ECN threshold configuration information generation method and congestion control system

Abstract

The embodiment of the invention discloses an ECN threshold configuration information generation method and a congestion control system, and relates to the technical field of computers. The ECN threshold configuration information generation method comprises the following steps: receiving a current traffic state information sequence of network node equipment; based on a traffic model file of the network node equipment, identifying whether the traffic state information sequence is an existing traffic model in the traffic model file; and when the traffic state information sequence is not the existing traffic model in the traffic model file, inputting the traffic state information sequence into an ECN threshold prediction model corresponding to the network node equipment to perform ECN threshold configuration information prediction, determining the ECN threshold configuration information predicted by the ECN threshold prediction model as the current ECN threshold configuration information of the network node equipment; wherein the ECN threshold prediction model corresponding to the network node equipment is obtained by training an LSTM (Long Short Term Memory) model by taking a sample traffic state information sequence of the network node equipment as input and taking sample ECN threshold configuration information corresponding to the sample traffic state information sequence as an output label; the sample ECN threshold configuration information is ECN threshold configuration information capable of giving consideration to both mouse flow and elephant flow.

Description

Technical Field

[0001] The present application relates to the computer field, and in particular to a method for generating ECN threshold configuration information and a congestion control system. Background Art

[0002] Currently, the ECN threshold value of the intelligent lossless network RoCEv2 is usually manually configured based on expert experience and manually modified later according to changes in the network model.

[0003] The manually configured ECN threshold value cannot take into account the latency-sensitive rat flows and throughput-sensitive elephant flows that exist simultaneously in the network. When the ECN threshold is set too low, the ECN congestion mark can be triggered as soon as possible to notify the source server to slow down, thereby maintaining a low cache depth (that is, a low queue delay), which is beneficial to latency-sensitive rat flows. However, an ECN threshold that is too low will affect throughput-sensitive elephant flows, limit the traffic bandwidth of elephant flows, and fail to meet the high throughput of elephant flows. When the ECN threshold is set too high, the time to trigger the ECN congestion mark can be extended to ensure the burst absorption capacity of the queue and meet the traffic bandwidth of throughput-sensitive elephant flows. However, when the queue is congested, due to the large cache, it will cause queue queuing and cause a large queue delay, which is not beneficial to latency-sensitive rat flows.

[0004] In addition, the manually configured ECN threshold cannot cope with the burst traffic in the Incast scenario. In order to ensure no packet loss, the manually configured ECN threshold is often set to a fixed ECN threshold based on the maximum link bandwidth of the access. This makes it easy for the upstream and downstream queues in the same switch to have N-to-1 Incast scenarios in high-performance distributed applications. Summary of the invention

[0005] The embodiment of the present application provides a method for generating ECN threshold configuration information and a congestion control system to dynamically and automatically generate appropriate ECN thresholds, taking into account the delay-sensitive mouse flows and throughput-sensitive elephant flows that exist simultaneously in the network, and coping with burst traffic in an Incast scenario.

[0006] In a first aspect, an embodiment of the present application provides a method for generating ECN threshold configuration information, the method comprising: Receive the current flow status information sequence of the network node device; wherein the flow status information sequence is a time sequence composed of the flow status information of the network node device at each time point within a specified time length ending at the current time point, and the flow status information at each time point includes: the flow status information of each virtual channel of the network node device at that time point; Based on the traffic model file of the network node device, identifying whether the traffic state information sequence is an existing traffic model in the traffic model file; wherein the traffic model file stores a plurality of existing traffic models, each traffic model being a traffic state information sequence; When the traffic state information sequence is not an existing traffic model in the traffic model file, the traffic state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device; wherein the ECN threshold configuration information includes the ECN threshold value of each virtual channel of the network node device; the ECN threshold prediction model corresponding to the network node device uses the sample traffic state information sequence of the network node device as input, and the sample ECN threshold configuration information corresponding to the sample traffic state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow.

[0007] In a second aspect, an embodiment of the present application provides a congestion control system, the system comprising: a network node device, a collector, and an ECN threshold configuration automatic generation component; The network node device is used to periodically push the traffic status information of the network node device at the current time point to the collector; The collector is used to combine the flow status information of the network node device at the current time point with the flow status information of the network node device at other time points within a specified time length before the current time point to obtain the current flow status information sequence of the network node device, and send the flow status information sequence to the ECN threshold configuration automatic generation component; The ECN threshold configuration automatic generation component is used to detect whether the flow state information sequence is an existing flow model in the flow model file based on the flow model file of the network node device. When the flow state information sequence is not an existing flow model in the flow model file, the flow state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device and returned to the network node device; wherein, the flow model file stores a plurality of existing flow models, each flow model is a flow state information sequence; the ECN threshold prediction model corresponding to the network node device uses the sample flow state information sequence of the network node device as input, and uses the sample ECN threshold configuration information corresponding to the sample flow state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow; The network node device is used to configure the ECN threshold of its virtual channel based on the current ECN threshold configuration information of the network node device to perform congestion control on its virtual channel.

