Communication method and apparatus

Abstract

Embodiments of the present application provide a communication method and apparatus. The method comprises: a first device acquires transmission information of a first cell served by the first device and transmission information of at least one adjacent second cell; the first device obtains target transmission information of the first cell on the basis of the transmission information of the first cell and the transmission information of the at least one second cell, wherein the target transmission information of the first cell is used for determining channel access information of the first cell; and the first device sends the target transmission information of the first cell to a second device. In the method, after obtaining transmission information of the present cell and transmission information of an adjacent cell, a first device obtains target transmission information of the first cell on the basis of both the transmission information of the present cell and the transmission information of the adjacent cell, the target transmission information of the first cell being used for subsequently determining more accurate and reliable channel access information of the first cell, thereby effectively improving the performance of transmission in the first cell, thus reducing transmission trailing delay.

Description

A communication method and apparatus

[0001] Cross-reference to Related Applications

[0002] This application claims priority to the Chinese Patent Application No. 202411089136.4, filed on August 8, 2024, and entitled “A communication method and apparatus”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the field of communication technology, and in particular to a communication method and apparatus. BACKGROUND

[0004] Wireless communication is developing rapidly, and the 5th-generation (5G) mobile communication system and the Wi-Fi 7 standard have gradually been commercialized. The next generation of wireless technology and standardization is being carried out worldwide. Wireless communication has penetrated into all aspects of daily life and work, and has become an indispensable part. With the rapid growth of the number of intelligent terminal devices and the popularity of IoT devices, new wireless applications such as virtual reality, augmented reality and holographic images have emerged in an endless stream.

[0005] New wireless technologies, new terminal devices and new wireless applications have made wireless networks more complex than ever. It can be predicted that future wireless networks will become more complex. In order to counter the high complexity trend of wireless networks, AI has become the industry consensus as an effective tool for wireless network design and management. Currently, AI-based Wi-Fi network optimization methods have been discussed in standards. In addition, AI has been widely used in Wi-Fi network MAC resource management, such as channel access, rate adaptation, channel aggregation, channel prediction, roaming, etc.

[0006] Future Wi-Fi proposes higher targets for the optimization of network parameters (such as tail latency and packet error rate (PER)) in single basic service set (BSS) or overlapping BSS (OBSS) scenarios, especially for the improvement of tail latency in OBSS scenarios. Therefore, how to effectively improve the performance of tail latency in network transmission scenarios is one of the problems that need to be solved at present. SUMMARY

[0007] The application provides a communication method and device, which can effectively improve the performance of tail latency in a network transmission scenario.

[0008] In a first aspect, the application provides a communication method, which can be applied to a first device, or a component (such as a processor, a chip, or a chip system, etc.) of the first device, or a logic node, a logic module or software capable of realizing all or part of the functions of the first device, or a device matched with the first device. Taking the method applied to the first device as an example, the method comprises the following steps: a first device acquires transmission information of a first cell served by the first device and transmission information of at least one second cell; the at least one second cell is adjacent to the first cell;

[0009] The first device obtains target transmission information of the first cell based on the transmission information of the first cell and the transmission information of the at least one second cell; the target transmission information of the first cell is used to determine channel access information of the first cell; and the first device sends the target transmission information of the first cell to at least one second device.

[0010] In the embodiments of the application, the first device can be an access point (such as an AP or an AP multi-link device (MLD)), the second device can be a non-access station (such as a Non-AP STA or a Non-AP STA MLD) in the first cell, or a relay node (or a relay node serving the first cell) in the first cell. The relay node can refer to a node or device with access and / or forwarding functions. The first cell served by the first device can be referred to as a first basic service set (BSS) (or simply BSS1); the at least one second cell adjacent to the first BSS can be referred to as a neighbor BSS or an adjacent BSS of the first BSS.

[0011] In the above, the transmission information of the first cell (or the transmission information of the second cell) can include but is not limited to one or more of the following:

[0012] Information of latency, tail latency, contention window size, throughput, or packet loss rate;

[0013] The information of latency can be the information of latency reported by each second device in the first cell, such as one or more of the following: segmented information of latency of the second device, an index of a segment where the tail latency is located, a number of data packets transmitted on each segment, or latency of each data packet.

[0014] The delay includes a delay of at least one data packet, and a delay of 95% of the data packets in the at least one data packet is less than the tail delay; the delay of each data packet can include but is not limited to queuing delay of the data packet and / or access delay of the data packet.

[0015] In the embodiments of the present application, the queuing delay of the data packet can refer to the time length from the data packet entering the buffer / queue to starting transmission. The access delay of the data packet can refer to the time length from the data packet starting transmission to transmission success. The queuing delay and the access delay of the data packet (i.e. the sum of the queuing delay and the access delay of the data packet) can refer to the time length from the data packet entering the buffer / queue to transmission success.

[0016] In addition, in the embodiments of the present application, the transmission information of the first cell can be referred to as the observation information of the first cell or the observation data of the first cell, and the target transmission information of the first cell can be referred to as the fusion information of the first cell or the fusion data of the first cell. The same applies to other cells, for example, the transmission information of the second cell can be referred to as the observation information of the second cell or the observation data of the second cell, and the target transmission information of the second cell can be referred to as the fusion information of the second cell or the fusion data of the second cell.

[0017] In the present application, the first device obtains the transmission information (i.e. the observation information) of the serving cell and the transmission information (i.e. the observation information) of the adjacent cell, and then obtains the target transmission information (which can be referred to as the fusion information) of the first cell based on the transmission information of the first cell and the transmission information of the adjacent cell. The target transmission information of the first cell can be used to determine more accurate and reliable channel access information of the first cell, thereby effectively improving the transmission performance in the first cell, and further reducing the tail delay of transmission and reducing the communication overhead of the network.

[0018] In addition, in the above, the first device can also send the transmission information of the first cell and / or the target transmission information (i.e. the fusion information) of the first cell to the access site of the adjacent cell (i.e. the second cell) for use. The access site of the adjacent cell can refer to the steps performed by the first device for implementation to determine more accurate and reliable channel access information, which will not be described in detail.

[0019] In a possible implementation, the first device obtains the target transmission information of the first cell based on the transmission information of the first cell and the transmission information of the at least one second cell, which can include: the first device performs fusion processing on the transmission information of the first cell and the transmission information of the at least one second cell through the set fusion network model to obtain the target transmission information of the first cell (which can be referred to as the fusion information of the first cell).

[0020] In the above, the fusion network model can be obtained by training and setting of the first device, training and setting of a network device (e.g., a cloud server) and deploying on the first device, or training and setting of a third party and deploying on the first device, which is not limited in the present application.

[0021] Through the implementation manner, the first device can effectively obtain the information fused from the transmission information of the first cell and the transmission information of the neighboring cell of the first cell.

[0022] In a possible implementation manner, the method can further include: the first device receives target transmission information of the at least one second cell, the target transmission information of the second cell being obtained by fusion processing based on the transmission information of the second cell and the transmission information of at least one cell neighboring the second cell in the first time period; and the first device performs decision based on the transmission information of the first cell and the target transmission information of the first cell and the target transmission information of the at least one second cell, by using the set decision network model, to obtain channel access information of the first cell.

[0023] In the embodiments of the present application, the channel access information can include, but is not limited to, one or more of the following:

[0024] a contention window size, a carrier sensing threshold, an access channel result, a modulation and coding scheme, a channel aggregation result, or a channel prediction result.

[0025] Through the implementation manner, the first device can effectively obtain the channel access information of the first cell, and then perform transmission based on the channel access information, which can effectively improve the transmission performance, and in turn reduce the tail delay of transmission and the communication overhead of the network.

[0026] In a possible implementation manner, the method further includes: the first device trains the set fusion network model and updates the parameters of the set fusion network model based on one or more of the following information:

[0027] the transmission information of the first cell, the transmission information of the at least one second cell, or the target transmission information of the first cell.

[0028] Through the implementation manner, the first device can effectively obtain a more accurate fusion network model, which can improve the accuracy and reliability of the fusion processing.

[0029] In a possible implementation manner, the method can further include: the first device trains the set decision network model by using a reinforcement learning method and updates the parameters of the set decision network model by using a reward function, based on one or more of the following information:

[0030] transmission information of the first cell, target transmission information of the first cell, target transmission information of the at least one second cell, or the decided channel access information;

[0031] The first device sends the updated parameters of the set decision network model to the at least one second device.

[0032] In the embodiments of the present application, the reward function can satisfy the following formula:

[0033] Wherein, condition one is that the transmission performance (such as throughput, packet loss rate) realized by the channel parameter information of the first cell output by the set decision network model is not weaker than the transmission performance (such as throughput, packet loss rate) realized by using the Wi-Fi DCF method; R represents the reward value, which can be used to optimize the parameters of the set decision network model; CDF1 represents the tail delay realized by the channel access information of the first cell obtained by using the Wi-Fi DCF method, and CDF2 represents the tail delay realized by outputting the channel access information of the first cell by using the set decision network model.

[0034] Through the implementation mode, the first device can effectively obtain a more accurate decision network model, so as to improve the accuracy and reliability of the decision processing (i.e., determining the channel access information).

[0035] In a possible implementation mode, the first device obtains the transmission information of the first cell served by the first device, which can include but is not limited to the following modes:

[0036] Mode one: the first device itself statistically obtains the transmission information of the first cell in the current first time period.

[0037] Mode two: the first device receives the transmission information reported by the at least one second device in the current first time period; then the first device calculates the transmission information of the first cell based on the transmission information of the at least one second device; wherein the at least one second device is a non-access device in the first cell, and the reporting mode of the at least one second device can be but is not limited to any one of the following:

[0038] Active reporting, periodic reporting, or first device triggered reporting.

[0039] For the first device triggered reporting mode, the first device can send a trigger frame to the at least one second device, and the at least one second device reports the corresponding transmission information to the first device after receiving the trigger frame.

[0040] Through the implementation mode, the first device can effectively obtain the transmission information of the first cell.

[0041] In a possible implementation, the transmission information reported by the second device includes information of a time delay, and the information of the time delay can include one or more of the following:

[0042] segment information of the time delay, an index of a segment where a tail time delay is located, a number of data packets transmitted on each segment, or a time delay of each data packet;

[0043] The time delay includes a time delay of at least one data packet, and the time delay of the at least one data packet includes a time delay of 95% of the data packets that is less than the tail time delay. The time delay of each data packet can include, but is not limited to, a queuing time delay of the data packet and / or an access time delay of the data packet.

[0044] If the segment information of the time delay indicates uniform segmentation, the segment information of the time delay can include at least one of the following:

[0045] a number of segments, a maximum value of the time delay, or a minimum value of the time delay;

[0046] In the foregoing, the maximum value and / or the minimum value of the time delay can correspond to a total maximum value and / or a total minimum value of the time delay, or can correspond to a maximum value and / or a minimum value of a time delay of any one segment.

[0047] If the segment information of the time delay indicates non-uniform segmentation, the segment information of the time delay can include at least one of the following:

[0048] a number of segments, a maximum value of a time delay corresponding to each segment, or a minimum value of a time delay corresponding to each segment.

[0049] By means of the implementation, the first device can effectively obtain the information of the time delay of the second device, and thus can effectively obtain the time delay distribution information (i.e., a time delay distribution of data packets transmitted by the second device) of the second device.

[0050] In a second aspect, a communication method is provided. The method can be applied to a second device, or a component (for example, a processor, a chip, or a chip system) of the second device, or a logic node, a logic module, or software capable of realizing all or part of the function of the second device, or an apparatus used in conjunction with the second device. For example, the method is applied to the second device, and the method includes: receiving, by the second device, target transmission information of a first cell served by a first device, the target transmission information of the first cell being obtained based on transmission information of the first cell and transmission information of at least one second cell adjacent to the first cell; and determining, by the second device, channel access information of the second device based on the target transmission information of the first cell.

