Data transmission method, device and equipment, readable storage medium and program product

Abstract

The invention relates to a data transmission method and device, equipment, a readable storage medium and a program product, and particularly relates to the technical field of communication. The method comprises the following steps: acquiring transmission state data of a wireless communication network; determining a first window value of a congestion window in the wireless communication network according to the transmission state data; acquiring a second window value of a congestion window in the target communication network; determining a target window value according to the first window value and the second window value; and transmitting the target data packet to the second data transmission end according to the target window value. By adopting the method, the congestion condition in the wireless communication network can be sensed in time based on the transmission state data in the wireless communication network, so that the conditions that the network transmission delay is increased, the packet loss rate is suddenly increased and the like due to the fact that the congestion condition of the wireless communication network is not sensed in time are reduced to a certain extent.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a data transmission method, apparatus, device, readable storage medium, and program product. Background Technology

[0002] In the field of communication technology, in order to avoid network congestion, traditional congestion control methods use a congestion window to control congestion.

[0003] Traditional congestion control methods often use congestion control algorithms based on the Transmission Control Protocol (TCP) to sense the network status between the data sender and receiver and adjust the congestion window accordingly.

[0004] However, in the data transmission scenario of wireless communication networks, traditional congestion control methods cannot detect the congestion situation in the wireless communication network in a timely manner, and therefore cannot perform accurate congestion control, which can easily lead to increased network transmission latency, sudden increase in packet loss rate, and other problems. Summary of the Invention

[0005] Therefore, it is necessary to provide a data transmission method, apparatus, device, readable storage medium, and program product that can promptly detect congestion in wireless communication networks to reduce network transmission latency and packet loss rate, in order to address the aforementioned technical problems.

[0006] In a first aspect, this application provides a data transmission method applied to a first data transmission end, wherein the first data transmission end and a second data transmission end are communicatively connected via a wireless access device; a wireless communication network is deployed between the first data transmission end and the wireless access device; and a target communication network is deployed between the first data transmission end and the second data transmission end; the method includes:

[0007] Acquire transmission status data from the wireless communication network;

[0008] Based on the transmission status data, determine the first window value of the congestion window in the wireless communication network;

[0009] Obtain the second window value of the congestion window in the target communication network;

[0010] Determine the target window value based on the first window value and the second window value;

[0011] Based on the target window value, transmit the target data packet to the second data transmission terminal.

[0012] In one embodiment, determining the first window value of the congestion window in the wireless communication network based on transmission status data includes: inputting the transmission status data into a pre-trained congestion window adjustment model to obtain window adjustment information for the current data transmission process; the congestion window adjustment model is implemented based on a reinforcement learning algorithm; and adjusting the first window value for the previous data transmission process based on the window adjustment information to obtain the first window value for the current data transmission process.

[0013] In one embodiment, the congestion window adjustment model is trained through the following steps: In each iteration, the sample transmission state data of the sample wireless communication network in the previous iteration is used as the current transmission state data in the current iteration; based on the current transmission state data, the sample window adjustment information in the previous iteration is evaluated to obtain the sample evaluation result; based on the current transmission state data and the sample evaluation result, the sample window value in the previous iteration is adjusted to obtain the current sample window value in the current iteration; based on the current sample window value, data is transmitted to obtain the sample transmission state data in the current iteration; based on the current transmission state data and the sample evaluation result, the sample window value in the previous iteration is adjusted to obtain the current sample window value in the current iteration; based on the current sample window value, data is transmitted to obtain the sample transmission state data in the current iteration; based on the current transmission state data in the current iteration... The congestion window adjustment model is tuned based on the sample evaluation results from the first iteration and the sample evaluation results from the previous iteration until the iteration termination condition is met. The current transmission status data in the first iteration is obtained by adjusting the preset sample window value according to the preset window adjustment information, and then transmitting data based on the current sample window value. The sample evaluation results in the first iteration are obtained by evaluating the preset window adjustment information. The iteration termination condition includes: the change in the cumulative reward parameter between two adjacent iterations satisfies the first preset condition, and the change in the amount of data transmitted between two adjacent iterations satisfies the second preset condition.

[0014] In one embodiment, the sample window adjustment information of the previous iteration is evaluated based on the current transmission status data to obtain a sample evaluation result, including: determining the cumulative reward parameter of the current iteration based on the current transmission status data; and obtaining the sample evaluation result of evaluating the sample window adjustment information of the previous iteration based on the cumulative reward parameter of the current iteration and the cumulative reward parameter of the previous iteration.

[0015] In one embodiment, the current transmission status data includes throughput data, round-trip time data, packet loss rate data, and the rate of change of round-trip time data; accordingly, based on the current transmission status data, the cumulative reward parameter under the local iteration process is determined, including: weighted summation of the rate of change of throughput data, round-trip time data, packet loss rate data, and round-trip time data to obtain the cumulative reward parameter under the local iteration process.

[0016] In one embodiment, the sample window value under the previous iteration is adjusted based on the current transmission status data and the sample evaluation results to obtain the current sample window value under the current iteration. This includes: determining the current window adjustment information under the current iteration based on the current transmission status data and the evaluation results; and adjusting the window value under the previous iteration based on the current window adjustment information to obtain the current window value under the current iteration.

[0017] In one embodiment, determining a target window value based on a first window value and a second window value includes: determining the target window value based on the size relationship between the first window value and the second window value.

[0018] In one embodiment, when the target data packet is the first service data packet in the initial data transmission process from the first data transmission end to the second data transmission end, obtaining the second window value of the congestion window in the target communication network includes: obtaining the initial window value of the congestion window in the target communication network and using the initial window value as the second window value; correspondingly, determining the target window value according to the size relationship between the first window value and the second window value includes: if the first window value is less than or equal to the second window value, using the first window value as the target window value; if the first window value is greater than the second window value, determining the target window value according to the second window value.

