Bandwidth allocation method and apparatus, electronic device, and computer-readable storage medium

Abstract

The application provides a bandwidth allocation method and device, electronic equipment and a computer readable storage medium. The method predicts the rate prediction value and the guaranteed bandwidth prediction value of each slave device in the FTTR at at least one future time point through a network device, so that the master device can obtain a bandwidth scheduling strategy for allocating guaranteed bandwidth and non-guaranteed bandwidth to each slave device at at least one future time point. Since the rate prediction value of each slave device at each future time point is considered when generating the bandwidth scheduling strategy, when allocating non-guaranteed bandwidth, not only the congestion degree of the future target time point is considered, but also the congestion trend after the future target time point is considered, so that the transmission pressure caused by subsequent burst traffic can be relieved in advance, and the service guarantee capability is improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to bandwidth allocation methods, apparatus, electronic devices and computer-readable storage media. Background Technology

[0002] With the deployment of gigabit-level network strategies, Fiber to the Room (FTTR) networking is widely used in various scenarios such as homes, government and enterprise offices, commercial stores, and hotels. FTTR networking consists of one master device and at least one slave device. In FTTR, the master and slave devices are connected by a gigabit-capable passive optical network (GPON).

[0003] In FTTR, on the one hand, the master device reserves a fixed amount of bandwidth for the slave device. Since this reserved bandwidth is a fixed value, it differs significantly from the actual network traffic, leading to bandwidth waste or insufficient bandwidth causing inadequate service guarantees. On the other hand, the master device allocates non-reserved bandwidth based on the pending transmission traffic when the slave device sends its request. Because this allocation only considers the current congestion level, it cannot alleviate the transmission pressure caused by sudden surges in traffic later, resulting in inadequate service guarantees. Summary of the Invention

[0004] In view of this, this application provides a bandwidth allocation method, apparatus, electronic device, and computer-readable storage medium to improve service assurance capabilities.

[0005] This application provides a bandwidth allocation method, which is applied to network devices in an FTTR network or to network devices outside the FTTR network that are associated with the FTTR network. The method includes:

[0006] For each slave device in an FTTR network, predict the rate of data flow sent by the slave device to the master device in the FTTR network at at least one future time point, and predict the guaranteed bandwidth of the slave device at at least one future time point.

[0007] The predicted rate and guaranteed bandwidth of the slave device at at least one future time point are sent to the master device. The master device then generates a bandwidth scheduling policy for each slave device at that future time point based on these predictions. According to the bandwidth scheduling policy, the master device allocates guaranteed bandwidth for each slave device within the corresponding scheduling period for each future time point and notifies each slave device of the guaranteed bandwidth allocation result, enabling the slave device to send a data stream to the master device based on the guaranteed bandwidth allocation result. Furthermore, upon receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time point, the master device allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) for that slave device within the corresponding scheduling period of the future target time point according to the bandwidth scheduling policy and notifies the slave device of the non-guaranteed bandwidth allocation result, enabling the slave device to... The system can either send a data stream to the master device based on the non-guaranteed bandwidth allocation result, or generate a bandwidth scheduling policy for at least one future time point based on the rate prediction value and guaranteed bandwidth prediction value of each slave device at at least one future time point, distribute the bandwidth scheduling policy to the master device, and allocate guaranteed bandwidth for each slave device for each scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notify each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, upon receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, allocate non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device for the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0008] This application embodiment also provides a bandwidth allocation method, which is a master device in an FTTR network, and the method includes:

[0009] The network device receives the predicted data flow rate of each slave device in the FTTR network to the master device at at least one future time point, and the predicted guaranteed bandwidth of the slave device at at least one future time point; the predicted data flow rate and guaranteed bandwidth of the slave device at at least one future time point are predicted by the network device; and generates a bandwidth scheduling policy for the at least one future time point based on the predicted data flow rate and guaranteed bandwidth of each slave device at at least one future time point; or, the network device receives the bandwidth scheduling policy for the at least one future time point; wherein the bandwidth scheduling policy for the at least one future time point is generated by the network device after predicting the predicted data flow rate of each slave device to the master device in the FTTR network at at least one future time point, and predicting the predicted guaranteed bandwidth of the slave device at at least one future time point, based on the predicted data flow rate and guaranteed bandwidth of each slave device at at least one future time point.

[0010] According to the bandwidth scheduling policy, the system allocates guaranteed bandwidth to each slave device for each future time point within the corresponding scheduling period, and notifies each slave device of the corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, the system allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device for the corresponding scheduling period at the future target time point according to the bandwidth scheduling policy, and notifies the slave device of the corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0011] This application embodiment also provides a bandwidth allocation device, which is applied to network devices in an FTTR network or to network devices outside the FTTR network that are associated with the FTTR network. The device includes:

[0012] The prediction module is used to predict, for each slave device in the FTTR network, the rate prediction value of the data flow sent by the slave device to the master device in the FTTR network at at least one future time point, and the guaranteed bandwidth prediction value of the slave device at at least one future time point.

[0013] The first strategy management module is used to send the predicted rate value and the guaranteed bandwidth prediction value of the slave device at at least one future time point to the master device. The master device then generates a bandwidth scheduling policy for each slave device at the at least one future time point based on the predicted rate and guaranteed bandwidth values. According to the bandwidth scheduling policy, the master device allocates guaranteed bandwidth for each slave device within the scheduling period corresponding to each future time point and notifies each slave device of the corresponding guaranteed bandwidth allocation result, enabling the slave device to send a data stream to the master device based on the guaranteed bandwidth allocation result. Furthermore, upon receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time point, the master device allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device within the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy and notifies the slave device of the corresponding non-guaranteed bandwidth allocation result. The system enables the slave device to send a data stream to the master device based on the non-guaranteed bandwidth allocation result; or, it generates a bandwidth scheduling policy for at least one future time point based on the rate prediction value and guaranteed bandwidth prediction value of each slave device at at least one future time point, distributes the bandwidth scheduling policy to the master device, and allocates guaranteed bandwidth for each slave device for each scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notifies each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device sends a data stream to the master device according to the guaranteed bandwidth allocation result; and, upon receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, it allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device for the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notifies the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device sends a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0014] This application embodiment also provides a bandwidth allocation device, which should be a master device in an FTTR network, and the device includes:

[0015] The second policy management module is configured to receive, from the network device, the predicted rate of data flow sent by each slave device in the FTTR network to the master device at at least one future time point, and the predicted guaranteed bandwidth of the slave device at at least one future time point; the predicted rate and guaranteed bandwidth of the device at at least one future time point are predicted by the network device; and generate a bandwidth scheduling policy for the at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point; or, receive the bandwidth scheduling policy for the at least one future time point sent by the network device; wherein the bandwidth scheduling policy for the at least one future time point is generated by the network device after predicting the predicted rate of data flow sent by each slave device to the master device in the FTTR network at at least one future time point, and predicting the predicted guaranteed bandwidth of the slave device at at least one future time point, based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point;

[0016] The strategy execution module is used to allocate guaranteed bandwidth to each slave device under the scheduling period corresponding to each future time point according to the bandwidth scheduling strategy, and notify each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device under the future target time point, allocate non-guaranteed bandwidth other than guaranteed bandwidth to the slave device under the scheduling period corresponding to the future target time point according to the bandwidth scheduling strategy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0017] This application also provides an electronic device, including: a processor and a memory for storing computer program instructions, which, when executed by the processor, cause the processor to perform the steps of the method described above.

[0018] This application also provides a machine-readable storage medium storing computer program instructions that, when executed, enable the implementation of the steps described above.

[0019] As can be seen from the above technical solutions, in this embodiment, the network device predicts the predicted rate values ​​sent by each slave device in the FTTR network to the master device in the FTTR network at at least one future time point, and the predicted guaranteed bandwidth values ​​of the slave devices at at least one future time point. This enables the master device to obtain a bandwidth scheduling strategy for allocating guaranteed and non-guaranteed bandwidth to each slave device at at least one future time point. This allows the master device to allocate guaranteed bandwidth to each slave device for each future time point according to the obtained bandwidth scheduling strategy, and, upon receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, allocate non-guaranteed bandwidth (excluding guaranteed bandwidth) to that slave device for the scheduling period corresponding to the future target time point according to the bandwidth scheduling strategy. Since the bandwidth scheduling strategy comprehensively considers the predicted rate values ​​of each slave device at each future time point when generating the strategy, the master device, when allocating non-guaranteed bandwidth according to the obtained strategy, not only considers the congestion level at the future target time point but also takes into account the congestion trend after the future target time point. This can alleviate the transmission pressure caused by subsequent sudden traffic surges in advance, thereby improving service guarantee capabilities.

