Method and system for adjusting tcp flow

Abstract

The embodiment of the application relates to the communication field, and discloses a TCP flow adjusting method and system. In the application, by using intelligent analysis and statistics of the NWDAF and trend prediction, SMF data provided by the SMF and UPF data provided by the UPF are analyzed, and then an adjusting strategy of TCP flow generated when each APP accesses a network is estimated, such as accelerating TCP flow of certain APP, and limiting speed of certain APP, finally, the estimated TCP flow adjusting strategy is pushed to a TCP acceleration device between a UPF and an external gateway, so that the TCP acceleration device can reasonably adjust TCP flow from the UPF, and then the experience of user network access of a mobile terminal is improved as much as possible under limited network resources.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular to a method and system for adjusting TCP streams. Background Technology

[0002] 5G communication networks are characterized by high speed (enhanced mobile broadband, eMBB), large capacity (massive machine-type communications, mMTC), and low latency (ultra-reliable low-latency communications, uRLLC). Therefore, with the development of 5G communication networks, the user's network access experience has been greatly improved.

[0003] However, as people's internet browsing habits shift from PCs to mobile devices, coupled with the increasing popularity of video and live streaming, users' demand for mobile network bandwidth is growing rapidly. In order to enhance operators' competitiveness, it is particularly important to maximize the network access experience for mobile users by utilizing limited network resources. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for adjusting TCP (Transmission Control Protocol) streams, aiming to solve the above-mentioned technical problems.

[0005] To address the aforementioned technical problems, embodiments of this application provide a TCP stream adjustment method applied to NWDAF (Network Data Analytics Function), the method comprising: SMF (Session management function, which sends log subscription commands to both the session management function and UPF (User Plane Function); Receive SMF data fed back by the SMF according to the log subscription instruction, and UDF data fed back by the UPF according to the log subscription instruction; Analyze the SMF data and the UDF data to predict TCP flow adjustment strategies; The TCP flow adjustment strategy is pushed to the TCP acceleration device that is pre-connected between the UPF and the external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each APP (Application) when accessing the network according to the TCP flow adjustment strategy.

[0006] To achieve the above objectives, this application also provides a TCP stream adjustment method applied to a TCP acceleration device, wherein the TCP acceleration device is communicatively connected to a Network Data Analysis Function (NWDAF), a User Plane Function (UPF), and an external gateway, respectively. The method includes: Send a TCP stream adjustment policy subscription instruction to the NWDAF; The system receives a TCP traffic adjustment strategy from the NWDAF based on the TCP traffic adjustment strategy subscription instruction. The TCP traffic adjustment strategy is determined by the SMF data fed back by the NWDAF based on the Session Management Function (SMF) and the UPF data fed back by the UPF. According to the TCP traffic adjustment strategy, the TCP streams generated by each application (APP) when accessing the network are adjusted.

[0007] To achieve the above objectives, embodiments of this application also provide a TCP stream adjustment device, comprising: The log subscription module is used to send log subscription instructions to the Session Management Function (SMF) and the User Plane Function (UPF), respectively. The data receiving module is used to receive SMF data fed back by the SMF according to the log subscription instruction, and UDF data fed back by the UPF according to the log subscription instruction; The data analysis module is used to analyze the SMF data and the UDF data to predict TCP flow adjustment strategies. The strategy push module is used to push the TCP flow adjustment strategy to the TCP acceleration device that is pre-connected between the UPF and the external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

[0008] To achieve the above objectives, embodiments of this application also provide a TCP stream adjustment device, comprising: The policy subscription module is used to send TCP stream adjustment policy subscription instructions to the NWDAF; The policy receiving module is used to receive the TCP traffic adjustment policy fed back by the NWDAF according to the TCP traffic adjustment policy subscription instruction. The TCP traffic adjustment policy is determined by the SMF data fed back by the NWDAF based on the session management function SMF and the UPF data fed back by the UPF. The TCP flow adjustment module is used to adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

[0009] To achieve the above objectives, embodiments of this application also provide a network data analysis function, including: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the adjustment method for the TCP stream applied to NWDAF as described above.

[0010] To achieve the above objectives, embodiments of this application also provide a TCP acceleration device, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the TCP stream adjustment method applied to the TCP acceleration device as described above.

[0011] To achieve the above objectives, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the TCP stream adjustment method applied to NWDAF as described above, or the TCP stream adjustment method applied to a TCP acceleration device as described above.

[0012] To achieve the above objectives, embodiments of this application also provide a TCP stream adjustment system, comprising: The TCP acceleration device described above; and, The network data analysis function NWDAF, user plane function UPF, and external gateway described above are communicatively connected to the TCP acceleration device; and, The session management function (SMF) is connected to the NWDAF; wherein, The NWDAF is also communicatively connected to the UPF; The NWDAF is used to perform the TCP stream adjustment method applied to the NWDAF as described above; The TCP acceleration device is used to execute the TCP stream adjustment method applied to the TCP acceleration device as described above.

[0013] NWDAF is a data-aware analysis network element that automatically senses and analyzes the network based on network data, participating in the entire lifecycle of network planning, construction, operation, optimization, and maintenance. This makes the network easier to maintain and control, improves network resource utilization efficiency, and enhances user service experience. Based on this, the TCP flow adjustment method and system proposed in this application utilizes NWDAF's intelligent analysis and statistics, combined with trend prediction, to analyze SMF data provided by SMF and UPF data provided by UPF. This analysis then predicts adjustment strategies for the TCP flows generated when various apps access the network, such as accelerating the TCP flows of certain apps and limiting the rates of others. Finally, the predicted TCP flow adjustment strategies are pushed to a TCP acceleration device pre-connected between the UPF and the external gateway. This allows the TCP acceleration device to reasonably adjust the TCP flows from the UPF, thereby maximizing the user network access experience for mobile terminals within limited network resources. Attached Figure Description

[0014] One or more embodiments are illustrated by way of example with reference to the accompanying drawings, and these illustrative descriptions do not constitute a limitation on the embodiments.