[0019] In one embodiment, determining a target window value based on a second window value includes: determining an adjustment parameter corresponding to the second window value based on the window range to which the first window value belongs; wherein the window threshold in the window range is determined based on the second window value; and determining the target window value based on the adjustment parameter and the second window value.

[0020] In one embodiment, when the target data packet is not the first service data packet in the process of the first data transmission from the first data transmission terminal to the second data transmission terminal, the target window value is determined according to the size relationship between the first window value and the second window value, including: taking the smaller value of the first window value and the second window value as the target window value.

[0021] Secondly, this application also provides a data transmission device, configured at a first data transmission end, wherein the first data transmission end and a second data transmission end are communicatively connected via a wireless access device; a wireless communication network is deployed between the first data transmission end and the wireless access device; a target communication network is deployed between the first data transmission end and the second data transmission end; the device includes:

[0022] The first acquisition module is used to acquire transmission status data of the wireless communication network;

[0023] The first determining module is used to determine the first window value of the congestion window in the wireless communication network based on the transmission status data.

[0024] The second acquisition module is used to acquire the second window value of the congestion window in the target communication network;

[0025] The second determining module is used to determine the target window value based on the first window value and the second window value;

[0026] The sending module is used to transmit the target data packet to the second data transmission terminal according to the target window value.

[0027] Thirdly, this application also provides a computer device configured at a first data transmission end, wherein the first data transmission end and a second data transmission end are communicatively connected via a wireless access device; a wireless communication network is deployed between the first data transmission end and the wireless access device; a target communication network is deployed between the first data transmission end and the second data transmission end; the computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0028] Acquire transmission status data from the wireless communication network;

[0029] Based on the transmission status data, determine the first window value of the congestion window in the wireless communication network;

[0030] Obtain the second window value of the congestion window in the target communication network;

[0031] Determine the target window value based on the first window value and the second window value;

[0032] Based on the target window value, transmit the target data packet to the second data transmission terminal.

[0033] Fourthly, this application also provides a computer-readable storage medium configured at a first data transmission end, wherein the first data transmission end and a second data transmission end are communicatively connected via a wireless access device; a wireless communication network is deployed between the first data transmission end and the wireless access device; a target communication network is deployed between the first data transmission end and the second data transmission end; a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it performs the following steps:

[0034] Acquire transmission status data from the wireless communication network;

[0035] Based on the transmission status data, determine the first window value of the congestion window in the wireless communication network;

[0036] Obtain the second window value of the congestion window in the target communication network;

[0037] Determine the target window value based on the first window value and the second window value;

[0038] Based on the target window value, transmit the target data packet to the second data transmission terminal.

[0039] Fifthly, this application also provides a computer program product configured on a first data transmission terminal, wherein the first data transmission terminal and a second data transmission terminal are communicatively connected via a wireless access device; a wireless communication network is deployed between the first data transmission terminal and the wireless access device; a target communication network is deployed between the first data transmission terminal and the second data transmission terminal; the computer program product includes a computer program, which, when executed by a processor, performs the following steps:

[0040] Acquire transmission status data from the wireless communication network;

[0041] Based on the transmission status data, determine the first window value of the congestion window in the wireless communication network;

[0042] Obtain the second window value of the congestion window in the target communication network;

[0043] Determine the target window value based on the first window value and the second window value;

[0044] Based on the target window value, transmit the target data packet to the second data transmission terminal.

[0045] The aforementioned data transmission method, apparatus, device, readable storage medium, and program product determine the first window value of the congestion window in the wireless communication network based on the transmission status data of the wireless communication network. This enables timely perception of congestion in the wireless communication network based on the transmission status data. After determining the first window value of the congestion window in the wireless communication network, a more accurate target window value can be obtained by combining the first window value with the second window value of the congestion window in the target communication network. This allows for precise congestion control based on the target window value, reducing, to some extent, the increase in network transmission delay and sudden increase in packet loss rate caused by untimely perception of congestion in the wireless communication network. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is an application environment diagram of a data transmission method in one embodiment;

[0048] Figure 2 This is a flowchart illustrating a data transmission method in one embodiment;

[0049] Figure 3 This is a flowchart illustrating the steps for determining the first window value in one embodiment;

[0050] Figure 4 This is a flowchart illustrating the training steps of a congestion window adjustment model in one embodiment.

[0051] Figure 5 This is a flowchart illustrating the steps for determining the target window value in one embodiment;

[0052] Figure 6 This is a flowchart illustrating the data transmission method in another embodiment;

[0053] Figure 7 This is a flowchart illustrating the steps for obtaining the congestion window value in a WiFi network in one embodiment.

[0054] Figure 8 This is a flowchart illustrating the training steps of the congestion window adjustment model in another embodiment.

[0055] Figure 9 This is a flowchart illustrating the data transmission method in yet another embodiment;

[0056] Figure 10 This is a flowchart illustrating the data transmission method in yet another embodiment;

[0057] Figure 11 This is a structural block diagram of a data transmission device in one embodiment;

[0058] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] The data transmission method provided in this application can be applied to scenarios where a first data transmission terminal transmits data to a second data transmission terminal. For example, it can be applied to scenarios where a wireless terminal sends video data to a client. For example, the wireless terminal may include an Internet Protocol Camera (IPC), etc. The client may include, but is not limited to, personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices may include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices may include virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0061] For example, in Figure 1 In the application scenario shown, a wireless access device can be deployed between the first data transmission end, i.e., the wireless terminal (such as a wireless network camera), and the second data transmission end, i.e., the client. The wireless terminal can communicate with the wireless access device via a Layer 2 wireless network. The wireless access device can communicate with the client via a Layer 3 Internet Protocol (IP) network. The wireless terminal can send video data within its field of view to the client via the wireless access device for viewing.