[0051] In the embodiments of the present application, the first device can be an access point (for example, an AP or an AP MLD), the second device can be a non-access station (for example, a Non-AP STA or a Non-AP STA MLD) in the first cell, or a relay node in the first cell (or a relay node serving the first cell), which can refer to a node or device with access and / or forwarding functions. The first cell served by the first device can be referred to as a first basic service set (BSS) (or simply BSS1); the at least one second cell adjacent to the first BSS can be referred to as a neighbor BSS of the first BSS or an adjacent BSS.

[0052] In the above, the transmission information of the first cell (or the transmission information of the second cell) can include but is not limited to one or more of the following:

[0053] information of a delay, a tail delay, a contention window size, a throughput, or a packet loss rate;

[0054] In the above, the information of the delay can be the information of the delay reported by each second device in the first cell, for example, one or more of the following: segmented information of the delay of the second device, an index of a segment where the tail delay is located, a number of data packets transmitted on each segment, or a delay of each data packet.

[0055] In the above, the delay includes a delay of at least one data packet, and the delay of the at least one data packet includes a delay of 95% of the data packets being less than the tail delay; the delay of each data packet can include but is not limited to a queuing delay of the data packet and / or an access delay of the data packet.

[0056] In the embodiments of the present application, the queuing delay of the data packet can refer to the time length from when the data packet enters the buffer / queue to when the transmission begins. The access delay of the data packet can refer to the time length from when the data packet begins to transmit to when the transmission is successful. The queuing delay and the access delay of the data packet (i.e., the sum of the queuing delay and the access delay of the data packet) can refer to the time length from when the data packet enters the buffer / queue to when the transmission is successful.

[0057] In the present application, the second device obtains the target transmission information of the first cell. Since the target transmission information of the first cell (i.e., the fusion information) is obtained based on the transmission information of the first cell and the transmission information of at least one second cell (i.e., a neighboring cell of the first cell), the second device can determine more accurate and reliable channel access information of the second device based on the target transmission information of the first cell. Subsequently, the second device performs transmission based on the channel access information, and the transmission performance can be effectively improved, and the tail delay of the transmission can be effectively improved.

[0058] In a possible implementation, the method further includes: receiving, by the second device, the updated parameters of the set decision network model; and updating, by the second device, the set decision network model based on the updated parameters of the set decision network model.

[0059] By this implementation, the second device can effectively obtain a more accurate decision network model, thereby improving the accuracy and reliability of the decision processing.

[0060] In a possible implementation, the method further includes: obtaining, by the second device, transmission information of the second device in a first time period (which can be referred to as statistical information of the second device), and receiving, by the second device, target transmission information of the at least one second cell from the first device, wherein the target transmission information of the second cell (i.e., fusion information of the second cell) is obtained by fusing the transmission information of the second cell and the transmission information of at least one cell adjacent to the second cell in the first time period.

[0061] Then, determining, by the second device, the channel access information of the first cell based on the target transmission information of the first cell can include: determining, by the second device, the channel access information of the second device by the set decision network model based on the transmission information of the second device in the first time period, the target transmission information of the first cell, and the target transmission information of the at least one second cell.

[0062] In the embodiments of the present application, the channel access information can include, but is not limited to, one or more of the following:

[0063] a contention window size, a carrier sensing threshold, an access channel result, a modulation and coding scheme, a channel aggregation result, or a channel prediction result.

[0064] By this implementation, the second device can effectively obtain the channel access information of the second device, and then the second device can effectively improve the transmission performance by transmitting based on the channel access information, thereby reducing the tail latency of the transmission of the second device.

[0065] In a possible implementation, the method further includes: reporting, by the second device, the transmission information of the second device (which can also be referred to as statistical information of the second device) to the first device.

[0066] In the embodiments of the present application, the manner in which the second device reports the transmission information of the second device to the first device can be, but is not limited to, any one of the following:

[0067] active reporting, periodic reporting, or first device triggered reporting.

[0068] In the manner of triggering the reporting by the first device, the second device can receive a trigger frame sent by the first device, and report the transmission information of the second device to the first device based on the trigger frame.

[0069] By this implementation, the first device can effectively obtain the transmission information of the second device in the first cell.

[0070] In a possible implementation, the transmission information reported by the second device includes information of a time delay, which can include one or more of the following:

[0071] segmented information of the time delay, an index of a segment where a tail delay is located, a number of data packets transmitted in each segment, or a time delay of each data packet; the time delay includes a time delay of at least one data packet; the time delay of the at least one data packet includes a time delay of 95% of the data packet that is less than the tail delay; the time delay of each data packet can include, but is not limited to, a queuing time delay of the data packet and / or an access time delay of the data packet.

[0072] If the segmented information of the time delay indicates uniform segmentation, the segmented information of the time delay can include at least one of the following:

[0073] a number of segments, a maximum value of the time delay, or a minimum value of the time delay.

[0074] In the above, the maximum value and / or the minimum value of the time delay can correspond to a total maximum value and / or a total minimum value of the time delay, or can correspond to a maximum value and / or a minimum value of a time delay of any segment.

[0075] If the segmented information of the time delay indicates non-uniform segmentation, the segmented information of the time delay can include at least one of the following:

[0076] a number of segments, a maximum value of the time delay corresponding to each segment, or a minimum value of the time delay corresponding to each segment.

[0077] By this implementation, the first device can effectively obtain the information of the time delay of the second device, and thus can effectively obtain the distribution information of the time delay of the second device (i.e., the distribution of the time delay of the data packet transmitted by the second device).

[0078] In a third aspect, the present application also provides a communication apparatus, which is the first device or a chip corresponding to the first device. The communication apparatus has the functions of the first aspect and any possible implementation manner thereof. The communication apparatus can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the above functions.

[0079] In one design, the communication device includes a processor configured to support the communication device in performing the corresponding functions of the first device in the methods described above. The communication device can also include a memory coupled with the processor, the memory storing program instructions and data for the communication device. Optionally, the communication device includes an interface circuitry for supporting communication between the communication device and other devices, for example, receiving and transmitting data or signals. The communication interface can be, for example, a transceiver, a circuit, a bus, a module, or another type of communication interface.

[0080] In one design, the communication device includes corresponding functional modules for implementing the steps of the above methods. The functions can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.

[0081] In one design, the communication device includes a processing unit and a communication unit, which can perform the corresponding functions in the above method examples, as described in the method provided in the first aspect, which will not be repeated here.

[0082] In the fourth aspect, the present application also provides a communication device, which is a chip corresponding to the second device. The communication device has the functions of the above second aspect and any possible implementation manner thereof. The communication device can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the functions described above.

[0083] In one design, the communication device includes a processor configured to support the communication device in performing the corresponding functions of the second device in the methods described above. The communication device can also include a memory coupled with the processor, the memory storing program instructions and data for the communication device. Optionally, the communication device includes an interface circuitry for supporting communication between the communication device and other devices, for example, receiving and transmitting data or signals. The communication interface can be, for example, a transceiver, a circuit, a bus, a module, or another type of communication interface.

[0084] In one design, the communication device includes corresponding functional modules for implementing the steps of the above methods. The functions can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.

[0085] In one design, the communication device includes a processing unit and a communication unit, which can perform the corresponding functions in the above method examples, as described in the method provided in the second aspect, which will not be repeated here.

[0086] In a fifth aspect, a communication apparatus is provided, which comprises a processor and an interface circuit, the interface circuit being configured to receive signals from other communication apparatuses outside the communication apparatus and transmit the signals to the processor or send signals from the processor to other communication apparatuses outside the communication apparatus, and the processor being configured to implement the method in the first aspect and any possible implementation thereof by means of a logic circuit or by executing code instructions.

[0087] In a sixth aspect, a communication apparatus is provided, which comprises a processor and an interface circuit, the interface circuit being configured to receive signals from other communication apparatuses outside the communication apparatus and transmit the signals to the processor or send signals from the processor to other communication apparatuses outside the communication apparatus, and the processor being configured to implement the method in the second aspect and any possible implementation thereof by means of a logic circuit or by executing code instructions.

[0088] In a seventh aspect, a computer readable storage medium is provided, which stores a computer program or instructions, when the computer program or instructions are executed by a processor, the method in any one of the first aspect and the second aspect and any possible implementation thereof is implemented.

[0089] In an eighth aspect, a computer program product is provided, which stores instructions, when the instructions are run by a processor, the method in any one of the first aspect and the second aspect and any possible implementation thereof is implemented.

[0090] In a ninth aspect, a chip system is provided, which comprises a processor and can further comprise a memory, and is configured to implement the method in any one of the first aspect and the second aspect and any possible implementation thereof. The chip system can be composed of a chip or can comprise a chip and other discrete devices.

[0091] In a tenth aspect, a communication system is provided, which comprises the first device in the first aspect and the second device in the second aspect.

[0092] It should be noted that the technical effects achieved by the third aspect to the tenth aspect or any possible implementation of the third aspect to the tenth aspect can be described with reference to the technical effects achieved by the first aspect and the second aspect or any possible implementation of the first aspect and the second aspect, which will not be described herein. BRIEF DESCRIPTION OF DRAWINGS

[0093] FIG. 1 is a communication system architecture diagram of a WLAN to which the method of the embodiments of the present application can be applied;

[0094] Figure 2 is a flow diagram of a communication method according to an embodiment of the present application;

[0095] Figure 3A is a flow diagram of a method according to an embodiment of the present application;

[0096] Figure 3B is a diagram of a timeline corresponding to the execution of multiple processes according to an embodiment of the present application;

[0097] Figure 4 is a diagram of a structure of a fusion network model according to an embodiment of the present application;

[0098] Figure 5A is a diagram of a structure of a beacon frame carrying statistical information according to an embodiment of the present application;

[0099] Figure 5B is a diagram of a format of a control subfield carrying statistical information according to an embodiment of the present application;

[0100] Figure 6A is a diagram of a structure of a beacon frame carrying a decision network model and / or fusion information according to an embodiment of the present application;

[0101] Figure 6B is a diagram of a format of a control subfield carrying a decision network model and / or fusion information according to an embodiment of the present application;

[0102] Figure 6C is a diagram of a structure of a trigger frame carrying a decision network model and / or fusion information according to an embodiment of the present application;

[0103] Figure 6D is a diagram of a structure of a BAR frame carrying a decision network model and / or fusion information according to an embodiment of the present application;

[0104] Figure 7 is a diagram of a structure of a decision network model according to an embodiment of the present application;

[0105] Figure 8 is a flow diagram of a method according to an embodiment of the present application;

[0106] Figure 9 is a diagram of a structure of a BA frame carrying statistical information of a STA according to an embodiment of the present application;

[0107] Figure 10A is a diagram of a structure of statistical information according to an embodiment of the present application;

[0108] Figure 10B is a diagram of a structure of another type of statistical information according to an embodiment of the present application;

[0109] Figure 10C is a diagram of a structure of yet another type of statistical information according to an embodiment of the present application;

[0110] Figure 10D is a diagram of a distribution of a time delay according to an embodiment of the present application;

[0111] FIG. 11 is a structural schematic diagram of a communication device according to an embodiment of the present application;

[0112] FIG. 12 is a structural schematic diagram of another communication device according to an embodiment of the present application;

[0113] FIG. 13 is a structural schematic diagram of a chip device according to an embodiment of the present application. DETAILED DESCRIPTION

[0114] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0115] First, the related technologies, words and features involved in the embodiments of the present application will be explained. It should be noted that these explanations are to make the embodiments of the present application easier to be understood, and should not be regarded as limitations on the scope of protection required by the present application.

[0116] 1) basic service set (BSS), generally refers to the range covered by an access point (AP), and stations (STAs) under the AP can communicate with each other.

[0117] 2) overlapping BSS (OBSS), which represents other BSSs that have overlapping channels with the current BSS. The OBSSs can be the same channel or different channels.