[0015] Figure 1 This is a schematic diagram of the structure of the TCP stream adjustment system provided in the first embodiment of this application; Figure 2 This is a schematic diagram of the architecture of the TCP stream adjustment system provided in the first embodiment of this application in a 5G network; Figure 3 This is a flowchart of the TCP stream adjustment method provided in the second embodiment of this application; Figure 4 This is a schematic diagram of the interactions between the various functional entities involved in the TCP stream adjustment method provided in the second embodiment of this application; Figure 5 This is a flowchart of the TCP stream adjustment method provided in the third embodiment of this application; Figure 6 This is a schematic diagram of the TCP stream adjustment device provided in the fourth embodiment of this application; Figure 7 This is a schematic diagram of the structure of the TCP stream adjustment device provided in the fifth embodiment of this application; Figure 8 This is a schematic diagram of the network data analysis function provided in the sixth embodiment of this application; Figure 9 This is a schematic diagram of the TCP acceleration device provided in the seventh embodiment of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the various embodiments of this application will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details have been provided in the various embodiments of this application to help readers better understand this application. However, the technical solutions claimed in this application can be implemented even without these technical details and various changes and modifications based on the following embodiments. The division of the various embodiments below is for the convenience of description and should not constitute any limitation on the specific implementation of this application. The various embodiments can be combined with and referenced by each other without contradiction.

[0017] The first embodiment of this application relates to a TCP stream adjustment system, such as... Figure 1 As shown, the TCP stream adjustment system includes: a TCP acceleration device 10, a network data analysis function 20, a session management function 30, a user plane function 40, and an external gateway 50.

[0018] The TCP acceleration device 10 is communicatively connected to the network data analysis function 20, the user plane function 40, and the external gateway 50, respectively. The network data analysis function 20 is also communicatively connected to the session management function 30 and the user plane function 40.

[0019] It is understood that the network data analysis function 20 mentioned in this embodiment is the NWDAF (Network Data Analytics Function) in the field of communications. It is a functional entity proposed by the 5th-Generation (5G) mobile communication technology system. It can be regarded as a data-aware analysis network element. It mainly uses network data as a basis to automatically sense and analyze the network, and participates in the entire life cycle of network planning, construction, operation and maintenance, network optimization and operation, so as to make the network easier to maintain and control, improve the efficiency of network resource utilization, and enhance the user service experience.

[0020] Similarly, Session Management Function 30 is also a functional entity of the 5G service-based architecture, namely the SMF (Session Management Function) in the communications field. Specifically, in practical applications, the SMF is mainly responsible for interacting with the classified data plane, creating, updating, and deleting Protocol Data Unit (PDU) sessions, and managing the session context with User Plane Function 40. That is, in practical applications, there is also a communication connection between Session Management Function 30 and User Plane Function 40.

[0021] Similarly, User Plane Function 40 is also an important functional entity in the 5G service-based architecture, namely the UPF (User Plane Function) in the field of communications.

[0022] The TCP acceleration device 10 is a new functional entity added to the 5G service-based architecture in this embodiment. It is mainly used to accelerate or limit the TCP flow according to the TCP flow adjustment strategy provided by the network data sub-function 20.

[0023] To better understand the TCP stream adjustment strategy provided in this embodiment and its impact on TCP stream adjustment, the following is combined with... Figure 2 The architecture diagram of the given 5G network is used for illustration.

[0024] For ease of explanation, the following will first... Figure 2 A brief description of the network element functional entities in the architecture shown: like Figure 2As shown, the network element functional entities such as NSSF (Network Slice Selection Function), AUSF (Authentication Server Function), NEF (Network Exposure Function), UDM (Unified Data Management), NRF (NF Repository Function), PCE (Policy Control Function), and AF (Application Function) are connected to the network element functional entities such as AMF (Access and Mobility Management Function), SMF (Session Management Function), and NWDAF (Network Data Analytics Function) through the network bus. AMF, in turn, is connected to UE (User Equipment) through the N1 interface (the signaling plane interface between UE and AMF, a logical interface) and to (R)AN (Radio Access Authentication Server Function) through the N2 interface (the signaling plane interface between (R)AN and AMF, similar to the s1-mme interface in 4G). The UE connects to the (R)AN via wired or wireless means. The (R)AN connects to the UPF via the N3 interface (the interface between the (R)AN and the UPF, mainly used to transmit uplink and downlink user plane data between the 5G (R)AN and the UPF). The UPF connects to the SMF via the N4 interface (the interface between the SMF and the UPF, used to transmit control plane information between the SMF and the UPF). The TCPO (TCP acceleration device) connects to the UPF and the DN (Data Network, such as operator services, Internet access, or third-party services) via the N6 interface (the interface between the UPF and the DN, used to transmit uplink and downlink user data streams between the UPF and the DN, and communicates with the DN network based on IP and routing protocols).

[0025] It should be noted that the DN mentioned above is the external gateway mentioned in this embodiment. In practical applications, the external gateway can be a DN, a FW (firewall), or other network devices in the core network that carry out the function of a gateway.

[0026] Furthermore, it should be understood that the above is only a specific architecture in the current 5G network and does not constitute a limitation on the technical solution of this application. In practical applications, the specific network element functional entities in the architecture can be changed according to business needs, as long as the architecture contains the TCP acceleration device 10, network data analysis function 20, session management function 30, user plane function 40 and external gateway 50 mentioned in this embodiment, and ensures that these five network element functional entities communicate and connect in accordance with the connection relationship described in this embodiment.

[0027] based on Figure 2 The structure shown, when implementing adjustments to the TCP stream, is as follows: First, by TCPO (i.e. Figure 1 The TCP acceleration device 10 in the middle) sends to NWDAF (i.e. Figure 1 The network data analysis function 20) sends a TCP stream adjustment strategy subscription instruction.