[0020] Furthermore, since the bandwidth scheduling strategy is dynamically generated based on predictions and is not fixed, this not only makes the guaranteed bandwidth allocated to each slave device change over time, ensuring that the allocation of guaranteed bandwidth matches the actual network traffic and avoiding waste caused by reserving too much guaranteed bandwidth or insufficient guarantee capacity caused by insufficient reserved guaranteed bandwidth, but also makes the allocation of non-guaranteed bandwidth match the actual network traffic distribution, making the latency in FTTR more uniform, thereby improving the quality of network services. Attached Figure Description

[0021] Figure 1 A network architecture diagram of an FTTR network provided for an exemplary embodiment of this application;

[0022] Figure 2 A schematic flowchart of a bandwidth allocation method provided for an exemplary embodiment of this application;

[0023] Figure 3 A framework diagram of a network device deployed outside an FTTR network, provided as another exemplary embodiment of this application;

[0024] Figure 4 A schematic diagram illustrating a cloud server-based prediction process, provided as an exemplary embodiment of this application;

[0025] Figure 5 This is a schematic diagram illustrating the framework of an exemplary embodiment of this application when a network device is deployed within an FTTR network.

[0026] Figure 6 A schematic diagram of the process for generating a bandwidth scheduling strategy provided in an embodiment of this application;

[0027] Figure 7 A flowchart illustrating a bandwidth allocation method provided as another exemplary embodiment of this application;

[0028] Figure 8 This is a schematic diagram of the structure of a bandwidth allocation device provided in an embodiment of this application;

[0029] Figure 9 This is a schematic diagram of the structure of a bandwidth allocation device provided in another embodiment of this application;

[0030] Figure 10 A schematic diagram of the structure of an electronic device provided in another embodiment of this application. Detailed Implementation

[0031] Exemplary embodiments will now be described in detail, examples of which are identified in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings identify the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0032] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0033] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of this application, and to make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the technical solutions in the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0034] To better describe this solution, let's first explain the GPON network in related technologies before proceeding:

[0035] A GPON network consists of an Optical Line Terminal (OLT), an Optical Distribution Network (ODN), and Optical Network Units (ONUs). One port of the OLT connects to multiple ONUs through the ODN.

[0036] In a GPON network, the data transmission direction from the OLT to the ONU is called the downlink direction, and the opposite is called the uplink direction. In the downlink direction, the OLT broadcasts data streams to multiple ONUs. In the uplink direction, the OLT uses a dynamic bandwidth allocation (DBA) algorithm based on time division multiplexing (TDMA) technology to allocate time slots to each ONU for transmitting uplink data streams (allocating time slots can also be called allocating bandwidth). Data streams from each ONU are coupled to the same optical fiber through the ODN without interference, according to their respective allocated time slots, and finally sent to the OLT.

[0037] After introducing the GPON network, the FTTR networking provided in the embodiments of this application will be described as follows:

[0038] See Figure 1 , Figure 1 A network architecture diagram of an FTTR network provided for an exemplary embodiment of this application.

[0039] like Figure 1 As shown, this FTTR network includes one master device and multiple slave devices. One optical port of the master device connects to the central office OLT device, and the other optical port connects to multiple slave devices through an optical splitter. The master and slave devices form a GPON network, where the master device is equivalent to the OLT in the GPON network, and each slave device is equivalent to an ONU in the GPON network.

[0040] If an OLT device connects to multiple master devices, a GPON network is also formed between the OLT device and the multiple master devices. In this case, the multiple master devices are equivalent to ONUs in the GPON network.

[0041] Among them, the slave device has radio frequency capability and can provide Wi-Fi service to terminals such as mobile phones and laptops; the master device can optionally have radio frequency capability and provide Wi-Fi service.

[0042] The method provided in the application embodiments is described in detail below:

[0043] See Figure 2 , Figure 2 This is a schematic flowchart illustrating a bandwidth allocation method provided in an exemplary embodiment of this application. As an example, this method is applied to network devices within an FTTR network or to network devices outside the FTTR network that are associated with it. These network devices can be cloud servers deployed outside the FTTR network or servers deployed within the FTTR network; this embodiment is not specifically limited to any particular type.

[0044] like Figure 2 As shown, the method may include the following steps:

[0045] S201, for each slave device in the FTTR network, predict the predicted rate of the data flow sent by the slave device to the master device in the FTTR network at at least one future time point, and predict the predicted guaranteed bandwidth of the slave device at at least one future time point.

[0046] In this embodiment, at least one future time point can be a future time point within a specified future day (e.g., the day after today, i.e., tomorrow), a future time point within a specified future week, or a future time point within a specified future month. This embodiment does not impose specific limitations. The multiple future times can be selected at equal time intervals or at unequal time intervals. This embodiment does not impose specific limitations.

[0047] For example, predict the data flow rate of device K to the master device in the FTTR network at 1:00, 2:00, 3:00, ..., 24:00 on the next day after the current day, and predict the guaranteed bandwidth of the device at these 24 future time points.

[0048] In this embodiment, the fixed bandwidth refers to the bandwidth (i.e., the reserved time slots) fully reserved by the master device for the slave device or for the slave device to guarantee services. Even if the slave device has no uplink traffic, this bandwidth cannot be used by other slave devices. In this embodiment, the bandwidth other than the fixed bandwidth is the non-guaranteed bandwidth.

[0049] In this embodiment, when the network device is a different server, its connection method with the FTTR network will also be different, and thus the specific implementation of step S201 will also be different. Two implementation methods will be described later using two examples, and will not be elaborated upon here.

[0050] S202, the predicted rate and guaranteed bandwidth of the slave device at at least one future time point are sent to the master device. The master device then generates a bandwidth scheduling policy for each slave device at at least one future time point based on these predictions. According to the bandwidth scheduling policy, the master device allocates guaranteed bandwidth and non-guaranteed bandwidth (excluding guaranteed bandwidth) to each slave device at a future target time point. It also allocates guaranteed bandwidth for each scheduling period corresponding to each future time point according to the bandwidth scheduling policy and notifies each slave device of its corresponding guaranteed bandwidth allocation result, enabling the slave device to send a data stream to the master device based on the guaranteed bandwidth allocation result. Furthermore, upon receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time point, the master device allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device for the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy and notifies the master device of the allocation result. The system can: 1) Know the non-guaranteed bandwidth allocation result for each slave device, so that the slave device can send a data stream to the master device based on the non-guaranteed bandwidth allocation result; 2) Generate a bandwidth scheduling policy for each slave device at at least one future time point based on the rate prediction value and guaranteed bandwidth prediction value for each slave device at at least one future time point, and distribute the bandwidth scheduling policy to the master device, so that the master device can allocate guaranteed bandwidth for each slave device in the scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notify each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device based on the guaranteed bandwidth allocation result; and 3) Upon receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, allocate non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device in the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device based on the non-guaranteed bandwidth allocation result.

[0051] In this embodiment, after the network device predicts the predicted rate and guaranteed bandwidth for each slave device at at least one future time point, there are two specific implementation methods:

[0052] In the first specific implementation, the network device generates a bandwidth scheduling policy for at least one future time point based on the predicted rate and guaranteed bandwidth values ​​of each slave device at at least one future time point. How the network device specifically generates this bandwidth scheduling policy for at least one future time point will be explained later and will not be elaborated here.

[0053] In the second specific implementation, it is only necessary to send the predicted rate and guaranteed bandwidth values ​​of each slave device at at least one future time point to the master device. Then, the master device generates a bandwidth scheduling policy for the at least one future time point based on the predicted rate and guaranteed bandwidth values ​​of each slave device at the at least one future time point, and allocates guaranteed bandwidth for each slave device in the scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notifies each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, the master device allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) for the slave device in the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notifies the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0054] Typically, a scheduling period is 125μs. The scheduling period corresponding to each future time point refers to the multiple scheduling periods between that future time point and the next future time point. The future target time point is denoted as T0. The scheduling period corresponding to the future target time point T0 refers to at least one scheduling period after T0. The specific number of scheduling periods corresponding to the target time point T0 depends on the amount of data to be uploaded in the non-guaranteed bandwidth allocation request sent by the slave device.