[0118] 3) Channel, in a wireless local area network (WLAN), a channel is usually divided into a primary channel and a secondary channel, the primary channel is a working channel common to all stations in a basic service set (BSS), wherein the secondary channel can include one or more sub-channels. In an example, if 20MHz is taken as the basic bandwidth unit for division, when the channel bandwidth is 20MHz, there is only one primary channel with a bandwidth of 20MHz; when the channel bandwidth is greater than 20MHz, one channel with a bandwidth of 20MHz is taken as the primary channel, and the remaining one or more 20MHz channels are taken as secondary channels. For example, when the channel bandwidth is 80MHz, the channel is numbered as channel 1 to channel 4 in sequence, and each serial number represents a 20MHz channel; wherein channel 1 represents a 20MHz primary channel, channel 2 represents a 20MHz secondary channel (S20), and a 40MHz secondary channel (S40) includes two 20MHz sub-channels, which are channel 3 and channel 4.

[0119] 4) Tail latency, which can refer to the 95th percentile of the latency distribution. In an embodiment of the present application, it is assumed that there are n data packets in total, n is a positive integer, and the latencies of the n data packets are sorted in ascending order of value, that is, there are n bits, wherein the latency of n*95% data packets is less than a latency, and the bit where the latency is located can be referred to as the 95th percentile, that is, the latency can be taken as the tail latency. In the present application, the tail latency can be a latency among the n data packet latencies, or can not be a latency among the n data packet latencies.

[0120] For example, there are 100 data packet latencies in total, which are sorted in ascending order of value from left to right, and the latency of the 96th data packet from the left can be referred to as the tail latency.

[0121] However, if n*95% is not an integer when there are n data packet latencies in total, the tail latency can be taken as the latency of the th data packet by using the upward rounding method; wherein is the upward rounding symbol.

[0122] For example, there are 90 data packet latencies in total, which are sorted in ascending order of value, and the latency of the The delay of the 86th bit, i.e., the tail delay.

[0123] It should be noted that as the network optimization index improves, the percentage (95%) corresponding to the tail delay described above can change, for example, it can be lower or higher than 95%.

[0124] 3) Throughput, which can be used to measure the key index of the overall performance of the network under one or more cells.

[0125] 4) Packet loss rate, which can refer to the ratio of data that is not successfully transmitted to the destination due to various reasons during network transmission. The high or low packet loss rate will usually directly affect the network performance, data transmission speed and stability.

[0126] 5) Link, which can refer to a transmission link between one network device and another network device. In this application, the first link refers to the transmission link in which the first access point AP1 participates, which can include uplink (UL) and downlink (DL), for example. The second link refers to the link in which the second access point AP2 participates concurrently with the first link, which can include uplink and downlink, device-to-device (D2D) link, in one example, the first AP1 is the master access point AP, and the second AP2 is the adjacent AP (or slave access point AP). It can be understood that in the entire network, other links such as the third link, the fourth link, etc. can also be included, which are not listed one by one here.

[0127] It should be noted that "at least one" in the embodiments of the present application means one or more, and "multiple" means two or more. The "and / or" describes the association relationship between the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including single item or any combination of multiple items. For example, at least one of a, b, or c, can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0128] In addition, unless otherwise stated, the terms "first", "second", etc. or "1", "2", etc. (except for special cases where the numerical value is represented) used in the embodiments of the present application are used to distinguish a plurality of objects, and are not used to limit the size, content, order, timing, priority or importance of the plurality of objects. For example, the first information and the second information are only used to distinguish different phase information, and do not represent the difference in size, priority or importance of the two information.

[0129] It should be noted that in the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or having more advantages than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner.

[0130] In the description of the embodiments of the present application, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device. In addition, the term "for indicating" mentioned in the description of the embodiments of the present application can include "for directly indicating" and "for indirectly indicating". When describing that certain indication information is used to indicate A, it can include that the indication information directly indicates A or indirectly indicates A, and it does not mean that A must be carried in the indication information.

[0131] The foregoing introduces some language / terminology related to the embodiments of the present application, and the following introduces the technical background related to the embodiments of the present application.

[0132] Wireless communication is developing rapidly, and the 5th-generation (5G) mobile communication system and the Wi-Fi 7 standard have gradually been commercialized, and the next generation of wireless technology and standardization is being carried out worldwide. Wireless communication has penetrated into all aspects of daily life and work, and has become an indispensable part. With the rapid growth of the number of intelligent terminal devices and the popularity of internet of things (IoT) devices, new wireless applications such as virtual reality, augmented reality and holographic images have emerged in an endless stream.

[0133] New radio technologies, new terminal devices, and new wireless applications make wireless networks more complex than ever. It is foreseeable that future wireless networks will be even more complex. In order to combat the high complexity development trend of wireless networks, artificial intelligence (AI) has become the industry consensus as an effective tool for wireless network design and management. Currently, AI-based Wi-Fi network optimization methods have been discussed in standards. In addition, AI has been widely used in Wi-Fi network media access control (MAC) resource management, such as channel access, rate adaptation, channel aggregation, channel prediction, roaming, and the like.

[0134] Future Wi-Fi proposes higher targets for the optimization of network parameters (such as tail latency and packet error rate (PER)) in single basic service set (BSS) or overlapping basic service set (OBSS) scenarios, especially for the improvement of tail latency in OBSS scenarios. Therefore, how to effectively improve the performance of tail latency in network transmission scenarios is one of the problems that need to be solved at present.

[0135] Based on the above problems, the embodiments of the present application propose a communication method and device, which can effectively improve the performance of tail latency in network transmission. The method and device are based on the same inventive concept. Since the principles of the method and device for solving problems are similar, the implementation of the device and the method can be mutually referred to, and the repeated parts will not be described again.

[0136] The embodiments of the present application can be applicable to the scenario of WLAN, for example, can be applicable to the institute of electrical and electronics engineers (IEEE) 802.11 system standard, such as 802.11be standard, Wi-Fi 7 or extremely high throughput (EHT), 802.11bf, or 802.11be next generation, such as Wi-Fi 8 or more next generation standard. Or the embodiments of the present application can also be applicable to wireless local area network systems such as internet of things (IoT) networks or vehicle to X (V2X) networks. Of course, the embodiments of the present application can also be applicable to other possible communication systems, for example, worldwide interoperability for microwave access (WiMAX) communication systems, 5G communication systems, and future communication systems.

[0137] Hereinafter, the scenario to which the embodiments of the present application can be applied is taken as an example. It should be understood that the WLAN starts from the 802.11a / g standard, goes through 802.11n, 802.11ac, 802.11ax, and 802.11be which is currently being discussed. Among them, 802.11n can also be referred to as high throughput (HT); 802.11ac can also be referred to as very high throughput (VHT); 802.11ax can also be referred to as high efficiency (HE) or Wi-Fi 6; 802.11be can also be referred to as EHT or Wi-Fi 7, and the standards before HT, such as 802.11a / b / g, etc. can be collectively referred to as Non-HT.

[0138] FIG. 1 shows a communication system architecture diagram of a WLAN to which the embodiments of the present application can be applied. Referring to FIG. 1, the communication system includes an access point AP1, an access point AP2, and further includes a station STA1, a station STA2, and a station STA3 associated with the access point AP1, and a station STA4, a station STA5, and a station STA6 associated with the access point AP2. Among them, the access point AP1, the station STA1, the station STA2, and the station STA3 can constitute a basic service set BSS1; the access point AP2, the station STA4, the station STA5, and the station STA6 can constitute a basic service set BSS2. In one example, the first link can be an uplink or a downlink between the AP1 and the stations associated with the AP1; the second link can be an uplink or a downlink between the AP2 and the stations associated with the AP2, and can also be a D2D link between any two stations in the BSS2, for example, a D2D link between the STA4 and the STA5. It should be noted that in addition, the embodiments of the present application can also be applied to the communication between APs, for example, the APs can communicate with each other through a distributed system (DS), and the embodiments of the present application can also be applied to the communication between STAs. It should be understood that the number of access points AP and stations STA shown in FIG. 1 is only an example, and in actual application, the number of access points AP and / or stations STA can be more or less.

[0139] It should be noted that the communication system shown in FIG. 1 does not constitute a limitation of the communication system to which the embodiments of the present application can be applied. Therefore, the method provided by the embodiments of the present application is applicable to various wireless communication systems, for example, a Wi-Fi system, a 5th generation (5G) communication system, or various mobile communication systems in the future, which are not limited by the present application.

[0140] The access point can be an access point for a terminal device (such as a mobile phone) to enter a wired (or wireless) network, and is mainly deployed in a home, a building, and a park, and has a typical coverage radius of tens of meters to hundreds of meters, and can also be deployed outdoors. The access point is equivalent to a bridge connecting a wired network and a wireless network, and mainly functions to connect various wireless network clients together and then access the wireless network to an Ethernet. Specifically, the access point can be a terminal device (such as a mobile phone) or a network device (such as a router) with a Wi-Fi chip, or a wireless communication chip, a wireless sensor, or a wireless communication terminal with an access point function. The access point can be a device supporting the 802.11be standard. The access point can also be a device supporting various wireless local area network (WLAN) standards of the 802.11 family, such as 802.11ax, 802.11ac, 802.11ad, 802.11ay, 802.11n, 802.11g, 802.11b, 802.11a, and the next generation of 802.11be.

[0141] The station can be a wireless communication chip, a wireless sensor, or a wireless communication terminal, and can also be referred to as a user. For example, the station can be a mobile phone supporting Wi-Fi communication function, a tablet computer supporting Wi-Fi communication function, a set-top box supporting Wi-Fi communication function, a smart television supporting Wi-Fi communication function, a smart wearable device supporting Wi-Fi communication function, a vehicle-mounted communication device supporting Wi-Fi communication function, and a computer supporting Wi-Fi communication function, and the like. Optionally, the station can support the 802.11be standard. The station can also support various wireless local area network (WLAN) standards of the 802.11 family, such as 802.11ax, 802.11ac, 802.11n, 802.11g, 802.11b, 802.11a, the next generation of 802.11be, and the like.

[0142] For example, the access point and the station can be devices applied to the Internet of Vehicles, Internet of Things (IoT) nodes, sensors, smart cameras in smart homes, smart remote controllers, smart water and electricity meters, and sensors in smart cities, and the like.

[0143] The AP and STA involved in the embodiments of the present application can be APs and STAs applicable to the IEEE 802.11 system standard. The AP is a device deployed in a wireless communication network to provide wireless communication functions for its associated STAs. The AP can be used as the hub of the communication system, and is usually a network-side product supporting the MAC and PHY of the 802.11 system standard, for example, a base station, a router, a gateway, a repeater, a communication server, a switch, or a bridge, and the like. The base station can include various forms of macro base stations, micro base stations, relay stations, and the like. For the sake of convenience, the above-mentioned devices are collectively referred to as APs. The STA is usually a terminal product supporting the MAC and PHY of the 802.11 system standard, for example, a mobile phone, a notebook computer, and the like.

[0144] The embodiments of the present application can be applicable to but not limited to the OBSS scenario. For the single BSS scenario, the single BSS can also be regarded as a special case of the OBSS. For example, when the AP1 has no neighbor / adjacent access point or cell, 0 can be used instead of the information of the adjacent BSS to input into the neural network (such as the fusion network model) to obtain the fusion information of the BSS served by the AP1.

[0145] The communication system architecture or network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It can be known by those skilled in the art that, with the evolution of the communication system or network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application can also be applicable to similar technical problems.

[0146] In the absence of special description in this paper, the first device and the second device are described as the execution subject.

[0147] The first device (or the second device) can be a network device, or a device with network device function, or a device implementing network device function. For example, the first device (or the second device) is an access network device (such as an AP or an AP multi-link device MLD), or the first device (or the second device) can be a module (such as a chip or a circuit, etc.) in the access network device (such as an AP or an AP MLD), and can also be a module or unit (such as a CU or a DU or a RU), a logic module, or software, etc. that implements the access network device (such as an AP or an AP MLD) in whole or in part.

