Channel access method and apparatus
Through the information exchange between the first device and the second device, the neural network model is used to predict channel access decision information and update model parameters, the problems of channel conflicts and large network overhead in the Wi-Fi system are solved, and more efficient Channel management and adaptability.
Patent Information
- Application Number
- PCT/CN2023/142066
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-11
- Filing Date
- 2023-12-26
- Publication Date
- 2024-11-14
AI Technical Summary
Existing Wi-Fi systems are prone to communication conflicts when multiple nodes share channels, resulting in reduced throughput and increased latency. The frequent issuance of parameters for artificial intelligence training neural networks in real time leads to high network overhead.
Through the information exchange between the first device and the second device, the neural network model is used to predict channel access decision information, update model parameters to adapt to the dynamic network environment, and reduce the need for real-time training and parameter issuance.
It effectively reduces network overhead, improves the accuracy and adaptability of channel access decision-making, and reduces the network burden caused by environmental changes.
Smart Images

Figure CN2023142066_14112024_PF_FP_ABST
Abstract
Description
Channel access method and device
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on May 11, 2023, with application number 202310533970.7 and application name “A Channel Access Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field
[0003] The present application relates to the field of wireless communications, and in particular to a channel access method and device. Background Art
[0004] In a short-distance transmission network system (such as Wi-Fi), multiple nodes use the same shared channel for communication. If two or more nodes send messages on the shared channel at the same time, a communication conflict will occur, and the message transmission will fail, resulting in a decrease in the throughput of the shared channel and an increase in the communication delay of nodes in the network, affecting the user experience. The existing Wi-Fi system uses a carrier sense multiple access with collision avoidance (CSMA / CA) access mechanism to share the channel to avoid conflicts. In order to ensure the fairness of multiple nodes competing for the channel at the same time, a random backoff mechanism is also introduced. Each node selects a random backoff number according to its corresponding contention window (CW). When the channel is idle in the detection time slot, the corresponding backoff number decreases. Only after the random backoff ends can the channel be accessed. This method of avoiding conflicts by random numbers has the disadvantages of low capacity, large latency, poor fairness, and no anti-interference ability.
[0005] Current technologies propose using artificial intelligence (AI) to perform the intelligent distributed coordination function (IDCF) access process to complete channel access. Channel access decisions are made by a neural network (NN). Since NN parameters are trained using large amounts of environmental data, dynamic wireless environments require real-time training of the NN model to adapt to environmental changes. This requires frequent delivery of the NN model (or neural network parameters), resulting in significant air interface overhead.
[0006] Summary of the Invention
[0007] The present application provides a channel access method and device, which can use a neural network model that adapts to a dynamic network environment to predict or decide channel access, thereby reducing network overhead.
[0008] In a first aspect, a channel access method is provided. The method can be executed by a first device, or by a chip / chip system corresponding to the first device, without limitation. The method can specifically include: the first device determining first state information; the first state information being input information of a first model, the first model being used to predict decision information for the first device to access a channel, the first state information including occupancy information of the channel and node information of nodes whose resources occupying the channel exceed a preset resource threshold; the first device sending the first state information to a second device; the first device receiving model parameters of the first model from the second device; the model parameters including biases and / or weights corresponding to different variables in the first model; the biases and / or weights corresponding to different variables being determined by the second device based on the first state information; the first device updating the first model based on the model parameters of the first model to obtain an updated first model; the first device inputting the first state information into the updated first model, and obtaining decision information for the first device to access the channel based on the output of the updated first model.
[0009] In an embodiment of the present application, the first device may be, but is not limited to, a station (STA), and the second device may be, but is not limited to, an access point (AP). In addition, the first device may also be an access point (AP), and the second device may also be a station (STA). Here, the decision information for the first device to access the channel may include, but is not limited to: whether to access the channel, the probability value of accessing the channel, the contention window duration for accessing the channel, etc.
[0010] Through this method, not only can the decision information of the first device to access the channel be effectively obtained, but the first status information used by the second device to determine the model parameters of the first model includes the occupancy information of the channel and the node information occupying the channel resources greater than the preset resource threshold. Therefore, the first device updates the first model based on the model parameters from the second device, so that the updated first model can better adapt to the dynamic network environment, thereby avoiding the need for the second device to determine and send the model parameters of the first model in real time due to changes in the network environment, thereby reducing network overhead.
[0011] In one possible implementation, the occupancy information of the channel includes a first occupancy rate of the first device occupying the channel based on the target access type and a second occupancy rate of other devices occupying the channel based on the target access type, where the other devices are at least one device occupying the channel other than the first device.
[0012] In the embodiment of the present application, the target access type may be, but is not limited to: an access type for voice data, an access type for video data, an access type for maximum capability transmission data, and an access type for background data.
[0013] Exemplarily, the first occupancy rate corresponding to the target access type of the first device occupying the channel may be a proportion of the total duration during which the first device occupies the channel for data transmission based on the target access type within a specified measurement duration.
[0014] In one possible implementation, the second occupancy can be determined in the following manner: the first device sends the first occupancy to the second device; the first device receives first information from the second device; the first information includes the total occupancy of the channel based on the target access type, and the total occupancy is obtained by the second device based on the first occupancy and the occupancy of the channel occupied by other devices based on the target access type; the first device subtracts the first occupancy of the first device from the total occupancy to obtain the second occupancy.
[0015] Through this implementation, the first device can effectively and accurately obtain the occupancy rate of the channel occupied by other devices based on the target access type.
[0016] In one possible implementation, before the first device sends the first occupancy to the second device, the method further includes: the first device receives second information from the second device, the second information including the channel occupancy threshold of the target access type; the first device determines that the first occupancy of the first device is greater than the channel occupancy threshold. That is, the first device sends the first occupancy to the second device only when it determines that the first occupancy is greater than the channel occupancy threshold. In this implementation, other devices can report their own occupancy of the target channel based on the target access type to the second device in a manner similar to that of the first device, while devices whose occupancy of the channel for the target access type is not greater than the channel occupancy threshold do not need to report to the second device.
[0017] Through this implementation, the efficiency of the second device in collecting node information statistics can be improved, and network transmission overhead can also be saved.
[0018] In a possible implementation, the method further includes: the first device receiving a first request message from the second device, where the first request message is used to request the first device to occupy a first occupancy rate of the channel based on the target access type.
[0019] Through this implementation, the second device can actively request the first device to obtain the occupancy rate of one or more access types occupying the channel. Then, the first device can send the occupancy rate of the one or more access types corresponding to its own to the second device based on the request message of the first device. There is no need to report the occupancy rate of the channel corresponding to all access types, thereby further reducing network transmission overhead.
[0020] In a possible implementation, the node information includes the number of the nodes, and the nodes specifically refer to devices whose resource occupancy rate of the channel based on the target access type is greater than a resource occupancy rate threshold of the channel based on the target access type.
[0021] In one possible implementation, the number of nodes can be obtained in the following manner: the first device receives the number of nodes from the second device, and the number of nodes is obtained by the second device based on the resource occupancy rate of the channel occupied by the first device based on the target access type and the resource occupancy rate of the channel occupied by other devices based on the access type, as well as the resource occupancy rate threshold of the channel.
[0022] Through this implementation, the number of devices that occupy a large amount of the channel resources can be effectively obtained, so as to facilitate subsequent training to obtain model parameters of the first model that can adapt to the dynamic network environment.
[0023] In one possible implementation, the first status information also includes one or more of the following: carrier sensing result information of the channel in a preset historical time period, the length of time between the time when the first device currently sends data and the time when the first device last successfully sent data, and the length of time between the time when other devices currently send data and the time when the other devices last successfully sent data.
[0024] Through this implementation, the first state information can be effectively used to obtain the decision information for the first device to access the channel.
[0025] In one possible implementation, when the decision information for the first device to access the channel is the probability value of the first device successfully accessing the channel, the method further includes: the first device obtains the contention window duration for the first device to access the channel based on the probability value of the channel, and the first device can access the channel within the contention window duration.
[0026] Through this implementation, the duration of the contention window in which the first device occupies the channel based on the target access type can be effectively obtained. Compared with the probability value of the target access type occupying the target channel, the duration of the contention window has better characteristics and compatibility.
[0027] In a second aspect, a channel access method is provided. The method can be executed by a second device, or by a chip / chip system corresponding to the second device, without limitation. The method may specifically include: the second device receives first state information from a first device; the first state information is input information of a first model, the first model is used to predict the decision information of the first device accessing the channel, the first state information includes channel occupancy information and information about nodes occupying the channel resources exceeding a preset resource threshold; the second device determines the model parameters of the first model based on the first state information; the model parameters include the bias and / or weight corresponding to each variable in the first model; the second device sends the model parameters of the first model to the first device.
[0028] In the embodiment of the present application, the first device may be but is not limited to a station (STA), and the second device may be but is not limited to an access point (AP). In addition, the first device may also be an access point (AP), and the second device may also be a station (STA).
[0029] In an embodiment of the present application, the first status information also includes one or more of the following: carrier sensing result information of the channel in a preset historical time period, the length of time between the time when the first device currently sends data and the time when the first device last successfully sent data, and the length of time between the time when other devices currently send data and the time when the other devices last successfully sent data.
[0030] In the method of the present application, the second device receives first status information from the first device; the first status information is input information of the first model, and the first model is used to predict the decision information of the first device to access the channel. The first status information includes the occupancy information of the channel and the node information of the node that occupies the channel resources exceeding the preset resource threshold; then the second device determines the model parameters of the first model based on the first status information; and then sends the model parameters of the first model to the first device. After receiving the model parameters of the first model, the first device can use the model parameters to update the first model, and then can effectively obtain the decision information of the first device to access the channel through the updated first model, and the updated first model can better adapt to the dynamic network environment, thereby avoiding the need for the second device to train the first model in real time and send the model parameters of the first model due to changes in the network environment, thereby reducing network overhead.
[0031] In one possible embodiment, the method also includes: the second device receives the occupancy rate of the channel occupied by at least one device based on the target access type, and the at least one device includes the first device; the second device determines the total occupancy rate of the channel occupied by the target access type based on the occupancy rate of the channel occupied by the at least one device based on the target access type; the second device sends first information to the first device, and the first information includes the total occupancy rate of the channel occupied by the target access type.
[0032] In the embodiment of the present application, the target access type may be, but is not limited to: an access type for voice data, an access type for video data, an access type for maximum capability transmission data, and an access type for background data.
[0033] Through the implementation method, the second device counts the total occupancy rate of the target access type occupying the channel and sends it to the first device, so that the first device can use the total occupancy rate to effectively obtain the occupancy rate of other devices occupying the channel based on the target access type.