[0062] In one exemplary embodiment, such as Figure 2 As shown, a data transmission method is provided. This embodiment illustrates the application of this method to a first data transmission terminal. In this embodiment, the first data transmission terminal and the second data transmission terminal are communicatively connected via a wireless access device. A wireless communication network is deployed between the first data transmission terminal and the wireless access device. A target communication network is deployed between the first data transmission terminal and the second data transmission terminal.

[0063] This can be understood as the target communication network including a wireless communication network between the first data transmission terminal and the wireless access device, and a third communication network between the wireless access device and the second data transmission terminal. Optionally, the third communication network may include a wireless communication network between the wireless access device and the public cloud platform, and a communication network between the public cloud platform and the second data transmission terminal. Optionally, the communication network between the public cloud platform and the second data transmission terminal may include a wireless communication network or a mobile communication network. Optionally, the wireless communication network may include a Wireless Fidelity (WiFi) network.

[0064] Figure 2The data transmission method shown includes the following steps:

[0065] S210, acquire transmission status data of the wireless communication network.

[0066] Among them, transmission status data can be understood as at least one of the following: Received Signal Strength Indicator (RSSI), negotiated transmission rate (RATE), transmission throughput (TP), round-trip time (RTT), number of retransmissions (TRY), and packet loss rate (LOSS) at the current moment.

[0067] In wireless communication networks, RSSI can be denoted as W-RSSI, which can be understood as the strength of the received signal in the wireless communication network, and the unit is decibel milliwatt (dBm).

[0068] In this context, the RATE of a wireless communication network can be denoted as W-RATE, which can be understood as the transmission rate negotiated between the first data transmission end and the second data transmission end in the wireless communication network.

[0069] The transmission throughput of the wireless communication network can be denoted as W-TP, which can be understood as the amount of data transmitted per second by the first data transmission end through the wireless communication network.

[0070] The round-trip time (RTT) of a wireless communication network can be denoted as W-RTT, which can be understood as the total time consumed in the complete process of a data packet being sent from the first data transmission end to the second data transmission end confirming and returning.

[0071] In wireless communication networks, the number of retransmissions (TRY) can be denoted as W-TRY, which can be understood as the number of times data packets are retransmitted.

[0072] The packet loss rate of a wireless communication network can be denoted as W-LOSS, which can be understood as the proportion of data packets lost during data transmission to the total number of data packets sent.

[0073] In one optional embodiment, obtaining transmission status data of a wireless communication network may include the following steps: obtaining initial status data of the wireless communication network at the current moment; and using a correlation analysis method to extract target status data that meets the correlation requirements from the initial status data as transmission status data.

[0074] In an optional embodiment, when the wireless communication network is a WiFi network, obtaining the initial state data of the wireless communication network at the current moment may include: obtaining the initial state data of the WiFi network at the current moment through the WiFi driver.

[0075] In an alternative embodiment, where there is little or no interference in the wireless communication network, W-RTT can be approximated by the RTT of the wireless router in the Packet Internet Groper (PING) network, and W-LOSS can be approximated by the packet loss rate of the wireless router in the PING network, thereby reducing the complexity of data acquisition.

[0076] S220, Based on the transmission status data, determine the first window value of the congestion window in the wireless communication network.

[0077] Among them, transmission status data can reflect the network status of the wireless communication network, and the first window value of the congestion window that matches the network status of the wireless communication network can be determined based on the transmission status data.

[0078] The congestion window can be understood as the congestion control window (CWND) maintained by the first data transmission end, representing the amount of data that the first data transmission end can send to the wireless access device. The unit of the congestion window is a segment.

[0079] The first window value can be understood as the amount of data that the first data transmission end can send to the wireless access device.

[0080] S230, obtain the second window value of the congestion window in the target communication network.

[0081] In an optional embodiment, the second window value of the congestion window in the target communication network can be obtained according to a conventional TCP congestion control algorithm. The second window value can be understood as the amount of data that the first data transmission end can send to the second data transmission end, as obtained according to the conventional TCP congestion control algorithm.

[0082] Optionally, traditional TCP congestion control algorithms may include at least one of the following: congestion control algorithms based on packet loss rate, congestion control algorithms based on round-trip time, and congestion control algorithms based on bottleneck bandwidth and round-trip propagation time (BBR). This embodiment does not elaborate on the specific process of obtaining the second window value using traditional TCP congestion control algorithms.

[0083] It should be noted that the execution order of S210 and S230 is not limited in this embodiment.

[0084] S240, determine the target window value based on the first window value and the second window value.

[0085] The target window value can be understood as the amount of data that the first data transmission terminal can transmit to the second data transmission terminal, determined based on the first window value and the second window value.

[0086] S250: Based on the target window value, transmit the target data packet to the second data transmission terminal.

[0087] The target data packet can be understood as the business data packet to be sent. For example, the target data packet can be a video data packet.

[0088] In an optional embodiment, when the target data packet is a video data packet, the target data packet may be obtained in the following manner: obtaining the video data corresponding to the current video frame; dividing the video data according to a preset maximum segment size (MSS) to obtain at least one video data packet of size MSS; if the remaining video data after obtaining at least one video data packet is less than MSS, the remaining video data is treated as a single video data packet.

[0089] In the aforementioned data transmission method, determining the first window value of the congestion window in the wireless communication network based on the transmission status data of the wireless communication network enables timely perception of congestion in the wireless communication network. After determining the first window value of the congestion window in the wireless communication network, combining it with the second window value of the congestion window in the target communication network yields a more accurate target window value. This allows for precise congestion control based on the target window value, reducing, to some extent, the increase in network transmission delay and sudden spikes in packet loss caused by untimely perception of congestion in the wireless communication network.

[0090] Based on the technical solutions of the above embodiments, this application also provides another optional embodiment, in which the step of determining the first window value in S220 is refined.