[0055] As one embodiment, after obtaining the bandwidth scheduling policy, the master device allocates guaranteed bandwidth to each slave device according to the bandwidth scheduling policy for the scheduling period between each future time point and the next future time point. The master device then sends a guaranteed bandwidth allocation message to the slave device, which carries the guaranteed bandwidth allocation result for the slave device. The guaranteed bandwidth allocation result of the slave device indicates the time slot allocated to the slave device for transmitting guaranteed service data streams. After receiving the guaranteed bandwidth allocation message, when the slave device has guaranteed service data streams that need to be uploaded, it sends the guaranteed service data streams to the master device according to the guaranteed bandwidth allocated to the slave device.

[0056] When the master device receives a non-guaranteed bandwidth allocation request from any slave device at a future target time, it allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device according to the bandwidth scheduling policy for the scheduling period corresponding to the future target time. The master device then sends a non-guaranteed bandwidth allocation message to the slave device, carrying the non-guaranteed bandwidth allocation result. This result indicates the time slot allocated to the slave device for non-guaranteed service data streams. After receiving the non-guaranteed bandwidth allocation message, the slave device sends guaranteed service data streams to the master device based on the allocated non-guaranteed bandwidth.

[0057] It should be noted that the specific implementation of the master device notifying the slave device of its corresponding guaranteed bandwidth allocation result and non-guaranteed bandwidth allocation result is not limited to the methods of sending guaranteed bandwidth allocation messages and sending non-guaranteed bandwidth allocation messages described in the above embodiments. Other methods are also possible, and the embodiments of this application do not impose specific limitations.

[0058] Here, the specific implementation method of the master device allocating guaranteed bandwidth and non-guaranteed bandwidth to each slave device according to the bandwidth scheduling strategy will be described in detail when describing the method of the embodiment of this application from the perspective of the master device of FTTR, and will not be repeated here.

[0059] This concludes the process. Figure 2 The process is shown below.

[0060] pass Figure 2 The process achieves the following effect: by predicting the data flow rate forecast of each slave device in the FTTR network to the master device in the FTTR network at at least one future time point, and the guaranteed bandwidth forecast of each slave device at at least one future time point, the master device can obtain a bandwidth scheduling strategy for at least one future time point to allocate guaranteed and non-guaranteed bandwidth to each slave device. This allows the master device to allocate guaranteed bandwidth for each future time point within the corresponding scheduling period according to the obtained bandwidth scheduling strategy, and, upon receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time point, allocate non-guaranteed bandwidth (excluding guaranteed bandwidth) to that slave device within the corresponding scheduling period of the future target time point according to the bandwidth scheduling strategy. Because the bandwidth scheduling strategy comprehensively considers the rate forecast of each slave device at each future time point, when the master device allocates non-guaranteed bandwidth according to the obtained bandwidth scheduling strategy, it not only considers the congestion level at the future target time point but also the congestion trend after the future target time point, thereby alleviating the transmission pressure caused by subsequent sudden traffic surges in advance and improving service reliability.

[0061] Furthermore, since the bandwidth scheduling strategy is dynamically generated based on predictions and is not fixed, this not only makes the guaranteed bandwidth allocated to each slave device change over time, ensuring that the allocation of guaranteed bandwidth matches the actual network traffic and avoiding waste caused by reserving too much guaranteed bandwidth or insufficient guarantee capacity caused by insufficient reserved guaranteed bandwidth, but also makes the allocation of non-guaranteed bandwidth match the actual network traffic distribution, making the latency in FTTR more uniform, thereby improving the quality of network services.

[0062] The following two examples illustrate the predicted data flow rate and guaranteed bandwidth of the slave device at at least one future point in time.

[0063] Example 1:

[0064] In this embodiment 1, the network device is a cloud server, as shown in the following example. Figure 3 As shown, the cloud server communicates with the main device in the FTTR network through the local OLT.

[0065] In this embodiment 1, the specific implementation of predicting the rate prediction value and guaranteed bandwidth prediction value of the slave device at at least one future time point is as follows: A trained rate prediction model and a trained guaranteed bandwidth prediction model are obtained. For each preset future time point, the future time point and the device number are input into the trained rate prediction model and the trained guaranteed bandwidth prediction model to obtain the rate prediction value and guaranteed bandwidth prediction value of the slave device at that future time point. Each slave device reuses the above method to obtain the rate prediction value and guaranteed bandwidth prediction value of each slave device at at least one future time point.

[0066] In this embodiment 1, the rate prediction model is trained based on the rate values ​​of each slave device at each historical time point. The rate value of any slave device at any historical time point is determined based on the traffic sent by the slave device to the master device between that historical time point and the previous historical time point.

[0067] The guaranteed bandwidth prediction model is trained based on the guaranteed bandwidth usage of each slave device at each historical time point. The guaranteed bandwidth usage of any slave device at any historical time point is determined based on the traffic sent by the slave device through the guaranteed bandwidth allocated to the slave device between the historical time point and the previous historical time point.

[0068] As one embodiment, the aforementioned historical time points are selected at equal time intervals. These time intervals can be set according to specific application scenarios, and this embodiment does not specifically limit them. For example, selecting the 7 days prior to the current day, and then selecting a historical time point every 5 minutes for each of these 7 days, i.e., (0:00, 0:05, 0:10, 0:15, ..., 24:00). Of course, there are other ways to select these historical time points, and this application does not specifically limit them.

[0069] The following examples illustrate how the rate prediction model and the guaranteed bandwidth prediction model are trained.

[0070] After connecting to FTTR on the cloud server, the storage capacity and computing power of the cloud server can be used to train the rate prediction model and the guaranteed bandwidth prediction model. Here, the cloud server is pre-configured with a first initial neural network model and a second initial neural network model.

[0071] For example, firstly, refer to Figure 4 As shown, the data statistics module on the master device selects a time point every 5 minutes when it receives data streams from each slave device. At this time point, it counts the traffic sent from each slave device to the master device between the previous time point and the current time point, as well as the traffic sent from each slave device to the master device through the guaranteed bandwidth. This yields the rate value and guaranteed bandwidth usage at that time point, which are then sent to the data collection module. The data collection module sends the obtained data to the cloud server for storage in the cloud service's data storage module, adding a timestamp during transmission to identify the specific time point. It should be noted that the selected time point becomes a historical time point during subsequent model training.

[0072] Then, since the cloud server and FTTR have no data or very little data stored in their data storage modules for a period of time after they start working, once the data received and stored from the master device accumulates to a certain amount (e.g., after one day or one week of operation), the rate values ​​and guaranteed bandwidth usage of each slave device at various historical time points stored in the data storage module are used to train the first and second initial neural network models until the parameters of the first and second initial neural network models meet the set conditions, thus obtaining the rate prediction model and the guaranteed bandwidth prediction model. After this, the rate prediction model and the guaranteed bandwidth prediction model are iteratively trained using the rate values ​​and guaranteed bandwidth usage of each slave device at various historical time points stored within the current period (e.g., one day, one week, one month) to update the parameters of these two models, thereby using the updated models for prediction.

[0073] The trained rate prediction model, given a slave device ID and a future time point as input, can predict the rate at which the slave device represented by that ID will send data streams to the master device at that future time point (i.e., the rate prediction value). The trained guaranteed bandwidth prediction model, given a slave device ID and a future time point as input, can predict the guaranteed bandwidth requirement of the slave device represented by that ID at that future time point (i.e., the guaranteed bandwidth prediction value).

[0074] It should be noted that the above rate prediction model and guaranteed bandwidth prediction model are trained periodically and iteratively. The parameters of the two models are not fixed after the first training. Instead, they are dynamically adjusted based on the rate values ​​and guaranteed bandwidth usage of each slave device in the most recent historical time points. This effectively ensures the accuracy of the predictions of the two models.

[0075] The above details how to train the rate prediction model and ensure the bandwidth prediction model.

[0076] As an example, the rate prediction model is denoted as S. i,t =F1(i,t), where S i,t Let C represent the predicted rate of device i at a future time point t. Similarly, the guaranteed bandwidth prediction model is denoted as C. i,t =F2(i,t) where, C i,t This represents the predicted guaranteed bandwidth value for device i at a future time point t.

[0077] At this point, the cloud server can input the serial number of each slave device and each preset future time point into the two models mentioned above to obtain the predicted rate and guaranteed bandwidth of each slave device at at least one future time point.