[0028] Next, after receiving the TCP flow adjustment policy subscription instruction from TCPO, NWDAF generates a log subscription instruction and sends the generated log subscription instruction to SMF (i.e., Figure 1 The session management function 30) and UPF (i.e. Figure 1 The user face function 40 in the middle enables SMF to push the generated data (hereinafter referred to as SMF data) to NWDAF when it detects the creation, updating or release of PDU sessions; and enables UF to push the generated data (hereinafter referred to as UPF data) to NWDAF when it detects a stream release operation.

[0029] Next, based on its ability to analyze and predict network data, NWDAF analyzes SMF and UDF data, and then estimates a suitable TCP flow adjustment strategy for the current network, and pushes the obtained TCP flow adjustment strategy to TCPO.

[0030] Finally, TCPO adjusts the TCP streams generated by each application (APP) accessing the network released by UPF according to the received TCP stream adjustment strategy. For example, it accelerates the TCP streams corresponding to high-value APPs and then sends them to the external gateway DN, while it limits the TCP streams corresponding to low-value APPs and then sends them to the external gateway DN.

[0031] Therefore, the TCP flow adjustment system provided in this embodiment utilizes the intelligent analysis and statistics of NWDAF combined with trend prediction to analyze the SMF data provided by SMF and the UPF data provided by UPF, and then predicts the adjustment strategy for the TCP flow generated when each APP accesses the network. For example, the TCP flow of a certain type of APP is accelerated, while the TCP flow of another type is rate-limited. Finally, the predicted TCP flow adjustment strategy is pushed to the TCP acceleration device that is pre-connected between UPF and external gateway, so that the TCP acceleration device can reasonably adjust the TCP flow from UPF, thereby improving the user network access experience of mobile terminals as much as possible under limited network resources.

[0032] The second embodiment of this application relates to a TCP stream adjustment method applied to the Network Data Analysis Function (NWDAF).

[0033] For details regarding NWDAF, other network element functional entities involved in implementing the TCP flow adjustment method, and the connection relationships between these network element functional entities, please refer to the TCP flow adjustment system corresponding to the first embodiment of this application. Figure 1 and Figure 2 .

[0034] The implementation details of the TCP stream adjustment method in this embodiment are described below. The following implementation details are provided for ease of understanding only and are not necessary for implementing this solution.

[0035] The specific process of this embodiment is as follows: Figure 3 As shown, the specific steps include: Step 301: Send log subscription instructions to the Session Management Function (SMF) and the User Plane Function (UPF) respectively.

[0036] Step 302: Receive SMF data fed back by the SMF according to the log subscription instruction, and UDF data fed back by the UPF according to the log subscription instruction.

[0037] Step 303: Analyze the SMF data and the UDF data to predict the TCP flow adjustment strategy.

[0038] Step 304: Push the TCP flow adjustment strategy to the TCP acceleration device that is pre-connected between the UPF and the external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

[0039] To better understand the operations in steps 301 to 304, the following will be combined with... Figure 4 Please provide a detailed explanation: (1) TCPO (TCP Accelerator) sends a TCP stream adjustment policy subscription instruction to NWDAF.

[0040] That is, in practical applications, the prerequisite for triggering NWDAF to execute steps 301 to 304 is that NWDAF receives a TCP stream adjustment policy subscription instruction sent by TCPO (TCP Acceleration Device).

[0041] (2) After receiving the TCP flow adjustment policy subscription instruction sent by TCPO, NWDAF will generate a log subscription instruction and send the generated log subscription instruction to SMF and UPF respectively.

[0042] In practical applications, the log subscription instruction mentioned above specifically refers to the instruction to subscribe to the call history record log (CHR log). That is, the SMF data and UPF data subsequently received from the CHR log are extracted from the CHR log.

[0043] As described in the first embodiment, the SMF is primarily responsible for interacting with the classified data plane, creating, updating, and deleting PDU sessions. Therefore, when a PDU session is generated by an interaction such as creation, updating, or deletion, the SMF will perform a control plane creation information collection operation and push the collected data (hereinafter referred to as SMF data) to the NWDAF.

[0044] Accordingly, since the UPF is mainly responsible for sending the flow generated when the UE (in this embodiment, mainly the TCP flow) accesses the network by the APP in the mobile user equipment to the external gateway, i.e., releasing the flow, the UPF will collect flow information when there is a flow release and push the collected data (hereinafter referred to as UPF data) to the NWDAF.

[0045] (3) After receiving SMF data and UPF data, NWDAF will analyze the SMF data and UDF data based on its own analysis and prediction capabilities, and then predict the TCP flow adjustment strategy.

[0046] Specifically, regarding the NWDAF's analysis of the SMF and UDF data to predict the TCP flow adjustment strategy, in practical applications, it specifically involves: First, the SMF data and the UDF data are merged according to preset field information to obtain the data to be processed.

[0047] Specifically, in this embodiment, the SEID (Near Field Communication NFC serial number) and N4 interface are used as preset field information, and the SMF data and UDF data are merged, that is, the data with the same SEID provided by the N4 interface are merged.

[0048] Based on this approach, the merged data to be processed mainly includes: International Mobile Subscriber Identity (IMSI), private network address, private network port, protocol type, destination address, destination port, number of packets, duration, known APP type, and Uniform Resource Locator (URL).

[0049] Then, based on a preset trend prediction machine learning algorithm, the data in different time dimensions and different usage areas of the data to be processed are analyzed using preset time granularity and preset region as dimensions to obtain the TCP flow adjustment strategy.

[0050] Specifically, in this embodiment, the TCP flow adjustment strategy is designed to quickly identify apps that consume a lot of bandwidth but have low value, as well as high-value apps, such as popular apps.

[0051] Therefore, when estimating the TCP flow adjustment strategy based on the above method, specifically using a preset time granularity and preset region as dimensions, the source IP address of each user terminal, the destination IP address corresponding to each APP in each user terminal, and the historical traffic usage information of each APP are statistically analyzed in the data to be processed at different time dimensions and different usage regions. Then, by traversing each APP, a mapping relationship is established between the source IP address and the destination IP address and historical traffic usage information corresponding to the traversed APP, resulting in a historical traffic usage statistics table for each APP. Finally, based on a preset trend prediction machine learning algorithm, each piece of data with a mapping relationship recorded in the historical traffic usage statistics table is analyzed to obtain the TCP flow adjustment strategy.