[0091] See Figure 3 The steps for determining the first window value shown include:

[0092] S310, input the transmission status data into the pre-trained congestion window adjustment model to obtain the window adjustment information during this data transmission process; the congestion window adjustment model is implemented based on the reinforcement learning algorithm.

[0093] The window adjustment information can be understood as information on adjusting the congestion window in the wireless communication network.

[0094] Optionally, window adjustment information may include adjustment direction and adjustment value. Adjustment direction can be understood as increasing or decreasing the value. Adjustment value can be understood as the magnitude of the adjusted value.

[0095] S320: Based on the window adjustment information, adjust the first window value under the previous data transmission process to obtain the first window value under the current data transmission process.

[0096] In this embodiment, by utilizing a congestion window adjustment model based on reinforcement learning algorithms, changes in the transmission state in the wireless communication network can be quickly detected. This allows for the adjustment of the first window value from the previous data transmission process during each data transmission process, resulting in the first window value for the current data transmission process. This enables rapid and precise control of the congestion window, thus improving the problem of inaccurate congestion window control caused by untimely congestion detection in the wireless communication network.

[0097] Based on the technical solutions of the above embodiments, this application also provides another optional embodiment, in which the training process of the congestion window adjustment model is described.

[0098] See Figure 4 The training steps for the congestion window adjustment model shown include:

[0099] S410: In each iteration, the sample transmission state data of the sample wireless communication network in the previous iteration is used as the current transmission state data in the current iteration.

[0100] The sample wireless communication network can be understood as a communication network that is the same as or similar to the wireless communication network.

[0101] The sample transmission status data can be understood as the data obtained after transmitting the data using the current sample window value from the previous iteration.

[0102] S420: Based on the current transmission status data, evaluate the sample window adjustment information from the previous iteration to obtain the sample evaluation result.

[0103] The sample window adjustment information can be understood as the information used to adjust the congestion window of the sample wireless communication network during training. This information can include the adjustment direction and size.

[0104] In this context, evaluating the sample window adjustment information from the previous iteration can be understood as evaluating the execution actions corresponding to the sample window adjustment information.

[0105] The execution action corresponding to the sample window adjustment information can be understood as the action of executing the sample window adjustment information, that is, the action of adjusting the direction and size of the congestion window of the sample wireless communication network.

[0106] The sample evaluation result can be understood as the evaluation result obtained by evaluating the execution action corresponding to the sample window adjustment information.

[0107] In one optional embodiment, evaluating the sample window adjustment information from the previous iteration based on the current transmission status data to obtain a sample evaluation result may include: determining the cumulative reward parameter for the current iteration based on the current transmission status data; and obtaining the sample evaluation result for evaluating the sample window adjustment information from the previous iteration based on the cumulative reward parameter for the current iteration and the cumulative reward parameter for the previous iteration.

[0108] The cumulative reward parameter in the previous iteration can be understood as the reward parameter accumulated from the first iteration to the previous iteration.

[0109] The cumulative reward parameter in this iteration process can be understood as the reward parameter accumulated from the first iteration process to the current iteration process.

[0110] In one optional embodiment, the current transmission status data may include throughput data, round-trip time (RTD) data, packet loss rate data, and the rate of change of RTD data. Determining the cumulative reward parameter for the local iteration process based on the current transmission status data may include: weighted summation of the rates of change of throughput data, RTD data, packet loss rate data, and RTD data to obtain the cumulative reward parameter for the local iteration process.

[0111] It can be understood here that the cumulative reward parameter in any iteration process can be determined based on the current transmission state data in that iteration process. The steps for determining the cumulative reward parameter in any iteration process are similar to the steps for determining the cumulative reward parameter in the current iteration process, and will not be repeated here.

[0112] In an optional embodiment, the cumulative reward parameter can be obtained by the following formula:

[0113]

[0114] in, This represents the cumulative reward parameter; This represents the throughput in a wireless communication network; Indicates the round-trip delay in a wireless communication network; This represents the packet loss rate in a wireless communication network. This indicates the rate of change of round-trip time delay; , , , These represent hyperparameters. and The round-trip time and packet loss rate of the wireless router in the network can be used as an approximation by PING.

[0115] It should be noted that the formula for determining the cumulative reward parameters can be set according to user needs, and this embodiment does not specifically limit the formula for determining the cumulative reward parameters.

[0116] In an optional embodiment, a Critic Network can be used to evaluate the sample window adjustment information from the previous iteration based on the cumulative reward parameters of the current iteration and the previous iteration.

[0117] In an optional embodiment, the difference between the cumulative reward parameter in the current iteration and the cumulative reward parameter in the previous iteration can be used as the sample evaluation result in the current iteration.

[0118] S430, based on the current transmission status data and sample evaluation results, adjust the sample window value under the previous iteration process to obtain the current sample window value under the current iteration process.

[0119] In one optional embodiment, the current window adjustment information for the current iteration can be determined based on the current transmission status data and sample evaluation results. The window value from the previous iteration is then adjusted according to this current window adjustment information to obtain the current window value for the current iteration.

[0120] In one alternative embodiment, a corresponding adjustment action can be generated based on the current window adjustment information, and the adjustment action can be executed through an actor network to adjust the window value under the previous iteration process to obtain the current window value under the current iteration process.

[0121] S440: Based on the current sample window value, perform data transmission to obtain the sample transmission status data during this iteration.

[0122] S450, based on the sample evaluation results of this iteration and the sample evaluation results of the previous iteration, adjust the parameters of the congestion window adjustment model until the iteration termination condition is met.

[0123] In the first iteration, the current transmission status data is obtained by adjusting the preset sample window value according to the preset window adjustment information, and then transmitting the data according to the current sample window value. The sample evaluation result in the first iteration is obtained by evaluating the preset window adjustment information.

[0124] The iteration termination conditions include: the change between the cumulative reward parameters in two adjacent iterations meets the first preset condition, and the change between the amount of data transmitted in two adjacent iterations meets the second preset condition.

