channels are aggregated with the primary channel, N ' is the same as or different from N, and the t-1 th time period is a time period before the t-1 th time period; the processing unit 1010 is specifically configured to input the channel environment information of the t-th time period and the reward value of the t-1 th channel aggregation indicator value into the channel aggregation model for processing when the t-th channel aggregation indicator value is obtained by inputting the channel environment information of the t-th time period into the channel aggregation model for processing, and obtain the t-th channel aggregation indicator value.

In a possible implementation, the processing unit 1010 is specifically configured to, when determining, according to the load information of each of the primary channel and the N' secondary channels in the t-1 th time period, a prize value of the t-1 th channel aggregation indicator value based on the channel aggregation model: when the interface unit 1020 does not collide with the other terminal device transmission data packets in the channel transmission data packets aggregated by the primary channel and the N 'secondary channels and N' is not zero, the processing unit 1010 performs the following stepsDetermining a reward value of a t-1 channel aggregation indicated value based on the channel aggregation model; wherein R is _t Represents a reward value for deriving a t-1 channel aggregate indicator value based on a channel aggregate model, K represents a kth secondary channel of the N 'secondary channels, k=1, 2, …, N',representing the load information of the kth secondary channel in the t-1 time period.

In another possible implementation, the processing unit 1010 may be configured to receive a message from the hostThe method is specifically used for determining the rewarding value of the t-1 channel aggregation indicated value based on the channel aggregation model when the load information of each sub-channel in the t-1 time period of the channel and N' sub-channels is determined: when the interface unit 1020 does not collide with the other terminal device transmission data packets in the channel transmission data packets aggregated by the main channel and the N 'secondary channels and N' is zero, the processing unit 1010 performs the following steps Determining a reward value of a t-th channel aggregation indicated value based on the channel aggregation model; wherein R is _t A reward value indicating that the t-1 th channel aggregation indication value is obtained based on the channel aggregation model,/for>Load information indicating the primary channel in the t-1 th time period.

In another possible implementation, the processing unit 1010 is specifically configured to, when determining, according to the load information of each of the primary channel and the N' secondary channels in the t-1 th time period, to obtain the prize value of the t-1 th channel aggregation indicator value based on the channel aggregation model: when the interface unit 1020 collides with other terminal device transmission data packets in the channel transmission data packets aggregated by the primary channel and the N 'secondary channels and N' is not zero, the processing unit 1010 performs the following stepsDetermining a reward value of a t-1 channel aggregation indicated value based on the channel aggregation model; wherein R is _t Represents a reward value for deriving a t-1 channel aggregate indicator value based on a channel aggregate model, K represents a kth secondary channel of the N 'secondary channels, k=1, 2, …, N',load information indicating the kth secondary channel in the t-1 time period, +.>Indicating that the primary channel is in the t-1 time periodIs set, is provided.

In yet another possible implementation, the processing unit 1010 is specifically configured to, when determining, based on the channel aggregation model, a prize value of the t-1 th channel aggregation indicator value according to the load information of the primary channel and each of the N' secondary channels in the t-1 th time period: when the interface unit 1020 collides with other terminal device transmission data packets in the channel transmission data packets aggregated by the primary channel and the N 'secondary channels and N' is zero, the processing unit 1010 performs the following steps Determining a reward value of a t-1 channel aggregation indicated value based on the channel aggregation model; wherein R is _t A reward value indicating that the t-1 th channel aggregation indication value is obtained based on the channel aggregation model,/for>Load information indicating the primary channel in the t-1 th time period.

In one possible design, the processing unit 1010 is further configured to determine, according to the load information of the primary channel and each of the N secondary channels in the t-th time period, a prize value for deriving the t-th channel aggregation indicator value based on the channel aggregation model.

In a possible implementation, the processing unit 1010 is specifically configured to, when determining, according to load information of each of the primary channel and the N secondary channels in the t-th time period, to obtain the prize value of the t-th channel aggregation indicator value based on the channel aggregation model: when the interface unit 1020 does not collide with the other terminal device transmission data packets in the channel transmission data packets aggregated by the main channel and the N secondary channels and N is not zero, the processing unit 1010 performs the following stepsDetermining a reward value for obtaining a t-th channel aggregation indicated value based on the channel aggregation model.

