Rate control method, apparatus, device, and storage medium

Abstract

The application provides a rate control method, device, equipment and storage medium, the method comprises the steps of obtaining N candidate rates and environmental characteristic vectors at the current time; for each candidate rate, determining the corresponding environmental characteristic library and the packet sending success rate of the candidate rate, wherein the environmental characteristic library is obtained based on the environmental characteristic vector corresponding to each time of sending a data packet using the candidate rate; for each candidate rate, determining the estimated packet sending success rate corresponding to the candidate rate based on the environmental characteristic library corresponding to the candidate rate, the environmental characteristic vector at the current time, and the packet sending success rate; determining the target rate at the current time based on the N candidate rates and the estimated packet sending success rate corresponding to each candidate rate, and sending a data packet based on the target rate, wherein the environmental characteristic vector is obtained based on M environmental parameters. In this way, in the rate control process, the selected packet sending rate can maximize the throughput of the wireless local area network.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a rate control method, apparatus, device, and storage medium. Background Technology

[0002] Wireless devices can send and receive data in frames. A frame is the basic message unit used for communication over a network (such as a wireless network). Depending on the physical layer protocol, frames can be transmitted at various rates; for example, IEEE 802.11a PHY supports rate sets {6, 12, 18, 24, 36, 48, 54} Mbits / s. How to select the frame transmission rate to ensure the client correctly receives the data packets is a key research area in the field of communication technology.

[0003] Rate control algorithms are algorithms that dynamically adjust the packet transmission rate of wireless devices based on environmental factors to achieve higher throughput or lower latency. One existing rate control algorithm uses PER (Packet Error Rate) as a performance standard. If the PER corresponding to the current rate is lower than the PER threshold, the wireless transmission rate is increased; if the PER corresponding to the current rate is not lower than the PER threshold, the wireless transmission rate is decreased.

[0004] However, on the one hand, this method evaluates PER based on the current transmission rate, and may not estimate PER at other rates. Therefore, the selected transmission rate may not be the optimal one. On the other hand, the performance of PER-based rate control methods may be affected by interference. The reason is simple: interference can increase the PER for all wireless rates above the PER threshold, at which point this method is no longer applicable. Therefore, a method is needed to adjust the wireless transmission rate to improve throughput. Summary of the Invention

[0005] This application provides a rate control method, apparatus, device, and storage medium that can achieve the selected transmission rate and provide better throughput, efficiency, and quality of service.

[0006] In a first aspect, embodiments of this application provide a rate control method, the method comprising:

[0007] Obtain the N candidate rates corresponding to the current time and determine the environmental feature vector at the current time;

[0008] For each of the N candidate rates, determine the environmental feature library corresponding to the candidate rate. The environmental feature library is obtained based on the environmental feature vector corresponding to each time a data packet is sent using the candidate rate. Then, determine the packet sending success rate corresponding to each environmental feature vector in the environmental feature library when sending a data packet using the candidate rate.

[0009] For each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library, the estimated packet transmission success rate corresponding to the candidate rate is determined.

[0010] Based on N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, the target rate at the current moment is determined, and data packets are sent based on the target rate.

[0011] The environmental feature vectors mentioned above are obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2.

[0012] Secondly, embodiments of this application provide a rate control device, the device comprising:

[0013] The first determining unit is used to obtain the N candidate rates corresponding to the current time and determine the environmental feature vector at the current time.

[0014] The second determining unit is used to determine the environmental feature library corresponding to each of the N candidate rates. The environmental feature library is obtained based on the environmental feature vector corresponding to each time a data packet is sent using the candidate rate. The unit also determines the packet sending success rate corresponding to each environmental feature vector in the environmental feature library when sending a data packet using the candidate rate.

[0015] The third determining unit is used to determine the estimated packet success rate of each of the N candidate rates based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current time, and the packet success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library.

[0016] The fourth determining unit determines the target rate at the current moment based on N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, and sends data packets based on the target rate.

[0017] The environmental feature vectors mentioned above are obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2.

[0018] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor; the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the methods in the first aspect or its various implementations described above.

[0019] Fourthly, a chip is provided for implementing the methods of any one of the first or second aspects or their respective implementations. Specifically, the chip includes a processor for calling and running a computer program from a memory, causing a device equipped with the chip to perform the methods of the first aspect or their respective implementations.

[0020] Fifthly, a computer-readable storage medium is provided for storing a computer program that causes a computer to perform the methods described in the first aspect or its various implementations.

[0021] In a sixth aspect, a computer program product is provided, including computer program instructions that cause a computer to perform the methods described in the first aspect or its various implementations.

[0022] In a seventh aspect, a computer program is provided that, when run on a computer, causes the computer to perform the methods described in the first aspect or its various implementations.