[0148] Or, the "first device" (or "second device") can be a terminal, or a device with terminal function, or a device implementing terminal function. For example, the "first device" (or "second device") can be a terminal (such as a Non-AP STA or a Non-AP MLD), or a module (such as a chip or a circuit, etc.) in the terminal (such as a Non-AP STA or a Non-AP MLD), or a module or unit implementing the terminal (such as a Non-AP STA or a Non-AP MLD) in whole or in part, or a logic module or software, etc. Or, the "first device" (or "second device") can be a core network device. Or, the "first device" (or "second device") can be a server, such as a cloud server, etc. Or, the "first device" (or "second device") can also be a device or apparatus with sensing and / or positioning capabilities, or a device or apparatus capable of performing artificial intelligence tasks. The device capable of performing artificial intelligence tasks can also be referred to as an artificial intelligence task performing device.

[0149] Hereinafter, the "first device" is taken as a network device (such as an AP or an AP MLD), and the "second device" is taken as a terminal (such as a Non-AP STA or a Non-AP MLD) as an example to introduce the solutions of the embodiments of the present application. In addition, the "first device" can be replaced by "first apparatus", or "first communication apparatus", or "initiating device", etc., and the "second device" can be replaced by "second apparatus", or "second communication apparatus", or "responding device", etc.

[0150] In the present application, "sending" and "receiving" represent the direction of information / data / signal transmission. For example, "sending information to XX" can be understood as that the destination of the information is XX, and "sending information" can include direct sending and indirect sending through other units or modules. "Receiving information from YY" can be understood as that the source of the information is YY, and "receiving information" can include direct receiving from YY and indirect receiving from YY through other units or modules. In addition, "sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, "sending" or "receiving" can be performed between devices, for example, between a base station and a terminal through an air interface, and "sending" or "receiving" can also be performed within a device, for example, between components, modules, chips, software modules or hardware modules in the device through a bus, wire or interface.

[0151] It should be understood that, in the present application, the names of various messages (or information) in the following various procedures are only examples, and as the communication technology evolves, the names of various messages (or information, etc.) in the following various procedures can change, but as long as the meaning is the same as the function or meaning of the message (or information, etc.) in the present application, it falls within the protection scope of the present application. For example, "first cell" can be replaced by "first BSS", "second cell" can be replaced by "second BSS"; "transmission information of the first cell" can be replaced by "observation information of the first cell", or "observation data of the first cell", etc.; "target transmission information of the first cell" can be replaced by "fusion information of the first cell". In addition, some names "information" involved in the present application can be replaced by "frame" or "field", for example, the newly added "statistical information" in the frame can be replaced by "statistical field", etc. The information involved in the present application can be replaced according to the foregoing replacement form, which will not be listed one by one here.

[0152] The scheme of the embodiments of the present application will be introduced below.

[0153] The embodiments of the present application provide a communication method, which can be applied to but not limited to the communication system architecture shown in FIG. 1. The method can be executed by a first device (which can also be a second device), or a module (such as a processor, a chip, or a chip system, etc.) of the first device (which can also be the second device), or a logic node, a logic module or software capable of realizing all or part of the functions of the first device (which can also be the second device); in addition, the specific structure of the execution subject (the first device, the second device) of the method provided by the embodiments of the present application and the number of each execution subject (the first device, the second device) are not limited specifically, as long as the program code recorded with the method provided by the embodiments of the present application can be run to communicate according to the method provided by the embodiments of the present application. In order to facilitate description, the following will be introduced as an example by taking the interaction between the first device and the second device. The order of the steps in the following various procedures is only an example, and in actual application, the order of the steps in each procedure can be adjusted, and all or part of the steps described below can be adaptively executed.

[0154] Referring to FIG. 2, the method provided by the embodiments of the present application can include the following:

[0155] S201: The first device acquires transmission information of a first cell served by the first device and transmission information of at least one second cell; the at least one second cell is adjacent to the first cell.

[0156] In the embodiments of the present application, the first device can act as an access point (for example, an AP or an AP MLD), and the first cell served by the first device can be referred to as a first basic service set (BSS, or simply BSS1); the at least one second cell adjacent to the first BSS can be referred to as a neighbor BSS or an adjacent BSS of the first BSS.

[0157] In the above, the transmission information of the first cell (or the transmission information of the second cell) can include but is not limited to include one or more of the following:

[0158] information of a latency, a tail latency, a contention window size, a throughput, or a packet loss rate;

[0159] The information of the latency can be information of a latency reported by each second device in the first cell, for example, one or more of segmented information of a latency of a second device, an index of a segment in which a tail latency is located, a number of data packets transmitted on each segment, or a latency of each data packet.

[0160] In the above, the latency includes a latency of at least one data packet, and a latency of 95% of the data packets in the at least one data packet is less than the tail latency; the latency of each data packet can include but is not limited to a queuing latency of the data packet and / or an access latency of the data packet.

[0161] In the embodiments of the present application, the queuing latency of a data packet can refer to a time length from when the data packet enters a buffer / queue to when transmission begins. The access latency of a data packet can refer to a time length from when the data packet begins transmission to when transmission is successful. The queuing latency and the access latency of a data packet (i.e., the sum of the queuing latency and the access latency of the data packet) can refer to a time length from when the data packet enters the buffer / queue to when transmission is successful.

[0162] In the embodiments of the present application, the first device obtains transmission information of a first cell served by the first device (the transmission information of the first cell can also be referred to as observation information or observation data of the first cell), which can include but is not limited to the following several implementation manners:

[0163] Manner one: The first device itself statistically obtains transmission information of the first cell in a current first time period.

[0164] For example, taking the access latency of the first cell obtained by the first device as an example, the first device is AP1, and the first cell is BSS1. Assuming that BSS1 includes N STAs, N being a positive integer; AP1 transmits with the N STAs respectively, and AP1 statistically obtains access latencies of the N STAs in a current first time period (i.e., the access latency of a STA is a time length from when a data packet transmitted by the STA begins transmission to when transmission is successful), and then calculates the access latency of BSS1 according to the access latencies of the N STAs.

[0165] Mode two: at least one second device reports its own transmission information (which is equivalent to the statistical information of the second device) in the current first time period to the first device; correspondingly, the first device receives the transmission information reported by the at least one second device; then, the first device calculates the transmission information of the first cell based on the transmission information of the at least one second device.

[0166] In the embodiments of the present application, the second device can be a non-access point station (for example, a Non-AP STA or a Non-AP MLD) in the first cell, and the second device can also be a relay node (or a relay node serving the first cell) in the first cell. The relay node can refer to a node or device with access and / or forwarding functions.

[0167] The mode in which the at least one second device reports its own transmission information to the first device can be, but is not limited to, any one of the following modes:

[0168] (1) The second device actively reports the transmission information to the first device;

[0169] (2) The second device periodically reports the transmission information to the first device;

[0170] (3) The second device reports the transmission information to the first device upon being triggered by the first device.

[0171] In the embodiments of the present application, the second device reports the transmission information to the first device upon being triggered by the first device, which can include that the first device sends a trigger frame to the second device, the trigger frame being used to trigger the second device to report the transmission information in the current first time period; after receiving the trigger frame, the second device reports the transmission information in the current first time period to the first device.

[0172] In a possible implementation manner, the transmission information (which is equivalent to the statistical information of the second device) reported by the second device can include information of a time delay, and the information of the time delay can include one or more of the following:

[0173] segmented information of the time delay, an index of a segment where a tail time delay is located, a number of data packets transmitted on each segment, or a time delay of each data packet;

[0174] The time delay includes a time delay of at least one data packet, and the time delay of the at least one data packet includes a time delay of 95% of the data packets being less than the tail time delay. The time delay of each data packet can include, but is not limited to, a queuing time delay of the data packet and / or an access time delay of the data packet.

[0175] If the segmented information of the time delay indicates uniform segmentation, the segmented information of the time delay can include at least one of the following:

[0176] the maximum value of the latency, or the minimum value of the latency.

[0177] In the above, the maximum value and / or the minimum value of the latency can correspond to the maximum value and / or the minimum value of the total latency, or can correspond to the maximum value and / or the minimum value of the latency of any one segment.

[0178] If the segment information of the latency indicates non-uniform segmentation, the segment information of the latency can include at least one of the following:

[0179] the number of segments, the maximum value of the latency corresponding to each segment, or the minimum value of the latency corresponding to each segment.

[0180] S202: The first device obtains target transmission information of the first cell based on the transmission information of the first cell and the transmission information of the at least one second cell (which can be referred to as fusion information of the first cell).

[0181] In a possible implementation, the first device obtains target transmission information of the first cell based on the transmission information of the first cell and the transmission information of the at least one second cell, including: the first device performs fusion processing on the transmission information of the first cell and the transmission information of the at least one second cell through a set fusion network model to obtain the target transmission information of the first cell (which can also be referred to as fusion information or fusion data of the first cell).

[0182] In the embodiments of the present application, the set fusion network model can be obtained by training and setting of the first device, or can be obtained by training and setting of a network device (such as a cloud server) and deployed on the first device side, or can be obtained by training and setting of other third parties and deployed on the first device side, which is not limited in the present application.

[0183] In a possible implementation, the method of the embodiments of the present application can further include: the first device trains and updates parameters of the set fusion network model based on one or more of the following information:

[0184] the transmission information of the first cell, or the transmission information of the at least one second cell, or the target transmission information of the first cell (fusion information of the first cell).

[0185] S203: The first device sends the target transmission information of the first cell to the at least one second device. Correspondingly, the second device receives the target transmission information of the first cell served by the first device.

[0186] In the embodiments of the present application, when performing S203, the first device can send the target transmission information of the first cell (i.e., the fusion information of the first cell) in the form of broadcasting.

[0187] S204: The second device determines channel access information of the second device based on the target transmission information of the first cell.

[0188] In a possible implementation, the method can further include: the first device receives target transmission information of the at least one second cell, wherein the target transmission information of the second cell (which can also be referred to as fusion information of the second cell) is obtained by fusing transmission information of the second cell and transmission information of at least one cell adjacent to the second cell in a first time period; and then the first device can determine channel access information of the first cell based on transmission information of the first cell, the target transmission information of the first cell, and the target transmission information of the at least one second cell, by using a set decision network model.

[0189] In the embodiments of the present application, the set decision network model can be trained and set by the first device, or can be trained and set by a network device (for example, a cloud server), or can be trained and set by other third parties, which is not limited in the present application. In addition, the set fusion network model and the set decision network model can be trained and set parameters separately, or can be trained and set parameters jointly, which is not limited.

[0190] In a possible implementation, the method can further include: the first device trains the set decision network model by using a reinforcement learning method and updates parameters of the set decision network model by using a reward function, based on one or more of the following information:

[0191] the transmission information of the first cell, the target transmission information of the first cell, the target transmission information of the at least one second cell, and the determined channel access information;

[0192] Then the first device can send the updated parameters of the set decision network model to at least one second device in the first cell; and correspondingly, the at least one second device receives the updated parameters of the set decision network model sent by the first device.

[0193] Further, the at least one second device can update the set decision network model based on the updated parameters of the set decision network model.

[0194] In the embodiments of the present application, the reward function can satisfy the following formula:

[0195] Wherein, the condition one is that the transmission performance (such as throughput, or packet loss rate, etc.) realized by the channel parameter information of the first cell output by the set decision network model is not weaker than the transmission performance (such as throughput, or packet loss rate, etc.) realized by using the wireless network Wi-Fi distributed coordination function (DCF) method (current technology); R represents a reward value, which can be used to optimize the parameters of the set decision network model; CDF1 represents the tail delay realized by the channel access information of the first cell obtained by using the Wi-Fi DCF method, and CDF2 represents the tail delay realized by the channel access information of the first cell output by the set decision network model. For other cases, R = -1.

[0196] In the embodiments of the present application, based on the above steps, if the second device side has stored the set decision network model, the set decision network model can be the last used one, and can come from the first device or from a network device (such as a cloud server), then the second device can update the parameters of the set strategy network model based on the updated parameters of the set decision network model provided by the first device this time, to obtain an updated decision network model; if the second device side does not store the set decision network model, then the first device this time can send the set decision network model (including the model itself, the updated parameters of the model) to the second device.

[0197] In a possible implementation manner, the method of the embodiments of the present application can further include: the second device obtains the transmission information of the second device in the current first time period, and receives the target transmission information of the at least one second cell from the first device, wherein the target transmission information of the second cell (i.e. the fusion information of the second cell) is obtained by fusion processing the transmission information of the second cell and the transmission information of at least one cell adjacent to the second cell in the first time period.