In another possible implementation, the processing unit 1010 determines the channel-based aggregation based on the load information of the primary channel and each of the N secondary channels in the t-th time period When the aggregate model obtains the rewarding value of the t channel aggregate indicated value, the aggregate model is specifically used for: when the interface unit 1020 does not collide with the other terminal device transmission data packets in the channel transmission data packets aggregated by the main channel and the N secondary channels and N is zero, the processing unit 1010 performs the following stepsDetermining a reward value for obtaining a t-th channel aggregation indicated value based on the channel aggregation model.

In another possible implementation, the processing unit 1010 is specifically configured to, when determining, according to the load information of the primary channel and each of the N secondary channels in the t-th time period, to obtain the prize value of the t-th channel aggregation indicator value based on the channel aggregation model: when the interface unit 1020 collides with other terminal device transmission data packets in the channel transmission data packets aggregated by the primary channel and the N secondary channels and N is not zero, the processing unit 1010 performs the following stepsDetermining a reward value for obtaining a t-th channel aggregation indicated value based on the channel aggregation model.

In another possible implementation, the processing unit 1010 is specifically configured to, when determining, according to the load information of the primary channel and each of the N secondary channels in the t-th time period, to obtain the prize value of the t-th channel aggregation indicator value based on the channel aggregation model: when the interface unit 1020 collides with other terminal device transmission data packets in the channel transmission data packets aggregated by the primary channel and the N secondary channels and N is zero, the processing unit 1010 performs the following steps Determining a reward value of a t-th channel aggregation indicated value based on the channel aggregation model;

in the above several designs, R _t+1 Represents a prize value for deriving a t-th channel aggregate indicator value based on a channel aggregate model, K represents a kth secondary channel of the N secondary channels, k=1, 2, …, N,load information indicating the kth secondary channel in the t-th time period,/for the K-th secondary channel>Load information indicating a primary channel in a t-th period.

In one possible design, the processing unit 1010 is further configured to determine, according to the channel environment information of the t-th time period, the t-th channel aggregation instruction value, and the set state action value function, a first state action value of a channel aggregation manner corresponding to the t-th channel aggregation instruction value based on the channel environment information of the t-th time period; according to channel environment information of the t-th time period, 2 of main channels corresponding to M-1 secondary channels ^M-1 -1 candidate channel aggregate indicator value and set state action value function, determining a second state action value, 2 ^M-1 -1 candidate channel aggregate indicator value corresponds to 2 of primary channel and M-1 secondary channels ^M-1 -1 candidate channel aggregation, the second state action value is 2 based on the channel environment information of the t-th time period ^M-1 -a maximum state action value of state action values of candidate channel aggregation modes corresponding to the 1 candidate channel aggregation instruction values; obtaining a reward value of a t-th channel aggregation indicated value according to the first state action value, the second state action value and the channel aggregation model, and determining loss of the channel aggregation model; and training and updating the channel aggregation model according to the loss of the channel aggregation model.

As shown in fig. 11, the present application further provides a communication device 1100, including a processor 1110 and an interface circuit 1120. The processor 1110 and the interface circuit 1120 are coupled to each other. It is understood that the interface circuit 1120 may be a transceiver, an input-output interface, an input interface, an output interface, a communication interface, etc. Optionally, the communication device 1100 may further include a memory 1130 for storing instructions to be executed by the processor 1110 or for storing input data required by the processor 1110 to execute instructions or for storing data generated after the processor 1110 executes instructions. Optionally, memory 1130 may also be integrated with processor 1110.

When the communication device 1100 is used to implement the method shown in fig. 6, the processor 1110 may be used to implement the functions of the processing unit 1010 described above, and the interface circuit 1120 may be used to implement the functions of the interface unit 1020 described above.