[0125] The change in the cumulative reward parameter between two adjacent iterations can be understood as the difference between the exponentially weighted moving average (EWMA) of the cumulative reward parameter between the two adjacent iterations. The cumulative reward parameter for each iteration can be obtained by weighted summation of the rates of change of throughput data, round-trip delay data, packet loss rate data, and round-trip delay data in that iteration.

[0126] The change in the amount of data transmitted between two adjacent iterations can be understood as the difference in the effective throughput TP between two adjacent iterations.

[0127] The first preset condition may include the difference between the cumulative reward parameters corresponding to the EWMA in two adjacent iterations being less than a first preset threshold.

[0128] The second preset condition can be understood as the difference between the effective throughput TP in two adjacent iteration processes being less than the second preset threshold.

[0129] In this embodiment, the congestion window adjustment model is trained using the cumulative reward parameters and evaluation results in each iteration. This allows the trained congestion window adjustment model to automatically adapt to changes in the transmission state of the wireless communication network. By interacting with the transmission state of the wireless communication network, window adjustment information for the congestion window of the wireless communication network can be obtained quickly.

[0130] Based on the technical solutions of the above embodiments, this application also provides another optional embodiment, in which the steps for determining the target window value are refined.

[0131] See Figure 5 The steps for determining the target window value shown include:

[0132] S510, determine the target window value based on the size relationship between the first window value and the second window value.

[0133] In one alternative embodiment, the target data packet to be sent can be refined into the first service data packet in the process of the first data transmission from the first data transmission end to the second data transmission end.

[0134] Accordingly, obtaining the second window value of the congestion window in the target communication network may include obtaining the initial window value of the congestion window in the target communication network and using the initial window value as the second window value.

[0135] Accordingly, determining the target window value based on the relationship between the first window value and the second window value may include: using the first window value as the target window value when the first window value is less than or equal to the second window value; and determining the target window value based on the second window value when the first window value is greater than the second window value.

[0136] It needs to be explained here that when the target data packet is the first service data packet in the process of the first data transmission end transmitting data to the second data transmission end, the first data transmission end has not yet sent any service data packets to the second data transmission end, that is, the congestion window of the target communication network has not yet been initialized. Therefore, the initial window value of the congestion window in the target communication network is used as the second window value.

[0137] In one optional embodiment, if the first window value is greater than the second window value, the adjustment parameter corresponding to the second window value is determined according to the window range to which the first window value belongs; the target window value is determined according to the adjustment parameter and the second window value; wherein, the window threshold in the window range is determined according to the second window value.

[0138] Optionally, the adjustment parameters can be different depending on the window range to which the first window value belongs.

[0139] In one optional embodiment, the adjustment parameter corresponding to the second window value can be determined based on the window range to which the first window value belongs and the correspondence between each preset window range and the adjustment parameter. Then, the target window value is determined based on the adjustment parameter and the second window value.

[0140] In an alternative embodiment, the target window value can be determined according to the following formula:

[0141]

[0142] in, Indicates the target window value; This represents the first window value of the congestion window in a wireless communication network; This represents the initial window value of the congestion window in the target communication network; and These represent the preset weighting coefficients; and It can be derived from experience.

[0143] In one alternative embodiment, the target data packet to be sent can be refined into non-first service data packets during the initial data transmission process from the first data transmission end to the second data transmission end.

[0144] Accordingly, determining the target window value based on the size relationship between the first window value and the second window value may include: taking the smaller value between the first window value and the second window value as the target window value.

[0145] It needs to be explained here that when the target data packet is not the first service data packet in the process of the first data transmission end transmitting data to the second data transmission end, the first data transmission end has already sent service data packets to the second data transmission end, which means that the congestion window of the target communication network has been initialized. Therefore, the second window value of the congestion window in the target communication network can be obtained according to the traditional congestion control algorithm.

[0146] In this embodiment, based on the relationship between the first window value and the second window value, a target window value that conforms to the current transmission state can be determined, thereby enabling precise control of the congestion window.

[0147] Based on the technical solutions of the above embodiments, this application also provides another optional embodiment, detailing the data transmission method. This optional embodiment can be applied to a first data transmission terminal; the first data transmission terminal and a second data transmission terminal are communicatively connected via a wireless access device; a WiFi network is deployed between the first data transmission terminal and the wireless access device; and a target communication network is deployed between the first data transmission terminal and the second data transmission terminal. The target communication network may include a WiFi network deployed between the first data transmission terminal and the wireless access device, a wireless communication network deployed between the wireless access device and the second data transmission terminal, or a mobile communication network.

[0148] See Figure 6 The data transmission method shown includes:

[0149] S610, acquire the target data packet to be sent.

[0150] The target data packet can be understood as a business data packet. For example, the target data packet can be a video data packet.

[0151] In an optional embodiment, when the target data packet is a video data packet, the target data packet can be obtained in the following manner: obtain the video data corresponding to the current video frame; divide the video data according to a preset MSS to obtain at least one video data packet of size MSS; if the remaining video data after obtaining at least one video data packet is less than MSS, the remaining video data is used as a video data packet.

[0152] S620, obtain the congestion window value W-CWND in the WiFi network.

[0153] In an alternative embodiment, see Figure 7 The steps for obtaining the congestion window value W-CWND in the WiFi network shown may include:

[0154] S710, the first data transmission terminal loads a pre-trained congestion window adjustment model.

[0155] S720, the first data transmission end obtains transmission status data through WiFi driver.

[0156] S730 inputs the transmission status data into a pre-trained congestion window adjustment model to obtain window adjustment information during this data transmission process.

[0157] S740 adjusts the congestion window value under the previous data transmission process according to the window adjustment information to obtain the congestion window value W-CWND under the current data transmission process.