[0198] Further, when the second device executes S204 (i.e. the second device determines the channel access information of the second device based on the target transmission information of the first cell), specifically, the second device can include: the second device determines the channel access information of the second device by the set decision network model based on the transmission information of the second device in the first time period and the target transmission information of the first cell, and the target transmission information of the at least one second cell.

[0199] In the embodiments of the present application, the above-mentioned channel access information can include but is not limited to one or more of the following:

[0200] The contention window size, the carrier sensing threshold, the access channel result, the modulation and coding scheme, the channel aggregation result, or the channel prediction result.

[0201] To sum up, the embodiment of the present application provides a communication method, which comprises: a first device obtaining transmission information of a first cell served by the first device and transmission information of at least one second cell; the at least one second cell is adjacent to the first cell; the first device obtaining target transmission information of the first cell based on the transmission information of the first cell and the transmission information of the at least one second cell; the target transmission information of the first cell is used to determine channel access information of the first cell; and the first device sending the target transmission information of the first cell to a second device. It can be known that in the method, after the first device obtains the transmission information (i.e. observation information) of the cell served by itself and the transmission information (i.e. observation information) of the adjacent cell, the target transmission information (which can also be called fusion information) of the first cell is obtained based on the transmission information of the cell and the transmission information of the adjacent cell, the target transmission information of the first cell can be used to determine more accurate and reliable channel access information of the first cell, so as to effectively improve the transmission performance in the first cell, and further reduce the tail delay of transmission and the communication overhead of the network.

[0202] The above scheme shown in FIG. 2 will be described in detail through several specific embodiments.

[0203] Embodiment one:

[0204] In the embodiment one, based on the above scheme shown in FIG. 2, the first device is AP1, the first cell is BSS1 (i.e. the current BSS), at least one second device in the first cell is taken as STA1 and STA2 and STA3 as examples, in addition, at least one second cell adjacent to the first cell is taken as BSS2 and BSS3 as examples, BSS2 is provided with access service by AP2, and BSS3 is provided with access service by AP3, and the embodiment of the present application will be described in detail. Referring to FIG. 3A, the method flow of the embodiment one comprises the following:

[0205] S301A: AP1 obtains the observation information of BSS1.

[0206] In one possible implementation, the observation information of BSS1 (an example of the transmission information of the first cell in the scheme shown in FIG. 2) can refer to the observation information of BSS1 in a first time period.

[0207] The observation information of BSS1 can comprise one or more of the information of the time delay (the information of the time delay reported by each STA in BSS1 described below), the tail delay, the contention window size, the throughput, or the packet loss rate, etc.

[0208] In the embodiment of the present application, AP1 obtains the observation information of BSS1, which can be obtained through but not limited to the following several ways:

[0209] Manner 1: AP1 obtains the observation information of BSS1 by self-statistics when communicating with all STAs in BSS1.

[0210] For example, AP1 communicates with STA1, STA2 and STA3 respectively, AP1 real-time statistics the access delay of the three STAs in the first time period (i.e. the time length from the start of STA transmission to the successful transmission of data packet), and AP1 calculates the access delay of BSS1 according to the access delay of the three STAs.

[0211] Manner 2: AP1 collects the statistics information of STAs (the example of transmission information reported by the second device in the scheme shown in FIG. 2) from all STAs (e.g. STA1, STA2 and STA3) served by AP1, and then calculates the observation information of BSS1 according to the statistics information of the STAs; wherein the statistics information of each STA (the example of transmission information reported by the second device in the scheme shown in FIG. 2) can include but not limited to the information of delay (i.e. the information of delay in the scheme shown in FIG. 2).

[0212] For example, STA1 reports delay information 1 to AP1, STA2 reports delay information 2 to AP2, and STA3 reports delay information 3 to AP1.

[0213] For example, the delay information 1 reported by STA1 includes the delay information of 100 data packets transmitted by STA1, the delay information 2 reported by STA2 includes the delay information of 100 data packets transmitted by STA2, and the delay information 3 reported by STA3 includes the delay information of 100 data packets transmitted by STA3; wherein the delay information of each data packet can include the queuing delay and / or the access delay of the data packet. Further, AP1 calculates the delay information of BSS1 according to the delay information 1, the delay information 2 and the delay information 3.

[0214] In addition, AP2 adjacent to AP1 can obtain the observation information of BSS2, and AP3 can obtain the observation information of BSS3. AP2 and AP3 can respectively refer to the manner of AP1 in S301A to obtain the observation information of the BSS served by themselves, which will not be described herein.

[0215] S302A: AP1 and adjacent APs exchange the observation information of BSS.

[0216] In the embodiments of the present application, the AP (e.g. AP1, AP2, AP3) can send the observation information of the BSS served by itself in the form of broadcast.

[0217] After AP1 interacts the observation information of BSS with the neighboring APs, AP1 can receive the observation information of neighboring BSS2 from AP2 and the observation information of neighboring BSS3 from AP3 (an example of transmission information of at least one second cell in the scheme shown in FIG. 2).

[0218] In addition, AP2 and AP3 neighboring to AP1 can perform the interaction of the observation information of BSS between the APs neighboring to themselves with reference to AP1.

[0219] For example, the BSSs neighboring to AP2 are BSS1 and BSS4, and BSS4 is provided with access services by AP4; therefore, AP2 obtains the observation information of BSS1 from AP1 and the observation information of BSS4 from AP4.

[0220] For example, the BSSs neighboring to AP3 are BSS1 and BSS5, and BSS5 is provided with access services by AP5; therefore, AP3 can obtain the observation information of BSS1 from AP1 and the observation information of BSS5 from AP5.

[0221] S303A: AP1 performs fusion processing on the observation information of BSS1 and the observation information of the neighboring BSSs (i.e., the observation information of BSS2 and the observation information of BSS3) to obtain the fusion information of BSS1.

[0222] In a possible implementation, AP1 performs fusion processing on the observation information of BSS1, the observation information of BSS2 and the observation information of BSS3 by using a set fusion network model to obtain the fusion information of BSS1.

[0223] In the embodiments of the present application, the set fusion network model described above can be obtained by training and setting of AP1 or by training and setting of a network device (such as a cloud server), and is not limited in this regard; in addition, the fusion network model can adopt, but is not limited to, the structure of an autoencoder, and is trained by minimizing the mean-square error (MSE) between the input and the output.

[0224] For example, a structure diagram of a fusion network model to which the present application can be applied is shown in FIG. 4, which includes an input layer, a fully connected (FC) layer 64, FC32, FC16, FC32, FC64, and an output layer. The numbers after the FCs can represent the number of neurons included in the fully connected layer, for example, FC64 can represent a fully connected layer with 64 neurons. The AP1 can input the observation information of the BSS1, the observation information of the neighboring BSSs (i.e., the observation information of the BSS2 and the observation information of the BSS3) into the fusion network model, and then the fusion network model outputs the fusion information for the BSS1.

[0225] Through the set fusion network model, the AP1 can effectively compress the observation information of the BSS1 and the observation information of the multiple neighboring BSSs (i.e., the observation information of the BSS2 and the observation information of the BSS3), so as to provide the two-hop information for the neighboring APs, while reducing the communication overhead.

[0226] In the above, the two-hop information of the AP can refer to the non-adjacent BSS information (such as the observation information of the BSS) obtained by the AP indirectly through the neighboring AP. For example, the BSS2 and the BSS3 are adjacent to the BSS1 respectively, but the BSS2 is not adjacent to the BSS3, so the observation information of the BSS3 provided by the AP1 to the AP2 can be referred to as the two-hop information of the AP2.

[0227] In the embodiments of the present application, the AP1 can also use a traditional method to fuse the observation information of the BSS1, the observation information of the BSS2, and the observation information of the BSS3. The traditional method can refer to a method other than AI or neural network, for example, an average method, and the like, which is not limited herein.

[0228] In addition, the AP2 and the AP3 can refer to the AP1, that is, the AP2 can fuse the observation information of the BSS2 and the observation information of the neighboring BSSs to obtain the fusion information of the BSS2.

[0229] For example, if the BBS2 served by the AP2 has the BSS1 and the BSS4 adjacent thereto, then the AP2 can fuse the observation information of the BSS1 and the observation information of the BSS4 according to the observation information of the BSS2 and the observation information of the neighboring BSS1 and the observation information of the BSS4 to obtain the fusion information of the BSS2.

[0230] The AP3 can fuse the observation information of the BSS3 and the observation information of the neighboring BSSs to obtain the fusion information of the BSS3.

[0231] For example, if the BBS3 served by the AP3 is adjacent to BSS1 and BSS5, the AP3 can obtain the observation information of BSS1 and the observation information of BSS5, and then perform fusion processing on the observation information of BSS3 and the observation information of the adjacent BSS1 and the observation information of BSS5 to obtain the fusion information of BSS3.

[0232] Specifically, the AP2 and the AP3 can perform fusion processing according to the implementation manner of the AP1 in the S303A to obtain the fusion information of BSS3, which will not be described herein again.

[0233] The S304A: the AP1 and the adjacent APs (the AP2 and the AP3) exchange the fusion information of the BSS obtained by the AP1.

[0234] In addition, the AP1 can also exchange the updated observation information of BSS1 with the adjacent APs.

[0235] In the embodiments of the present application, the AP1 can obtain the observation information of BSS1 in real time and update the previously obtained observation information of BSS1. Therefore, in the S304A, the AP1 can also exchange the updated observation information of BSS1 with the adjacent APs (the AP2 and the AP3), that is, the AP1 can exchange the fusion information obtained at present and the updated observation information of BSS1 with the adjacent APs.

[0236] The AP1 can carry the fusion information obtained by the AP1 and the updated observation information of BSS1 in the same message / information and send to the adjacent AP2 and the AP3, or the AP1 can separately send the fusion information obtained by the AP1 and the updated observation information of BSS1 to the adjacent AP2 and the AP3, which is not limited in the present application.

[0237] Similarly, the other APs (such as the AP2 and the AP3) can refer to the AP1 for implementation, which will not be described herein again.

[0238] In a possible implementation manner, when the APs exchange the fusion information obtained by the APs and / or the observation information (updated) of the BSS served by the APs, the exchange can be performed in the form of broadcast.

[0239] For example, the AP1 broadcasts the fusion information of BSS1 and the observation information (updated) of BSS1. Accordingly, the adjacent AP2 and the AP3 can receive the fusion information of BSS1 and the observation information (updated) of BSS1; wherein the observation information (updated) of BSS1 can be used for fusion processing in the next processing procedure.

[0240] Similarly, AP2 and AP3 can broadcast the observation information (updated in real time) of the BSSs they serve respectively with reference to AP1, and / or the fusion information they obtain respectively with reference to AP1, which will not be described herein again. Accordingly, AP1 can obtain the fusion information of BSS2 and the observation information (updated) of BSS2, and the fusion information of BSS3 and the observation information (updated) of BSS3, wherein the observation information (updated) of BSS2 and the observation information (updated) of BSS3 can be used for fusion processing in the next processing procedure.

[0241] Based on the above, AP1 can interact with the neighboring APs the updated observation information of BSS1 while interacting with the neighboring APs the fusion information of the BSSs it serves. Since the APs can interact with each other through management frames (such as beacon frames and the like), embodiments of the present application propose that a new information element (IE) can be defined in the management frames, which is used to carry the statistical information of the APs, and the statistical information of the APs can include the observation information (updated) of the BSSs the APs serve and / or the fusion information of the BSSs.

[0242] For example, referring to FIG. 5A, taking the beacon frame broadcasted by AP1 as an example, a field of statistical information (a new IE defined) is added in the beacon frame, and the field of statistical information can include a field of observation information and a field of fusion information, wherein the field of observation information is used to indicate / represent the observation information or observation data (updated) of BSS1, and the field of fusion information is used to indicate / represent the fusion information or fusion data of BSS1; further, the field of observation information can specifically include one or more information fields as follows:

[0243] information of delay, tail delay, contention window size, throughput, or packet loss rate.