As shown in fig. 12, a schematic structural diagram of a device provided in an embodiment of the present application, where the device may be a network device or a first terminal device, and the device may include a processor, a transceiver, and an antenna, where the processor may include one or more processing units, and the different processing units may be separate devices or may be integrated into one or more processors. The processor may be a neural hub and a command center of the device, among others. The processor can generate an operation control signal according to the instruction operation code and the time sequence signal to finish the operations of fetching and executing the instruction. In the embodiment of the application, the processor may execute a corresponding channel aggregation method flow according to an instruction corresponding to the channel aggregation method; the transceiver and antenna may receive signals from other devices and transmit signals to or send signals from the processor to other devices.

In addition, the device may further include a neural Network Processor (NPU), where the NPU performs training and updating on the channel aggregation model (i.e., the neural network model), and performs operation according to information input into the channel aggregation model to output a channel aggregation mode (or a channel aggregation instruction value corresponding to the channel aggregation mode). It is to be appreciated that an inference module and a training module can be included in the NPU, wherein the training module can be utilized to implement training updates to the channel aggregation model (i.e., the neural network model). The reasoning module can operate and output a channel aggregation mode according to the information of the input channel aggregation model. In addition, the NPU may be coupled to a central processing unit, which is not limited in this application.

It is to be appreciated that the processor in embodiments of the present application may be a central processing unit (central processing unit, CPU), but may also be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), logic circuits, field programmable gate arrays (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general purpose processor may be a microprocessor, but in the alternative, it may be any conventional processor.

The method steps in the embodiments of the present application may be implemented by hardware, or may be implemented by a processor executing software instructions. The software instructions may be comprised of corresponding software modules that may be stored in random access memory, flash memory, read only memory, programmable read only memory, erasable programmable read only memory, electrically erasable programmable read only memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. In addition, the ASIC may reside in a network device or terminal device. The processor and the storage medium may reside as discrete components in a network device or terminal device.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a network device, a user device, or other programmable apparatus. The computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, from one network device, terminal, computer, server, or data center to another network device, terminal, computer, server, or data center by wire or wirelessly. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, e.g., floppy disk, hard disk, tape; but also optical media such as digital video discs; but also semiconductor media such as solid state disks. The computer readable storage medium may be volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage medium.

In the various embodiments of the application, if there is no specific description or logical conflict, terms and/or descriptions between the various embodiments are consistent and may reference each other, and features of the various embodiments may be combined to form new embodiments according to their inherent logical relationships.

In addition, it should be understood that in the embodiments of the present application, the term "exemplary" is used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the term use of an example is intended to present concepts in a concrete fashion.

It will be appreciated that the various numerical numbers referred to in the embodiments of the present application are merely for ease of description and are not intended to limit the scope of the embodiments of the present application. The sequence number of each process does not mean the sequence of the execution sequence, and the execution sequence of each process should be determined according to the function and the internal logic.

Claims

1. A method of channel aggregation, comprising:

a first terminal device receives a load report from a network device, wherein the load report comprises load information of each channel in M channels of the network device in a t-th time period, the M channels comprise 1 main channel and M-1 secondary channels corresponding to the first terminal device, M is an integer greater than or equal to 2, and t is an integer greater than or equal to 2;

The first terminal equipment inputs channel environment information of the t-th time period into the channel aggregation model for processing to obtain a t-th channel aggregation indicated value, wherein the channel environment information of the t-th time period comprises load information of each secondary channel in the t-th time period in the main channel and the M-1 secondary channels and channel state monitoring information obtained by the first terminal equipment in the t-th time period for monitoring channel states of the main channel and the M-1 secondary channels, and the t-th channel aggregation indicated value is used for indicating N secondary channels in the M-1 secondary channels to aggregate with the main channel, and N is an integer which is more than or equal to 0 and less than or equal to M-1;

and the first terminal equipment transmits a data packet through the channel aggregated by the main channel and the N secondary channels in the t+1th time period, wherein the t+1th time period is a time period after the t time period.

2. The method of claim 1, wherein the channel state monitoring information obtained by the first terminal device performing channel state monitoring on the primary channel and the M-1 secondary channels in the t-th time period includes one or more of:

The first terminal equipment monitors the busy state of each time unit of the main channel and each secondary channel of the M-1 secondary channels in the t-th time period;

the data packet sending state of each time unit of the first terminal device on each secondary channel of the primary channel and the M-1 secondary channels, wherein the data packet sending state of each time unit of the first terminal device is monitored by the first terminal device in the t-th time period;

and the first terminal equipment monitors the number of time units of which the data packet sending state and the busy and idle state of the channel are kept unchanged and continuous on each secondary channel in the primary channel and the M-1 secondary channels in the t-th time period.