[0158] In an alternative embodiment, see Figure 8 The training process of the congestion window adjustment model shown may include:

[0159] S810, the first data transmission end in the sample WiFi network obtains the initial state data of this iteration process through WiFi driver, and uses the correlation analysis method to extract the target state data that meets the correlation requirements in the initial state data as the current transmission state data.

[0160] In an alternative embodiment, the current transmission state data can be represented in the form of a state space St.

[0161] The state space St can include at least one of the following information: WiFi signal strength RSSI, negotiated transmission rate RATE, wireless air interface link transmit throughput W-TP, wireless air interface link round-trip time W-RTT, wireless air interface link retransmission count W-TRY, wireless air interface link W-LOSS, and wireless air interface link round-trip time W-RTT change rate. W-RTT and W-LOSS can be approximated by pinging the wireless router's RTT and packet loss rate, respectively, to reduce the complexity of data acquisition.

[0162] S820 calculates the cumulative reward parameter Rt for this iteration based on the preset transport layer reward function.

[0163] The reward function can be adjusted according to user needs. In one optional embodiment, the reward function is as follows:

[0164]

[0165] in, This represents the cumulative reward parameter; Indicates the link transmission throughput of a WiFi network. This represents the round-trip time of a WiFi network link. This indicates the packet loss rate of a WiFi network. This represents the rate of change of the round-trip delay of the WiFi network link; the values ​​of α, β, γ, and δ are hyperparameters and need to be determined before training. , , , These represent hyperparameters. and The round-trip time and packet loss rate of the wireless router in the network can be used as an approximation by PING.

[0166] S830: Based on the cumulative reward parameters of the current iteration and the cumulative reward parameters of the previous iteration, obtain the sample evaluation results for evaluating the sample window adjustment information of the previous iteration.

[0167] In one alternative embodiment, the Critic network can be used to evaluate the sample evaluation result Qt resulting from the action corresponding to the sample window adjustment information in the previous iteration. If the value indicated by the sample evaluation result Qt is high, the probability of selecting that action in the subsequent policy selection of the current state is higher, and vice versa.

[0168] S840, based on the current transmission status data and sample evaluation results Qt in this iteration process, select the current window adjustment information in this iteration process through the Actor network, and form the execution action At according to the window adjustment size and adjustment direction contained in the current window adjustment information, adjust the window value in the previous iteration process, and obtain the current sample window value in this iteration process.

[0169] S850 transmits the target data packet to the second data transmission terminal based on the current sample window value, and obtains the sample transmission status data under this iteration process.

[0170] S860, based on the sample evaluation results of the current iteration and the sample evaluation results of the previous iteration, adjusts the parameters of the congestion window adjustment model.

[0171] S870: After the preset time is reached or the preset event is triggered, repeat the process from S810 to S860 until the change of the exponentially weighted moving average Rewma of the accumulated reward value in each iteration is less than the preset threshold α, and the change of the effective throughput TP of the transport layer is less than the preset threshold β, then end the training process.

[0172] The preset events may include receiving an acknowledgment character (ACK) data packet from the second data transmission end and a sudden change in the WiFi link negotiation transmission rate.

[0173] In the first iteration, the current transmission status data is obtained by adjusting the preset sample window value according to the preset window adjustment information, and then transmitting the data according to the current sample window value. The sample evaluation result in the first iteration is obtained by evaluating the preset window adjustment information.

[0174] S630: Determine whether the target data packet is the first service data packet; if yes, execute S640; if no, execute S660.

[0175] S640: Obtain the initial window value T-CWND_0 of the congestion window in the target communication network; obtain the target congestion window value CWND based on the interference state W-STATE and the initial window value T-CWND_0; and send the target data packet to the second data transmission end using the target congestion window value CWND.

[0176] S650: Determine whether the data transmission process has ended; if yes, end it; otherwise, execute S810.

[0177] S660, obtain the congestion window value T-CWND in the target communication network.

[0178] S670 obtains the target congestion window value CWND based on the congestion window value W-CWND in the WiFi network and the congestion window value T-CWND in the target communication network, and sends the target data packet to the second data transmission end using the target congestion window value CWND.

[0179] S680: Determine if the data transmission process has ended; if yes, end it; otherwise, execute S610.

[0180] Based on the technical solutions of the above embodiments, this application also provides another optional embodiment, detailing the data transmission method. This optional embodiment can be applied to a wireless terminal; the wireless terminal and the client are connected via a wireless access device; a WiFi network is deployed between the wireless terminal and the wireless access device; and a target communication network is deployed between the wireless terminal and the client. The target communication network may include a WiFi network deployed between the wireless terminal and the wireless access device, a wireless communication network deployed between the wireless access device and the client, or a mobile communication network.

[0181] The wireless terminal may include a wireless driving unit, a wireless congestion control unit, a traditional congestion control unit, a congestion window decision unit, a transmission queue scheduling unit, and a network transmission unit.

[0182] See Figure 9 and Figure 10 The flowcharts illustrating the data transmission methods shown below include:

[0183] The wireless terminal divides the video frame into at least one video data packet according to the maximum segment length (MSS).

[0184] The wireless drive unit will sense the transmission status data in real time and send it to the wireless congestion control unit.

[0185] Next, the wireless congestion control unit can input the current transmission status data and the cumulative reward parameters from the previous time step into the trained congestion window adjustment model. Using the actor network and evaluation network in the congestion window adjustment model, it obtains the window adjustment information at the current time step, and uses the window adjustment information to adjust the wireless congestion window value from the previous time step, thus obtaining the wireless congestion window value W-CWND in the WiFi network at the current time step.

[0186] For the first video data packet, the congestion window decision unit can calculate the congestion window value CWND used to send the first video data packet by combining the wireless congestion window value W-CWND determined by the wireless congestion control unit and the initial congestion window value T-CWND_0 in the target communication network determined by the traditional congestion control unit.