[0052] The preset time granularity mentioned above can be in units of minutes, hours, or days, that is, once every minute, hour, or day; the preset area can be in units of communities.

[0053] Furthermore, it should be noted that in practical applications, TCP acceleration devices used to adjust TCP streams can only identify the destination IP address and adjust the corresponding TCP stream for acceleration or rate limiting based on the destination IP. Therefore, the TCP stream adjustment strategies described above specifically record the destination IP addresses that need acceleration and the destination IP addresses that need rate limiting.

[0054] Regarding the aforementioned destination IP addresses that require rate limiting, NWDAF specifically identifies the destination IP addresses corresponding to low-value apps that consume large amounts of bandwidth by analyzing each data entry with a mapping relationship recorded in the historical traffic usage statistics table based on a preset trend prediction machine learning algorithm.

[0055] It should be noted that the low-value apps that consume a lot of traffic mentioned in this embodiment are specifically derived by NWDAF through analysis and statistics based on the data recorded in the historical traffic usage statistics table. This includes the historical traffic usage of the N cells that experienced network congestion, as well as the IMSI of UEs that frequently occurred during congestion and the apps that consumed a lot of traffic but had a low usage rate.

[0056] For example, statistics might reveal that within the current statistical period, congestion occurs in one of the top N cells. In this cell, 1000 users are connected to the network, but only 10 users (10 different IMSI UEs) are using P2P apps to access the network, yet they are consuming a significant amount of bandwidth allocated to that cell. In order to avoid impacting the internet experience of other users (the other 990), these 0 different IMSI UEs using P2P apps would be considered low-value apps consuming large amounts of bandwidth, and therefore, their bandwidth would need to be limited.

[0057] Accordingly, the destination IP address that needs to be accelerated, as mentioned above, is specifically identified by NWDAF based on a preset trend prediction machine learning algorithm. This algorithm analyzes each data point with a mapping relationship recorded in the historical traffic usage statistics table to identify the destination IP address corresponding to a high-value app.

[0058] Regarding the high-value apps mentioned above, in practical applications, they can be determined based on user popularity. For example, apps with high user traffic can be considered popular apps. These types of apps can be considered high-value apps.

[0059] It should be understood that the above examples are merely examples listed for the purpose of better understanding the technical solutions of this embodiment, and are not intended to be the only limitation of this embodiment.

[0060] Furthermore, considering the impact of factors such as seasons and holidays on the prediction results, high-frequency access to a certain type of app may only occur during specific seasons or holidays. For example, in winter, when it's cold, most users prefer to stay home and watch dramas, making video apps popular during this period. Similarly, for e-commerce online promotions at a specific time, live streaming apps may become popular at fixed points during that period due to online promotions. Therefore, to make the estimated TCP flow adjustment strategy more consistent with reality, NWDAF, when estimating the TCP flow adjustment strategy, can first obtain the generation time of the historical traffic usage information recorded in the historical traffic usage statistics table for each data point with a mapping relationship. Then, for each data point with a mapping relationship recorded in the historical traffic usage statistics table, based on the trend prediction machine learning algorithm and combined with the generation time, it analyzes and obtains the TCP flow adjustment strategy.

[0061] Therefore, by incorporating the generation time of historical traffic usage information of each APP when estimating TCP flow adjustment strategies, the current season, as well as whether it is a holiday or a certain specific event day, can be determined based on the generation time. In turn, when analyzing the data in the historical traffic usage statistics table based on trend prediction machine learning algorithms, the impact of factors such as seasons and holidays on the trend can be taken into account, making the estimated TCP flow adjustment strategy more reasonable.

[0062] Furthermore, it is worth mentioning that the aforementioned trend prediction machine learning algorithms can be, in practical applications, Autoregressive Integrated Moving Average Model (ARIMA), Prophet (Time Series Forecasting Library) model, Long Short-Term Memory (LSTM) model, etc., which will not be listed here, and this embodiment does not limit them.

[0063] To facilitate understanding, the following explanation uses the LSTM model as an example to illustrate the operation of predicting TCP flow adjustment strategies: Specifically, in practical applications, in order to quickly and accurately predict TCP flow adjustment strategies suitable for the actual situation, a network model with an LSTM and a fully connected layer can be pre-built. Then, by iteratively training the built network model, a TCP flow adjustment strategy prediction model can be obtained. In this way, each time new SMF and UDF data are obtained, the two can be directly merged and input into the TCP flow adjustment strategy prediction model, and the output of the TCP flow adjustment strategy prediction model can be used as the predicted TCP flow adjustment strategy.

[0064] The training of the TCP flow adjustment strategy prediction model is detailed below: First, the pre-acquired sample data, which is the data formed by merging SMF data and UDF data generated at historical moments, is divided into training set and test set in a 7:3 ratio.

[0065] Then, the flow values ​​in the training set for a fixed time period are normalized to improve the descent speed of the gradient term.

[0066] Next, the normalized flow values ​​are sequentially input into the constructed network model for iterative training. For example, the input flow values ​​are the flow values ​​at times t-4, t-3, t-2, and t-1. Based on these flow values, the flow value at time t is predicted. Then, the predicted flow value at time t is added to the training set to predict the flow value at time t+1. The overall process is as follows: Input: t-4, t-3, t-2, t-1; Prediction: t Input: t-3, t-2, t-1, t; Prediction: t+1 Input: t-2, t-1, t-0, t+1; Prediction: t+2 The entire process iterates continuously until the required granularity for prediction is reached.

[0067] Next, the predicted values ​​output by the above time series are input into the network model and compared with the actual values. The mean squared error (MSE) loss function is used, and the ADAM optimization algorithm is used to optimize the loss function. By optimizing the loss function, gradient descent training is continuously performed. As the loss function converges, a suitable network model can be obtained.