3. The method of claim 1 or 2, wherein the method further comprises:

the first terminal equipment determines a reward value of the t-1 channel aggregation indicated value based on the channel aggregation model according to the load information of each secondary channel in the t-1 time period of the main channel and N 'secondary channels, wherein the t-1 channel aggregation indicated value is used for indicating the N' secondary channels in the M-1 secondary channels to aggregate with the main channel;

The first terminal equipment determines a first state action value of a channel aggregation mode corresponding to the t-1 channel aggregation indicated value based on the channel environment information of the t-1 time period according to the channel environment information of the t-1 time period, the t-1 channel aggregation indicated value and a set state action value function;

the first terminal equipment receives the channel environment information of the t-1 time period, and 2 corresponding to the primary channel and the M-1 secondary channels according to the channel environment information of the t-1 time period ^M-1 -1 candidate channel aggregate indicator value and said set state action value function, determining a second state action value, wherein said 2 ^M-1 -1 candidate channel aggregate indicator value corresponds to 2 of the primary channel and the M-1 secondary channels ^M ^-1 -1 candidate channel aggregation, wherein the second state action value is obtained by respectively performing the 2 th state actions based on the channel environment information of the t-1 th time period ^M-1 -a maximum state action value of state action values of candidate channel aggregation modes corresponding to the 1 candidate channel aggregation instruction values;

the first terminal equipment determines the loss of the channel aggregation model according to the first state action value, the second state action value and the rewarding value of the t-1 channel aggregation indicated value;

The first terminal equipment trains and updates the channel aggregation model according to the loss of the channel aggregation model;

wherein the N' is the same as or different from the N, and the t-1 th time period is a time period before the t-1 th time period.

4. The method of claim 1 or 2, wherein the method further comprises:

the first terminal equipment determines a reward value of a t-1 th channel aggregation indicated value based on the channel aggregation model according to load information of each secondary channel in the t-1 th time period of the main channel and N ' secondary channels, wherein the t-1 th channel aggregation indicated value is used for indicating that the N ' secondary channels in the M-1 secondary channels are aggregated with the main channel, N ' is the same as or different from N, and the t-1 th time period is a time period before the t-1 th time period;

the first terminal device inputs the channel environment information of the t-th time period into the channel aggregation model for processing to obtain a t-th channel aggregation indicated value, and the method comprises the following steps:

and the first terminal equipment inputs the channel environment information of the t-th time period and the rewarding value of the t-1 channel aggregation indicated value into the channel aggregation model for processing to obtain the t-th channel aggregation indicated value.

5. The method according to claim 3 or 4, wherein the first terminal device determining a prize value for the t-1 th channel aggregation indicator value based on the channel aggregation model according to load information of the primary channel and each of the N' secondary channels in the t-1 th time period, includes:

when the first terminal device does not collide with other terminal device transmitting data packets in the channel transmitting data packet aggregated by the main channel and the N 'secondary channels and the N' is not zero, the first terminal device performs the following steps Determining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model;

wherein the R is _t Representing a prize value for deriving the t-1 th channel aggregate indicator value based on the channel aggregate model, the K representing a kth secondary channel of the N 'secondary channels, the K = 1, 2, …, N', theLoad information indicating that the kth secondary channel is in the t-1 time period.

6. The method according to claim 3 or 4, wherein the first terminal device determining a prize value for the t-1 th channel aggregation indicator value based on the channel aggregation model according to load information of the primary channel and each of the N' secondary channels in the t-1 th time period, includes:

When the first terminal device does not collide with other terminal device transmitting data packets in the channel transmitting data packet aggregated by the main channel and the N 'secondary channels and the N' is zero, the first terminal device performs the following steps Determining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model;

wherein the R is _t A reward value representing the t-1 th channel aggregation instruction value obtained based on the channel aggregation model, theLoad information indicating the primary channel in the t-1 th time period.