[0023] In summary, the technical solution of this application, when controlling the packet transmission rate, firstly, obtains the environmental feature vector at the current moment. For each of the N candidate rates, determines the environmental feature library corresponding to that candidate rate, and determines the packet transmission success rate corresponding to sending packets using that candidate rate under each environmental feature vector in the environmental feature library. Next, for each of the N candidate rates, based on the environmental feature library corresponding to that candidate rate, the environmental feature vector at the current moment, and the packet transmission success rate corresponding to sending data packets using that candidate rate under each environmental feature vector in the environmental feature library, determines the estimated packet transmission success rate corresponding to that candidate rate. Here, the environmental feature vector is obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2. Then, based on the N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, determines the target rate at the current moment, and sends data packets based on the target rate. In this way, during the rate control process, an environmental feature vector and an environmental feature library are constructed based on multiple environmental parameters. The environmental parameters are richer and can more accurately reflect the environmental conditions at the time of packet transmission. As a result, the estimated packet transmission success rate obtained based on the environmental feature vector and environmental feature library at the current moment, as well as the packet transmission success rate, is more accurate. Therefore, the selected packet transmission rate based on the estimated packet transmission success rates corresponding to N candidate rates can provide the optimal throughput, efficiency, and service quality. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A schematic flowchart illustrating a rate control method provided in an embodiment of this application;

[0026] Figure 2 This is a schematic diagram of the structure of a rate control device provided in an embodiment of this application;

[0027] Figure 3 This is a schematic block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0030] Before introducing the technical solution of this application, the relevant background knowledge involved in the technical solution of this application will be explained below.

[0031] Wireless devices can send and receive data in frames. A frame is the basic message unit used for communication over a network (such as a wireless network). Frames can include routing information, data, and error detection information. Depending on the Physical Layer (PHY) protocol, frames can be transmitted at various rates; for example, the IEEE 802.11a PHY supports rate sets {6, 12, 18, 24, 36, 48, 54} Mbits / s.

[0032] Generally, the greater the distance between the transmitter and the target receiver, the lower the data rate because the received signal strength is lower. Furthermore, wireless communication is susceptible to interference signals. For example, microwave ovens, cordless phones, Bluetooth devices, and other wireless devices operating in overlapping or adjacent frequency ranges can generate signals that interfere with data packet transmission. In such challenging environments, frame transmission rates tend to be lower to improve throughput and maintain a low packet error rate (PER). However, transmission rate is only one factor affecting throughput; therefore, a lower transmission rate does not necessarily provide higher throughput.

[0033] As mentioned above, current rate control algorithms are mainly based on PER (Performance Ratio) control methods. These methods use PER as a performance standard, adjusting the wireless rate based on whether the PER corresponding to the current wireless rate exceeds a preset PER threshold. However, this rate control algorithm does not evaluate the PER of all wireless rates to select the optimal one. Therefore, the transmission rate selected by this method is not necessarily the one with the lowest PER. Furthermore, in poor environmental conditions, with numerous interference factors, the PER for all wireless rates may exceed the PER threshold, rendering this rate control method inapplicable.

[0034] To address the aforementioned technical problems, this application provides a rate control method. When selecting a packet transmission rate, firstly, the environmental feature vector at the current moment is obtained. For each of the N candidate rates, an environmental feature library corresponding to that candidate rate is determined, and the packet transmission success rate corresponding to sending packets using that candidate rate under each environmental feature vector in the environmental feature library is determined. Next, for each of the N candidate rates, based on the environmental feature library corresponding to that candidate rate, the environmental feature vector at the current moment, and the packet transmission success rate corresponding to sending data packets using that candidate rate under each environmental feature vector in the environmental feature library, an estimated packet transmission success rate corresponding to that candidate rate is determined. Here, the environmental feature vector is obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2. Then, based on the N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, the target rate at the current moment is determined, and data packets are sent based on the target rate. In this way, during rate control, an environmental feature vector and an environmental feature library are constructed based on multiple environmental parameters. The richer the environmental parameters, the more accurately they reflect the environmental conditions at the time of packet transmission. This leads to a more accurate prediction of the packet transmission success rate based on the current environmental feature vector and environmental feature library, as well as the packet transmission success rate. Therefore, by selecting the transmission rate based on the predicted packet transmission success rates corresponding to N candidate rates, the selected rate can maximize the throughput of the wireless local area network (WLAN) even in the presence of interference. Because a throughput-based solution is provided, wireless transmission is optimized in terms of throughput, efficiency, and quality of service.

[0035] It should be noted that the rate control method provided in this application embodiment can be applied to any field that requires wireless rate control.

[0036] The technical solutions of the embodiments of this application will be described in detail below through some examples. The following embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0037] Figure 1 This is a schematic flowchart illustrating a rate control method provided in an embodiment of this application.

[0038] like Figure 1 As shown, the rate control method includes the following steps S101 to S104:

[0039] S101. Obtain the N candidate rates corresponding to the current time and determine the environmental feature vector at the current time.

[0040] The environmental feature vector is obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2.

