Bandwidth allocation method and device of PON home gateway, medium and equipment

Abstract

The embodiment of the invention discloses a bandwidth allocation method and device for a PON home gateway, a medium and equipment, and relates to the technical field of bandwidth allocation, equipment accessing the PON home gateway is firstly detected to obtain equipment information, the method is different from a mode of allocation according to equipment types in the prior art, and the bandwidth allocation efficiency is improved. Bandwidth allocation is carried out according to the current demand of the equipment, the actual use condition is better matched, the bandwidth utilization rate is improved, then prediction is carried out according to the equipment type and the equipment identity by using the traffic prediction model, historical traffic use data of the corresponding equipment is called, future traffic use data of the target equipment is predicted, and the traffic use efficiency is improved. And finally, bandwidth pre-allocation is performed on the target equipment according to a prediction result, and bandwidth allocation is adjusted in advance in a pre-allocation manner, so that network congestion is effectively avoided, delay fluctuation is reduced, and the bandwidth allocation effect of the PON home gateway is improved.

Description

Technical Field

[0001] The present application relates to the technical field of bandwidth allocation, and in particular to a bandwidth allocation method, apparatus, medium and equipment for a PON home gateway. Background Art

[0002] A PON home gateway (Passive Optical Network Home Gateway) is a user-side access device based on passive optical network (PON) technology. It serves as a core terminal device in fiber-to-the-room (FTTR) deployments. It connects the operator's fiber network to the home network, integrating multiple functions such as routing, switching, and wireless access. For devices connected to the PON home gateway, bandwidth allocation is essential to ensure optimal operation and bandwidth utilization.

[0003] The fixed allocation method used in the existing technology directly allocates a fixed quota of bandwidth according to the type of access device. Although it has a good allocation effect when there are few access devices and the usage requirements are simple, as the types of devices that can be connected to the PON home gateway increase and the usage requirements of the devices become more and more diverse, the fixed allocation method cannot guarantee the utilization of bandwidth. It is often passively reallocated when network congestion occurs, and the bandwidth is adjusted immediately after reallocation, which will cause large delay fluctuations and affect the user experience. Summary of the Invention

[0004] The main purpose of this application is to provide a bandwidth allocation method, device, medium and equipment for a PON home gateway, aiming to solve the problem of poor bandwidth allocation effect of the PON home gateway in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows: In a first aspect, an embodiment of the present application provides a bandwidth allocation method for a PON home gateway, comprising the following steps: Detect the target device connected to the PON home gateway and obtain device information; the device information includes device identity, device type and current device requirements; Allocate current bandwidth to target devices based on their current needs; The device type and device identity are used as input data and fed into a traffic prediction model to perform predictions, thereby obtaining predicted traffic usage data for the target device. The traffic prediction model is used to retrieve the device's historical traffic usage data based on the device type and device identity, and to predict the device's future traffic usage data based on the historical traffic usage data. Pre-allocate bandwidth to target devices based on predicted traffic usage data.

[0006] In one possible implementation of the first aspect, before the device type and device identity are input into a traffic prediction model for prediction and the predicted traffic usage data of the target device is obtained, the method further includes: Obtain the type and identity of historical access devices; Retrieve historical traffic usage data of historical access devices based on their type and identity; The traffic prediction model is obtained by training with the long short-term memory network as the neural network architecture, the type and identity of the historical access device as the input label, and the historical traffic usage data of the historical access device as the sample data.

[0007] In one possible implementation of the first aspect, before obtaining the traffic prediction model, the method further includes: using a long short-term memory network as a neural network architecture, using the type and identity of historical access devices as input labels, and using historical traffic usage data of historical access devices as sample data for training. An attention layer is set in the long short-term memory network; wherein the attention layer includes a time attention layer and a feature attention layer, the time attention layer is used to extract the time characteristics of the historical traffic usage data of the historical access device, and the feature attention layer is used to extract the traffic characteristics of the historical traffic usage data of the historical access device.