[0034] In one possible implementation, the occupancy information of the channel includes a first occupancy rate of the first device occupying the channel based on the target access type and a second occupancy rate of other devices occupying the channel based on the target access type, where the other devices are at least one device occupying the channel other than the first device; the node information includes the number of nodes, and the node specifically refers to a device whose resource occupancy rate of occupying the channel based on the target access type is greater than a resource occupancy rate threshold of occupying the channel based on the target access type.
[0035] Through this implementation, the occupancy information of the channel includes the occupancy information of the first device occupying the channel and the occupancy information of other devices occupying the channel. Therefore, the second device obtains the model parameters of the first model based on the first status information containing the occupancy information of the channel and can better adapt to changes in the network environment.
[0036] In one possible implementation, the second device determines model parameters of the first model based on the first state information, including: the second device uses a reinforcement learning method to train the model parameters of the first model based on the first state information and reward function information, where the reward function information is associated with the first occupancy rate of the first device. This implementation effectively obtains model parameters of the first model that can adapt to dynamic network environments.
[0037] In a third aspect, an embodiment of the present application also provides a communication device, which can be used to execute the method of the first aspect. The communication device can be a first device (for example, a station STA), or can be a component of the first device (for example, a chip, or a chip system, or a circuit), or can be a device that can be used in conjunction with the first device.
[0038] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in the first aspect. The module or unit may be implemented as a hardware circuit, software, or a combination of hardware circuits and software. In one possible implementation, the communication device may include a processing module and a communication module. The processing module is configured to invoke the communication module to perform receiving and / or transmitting functions.
[0039] In one possible implementation, the communication device may include a processing unit and a communication unit, which can perform the corresponding functions in the above method example. For details, please refer to the description of the method provided in the above first aspect or any possible implementation method, which will not be repeated here.
[0040] In a fourth aspect, an embodiment of the present application also provides a communication device, which can be used to execute the method of the second aspect. The communication device can be a second device (for example, an access point AP), or can be a component of the second device (for example, a chip, or a chip system, or a circuit), or can be a device that can be used in conjunction with the second device.
[0041] In one possible implementation, the communication device may include a module or unit corresponding to the method / operation / step / action described in the second aspect. The module or unit may be implemented as a hardware circuit, software, or a combination of hardware circuit and software. In one possible implementation, the communication device may include a processing module and a communication module. The processing module is configured to call the communication module to perform receiving and / or transmitting functions.
[0042] In one possible implementation, the communication device may include a processing unit and a communication unit, which can perform the corresponding functions in the above method example. For details, please refer to the description of the method provided in the above second aspect or any possible implementation method, which will not be repeated here.
[0043] In a fifth aspect, the present application also provides a communication system, which includes a first device for executing the method provided in the first aspect and a second device for executing the method provided in the second aspect.
[0044] In a sixth aspect, an embodiment of the present application further provides a computer storage medium storing a software program, which, when read and executed by one or more processors, can implement the method provided by the above-mentioned first aspect or any possible implementation method thereof, or implement the method provided by the above-mentioned second aspect or any possible implementation method thereof.
[0045] In the seventh aspect, an embodiment of the present application also provides a computer program product comprising instructions, which, when run on a computer, enables the execution of the method provided in the above-mentioned first aspect or any possible implementation method thereof, or enables the execution of the method provided in the above-mentioned second aspect or any possible implementation method thereof.
[0046] In an eighth aspect, an embodiment of the present application further provides a chip system, which includes a processor for supporting a first device to implement the functions involved in the above-mentioned first aspect; or for supporting a second device to implement the functions involved in the above-mentioned second aspect.
[0047] In one possible design, the chip system further includes a memory for storing necessary program instructions and data for execution by the loading device. The chip system can be composed of a chip or include a chip and other discrete devices.
[0048] It should be noted that the technical effects that can be achieved by any possible implementation method of the third to eighth aspects mentioned above can be correspondingly described with reference to the technical effects that can be achieved by any possible implementation method of the first to second aspects or the first to second aspects mentioned above; they will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] FIG1 is a schematic diagram of a Wi-Fi network architecture;
[0050] FIG2 is a schematic diagram of a communication system architecture to which the method according to an embodiment of the present application is applicable;
[0051] FIG3A is a schematic diagram of a neural network structure;
[0052] Figure 3B is a schematic diagram of a neuron calculating output based on input;
[0053] FIG4 is a flow chart of a channel access method provided in an embodiment of the present application;
[0054] FIG5 is a specific flow chart of the first embodiment provided in the embodiments of the present application;
[0055] FIG6 is a specific flow chart of a second embodiment provided in the embodiments of the present application;
[0056] FIG7 is a specific flow chart of a third embodiment provided in the embodiments of the present application;
[0057] FIG8A is a schematic diagram of a CW conversion structure provided in an embodiment of the present application;
[0058] FIG8B is a schematic diagram of another CW conversion structure provided in an embodiment of the present application;
[0059] FIG9 is a schematic structural diagram of a communication device provided in an embodiment of the present application;
[0060] FIG10 is a schematic structural diagram of another communication device provided in an embodiment of the present application;
[0061] FIG11 is a schematic diagram of the structure of a chip provided in an embodiment of the present application. DETAILED DESCRIPTION
[0062] In a short-distance transmission network system (for example, Wi-Fi), channels are shared, that is, multiple nodes in the wireless network use the same shared channel for communication. In this network, if two or more nodes send messages at the same time, a communication conflict will occur, and the message transmission of the node will fail, resulting in a decrease in the throughput of the channel and an increase in the communication latency of nodes in the network, which greatly affects the user experience. It can be seen that the node channel access decision has an important impact on communication and plays a decisive role in the user experience. In a distributed scenario, there is no central node to perform unified scheduling and coordination for all nodes in the network. The decision whether to access the shared channel is made directly by the node.
[0063] New wireless technologies, new terminals, and new applications are making wireless networks increasingly complex. To combat this increasing complexity, artificial intelligence (AI) has become an industry consensus as an effective tool for wireless network design and management.
[0064] In wireless networks, AI's advantages are reflected in four key areas: 1. Solving complex network problems for which mathematical models are unavailable; 2. Addressing wireless network management challenges with large search spaces; 3. Global network-level optimization across layers and nodes; and 4. Proactively optimizing wireless network parameters through AI's predictive capabilities. Wireless resource allocation is crucial to wireless network performance and encompasses channel access, channel allocation, rate configuration, and power configuration.
[0065] Traditional wireless network design and management is rule-based. Designers achieve specific design goals by designing algorithms or functions, represented as f(·). Designers need to clearly define the operational rules for each step of f(·). For example, if y = f(x), the designer needs to explain how each step from input x to output y is calculated. With the introduction of AI, f(·) is no longer rule-based. Instead, it is described using a neural network structure and parameters, expressed as f(θ,·), where θ represents the neural network parameters. Designers no longer need to design each step of an algorithm or function, but instead achieve specific design goals by designing the neural network structure and training its parameters. Consequently, AI is becoming increasingly widely used in wireless networks.
[0066] In view of the above, the prior art proposes an AI-based channel access method. Referring to FIG1 , taking a Wi-Fi network as an example, there is at least one station STA in the network, and each station STA sends its status information s i The AP trains the neural network and sends the trained neural network parameters (NN as shown in Figure 1) to the central node (using the access point AP as an example in Figure 2). i ) is sent to STA, and then STA sends its status information s i By inputting the neural network, the decision result can be inferred. Where i = 1, 2, 3…. STA status information may include: the carrier sensing result information of the channel in a preset historical time period, the time between the current data transmission time and the last successful data transmission time, and the time between the current data transmission time of other nodes and the last successful data transmission time, etc. The decision result may include whether to access the channel, the probability value of accessing the channel, the contention window length of the access channel, etc. According to the above, the neural network parameters are obtained through training of network environment data. In a dynamic network environment, the AP needs to train the NN Model in real time to obtain the neural network parameters, and needs to frequently send down the neural network parameters, which will generate a large network overhead.
[0067] In response to the above problems, the present application proposes a channel access method to obtain policy information for the first device to access the channel on the basis of reducing network overhead, and the updated first model can adapt to changes in the network environment.
[0068] The technical solution provided in the embodiment of the present application can be applied to wireless local area network (WLAN) systems, such as Wi-Fi, etc. For example, the embodiment of the present application can also be applied to the Institute of Electrical and Electronics Engineers (IEEE) 802.11 system standards, such as 802.11a / b / g protocols, 802.11n protocols, 802.11ac protocols, 802.11ax protocols, 802.11be protocols or next-generation protocols, etc., which are not listed here one by one. Of course, the embodiment of the present application can also be applied to other types of communication systems, such as cellular systems (including but not limited to: long term evolution (LTE) systems, fifth-generation (5G) communication systems, and new communication systems (such as 6G) emerging in future communication development), Internet of Things (IoT) systems, narrowband Internet of Things (NB-IoT) systems, other short-range communication systems (including but not limited to: Bluetooth, ultra-wide band (UWB)), etc.
[0069] In addition, the embodiments of the present application can be applied to scenarios where a node transmits data to one or more nodes. For example, uplink / downlink transmission of a single user, uplink / downlink transmission of multiple users, and device-to-device (D2D) transmission. Any of the above nodes can be a communication device in a wireless communication system, that is, the method provided in the embodiments of the present application can be implemented by a communication device in a wireless communication system. For example, the communication device can be at least one of an access point (AP) or a station (STA). The communication devices (such as AP and STA) in the embodiments of the present application all have certain AI capabilities. For example, the AP can train a neural network, and the STA can use a neural network for inference and decision-making.
[0070] In the embodiments of the present application, the WLAN system can provide high-speed and low-latency transmission. As WLAN application scenarios continue to evolve, the WLAN system will be applied to more scenarios or industries, such as the Internet of Things (IoT) industry, the Internet of Vehicles (IoV) industry, the banking industry, corporate offices, stadiums and exhibition halls, concert halls, hotel rooms, dormitories, hospital wards, classrooms, supermarkets, squares, streets, production workshops and warehouses, etc. Of course, devices (such as access points or stations) that support WLAN communication or perception can be sensor nodes in smart cities (such as smart water meters, smart electricity meters, and smart air detection nodes), smart devices in smart homes (such as smart cameras, projectors, displays, televisions, speakers, refrigerators, washing machines, etc.), nodes in the Internet of Things (IoT), entertainment terminals (such as wearable devices such as AR and VR), smart devices in smart offices (such as printers, projectors, loudspeakers, speakers, etc.), IoV devices in IoV, infrastructure in daily life scenarios (such as vending machines, self-service navigation kiosks in supermarkets, self-service cash registers, self-service ordering machines, etc.), and equipment in large sports and music venues. For example, access points and stations can be devices used in the Internet of Vehicles (IoV), IoT nodes and sensors in the Internet of Things (IoT), smart cameras and remote controls in smart homes, smart water and electricity meters, and sensors in smart cities. The specific forms of STAs and APs are not limited in the embodiments of this application and are provided for illustrative purposes only.