[0078] Example 2:

[0079] In this embodiment 2, the network device is a server whose computing power cannot support the training of neural network models, referring to... Figure 5 As shown, the server is set up within the FTTR network and communicates directly with the master device in the FTTR network.

[0080] In this embodiment 2, for any slave device, the average value and variance of the data flow rate from the slave device to the master device at multiple historical time points corresponding to any future time point are obtained. If the variance of the rate value is less than or equal to a first preset threshold, the average value of the rate value is determined as the predicted rate value of the slave device at that future time point. The average value and variance of the guaranteed bandwidth occupancy of the slave device at multiple historical time points corresponding to any future time point are also obtained. If the variance of the guaranteed bandwidth occupancy is less than or equal to a second preset threshold, the average value of the guaranteed bandwidth occupancy is determined as the predicted guaranteed bandwidth value of the slave device at that future time point.

[0081] For example, if at least one future time point is one of 288 specified future time points from 1 to 24 on a specified future day, and each historical time point is represented by a time point identifier, then for 1 on a specified future day, seven historical time points represented by 1 within the past seven days are determined. The average and variance of the data stream rate from the slave device to the master device at these seven historical time points are calculated. If the obtained variance is less than or equal to a first preset threshold, the obtained average is determined as the predicted rate value at 1 on that specified future day. This process is repeated to obtain the predicted rate values ​​for all 288 specified future time points. The guaranteed bandwidth prediction value can be calculated similarly, and will not be elaborated here.

[0082] Regardless of which method is used in Embodiments 1 and 2 described above, the network device can obtain the predicted rate and guaranteed bandwidth for each slave device at at least one future time point. Afterward, the network device can generate a bandwidth scheduling policy. The specific implementation method for generating the bandwidth scheduling policy is described in detail below.

[0083] The following is in conjunction with the appendix Figure 6 This section provides a detailed explanation of how network devices generate bandwidth scheduling strategies.

[0084] As one embodiment, the bandwidth scheduling strategy includes a weighted allocation strategy and a guaranteed bandwidth allocation strategy. Specifically, the master device allocates guaranteed bandwidth to each slave device at each future time point according to the guaranteed bandwidth allocation strategy. When any slave device sends a bandwidth request at a future target time point, the master device allocates non-guaranteed bandwidth to that slave device according to the weighted allocation strategy.

[0085] Reference Figure 6 As shown, Figure 6 This is a flowchart illustrating the generation of a bandwidth scheduling strategy according to an embodiment of this application.

[0086] like Figure 6 As shown, the method may include the following steps:

[0087] S601, for each future time point t, based on the predicted guaranteed bandwidth value of each slave device at that future time point t and the maximum guaranteed bandwidth value B set for each slave device... max Determine the bandwidth allocation strategy Q(t).

[0088] In this embodiment, Q(t) is expressed by the following formula: Q(t)={V 1,t V 2,t V 3,t ...V i,t};

[0089] Among them, V i,tThis represents the guaranteed bandwidth threshold for device i at a future time point t.

[0090] In this embodiment, the bandwidth threshold V is guaranteed. i,t The maximum guaranteed bandwidth allocated by the master device to slave device i at a future time point t. Optionally, the guaranteed bandwidth allocated by the master device to slave device i at a future time point t.

[0091] As an example, for each slave device, the predicted guaranteed bandwidth value of the slave device at the future time point t and the maximum guaranteed bandwidth value B set for the slave device are... max The smaller value between t and t is determined as the guaranteed bandwidth threshold for the slave device at that future time point t.

[0092] In other words, the guaranteed bandwidth threshold for device i at that future time point t is obtained by the following formula:

[0093] V i,t =min(B max C i,t )

[0094] Among them, V i,t Let B represent the guaranteed bandwidth threshold of device i at the future time point t, and let Ci,t represent the predicted guaranteed bandwidth of device i at the future time point t. max This indicates the maximum guaranteed bandwidth value set for device i.

[0095] S602, for each future time point t, determine the weight allocation strategy P(t) based on the predicted rate and guaranteed bandwidth of each slave device at that future time point t.

[0096] In this embodiment, P(t) is expressed by the following formula:

[0097] P(t)={W 1,t W 2,t W 3,t ...W i,t};

[0098] Among them, W i,t This represents the non-guaranteed bandwidth weight of device i at a future time point t.

[0099] As an example, for each slave device, the difference between the predicted rate and the predicted guaranteed bandwidth of the slave device at the future time point t is determined as the non-guaranteed bandwidth weight of the slave device at the future time point t.

[0100] In other words, the non-guaranteed bandwidth weight of the device at that future time point t is obtained by the following formula:

[0101] W i,t =Si,t -C i,t

[0102] Among them, W it S represents the non-guaranteed bandwidth weight of device i at that future time point t; it This represents the predicted rate of device i at that future time point t.

[0103] This concludes the process. Figure 6 The process is shown below.

[0104] The above details the specific implementation method of the network device generating the bandwidth scheduling strategy for at least one future point in time.

[0105] The above description of the solution provided in the embodiments of this application is from the perspective of network devices. The following description is from the perspective of the master device in FTTR networking.

[0106] See Figure 7 , Figure 7 This is a flowchart illustrating a bandwidth allocation method provided as another exemplary embodiment of this application. As an example, the method is applied to a master device in an FTTR network.

[0107] like Figure 7 As shown, the method may include the following steps:

[0108] S701, receiving from the network device the predicted rate of the data flow sent by each slave device in the FTTR network to the master device at at least one future time point, and the predicted guaranteed bandwidth of the slave device at at least one future time point; the predicted rate and guaranteed bandwidth of the device at at least one future time point are predicted by the network device; and generating a bandwidth scheduling policy for the at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point; or, receiving a bandwidth scheduling policy for the at least one future time point sent by the network device; wherein the bandwidth scheduling policy for the at least one future time point is generated by the network device after predicting the predicted rate of the data flow sent by each slave device to the master device in the FTTR network at at least one future time point, and predicting the predicted guaranteed bandwidth of the slave device at at least one future time point, based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point.

[0109] In this embodiment, if the main device receives a bandwidth scheduling policy for at least one future time point from the network device, then the following step S702 is executed.

[0110] If the data received by this master device from the network device is the predicted rate and guaranteed bandwidth for each slave device in the FTTR network at at least one future time point, then according to the above... Figure 6 The process shown generates a bandwidth scheduling policy, and then the following step S702 is executed.

[0111] It should be noted that the bandwidth scheduling strategy generated by this main device differs from the specific implementation of the bandwidth scheduling strategy generated by the aforementioned network devices (i.e., Figure 6 The process shown is exactly the same, so it will not be repeated here.

[0112] In other words, whether the host device receives the bandwidth allocation strategy Q(t) from the network device or generates it itself, it guarantees the bandwidth allocation strategy Q(t) = {V 1,t V 2,t V 3,t ...V i,t} and weight allocation strategy P(t)={W 1,t W 2,t W 3,t ...W i,t}

[0113] S702, according to the bandwidth scheduling policy, the system allocates guaranteed bandwidth for each slave device under the scheduling period corresponding to each future time point, and notifies each slave device of the corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device under the future target time point, the system allocates non-guaranteed bandwidth other than guaranteed bandwidth for the slave device under the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notifies the slave device of the corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0114] As an example, step S702 is specifically implemented as follows: For each slave device, based on the obtained guaranteed bandwidth threshold for the slave device at each future time point, guaranteed bandwidth is allocated to the slave device during the scheduling period between the future time point and the next future time point. When a non-guaranteed bandwidth allocation request is received from any slave device at a future target time point T0, the future time point closest to T0 before T0 is obtained from the predicted future time points. Using the obtained non-guaranteed bandwidth weight of the slave device at the closest future time point, non-guaranteed bandwidth is allocated to the slave device during the scheduling period corresponding to T0, wherein the non-guaranteed bandwidth weight of the closest future time point is positively correlated with the amount of non-guaranteed bandwidth allocated to the slave device at T0 and the priority of the allocated non-guaranteed bandwidth.

[0115] For example, if each future time point is one of 24 future time points from 1 to 24 on the next day of the current day.