[0041] It should be noted that the environment is a significant factor affecting packet transmission success rate. For example, in poor environmental conditions, data packets may experience strong interference during transmission, preventing the receiver from correctly receiving the packets and resulting in a low packet transmission success rate. This application's embodiments take into account the impact of the environment on packet transmission success rate, considering at least two environmental factors when adaptively adjusting the wireless rate to more accurately select the optimal packet transmission rate.

[0042] In some embodiments, the environmental parameters mentioned above include environmental interference index (e.g., noise intensity), channel occupancy, number of communicating parties sending packets, signal strength of the client, and packet sending time of the communicating parties.

[0043] In this embodiment of the application, the environmental feature vector corresponding to each data packet transmission can be determined based on the above-mentioned environmental parameters.

[0044] The embodiments of this application do not limit the specific method for determining the environmental feature vector (e.g., the environmental feature vector at the current moment) for each packet transmission.

[0045] In some embodiments, the environmental feature vector is obtained directly based on the M environmental parameters corresponding to the data packet being sent.

[0046] For example, if M = 5, and the environmental parameters are a1, a2, a3, a4, and a5, then the environmental feature vector F = [a1, a2, a3, a4, a5] is obtained based on a1, a2, a3, a4, and a5. T .

[0047] In some embodiments, the environmental feature vector corresponding to each packet transmission is determined through the following steps S101-B1 to S101-B3.

[0048] S101-B1: Obtain the M environmental parameters when sending data packets, and determine the weight of each of the M environmental parameters.

[0049] S101-B2: For each of the M environmental parameters, obtain the weighted value of the environmental parameter according to its corresponding weight.

[0050] It should be noted that, in this embodiment, considering the varying degrees of influence of different environmental parameters on packet success rate, different weights are assigned to different environmental parameters. Specifically, the environmental parameter with the greater influence on packet success rate has a higher weight. This approach yields more accurate environmental characteristics that better reflect the relationship with packet success rate.

[0051] S101-B3: Determine the environmental feature vector corresponding to the transmission of data packets based on the weighted value of each of the M environmental parameters.

[0052] This application does not limit the specific method of determining the environmental feature vector corresponding to the data packet when sending it based on the weighted value of each of the M environmental parameters.

[0053] In some embodiments, the environmental feature vector corresponding to the sending of data packets is obtained directly based on the weighted value corresponding to each of the M environmental parameters.

[0054] For example, if M = 3, the M environmental parameters obtained through steps S101-B1 are b1, b2, and b3. Step S101-B1 determines the weight of b1 as s1, the weight of b2 as s2, and the weight of b3 as s3. Among these, environmental parameter b1 has the greatest impact on the packet sending success rate, followed by b2, and then b3. Therefore, s1 > s2 > s3. Step S101-B2 determines the weighted value of environmental parameter b1 as b1 × s1, the weighted value of environmental parameter b2 as b2 × s2, and the weighted value of environmental parameter b3 as b3 × s3. The environmental feature vector determined through steps S101-B3 is F = [b1 × s1, b2 × s2, b3 × s3]. T .

[0055] In some embodiments, the environmental feature vector corresponding to each packet transmission is determined through the following steps S101-B3-1 to S101-B3-2.

[0056] S101-B3-1: Normalize the weighted value of each of the M environmental parameters to obtain the standard value of each of the M environmental parameters.

[0057] S101-B3-2: Obtain the environmental feature vector based on the standard value corresponding to each of the M environmental parameters.

[0058] It should be noted that, in this embodiment, not only are the varying degrees of influence of different environmental parameters on the packet success rate considered, and each environmental parameter is weighted according to its influence on the packet success rate, but the impact of anomalous sample data (e.g., data significantly different from other sample data) on the accuracy of the extracted environmental features is also taken into account. After obtaining the weighted values, this embodiment normalizes each environmental parameter to limit it to a certain range, such as [0,1]. Processing environmental parameters in this way can center them, thereby eliminating the adverse effects caused by abnormal and extreme data.

[0059] This application does not impose specific limitations on the above-described normalization method in its embodiments.

[0060] In one example, normalization is performed using the min-max normalization method.

[0061] For example, if the environmental parameter is x,

[0062] Where x is the weighted environmental parameter, x ′ Let x be the normalized standard value, min(x) be the environmental parameter with the smallest data value, and max(x) be the environmental parameter with the largest data value.

[0063] In another example, normalization is performed using a neural network.

[0064] By using some data functions, the original values ​​(weighted values) are mapped to standard values.

[0065] In another example, normalization is performed using the logarithmic function.

[0066]

[0067] Where x is the weighted environmental parameter, x ′ Let x be the standard value after normalization, and max(x) be the environmental parameter with the largest data value.

[0068] S102. For each of the N candidate rates, determine the environmental feature library corresponding to the candidate rate. The environmental feature library is obtained based on the environmental feature vector corresponding to each time a data packet is sent using the candidate rate. Then, determine the packet sending success rate corresponding to each environmental feature vector in the environmental feature library when sending data packets using the candidate rate.

[0069] It should be noted that the packet success rate (PSR) corresponding to various candidate rates can be obtained from previous frame transmission results. For example, the packet success rate during previous data transmission can be obtained in the form of acknowledgment frames (ACK).