[0008] In a possible implementation of the first aspect, after retrieving historical traffic usage data of the historical access device according to the type and identity of the historical access device, the method further includes: Based on time characteristics and traffic characteristics, the historical traffic usage data of historical access devices is supplemented to obtain the target historical traffic usage data; The traffic prediction model is obtained by using the long short-term memory network as the neural network architecture, the type and identity of historical access devices as input labels, and the historical traffic usage data of historical access devices as sample data for training, including: The traffic prediction model is obtained by training with the long short-term memory network as the neural network architecture, the type and identity of the historical access device as the input label, and the target historical traffic usage data as the sample data.

[0009] In a possible implementation of the first aspect, supplementing historical traffic usage data of historical access devices based on time characteristics and traffic characteristics to obtain target historical traffic usage data includes: Based on time characteristics and traffic characteristics, we conduct missing query on the historical traffic usage data of historical access devices to obtain the time series position of missing values; According to the data at the position of the natural day time series corresponding to the time series position of the missing value, the data at the time series position of the missing value is supplemented to obtain the target historical traffic usage data.

[0010] In a possible implementation of the first aspect, the data at the missing value time series position is supplemented based on the data at the natural day time series position corresponding to the missing value time series position to obtain the target historical traffic usage data, including: According to the data at the position of the natural day time series corresponding to the time series position of the missing value, the frame average flow data is obtained by summing and averaging according to the time series; Randomly select the frame average traffic data as the data of the time series position of some missing values to randomly fill in the missing values and obtain the first historical traffic usage data; Interpolation and completion are performed based on the first historical traffic usage data to obtain target historical traffic usage data.

[0011] In a possible implementation of the first aspect, before pre-allocating bandwidth to the target device based on the predicted traffic usage data, the method further includes: Determine the pre-allocated time period based on the current needs of the equipment; Pre-allocate bandwidth to target devices based on predicted traffic usage data, including: According to the predicted traffic usage data, the current bandwidth allocation result is gradually changed to the bandwidth pre-allocation result within the pre-allocation time period to pre-allocate bandwidth to the target device.

[0012] In a second aspect, an embodiment of the present application provides a bandwidth allocation device for a PON home gateway, including: A detection module is used to detect target devices connected to the PON home gateway and obtain device information; wherein the device information includes device identity, device type and current device requirements; A first allocation module is used to allocate current bandwidth to the target device according to the current demand of the device; A prediction module, configured to input the device type and device identity as input data into a traffic prediction model to perform prediction and obtain predicted traffic usage data for the target device; wherein the traffic prediction model is configured to retrieve historical traffic usage data of the device based on the device type and device identity, and predict future traffic usage data for the device based on the historical traffic usage data; The second allocation module is used to pre-allocate bandwidth to the target device based on the predicted traffic usage data.

[0013] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, the bandwidth allocation method for a PON home gateway provided in any one of the first aspects above is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein: Memory is used to store computer programs; The processor is used to load and execute a computer program so as to enable the electronic device to execute the bandwidth allocation method for a PON home gateway provided in any one of the first aspects above.