[0116] Then, for each scheduling cycle (e.g., 125μs) between 1 AM and 2 AM on the next day, the master device will follow the formula Q(1)={V 1,1 V 2,1 V 3,1 ...V i,1} Allocate guaranteed bandwidth to slave device 1-i (or, allocate the 125μs time slots occupied by each slave device 1-i), and send the guaranteed bandwidth allocation results of each slave device 1-i in each scheduling cycle to slave device 1-i respectively, so that when a guaranteed service data flow is generated in each scheduling cycle, slave device 1-i can transmit the guaranteed service data flow according to its allocated guaranteed bandwidth. And so on, in each scheduling cycle between 2:00 and 3:00 on the next day of the current day, according to Q(2)={V 1,2 V 2,2 V 3,2 ...V i,2 Allocate guaranteed bandwidth to device 1-i.

[0117] If T0 is 18:55, and slave devices 3, 5, and i simultaneously send non-guaranteed bandwidth allocation requests to the master device at 18:55, then the master device will use P(18)={W 1,18 W 2,18 W 3,18 ...W i,18 W in} 3,18 W 5,18 W i,18 As a weight, non-guaranteed bandwidth is allocated to device 3, slave device 5, and slave device i under the corresponding scheduling period of 18:55.

[0118] This concludes the process. Figure 7 The process is shown below.

[0119] Another embodiment of this application provides a bandwidth allocation method. In this embodiment, the network device is a cloud server, located outside the FTTR network. The cloud server communicates with the master device in the FTTR network through the central office OLT (see details of the connection method). Figure 3 ).

[0120] In this embodiment, after obtaining the trained rate prediction model and the trained guaranteed bandwidth prediction model, the cloud server distributes the trained rate prediction model and the trained guaranteed bandwidth prediction model to the master device. It should be noted that the rate prediction model and the guaranteed bandwidth prediction model are trained iteratively periodically. After each update of the rate prediction model and the guaranteed bandwidth prediction model, the updated rate prediction model and the updated guaranteed bandwidth prediction model are distributed to the master device, the old rate prediction model and the old guaranteed bandwidth prediction model are deleted, and the updated rate prediction model and the updated guaranteed bandwidth prediction model are used for prediction.

[0121] Here, the specific processes for training the cloud server rate prediction model and the guaranteed bandwidth prediction model are the same as those for training the rate prediction model and the guaranteed bandwidth prediction model in Example 1, and will not be repeated here.

[0122] The main device performs the following steps:

[0123] 1. Based on the trained rate prediction model, predict the rate of the slave device at at least one future time point, and based on the trained guaranteed bandwidth prediction model, predict the guaranteed bandwidth of the slave device at at least one future time point.

[0124] Specifically, the master device inputs the serial number of each slave device and the set future time point into the two models mentioned above to obtain the rate prediction value and guaranteed bandwidth prediction value of each slave device at at least one future time point.

[0125] 2. Generate a bandwidth scheduling strategy for at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point.

[0126] The specific implementation method of step 2 and Figure 6 The process shown is exactly the same, so it will not be repeated here.

[0127] 3. Allocate guaranteed bandwidth for each slave device under the scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notify each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device under the future target time point, allocate non-guaranteed bandwidth other than guaranteed bandwidth for the slave device under the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0128] The specific implementation method of step 3 and Figure 7 The process shown is exactly the same, so it will not be repeated here.

[0129] It should be noted that the condition for the cloud server to send the rate prediction model and the guaranteed bandwidth prediction model to the main device is that the computing power of the main device meets the set conditions.

[0130] See Figure 8 , Figure 8 A bandwidth allocation device is provided in one embodiment of this application, such as Figure 8 As shown, the bandwidth allocation device 800 can be applied to network devices in an FTTR network or to network devices outside the FTTR network that are associated with it. The device 800 includes a prediction module 801 and a first policy management module 802.

[0131] The prediction module 801 is used to predict, for each slave device in the FTTR network, the predicted rate of the data flow sent by the slave device to the master device in the FTTR network at at least one future time point, and the predicted guaranteed bandwidth of the slave device at at least one future time point.

[0132] The first strategy management module 802 is used to send the predicted rate value and the guaranteed bandwidth prediction value of the slave device at at least one future time point to the master device, so that the master device can generate a bandwidth scheduling policy for the at least one future time point based on the predicted rate value and guaranteed bandwidth prediction value of each slave device at the at least one future time point, allocate guaranteed bandwidth for each slave device in the scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notify each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, allocate non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device in the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result. This allows the slave device to send a data stream to the master device based on the non-guaranteed bandwidth allocation result; or, based on the rate prediction value and guaranteed bandwidth prediction value of each slave device at at least one future time point, a bandwidth scheduling policy for that at least one future time point is generated, and the bandwidth scheduling policy is sent to the master device, so that the master device allocates guaranteed bandwidth for each slave device in the scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notifies each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device sends a data stream to the master device based on the guaranteed bandwidth allocation result; and, upon receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, the master device allocates non-guaranteed bandwidth other than guaranteed bandwidth in the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notifies the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device sends a data stream to the master device based on the non-guaranteed bandwidth allocation result.

[0133] As one example, the predicted rate of data flow from the slave device to the master device in the FTTR network at at least one future point in time includes:

[0134] Predict the rate of the slave device at at least one future time point based on the trained rate prediction model;

[0135] The predicted guaranteed bandwidth of the slave device at at least one future point in time includes:

[0136] The guaranteed bandwidth prediction model is used to predict the guaranteed bandwidth of the slave device at at least one future point in time.

[0137] The rate prediction model is trained based on the rate values ​​of each slave device at each historical time point. The rate value of any slave device at any historical time point is determined based on the traffic sent by the slave device to the master device between that historical time point and the previous historical time point. The guaranteed bandwidth prediction model is trained based on the guaranteed bandwidth usage of each slave device at each historical time point. The guaranteed bandwidth usage of any slave device at any historical time point is determined based on the traffic sent by the slave device through the guaranteed bandwidth allocated to it between that historical time point and the previous historical time point.

[0138] As one example, the predicted rate of data flow from the slave device to the master device in the FTTR network at at least one future point in time includes:

[0139] Obtain the average and variance of the rate value of the slave device at multiple historical time points corresponding to any future time point;

[0140] If the variance of the rate value is less than or equal to the first set threshold, then the average value of the rate value is determined as the rate prediction value of the slave device at that future time point;

[0141] The predicted guaranteed bandwidth of the slave device at at least one future point in time includes:

[0142] Obtain the average and variance of the guaranteed bandwidth usage of the slave device at multiple historical time points corresponding to any future time point;

[0143] If the variance of the guaranteed bandwidth usage is less than or equal to the second set threshold, then the average value of the guaranteed bandwidth usage is determined as the predicted guaranteed bandwidth value of the slave device at that future point in time.

[0144] As an example, the bandwidth scheduling strategy includes a weight allocation strategy and a guaranteed bandwidth allocation strategy;

[0145] The bandwidth scheduling strategy for at least one future time point is generated based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point, including:

[0146] For each future time point t, based on the predicted guaranteed bandwidth value of each slave device at that future time point t and the maximum guaranteed bandwidth value B set for each slave device. max Determine the bandwidth allocation strategy Q(t); Q(t) is expressed by the following formula:

[0147] Q(t)={V 1,t V 2,t V 3,t ...V i,t};

[0148] Among them, V i,t This represents the guaranteed bandwidth threshold for device i at a future time point t;

[0149] For each future time point t, based on the predicted rate and guaranteed bandwidth of each slave device at that future time point t, a weight allocation strategy P(t) is determined; P(t) is expressed by the following formula:

[0150] P(t)={W 1,t W 2,t W 3,t ...W i,t};

[0151] Among them, W i,t This represents the non-guaranteed bandwidth weight of device i at a future time point t.

[0152] As an example, the guaranteed bandwidth allocation strategy Q(t) is determined based on the predicted guaranteed bandwidth value of each slave device at the future time point t and the maximum guaranteed bandwidth value Bmax set for each slave device, including:

[0153] For each slave device, the guaranteed bandwidth threshold for that slave device at the future time point t is obtained by the following formula:

[0154] V i,t =min(B max C i,t )

[0155] Among them, V i,t Let B represent the guaranteed bandwidth threshold of device i at the future time point t, and let Ci,t represent the predicted guaranteed bandwidth of device i at the future time point t. max This indicates the maximum guaranteed bandwidth value set for device i;

[0156] Based on the predicted rate values ​​and guaranteed bandwidth thresholds of each slave device at the future time point t, the weight allocation strategy P(t) is determined as follows:

[0157] For each slave device, its non-guaranteed bandwidth weight at the future time t is obtained by the following formula:

[0158] W i,t =S i,t -C i,t

[0159] Among them, W i,t S represents the non-guaranteed bandwidth weight of device i at that future time point t; i,t This represents the predicted rate of device i at that future time point t.