[0071] While the embodiments of the present application are described using a network deployed on IEEE 802.11 as an example, various aspects of the present application can also be extended to other networks that adopt various standards or protocols, such as high-performance wireless LAN (HIPERLAN) (a wireless standard similar to the IEEE 802.11 standard, mainly used in Europe) and wide area network (WAN), wireless local area network (WLAN), personal area network (PAN) or other currently known or later developed networks.
[0072] Refer to Figure 2, which shows a wireless network architecture and device diagram applicable to an embodiment of the present application. As shown in Figure 2, in the network architecture, the device includes one wireless access point (AP) and three associated stations (STA), and each STA can communicate with the AP. The internal functional modules of the AP and STA may include a central processing unit, a media access control (MAC), a transceiver, an antenna, and a neural network processing unit (NPU). The NPU includes a training module and an inference module. The trained neural network parameters will be fed back to the inference module. The NPU can act on various other modules of the network node, including the central processing unit, MAC, transceiver, and antenna. The NPU can act on the decision-making tasks of each module, such as interacting with the transceiver, deciding the switch of the transceiver for energy saving, interacting with the antenna, controlling the direction of the antenna, interacting with the MAC, controlling channel access, channel selection, and spatial multiplexing decisions, etc.
[0073] FIG2 is merely an example. The system in which the embodiments of the present application are actually applied may include more or fewer devices than those shown in FIG2. Furthermore, the embodiments of the present application are also applicable to communication between APs, for example, APs can communicate with each other via a distributed system (DS). The embodiments of the present application are also applicable to communication between STAs.
[0074] In an embodiment of the present application, an access point may be an access point for a terminal device (such as a mobile phone) to enter a wired (or wireless) network. It is mainly deployed in homes, inside buildings, and inside campuses, with a typical coverage radius of tens to hundreds of meters. Of course, it can also be deployed outdoors. An access point is equivalent to a bridge connecting a wired network and a wireless network. Its main function is to connect various wireless network clients together and then connect the wireless network to the Ethernet. Specifically, an access point may be a terminal device (such as a mobile phone) or a network device (such as a router) with a Wi-Fi chip. An access point may be a device that supports the 802.11be standard. An access point may also be a device that supports various wireless local area networks (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. The access point in this application may be a HE AP or an extremely high throughput (EHT) AP, or may be an access point applicable to a future generation of Wi-Fi standards.
[0075] A 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, a station can be a mobile phone that supports Wi-Fi communication, a tablet that supports Wi-Fi communication, a set-top box that supports Wi-Fi communication, a smart TV that supports Wi-Fi communication, a smart wearable device that supports Wi-Fi communication, an in-vehicle communication device that supports Wi-Fi communication, or a computer that supports Wi-Fi communication, etc. Optionally, the station can support the 802.11be standard. The station can also support various wireless local area network (WLAN) standards in the 802.11 family, such as 802.11ax, 802.11ac, 802.11n, 802.11g, 802.11b, 802.11a, and the next generation of 802.11be.
[0076] The station in this application may be a HE STA or an extremely high throughput (EHT) STA, or may be a STA applicable to a future generation of Wi-Fi standards.
[0077] For example, access points and sites can be devices used in the Internet of Vehicles, IoT nodes and sensors in the Internet of Things (IoT), smart cameras and remote controls in smart homes, smart water and electricity meters, and sensors in smart cities.
[0078] The AP and STA involved in the embodiments of the present application may be APs and STAs applicable to the IEEE 802.11 system standard. An 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 typically a network-side product that supports the MAC and PHY of the 802.11 system standard. For example, it may be a base station, router, gateway, repeater, communication server, switch or bridge and other communication equipment, wherein the base station may include various forms of macro base stations, micro base stations, relay stations, etc. Here, for the sake of convenience of description, the above-mentioned devices are collectively referred to as APs. A STA is typically a terminal product that supports the media access control (MAC) and physical layer (PHY) of the 802.11 system standard, such as a mobile phone, a laptop computer, etc.
[0079] In order to better understand the embodiments of the present application, the names and technical features involved in the embodiments of the present application are explained below. It should be noted that these explanations are intended to make the embodiments of the present application easier to understand and should not be regarded as limiting the scope of protection claimed by this application.
[0080] 1) Model: This refers to an AI model, also known as a neural network, and is related to the task performed by the device. For example, if a device can perform a channel access task, the model's input information may include carrier sensing results, channel access behavior, and packet transmission results, and the output information may include the expected reward for accessing or not accessing the channel. For another example, if a device can perform a rate adaptation task, the model's input information may include received power, carrier sensing results, modulation and coding scheme (MCS), and packet transmission results, and the output information may include the probability of using each MCS. For another example, if a device can perform a channel aggregation task, the model's input information may include the carrier sensing results and load of each channel, and the output information may include the expected reward for using different channel aggregation methods. For another example, if a device can perform a channel state information (CSI) feedback task, the model's input information may include the channel matrix and beamforming matrix, and the output information may include compressed channel information. For another example, if a device can perform a traffic prediction task, the model's input information may include historical traffic information, and the output information may include predicted traffic. Models can implement task-related functions and assist devices in making predictions or decisions.
[0081] A neural network (NN) is a machine learning technology that simulates the human brain's neural networks in order to achieve artificial intelligence-like capabilities. A neural network can include an input layer, an intermediate layer (also called a hidden layer), and an output layer. Taking the simplest neural network as an example, its internal structure and implementation will be explained. See Figure 3A, which is a schematic diagram of a fully connected neural network with three layers. As shown in Figure 3A, the neural network consists of three layers: an input layer, a hidden layer, and an output layer. The input layer has three neurons, the hidden layer has four neurons, and the output layer has two neurons. Each neuron in each layer is fully connected to the neurons in the next layer. Each connection between neurons corresponds to a weight, which can be updated through training. Each neuron in the hidden and output layers can also be associated with a bias, which can be updated through training. Updating a neural network means updating these weights and biases. Once the neural network's structure—the number of neurons in each layer and how the outputs of previous neurons are input to subsequent neurons (i.e., the connections between neurons)—is determined, along with the neural network's parameters, namely the weights and biases, the complete information about the neural network can be determined.
[0082] As shown in Figure 3A, each neuron may have multiple input connections, and each neuron can calculate output based on the input. Figure 3B is a schematic diagram of a neuron calculating output based on input. As shown in Figure 3B, a neuron contains 3 inputs, 1 output, and 2 calculation functions. The calculation formula for the output can be expressed as:
[0083] Output = activation function (input 1 * weight 1 + input 2 * weight 2 + input 3 * weight 3 + bias) Formula 1
[0084] The symbol “*” represents the mathematical operation “multiplication” or “times”, and the same applies to the symbols shown below.
[0085] In addition, each neuron may also have multiple output connections, and the output of one neuron can serve as the input of the next neuron. It should be understood that the input layer only has output connections, and each neuron in the input layer is the value input to the neural network, and the output value of each neuron directly serves as the input of all output connections. The output layer only has input connections, and the output is calculated using the calculation method of the above formula 1. Optionally, the output layer can have no activation function calculation, then the above formula 1 can be transformed into: output = input 1 * weight 1 + input 2 * weight 2 + input 3 * weight 3 + bias.
[0086] For example, a k-layer neural network can be expressed as: y = f k (f k-1 (…(f1(w1*x+b1))) Formula 2
[0087] Among them, x represents the input of the neural network, y represents the output of the neural network, and w i represents the weight of the i-th layer neural network, b i represents the bias of the i-th layer neural network, f i Represents the activation function of the i-th layer of the neural network. i=1,2,…,k.
[0088] 2) State information, which may be input information of the model, such as the aforementioned carrier sensing results, channel access behavior, and data packet transmission results, etc. It is understandable that the state information may be preset or predefined by the protocol.
[0089] 3) In the embodiments of this application, "at least one" can also be described as one or more, and "multiple" can be two, three, four, or more, without limitation. In the embodiments of this application, " / " can indicate an "or" relationship between the associated objects. For example, A / B can mean A or B. "And / or" can be used to describe three relationships between the associated objects. For example, "A and / or B" can mean: A exists alone, A and B exists simultaneously, or B exists alone. A and B can be singular or plural. To facilitate the description of the technical solutions of the embodiments of this application, the words "first" and "second" may be used in the embodiments of this application to distinguish between technical features with the same or similar functions. The words "first" and "second" do not limit the quantity or order of execution, and the words "first" and "second" do not necessarily mean different. In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. The use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.
[0090] It should be noted that in this application, "indication" can include direct indication, indirect indication, explicit indication, and implicit indication. When describing that a certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A.
[0091] In this application, the information indicated by the indication information is referred to as the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, where there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can also be achieved with the help of the arrangement order of each information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent.
[0092] The information to be indicated can be sent as a whole, or divided into multiple sub-information and sent separately, and the sending period and / or sending timing of these sub-information can be the same or different. The specific sending method is not limited in this application. Among them, the sending period and / or sending timing of these sub-information can be pre-defined, for example, pre-defined according to the protocol, or configured by the transmitting device by sending configuration information to the receiving device. Among them, the configuration information can, for example, but not limited to, include one or a combination of at least two of radio resource control signaling, media access control (MAC) layer signaling and physical layer signaling. Among them, radio resource control signaling, for example, radio resource control (RRC) signaling; MAC layer signaling, for example, includes MAC control element (CE); physical layer signaling, for example, includes downlink control information (DCI).
[0093] The technical solution of this application is introduced below in conjunction with specific embodiments.
[0094] The embodiment of the present application provides a channel access method, which is applicable to but not limited to the system architecture shown in Figure 1, and the method can be executed by the first device (or the second device) involved in the present application, or by the chip corresponding to the first device (or the second device) involved. The present application does not specifically limit the form of the first device (or the second device) involved. In addition, the first device in the embodiment of the present application can be but not limited to a station (STA), and the second device can be but not limited to an access point (AP). Referring to Figure 4, the method can specifically include the following steps:
[0095] S401: The first device determines first state information; the first state information is input information of the first model, and the first state information includes occupancy information of the channel and node information of nodes that occupy resources of the channel exceeding a preset resource threshold.
[0096] The first model is used to predict the decision information of the first device to access the channel. Exemplarily, the first model can be a neural network used by the first device to make a channel access decision.
[0097] In one possible embodiment, the occupancy information of the channel may include a first occupancy rate of the first device occupying the channel based on the target access type and a second occupancy rate of other devices occupying the channel based on the target access type, where the other devices are at least one device occupying the channel other than the first device.