[0015] Compared with the prior art, the present invention has the following advantages: The embodiments of the present application propose a bandwidth allocation method, apparatus, medium, and device for a PON home gateway. The method includes: detecting a target device connected to the PON home gateway and obtaining device information; wherein the device information includes the device identity, device type, and current device demand; allocating current bandwidth to the target device based on the current device demand; using the device type and device identity as input data, inputting them into a traffic prediction model for prediction, and obtaining predicted traffic usage data for the target device; wherein the traffic prediction model is used to retrieve historical traffic usage data of the device based on the device type and device identity, and predict future traffic usage data of the device based on the historical traffic usage data; and pre-allocating bandwidth to the target device based on the predicted traffic usage data. This application first detects the devices connected to the PON home gateway to obtain device information. Unlike the existing method of allocating bandwidth based on device type, this application allocates bandwidth based on the current needs of the device, which better matches actual usage and improves bandwidth utilization. It then uses a traffic prediction model to make predictions based on device type and device identity, retrieves historical traffic usage data of the corresponding device, and predicts future traffic usage data of the target device. Finally, it pre-allocates bandwidth to the target device based on the prediction results. By pre-allocating bandwidth, it adjusts bandwidth allocation in advance, effectively avoids network congestion, reduces delay fluctuations, and improves the bandwidth allocation effect of the PON home gateway. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of the present application; Figure 2 A flow chart of a bandwidth allocation method for a PON home gateway provided in an embodiment of the present application; Figure 3 A schematic diagram of a neural network architecture in a bandwidth allocation method for a PON home gateway provided in an embodiment of the present application; Figure 4 A schematic diagram of a module of a bandwidth allocation device for a PON home gateway provided in an embodiment of the present application; Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] Refer to the attached Figure 1 , attached Figure 1 This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and optionally the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or a stable non-volatile memory (NVM), such as at least one disk storage. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0019] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation to the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0020] As attached Figure 1 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and a bandwidth allocation device of a PON home gateway.

[0021] In the attached Figure 1 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device, and the electronic device calls the bandwidth allocation device of the PON home gateway stored in the memory 105 through the processor 101, and executes the bandwidth allocation method of the PON home gateway provided in the embodiment of the present application.

[0022] Refer to the attached Figure 2 Based on the hardware device of the aforementioned embodiment, an embodiment of the present application provides a bandwidth allocation method for a PON home gateway, comprising the following steps: S10: Detect the target device connected to the PON home gateway and obtain device information; wherein the device information includes device identity, device type and current requirements of the device.

[0023] In specific implementations, the target devices are all devices currently connected to the PON home gateway, including mobile phones, computers, and internet-connected TVs. Automatic device detection is achieved through the DHCP dynamic host configuration protocol or the ARP address resolution protocol. Device information is obtained through detection to determine the device's identity, type, and current needs. The device identity is a unique identifier used to represent the target device in the PON home gateway, equivalent to a device ID card. The device's current needs can also be understood as the function currently being performed by the device, such as video playback, software updates, game execution, online conferencing, etc.

[0024] S20: Allocate current bandwidth to the target device according to the current demand of the device.

[0025] In the specific implementation process, since the current level of intelligence of equipment is becoming higher and higher, different types of equipment can have multiple functions. Therefore, this application adopts a bandwidth allocation method based on current needs that is more in line with the actual situation, and allocates different bandwidths according to the current different needs of different devices.

[0026] S30: The device type and device identity are used as input data and input into a traffic prediction model for prediction to obtain predicted traffic usage data of the target device; wherein the traffic prediction model is used to retrieve the historical traffic usage data of the device according to the device type and device identity, and predict the future traffic usage data of the device based on the historical traffic usage data.

[0027] In the specific implementation process, under the current allocation, the effect of bandwidth allocation is optimized, and subsequent usage is predicted. The bandwidth allocation demand actually comes from the traffic demand during device use. Greater traffic demand means that more bandwidth needs to be allocated. This application makes predictions by training a neural network model to ensure the efficiency and effectiveness of the prediction. By learning the historical traffic usage data of the device, it predicts what kind of traffic demand the device is more likely to have at a certain time in the future. Specifically: the device type and device identity are used as input data, and are input into the traffic prediction model for prediction. Before obtaining the predicted traffic usage data of the target device, the method also includes: Obtain the type and identity of historical access devices; Retrieve historical traffic usage data of historical access devices based on their type and identity; The traffic prediction model is obtained by training with the long short-term memory network as the neural network architecture, the type and identity of the historical access device as the input label, and the historical traffic usage data of the historical access device as the sample data.