[0160] See Figure 9 , Figure 9 A bandwidth allocation device provided in another embodiment of this application, such as Figure 9 As shown, the bandwidth allocation device 900 can be applied to the main equipment in an FTTR network. The device 900 includes: a second policy management module 901 and a policy execution module 902.

[0161] The second policy management module 901 is configured to receive, from the network device, the predicted rate of the data flow sent by each slave device in the FTTR network to the master device at at least one future time point, and the predicted guaranteed bandwidth of the slave device at at least one future time point; the predicted rate and guaranteed bandwidth of the device at at least one future time point are predicted by the network device; and generate a bandwidth scheduling policy for the at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point; or, receive the bandwidth scheduling policy for the at least one future time point sent by the network device; wherein the bandwidth scheduling policy for the at least one future time point is generated by the network device after predicting the predicted rate of the data flow sent by each slave device to the master device in the FTTR network at at least one future time point, and predicting the predicted guaranteed bandwidth of the slave device at at least one future time point, based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point;

[0162] The strategy execution module 902 is used to allocate guaranteed bandwidth to each slave device under the scheduling period corresponding to each future time point according to the bandwidth scheduling strategy, and notify each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device under the future target time point, allocate non-guaranteed bandwidth other than guaranteed bandwidth to the slave device under the scheduling period corresponding to the future target time point according to the bandwidth scheduling strategy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

[0163] As an example, the bandwidth scheduling strategy includes a weight allocation strategy and a guaranteed bandwidth allocation strategy;

[0164] The bandwidth scheduling strategy for at least one future time point is generated based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point, including:

[0165] For each future time point t, based on the predicted guaranteed bandwidth value of each slave device at that future time point t and the maximum guaranteed bandwidth value B set for each slave device. maxDetermine the bandwidth allocation strategy Q(t); Q(t) is expressed by the following formula:

[0166] Q(t)={V 1,t V 2,t V 3,t ...V i,t};

[0167] Among them, V i,t This represents the guaranteed bandwidth threshold for device i at a future time point t;

[0168] For each future time point t, based on the predicted rate and guaranteed bandwidth of each slave device at that future time point t, a weight allocation strategy P(t) is determined; P(t) is expressed by the following formula:

[0169] P(t)={W 1,t W 2,t W 3,t ...W i,t};

[0170] Among them, W i,t This represents the non-guaranteed bandwidth weight of device i at a future time point t.

[0171] As an example, the guaranteed bandwidth allocation strategy Q(t) is determined based on the predicted guaranteed bandwidth value of each slave device at the future time point t and the maximum guaranteed bandwidth value Bmax set for each slave device, including:

[0172] For each slave device, the guaranteed bandwidth threshold for that slave device at the future time point t is obtained by the following formula:

[0173] V i,t =min(B max C i,t )

[0174] Among them, V i,t Let B represent the guaranteed bandwidth threshold of device i at the future time point t, and let Ci,t represent the predicted guaranteed bandwidth of device i at the future time point t. max This indicates the maximum guaranteed bandwidth value set for device i;

[0175] Based on the predicted rate values ​​and guaranteed bandwidth thresholds of each slave device at the future time point t, the weight allocation strategy P(t) is determined as follows:

[0176] For each slave device, its non-guaranteed bandwidth weight at the future time t is obtained by the following formula:

[0177] W i,t =S i,t -C i,t

[0178] Among them, W i,t S represents the non-guaranteed bandwidth weight of device i at that future time point t; i,t This represents the predicted rate of device i at that future time point t.

[0179] As one example, allocating guaranteed bandwidth for each slave device under the scheduling period corresponding to each future time point according to the bandwidth scheduling policy includes:

[0180] For each slave device, based on the guaranteed bandwidth threshold of the slave device at each future time point, the guaranteed bandwidth is allocated to the slave device during the scheduling period between the future time point and the next future time point.

[0181] Upon receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time, the slave device is allocated non-guaranteed bandwidth (excluding guaranteed bandwidth) for the scheduling period corresponding to the future target time, according to the bandwidth scheduling policy. This includes:

[0182] When a non-guaranteed bandwidth allocation request is received from any slave device at a future target time point T0, the future time point that is before T0 and closest to T0 is obtained from the predicted future time points.

[0183] Based on the unguaranteed bandwidth weight of the slave device at the nearest future time point, the unguaranteed bandwidth is allocated to the slave device in the scheduling period corresponding to T0. The unguaranteed bandwidth weight at the nearest future time point is positively correlated with the amount of unguaranteed bandwidth allocated to the slave device at T0 and the priority of the allocated unguaranteed bandwidth.

[0184] Please see Figure 10 , Figure 10 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device may include a processor 1001, a communication interface 1002, a memory 1003, and a communication bus 1004. The processor 1001, communication interface 1002, and memory 1003 communicate with each other via the communication bus 1004. The memory 1003 stores a computer program; the processor 1001 can execute the steps of the method described in the above embodiment by executing the program stored in the memory 1003. Depending on the actual function of the electronic device, other hardware may also be included, which will not be elaborated further.

[0185] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0186] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by special-purpose logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as special-purpose logic circuitry.

[0187] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0188] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0189] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily used to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0190] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0191] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0192] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A bandwidth allocation method, characterized in that, This method is applied to network devices in an FTTR network or to network devices outside the FTTR network that are associated with it. The method includes: For each slave device in an FTTR network, predict the rate of the data stream sent by the slave device to the master device in the FTTR network at at least one future time point, and predict the guaranteed bandwidth of the slave device at the at least one future time point. The predicted rate and guaranteed bandwidth of the slave device at at least one future time point are sent to the master device. The master device then generates a bandwidth scheduling policy for each slave device at at least one future time point based on these predictions. According to the bandwidth scheduling policy, the master device allocates guaranteed bandwidth for each slave device within the corresponding scheduling period for each future time point and notifies each slave device of the guaranteed bandwidth allocation result, enabling the slave device to send a data stream to the master device based on the guaranteed bandwidth allocation result. Furthermore, upon receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time point, the master device allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) for that slave device within the corresponding scheduling period of the future target time point according to the bandwidth scheduling policy and notifies the slave device of the non-guaranteed bandwidth allocation result, enabling the slave device to send a data stream to the master device based on the guaranteed bandwidth allocation result. The system can either send a data stream to the master device based on the non-guaranteed bandwidth allocation result; or generate a bandwidth scheduling policy for at least one future time point based on the rate prediction value and guaranteed bandwidth prediction value of each slave device at at least one future time point, and distribute the bandwidth scheduling policy to the master device so that the master device can allocate guaranteed bandwidth for each slave device in the scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notify each slave device of its corresponding guaranteed bandwidth allocation result so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, upon receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, allocate non-guaranteed bandwidth other than guaranteed bandwidth for the slave device in the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

2. The method according to claim 1, characterized in that, The predicted rate of the data flow sent by the slave device to the master device in the FTTR network at at least one future time point includes: Predict the rate of the slave device at at least one future time point based on the trained rate prediction model; The prediction of the guaranteed bandwidth forecast value of the slave device at the at least one future time point includes: The guaranteed bandwidth prediction model is used to predict the guaranteed bandwidth of the slave device at at least one future point in time. The rate prediction model is trained based on the rate values ​​of each slave device at each historical time point. The rate value of any slave device at any historical time point is determined based on the traffic sent by the slave device to the master device between that historical time point and the previous historical time point. The guaranteed bandwidth prediction model is trained based on the guaranteed bandwidth occupancy of each slave device at each historical time point. The guaranteed bandwidth occupancy of any slave device at any historical time point is determined based on the traffic sent by the slave device through the guaranteed bandwidth allocated to it between that historical time point and the previous historical time point.

3. The method according to claim 1, characterized in that, The predicted rate of the data flow sent by the slave device to the master device in the FTTR network at at least one future time point includes: Obtain the average and variance of the rate value of the slave device at multiple historical time points corresponding to any future time point; If the variance of the rate value is less than or equal to a first set threshold, then the average value of the rate value is determined as the rate prediction value of the slave device at that future time point; The prediction of the guaranteed bandwidth forecast value of the slave device at the at least one future time point includes: Obtain the average and variance of the guaranteed bandwidth usage of the slave device at multiple historical time points corresponding to any future time point; If the variance of the guaranteed bandwidth occupancy is less than or equal to the second set threshold, then the average value of the guaranteed bandwidth occupancy is determined as the guaranteed bandwidth prediction value of the slave device at that future point in time.