[0068] Finally, in the test set that has also undergone normalization, the traffic values ​​corresponding to different times are input into the network model after iterative training. Then, the output predicted value is compared with the actual value. When the performance index of the test result reaches the expectation, such as the test value being basically the same as the actual value, or the error being within a certain range, the current network model can be determined as the TCP flow adjustment strategy prediction model. That is, the model can be used to predict the traffic trend of the cell at a certain time in the future, and to formulate a TCP flow adjustment strategy suitable for the cell.

[0069] For example, once it is predicted that the traffic trend behind the cell shows a significant upward trend, such as the growth rate of the upward trend exceeding the preset value, for example, the traffic increases by 30% within 30 minutes, the private network IP corresponding to the IMSI that caused the cell congestion and the destination IP of the low-value APP accessing it will be identified as the destination IP that needs to be rate-limited. This TCP flow adjustment strategy will be pushed to the TCP acceleration device, which will then limit the TCP flow generated by the APP corresponding to the destination IP when accessing the network according to the required rate-limited destination IP. Conversely, the TCP acceleration device will accelerate the TCP flow generated by the APP corresponding to the destination IP when accessing the network according to the required acceleration destination IP.

[0070] In other words, Figure 4 In the process, after receiving the TCP flow adjustment policy pushed by NWDAF, TCPO identifies the destination IP address in the UE Internet access flow sent by UPF based on the destination IP address that needs to be accelerated recorded in the TCP flow adjustment policy. Then, it accelerates the TCP flow corresponding to the destination IP address that needs to be accelerated, i.e., the high-value APP, and then sends the accelerated TCP flow to the external gateway. Conversely, based on the destination IP address that needs to be rate-limited recorded in the TCP flow adjustment policy, it identifies the destination IP address in the UE Internet access flow sent by UPF. Then, it rates the TCP flow corresponding to the destination IP address that needs to be rate-limited, i.e., the low-value APP, and then sends the rate-limited TCP flow to the external gateway.

[0071] As can be seen from the above description, the TCP flow adjustment method provided in this embodiment utilizes the intelligent analysis and statistics of NWDAF combined with trend prediction to analyze the SMF data provided by SMF and the UPF data provided by UPF, thereby predicting the adjustment strategy for the TCP flow generated when each APP accesses the network. For example, the TCP flow of a certain type of APP is accelerated, while the TCP flow of another type is rate-limited. Finally, the predicted TCP flow adjustment strategy is pushed to the TCP acceleration device that is pre-connected between UPF and external gateway, so that the TCP acceleration device can reasonably adjust the TCP flow from UPF, thereby improving the user network access experience of mobile terminals as much as possible under limited network resources.

[0072] In other words, based on the TCP stream adjustment method provided in this embodiment, it is possible to adjust the TCP stream generated by each APP when accessing the network reasonably, rather than uniformly adjusting all TCP streams, such as limiting or accelerating the TCP streams of high-value APPs, when the mobile network is busy. This allows limited mobile network resources to be used more efficiently, thereby improving user experience, increasing operator user stickiness, and enhancing operator competitiveness.

[0073] The third embodiment of this application relates to a TCP stream adjustment method, applied to a TCP acceleration device.

[0074] For details regarding the TCP acceleration device, other network element functional entities involved in implementing the TCP stream adjustment method, and the connection relationships between these network element functional entities, please refer to the TCP stream adjustment system corresponding to the first embodiment of this application. Figure 1 and Figure 2 .

[0075] The implementation details of the TCP stream adjustment method in this embodiment are described below. The following implementation details are provided for ease of understanding only and are not necessary for implementing this solution.

[0076] like Figure 5 As shown, the TCP stream adjustment method involved in the second embodiment includes the following steps: Step 501: Send a TCP stream adjustment policy subscription instruction to the NWDAF.

[0077] Step 502: Receive the TCP traffic adjustment strategy fed back by the NWDAF according to the TCP traffic adjustment strategy subscription instruction. The TCP traffic adjustment strategy is determined by the SMF data fed back by the NWDAF based on the Session Management Function (SMF) and the UPF data fed back by the UPF.

[0078] Step 503: Adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

[0079] Specifically, the TCP flow adjustment strategy predicted by NWDAF records the destination IP addresses that need to be accelerated and the destination IP addresses that need to be rate-limited.

[0080] Therefore, when adjusting the TCP streams generated by each APP when accessing the network according to the TCP stream adjustment strategy, the specific process is to read the destination IP address that needs to be accelerated and the destination IP address that needs to be rate-limited from the TCP stream adjustment strategy, and then accelerate the TCP streams generated by the APP corresponding to the destination IP address that needs to be accelerated when accessing the network based on the destination IP address that needs to be accelerated.

[0081] Accordingly, based on the destination IP address that needs to be rate-limited, the TCP streams generated when the APP corresponding to the destination IP address accesses the network are rate-limited.

[0082] Furthermore, in practical applications, NWDAF may analyze SMF and UPF data, and the estimated TCP flow adjustment strategy may only include one type of adjustment information for the TCP flow: acceleration or rate limiting.

[0083] Therefore, in order to enable the TCP acceleration device to better adapt to actual use scenarios, before the TCP acceleration device reads the destination IP address that needs to be accelerated and the destination IP address that needs to be rate-limited from the TCP flow adjustment policy, it can first determine whether the TCP flow adjustment policy carries the destination IP address that needs to be accelerated and the destination IP address that needs to be rate-limited, and then trigger the subsequent adjustment operation based on the determination result.