[0028] During the specific implementation process, by obtaining the type and identity of the historical access device, its historical traffic usage data is retrieved accordingly. Since the traffic usage of the device is characterized by long intervals and long delays, when predicting traffic as an important event, a long short-term memory network is used as the neural network architecture, which is suitable for processing network traffic, a time series data with long-term dependencies. The type and identity of the device are bound to its historical traffic usage data, and the type and identity are used as input labels for training. The trained traffic prediction model can automatically match the corresponding historical data for prediction by identifying the type and identity of the device.

[0029] In one embodiment, before obtaining a traffic prediction model, the method further includes: using a long short-term memory network as a neural network architecture, using the type and identity of historically connected devices as input labels, and using historical traffic usage data of historically connected devices as sample data for training. An attention layer is set in the long short-term memory network; wherein the attention layer includes a time attention layer and a feature attention layer, the time attention layer is used to extract the time characteristics of the historical traffic usage data of the historical access device, and the feature attention layer is used to extract the traffic characteristics of the historical traffic usage data of the historical access device.

[0030] In the specific implementation process, the long short-term memory network is used as the neural network architecture. The overall basic structure includes the input layer, LSTM, fully connected layer and output layer. In order to reduce the prediction error, a two-layer attention mechanism is introduced into the architecture, as shown in the attached figure. Figure 3 The temporal attention layer and feature attention layer shown in the attached Figure 3 In the neural network architecture shown, the LSTM layer uses a bidirectional LSTM. LSTM is used to capture temporal dependencies and the attention mechanism is used to enhance key features and their positions in time series, which can effectively reduce prediction errors.

[0031] In one embodiment, after retrieving historical traffic usage data of historical access devices based on the type and identity of the historical access devices, the method further includes: Based on time characteristics and traffic characteristics, the historical traffic usage data of historical access devices is supplemented to obtain the target historical traffic usage data.

[0032] During implementation, network outages and fluctuations are inevitable in daily use, which can affect the integrity of traffic usage data, leading to missing traffic usage data for certain time points and time periods, and thus affecting the accuracy of predictions. Therefore, it is necessary to supplement historical traffic usage data. This process uses the time and traffic characteristics extracted from the traffic prediction model as an aid to identify missing locations and data.

[0033] Based on the above steps, a traffic prediction model is obtained by using a long short-term memory network as the neural network architecture, the type and identity of historical access devices as input labels, and the historical traffic usage data of historical access devices as sample data for training. The model includes: The traffic prediction model is obtained by training with the long short-term memory network as the neural network architecture, the type and identity of the historical access device as the input label, and the target historical traffic usage data as the sample data.

[0034] In one embodiment, based on the time characteristics and traffic characteristics, the historical traffic usage data of the historical access device is supplemented to obtain the target historical traffic usage data, including: Based on time characteristics and traffic characteristics, we conduct missing query on the historical traffic usage data of historical access devices to obtain the time series position of missing values; According to the data at the position of the natural day time series corresponding to the time series position of the missing value, the data at the time series position of the missing value is supplemented to obtain the target historical traffic usage data.

[0035] In the specific implementation process, by extracting time features and traffic features, we first determine the position of missing values in the historical traffic usage data, and identify the time series position of the missing values based on the time series. Due to the long-term use of the equipment, a certain pattern will be generated with natural days as the boundary. For example, there is a demand for video playback traffic at noon every day, and there is a demand for running game traffic every night. Therefore, after determining the time series position of the missing value, it is supplemented according to the data at the position of the time series corresponding to the natural day. For example, there are five days of data in the historical traffic usage data. It is detected that the data of the time period of 14:00-15:00 on a certain day is missing. Then, the missing data can be supplemented by retrieving the traffic usage data of the other four days from 14:00-15:00. Specifically: based on the data at the position of the time series of the natural day corresponding to the time series position of the missing value, the data of the time series position of the missing value is supplemented to obtain the target historical traffic usage data, including: According to the data at the position of the natural day time series corresponding to the time series position of the missing value, the frame average flow data is obtained by summing and averaging according to the time series; Randomly select the frame average traffic data as the data of the time series position of some missing values to randomly fill in the missing values and obtain the first historical traffic usage data; Interpolation and completion are performed based on the first historical traffic usage data to obtain target historical traffic usage data.