4. The method according to claim 1, characterized in that, The bandwidth scheduling strategy includes a weighted allocation strategy and a guaranteed bandwidth allocation strategy; The generation of the bandwidth scheduling strategy for at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point includes: For each future time point t, based on the predicted guaranteed bandwidth value of each slave device at that future time point t and the maximum guaranteed bandwidth value B set for each slave device. max Determine the bandwidth allocation strategy Q(t); Q(t) is expressed by the following formula: Q(t)={V 1,t ,V 2,t ,V 3,t ……V i,t }; Among them, V i,t This represents the guaranteed bandwidth threshold for device i at a future time point t; For each future time point t, a weight allocation strategy P(t) is determined based on the predicted rate and guaranteed bandwidth of each slave device at that future time point t; P(t) is expressed by the following formula: P(t)={W 1,t ,W 2,t ,W 3,t ……W i,t }; Among them, W i,t This represents the non-guaranteed bandwidth weight of device i at a future time point t.

5. The method according to claim 4, characterized in that, The determination of the guaranteed bandwidth allocation strategy Q(t) based on the predicted guaranteed bandwidth value of each slave device at the future time point t and the maximum guaranteed bandwidth value Bmax set for each slave device includes: For each slave device, the guaranteed bandwidth threshold for that slave device at the future time point t is obtained by the following formula: V i,t =min(B max ,C i,t ) Among them, V i,t Let B represent the guaranteed bandwidth threshold of device i at the future time point t, and let Ci,t represent the predicted guaranteed bandwidth of device i at the future time point t. max This indicates the maximum guaranteed bandwidth value set for device i; The determination of the weight allocation strategy P(t) based on the predicted rate and guaranteed bandwidth of each slave device at the future time point t includes: For each slave device, the non-guaranteed bandwidth weight at the future time point t is obtained by the following formula: W i,t =S i,t -C i,t Among them, W i,t S represents the non-guaranteed bandwidth weight of device i at that future time point t; i,t This represents the predicted rate of device i at that future time point t.

6. A bandwidth allocation method, characterized in that, This method is applied to the master device in an FTTR network, and the method includes: The network device receives a predicted rate of data flow sent by each slave device in the FTTR network to its master device at at least one future time point, and a predicted guaranteed bandwidth value for the slave device at the at least one future time point; the predicted rate and guaranteed bandwidth values ​​for the slave device at the at least one future time point are predicted by the network device; and generates a bandwidth scheduling policy for the at least one future time point based on the predicted rate and guaranteed bandwidth values ​​for each slave device at the at least one future time point; or, the network device receives a bandwidth scheduling policy for the at least one future time point; wherein the bandwidth scheduling policy for the at least one future time point is generated by the network device after predicting the predicted rate of data flow sent by each slave device to the master device in the FTTR network at at least one future time point, and predicting the predicted guaranteed bandwidth value for the slave device at the at least one future time point, based on the predicted rate and guaranteed bandwidth values ​​for each slave device at the at least one future time point. According to the bandwidth scheduling policy, the system allocates guaranteed bandwidth to each slave device for each future time point within the corresponding scheduling period, and notifies each slave device of the corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, the system allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device for the corresponding scheduling period at the future target time point according to the bandwidth scheduling policy, and notifies the slave device of the corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

7. The method according to claim 6, characterized in that, The bandwidth scheduling strategy includes a weighted allocation strategy and a guaranteed bandwidth allocation strategy; The generation of the bandwidth scheduling strategy for at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point includes: For each future time point t, based on the predicted guaranteed bandwidth value of each slave device at that future time point t and the maximum guaranteed bandwidth value B set for each slave device. max Determine the bandwidth allocation strategy Q(t); Q(t) is expressed by the following formula: Q(t)={V 1,t ,V 2,t ,V 3,t ……V i,t }; Among them, V i,t This represents the guaranteed bandwidth threshold for device i at a future time point t; For each future time point t, a weight allocation strategy P(t) is determined based on the predicted rate and guaranteed bandwidth of each slave device at that future time point t; P(t) is expressed by the following formula: P(t)={W 1,t ,W 2,t ,W 3,t ……W i,t }; Among them, W i,t This represents the non-guaranteed bandwidth weight of device i at a future time point t.

8. The method according to claim 7, characterized in that, The determination of the guaranteed bandwidth allocation strategy Q(t) based on the predicted guaranteed bandwidth value of each slave device at the future time point t and the maximum guaranteed bandwidth value Bmax set for each slave device includes: For each slave device, the guaranteed bandwidth threshold for that slave device at the future time point t is obtained by the following formula: V i,t =min(B max ,C i,t ) Among them, V i,t Let B represent the guaranteed bandwidth threshold of device i at the future time point t, and let Ci,t represent the predicted guaranteed bandwidth of device i at the future time point t. max This indicates the maximum guaranteed bandwidth value set for device i; The determination of the weight allocation strategy P(t) based on the predicted rate value and guaranteed bandwidth threshold of each slave device at the future time point t includes: For each slave device, the non-guaranteed bandwidth weight at the future time point t is obtained by the following formula: W i,t =S i,t -C i,t Among them, W i,t S represents the non-guaranteed bandwidth weight of device i at that future time point t; i,t This represents the predicted rate of device i at that future time point t.

9. The method according to claim 8, characterized in that, The allocation of guaranteed bandwidth to each slave device for each future time point within the corresponding scheduling period based on the bandwidth scheduling strategy includes: For each slave device, based on the guaranteed bandwidth threshold of the slave device at each future time point, the guaranteed bandwidth is allocated to the slave device during the scheduling period between the future time point and the next future time point. When receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time, allocating non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device according to the bandwidth scheduling policy for the scheduling period corresponding to the future target time includes: When a non-guaranteed bandwidth allocation request is received from any slave device at a future target time point T0, the future time point that is closest to T0 before T0 is obtained from the predicted future time points. Based on the obtained non-guaranteed bandwidth weight of the slave device at the nearest future time point, non-guaranteed bandwidth is allocated to the slave device in the scheduling period corresponding to T0, wherein the non-guaranteed bandwidth weight at the nearest future time point is positively correlated with the amount of non-guaranteed bandwidth allocated to the slave device at T0 and the priority of the allocated non-guaranteed bandwidth.

10. A bandwidth allocation device, characterized in that, This device is applied to network devices within an FTTR network or to network devices outside the FTTR network that are associated with it. The device includes: The prediction module is used to predict the rate of data flow sent by each slave device to the master device in the FTTR network at at least one future time point, and to predict the guaranteed bandwidth of the slave device at the at least one future time point. The first strategy management module is configured to send the predicted rate value and the guaranteed bandwidth prediction value of the slave device at the at least one future time point to the master device. The master device then generates a bandwidth scheduling policy for the at least one future time point based on the predicted rate and guaranteed bandwidth values ​​of each slave device. According to the bandwidth scheduling policy, the master device allocates guaranteed bandwidth for each slave device within the scheduling period corresponding to each future time point and notifies each slave device of the corresponding guaranteed bandwidth allocation result, enabling the slave device to send a data stream to the master device based on the guaranteed bandwidth allocation result. Furthermore, upon receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time point, the master device allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device within the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy and notifies the slave device of the corresponding non-guaranteed bandwidth allocation result. This allows the slave device to send a data stream to the master device based on the non-guaranteed bandwidth allocation result; or, based on the rate prediction value and guaranteed bandwidth prediction value of each slave device at at least one future time point, a bandwidth scheduling policy for that at least one future time point is generated, and the bandwidth scheduling policy is sent to the master device, so that the master device allocates guaranteed bandwidth for each slave device in the scheduling period corresponding to each future time point according to the bandwidth scheduling policy, and notifies each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device sends a data stream to the master device according to the guaranteed bandwidth allocation result; and, upon receiving a non-guaranteed bandwidth allocation request sent by any slave device at a future target time point, the master device allocates non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device in the scheduling period corresponding to the future target time point according to the bandwidth scheduling policy, and notifies the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device sends a data stream to the master device according to the non-guaranteed bandwidth allocation result.