[0244] For another example, the HT control field broadcasted by AP1 includes at least one control subfield (A-control subfield), wherein the MAC header of one control subfield (A-control subfield) carries the above-mentioned statistical information (i.e. the defined IE), and the specific format of the control subfield (A-control subfield) is shown in FIG. 5B; referring to FIG. 5B, the control subfield includes a control list and padding, the control list includes a plurality of control fields, and the control information of the first control field carries the above-mentioned statistical information (which can include the observation information (updated) of BSS1 and / or the fusion information of BSS1).

[0245] Similarly, AP2 and AP3 can also broadcast the statistical information of their own service BSS (the observation information (updated) and / or fusion information of the BSS) to the neighboring APs and / or served STAs, according to the above-mentioned example of AP1 (the structure / format of the AP1 broadcast frame), which will not be described here.

[0246] Based on the above description, AP1 can effectively obtain the statistical information of the neighboring BSS2 (including the fusion information of BSS2 and / or the observation information (updated) of BSS2) and the statistical information of BSS3 (including the fusion information of BSS3 and / or the observation information (updated) of BSS3). AP2 and AP3 can also implement in the same way as AP1 to obtain the statistical information (i.e. the observation information (updated) and / or fusion information) of the neighboring BSS, which will not be described here.

[0247] S305A: AP1 trains the fusion network model and / or the decision network model.

[0248] S305A is an optional step.

[0249] In the embodiments of the present application, AP1 can also send at least one of the statistical information of BSS1 (including the observation information (updated) and / or fusion information of BSS1), the statistical information of BSS2 (including the observation information (updated) and / or fusion information of BSS3), and the statistical information of BSS3 (including the observation information (updated) and / or fusion information of BSS3) to a network device (such as a cloud server), which can then train the fusion network model and / or the decision network model.

[0250] AP1 / network device (such as a cloud server) can train the fusion network model and the decision network model separately, or jointly train the fusion network model and the decision network model, which is not limited. The trained fusion network model can be deployed on the AP1 side and / or the STA side, and the trained decision network model can be deployed on the AP1 side and / or the STA side.

[0251] In addition, the present application does not make specific limitations on the time of training the fusion network model and / or the decision network model, which can be performed before or after one or more of the following, or simultaneously:

[0252] AP1 obtains the statistical information of BSS1 in the current first time period, AP1 obtains the statistical information of the neighboring BSS in the current first time period, and AP1 / STA performs channel access parameter decision.

[0253] For example, the AP1 / network device can train the fusion network model after S303A (i.e., the AP1 performs the fusion processing procedure), before S303A, or synchronously with S303A. If the AP1 / network device trains the fusion network model before S303A, the AP1 can use the fusion network model trained in the current / this time in S303A. If the AP1 / network device trains the fusion network model after (or synchronously with) S303A, the AP1 can use the fusion network model trained in the last time in S303A, and the fusion network model trained in the current / this time can be used in the next time when the AP1 performs the fusion processing procedure.

[0254] The decision network model can be the same as the fusion network model, and the time for training the decision network model is not limited in the present application.

[0255] In a possible implementation, the AP1 / network device can train the fusion network model based on at least one of the following information:

[0256] The observation information of the BSS1, the observation information of the BSS2, or the observation information of the BSS3.

[0257] In the embodiments of the present application, the decision network model can adopt an LSTM-based structure.

[0258] In a possible implementation, the AP1 / network device can train the set decision network model by using a reinforcement learning method (for example, DQN) based on one or more of the following information, and update the parameters of the set decision network model by using a reward function:

[0259] The observation information of the BSS1 (or the observation information of the STA served by the AP1), the fusion information of the BSS1, the fusion information of the BSS2, the fusion information of the BSS3, or the channel access parameter of the AP1 (or the channel access parameter of the STA served by the AP1).

[0260] The channel access parameter of the AP1 can be determined based on at least one of the observation information of the BSS1, the fusion information of the BSS1, the fusion information of the BSS2, and the fusion information of the BSS3. The channel access parameter of the STA served by the AP1 can be determined based on at least one of the observation information of the STA, the fusion information of the BSS1, the fusion information of the BSS2, and the fusion information of the BSS3.

[0261] In the above, the observation information of the BSS1, the observation information of the BSS2, and the observation information of the BSS3 used for training the fusion network model and the decision network model can be previously obtained information or real-time obtained information, which is not limited in the present application.

[0262] For the reward function described above, the embodiments of the present application provide a design of a reward function for DQN training, as follows:

[0263] If the transmission performance (e.g., throughput and / or packet loss rate) achieved by the method (i.e., based on AI) of the embodiments of the present application does not degrade compared to the transmission performance (e.g., throughput and / or packet loss rate) of the CSMA / CA method, then the reward value R = CDF CSAM / CA -CDF AI The reward value R can be used to train and optimize the decision network model; wherein CDF CSAM / CA represents the tail latency (CDF95%) achieved using the standard CSMA / CA method, CDF AI represents the tail latency (CDF95%) achieved using the method (based on AI) of the embodiments of the present application; otherwise, in other cases, the reward value R = -1.

[0264] S306A: AP1 sends the decision network model and the fusion information of the adjacent BSSs (i.e., the fusion information of BSS2 and the fusion information of BSS3) to the served STA1 / STA2 / STA3. Accordingly, STA1 / STA2 / STA3 receives the decision network model and the fusion information of the adjacent BSSs.

[0265] In the embodiments of the present application, the AP1 can send the decision network model and the fusion information (i.e., the fusion information of BSS1 and the fusion information of the adjacent BSSs) separately, or together, without limitation.

[0266] The embodiments of the present application exemplarily list several possible structures of messages / information carrying the decision network model and / or the fusion information:

[0267] Example 1: As shown in FIG. 6A, the field carrying the decision network model and / or the fusion information in the beacon frame.

[0268] Example 2: As shown in FIG. 6B, the field carrying the decision network model and / or the fusion information in the control subfield.

[0269] Example 3: As shown in FIG. 6C, the field carrying the decision network model and / or the fusion information in the trigger frame.

[0270] Example 4: As shown in FIG. 6D, the field carrying the decision network model and / or the fusion information in the block acknowledgment request (BAR) frame.

[0271] In the foregoing, the field of the decision network model can be used to indicate / represent the decision network model and / or parameters of the decision network model. The field of the fusion information can be used to indicate / represent the fusion information of the BSS1 and / or the fusion information of the neighboring BSS (i.e., the fusion information of the BSS2 and the fusion information of the BSS3).

[0272] S307A: The STA1 / STA2 / STA3 determines the channel access parameter of the STA according to the observation information of the STA itself, the fusion information of the BSS1, and the fusion information of the neighboring BSS (i.e., the fusion information of the BSS2 and the fusion information of the BSS3).

[0273] In the embodiments of the present application, the decision network model can adopt an LSTM-based structure.

[0274] Exemplarily, FIG. 7 shows a structure diagram of a decision network model which can be applicable to the embodiments of the present application, which can include: an input layer, an LSTM layer LSTM64, an LSTM64, an FC64, and an output layer. Wherein, the numerical value after the LSTM represents the number of hidden layer neurons of the LSTM layer, for example, LSTM64 represents an LSTM layer with 64 hidden layer neurons. FC64 represents a fully connected layer with 64 hidden layer neurons.

[0275] For example, the STA1 can input the observation information of the STA1, the fusion information of the BSS1, and the fusion information of the neighboring BSS (i.e., the fusion information of the BSS2 and the fusion information of the BSS3) into the policy network model, and the policy network model outputs the channel access parameter of the STA1.

[0276] Similarly, referring to the manner of the STA1 described above, the STA2 and the STA3 can also input the observation information of the STA itself, the fusion information of the BSS1, and the fusion information of the neighboring BSS (i.e., the fusion information of the BSS2 and the fusion information of the BSS3) into the policy network model, and then output the channel access parameter of the STA itself.

[0277] In addition, the AP1 can also output the corresponding channel access parameter through the decision network model according to the observation information of the AP1 itself, the fusion information of the BSS1, and the fusion information of the neighboring BSS2 and BSS3.

[0278] In the foregoing, the channel access parameter can include one or more of the following: a contention window size, a carrier sensing threshold, an access channel result, a modulation and coding scheme, a channel aggregation result, or a channel prediction result.

[0279] The S301A to S307A above are introduced by taking the devices in the BSS1 (i.e., the AP1 and the served STA1 and STA2 and STA3) as an example, and the devices in other BSSs can also perform the steps to implement the scheme of the embodiments of the present application.

[0280] In the first embodiment of the present application, the S301A to S307A above can be regarded as a complete processing procedure of the embodiments of the present application, and in addition, the similar processing procedure can be performed once or multiple times, and the execution time of adjacent processing procedures can overlap.

[0281] Exemplarily, taking the AP1 as an example, FIG. 3B shows a schematic diagram of the timeline corresponding to N processing procedures performed in the embodiments of the present application, where N is a positive integer.

[0282] Referring to FIG. 3B, the steps shown in each processing procedure can be one-to-one corresponding to the steps shown in the S301A to S307A above, i.e., in FIG. 3B, the step S1 can refer to the content described in the S301A above, the step S2 can refer to the content described in the S302A above, the step S3 can refer to the content described in the S303A above, the step S4 can refer to the content described in the S304A above, the step S5 can refer to the content described in the S305A above, the step S6 can refer to the content described in the S306A above, and the step S7 can refer to the content described in the S307A above.

[0283] In the first processing procedure, after the AP1 performs the S1 to S3, since the AP1 can obtain and update the observation information of the BSS1 in real time, when the AP1 performs the S4 (i.e., the AP1 interacts with the adjacent AP to exchange the fusion information of the BSS), the AP1 can also synchronously interact with the adjacent AP to exchange the updated observation information of the BSS1 (equivalent to performing the S2 in the second processing procedure), and the updated observation information of the BSS1 is applied to the second processing procedure. Similarly, when the AP1 performs the S4 in the second processing procedure (i.e., the AP1 interacts with the adjacent AP to exchange the fusion information of the BSS), the AP1 can also synchronously interact with the adjacent AP to exchange the updated observation information of the BSS1 (equivalent to performing the S2 in the third processing procedure), and so on, which will not be repeated here.

[0284] In addition, in the first processing procedure, when the AP1 performs the S5 to S6, the AP1 can also synchronously perform part or all of the steps in the S3 to S7 in the second processing procedure, and the specific synchronous execution is not limited.

[0285] For example, S3 (fusion processing) in the second processing procedure can be executed after S5 (training model) in the first processing procedure, or executed synchronously with S6 or S7 in the first processing procedure, and no limitation is made to this, then in the second processing procedure, the fusion model used by AP1 in performing S3 (fusion processing) can be the fusion model trained in S5 in the first processing procedure, and in the second processing procedure, AP1 trains a decision network model and a fusion network model in S5, wherein the decision network model can be used in S7 in the second processing procedure, or used in S7 in the third processing procedure, and the fusion network model can be used in S3 in the third processing procedure.

[0286] Similarly, the timeline executed between the second processing procedure and the third processing procedure, and the timeline executed between the N-1th processing procedure and the Nth processing procedure can all refer to the timeline executed between the first processing procedure and the second processing procedure, and this is recursively deduced, and will not be described one by one.

[0287] In the first embodiment, after AP1 obtains the observation information of the BSS1 and the observation information of the neighboring BSS, the AP1 can fuse the observation information of the BSS1 and the observation information of the neighboring BSS to obtain the fusion information of the BSS1. In addition, the AP1 can also obtain the fusion information of the neighboring BSS. For the foregoing fusion information of the BSS, the AP1 can not only use it to determine the corresponding channel access parameter, but also send it to the served STA for determining the corresponding channel access parameter of the STA. The accuracy and reliability of the channel access parameter obtained by the AP1 / STA through the method shown in the embodiments of the present application are high, so that the transmission performance of the AP1 / STA based on the channel access parameter can be effectively improved, and the tail delay of the transmission can be effectively improved.