[0187] The sending queue scheduling unit can send the first video data packet to the wireless access device according to the congestion window value CWND, and then the wireless access device can send the first video data packet to the client.

[0188] The network transmitting unit can feed back the transmission status data after transmitting the first video data packet and the cumulative reward parameters adjusted for the wireless congestion window value to the wireless congestion control unit.

[0189] For video data packets that are not the first, the network sending unit can receive the transmission status information of the target communication network from the client and send it to the traditional congestion control unit.

[0190] Next, the traditional congestion control unit can determine the traditional congestion window value T-CWND in the target communication network based on the transmission status information of the target communication network and using the traditional congestion control algorithm.

[0191] Subsequently, the congestion window decision unit can calculate the congestion window value CWND for sending non-first video data packets based on the wireless congestion window value W-CWND determined by the wireless congestion control unit and the traditional congestion window value T-CWND determined by the traditional congestion control unit.

[0192] Then, the sending queue scheduling unit can send non-first video data packets according to the congestion window value CWND. The network sending unit continues to send the received ACK data packets to the traditional congestion control unit, so that the traditional congestion control unit readjusts the traditional congestion window value T-CWND until at least one video data packet has been sent.

[0193] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0194] Based on the same inventive concept, this application also provides a data transmission apparatus for implementing the data transmission method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, specific limitations in one or more data transmission apparatus embodiments provided below can be found in the limitations of the data transmission method described above, and will not be repeated here.

[0195] In one exemplary embodiment, such as Figure 11 As shown, a data transmission device is provided, configured at a first data transmission end, the first data transmission end and a second data transmission end being communicatively connected via a wireless access device; a wireless communication network is deployed between the first data transmission end and the wireless access device; a target communication network is deployed between the first data transmission end and the second data transmission end; the data transmission device includes: a first acquisition module 1110, a first determination module 1120, a second acquisition module 1130, a second determination module 1140, and a transmission module 1150, wherein:

[0196] The first acquisition module 1110 is used to acquire transmission status data of the wireless communication network;

[0197] The first determining module 1120 is used to determine the first window value of the congestion window in the wireless communication network based on the transmission status data.

[0198] The second acquisition module 1130 is used to acquire the second window value of the congestion window in the target communication network;

[0199] The second determining module 1140 is used to determine the target window value based on the first window value and the second window value;

[0200] The sending module 1150 is used to transmit the target data packet to the second data transmission terminal according to the target window value.

[0201] In one embodiment, the first determining module 1120 is specifically used to: input transmission status data into a pre-trained congestion window adjustment model to obtain window adjustment information for the current data transmission process; the congestion window adjustment model is implemented based on a reinforcement learning algorithm; and adjust the first window value for the previous data transmission process according to the window adjustment information to obtain the first window value for the current data transmission process.

[0202] In one embodiment, the data transmission device further includes a training module for training a congestion window adjustment model. The training module includes: a first determining unit, used in each iteration to take the sample transmission state data of the sample wireless communication network in the previous iteration as the current transmission state data in the current iteration; an evaluation unit, used to evaluate the sample window adjustment information in the previous iteration based on the current transmission state data to obtain a sample evaluation result; an adjustment unit, used to adjust the sample window value in the previous iteration based on the current transmission state data and the sample evaluation result to obtain the current sample window value in the current iteration; and a transmission unit, used to transmit data based on the current sample window value to obtain the current iteration value. The process includes sample transmission status data during the iteration process; a parameter tuning unit, used to tune the congestion window adjustment model based on the sample evaluation results of the current iteration process and the sample evaluation results of the previous iteration process, until the iteration termination condition is met; wherein, the current transmission status data of the first iteration process is obtained by adjusting the preset sample window value according to the preset window adjustment information to obtain the current sample window value, and then transmitting data according to the current sample window value; the sample evaluation results of the first iteration process are obtained by evaluating the preset window adjustment information; wherein, the iteration termination condition includes: the change between the cumulative reward parameters of two adjacent iteration processes meets the first preset condition, and the change between the amount of data transmitted in two adjacent iteration processes meets the second preset condition.

[0203] In one embodiment, the evaluation unit is specifically used to: determine the cumulative reward parameter for the current iteration process based on the current transmission status data; and obtain the sample evaluation result for evaluating the sample window adjustment information of the previous iteration process based on the cumulative reward parameter for the current iteration process and the cumulative reward parameter for the previous iteration process.

[0204] In one embodiment, the adjustment unit is specifically used to: determine the current window adjustment information under the current iteration process based on the current transmission status data and evaluation results; and adjust the window value under the previous iteration process based on the current window adjustment information to obtain the current window value under the current iteration process.

[0205] In one embodiment, the current transmission status data includes throughput data, round-trip time data, packet loss rate data, and the rate of change of round-trip time data; the adjustment unit is specifically used to: perform a weighted summation of the rate of change of throughput data, round-trip time data, packet loss rate data, and round-trip time data to obtain the cumulative reward parameter under the local iteration process.

[0206] In one embodiment, the second determining module is specifically used to: determine the target window value based on the size relationship between the first window value and the second window value.

[0207] In one embodiment, when the target data packet is the first service data packet in the process of the first data transmission from the first data transmission end to the second data transmission end, the second acquisition module is specifically used to: acquire the initial window value of the congestion window in the target communication network and use the initial window value as the second window value; correspondingly, the second determination module 1140 is specifically used to: use the first window value as the target window value when the first window value is less than or equal to the second window value; and determine the target window value according to the second window value when the first window value is greater than the second window value.

[0208] In one embodiment, the second determining module 1140 is specifically used to: determine the adjustment parameter corresponding to the second window value according to the window range to which the first window value belongs; wherein the window threshold in the window range is determined according to the second window value; and determine the target window value according to the adjustment parameter and the second window value.