11. The apparatus according to claim 10, characterized in that, The predicted rate of the data flow sent by the slave device to the master device in the FTTR network at at least one future time point includes: Predict the rate of the slave device at at least one future time point based on the trained rate prediction model; The prediction of the guaranteed bandwidth forecast value of the slave device at the at least one future time point includes: The guaranteed bandwidth prediction model is used to predict the guaranteed bandwidth of the slave device at at least one future point in time. The rate prediction model is trained based on the rate values ​​of each slave device at each historical time point. The rate value of any slave device at any historical time point is determined based on the traffic sent by that slave device to the master device between that historical time point and the previous historical time point. The guaranteed bandwidth prediction model is trained based on the guaranteed bandwidth usage of each slave device at each historical time point. The guaranteed bandwidth usage of any slave device at any historical time point is determined based on the traffic sent by that slave device through the guaranteed bandwidth allocated to that slave device between that historical time point and the previous historical time point. Or, The predicted rate of the data flow sent by the slave device to the master device in the FTTR network at at least one future time point includes: Obtain the average and variance of the rate value of the slave device at multiple historical time points corresponding to any future time point; If the variance of the rate value is less than or equal to a first set threshold, then the average value of the rate value is determined as the rate prediction value of the slave device at that future time point; The prediction of the guaranteed bandwidth forecast value of the slave device at the at least one future time point includes: Obtain the average and variance of the guaranteed bandwidth usage of the slave device at multiple historical time points corresponding to any future time point; If the variance of the guaranteed bandwidth occupancy is less than or equal to the second set threshold, then the average value of the guaranteed bandwidth occupancy is determined as the guaranteed bandwidth prediction value of the slave device at that future point in time.

12. The apparatus according to claim 10 or 11, characterized in that, The bandwidth scheduling strategy includes a weighted allocation strategy and a guaranteed bandwidth allocation strategy; The generation of the bandwidth scheduling strategy for at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point includes: For each future time point t, based on the predicted guaranteed bandwidth value of each slave device at that future time point t and the maximum guaranteed bandwidth value B set for each slave device. max Determine the bandwidth allocation strategy Q(t); Q(t) is expressed by the following formula: Q(t)={V 1,t ,V 2,t ,V 3,t ……V i,t }; Among them, V i,t This represents the guaranteed bandwidth threshold for device i at a future time point t; For each future time point t, a weight allocation strategy P(t) is determined based on the predicted rate and guaranteed bandwidth of each slave device at that future time point t; P(t) is expressed by the following formula: P(t)={W 1,t ,W 2,t ,W 3,t ……W i,t }; Among them, W i,t This represents the non-guaranteed bandwidth weight of device i at a future time point t.

13. The apparatus according to claim 12, characterized in that, The determination of the guaranteed bandwidth allocation strategy Q(t) based on the predicted guaranteed bandwidth value of each slave device at the future time point t and the maximum guaranteed bandwidth value Bmax set for each slave device includes: For each slave device, the guaranteed bandwidth threshold for that slave device at the future time point t is obtained by the following formula: V i,t =min(B max ,C i,t ) Among them, V i,t Let B represent the guaranteed bandwidth threshold of device i at the future time point t, and let Ci,t represent the predicted guaranteed bandwidth of device i at the future time point t. max This indicates the maximum guaranteed bandwidth value set for device i; The determination of the weight allocation strategy P(t) based on the predicted rate value and guaranteed bandwidth threshold of each slave device at the future time point t includes: For each slave device, the non-guaranteed bandwidth weight at the future time point t is obtained by the following formula: W i,t =S i,t -C i,t Among them, W i,t S represents the non-guaranteed bandwidth weight of device i at that future time point t; i,t This represents the predicted rate of device i at that future time point t.

14. A bandwidth allocation device, characterized in that, This device is used as the main equipment in an FTTR network. The device includes: The second policy management module is configured to receive, from the network device, the predicted rate of data flow sent by each slave device in the FTTR network to the master device at at least one future time point, and the predicted guaranteed bandwidth of the slave device at the at least one future time point; the predicted rate and guaranteed bandwidth of the slave device at the at least one future time point are predicted by the network device; and generate a bandwidth scheduling policy for the at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at the at least one future time point; or, receive the bandwidth scheduling policy for the at least one future time point sent by the network device; wherein the bandwidth scheduling policy for the at least one future time point is generated by the network device after predicting the predicted rate of data flow sent by each slave device to the master device in the FTTR network at at least one future time point, and predicting the predicted guaranteed bandwidth of the slave device at the at least one future time point, based on the predicted rate and guaranteed bandwidth of each slave device at the at least one future time point; The strategy execution module is used to allocate guaranteed bandwidth to each slave device under the scheduling period corresponding to each future time point according to the bandwidth scheduling strategy, and notify each slave device of its corresponding guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the guaranteed bandwidth allocation result; and, when receiving a non-guaranteed bandwidth allocation request sent by any slave device under the future target time point, allocate non-guaranteed bandwidth other than guaranteed bandwidth to the slave device under the scheduling period corresponding to the future target time point according to the bandwidth scheduling strategy, and notify the slave device of its corresponding non-guaranteed bandwidth allocation result, so that the slave device can send a data stream to the master device according to the non-guaranteed bandwidth allocation result.

15. The apparatus according to claim 14, characterized in that, The bandwidth scheduling strategy includes a weighted allocation strategy and a guaranteed bandwidth allocation strategy; The generation of the bandwidth scheduling strategy for at least one future time point based on the predicted rate and guaranteed bandwidth of each slave device at at least one future time point includes: For each future time point t, based on the predicted guaranteed bandwidth value of each slave device at that future time point t and the maximum guaranteed bandwidth value B set for each slave device. max Determine the bandwidth allocation strategy Q(t); Q(t) is expressed by the following formula: Q(t)={V 1,t ,V 2,t ,V 3,t ……V i,t }; Among them, V i,t This represents the guaranteed bandwidth threshold for device i at a future time point t; For each future time point t, a weight allocation strategy P(t) is determined based on the predicted rate and guaranteed bandwidth of each slave device at that future time point t; P(t) is expressed by the following formula: P(t)={W 1,t ,W 2,t ,W 3,t ……W i,t }; Among them, W i,t This represents the non-guaranteed bandwidth weight of device i at a future time point t.

16. The apparatus according to claim 15, characterized in that, The determination of the guaranteed bandwidth allocation strategy Q(t) based on the predicted guaranteed bandwidth value of each slave device at the future time point t and the maximum guaranteed bandwidth value Bmax set for each slave device includes: For each slave device, the guaranteed bandwidth threshold for that slave device at the future time point t is obtained by the following formula: V i,t =min(B max ,C i,t ) Among them, V i,t Let B represent the guaranteed bandwidth threshold of device i at the future time point t, and let Ci,t represent the predicted guaranteed bandwidth of device i at the future time point t. max This indicates the maximum guaranteed bandwidth value set for device i; The determination of the weight allocation strategy P(t) based on the predicted rate value and guaranteed bandwidth threshold of each slave device at the future time point t includes: For each slave device, the non-guaranteed bandwidth weight at the future time point t is obtained by the following formula: W i,t =S i,t -C i,t Among them, W i,t S represents the non-guaranteed bandwidth weight of device i at that future time point t; i,t This represents the predicted rate of device i at that future time point t.

17. The apparatus according to claim 16, characterized in that, The allocation of guaranteed bandwidth to each slave device for each future time point within the corresponding scheduling period based on the bandwidth scheduling strategy includes: For each slave device, based on the guaranteed bandwidth threshold of the slave device at each future time point, the guaranteed bandwidth is allocated to the slave device during the scheduling period between the future time point and the next future time point. When receiving a non-guaranteed bandwidth allocation request from any slave device at a future target time, allocating non-guaranteed bandwidth (excluding guaranteed bandwidth) to the slave device according to the bandwidth scheduling policy for the scheduling period corresponding to the future target time includes: When a non-guaranteed bandwidth allocation request is received from any slave device at a future target time point T0, the future time point that is closest to T0 before T0 is obtained from the predicted future time points. Based on the obtained non-guaranteed bandwidth weight of the slave device at the nearest future time point, non-guaranteed bandwidth is allocated to the slave device in the scheduling period corresponding to T0, wherein the non-guaranteed bandwidth weight at the nearest future time point is positively correlated with the amount of non-guaranteed bandwidth allocated to the slave device at T0 and the priority of the allocated non-guaranteed bandwidth.

18. An electronic device, characterized in that, include: processor; as well as A memory storing computer program instructions that, when executed by the processor, cause the processor to perform the method as described in any one of claims 1 to 9.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1 to 9.

Images