[0084] Specifically, if it is determined through judgment that the TCP stream outgoing policy carries the destination IP address that needs to be accelerated and the destination IP address that needs to be rate-limited, then the steps of accelerating the TCP stream generated when the APP corresponding to the destination IP address that needs to be accelerated accesses the network according to the destination IP address that needs to be accelerated, and rate-limiting the TCP stream generated when the APP corresponding to the destination IP address that needs to be rate-limited accesses the network according to the destination IP address that needs to be rate-limited; If it is determined through judgment that the TCP stream outgoing policy only carries the destination IP address that needs to be accelerated, then only the step of accelerating the TCP stream generated when the APP corresponding to the destination IP address that needs to be accelerated accesses the network is executed; If, through judgment, it is determined that the TCP stream outgoing policy only carries the destination IP address that needs to be rate-limited, then only the step of rate-limiting the TCP stream generated when the APP corresponding to the destination IP address that needs to be rate-limited accesses the network is executed.

[0085] It is not difficult to see that steps 501 to 503 in this embodiment are related to steps 301 to 304 in the second embodiment. That is, when implementing TCP flow adjustment, the overall solution requires all operations of steps 301 to 304 and steps 501 to 503. The specific implementation of steps 501 to 503 in this embodiment has been discussed in the second embodiment. Figure 4 As explained in the introduction, it will not be repeated here.

[0086] Therefore, the TCP flow adjustment method provided in this embodiment utilizes the intelligent analysis and statistics of NWDAF combined with trend prediction to analyze the SMF data provided by SMF and the UPF data provided by UPF, and then predicts the adjustment strategy for the TCP flow generated when each APP accesses the network. For example, the TCP flow of a certain type of APP is accelerated, while the TCP flow of another type is rate-limited. Finally, the predicted TCP flow adjustment strategy is pushed to the TCP acceleration device that is pre-connected between UPF and external gateway, so that the TCP acceleration device can reasonably adjust the TCP flow from UPF, thereby improving the user network access experience of mobile terminals as much as possible under limited network resources.

[0087] Furthermore, it should be understood that the step divisions of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0088] The fourth embodiment of this application relates to a TCP stream adjustment device, such as... Figure 6 As shown, the TCP stream adjustment device 600 includes: a log subscription module 601, a data receiving module 602, a data analysis module 603, and a policy push module 604.

[0089] The system includes a log subscription module 601, which sends log subscription instructions to the Session Management Function (SMF) and the User Plane Function (UPF), respectively; a data receiving module 602, which receives SMF data fed back by the SMF according to the log subscription instructions, and UDF data fed back by the UPF according to the log subscription instructions; a data analysis module 603, which analyzes the SMF data and the UDF data to predict TCP flow adjustment strategies; and a strategy push module 604, which pushes the TCP flow adjustment strategy to a TCP acceleration device pre-connected between the UPF and an external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

[0090] In another example, the data analysis module 603 is specifically used to merge the SMF data and the UDF data according to preset field information to obtain data to be processed; based on a preset trend prediction machine learning algorithm, with preset time granularity and preset region as dimensions, it analyzes the data in different time dimensions and different usage regions in the data to be processed to obtain the TCP flow adjustment strategy.

[0091] Furthermore, in another example, the preset trend prediction machine learning algorithm analyzes data from different time dimensions and different usage areas in the data to be processed, using preset time granularity and preset region as dimensions, to obtain the TCP flow adjustment strategy, specifically: Using preset time granularity and preset region as dimensions, the source IP address of each user terminal, the destination IP address of each APP in each user terminal, and the historical traffic usage information of each APP are statistically analyzed in the data to be processed under different time dimensions and different usage regions. By iterating through each of the apps, a mapping relationship is established between the source IP address and the destination IP address and historical traffic usage information of the app, resulting in a historical traffic usage statistics table for each app. Based on a preset trend prediction machine learning algorithm, the TCP flow adjustment strategy is obtained by analyzing each data point with a mapping relationship recorded in the historical traffic statistics table.

[0092] Furthermore, in another example, the preset trend prediction machine learning algorithm analyzes each data point with a mapping relationship recorded in the historical traffic statistics table to obtain the TCP flow adjustment strategy, specifically: Obtain the generation time of the historical traffic usage information in each data entry with a mapping relationship recorded in the historical traffic usage statistics table; For each data point with a mapping relationship recorded in the historical traffic statistics table, the TCP flow adjustment strategy is obtained by analyzing the trend prediction machine learning algorithm in conjunction with the generation time.

[0093] Furthermore, in another example, the preset trend prediction machine learning algorithm analyzes each data point with a mapping relationship recorded in the historical traffic statistics table to obtain the TCP flow adjustment strategy, specifically: Based on a preset trend prediction machine learning algorithm, the system analyzes each data point with a mapping relationship recorded in the historical traffic usage statistics table to identify low-value apps and high-value apps that consume a lot of traffic. Obtain the destination IP address corresponding to the low-value APP and the destination IP address corresponding to the high-value APP; The TCP flow adjustment strategy is obtained by using the destination IP address corresponding to the low-value APP as the destination IP address that needs to be rate-limited, and the destination IP address corresponding to the high-value APP as the destination IP address that needs to be accelerated.

[0094] In another example, the step of pushing the TCP flow adjustment strategy to a TCP acceleration device pre-connected between the UPF and the external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy, specifically involves: The TCP flow adjustment policy is pushed to the TCP acceleration device that is pre-connected between the UPF and the external gateway. The TCP acceleration device accelerates the TCP flow generated when the APP corresponding to the destination IP address that needs acceleration is recorded in the TCP flow adjustment policy. Conversely, it limits the TCP flow generated when the APP corresponding to the destination IP address that needs rate limiting is recorded in the TCP flow adjustment policy.

[0095] It is not difficult to see that this embodiment is a device embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and will not be repeated here to reduce repetition. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the first embodiment.

[0096] It is worth mentioning that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by this invention; however, this does not mean that other units are absent from this embodiment.

[0097] The fifth embodiment of this application relates to a TCP stream adjustment device, such as... Figure 7 As shown, the TCP stream adjustment device 700 includes: a policy subscription module 701, a policy receiving module 702, and a TCP stream adjustment module 703.