[0036] In the specific implementation process, the data on the corresponding natural day time series are obtained and summed and averaged according to the time series, that is, the data on other days and the data at the same time series position are obtained according to the time series position of the missing value, and the frame average traffic data is obtained after summing and averaging. If the missing data is a single frame, the frame average traffic data can be used as the missing data. If the missing data is multiple frames, a more accurate completion method is provided. First, some frame average traffic data are selected to partially complete the data at the time series position of the missing value. The selection method adopts random selection, such as a simple random sampling algorithm. The randomly selected frame average traffic data corresponds to the frame data at the time series position of the missing value that needs to be completed. In this way, the accuracy of the data at a single time series position can be restored, but the traffic data as a whole still has dynamic changes. Therefore, after partial completion, the partially completed data is completed again by interpolation completion. The above implementation method takes into account the accuracy of traffic data and the trend of traffic data changes, and can improve the quality of the completed historical traffic usage data.

[0037] S40: Pre-allocate bandwidth to the target device based on the predicted traffic usage data.

[0038] During the specific implementation process, the future traffic usage of the target device is predicted. If there is a change in traffic demand at a certain point in the future, bandwidth can be pre-allocated to it. By adjusting bandwidth allocation in advance before this point in time, latency fluctuations can be reduced, effectively avoiding network congestion. Different transition time requirements can be matched to different predicted traffic usage situations. Since traffic changes are from current demand to future demand, the length of the transition time, that is, the length of the pre-allocated time period, can be determined based on the current demand of the device. That is, before pre-allocating bandwidth to the target device based on the predicted traffic usage data, the method also includes: Determine the pre-allocated time period based on the current needs of the equipment.

[0039] Based on the above steps, bandwidth is pre-allocated to the target device according to the predicted traffic usage data, including: According to the predicted traffic usage data, the current bandwidth allocation result is gradually changed to the bandwidth pre-allocation result within the pre-allocation time period to pre-allocate bandwidth to the target device.

[0040] For example, if the current demand traffic changes significantly compared to the predicted traffic, the pre-allocation period can be appropriately extended. During the entire pre-allocation period, the original current bandwidth allocation result is evenly and smoothly transitioned to the bandwidth pre-allocation result in a gradient manner.

[0041] In this embodiment, the device connected to the PON home gateway is first detected to obtain device information. Unlike the existing method of allocating bandwidth based on device type, bandwidth is allocated based on the current needs of the device, which better matches the actual usage and improves bandwidth utilization. Then, a traffic prediction model is used to make predictions based on the device type and device identity, and the historical traffic usage data of the corresponding device is retrieved to predict the future traffic usage data of the target device. Finally, bandwidth is pre-allocated to the target device based on the prediction results. The pre-allocation method adjusts bandwidth allocation in advance, effectively avoids network congestion, reduces delay fluctuations, and improves the bandwidth allocation effect of the PON home gateway.

[0042] Refer to the attached Figure 4 Based on the same inventive concept as the above-mentioned embodiment, the embodiment of the present application further provides a bandwidth allocation device for a PON home gateway, comprising: A detection module is used to detect target devices connected to the PON home gateway and obtain device information; wherein the device information includes device identity, device type and current device requirements; A first allocation module is used to allocate current bandwidth to the target device according to the current demand of the device; A prediction module, configured to input the device type and device identity as input data into a traffic prediction model to perform prediction and obtain predicted traffic usage data for the target device; wherein the traffic prediction model is configured to retrieve historical traffic usage data of the device based on the device type and device identity, and predict future traffic usage data for the device based on the historical traffic usage data; The second allocation module is used to pre-allocate bandwidth to the target device based on the predicted traffic usage data.