[0070] The technical solution of this application will be described in detail below by taking the determination of the environmental feature library corresponding to the i-th candidate rate among N candidate rates as an example, where i is a positive integer less than or equal to N.

[0071] For the i-th candidate rate among N candidate rates, the environmental feature vector corresponding to the previous use of the i-th candidate rate to send data packets is obtained, and an environmental feature library corresponding to the i-th candidate rate is established based on the obtained environmental feature vector. The process of determining the environmental feature vector corresponding to the use of the i-th candidate rate to send data packets can be referred to the description in the above embodiment, and will not be repeated here.

[0072] For example, there are three environmental parameters, f1, f2, and f3. If the communicating party has previously sent data packets three times using the i-th candidate rate, then we can obtain three environmental feature vectors corresponding to the three times the communicating party used the i-th candidate rate to send data packets, namely F1 = [f...]. 11 ,f 21 ,f 31 ] T F2 = [f 12 ,f 22 ,f 32 ] T and F3 = [f 13 ,f 23 ,f 33 ] T Then the environmental feature library corresponding to the i-th candidate rate is [F1,F2,F3] (a 3*3 matrix).

[0073] It should be noted that, in the embodiments of this application, the size of the environmental feature library corresponding to each candidate rate can be the same or different.

[0074] For example, when establishing the environmental feature library corresponding to the i-th candidate rate among N candidate rates, if the current communicating party has previously used the i-th candidate rate to send data packets 3 times, then the environmental feature library corresponding to the i-th candidate rate is an M*3 matrix.

[0075] For the j-th candidate rate among N candidate rates, when establishing the environmental feature library corresponding to the j-th candidate rate, if the current communicating party has previously used the j-th candidate rate to send data packets 5 times, then the environmental feature library corresponding to the j-th candidate rate is an M*5 matrix, where j is a positive integer from 1 to N, and j is not equal to i.

[0076] The embodiments of this application can also be based on the established environmental feature library, with adaptive rate adjustment.

[0077] For example, environmental parameters are collected each time the communication party sends a packet, and then environmental feature vectors are obtained. An environmental feature library of size M*K matrix is ​​built for each of the N candidate rates, where K is a positive integer.

[0078] S103. For each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library, determine the estimated packet transmission success rate corresponding to the candidate rate.

[0079] The above S103 mainly determines the estimated packet transmission success rate corresponding to each candidate rate through the following steps S103-A1 and S103-A2.

[0080] S103-A1. For each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, determine the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time.

[0081] This application does not limit the specific method for determining the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment.

[0082] In some embodiments, the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment is determined by the following steps S103-A1-1 and S103-A1-2.

[0083] S103-A1-1. For each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, determine the distance between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time.

[0084] S103-A1-2. For each of the N candidate rates, based on the distance between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, obtain the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time.

[0085] In this embodiment of the application, the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment can be determined by calculating the distance between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment. In one possible implementation, the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment can be determined by calculating the Euclidean distance between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment.

[0086] For example, the environmental feature vector at the current moment is F cur =[f 1cur ,f 2cur ,······f mcur ] T .

[0087] For the i-th candidate rate among N candidate rates, if the environmental feature library corresponding to the i-th candidate rate is [F1, F2, ..., Ft], then the environmental feature vector F at the current time is... curThe i-th environmental feature vector Fi = [f] in the environmental feature library corresponding to the i-th candidate rate 1i ,f 2i ,······f mi ] T The Euclidean distance is:

[0088]

[0089] It should be noted that the Euclidean distance between each environmental feature vector in the aforementioned environmental feature database and the environmental feature vector at the current moment reflects the similarity between the two. Specifically, the smaller the Euclidean distance between an environmental feature vector and the environmental feature vector at the current moment, the higher the similarity. Therefore, based on the Euclidean distance value between each environmental feature vector in the environmental feature database and the environmental feature vector at the current moment, the similarity between them can be determined.

[0090] In some embodiments, the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment is determined by the Support Vector Machine (SVM) method.

[0091] In some embodiments, the similarity between each environmental feature vector in the environmental feature database and the environmental feature vector at the current moment is determined by back-propagation (BP).

[0092] S103-A2. For each of the N candidate rates, based on the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library, determine the estimated packet transmission success rate corresponding to the candidate rate.

[0093] This application embodiment does not impose specific limitations on the method for determining the estimated packet success rate corresponding to the candidate rate in S103-A2 above.

[0094] In some embodiments, the estimated packet success rate in step S103-A2 is determined by the following steps S103-A2-11 and S103-A2-13.

[0095] S103-A2-11. For each of the N candidate rates, select P environmental feature vectors with similarity higher than a threshold from the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time. These P vectors are then used as the first environmental feature vector corresponding to the candidate rate, where P is a positive integer.