[0098] The policy subscription module 701 is used to send a TCP flow adjustment policy subscription instruction to the NWDAF; the policy receiving module 702 is used to receive the TCP flow adjustment policy fed back by the NWDAF according to the TCP flow adjustment policy subscription instruction, wherein the TCP flow adjustment policy is determined by the SMF data fed back by the NWDAF based on the Session Management Function (SMF) and the UPF data fed back by the UPF; and the TCP flow adjustment module 703 is used to adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment policy.

[0099] In another example, the TCP flow adjustment module 703 is specifically used to read the destination IP address that needs to be accelerated and the destination IP address that needs to be rate-limited from the TCP flow adjustment strategy; accelerate the TCP flow generated when the APP corresponding to the destination IP address that needs to be accelerated accesses the network according to the destination IP address that needs to be accelerated; and rate-limit the TCP flow generated when the APP corresponding to the destination IP address that needs to be rate-limited accesses the network according to the destination IP address that needs to be rate-limited.

[0100] Furthermore, in another example, before reading the destination IP addresses that need acceleration and the destination IP addresses that need rate limiting from the TCP stream adjustment policy, the following is also included: Determine whether the TCP flow adjustment policy includes the destination IP address that needs to be accelerated and the destination IP address that needs to be rate-limited; If the destination IP address to be accelerated and the destination IP address to be rate-limited are carried, then the steps of accelerating the TCP stream generated when the APP corresponding to the destination IP address to be accelerated accesses the network according to the destination IP address to be accelerated, and rate-limiting the TCP stream generated when the APP corresponding to the destination IP address to be rate-limited accesses the network according to the destination IP address to be rate-limited. If only the destination IP address that needs to be accelerated is carried, then only the step of accelerating the TCP stream generated when the APP corresponding to the destination IP address that needs to be accelerated accesses the network is executed; If only the destination IP address that needs to be rate-limited is carried, then only the step of rate-limiting the TCP stream generated when the APP corresponding to the destination IP address accesses the network is executed.

[0101] It is not difficult to see that this embodiment is a device embodiment corresponding to the second embodiment, and this embodiment can be implemented in conjunction with the second embodiment. The relevant technical details mentioned in the second embodiment are still valid in this embodiment, and will not be repeated here to reduce repetition. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the second embodiment.

[0102] It is worth mentioning that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by this invention; however, this does not mean that other units are absent from this embodiment.

[0103] The sixth embodiment of this application relates to a network data analysis function, such as... Figure 8 As shown, it includes: at least one processor 801; and a memory 802 communicatively connected to the at least one processor; wherein the memory 802 stores instructions executable by the at least one processor 801, the instructions being executed by the at least one processor 801 to enable the at least one processor 801 to perform the TCP stream adjustment method applied to network data analysis functions as described above.

[0104] The memory 802 and processor 801 are connected via a bus, which can include any number of interconnecting buses and bridges. The bus connects various circuits of one or more processors 801 and memory 802 together. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 801 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to processor 801.

[0105] The processor 801 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. The memory 802 can be used to store data used by the processor 801 during operation.

[0106] The seventh embodiment of this application relates to a TCP acceleration device, such as... Figure 9As shown, it includes: at least one processor 901; and a memory 902 communicatively connected to the at least one processor; wherein the memory 902 stores instructions executable by the at least one processor 901, the instructions being executed by the at least one processor 901 to enable the at least one processor 901 to execute a TCP stream adjustment method applied to a TCP acceleration device.

[0107] The memory 902 and processor 901 are connected via a bus, which can include any number of interconnecting buses and bridges. The bus connects various circuits of one or more processors 901 and memory 902. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 901 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to processor 901.

[0108] Processor 901 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory 902 can be used to store data used by processor 901 during operation.

[0109] The eighth embodiment of this application relates to a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements a TCP stream adjustment method applied to network data analysis functions; or, a TCP stream adjustment method applied to a TCP acceleration device.

[0110] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0111] Those skilled in the art will understand that the above embodiments are specific embodiments for implementing this application, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of this application.

Claims

1. A method for adjusting a TCP stream, characterized in that, The method, applied to the Network Data Analysis Function (NWDAF), includes: Send log subscription commands to the Session Management Function (SMF) and the User Plane Function (UPF) respectively; Receive SMF data fed back by the SMF according to the log subscription instruction, and UDF data fed back by the UPF according to the log subscription instruction; Analyze the SMF data and the UDF data to predict TCP flow adjustment strategies; The TCP flow adjustment strategy is pushed to the TCP acceleration device that is pre-connected between the UPF and the external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

2. The TCP stream adjustment method as described in claim 1, characterized in that, The analysis of the SMF data and the UDF data to predict TCP flow adjustment strategies includes: The SMF data and the UDF data are merged according to preset field information to obtain the data to be processed; Based on a preset trend prediction machine learning algorithm, the TCP flow adjustment strategy is obtained by analyzing data in different time dimensions and different usage areas of the data to be processed, using preset time granularity and preset region as dimensions.

3. The TCP stream adjustment method as described in claim 2, characterized in that, The preset trend prediction machine learning algorithm analyzes data in different time dimensions and different usage areas of the data to be processed, using preset time granularity and preset region as dimensions, to obtain the TCP flow adjustment strategy, including: Using preset time granularity and preset region as dimensions, the source IP address of each user terminal, the destination IP address of each APP in each user terminal, and the historical traffic usage information of each APP are statistically analyzed in the data to be processed under different time dimensions and different usage regions. By iterating through each of the apps, a mapping relationship is established between the source IP address and the destination IP address and historical traffic usage information of the app, resulting in a historical traffic usage statistics table for each app. Based on a preset trend prediction machine learning algorithm, the TCP flow adjustment strategy is obtained by analyzing each data point with a mapping relationship recorded in the historical traffic statistics table.

4. The TCP stream adjustment method as described in claim 3, characterized in that, The preset trend prediction machine learning algorithm analyzes each data point with a mapping relationship recorded in the historical traffic statistics table to obtain the TCP flow adjustment strategy, including: Obtain the generation time of the historical traffic usage information in each data entry with a mapping relationship recorded in the historical traffic usage statistics table; For each data point with a mapping relationship recorded in the historical traffic statistics table, the TCP flow adjustment strategy is obtained by analyzing the trend prediction machine learning algorithm in conjunction with the generation time.