[0043] Those skilled in the art should understand that the division of the various modules in the embodiment is merely a division of logical functions, and in actual application, they can be fully or partially integrated into one or more actual carriers, and these modules can all be implemented in the form of software called through a processing unit, or all be implemented in the form of hardware, or in the form of a combination of software and hardware. It should be noted that the modules in the bandwidth allocation device of the PON home gateway in this embodiment correspond one-to-one to the steps in the bandwidth allocation method of the PON home gateway in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the bandwidth allocation method of the PON home gateway in the aforementioned embodiment, and will not be repeated here.

[0044] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, the bandwidth allocation method for the PON home gateway provided in the embodiment of the present application is implemented.

[0045] Based on the same inventive concept as in the above embodiment, an embodiment of the present application further provides an electronic device, including a processor and a memory, wherein: Memory is used to store computer programs; The processor is used to load and execute a computer program so that the electronic device executes the bandwidth allocation method for the PON home gateway provided in the embodiment of the present application.

[0046] In some embodiments, the computer-readable storage medium may be a memory device such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface mount memory, optical disk, or CD-ROM; or various devices including any one or any combination of the above memories. The computer may be various computing devices including smart terminals and servers.

[0047] In some embodiments, executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0048] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).

[0049] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0050] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0051] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0052] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0053] In summary, the embodiments of the present application provide a bandwidth allocation method, apparatus, medium, and device for a PON home gateway, the method comprising: detecting a target device connected to the PON home gateway and obtaining device information; wherein the device information includes device identity, device type, and current device demand; allocating current bandwidth to the target device according to the current device demand; using the device type and device identity as input data, inputting the data into a traffic prediction model for prediction, and obtaining predicted traffic usage data for the target device; wherein the traffic prediction model is used to retrieve historical traffic usage data of the device according to the device type and device identity, and predict future traffic usage data of the device based on the historical traffic usage data; and pre-allocating bandwidth to the target device based on the predicted traffic usage data. This application first detects the devices connected to the PON home gateway to obtain device information. Unlike the existing method of allocating bandwidth based on device type, this application allocates bandwidth based on the current needs of the device, which better matches actual usage and improves bandwidth utilization. It then uses a traffic prediction model to make predictions based on device type and device identity, retrieves historical traffic usage data of the corresponding device, and predicts future traffic usage data of the target device. Finally, it pre-allocates bandwidth to the target device based on the prediction results. By pre-allocating bandwidth, it adjusts bandwidth allocation in advance, effectively avoids network congestion, reduces delay fluctuations, and improves the bandwidth allocation effect of the PON home gateway.

[0054] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A bandwidth allocation method for a PON home gateway, characterized in that: The following steps are involved: Detecting target devices connected to the PON home gateway and obtaining device information; wherein the device information includes device identity, device type, and current device requirements; Allocating current bandwidth to the target device according to current demand of the device; The device type and the device identity are input into a traffic prediction model for prediction, thereby obtaining predicted traffic usage data of the target device; wherein the traffic prediction model is used to retrieve historical traffic usage data of the device based on the device type and the device identity, and predict future traffic usage data of the device based on the historical traffic usage data; Bandwidth is pre-allocated to the target device based on the predicted traffic usage data.

2. The bandwidth allocation method for a PON home gateway according to claim 1, characterized in that: Before inputting the device type and the device identity as input data into a traffic prediction model for prediction and obtaining the predicted traffic usage data of the target device, the method further includes: Obtain the type and identity of historical access devices; Retrieving historical traffic usage data of the historical access device according to the type and identity of the historical access device; The traffic prediction model is obtained by training using a long short-term memory network as a neural network architecture, the type and identity of the historical access device as input labels, and the historical traffic usage data of the historical access device as sample data.