[0288] The second embodiment is as follows.

[0289] In the second embodiment, S301A (AP1 obtains the observation information of the BSS1) in the first embodiment is further described in detail. In S301A, if the observation information of the BSS1 obtained by the AP1 is calculated by collecting the information of all the served STAs, the present embodiment provides a method for reporting the STA information to the AP by the STA. The following describes the method of the second embodiment by taking the AP1 and the served STAs as examples, as shown in FIG. 8, which can include the following steps.

[0290] S801: The AP1 sends a trigger frame to the STA1 / STA2 / STA3, and the trigger frame is used to trigger the STA to send its own statistical information (i.e., the example of the transmission information of the second device in the scheme shown in FIG. 2).

[0291] In the embodiments of the present application, the STA1 / STA2 / STA3 reports the statistical information of itself to the AP1, which can include one or more of the following: the information of the delay (i.e. the information of the delay in the transmission information reported by the second device in the scheme shown in FIG. 2), the tail delay, the contention window size, the throughput, or the packet loss rate.

[0292] The information of the delay of the STA1 / STA2 / STA3 can include one or more of the following: the segmented information of the delay, the index of the segment where the tail delay is located, the number of data packets transmitted on each segment, or the delay of each data packet.

[0293] S802: The STA1 / STA2 / STA3 reports the statistical information of itself to the AP1 based on the trigger frame (i.e. the example of the transmission information of the second device in the scheme shown in FIG. 2).

[0294] In the embodiments of the present application, the STA1 / STA2 / STA3 can report the statistical information of itself using a new frame, or can carry and report the statistical information of itself in an existing control frame, such as an acknowledgement (ACK) frame, a block acknowledgement (BA) frame, an M-BA frame, etc.

[0295] For example, as shown in FIG. 9, taking the BA frame as an example, the STA1 adds a field of statistical information in the BA frame, which is used to indicate / represent the statistical information of the STA1, such as one or more of the following: the information of the delay of the STA1, the tail delay, the contention window size, the throughput, or the packet loss rate.

[0296] The following describes several ways in which the STA1 / STA2 / STA3 reports the information of the delay to the AP1 in the embodiments of the present application:

[0297] Taking the STA1 as an example, other STAs (STA2\STA3) can implement the way of the STA1:

[0298] The segmented way of the delay is predefined and known by the AP1; the STA1 reports the information of the delay (i.e. the information of the delay in the scheme shown in FIG. 2) to the AP1, which can include at least one of the following:

[0299] (1) The index of the segment where the tail delay is located;

[0300] (2) The number of packets transmitted on each segment of the delay.

[0301] For mode 1, the AP1 knows the delay segment, that is, the AP1 knows the number of segments and the maximum and minimum values of each delay segment. Through the information of the delay reported by the STA1, the AP1 can further know the index of the tail delay segment and / or the corresponding packet sending number (i.e., the number of data packets sent) on each delay segment.

[0302] For example, it is assumed that the number of segments corresponding to the STA1 is N (N is a positive integer), and the N delay segments correspond to different indexes respectively. As shown in FIG. 10A, the STA1 sends a BA frame as an example, wherein the newly added field of the statistical information includes a first field and a second field, the first field is used to indicate the index of the tail delay segment of the STA1, and the second field is used to indicate the corresponding packet sending number on the N delay segments corresponding to the STA1.

[0303] For mode 2, taking the STA1 as an example, other STAs (STA2\STA3) can refer to the mode of the STA1:

[0304] The AP1 does not know the delay segment, and the STA1 reports the information of the delay to the AP1, which can include at least one of the following:

[0305] (1) the segment information of the delay, (2) the index of the tail delay segment, and (3) the packet sending number on each segment.

[0306] For mode 2, if the delay segment is uniformly segmented, the segment information of the delay can include at least one of the following:

[0307] the number of segments, the maximum value of the delay, or the minimum value of the delay.

[0308] In the above, the maximum value of the delay and / or the minimum value of the delay can correspond to the maximum value of the total delay and / or the minimum value of the total delay, or can correspond to the maximum value of the delay and / or the minimum value of the delay of any one segment.

[0309] For example, it is assumed that the number of segments corresponding to the STA1 is N (N is a positive integer), and the N delay segments correspond to different indexes respectively. As shown in FIG. 10B, the STA1 sends a BA frame as an example, wherein the BA frame carries a newly added field of the statistical information, and the field of the statistical information includes the segment information of the delay and a first field and a second field. The segment information of the delay includes the number of segments, the maximum value of the delay, and the minimum value of the delay. The first field is used to indicate the index of the tail delay segment of the STA1, and the second field is used to indicate the corresponding packet sending number on the N delay segments corresponding to the STA1.

[0310] For mode 2, if the delay segment is non-uniformly segmented, the segment information of the delay can include at least one of the following:

[0311] the number of segments, the maximum value of the delay on each segment, or the minimum value of the delay on each segment.

[0312] For example, assuming that the number of segments corresponding to STA1 is N (N is a positive integer), the N delay segments correspond to different indexes respectively; as shown in FIG. 10C, taking the BA frame sent by STA1 as an example, the BA frame carries a field of newly-added statistical information, the field of statistical information includes segment information of the delay and a first field and a second field; the segment information of the delay includes the number of segments, the maximum value of the delay, and the minimum value of the delay; the first field is used to indicate the index of the segment where the tail delay is located, and the second field is used to indicate the number of packets respectively corresponding to the N delay segments.

[0313] For example, referring to FIG. 10D, assuming that the delay T is divided into 7 non-uniform segments, i.e., [<1000, 1000-5000, 5000-9000, 9000-13000, 13000-17000, 17000-21000, >21000]us, and the number of packets in the 7 segments per second is [500, 200, 300, 150, 100, 30, 0], which is used to represent the distribution of the delay.

[0314] In the embodiments of the present application, the STA1 / STA2 / STA3 can report the statistical information of the STA1 / STA2 / STA3 to the AP1 in the following ways, but not limited to the following ways:

[0315] Example 1: Each STA in STA1, STA2 and STA3 actively reports the statistical information of the STA to the AP1.

[0316] Example 2: Each STA in STA1, STA2 and STA3 periodically reports the statistical information of the STA to the AP1 according to a set period.

[0317] The set period corresponding to STA1, STA2 and STA3 respectively can also be mutually negotiated or agreed with the AP1, or allocated in advance by the AP1, and the length of the set period corresponding to STA1, STA2 and STA3 respectively can be the same or different, which is not limited in the present application.

[0318] The above is an example of the AP1, which introduces how the STA served by the AP1 reports the statistical information of the STA to the AP1. Similarly, the other APs (such as AP2 and AP3) and the STA served by the APs can also be implemented by referring to the way shown in the above embodiment 2, which will not be described one by one here.

[0319] In the second embodiment, the AP1 can trigger all the STAs served by the AP1 to report their statistical information, and the AP1 is reported the statistical information and the delay information of each STA. In the original frame, various flexible ways are designed to achieve this, which not only ensures that the AP1 can effectively obtain the statistical information of all the STAs served by the AP1 to obtain the observation information of the BSS1, but also ensures that the transmission cost is low.

[0320] It should be noted that, in the first and second embodiments described above:

[0321] (1) The second embodiment described above can be implemented separately from the first embodiment, or can be partially or wholly combined with the first embodiment, and no specific limitation is made in this regard.

[0322] (2) The differences between the first and second embodiments are described above, and other contents except for the differences can be mutually referred to between the first and second embodiments.

[0323] (3) The step numbers of each flowchart described in the first and second embodiments are only one example of the execution flow, and do not constitute a limitation on the execution sequence of the steps. The steps in the present application have no time sequence dependency relationship between each other, and there is no strict execution sequence. In addition, the steps shown in each flowchart are not all the steps that must be executed, and some steps can be added or deleted based on the actual needs on the basis of each flowchart.

[0324] In the embodiments of the present application described above, the method provided by the embodiments of the present application is introduced from the perspective of interaction between each device. In order to implement each function in the method provided by the embodiments or implementation modes of the present application, the first device or the second device can include a hardware structure and / or a software module to implement the above-mentioned functions in the form of hardware structure, software module, or hardware structure plus software module. Whether a certain function in the above-mentioned functions is executed in the form of hardware structure, software module, or hardware structure plus software module depends on the specific application of the technical solution and the design constraint conditions.

[0325] The division of modules in the embodiments of the present application is illustrative, and is only a logical functional division. In actual implementation, another division mode can be used. In addition, each functional module in each embodiment or implementation mode of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0326] The communication apparatus 1100 can be a software module or a chip system. In the embodiments of the present application, the chip system can be composed of a chip or can include a chip and other discrete devices. The communication apparatus 1100 can include a communication unit 1101 and a processing unit 1102.

[0327] In the embodiments of the present application, the communication unit 1101 can also be referred to as a transceiver unit, which can include a sending unit and / or a receiving unit, and is used to perform the sending and receiving steps of the first device or the second device in the above method embodiments. The processing unit 1102 can be used to read the instructions and / or data in the storage module, so that the communication apparatus 1100 implements the above method embodiments.

[0328] Optionally, the communication apparatus 1100 can further include a storage unit 1103, which corresponds to the storage module, and is used to store instructions and / or data.

[0329] In the following, the communication apparatus provided by the embodiments of the present application will be described in detail in combination with FIG. 11 to FIG. 12. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments, and therefore, the contents not described in detail can be implemented in the manner shown in FIG. 2 and FIG. 3A and FIG. 8, which will not be described here for the sake of brevity.

[0330] The communication unit 1101 can also be referred to as a transceiver, a transceiver, a transceiver device, etc. The processing unit can also be referred to as a processor, a processing board, a processing module, a processing device, etc. Optionally, the devices in the communication unit 1101 used to implement the receiving function can be regarded as a receiving unit, and the devices in the communication unit 1101 used to implement the sending function can be regarded as a sending unit, that is, the communication unit 1101 includes a receiving unit and a sending unit. The communication unit can also be referred to as a transceiver, a transceiver, or a transceiver circuit, etc. The receiving unit can also be referred to as a receiver, a receiver, or a receiving circuit, etc. The sending unit can also be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0331] When the communication apparatus 1100 performs the first device in the flow shown in FIG. 2 in the above embodiments:

[0332] The communication unit 1101 is configured to obtain transmission information of a first cell serving the first device and transmission information of at least one second cell adjacent to the first cell;

[0333] The processing unit 1102 is configured to obtain target transmission information of the first cell based on the transmission information of the first cell and the transmission information of the at least one second cell; the target transmission information of the first cell is used to determine the channel access information of the first cell.

[0334] The communication unit 1101 is used to send target transmission information of the first cell.

[0335] When the communication device 1100 executes the second device in the process shown in Figure 2 of the above embodiment:

[0336] The communication unit 1101 is used to receive target transmission information of a first cell served by the first device. The target transmission information of the first cell is obtained based on the transmission information of the first cell and the transmission information of at least one second cell, wherein the at least one second cell is adjacent to the first cell.

[0337] The processing unit 1102 is used to determine the channel access information of the second device based on the target transmission information of the first cell.

[0338] The above are just examples. Processing unit 1102 and communication unit 1101 can also perform other functions. For a more detailed description, please refer to the relevant descriptions in the method embodiments shown in Figures 2 and 3A and Figure 8. They will not be repeated here.

[0339] Figure 12 shows a communication device 1200 provided in an embodiment of this application. The communication device shown in Figure 12 can be a hardware circuit implementation of the communication device shown in Figure 11. This communication device 1200 can be applied to the flowcharts shown above to perform the functions of the first device or the second device in the above method embodiments. For ease of explanation, Figure 12 only shows the main components of the communication device.

[0340] As shown in Figure 12, the communication device 1200 includes a communication interface 1201 and a processor 1202. The communication interface 1201 and the processor 1202 are coupled to each other. It is understood that the communication interface 1201 can be a transceiver or an input / output interface, or an interface circuit such as a transceiver circuit. Optionally, the communication device 1200 may further include a memory 1203 for storing instructions executed by the processor 1202, or storing input data required by the processor 1202 to execute instructions, or storing data generated after the processor 1202 executes instructions.