[0098] In the above, the target access type may refer to the data service type that occupies the channel for transmission. For example, when a STA in an IEEE 802.11 network accesses an AP for transmission, in order to distinguish the priority of the service, four access types (ACs) are defined, namely, the access type for voice, the access type for video, the access type for maximum capability, and the access type for background. Therefore, in an embodiment of the present application, the target access type may be, but is not limited to, one or more of the access type for voice data, the access type for video data, the access type for maximum capability transmission data (such as web browsing data), and the access type for background data (such as file type data).
[0099] In a possible implementation, the first device may calculate a first occupancy rate of the channel occupied by itself based on the target access type.
[0100] Exemplarily, the first occupancy rate of the channel occupied by the first device based on the target access type may refer to the proportion of the total duration during which the first device occupies the channel to transmit data using the target access type in a certain measurement duration.
[0101] In a possible implementation, the second occupancy rate may be determined by, but not limited to, the following methods:
[0102] Step 1: The first device sends a first occupancy rate of the channel occupied by the first device based on the target access type to the second device. Correspondingly, the second device receives the first occupancy rate.
[0103] In this embodiment, in addition to receiving the first occupancy rate of the first device, the second device also receives the occupancy rate of the target access type of other devices connected to the second device occupying the channel, so that the second device can subsequently use the occupancy rates corresponding to these devices to calculate the total occupancy rate of the target access type occupying the channel and determine the node information.
[0104] That is, the second device receives an occupancy rate of the channel occupied by at least one device based on the target access type, where the at least one device includes the first device;
[0105] Step 2: The second device determines a total occupancy rate of the channel based on the target access type according to the occupancy rate of the channel occupied by the at least one device based on the target access type;
[0106] In the above, the total occupancy rate of the target access type in the channel may refer to the sum of the occupancy rate of the target access type of the second device in the channel and the occupancy rate of the target access type of all devices (i.e., all devices occupying the channel, including the first device) in the channel.
[0107] For example, the total occupancy rate of the channel occupied by the target access type may satisfy the following formula: Load tol =channel load+load0;
[0108] Among them, Load tol Indicates the total occupancy rate of the channel occupied by the target access type, channel load indicates the sum of the occupancy rates of the channel occupied by all devices (i.e., all devices occupying the channel, including the first device, excluding the second device) based on the target access type, and load0 indicates the occupancy rate of the channel occupied by the second device based on the target access type.
[0109] Step 3: The second device sends first information to the first device, where the first information includes a total occupancy rate of the channel based on the target access type. Correspondingly, the first device receives the first information.
[0110] Step 4: The first device subtracts the first occupancy of the first device from the total occupancy of the target access type on the channel to obtain the second occupancy (i.e., the occupancy of the channel occupied by other devices based on the target access type).
[0111] In one possible embodiment, before the first device sends the first occupancy to the second device, the method may also include: the first device receives second information from the second device, the second information including the channel occupancy threshold of the target access type; the first device determines that the first occupancy of the first device is greater than the channel occupancy threshold.
[0112] In this embodiment, the first device can only report its first occupancy rate of the target channel based on the target access type to the second device when it determines that its first occupancy rate of the target channel based on the target access type is greater than the channel occupancy rate threshold; other devices can refer to the reporting method of the first device to report their own occupancy rate of the target channel based on the target access type to the second device, which not only makes it easier for the second device to count the number of devices greater than the channel occupancy rate threshold, but also reduces the network transmission overhead.
[0113] In a possible embodiment, before the first device sends the first occupancy rate to the second device, the method also includes: the first device receives a first request message from the second device, and the first request message is used to request the first device to occupy the first occupancy rate of the channel based on the target access type.
[0114] Through this implementation, the second device can actively request the first device to obtain the occupancy rate of one or more access types occupying the target channel. Then, the first device can send the occupancy rate of the one or more access types corresponding to its own to the second device based on the request message of the first device, without having to report the occupancy rate of all access types occupying the target channel.
[0115] In an embodiment of the present application, the node information in the first state information may include the number of nodes, and the node specifically refers to a device whose resource occupancy rate of the channel based on the target access type is greater than the resource occupancy rate threshold of the channel based on the target access type.
[0116] In a possible implementation, the number of nodes may be obtained by, but not limited to, the following methods:
[0117] The first device receives the number of nodes from the second device, and the number of nodes can be obtained by the second device based on the resource occupancy rate of the channel occupied by the first device based on the target access type, the resource occupancy rate of the channel occupied by other devices based on the access type, and the resource occupancy rate threshold of the channel.
[0118] In an embodiment of the present application, the first status information of the first device may also include but is not limited to: carrier sensing result information of the channel in a preset historical time period, the length of time between the time when the first device currently sends data and the time when the first device last successfully sent data, and the length of time between the time when other devices currently send data and the time when the other devices last successfully sent data.
[0119] S402: The first device sends the first status information to the second device. Correspondingly, the second device receives the first status information.
[0120] S403: The second device determines model parameters of the first model according to the first state information, where the model parameters include biases and / or weights corresponding to different variables in the first model.
[0121] Exemplarily, the biases and / or weights corresponding to different variables in the first model may refer to the biases and / or weights corresponding to different neurons in the neural network.
[0122] In a possible implementation, the second device determines the model parameters of the first model based on the first state information, which may include: the second device uses a reinforcement learning method to train the model parameters of the first model based on the first state information and reward function information, and the reward function information is associated with the first occupancy rate of the first device.
[0123] In the embodiment of the present application, the reward function information can be equivalent to the reward function used in the prior art for training a neural network. However, unlike the prior art, in the embodiment of the present application, the reward value used by the AP (i.e., the second device) when training the neural network model of the STA (i.e., the first device) is associated with the channel occupancy rate of the STA, so that the ultimately trained neural network model can better adapt to dynamic service environments.
[0124] S404: The second device sends the model parameters of the first model to the first device.
[0125] Accordingly, the first device receives the model parameters of the first model.
[0126] S405: The first device updates the first model based on the model parameters of the first model to obtain an updated first model.
[0127] Exemplarily, the first device may update previous model parameters of the first model based on the model parameters of the first model, thereby obtaining the updated first model.
[0128] S406: The first device inputs the first state information into the updated first model, and obtains decision information for the first device to access the channel based on an output of the updated first model.
[0129] In an embodiment of the present application, the first device inputs the first state information into an updated first model, and outputs decision information for the first device to access the channel based on the updated first model. The decision information for the first device to access the channel may include, but is not limited to: whether to access the channel in the current time slot, a probability value for accessing the channel, a contention window duration for accessing the channel, and a backoff window size.
[0130] In a possible embodiment, when the decision information for the first device to access the channel is the probability value of the first device successfully accessing the channel, the method may further include: the first device obtains the contention window duration for the first device to access the channel based on the probability value of the channel; and the first device accesses the channel within the contention window duration.
[0131] In summary, the present application proposes a channel access method, which includes: a first device determines first state information; the first state information is input information of a first model, and the first model is used to predict decision information of the first device accessing the channel, and the first state information includes occupancy information of the channel and node information of nodes that occupy resources of the channel exceeding a preset resource threshold; the first device sends the first state information to the second device; the first device receives model parameters of the first model from the second device; the model parameters include biases and / or weights corresponding to different variables in the first model; the biases and / or weights corresponding to different variables are determined by the second device according to the first state information; the first device updates the first model based on the model parameters of the first model to obtain an updated first model; the first device inputs the first state information into the updated first model, and obtains decision information of the first device accessing the channel based on the output of the updated first model. According to the foregoing, this method can effectively obtain the policy information of the first device accessing the channel, and the first state information used to determine the bias and / or weight corresponding to different variables in the first model includes the channel occupancy information and the node information occupying the channel resources greater than the preset resource threshold. Therefore, updating the first model based on the model parameters including the bias and / or weight corresponding to these different variables can enable the first model to better adapt to the dynamic network environment, thereby avoiding real-time updating of the first model due to changes in the network environment and reducing network overhead.
[0132] The channel access method proposed in the present application is further described in detail below through several specific embodiments.
[0133] Example 1:
[0134] In this embodiment 1, a detailed introduction is mainly given to how the first device determines the channel occupancy information in the first state information (i.e., the first occupancy rate of the channel occupied by the first device based on the target access type and the second occupancy rate of the channel occupied by other devices based on the target access type) in step S401 of the scheme described in Figure 4 above, and the node information (i.e., the number of nodes) of the nodes that occupy the resources of the channel exceeding the preset resource threshold. In this embodiment 1, the first device takes a station (STA) as an example, and the second device takes an AP (AP) as an example. One or more STAs can access the same AP, then the AP can be regarded as a central node, and one STA can be regarded as a node. Referring to Figure 5, the method flow of this embodiment 1 is as follows:
[0135] S501a: STA1 sends the channel occupancy rate of STA1 to the AP.
[0136] That is, STA1 sends the occupancy rate of the channel occupied by STA1 based on the target access type to the AP.
[0137] Exemplarily, the occupancy rate of the channel occupied by STA1 based on the target access type (the occupancy rate of the channel can be called channel occupancy rate or channel load) can be the proportion of the time that STA1 uses the target access type for transmission to the total statistical time.
[0138] S501b: STA2 sends its channel occupancy rate to the AP.
[0139] Exemplarily, the channel occupancy rate of STA2 is the ratio of the transmission duration of STA2 to the total statistical duration.
[0140] In a specific embodiment, when a STA in an IEEE 802.11 network accesses an AP for transmission, there may be several access categories (ACs): voice (equivalent to the access category for voice data in the solution described in FIG. 4 ), video (equivalent to the access category for video data in the solution described in FIG. 4 ), best effort (equivalent to the access category for best effort data transmission in the solution described in FIG. 4 ), and background (equivalent to the access category for background data in the solution described in FIG. 4 ). These ACs can be simply represented as AC_VO, AC_VI, AC_BE, and AC_BK. Therefore, when a STA reports its own channel load to the AP, it can send the channel load corresponding to one or more access categories (ACs) of the SAT to the AP (equivalent to the channel load occupied by the first device based on the target access category in the solution described in FIG. 4 ).
[0141] In the above description, the STA1 (or STA2) sends its own channel load corresponding to AC_VO, channel load corresponding to AC_VI, channel load corresponding to AC_BE, and channel load corresponding to AC_BK to the AP respectively.
[0142] In another specific embodiment, the AP may send a request message for the target access type (AC) to the connected STA (equivalent to the first request message sent by the second device to the first device in the solution described in FIG. 4 ). The request message is used to request the channel occupancy corresponding to the target access type (AC). After receiving the request message for the target access type (AC), the STA can report the channel occupancy corresponding to the target access type to the AP.