[0096] S103-A2-12. For each of the N candidate rates, based on the similarity between each of the P first environment feature vectors corresponding to that candidate rate and the environment feature vector at the current time, determine the weight of the packet transmission success rate corresponding to each of the P first environment feature vectors when sending data packets using that candidate rate. The higher the similarity of the first environment feature vector to the environment feature vector at the current time, the greater the weight of its corresponding packet transmission success rate.

[0097] S103-A2-13. For each of the N candidate rates, based on the weight of the packet transmission success rate corresponding to the first environment feature vector under each of the P first environment feature vectors corresponding to the candidate rate, the packet transmission success rate corresponding to the candidate rate under each first environment feature vector is weighted and summed to obtain the estimated packet transmission success rate corresponding to the candidate rate.

[0098] It should be noted that, in this embodiment, after determining the similarity between each environmental feature vector in the environmental feature library corresponding to each candidate rate and the environmental feature vector at the current moment, environmental feature vectors that do not meet the similarity requirements are first filtered out, and then the weight of the packet transmission success rate corresponding to the environmental feature vectors that meet the similarity requirements is determined. By discarding environmental feature vectors with low similarity in this way, the subsequent calculation process can be simplified and the latency of data packets can be reduced.

[0099] In some embodiments, the estimated packet success rate in step S103-A2 is determined by the following steps S103-A2-21 and S103-A2-22.

[0100] S103-A2-21. For each of the N candidate rates, based on the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, determine the weight of the packet transmission success rate corresponding to each environmental feature vector in the environmental feature library when sending data packets using the candidate rate. Wherein, the higher the similarity between the environmental feature vector and the environmental feature vector at the current time, the greater the weight of its corresponding packet transmission success rate.

[0101] For example, for the i-th candidate rate among N candidate rates, if the environmental feature library corresponding to the i-th candidate rate is [F1, F2, ..., Ft], and the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time, sorted from largest to smallest, is F1, F2, ..., Ft, where, under environmental feature vector F1, the packet transmission success rate when sending data packets using the i-th candidate rate is PSR1, under environmental feature vector F2, the packet transmission success rate when sending data packets using the i-th candidate rate is PSR2, and so on, under environmental feature vector Ft, the packet transmission success rate when sending data packets using the i-th candidate rate is PSRt, then based on the similarity between F1, F2, ..., Ft and the environmental feature vector at the current time, the weight corresponding to PSR1 is a1, the weight corresponding to PSR2 is a2, ..., the weight corresponding to PSRt is a... t Where a1>a2>······>a t .

[0102] In one possible implementation, a1 = a; a2 = (1-a)×a; ... a t =(1-a) t-1 ×a, where 0 < a < 1.

[0103] S103-A2-22. For each of the N candidate rates, based on the weight of the packet transmission success rate corresponding to the candidate rate when sending data packets using the candidate rate under each environmental feature vector in the environmental feature library corresponding to the candidate rate, the packet transmission success rate corresponding to the candidate rate when sending data packets under each environmental feature is weighted and summed to obtain the estimated packet transmission success rate corresponding to the candidate rate.

[0104] For example, as described in the example above, for the i-th candidate rate among N candidate rates, the estimated packet transmission success rate corresponding to the i-th candidate rate is:

[0105] E new (PSR up )=α1PSR1+α2PSR2+α3PSR3+…+α t PSR t

[0106] Among them, E new (PSR up ) represents the estimated packet transmission success rate corresponding to the i-th candidate rate.

[0107] S104. Based on N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, determine the target rate at the current moment, and send data packets based on the target rate.

[0108] This application embodiment does not limit the specific method of determining the target rate at the current moment in step S104 above.

[0109] In one possible implementation, the candidate rate with the highest estimated packet success rate is determined as the target rate at the current moment.

[0110] In another possible implementation, the target rate at the current moment is determined based on the following steps S104-A1 and S104-A2.

[0111] S104-A1 For each of the N candidate rates, the product of the candidate rate and the estimated packet success rate corresponding to the candidate rate is determined as the estimated throughput corresponding to the candidate rate.

[0112] It should be noted that in the field of communication technology, the wireless rate multiplied by the packet transmission success rate corresponding to that wireless rate can be considered as the throughput at that wireless rate. Therefore, the product of the i-th candidate rate among N candidate rates and the estimated packet transmission success rate corresponding to the i-th candidate rate can be considered as the estimated throughput corresponding to the i-th candidate rate.

[0113] S104-A2: Determine the target rate based on the estimated throughput corresponding to each of the N candidate rates.

[0114] The embodiments of this application do not limit the specific method of "determining the target rate based on the estimated throughput corresponding to each of the N candidate rates" in S104-A2 above.

[0115] Method 1: The candidate rate with the highest estimated throughput is determined as the target rate.

[0116] Method 2: The candidate rate whose estimated throughput is greater than the preset value is determined as the target rate. If there are multiple candidate rates whose estimated throughput is greater than the preset value, then any candidate rate can be selected as the target rate.