7. The method according to claim 3 or 4, wherein the first terminal device determining a prize value for the t-1 th channel aggregation indicator value based on the channel aggregation model according to load information of the primary channel and each of the N' secondary channels in the t-1 th time period, includes:

when the first terminal device collides with the other terminal device transmitting data packet in the channel transmitting data packet aggregated by the main channel and the N 'secondary channels and the N' is not zero, the first terminal device performs the following steps Determining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model;

Wherein the R is _t Representing a prize value for deriving the t-1 th channel aggregate indicator value based on the channel aggregate model, the K representing a kth secondary channel of the N 'secondary channels, the K = 1, 2, …, N', theLoad information representing said kth secondary channel in said t-1 th time period, said +.>Load information indicating the primary channel in the t-1 th time period.

8. The method according to claim 3 or 4, wherein the first terminal device determining a prize value for the t-1 th channel aggregation indicator value based on the channel aggregation model according to load information of the primary channel and each of the N' secondary channels in the t-1 th time period, includes:

when the first terminal device collides with the other terminal device transmitting data packet in the channel transmitting data packet aggregated by the main channel and the N' secondary channels, and the first terminal device transmits the data packet to the other terminal deviceWhen N' is zero, the first terminal equipment is according to the following conditionsDetermining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model;

wherein the R is _t A reward value representing the t-1 th channel aggregation instruction value obtained based on the channel aggregation model, the Load information indicating the primary channel in the t-1 th time period.

9. The method of any of claims 1-8, wherein the load report further comprises an expiration of the t-th period.

10. A communication device, comprising an interface unit and a processing unit;

the interface unit is configured to receive a load report from a network device, where the load report includes load information of each channel in M channels of the network device in a t-th time period, where the M channels include 1 primary channel and M-1 secondary channels corresponding to the first terminal device, M is an integer greater than or equal to 2, and t is an integer greater than or equal to 2;

the processing unit is configured to input channel environment information of the t-th time period into the channel aggregation model for processing, so as to obtain a t-th channel aggregation indicated value, where the channel environment information of the t-th time period includes load information of each secondary channel in the t-th time period in the primary channel and the M-1 secondary channels, and channel state monitoring information obtained by monitoring channel states of the primary channel and the M-1 secondary channels in the t-th time period, and the t-th channel aggregation indicated value is used to indicate that N secondary channels in the M-1 secondary channels are aggregated with the primary channel, where N is an integer greater than or equal to 0 and less than or equal to the M-1; and transmitting a data packet through the channel aggregated by the primary channel and the N secondary channels in a t+1th time period, wherein the t+1th time period is a time period after the t time period.

11. The apparatus of claim 10, wherein the channel state monitoring information obtained by the processing unit channel state monitoring the primary channel and the M-1 secondary channels for the nth time period comprises one or more of:

the processing unit monitors the busy state of each time unit of each of the primary channel and the M-1 secondary channels in the t-th time period;

the processing unit monitors the data packet transmission state of each time unit of the communication device on each secondary channel of the primary channel and the M-1 secondary channels in the t-th time period;

the processing unit monitors the number of time units of which the data packet sending state and the busy state of the channel of the communication device in each secondary channel in the primary channel and the M-1 secondary channels are kept unchanged and continuous in the t time period.

12. The apparatus of claim 10 or 11, wherein the processing unit is further configured to:

determining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model according to the load information of each secondary channel in the t-1 th time period of the primary channel and the N 'secondary channels, wherein the t-1 th channel aggregation indicated value is used for indicating the N' secondary channels in the M-1 secondary channels to aggregate with the primary channel;