[0143] Exemplarily, the AP sends a request message for the channel load of AC_VO to STA1 (or STA2), where the request message is used to request the channel load of AC_VO of STA1 (or STA2); then, based on the request message, STA1 (or STA2) sends the channel load corresponding to its own AC_VO to the AP.
[0144] In this first embodiment, STA1 and STA2 are merely examples of STAs connected to the AP. In practice, the STAs connected to the AP are not limited to STA1 and STA2. Furthermore, each STA connected to the AP can refer to the method described above for STA1 or STA2 to determine its own channel occupancy (i.e., the occupancy rate of the channel occupied by itself based on the target access type), and then report its own channel occupancy rate (i.e., the occupancy rate of the channel occupied by itself based on the target access type) to the AP. This embodiment of the present application does not specifically limit the order in which each STA reports its own channel occupancy rate to the AP. That is, the order in which S501a and S501b are executed is not limited.
[0145] In a possible implementation, the AP may also observe and count the packets sent by each STA (ie, the data packets or messages sent), and determine the channel occupancy rate corresponding to the STA based on the statistics of the packets sent by each STA.
[0146] For example, the AP may use the ratio of the statistical packet sending duration of STA1 to the total statistical duration as the channel occupancy rate of STA1.
[0147] Because the AP cannot fully detect the STA's transmission status, that is, conflicting messages, when performing statistics, it is more accurate for the STA to report its own channel occupancy to the AP.
[0148] S502: The AP determines the number of active nodes and the total channel occupancy based on the channel occupancy reported by the STA.
[0149] In a specific embodiment, the active node determined by the AP (equivalent to the node in the scheme described in Figure 4 above) may refer to a STA whose channel occupancy corresponding to the target access type is greater than the preset threshold value of the channel of the target access type (i.e., the channel occupancy threshold TH of the target access type). Therefore, the AP can obtain the number of STAs whose channel occupancy is greater than the preset threshold value (i.e., the channel occupancy threshold TH) based on the channel occupancy corresponding to the target access type reported by all STAs.
[0150] In a specific embodiment, the AP can determine the total occupancy of the channel corresponding to the access type (AC) (i.e., the total occupancy of the channel occupied by the target access type in the scheme described in Figure 4 above) and the number of active nodes corresponding to the access type (AC) based on the channel occupancy of the access type (AC) reported by the STA.
[0151] For example, if STA1 and STA2 each report (i.e., send) the channel load corresponding to the voice access type to the AP, the AP determines the number of active nodes corresponding to the voice access type and the total occupancy of the channel corresponding to the voice access type based on the channel load of the voice access type of STA1 and STA2. The specific determination method can be the same as the above-mentioned implementation method and will not be repeated here.
[0152] For example, the number of active nodes (ie, STAs) may satisfy the following formula:
[0153] Among them, N a Indicates the number of active nodes, n indicates the sequence number of the node, Indicates the total number of nodes, load n is the channel occupancy rate of node n based on the target access type (such as AC_VO), TH is the channel occupancy rate threshold corresponding to the target access type (such as AC_VO), and a typical value of TH is 0.1.
[0154] The total occupancy rate of the target access type (such as AC_VO) on the channel can satisfy the following formula: Load tol =channel load+load0;
[0155] in,
[0156] Load tol Indicates the total occupancy rate of the channel occupied by the target access type (such as AC_VO). Channel load indicates the total occupancy rate of the channel occupied by all SATs (i.e., STA1 and STA2) based on the target access type (such as AC_VO). Load0 indicates the occupancy rate of the channel occupied by the AP itself based on the target access type (such as AC_VO). Symbol Indicates rounding down.
[0157] In the above description, the AP's own channel occupancy rate based on the target access type (e.g., AC_VO) can be the ratio of the total time the AP uses the target access type (e.g., AC_VO) to the total statistical time. The messages sent by the AP using the target access type (e.g., AC_VO) may include both successfully sent messages and erroneously sent messages.
[0158] In an embodiment of the present application, the total occupancy rate of the channel can be counted by the AP and sent to each STA, which can effectively reduce the power consumption caused by the STA frequently monitoring the carrier. At the same time, it can also avoid inaccurate statistical results caused by STA sleep. Therefore, the total occupancy rate of the channel counted by the AP in the embodiment of the present application is more accurate.
[0159] S503a: The AP sends the number of active nodes and the total occupancy of the channel to STA1.
[0160] S503b: The AP sends the number of active nodes and the total occupancy of the channel to STA2.
[0161] In a specific embodiment, the AP broadcasts the number of active nodes and the total occupancy rate of the channel occupied by the target access type to STA1 and STA2. Correspondingly, STA1 and STA2 can receive the number of active nodes and the total occupancy rate of the channel occupied by the target access type.
[0162] S504a: STA1 calculates the channel occupancy of other STAs based on the total channel occupancy from the AP and its own channel occupancy.
[0163] Exemplarily, STA1 can calculate the occupancy rate of the channel occupied by other STAs based on the one or more access types based on the total occupancy rate of the channel occupied by one or more access types from the AP and its own occupancy rate of the channel based on the one or more access types.
[0164] S504b: STA2 calculates the channel occupancy of other STAs based on the total channel occupancy from the AP and its own channel occupancy.
[0165] Exemplarily, STA2 can calculate the occupancy rate of the channel occupied by other STAs based on the one or more access types based on the total occupancy rate of the channel occupied by one or more access types from the AP and its own occupancy rate of the channel based on the one or more access types.
[0166] For example, the STA with serial number n (which can be expressed as STA_n, n=1,2...) calculates that the occupancy rate of the channel occupied by other STAs based on the target access type (taking AC_VO as an example) can satisfy the following formula: load -n =load tol -load n
[0167] Among them, load -n The occupancy rate of the channel occupied by other STAs based on AC_VO, loadn The occupancy rate of the channel occupied by STA_n based on AC_VO.
[0168] For example, the occupancy rate of the AC_VO of STA1 is 30%, and the total occupancy rate of the AC_VO of the channel is 90% as calculated by the AP. Then the occupancy rate of the AC_VO of other STAs is 60%.
[0169] In the above steps, STA1 and STA2 are used only as examples of STAs connected to the AP. In practice, STAs connected to the AP are not limited to STA1 and STA2. Each STA connected to the AP can refer to the methods described above for STA1 or STA2 to obtain its own channel occupancy (i.e., its own channel occupancy rate based on the target access type), the channel occupancy rates of other STAs (i.e., the channel occupancy rates of other STAs based on the target access type), and the number of active nodes (i.e., the number of devices occupying channel resources greater than a preset resource threshold). These methods are not described in detail here.
[0170] After executing the above steps, the STA can add its own channel occupancy rate and the channel occupancy rates of other STAs and the number of active nodes to its own status information, and send the newly added status information to the AP. The AP trains the model parameters of the corresponding neural network model based on the newly added status information, and then sends the model parameters to the corresponding STA. The STA can use the model parameters from the AP to update its own neural network model, and thus use the updated neural network model to infer the decision information of accessing the channel (such as the probability value of accessing the channel).
[0171] In this embodiment 1, each STA accessing the AP reports its own channel occupancy (i.e., the occupancy rate of the channel occupied by each STA based on the target access type). The AP can use the channel occupancy reported by each STA to effectively obtain the total channel occupancy (i.e., the total occupancy rate of the channel occupied based on the target access type) and the number of active nodes, and then distribute the calculated total channel occupancy (i.e., the occupancy rate of the channel occupied by all devices based on the target access type) and the number of active nodes to each STA, so that each STA can obtain the channel occupancy of other STAs (i.e., the occupancy rate of the channel occupied by other STAs based on the target access type) and the number of active nodes. Therefore, each STA can add its own corresponding channel occupancy and the channel occupancy and the number of active nodes corresponding to other STAs to its own status information to train the neural network model parameters that adapt to the dynamic network environment.
[0172] Example 2:
[0173] Compared with the above embodiment 1, the main difference of the second embodiment is that the STA reports its own channel occupancy rate to the AP when it determines that its own channel occupancy rate reaches the preset threshold. Referring to Figure 6, the specific process of the second embodiment is as follows:
[0174] S601: Preset threshold of AP broadcast channel.
[0175] For example, the AP may include a preset threshold value for the channel (i.e., the channel occupancy threshold TH corresponding to the target access type) in the broadcast message. For example, channel TH = 0.1. Accordingly, after receiving the broadcast message, STA1 and STA2 connected to the AP can obtain the preset threshold value for the channel.
[0176] In one possible implementation, when a STA in an IEEE 802.11 network accesses an AP for transmission, there may be several access types (ACs): voice, video, best effort, and background. These ACs can be represented by AC_VO, AC_VI, AC_BE, and AC_BK. Therefore, the AP may include preset thresholds (or channel occupancy thresholds TH) for channels corresponding to one or more access types (ACs) in its broadcast message.
[0177] Exemplarily, the AP carries the load threshold of AC_VO in the broadcast message.
[0178] S602a: STA1 determines that its own channel occupancy is greater than a preset threshold of the channel, and sends the channel occupancy of STA1 to the AP.
[0179] If STA1 determines that its own channel occupancy is not greater than the preset threshold value (or channel occupancy threshold TH) of the channel, then the channel occupancy of STA1 is not sent to the AP.
[0180] Specifically, STA1 receives a preset threshold value of a channel corresponding to one or more access types in a broadcast message from the AP (i.e., equivalent to the channel occupancy threshold corresponding to the target access type in the scheme described in Figure 4 above). Then STA1 can compare the channel occupancy corresponding to its own one or more access types with the channel occupancy threshold (or threshold) of the corresponding access type; when STA1 determines that the channel occupancy of its own access type is greater than the channel occupancy threshold (or threshold) of the corresponding access type, it reports (sends) the channel occupancy of its own access type to the AP.
[0181] For example, STA1 receives a broadcast message from the AP containing the following channel load thresholds for different access types: Threshold 1, Threshold 2, Threshold 3, and Threshold 4. Threshold 1 is the channel load threshold for AC_VO, Threshold 2 is the channel load threshold for AC_VI, Threshold 3 is the channel load threshold for AC_BE, and Threshold 4 is the channel load threshold for AC_BK. Furthermore, if STA1 determines that its own channel load for AC_VO is greater than Threshold 1 and its own channel load for AC_VI is greater than Threshold 2, and that the channel loads for other access types are less than the corresponding thresholds, STA1 reports only its own channel load for AC_VO and AC_VI to the AP.
[0182] S602b: STA2 determines that its own channel occupancy is greater than the preset threshold of the channel, and sends the channel occupancy of STA2 to the AP.
[0183] If STA2 determines that its own channel occupancy is not greater than the preset threshold value (or channel occupancy threshold TH) of the channel, then the channel occupancy of STA2 is not sent to the AP.