[0209] In one embodiment, when the target data packet is not the first service data packet in the process of the first data transmission from the first data transmission terminal to the second data transmission terminal, the second determining module 1140 is specifically used to: take the smaller value between the first window value and the second window value as the target window value.

[0210] Each module in the aforementioned data transmission device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0211] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12As shown, the computer device includes a processor, memory, input / output interfaces, and a communication interface. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a data transmission method.

[0212] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0213] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the data transmission method provided in any of the above embodiments.

[0214] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the data transmission method provided in any of the above embodiments.

[0215] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the data transmission method provided in any of the above embodiments.

[0216] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0217] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0218] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A data transmission method, characterized in that, It is applied to a first data transmission terminal, which is connected to a second data transmission terminal via a wireless access device; a wireless communication network is deployed between the first data transmission terminal and the wireless access device. A target communication network is deployed between the first data transmission terminal and the second data transmission terminal; the method includes: Obtain the transmission status data of the wireless communication network; Based on the transmission status data, determine the first window value of the congestion window in the wireless communication network; Obtain the second window value of the congestion window in the target communication network; Determine the target window value based on the first window value and the second window value; Based on the target window value, the target data packet is transmitted to the second data transmission terminal.

2. The method according to claim 1, characterized in that, Determining the first window value of the congestion window in the wireless communication network based on the transmission status data includes: The transmission status data is input into a pre-trained congestion window adjustment model to obtain window adjustment information during this data transmission process; the congestion window adjustment model is implemented based on a reinforcement learning algorithm. Based on the window adjustment information, the first window value under the previous data transmission process is adjusted to obtain the first window value under the current data transmission process.

3. The method according to claim 2, characterized in that, The congestion window adjustment model is trained through the following steps: In each iteration, the sample transmission state data of the sample wireless communication network in the previous iteration is used as the current transmission state data in the current iteration. Based on the current transmission status data, the sample window adjustment information under the previous iteration process is evaluated to obtain the sample evaluation result; Based on the current transmission status data and the sample evaluation results, the sample window value under the previous iteration process is adjusted to obtain the current sample window value under the current iteration process; Based on the current sample window value, data transmission is performed to obtain sample transmission status data during this iteration process; Based on the sample evaluation results of the current iteration and the sample evaluation results of the previous iteration, the congestion window adjustment model is adjusted until the iteration termination condition is met. Specifically, the current transmission status data in the first iteration is obtained by adjusting a preset sample window value according to preset window adjustment information, and then transmitting data based on the current sample window value. The sample evaluation results in the first iteration are obtained by evaluating the preset window adjustment information. The iteration termination conditions include: the change between the cumulative reward parameters in two adjacent iterations meets a first preset condition, and the change between the amount of data transmitted in two adjacent iterations meets a second preset condition.

4. The method according to claim 3, characterized in that, The step of evaluating the sample window adjustment information from the previous iteration based on the current transmission status data to obtain sample evaluation results includes: Based on the current transmission status data, determine the cumulative reward parameters for this iteration process; Based on the cumulative reward parameters of the current iteration and the previous iteration, the sample evaluation results are obtained for evaluating the sample window adjustment information of the previous iteration.

5. The method according to claim 4, characterized in that, The current transmission status data includes throughput data, round-trip time data, packet loss rate data, and the rate of change of the round-trip time data; Accordingly, determining the cumulative reward parameter under the local iteration process based on the current transmission status data includes: The cumulative reward parameter under the local iterative process is obtained by weighted summing of the change rates of the throughput data, the round-trip delay data, the packet loss rate data, and the round-trip delay data.

6. The method according to claim 3, characterized in that, The step of adjusting the sample window value from the previous iteration based on the current transmission status data and the sample evaluation results to obtain the current sample window value for the current iteration includes: Based on the current transmission status data and the sample evaluation results, determine the current window adjustment information for this iteration process; The sample window value under the previous iteration is adjusted based on the current window adjustment information to obtain the current sample window value under the current iteration.

7. The method according to claim 1, characterized in that, Determining the target window value based on the first window value and the second window value includes: The target window value is determined based on the size relationship between the first window value and the second window value.

8. The method according to claim 7, characterized in that, When the target data packet is the first service data packet in the initial data transmission process from the first data transmission terminal to the second data transmission terminal, obtaining the second window value of the congestion window in the target communication network includes: Obtain the initial window value of the congestion window in the target communication network, and use the initial window value as the second window value; Accordingly, determining the target window value based on the size relationship between the first window value and the second window value includes: If the first window value is less than or equal to the second window value, the first window value is used as the target window value. If the first window value is greater than the second window value, the target window value is determined based on the second window value.

9. The method according to claim 8, characterized in that, Determining the target window value based on the second window value includes: Based on the window range to which the first window value belongs, the adjustment parameter corresponding to the second window value is determined; wherein, the window threshold in the window range is determined based on the second window value; The target window value is determined based on the adjustment parameters and the second window value.

10. The method according to claim 7, characterized in that, When the target data packet is not the first service data packet in the initial data transmission process from the first data transmission terminal to the second data transmission terminal, determining the target window value based on the size relationship between the first window value and the second window value includes: The smaller of the first window value and the second window value is used as the target window value.

11. A data transmission device, characterized in that, The device is configured at a first data transmission terminal, which is connected to a second data transmission terminal via a wireless access device; a wireless communication network is deployed between the first data transmission terminal and the wireless access device. A target communication network is deployed between the first data transmission terminal and the second data transmission terminal; The device includes: The first acquisition module is used to acquire the transmission status data of the wireless communication network; The first determining module is used to determine a first window value of the congestion window in the wireless communication network based on the transmission status data. The second acquisition module is used to acquire the second window value of the congestion window in the target communication network; The second determining module is used to determine the target window value based on the first window value and the second window value; The sending module is used to transmit the target data packet to the second data transmission terminal according to the target window value.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 10.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 10.

Images