[0341] When the communication device 1200 is used to implement the methods shown in FIG2, FIG3A and FIG8, the communication interface 1201 is used to implement the functions of the communication unit 1101, and the processor 1202 is used to implement the functions of the processing unit 1102.

[0342] The specific connection medium between the communication interface 1201, the processor 1202 and the memory 1203 is not limited in the embodiments of the present application. In FIG. 12, the memory 1203, the processor 1202 and the communication interface 1201 are connected through a communication bus 1204, which is represented by a thick line in FIG. 12. The connection mode between other components is only illustrative and is not limited. The communication bus 1204 can be divided into an address bus, a data bus, a control bus and the like. For convenience of representation, only one thick line is used in FIG. 12, but it does not mean that there is only one bus or only one type of bus.

[0343] When the communication device is a chip, FIG. 13 shows a simplified device structure schematic diagram of the chip 1300, which includes an interface circuit 1301 and one or more processors 1302. Optionally, the chip 1300 can also include a bus. Wherein:

[0344] The processor 1302 can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the method for determining the service node information can be completed by the integrated logic circuit of hardware in the processor 1302 or the instructions in the form of software. The processor 1302 described above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. Each method and step disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor.

[0345] The interface circuit 1301 can be used for sending or receiving data, instructions or information. The processor 1302 can process the data, instructions or other information received by the interface circuit 1301, and can send the processed information through the interface circuit 1301.

[0346] Optionally, the chip 1300 also includes a memory 1303, which can include read-only memory and random access memory, and provides operation instructions and data for the processor. Part of the memory 1303 can also include non-volatile random access memory (NVRAM).

[0347] Optionally, the memory stores executable software modules or data structures, and the processor can perform corresponding operations by calling operation instructions stored in the memory (the operation instructions can be stored in an operating system).

[0348] Optionally, the chip can be used in the first device or the second device related to the embodiments of the present application. Optionally, the interface circuit 1301 can be used to output the execution result of the processor 1302. The communication method provided by one or more embodiments of the present application can refer to the foregoing various embodiments, which will not be described here.

[0349] It should be noted that the functions of the interface circuit 1301 and the processor 1302 respectively can be realized by hardware design, software design, or a combination of software and hardware, which is not limited here.

[0350] The embodiments of the present application also provide a computer readable storage medium, which stores computer instructions for implementing the method executed by the first device or the second device in the above method embodiments.

[0351] For example, the computer program is executed by a computer, so that the computer can implement the method executed by the first device or the second device in the above method embodiments.

[0352] The embodiments of the present application also provide a computer program product containing instructions, which are executed by a computer to make the computer implement the method executed by the first device or the second device in the above method embodiments.

[0353] The embodiments of the present application also provide a chip, which includes a processor, and is used to call computer degrees or computer instructions stored in the memory, so that the processor executes the communication method of the implementation manners shown in FIG. 2, FIG. 3A and FIG. 8.

[0354] In a possible implementation manner, the input of the chip corresponds to the receiving operation in the implementation manners shown in FIG. 2, FIG. 3A and FIG. 8, and the output of the chip corresponds to the sending operation in the implementation manners shown in FIG. 2, FIG. 3A and FIG. 8.

[0355] Optionally, the processor is coupled with the memory through an interface.

[0356] Optionally, the chip further includes a memory, and the memory stores computer degrees or computer instructions.

[0357] The processor mentioned in any of the above can be a general central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of a program for implementing the communication method of the above-mentioned embodiments shown in FIGS. 2, 3A and 8. The memory mentioned in any of the above can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM), etc.

[0358] It should be noted that, for the convenience and brevity of description, the explanations and beneficial effects of the related content in any of the above-mentioned communication devices can refer to the corresponding service node information determination method embodiments provided above, which will not be repeated here.

[0359] In this application, the communication devices can also include a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer. The hardware layer can include central processing unit (CPU), memory management unit (MMU), memory (also known as main memory), and other hardware. The operating system of the operating system layer can be any one or more computer operating systems that implement business processing through processes, such as Linux operating system, Unix operating system, Android operating system, iOS operating system, or windows operating system, etc. The application layer can include browsers, address books, word processing software, instant messaging software, etc.

[0360] The division of modules in the embodiments of the present application is illustrative, and is only a logical functional division. In actual implementation, there can be another division manner. In addition, the functional modules in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0361] Those skilled in the art can clearly understand that the application can be implemented by a hardware only or a combination of hardware and software, or in an embodiment thereof. When the software is implemented, the above functions can be stored in or transmitted by a computer readable medium, as one or more instructions or codes. The computer readable medium includes a computer storage medium and a communication medium, and the communication medium includes any medium that facilitates the transfer of computer program from one place to another. The storage medium can be any available medium that can be accessed by a computer. For example, but not limited to, the computer readable medium can include RAM, ROM, electrically erasable programmable read only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage medium or other magnetic storage devices, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer. In addition, any connection can be properly included in the computer readable medium. For example, if the software is transmitted from a website, server or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwave, the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwave are included in the definition of the medium. As used in the embodiments of the present application, a disk and a disc include compact discs (CD), laser discs, optical discs, digital video discs (DVD), floppy disks and Blu-ray discs, wherein the disk usually magnetically copies data, and the disc uses laser to optically copy data. The combination of the above should also be included in the protection scope of the computer readable medium.

[0362] In summary, the above only describes the embodiments of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made according to the disclosure of the present application should be included in the protection scope of the present application.

Claims

1. A communication method characterized by comprising: The method is applied to a first device or a chip of the first device, and includes: obtaining transmission information of a first cell served by the first device and transmission information of at least one second cell adjacent to the first cell; obtaining target transmission information of the first cell based on the transmission information of the first cell and the transmission information of the at least one second cell; the target transmission information of the first cell is used to determine channel access information of the first cell; sending the target transmission information of the first cell.

2. The method of claim 1, wherein, The method further includes: receiving target transmission information of the at least one second cell, the target transmission information of the second cell being obtained by fusing the transmission information of the second cell and the transmission information of at least one cell adjacent to the second cell in a first time period; and 3. The method according to claim 1 or 2, characterized in that, determining the channel access information of the first cell based on the transmission information of the first cell, the target transmission information of the first cell, and the target transmission information of the at least one second cell by using a decision network model. The method further includes: training the fusion network model and updating parameters of the fusion network model based on one or more of the following information:

4. The method according to claim 2 or 3, characterized in that, the transmission information of the first cell, the transmission information of the at least one second cell, or the target transmission information of the first cell. The method further includes: training the decision network model by using a reinforcement learning method and updating parameters of the decision network model by using a reward function based on one or more of the following information:

5. The method according to claim 3 or 4, characterized in that, the transmission information of the first cell, the target transmission information of the first cell, the target transmission information of the at least one second cell, or the determined channel access information. sending the updated parameters of the decision network model. The condition one is that a transmission performance achieved by using the channel parameter information of the first cell output by the decision network model is not weaker than a transmission performance achieved by using a Wi-Fi DCF method; R represents a reward value, the reward value being used to optimize the parameters of the decision network model; CDF1 represents a tail latency achieved by using the channel access information of the first cell output by the Wi-Fi DCF method; and CDF2 represents a tail latency achieved by using the channel access information of the first cell output by the decision network model. The method further includes:

6. The method of claim 5, wherein, The reward function is in accordance with the following formula: counting and obtaining the transmission information of the first cell in a current first time period; or 7. The method according to any one of claims 1 to 6, characterized in that, ​ ​ receiving transmission information reported by the at least one second device in a current first time period; and calculating transmission information of the first cell based on the transmission information of the at least one second device, wherein the at least one second device is a non-access device in the first cell, and the at least one second device reports the transmission information in one of the following manners: actively, periodically, or triggered by the first device. The transmission information reported by the second device includes information of a delay, and the information of the delay includes one or more of the following:

8. The method of claim 7, wherein, segment information of the delay, an index of a tail delay segment, a number of data packets transmitted in each segment, and a delay of each data packet; The delay includes a delay of at least one data packet, and a delay of 95% of the data packets is less than the tail delay. The delay of the data packet includes one or more of the following: a queuing delay of the data packet or an access delay of the data packet. When the segment information of the delay indicates uniform segmentation, the segment information of the delay includes at least one of the following:

9. The method of claim 8, wherein, a number of segments, a maximum value of the delay, or a minimum value of the delay. When the segment information of the delay indicates non-uniform segmentation, the segment information of the delay includes at least one of the following: a number of segments, a maximum value of the delay corresponding to each segment, or a minimum value of the delay corresponding to each segment. The transmission information includes one or more of the following:

10. The method according to any one of claims 1 to 9, characterized in that, information of a delay, a tail delay, a contention window size, a throughput, or a packet loss rate. The delay includes a delay of at least one data packet, and a delay of 95% of the data packets is less than the tail delay. The delay of the data packet includes one or more of the following: a queuing delay of the data packet or an access delay of the data packet. The channel access information of the first cell includes one or more of the following:

11. The method according to any one of claims 1 to 10, characterized in that, a contention window size, a carrier sensing threshold, an access channel result, a modulation and coding scheme, a channel aggregation result, or a channel prediction result. The method is applied to a second device or a chip of the second device, and includes:

12. A communication method characterized by comprising: receiving target transmission information of a first cell served by a first device, wherein the target transmission information of the first cell is obtained based on transmission information of the first cell and transmission information of at least one second cell adjacent to the first cell; and determining channel access information of the second device based on the target transmission information of the first cell. The method further includes:

13. The method of claim 12, wherein, receiving updated parameters of a set decision network model; and updating the set decision network model based on the updated parameters of the set decision network model. The method further includes:

14. The method according to claim 12 or 13, characterized in that, obtaining transmission information of the second device and receiving target transmission information of the at least one second cell, wherein the target transmission information of the second cell is obtained based on transmission information of the second cell in a first time period and transmission information of at least one cell adjacent to the second cell; and The determination of the channel access information of the second device based on the target transmission information of the first cell includes: ​ The second device transmits transmission information to the first device in a current first time period, and the transmission information is reported in one of the following manners:

15. The method according to any one of claims 12 to 14, characterized in that, The transmission information is reported actively, periodically, or triggered by the first device. The transmission information includes one or more of the following: Information of the delay, tail delay, contention window size, throughput, or packet loss rate.

16. The method of claim 15, wherein, The delay includes delay of at least one data packet, and delay of 95% of the data packets is less than the tail delay. The delay of the data packet includes one or more of the following: Queuing delay of the data packet or access delay of the data packet. The transmission information includes one or more of the following: Information of the delay, tail delay, contention window size, throughput, or packet loss rate.

17. The method of claim 16, wherein, The delay includes delay of at least one data packet, and delay of 95% of the data packets is less than the tail delay. The delay of the data packet includes one or more of the following: Queuing delay of the data packet or access delay of the data packet. The channel access information includes one or more of the following:

18. The method according to any one of claims 12 to 17, characterized in that, Contention window size, carrier sensing threshold, access channel result, modulation and coding scheme, channel aggregation result, or channel prediction result. The method includes units or modules for performing the method of any one of claims 1-11, or units or modules for performing the method of any one of claims 12-19. The processor and the memory are configured to perform the method of any one of claims 1-11, or the processor and the memory are configured to perform the method of any one of claims 12-19. The computer readable storage medium stores computer readable programs or instructions, which, when executed on a communication device, cause the method of any one of claims 1-11 to be performed, or cause the method of any one of claims 12-19 to be performed. ​ 19. The method according to any one of claims 12 to 18, characterized in that, ​ ​ 20. A communications device, characterized by ​ 21. A communications device, characterized by ​ 22. A computer-readable storage medium, characterized in that, ​ 23. A computer program product, characterised in that, The computer program product comprises computer programs or instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 11, or cause the computer to perform the method of any one of claims 12 to 19.

24. A chip, characterized by The chip is for reading and executing computer programs or instructions in a memory to implement the method of any one of claims 1 to 19.

Images