[0117] In some embodiments, if the similarity between the current environmental feature vector and each environmental feature vector in the environmental feature library corresponding to the target rate is lower than a first threshold, then the current environmental feature vector is added to the environmental feature library corresponding to the target rate.

[0118] It should be noted that, in this embodiment, the environmental feature library can be updated based on the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current moment. For example, in the above embodiment, when the target rate at the current moment is the i-th candidate rate among N candidate rates, if the similarity between the environmental feature vector at the current moment and each environmental feature vector in the environmental feature library corresponding to the i-th candidate rate is lower than the first threshold, it indicates that the environment at the current moment has no similar environment in the environmental feature library corresponding to the i-th candidate rate. Therefore, in order to enrich the environmental feature library corresponding to the i-th candidate rate and further optimize the wireless transmission in terms of throughput, efficiency, and service quality, the environmental feature vector at the current moment is added to the environmental feature library corresponding to the i-th candidate rate, where i is a positive integer less than or equal to N.

[0119] In some embodiments, if the target rate at the current time is the i-th candidate rate among N candidate rates, and there is an environmental feature vector in the environmental feature library corresponding to the i-th candidate rate that has a similarity to the environmental feature vector at the current time that is higher than a second threshold, then the environmental feature vector is replaced with the environmental feature vector at the current time.

[0120] If there is more than one environmental feature vector in the environmental feature library corresponding to the i-th candidate rate whose similarity to the environmental feature vector at the current time is higher than the second threshold, then the environmental feature vector with the highest similarity can be replaced with the environmental feature vector at the current time, or the environmental feature vector farthest from the current time can be replaced with the environmental feature vector at the current time.

[0121] It should be noted that in the embodiments of this application, the establishment of the environmental feature vector takes into account at least two environmental parameters. If only one environmental parameter is considered, such as the time parameter, when evaluating the weight of the packet success rate when sending data packets using the i-th candidate rate out of N candidate rates, the more recent the packet success rate, the greater its corresponding weight. However, this rate control method that only considers the time parameter is based on the premise that the environmental conditions of the communicating party change uniformly each time a data packet is sent. But in reality, the environmental changes of the communicating party when sending data packets are irregular and can be abrupt. If only one factor is considered, the finally selected packet rate may not be the optimal packet rate. Sending data packets at this rate will affect both the packet success rate and throughput.

[0122] The rate control method provided in this application first obtains the environmental feature vector at the current moment when selecting the packet transmission rate. For each of the N candidate rates, an environmental feature library corresponding to the candidate rate is determined, and the packet transmission success rate corresponding to the candidate rate is determined under each environmental feature vector in the environmental feature library. Next, for each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current moment, and the packet transmission success rate corresponding to the candidate rate when sending data packets using the candidate rate under each environmental feature vector in the environmental feature library, the estimated packet transmission success rate corresponding to the candidate rate is determined. Here, the environmental feature vector is obtained based on M environmental parameters, and N and M are both positive integers greater than or equal to 2. Then, based on the N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, the target rate at the current moment is determined, and data packets are sent based on the target rate. In this way, during the rate control process, an environmental feature vector and an environmental feature library are constructed based on multiple environmental parameters. The environmental parameters are richer and can more accurately reflect the environmental conditions at the time of packet transmission. As a result, the estimated packet transmission success rate obtained based on the environmental feature vector and environmental feature library at the current moment, as well as the packet transmission success rate, is more accurate. Therefore, the selected packet transmission rate based on the estimated packet transmission success rates corresponding to N candidate rates can provide the optimal throughput, efficiency, and service quality.

[0123] The preferred embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this application, various simple modifications can be made to the technical solutions of this application, and these simple modifications all fall within the protection scope of this application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this application will not describe the various possible combinations separately. Furthermore, various different embodiments of this application can also be arbitrarily combined, as long as they do not violate the spirit of this application, they should also be considered as the content disclosed in this application.

[0124] Figure 2 This is a schematic diagram of a rate control device provided in an embodiment of this application.

[0125] like Figure 2 As shown, the rate control device 20 includes:

[0126] The first determining unit 21 is used to obtain the N candidate rates corresponding to the current time and determine the environmental feature vector at the current time;

[0127] The second determining unit 22 is used to determine the environmental feature library corresponding to each of the N candidate rates for each candidate rate. The environmental feature library is obtained based on the environmental feature vector corresponding to each time a data packet is sent using the candidate rate, and to determine the packet sending success rate corresponding to each environmental feature vector in the environmental feature library when sending a data packet using the candidate rate.

[0128] The third determining unit 23 is used to determine the estimated packet success rate corresponding to each of the N candidate rates based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current time, and the packet success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library.

[0129] The fourth determining unit 24 is used to determine the target rate at the current moment based on N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, and to send data packets based on the target rate.

[0130] The environmental feature vectors mentioned above are obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2.

[0131] In some embodiments, the third determining unit 23 is specifically configured to, for each of the N candidate rates, determine the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time, based on the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time; and for each of the N candidate rates, determine the estimated packet transmission success rate corresponding to the candidate rate, based on the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library.