[0184] In one embodiment, when STA2 receives the preset threshold value of the channel corresponding to one or more access types in the broadcast message from the AP, it refers to STA1 in the above step S602a, which is not repeated here.
[0185] S603: The AP determines the number of active nodes and the total channel occupancy based on the channel occupancy reported by the STA.
[0186] The AP may count the number of STAs that have reported the channel occupancy rate, and use the counted number of STAs as the number of active nodes.
[0187] The AP determines the total channel occupancy based on the channel occupancy reported by the STA. For example, the implementation method of the AP determining the total channel occupancy in step S502 above may be referred to and will not be described in detail here.
[0188] S604a: The AP sends the number of active nodes and the total occupancy of the channel to STA1.
[0189] The step S604a can be implemented with reference to the above-mentioned S503a, and will not be described in detail here.
[0190] S604b: The AP sends the number of active nodes and the total occupancy of the channel to STA2.
[0191] This step S604b can be implemented with reference to the above-mentioned S503b, and will not be described in detail here.
[0192] S605a: STA1 calculates the channel occupancy of other STAs based on the total channel occupancy from the AP and its own channel occupancy.
[0193] The step S605a can be implemented with reference to the above-mentioned S504a, and will not be described in detail here.
[0194] S605b: STA2 calculates the channel occupancy of other STAs based on the total channel occupancy from the AP and its own channel occupancy.
[0195] The step S605b can be implemented with reference to the above-mentioned S504b and will not be described in detail here.
[0196] Similar to the above embodiment, STA1 and STA2 in the above steps are only examples of STAs connected to the AP. In practice, the STAs connected to the AP are not limited to the above STA1 and STA2, and each STA connected to the AP can refer to the above STA1 or STA2 to obtain its own channel occupancy rate and the channel occupancy rate of other STAs and the number of active nodes. They will not be described in detail here.
[0197] After executing the above steps, the STA can add its own channel occupancy rate (i.e., the occupancy rate of the channel occupied by itself based on the target access type) and the channel occupancy rate of other STAs (i.e., the occupancy rate of the access type occupied by other STAs based on the target access type) and the number of active nodes to its own status information, and send the newly added status information to the AP. The AP trains the model parameters of the corresponding neural network model based on the newly added status information, and then sends the model parameters to the corresponding STA. The STA can use the model parameters from the AP to update its own neural network model, and thus can use the updated neural network model to infer decision information on accessing the channel (such as the probability value of accessing the channel).
[0198] Compared with the above-mentioned embodiment 1, in this embodiment 2, the STA can report its own channel occupancy rate (i.e., its own occupancy rate of the channel based on the target access type) to the AP on demand, that is, the preset threshold value of the AP broadcast channel (i.e., the channel occupancy threshold corresponding to the target access type). When each STA connected to the AP receives the preset threshold value, it can compare its own channel occupancy rate with the preset threshold value. If it is greater than the preset threshold value, it reports its own channel occupancy rate to the AP. If it is not greater than the preset threshold value, it does not need to report its own channel occupancy rate to the AP. Therefore, compared with the reporting method of embodiment 1, the method of embodiment 2 can effectively save air interface overhead.
[0199] Example 3:
[0200] In this third embodiment, the process of determining the model parameters of the first model based on the first state information of the first device in step S403 of the solution described in Figure 4 is described in detail. In this third embodiment, the first device is a station (STA) as an example, and the second device is an AP as an example. One or more STAs can access the same AP, so the AP can be regarded as a central node, and one STA can be regarded as a node. Referring to Figure 7, the method flow of this third embodiment is as follows:
[0201] S701a: STA1 sends its training data to the AP.
[0202] For example, the training data of STA1 (i.e., equivalent to the first state information in the scheme described in FIG4 above) includes but is not limited to: the channel occupancy rate of STA1 (i.e., equivalent to the occupancy rate of the channel occupied by the first device in the scheme described in FIG4 above based on the target access type, which can be expressed as load1), the channel occupancy rate of other STAs (i.e., equivalent to the occupancy rate of the channel occupied by other devices in the scheme described in FIG4 above based on the target access type, which can be expressed as load2), -1 ), the time between the time when STA1 currently sends data and the time when it last successfully sends data (which can be expressed as d1), the time between the time when other STAs currently send data and the time when they last successfully send data (which can be expressed as d -1 ), the number of active nodes (that is, the number of devices of the target access type in Figure 4 above that occupy channel resources greater than the preset resource threshold, which can be expressed as N), the carrier sensing results of the channel in a historical time period preset by STA1, STA1's channel access behavior and data packet transmission results, etc.
[0203] S701b: STA2 sends its training data to the AP.
[0204] For example, the training data of STA2 (i.e., equivalent to the first state information in the scheme described in FIG. 4 above) includes but is not limited to: the channel occupancy rate of STA2 (i.e., equivalent to the occupancy rate of the first device in the scheme described in FIG. 4 above occupying the channel based on the target access type, which can be expressed as load1), the channel occupancy rate of other STAs (i.e., equivalent to the occupancy rate of the other devices in the scheme described in FIG. 4 above occupying the channel based on the target access type, which can be expressed as load -1 ), the time between the time when STA2 currently sends data and the time when it last successfully sends data (which can be expressed as d1), the time between the time when other STAs currently send data and the time when they last successfully send data (which can be expressed as d -1), the number of active nodes (that is, the number of devices of the target access type in Figure 4 above that occupy channel resources greater than the preset resource threshold can be expressed as N), STA2's channel carrier sensing results in a preset historical time period, STA2's channel access behavior and data packet transmission results, etc.
[0205] In this third embodiment, STA1 and STA2 are used as examples of STAs connected to the AP. In practice, the STAs connected to the AP are not limited to STA1 and STA2. Furthermore, each STA connected to the AP can refer to STA1 or STA2 to report training data to the AP. This embodiment of the application does not specifically limit the order in which STAs report training data to the AP. That is, the order in which S701a and S701b are executed is not limited.
[0206] S702: The AP calculates the reward function corresponding to each STA based on the training data reported by each STA, and uses reinforcement learning for training to obtain the corresponding neural network model parameters.
[0207] The method of AP training neural network parameters is similar to the prior art. Compared with the prior art, the difference in training neural network parameters in the embodiment of the present application lies in the calculation of reward.
[0208] In this embodiment of the present application, the AP may calculate the reward values corresponding to different STAs to satisfy the following formula:
[0209] load n represents the channel occupancy rate of the STA with sequence number n (which may be equivalent to the first occupancy rate of the first device in the solution described in FIG4 ), d n Indicates the time from the last successful data transmission time to the current data transmission time of STA with sequence number n. n is a positive integer, the symbol "*" is a multiplication sign, and w represents the normalization coefficient. n *d n / w is not greater than 1.
[0210] That is, the AP loads the training data reported by each STA connected to the AP. n and d n , calculate the load corresponding to each STA respectively n *d n Value; for load n *d n The STA with the largest value and the last successful data transmission has its reward value equal to 1; n *d nThe value is not the largest, but the STA that successfully sent data last time determines that its reward value is equal to load n *d n ; For the STA that sends conflicting data, determine its reward value is equal to -1.
[0211] For example, the AP calculates load1*d1 based on load1 and d1 in the training data reported by STA1; and calculates load2*d2 based on load2 and d2 in the training data reported by STA2. If STA1's load1*d1 value is the maximum and STA1's last data transmission is successful, the AP determines the corresponding reward value for STA1 to be 1. If STA2's last data transmission is successful, the AP determines the corresponding reward value for STA2 to be load2*d2 / w.
[0212] The above-mentioned STA1 and STA2 are merely examples of STAs connected to the AP. In practice, the STAs connected to the AP are not limited to the above-mentioned STA1 and STA2.
[0213] In the embodiment of the present application, since the channel occupancy (load) information is added to the reward calculation, even if the STA with a small channel occupancy (load) successfully sends data, it will not receive a large reward, thereby adapting to the dynamic changes of the business.
[0214] S703a: The AP sends the neural network model parameters corresponding to STA1 to STA1.
[0215] S703b: The AP sends the neural network model parameters corresponding to STA2 to STA2.
[0216] Among them, the neural network model parameters may include the weights and biases of each neuron.
[0217] S704a: STA1 performs inference based on the neural network model parameters to obtain a channel access strategy.
[0218] S704b: STA2 performs inference based on the neural network model parameters to obtain a channel access strategy.
[0219] The process of STA1 (or STA2) inferring the channel access strategy based on the corresponding neural network model parameters (equivalent to the strategy information of the first device obtained based on the output of the first model in the scheme described in Figure 4 above) can refer to the existing technology and will not be repeated here.
[0220] The channel access strategy of STA1 (or STA2) may include but is not limited to: whether to access the channel in the current time slot, the probability of accessing the channel, the contention window, and the backoff window size.
[0221] Similar to the above-mentioned embodiments 1 and 2, STA1 and STA2 in the above steps are only examples of STAs connected to the AP. In practice, the STAs connected to the AP are not limited to the above-mentioned STA1 and STA2, and each STA connected to the AP can refer to the above-mentioned STA1 or STA2 to obtain the channel access strategy, which will not be described in detail here.
[0222] In this third embodiment, when the AP trains the neural network model of the STA, compared with the existing technology, for the calculation of the reward, the reward will be associated with the channel occupancy rate of the STA (that is, the channel occupancy information of the newly added STA) so that the neural network model finally trained can better adapt to dynamic changes in the network environment.
[0223] Example 4:
[0224] In this fourth embodiment, the direct decision strategy is one of the commonly used methods in reinforcement learning. In the context of Markov decision process (MDP), the strategy is a distribution function, that is, probability. However, compared with the duration of the contention window (CW), the characteristics and compatibility of directly using probability decisions are poor. Therefore, this embodiment proposes a method for converting the probability output by the neural network into the CW duration. In addition, in order to support CW conversion for different access types (AC), different access types (AC) will adopt different CW conversion methods. Figures 8A and 8B are schematic structural diagrams of two CW conversion methods provided in the embodiments of the present application.
[0225] As shown in Figure 8A , each AC corresponds to a neural network (NN). The input of each NN is the measurement information of the corresponding AC (the measurement information can be equivalent to the first state information in the solution described in Figure 4 ). The output of each NN is the probability of accessing the channel. The access channel probability output by each NN is converted using a corresponding CW conversion method to obtain the corresponding CW duration. That is, AC_VO corresponds to CW1, AC_VI corresponds to CW2, AC_BE corresponds to CW3, and AC_BK corresponds to CW4.
[0226] In the embodiment of the present application, there will be CWs of these four access types for a STA, and the final output is the CW duration of one of the ACs.