Determining a first state action value of a channel aggregation mode corresponding to the t-1 th channel aggregation indicated value based on the channel environment information of the t-1 st time period according to the channel environment information of the t-1 th time period, the t-1 th channel aggregation indicated value and a set state action value function;

according to the channel environment information of the t-1 time period, the main channel corresponds to 2 of the M-1 secondary channels ^M-1 -1 candidate channel aggregate indicator value and said set state action value function, determining a second state action value, wherein said 2 ^M ^-1 -1 candidate channel aggregate indicator value corresponds to 2 of the primary channel and the M-1 secondary channels ^M-1 -1 candidate channel aggregation, wherein the second state action value is obtained by respectively performing the 2 th state actions based on the channel environment information of the t-1 th time period ^M-1 -a maximum state action value of state action values of candidate channel aggregation modes corresponding to the 1 candidate channel aggregation instruction values;

determining a loss of the channel aggregation model according to the first state action value, the second state action value and the rewarding value of the t-1 channel aggregation indicated value; training and updating the channel aggregation model according to the loss of the channel aggregation model;

13. The apparatus of claim 10 or 11, wherein the processing unit is further configured to:

determining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model according to the load information of each secondary channel in the t-1 th time period of the primary channel and N ' secondary channels, wherein the t-1 th channel aggregation indicated value is used for indicating the N ' secondary channels in the M-1 secondary channels to aggregate with the primary channel, N ' is the same as or different from N, and the t-1 th time period is a time period before the t time period;

and inputting the channel environment information of the t-th time period into the channel aggregation model for processing, and when the t-th channel aggregation indicated value is obtained, inputting the channel environment information of the t-th time period and the rewarding value of the t-1-th channel aggregation indicated value into the channel aggregation model for processing, so as to obtain the t-th channel aggregation indicated value.

14. The apparatus according to claim 12 or 13, wherein the processing unit is configured to, when determining the prize value of the t-1 th channel aggregation indicator value based on the channel aggregation model according to the load information of the primary channel and each of the N' secondary channels in the t-1 th time period, specifically:

When the interface unit does not collide with other terminal equipment transmitting data packets in the channel transmitting data packets aggregated by the main channel and the N 'secondary channels and the N' is not zero, the processing unit processes the data packets according to the following conditions Determining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model;

15. The apparatus according to claim 12 or 13, wherein the processing unit is configured to, when determining the prize value of the t-1 th channel aggregation indicator value based on the channel aggregation model according to the load information of the primary channel and each of the N' secondary channels in the t-1 th time period, specifically:

when the channel transmission data packet aggregated by the interface unit in the main channel and the N' secondary channels does not collide with other terminal equipment transmission data packets, and the interface unit receives the channel transmission data packet from the other terminal equipment When N' is zero, the processing unit is used for processing the data according to the following conditionsDetermining a reward value of the t-th channel aggregation indicated value based on the channel aggregation model;

16. The apparatus according to claim 12 or 13, wherein the processing unit is configured to, when determining the prize value of the t-1 th channel aggregation indicator value based on the channel aggregation model according to the load information of the primary channel and each of the N' secondary channels in the t-1 th time period, specifically:

when the interface unit collides with the data packets sent by other terminal equipment in the channel after the aggregation of the main channel and the N 'secondary channels and the N' is not zero, the processing unit processes the data packets according to the following conditions Determining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model;

wherein the R is _t Representing a prize value for deriving the t-1 th channel aggregate indicator value based on the channel aggregate model, the K representing a kth secondary channel of the N 'secondary channels, the K = 1, 2, …, N', the Represents the KthLoad information of the sub-channels in said t-1 th time period, said +.>Load information indicating the primary channel in the t-1 th time period.

17. The apparatus according to claim 12 or 13, wherein the processing unit is configured to, when determining the prize value of the t-1 th channel aggregation indicator value based on the channel aggregation model according to the load information of the primary channel and each of the N' secondary channels in the t-1 th time period, specifically:

when the interface unit collides with the data packets sent by other terminal equipment and the data packets sent by the channel after the aggregation of the main channel and the N 'secondary channels and the N' is zero, the processing unit processes the data packets according to the following conditionsDetermining a reward value of the t-1 th channel aggregation indicated value based on the channel aggregation model;

18. The apparatus of any of claims 10-17, wherein the load report further comprises an expiration of the t-th period.

19. A computer program product comprising instructions which, when executed, cause the method of any one of claims 1-9 to be implemented.

20. A chip for implementing the method according to any one of claims 1-9.

21. A computer readable storage medium, characterized in that the storage medium has stored therein a computer program or instructions, which when executed, cause the method according to any of claims 1-9 to be implemented.