[0132] In some embodiments, the third determining unit 23 is further configured to, for each of the N candidate rates, determine the distance between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time based on the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time; and for each of the N candidate rates, obtain the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time based on the distance between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time.

[0133] In some embodiments, the third determining unit 23 is further configured to, for each of the N candidate rates, determine the weight of the packet transmission success rate corresponding to each environmental feature vector in the environmental feature library and the environmental feature vector at the current time, based on the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time; and for each of the N candidate rates, perform a weighted summation of the packet transmission success rates corresponding to each environmental feature under each environmental feature, based on the weight of the packet transmission success rate corresponding to each environmental feature vector in the environmental feature library, to obtain the estimated packet transmission success rate corresponding to the candidate rate.

[0134] The fourth determining unit 24 is specifically used to determine the estimated throughput corresponding to each of the N candidate rates by multiplying the candidate rate by the estimated packet success rate corresponding to the candidate rate; and to determine the target rate based on the estimated throughput corresponding to each of the N candidate rates.

[0135] The fourth determining unit 24 is specifically used to determine the candidate rate with the largest estimated throughput among the N candidate rates as the target rate.

[0136] In some embodiments, the above-described apparatus further includes a feature update unit 25, which is configured to add the environmental feature vector at the current moment to the environmental feature library corresponding to the target rate when the similarity between the environmental feature vector at the current moment and each environmental feature vector in the environmental feature library corresponding to the target rate is lower than a first threshold.

[0137] In some embodiments, environmental parameters include: environmental interference index, channel occupancy rate, number of communicating parties sending data packets, signal strength of the client, and packet transmission time of the communicating parties.

[0138] In some embodiments, when determining the environmental feature vector, the first determining unit 21 and / or the second determining unit 22 are specifically used to obtain M environmental parameters when sending data packets, and determine the weight corresponding to each of the M environmental parameters; for each of the M environmental parameters, obtain the weighted value corresponding to the environmental parameter according to the weight corresponding to the environmental parameter; and determine the environmental feature vector corresponding to sending data packets based on the weighted value corresponding to each of the M environmental parameters.

[0139] In some embodiments, the first determining unit 21 and / or the second determining unit 22 are specifically used to normalize the weighted value corresponding to each of the M environmental parameters to obtain the standard value corresponding to each of the M environmental parameters; and to obtain the environmental feature vector based on the standard value corresponding to each of the M environmental parameters.

[0140] It should be understood that the device embodiments and method embodiments can correspond to each other, and similar descriptions can be referred to the method embodiments. To avoid repetition, further details will not be provided here. Specifically, Figure 2 The apparatus shown can execute the above-described rate control method embodiments, and the foregoing and other operations and / or functions of each module in the apparatus are respectively for implementing the rate control method embodiments corresponding to the computing device. For the sake of brevity, they will not be described in detail here.

[0141] The apparatus of this application embodiment has been described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that this functional module can be implemented in hardware, in software instructions, or in a combination of hardware and software modules. Specifically, the steps of the method embodiments in this application can be completed by integrated logic circuits in the processor's hardware and / or by software instructions. The steps of the method disclosed in this application embodiment can be directly embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. Optionally, the software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps in the above method embodiments.

[0142] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application, which can be used to perform the above-described rate control method.

[0143] like Figure 3 As shown, the electronic device 30 may include:

[0144] The system includes a memory 31 and a processor 32. The memory 31 stores computer programs and transfers the program code to the processor 32. In other words, the processor 32 can retrieve and run the computer programs from the memory 31 to implement the methods described in the embodiments of this application.

[0145] For example, the processor 32 can be used to execute the above-described method embodiments according to instructions in the computer program.

[0146] In some embodiments of this application, the processor 32 may include, but is not limited to:

[0147] General-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0148] In some embodiments of this application, the memory 31 includes, but is not limited to:

[0149] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0150] In some embodiments of this application, the computer program may be divided into one or more modules, which are stored in the memory 31 and executed by the processor 32 to perform the method provided in this application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the rate control device.

[0151] like Figure 3 As shown, the electronic device 30 may further include:

[0152] Transceiver 33, which can be connected to processor 32 or memory 31.

[0153] The processor 32 can control the transceiver 33 to communicate with other devices; specifically, it can send information or data to other devices or receive information or data sent by other devices. The transceiver 33 may include a transmitter and a receiver. The transceiver 33 may further include antennas, and the number of antennas may be one or more.

[0154] It should be understood that the various components in the device are connected through a bus system, which includes a data bus, a power bus, a control bus, and a status signal bus.

[0155] According to one aspect of this application, a computer storage medium is provided that stores a computer program thereon, which, when executed by a computer, enables the computer to perform the methods of the above-described method embodiments. Alternatively, embodiments of this application also provide a computer program product containing instructions that, when executed by a computer, cause the computer to perform the methods of the above-described method embodiments.

[0156] According to another aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computing device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computing device to perform the method of the above-described method embodiments.