[0227] In one possible implementation, the STA's CW duration is the longest of the four access types. For example, the four access types of STA1 (AC_VO, AC_VI, AC_BE, and AC_BK) correspond to CW durations CW1, CW2, CW3, and CW4, respectively. Since CW2 has the largest value, the output decision contention window duration for STA1 is CW2.
[0228] As shown in FIG8B , all ACs correspond to the same neural network NN, which takes as input the measurement information of all ACs (this measurement information may be equivalent to the state information in the scheme described in FIG4 ), and outputs the probabilities of the access channels corresponding to all ACs. The probabilities of the access channels corresponding to all ACs are converted using the same CW conversion method to obtain the CWs corresponding to all ACs.
[0229] In the embodiment of the present application, there will be CWs of these four access types for a STA, and the final output is the CW duration of one of the ACs.
[0230] In one possible implementation, the STA's CW duration is the longest of the four access types. For example, the four access types of STA1 (AC_VO, AC_VI, AC_BE, and AC_BK) correspond to CW durations CW1, CW2, CW3, and CW4, respectively. Since CW2 has the largest value, the output decision contention window duration for STA1 is CW2.
[0231] In the embodiment of the present application, the above conversion method can satisfy the following formula:
[0232] Where p represents the probability of channel access output by the neural network (NN). X represents the bias term corresponding to the access type (AC). For example, the bias values corresponding to AC_VO, AC_VI, AC_BE, and AC_BK can be: 2, 1, -10, and -20.
[0233] Through this fourth embodiment, the probability of channel access output by neural network inference can be effectively converted into the contention window (CW) duration of the channel access; compared with the probability of channel access, the characteristics and compatibility of the CW duration will be better.
[0234] In the embodiments provided in the present application, the methods provided in the embodiments of the present application are introduced from the perspective of interaction between various devices. In order to implement the various functions in the methods provided in the embodiments of the present application, the first device or the second device may include a hardware structure and / or a software module to implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether a function of the above functions is executed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.
[0235] The division of modules in the embodiments of the present application is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the present application may be integrated into a single processor, or may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.
[0236] Similar to the above concept, as shown in FIG9 , an embodiment of the present application further provides a communication device 900 for implementing the functions of the AUSF network element in the above method. For example, the communication device 900 may be a software module or a chip system. In the embodiment of the present application, the chip system may be composed of a chip, or may include a chip and other discrete devices. The communication device 900 may include: a communication unit 901 and a processing unit 902.
[0237] In the embodiments of the present application, the communication unit 901 may also be referred to as a transceiver unit, and may include a transmitting unit and / or a receiving unit, each configured to execute the steps of transmitting and receiving by the first device or the second device in the above method embodiments. The processing unit 902 may be configured to read instructions and / or data from the storage module to enable the communication device 900 to implement the above method embodiments.
[0238] Optionally, the communication device 900 may further include a storage unit 903 , which is equivalent to a storage module and may be used to store instructions and / or data.
[0239] The communication device provided in the embodiment of the present application is described in detail below with reference to Figures 9 and 10. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment. Therefore, for matters not described in detail, reference can be made to the method embodiment above. For the sake of brevity, they will not be repeated here.
[0240] The communication unit 901 may also be referred to as a transceiver, transceiver, or transceiver device. The processing unit may also be referred to as a processor, processing board, processing module, or processing device. Alternatively, the device in the communication unit 901 that implements the receiving function may be considered a receiving unit, and the device in the communication unit 901 that implements the transmitting function may be considered a transmitting unit. That is, the communication unit 901 includes both a receiving unit and a transmitting unit. A communication unit may also be referred to as a transceiver, transceiver, or transceiver circuit. A receiving unit may also be referred to as a receiver, receiver, or receiving circuit. A transmitting unit may also be referred to as a transmitter, transmitter, or transmitting circuit.
[0241] When the communication device 900 performs the function of the first device in the process shown in Figure 4 of the above embodiment: the processing unit 902 is used to determine the first state information; the first state information is the input information of the first model, the first model is used to predict the decision information of the first device accessing the channel, and the first state information includes the occupancy information of the channel and the node information of the node occupying the resources of the channel exceeding the preset resource threshold; the communication unit 901 sends the first state information to the second device; the communication unit 901 is also used to receive the model parameters of the first model from the second device; the model parameters include the biases and / or weights corresponding to different variables in the first model; the biases and / or weights corresponding to the different variables are determined by the second device according to the first state information; the processing unit 902 is used to update the first model based on the model parameters of the first model to obtain an updated first model; and is also used to input the first state information into the updated first model, and obtain the decision information of the first device accessing the channel based on the output of the updated first model.
[0242] In one possible implementation, the occupancy information of the channel includes a first occupancy rate of the channel occupied by the first device based on the target access type and a second occupancy rate of the channel occupied by other devices based on the target access type, where the other devices are at least one device occupying the channel other than the first device.
[0243] In one possible implementation, the second occupancy may be determined in the following manner: sending the first occupancy to the second device through the communication unit 901; and receiving first information from the second device; the first information includes the total occupancy of the target access type occupying the channel, and the total occupancy is obtained by the second device based on the first occupancy and the occupancy of the channel occupied by the other devices based on the target access type; and subtracting the first occupancy of the first device from the total occupancy through the processing unit 902 to obtain the second occupancy.
[0244] In one possible implementation, the communication unit 901 can also be used to: receive second information from the second device before sending the first occupancy to the second device, the second information including the channel occupancy threshold of the target access type; and determine through the processing unit 902 that the first occupancy of the first device is greater than the channel occupancy threshold.
[0245] In a possible implementation, the communication unit 901 may also be used to: receive a first request message from the second device, where the first request message is used to request the first device to occupy a first occupancy rate of the channel based on a target access type.
[0246] In one possible implementation, the node information includes the number of the nodes, and the nodes specifically refer to devices whose resource occupancy rate of the channel based on the target access type is greater than the resource occupancy rate threshold of the channel based on the target access type.
[0247] In one possible implementation, the number of nodes can be obtained in the following manner: the number of nodes is received from the second device through the communication unit 901, and the number of nodes is obtained by the second device based on the resource occupancy rate of the channel occupied by the first device based on the target access type and the resource occupancy rate of the channel occupied by other devices based on the access type, as well as the resource occupancy rate threshold of the channel.
[0248] In a possible implementation, the target access type is one or more of the following: an access type for voice data, an access type for video data, an access type for data with maximum transmission capability, and an access type for background data.
[0249] In one possible implementation, the first status information also includes one or more of the following: carrier sensing result information of the channel in a preset historical time period, the length of time between the time when the first device currently sends data and the time when the first device last successfully sent data, and the length of time between the time when other devices currently send data and the time when the other devices last successfully sent data.
[0250] In one possible implementation, when the decision information for accessing the channel is the probability value of the first device successfully accessing the channel, the processing unit 902 can also be used to: obtain the contention window duration for the first device to access the channel based on the probability value of the channel, and the first device accesses the channel within the contention window duration.
[0251] In a possible implementation, the first device is a station, and the second device is an access point.
[0252] When the communication device 900 performs the function of the second device in the process shown in Figure 4 of the above embodiment: the communication unit 901 is used to receive first state information from the first device; the first state information is input information of the first model, and the first model is used to predict the decision information of the first device accessing the channel, and the first state information includes the occupancy information of the channel and the node information of the node occupying the resources of the channel exceeding the preset resource threshold; the processing unit 902 is used to determine the model parameters of the first model based on the first state information; the model parameters include the bias and / or weight corresponding to each variable in the first model; the communication unit 901 can also be used to send the model parameters of the first model to the first device.
[0253] In one possible implementation, the communication unit 901 may also be used to: receive the occupancy rate of the channel occupied by at least one device based on the target access type, the at least one device including the first device; the processing unit 902 may also be used to determine the total occupancy rate of the channel occupied based on the target access type according to the occupancy rate of the channel occupied by the at least one device based on the target access type; the communication unit 901 may also be used to send first information to the first device, the first information including the total occupancy rate of the channel occupied based on the target access type.
[0254] In one possible implementation, the channel occupancy information includes a first occupancy rate of the channel occupied by the first device based on the target access type and a second occupancy rate of the channel occupied by other devices based on the target access type, where the other devices are at least one device other than the first device that occupies the channel; the node information includes the number of nodes, and the node specifically refers to a device whose resource occupancy rate of the channel based on the target access type is greater than a resource occupancy rate threshold of the channel based on the target access type.
[0255] In one possible implementation, when determining the model parameters of the first model based on the first state information, the processing unit 902 can be specifically used to: based on the first state information and reward function information, use a reinforcement learning method to train to obtain the model parameters of the first model, and the reward function information is associated with the first occupancy rate of the first device.
[0256] In a possible implementation, the target access type is one or more of the following: an access type for voice data, an access type for video data, an access type for data with maximum transmission capability, and an access type for background data.
[0257] In one possible implementation, the first status information also includes one or more of the following: carrier sensing result information of the channel in a preset historical time period, the length of time between the time when the first device currently sends data and the time when the first device last successfully sent data, and the length of time between the time when other devices currently send data and the time when the other devices last successfully sent data.
[0258] In a possible implementation, the first device is a station, and the second device is an access point.
[0259] FIG10 shows a communication device 1000 provided in an embodiment of the present application. The communication device shown in FIG10 may be a hardware circuit implementation of the communication device shown in FIG9 . The communication device 1000 may be applicable to the flowchart shown above to perform the functions of the first device or the second device in the above-described method embodiment. For ease of illustration, FIG10 only shows the main components of the communication device.
[0260] As shown in Figure 10, communication device 1000 includes a communication interface 1001 and a processor 1002. Communication interface 1001 and processor 1002 are coupled to each other. It is understood that communication interface 1001 can be a transceiver or an input / output interface, or an interface circuit such as a transceiver circuit. Optionally, communication device 1000 can also include a memory 1003 for storing instructions executed by processor 1002, input data required by processor 1002 to execute instructions, or data generated by processor 1002 after executing instructions.
[0261] When the communication device 1000 is used to implement the method shown in FIG. 4 , the processor 1002 is used to implement the functions of the processing unit 902 , and the communication interface 1001 is used to implement the functions of the communication unit 901 .
[0262] The specific connection medium between the communication interface 1001, processor 1002, and memory 1003 is not limited in the embodiments of the present application. In Figure 10, the memory 1003, processor 1002, and communication interface 1001 are connected via a communication bus 1004. The communication bus 1004 is represented by a bold line in Figure 10. The connection methods between other components are only for schematic illustration and are not limiting. The communication bus 1004 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bold line is used in Figure 10, but this does not mean that there is only one bus or one type of bus.