3. The bandwidth allocation method for a PON home gateway according to claim 2, wherein: Before obtaining the traffic prediction model by performing training using a long short-term memory network as a neural network architecture, using the type and identity of the historical access device as input labels, and using the historical traffic usage data of the historical access device as sample data, the method further includes: An attention layer is set in the long short-term memory network; wherein, the attention layer includes a time attention layer and a feature attention layer, the time attention layer is used to extract the time characteristics of the historical traffic usage data of the historical access device, and the feature attention layer is used to extract the traffic characteristics of the historical traffic usage data of the historical access device.

4. The bandwidth allocation method for a PON home gateway according to claim 3, characterized in that: After retrieving historical traffic usage data of the historical access device according to the type and identity of the historical access device, the method further includes: Based on the time feature and the traffic feature, the historical traffic usage data of the historical access device is supplemented to obtain target historical traffic usage data; The traffic prediction model is obtained by using a long short-term memory network as a neural network architecture, the type and identity of the historical access device as input labels, and the historical traffic usage data of the historical access device as sample data for training, including: The traffic prediction model is obtained by training using a long short-term memory network as a neural network architecture, the type and identity of the historical access device as input labels, and the target historical traffic usage data as sample data.

5. The bandwidth allocation method for a PON home gateway according to claim 4, characterized in that: The method of supplementing the historical traffic usage data of the historical access device based on the time feature and the traffic feature to obtain target historical traffic usage data includes: Based on the time characteristics and the traffic characteristics, performing a missing value query on the historical traffic usage data of the historical access device to obtain a time series position of the missing value; According to the data at the position of the natural day time series corresponding to the time series position of the missing value, the data at the time series position of the missing value is supplemented to obtain the target historical traffic usage data.

6. The bandwidth allocation method for a PON home gateway according to claim 5, characterized in that: The method of completing the data at the position of the missing value time series according to the data at the position of the natural day time series corresponding to the time series position of the missing value to obtain the target historical traffic usage data includes: According to the data at the position of the natural day time series corresponding to the time series position of the missing value, summing and averaging are performed in time series to obtain the frame average flow data; Randomly selecting the frame average traffic data as data at some of the missing value time series positions to randomly complete the data to obtain first historical traffic usage data; Interpolation and completion are performed based on the first historical traffic usage data to obtain target historical traffic usage data.

7. The bandwidth allocation method for a PON home gateway according to claim 1, wherein: Before pre-allocating bandwidth to the target device based on the predicted traffic usage data, the method further includes: Determining a pre-allocated time period based on current demand of the equipment; Pre-allocating bandwidth to the target device according to the predicted traffic usage data includes: According to the predicted traffic usage data, the result of the current bandwidth allocation is gradually changed to a result of bandwidth pre-allocation within the pre-allocation time period, so as to perform the bandwidth pre-allocation on the target device.

8. A bandwidth allocation device for a PON home gateway, characterized in that: include: A detection module is used to detect a target device connected to the PON home gateway and obtain device information; wherein the device information includes device identity, device type and current device requirements; A first allocation module, configured to allocate current bandwidth to the target device according to current demand of the device; a prediction module, configured to input the device type and the device identity as input data into a traffic prediction model to perform prediction and obtain predicted traffic usage data of the target device; wherein the traffic prediction model is configured to retrieve historical traffic usage data of the device based on the device type and the device identity, and predict future traffic usage data of the device based on the historical traffic usage data; The second allocation module is configured to pre-allocate bandwidth to the target device according to the predicted traffic usage data.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is loaded and executed by a processor, the bandwidth allocation method for a PON home gateway according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: comprising a processor and a memory, wherein: The memory is used to store computer programs; The processor is configured to load and execute the computer program so as to enable the electronic device to execute the bandwidth allocation method for a PON home gateway according to any one of claims 1 to 7.

Images