5. The TCP stream adjustment method as described in claim 3 or 4, characterized in that, The preset trend prediction machine learning algorithm analyzes each data point with a mapping relationship recorded in the historical traffic statistics table to obtain the TCP flow adjustment strategy, including: Based on a preset trend prediction machine learning algorithm, the system analyzes each data point with a mapping relationship recorded in the historical traffic usage statistics table to identify low-value apps and high-value apps that consume a lot of traffic. Obtain the destination IP address corresponding to the low-value APP and the destination IP address corresponding to the high-value APP; The TCP flow adjustment strategy is obtained by using the destination IP address corresponding to the low-value APP as the destination IP address that needs to be rate-limited, and the destination IP address corresponding to the high-value APP as the destination IP address that needs to be accelerated.

6. The TCP stream adjustment method as described in claim 5, characterized in that, The step of pushing the TCP flow adjustment strategy to the TCP acceleration device pre-connected between the UPF and the external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy, includes: The TCP flow adjustment policy is pushed to the TCP acceleration device that is pre-connected between the UPF and the external gateway. The TCP acceleration device accelerates the TCP flow generated when the APP corresponding to the destination IP address that needs acceleration is recorded in the TCP flow adjustment policy. Conversely, it limits the TCP flow generated when the APP corresponding to the destination IP address that needs rate limiting is recorded in the TCP flow adjustment policy.

7. A method for adjusting a TCP stream, characterized in that, The method, applied to a TCP acceleration device that is communicatively connected to a Network Data Analysis Function (NWDAF), a User Plane Function (UPF), and an external gateway, includes: Send a TCP stream adjustment policy subscription instruction to the NWDAF; The system receives a TCP traffic adjustment strategy from the NWDAF based on the TCP traffic adjustment strategy subscription instruction. The TCP traffic adjustment strategy is determined by the SMF data fed back by the NWDAF based on the Session Management Function (SMF) and the UPF data fed back by the UPF. According to the TCP traffic adjustment strategy, the TCP streams generated by each application (APP) when accessing the network are adjusted.

8. The TCP stream adjustment method as described in claim 7, characterized in that, The step of adjusting the TCP flow generated by each application (APP) when accessing the network according to the TCP traffic adjustment strategy includes: Read the destination IP addresses that need to be accelerated and the destination IP addresses that need to be rate-limited from the TCP flow adjustment strategy; Based on the destination IP address that needs to be accelerated, the TCP stream generated when the APP corresponding to the destination IP address accesses the network is accelerated; Based on the destination IP address that needs to be rate-limited, the TCP stream generated when the APP corresponding to the destination IP address accesses the network is rate-limited.

9. The TCP stream adjustment method as described in claim 8, characterized in that, Before reading the destination IP addresses that need acceleration and the destination IP addresses that need rate limiting from the TCP flow adjustment strategy, the method further includes: Determine whether the TCP flow adjustment policy includes the destination IP address that needs to be accelerated and the destination IP address that needs to be rate-limited; If the destination IP address to be accelerated and the destination IP address to be rate-limited are carried, then the steps of accelerating the TCP stream generated when the APP corresponding to the destination IP address to be accelerated accesses the network according to the destination IP address to be accelerated, and rate-limiting the TCP stream generated when the APP corresponding to the destination IP address to be rate-limited accesses the network according to the destination IP address to be rate-limited. If only the destination IP address that needs to be accelerated is carried, then only the step of accelerating the TCP stream generated when the APP corresponding to the destination IP address that needs to be accelerated accesses the network is executed; If only the destination IP address that needs to be rate-limited is carried, then only the step of rate-limiting the TCP stream generated when the APP corresponding to the destination IP address accesses the network is executed.

10. A TCP stream adjustment device, characterized in that, include: The log subscription module is used to send log subscription instructions to the session management function (SMF) and the user plane function (UPF), respectively. The data receiving module is used to receive SMF data fed back by the SMF according to the log subscription instruction, and UDF data fed back by the UPF according to the log subscription instruction; The data analysis module is used to analyze the SMF data and the UDF data to predict TCP flow adjustment strategies. The strategy push module is used to push the TCP flow adjustment strategy to the TCP acceleration device that is pre-connected between the UPF and the external gateway, so that the TCP acceleration device can adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

11. A TCP stream adjustment device, characterized in that, include: The policy subscription module is used to send TCP flow adjustment policy subscription instructions to the Network Data Analysis Function (NWDAF). The policy receiving module is used to receive the TCP traffic adjustment policy fed back by the NWDAF according to the TCP traffic adjustment policy subscription instruction. The TCP traffic adjustment policy is determined by the NWDAF based on the SMF data fed back by the Session Management Function (SMF) and the UPF data fed back by the User Plane Function (UPF). The TCP flow adjustment module is used to adjust the TCP flow generated by each application (APP) when accessing the network according to the TCP flow adjustment strategy.

12. A network element supporting network data analysis functions, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the TCP stream adjustment method as described in any one of claims 1 to 6.

13. A TCP acceleration device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the TCP stream adjustment method as described in any one of claims 7 to 9.

14. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the TCP stream adjustment method according to any one of claims 1 to 6, or the TCP stream adjustment method according to any one of claims 7 to 9.

15. A TCP stream adjustment system, characterized in that, include: The TCP acceleration device as described in claim 13; as well as, The network data analysis function NWDAF, user plane function UPF, and external gateway as described in claim 12 are communicatively connected to the TCP acceleration device; and, The session management function (SMF) is connected to the NWDAF; wherein, The NWDAF is also communicatively connected to the UPF; The NWDAF is used to perform the TCP stream adjustment method as described in any one of claims 1 to 6; The TCP acceleration device is used to perform the TCP stream adjustment method as described in any one of claims 7 to 9.

Images