[0263] When the communication device is a chip, FIG11 shows a simplified schematic diagram of the chip structure, wherein the chip 1100 includes an interface circuit 1101 and one or more processors 1102. Optionally, the chip 1100 may further include a bus.
[0264] The processor 1102 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above-mentioned communication method can be completed by an integrated logic circuit of the hardware in the processor 1102 or an instruction in the form of software. The above-mentioned processor 1102 can be a general-purpose processor, a digital communicator (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods and steps disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
[0265] The interface circuit 1101 can be used to send or receive data, instructions or information. The processor 1102 can use the data, instructions or other information received by the interface circuit 1101 to process it, and can send the processing completion information through the interface circuit 1101.
[0266] Optionally, the chip further includes a memory 1103, which may include a read-only memory and a random access memory, and provides operation instructions and data to the processor. A portion of the memory 1103 may also include a non-volatile random access memory (NVRAM).
[0267] Optionally, the memory stores an executable software module or a data structure, and the processor can perform corresponding operations by calling an operation instruction stored in the memory (the operation instruction may be stored in an operating system).
[0268] Optionally, the chip can be used in the first device or the second device involved in the embodiments of the present application. Optionally, the interface circuit 1101 can be used to output the execution result of the processor 1102. For the channel access method provided in one or more embodiments of the present application, reference can be made to the aforementioned embodiments and will not be repeated here.
[0269] It should be noted that the corresponding functions of the interface circuit 1101 and the processor 1102 can be implemented through hardware design, software design, or a combination of hardware and software, and there is no limitation here.
[0270] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions for implementing the method executed by the first device or the second device in the above method embodiment.
[0271] For example, when the computer program is executed by a computer, the computer can implement the method performed by the first device or the second device in the above method embodiment.
[0272] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed by a computer, enables the computer to implement the method performed by the first device or the second device in the above method embodiment.
[0273] An embodiment of the present application also provides a chip device, including a processor, for calling the computer program or computer instructions stored in the memory so that the processor executes the channel access method of the embodiments shown in Figures 4-7 and Figures 8A-8B above.
[0274] In one possible implementation, the input of the chip device corresponds to the receiving operation in the embodiment shown in FIG. 4 , and the output of the chip device corresponds to the sending operation in the embodiments shown in FIG. 4 to FIG. 7 and FIG. 8A to FIG. 8B .
[0275] Optionally, the processor is coupled to the memory via an interface.
[0276] Optionally, the chip device further includes a memory, in which computer programs or computer instructions are stored.
[0277] The processor mentioned in any of the above may be a general-purpose central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of a program of a channel access method according to the embodiments shown in Figures 4-7 and 8A-8B. The memory mentioned in any of the above may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM), etc.
[0278] It should be noted that, for the sake of convenience and brevity of description, the explanation and beneficial effects of the relevant contents in any of the communication devices provided above can refer to the corresponding channel access method embodiments provided above, and will not be repeated here.
[0279] In the present application, the communication devices may further include a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system layer. The hardware layer may include hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory (also known as main memory). The operating system of the operating system layer may be any one or more computer operating systems that implement business processing through processes, such as the Linux operating system, Unix operating system, Android operating system, iOS operating system, or Windows operating system. The application layer may include applications such as browsers, address books, word processing software, and instant messaging software.
[0280] The module division in the embodiments of the present application is illustrative and represents only one logical functional division. In actual implementation, other divisions may be employed. Furthermore, the functional modules in the various embodiments of the present application may be integrated into a single processor, exist as separate physical components, or be integrated into a single module. These integrated modules may be implemented in either hardware or software functional modules.
[0281] Through the description of the above embodiments, it will be clear to those skilled in the art that the embodiments of the present application can be implemented in hardware, firmware, or a combination thereof. When software is used for implementation, the above functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein the communication media include any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that a computer can access. For example, but not limited to: a computer-readable medium may include RAM, ROM, electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer. In addition, any connection can be appropriately a 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, then 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, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc, where disks typically reproduce data magnetically and discs use lasers to reproduce data optically. Combinations of the above should also be included within the scope of protection of computer-readable media.
[0282] In short, the above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made based on the disclosure of the present application should be included in the scope of protection of the present application.
Claims
1. A channel access method, characterized in that: include: The first device determines first status information; The first state information is input information of a first model, the first model is used to predict decision information of the first device accessing a channel, and the first state information includes occupancy information of the channel and node information of nodes whose resources occupying the channel exceed a preset resource threshold; The first device sends the first status information to the second device; The first device receives model parameters of the first model from the second device; the model parameters include biases and / or weights corresponding to different variables in the first model respectively; The biases and / or weights respectively corresponding to the different variables are determined by the second device according to the first state information; The first device updates the first model based on the model parameters of the first model to obtain an updated first model; The first device inputs the first state information into the updated first model, and obtains decision information of the first device accessing the channel based on an output of the updated first model.
2. The method according to claim 1, characterized in that The occupancy information of the channel includes a first occupancy rate of the first device occupying the channel based on the target access type and a second occupancy rate of other devices occupying the channel based on the target access type, and the other device is at least one device occupying the channel except the first device.
3. The method according to claim 2, characterized in that The second occupancy rate is determined by: The first device sends the first occupancy rate to the second device; The first device receives first information from the second device; the first information includes a total occupancy rate of the channel occupied by the target access type, and the total occupancy rate is obtained by the second device according to the first occupancy rate and the occupancy rate of the channel occupied by other devices based on the target access type; The first device subtracts the first occupancy of the first device from the total occupancy to obtain the second occupancy.
4. The method according to claim 3, characterized in that Before the first device sends the first occupancy rate to the second device, the method further includes: The first device receives second information from the second device, where the second information includes a channel occupancy threshold of the target access type; and the first device determines that the first occupancy of the first device is greater than the channel occupancy threshold.
5. The method according to claim 3 or 4, characterized in that: The method further comprises: The first device receives a first request message from the second device, where the first request message is used to request the first device to occupy a first occupancy rate of the channel based on a target access type.
6. The method according to claim 1, characterized in that The node information includes the number of the nodes, and the nodes specifically refer to devices whose resource occupancy rate of the channel based on the target access type is greater than a resource occupancy rate threshold of the channel based on the target access type.
7. The method according to claim 6, characterized in that The number of nodes is obtained by: The first device receives the number of nodes from the second device, and the number of nodes is obtained by the second device based on the resource occupancy rate of the channel occupied by the first device based on the target access type, the resource occupancy rate of the channel occupied by other devices based on the access type, and the resource occupancy rate threshold of the channel.
8. The method according to any one of claims 2 to 7, characterized in that: The target access type is one or more of the following: Access type for voice data, access type for video data, access type for data with maximum transmission capability, and access type for background data.
9. The method according to any one of claims 1 to 8, characterized in that: The first status information also includes one or more of the following: The carrier sensing result information of the channel in a preset historical time period, the length of time between the current data transmission time of the first device and the last successful data transmission time of the first device, and the length of time between the current data transmission time of other devices and the last successful data transmission time of the other devices.
10. The method according to any one of claims 1 to 8, characterized in that: When the decision information for the first device to access the channel is a probability value of the first device successfully accessing the channel, the method further includes: The first device obtains a contention window duration for the first device to access the channel based on the probability value of the channel, and the first device accesses the channel within the contention window duration.
11. The method according to any one of claims 1 to 10, characterized in that The first device is a station, and the second device is an access point.
12. A channel access method, characterized in that: include: The second device receives the first status information from the first device; The first state information is input information of a first model, the first model is used to predict decision information of the first device accessing a channel, and the first state information includes occupancy information of the channel and node information of nodes whose resources occupying the channel exceed a preset resource threshold; The second device determines model parameters of the first model according to the first state information; the model parameters include biases and / or weights corresponding to different variables in the first model respectively; The second device sends the model parameters of the first model to the first device.
13. The method according to claim 12, characterized in that The method further comprises: The second device receives an occupancy rate of the channel occupied by at least one device based on a target access type, wherein the at least one device includes the first device; The second device determines, according to the occupancy rate of the channel occupied by the at least one device based on the target access type, a total occupancy rate of the channel occupied based on the target access type; The second device sends first information to the first device, where the first information includes a total occupancy rate of the channel based on the target access type.
14. The method according to claim 12, characterized in that The occupancy information of the channel includes a first occupancy rate of the first device occupying the channel based on the target access type and a second occupancy rate of other devices occupying the channel based on the target access type, wherein the other device is at least one device occupying the channel except the first device; The node information includes the number of the nodes, and the nodes specifically refer to devices whose resource occupancy rate of the channel based on the target access type is greater than a resource occupancy rate threshold of the channel based on the target access type.
15. The method according to claim 14, characterized in that The second device determines, according to the first state information, a model parameter of the first model, including: The second device uses a reinforcement learning method to train model parameters of the first model based on the first state information and reward function information, and the reward function information is associated with the first occupancy rate of the first device.
16. The method according to any one of claims 13 to 15, characterized in that The target access type is one or more of the following: Access type for voice data, access type for video data, access type for data with maximum transmission capability, and access type for background data.
17. The method according to any one of claims 12 to 16, characterized in that: The first status information also includes one or more of the following: The carrier sensing result information of the channel in a preset historical time period, the length of time between the current data transmission time of the first device and the last successful data transmission time of the first device, and the length of time between the current data transmission time of other devices and the last successful data transmission time of the other devices.
18. The method according to any one of claims 12 to 17, characterized in that The first device is a station, and the second device is an access point.
19. A communication device, characterized in that: The method comprises a unit for executing the method according to any one of claims 1 to 11, or comprises a unit for executing the method according to any one of claims 12 to 18.
20. A communication device, characterized in that: include: Processor and memory; The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instructions in the memory, so that the device performs the method according to any one of claims 1 to 11, or the device performs the method according to any one of claims 12 to 18.
21. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when called by an electronic device, enable the electronic device to execute the method as claimed in any one of claims 1 to 11 or enable the electronic device to execute the method as claimed in any one of claims 12 to 18.
22. A computer program product, characterized in that The method comprises computer-executable instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 11 or cause the computer to execute the method according to any one of claims 12 to 18.
23. A communication system, characterized in that: The invention comprises an apparatus for executing the method according to any one of claims 1 to 11 and an apparatus for executing the method according to any one of claims 12 to 18.
Citation Information
Patent Citations
Communication resource allocation method and device of unauthorized frequency band based on reinforcement learning
CN114928549A
Channel access method and related device
CN115499936A
Wireless network channel state prediction method and device, equipment and storage medium
CN115802401A
A Method and Apparatus for Distributed Congestion Control of VANET using Reinforcement Learning Based on Neural Network Model
KR102257536B1
Methods for federated learning over wireless (FLOW) in wireless local area networks (WLAN)
WO2023059639A1