[0157] In other words, when implemented using software, it can be implemented wholly or partially in the form of a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0158] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0159] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0160] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. For example, the functional modules in the various embodiments of this application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0161] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A rate control method, characterized in that, include: Obtain the N candidate rates corresponding to the current time and determine the environmental feature vector at the current time; For each of the N candidate rates, an environmental feature library corresponding to the candidate rate is determined. The environmental feature library is obtained based on the environmental feature vector corresponding to each time the candidate rate is used to send a data packet. The packet sending success rate corresponding to each environmental feature vector in the environmental feature library when the candidate rate is used to send a data packet is determined. For each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library, the estimated packet transmission success rate corresponding to the candidate rate is determined. Based on the N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, the target rate at the current moment is determined, and data packets are sent based on the target rate. The environmental feature vector is obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2.

2. The method according to claim 1, characterized in that, The step of determining the estimated packet success rate corresponding to the candidate rate based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library includes: For each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time is determined. For each of the N candidate rates, the estimated packet success rate corresponding to the candidate rate is determined based on the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library.

3. The method according to claim 2, characterized in that, The step of determining the similarity between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time, based on the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, includes: For each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time, the distance between each environmental feature vector in the environmental feature library and the environmental feature vector at the current time is determined; For each of the N candidate rates, the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time is obtained based on the distance between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current time.

4. The method according to claim 2, characterized in that, The method of determining the estimated packet success rate corresponding to the candidate rate based on the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current moment, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library, includes: For each of the N candidate rates, based on the similarity between each environmental feature vector in the environmental feature library corresponding to the candidate rate and the environmental feature vector at the current moment, the weight of the packet transmission success rate corresponding to each environmental feature vector in the environmental feature library when sending data packets using the candidate rate is determined. For each of the N candidate rates, based on the weight of the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library, the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature is weighted and summed to obtain the estimated packet transmission success rate corresponding to the candidate rate.

5. The method according to claim 2, characterized in that, The step of determining the target rate at the current moment based on the N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates includes: For each of the N candidate rates, the product of the candidate rate and the estimated packet success rate corresponding to the candidate rate is determined as the estimated throughput corresponding to the candidate rate. The target rate is determined based on the estimated throughput corresponding to each of the N candidate rates.

6. The method according to claim 5, characterized in that, Determining the target rate based on the estimated throughput corresponding to each of the N candidate rates includes: The candidate rate with the highest estimated throughput among the N candidate rates is determined as the target rate.

7. The method according to claim 2, characterized in that, The method further includes: If the similarity between the current environmental feature vector and each environmental feature vector in the environmental feature library corresponding to the target rate is lower than the first threshold, then the current environmental feature vector is added to the environmental feature library corresponding to the target rate.

8. The method according to claim 1, characterized in that, Determine the environmental feature vector corresponding to the time the data packet is sent, including: Obtain the M environmental parameters corresponding to the data packet being sent, and determine the weight of each of the M environmental parameters. For each of the M environmental parameters, a weighted value is obtained based on the weight corresponding to the environmental parameter. Based on the weighted value of each of the M environmental parameters, the environmental feature vector corresponding to the data packet is determined.

9. The method according to claim 8, characterized in that, The step of determining the environmental feature vector corresponding to the transmission of data packets based on the weighted value corresponding to each of the M environmental parameters includes: The weighted values ​​corresponding to each of the M environmental parameters are normalized to obtain the standard values ​​corresponding to each of the M environmental parameters. Based on the standard value corresponding to each of the M environmental parameters, the environmental feature vector corresponding to the data packet is obtained.

10. The method according to any one of claims 1-9, characterized in that, The environmental parameters include: environmental interference index, channel occupancy rate, number of communicating parties sending data packets, client signal strength, and the packet sending time of the communicating parties.

11. A rate control device, characterized in that, include: The first determining unit is used to obtain the N candidate rates corresponding to the current time and determine the environmental feature vector at the current time. The second determining unit is used to determine the environmental feature library corresponding to each of the N candidate rates for each candidate rate. The environmental feature library is obtained based on the environmental feature vector corresponding to each time the candidate rate is used to send a data packet, and to determine the packet sending success rate corresponding to each environmental feature vector in the environmental feature library when the candidate rate is used to send a data packet. The third determining unit is used to determine the estimated packet success rate corresponding to the candidate rate for each of the N candidate rates, based on the environmental feature library corresponding to the candidate rate, the environmental feature vector at the current time, and the packet transmission success rate corresponding to sending data packets using the candidate rate under each environmental feature vector in the environmental feature library. The fourth determining unit determines the target rate at the current moment based on the N candidate rates and the estimated packet transmission success rate corresponding to each of the N candidate rates, and sends data packets based on the target rate. The environmental feature vector is obtained based on M environmental parameters, where N and M are both positive integers greater than or equal to 2.

12. An electronic device, characterized in that, include: Memory, processor; The memory is used to store computer programs; The processor is configured to execute the computer program to implement the method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 10.

Images