[0008] In a third aspect, an embodiment of the present application provides a device for generating ECN threshold configuration information, the device comprising: An information receiving module is used to receive the current flow status information sequence of the network node device; wherein the flow status information sequence is a time sequence composed of the flow status information of the network node device at each time point within a specified time length ending at the current time point, and the flow status information at each time point includes: the flow status information of each virtual channel of the network node device at that time point; An identification module, used to identify whether the flow state information sequence is an existing flow model in the flow model file based on the flow model file of the network node device; wherein the flow model file stores a plurality of existing flow models, each flow model being a flow state information sequence; A prediction module is used to input the traffic state information sequence into the ECN threshold prediction model corresponding to the network node device to perform ECN threshold configuration information prediction when the traffic state information sequence is not a traffic model already in the traffic model file, and determine the ECN threshold configuration information predicted by the ECN threshold prediction model as the current ECN threshold configuration information of the network node device; wherein the ECN threshold configuration information includes the ECN threshold value of each virtual channel of the network node device; the ECN threshold prediction model corresponding to the network node device uses the sample traffic state information sequence of the network node device as input, and uses the sample ECN threshold configuration information corresponding to the sample traffic state information sequence as an output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, wherein the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow.

[0009] In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is executed by the processor to implement the method for generating ECN threshold configuration information provided in the first aspect of the embodiment of the present application.

[0010] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method for generating ECN threshold configuration information provided in the first aspect of the embodiment of the present application.

[0011] In an embodiment of the present application, a sample flow state information sequence of a network node device is used as input, and sample ECN threshold configuration information corresponding to the sample flow state information sequence that can take into account both mouse flow and elephant flow is used as an output label, and an LSTM model is trained to obtain an ECN threshold prediction model corresponding to the network node device. When the current flow state information sequence of the network node device is received, based on the flow model file of the network node device, it is identified whether the flow state information sequence is a flow model already in the flow model file; when the flow state information sequence is not a flow model already in the flow model file, the flow state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device. The ECN threshold prediction model of the network node device can dynamically generate suitable ECN threshold configuration information that can take into account both mouse flow and elephant flow for the network node device, so that the network node device can take into account both mouse flow and elephant flow based on the dynamic suitable ECN threshold configuration information to cope with burst traffic in the Incast scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate one or more embodiments of the present application or the technical solutions in the prior art, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only drawings of one or more embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 It is a schematic diagram of an application scenario of a method for generating ECN threshold configuration information provided in some embodiments of the present application; Figure 2 It is a flowchart of a method for generating ECN threshold configuration information provided by some embodiments of the present application; Figure 3 It is a schematic diagram of the training process of the ECN threshold prediction model provided in some embodiments of the present application; Figure 4 is a schematic diagram of a flow chart of obtaining a training data set provided in some embodiments of the present application; Figure 5 is a schematic diagram of the structure of a congestion control system provided by some embodiments of the present application; Figure 6 It is a module schematic diagram of a device for generating ECN threshold configuration information provided by some embodiments of the present application; Figure 7 It is a schematic diagram of the structure of an electronic device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0014] The embodiments of the present application provide a method for generating ECN threshold configuration information and an intelligent lossless network management platform, which can be used in an intelligent lossless network based on the RoCEv2 protocol to dynamically and automatically generate appropriate ECN threshold configuration information for network node devices in the network, so that the ECN threshold of the network can take into account the delay-sensitive mouse flow and throughput-sensitive elephant flow that exist simultaneously in the network, and cope with burst traffic in an Incast scenario.

[0015] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0016] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the application can be implemented in an order other than those illustrated or described herein.

[0017] Figure 1 Schematic diagram of application scenarios of ECN threshold configuration information provided by some embodiments of the present application. Figure 1 As shown, in this application scenario, it includes: multiple network node devices 110 of the intelligent lossless network and an intelligent lossless network management platform 120, wherein the intelligent lossless network management platform 120 further includes: a collector 121 and an ECN threshold configuration automatic generation component 122.

[0018] The method for generating ECN threshold configuration information provided in the embodiment of the present application can be applied to the ECN threshold configuration automatic generation component 122.

[0019] During implementation, the network node device 110 may periodically push the traffic status information of the network node device 110 at the current time point to the collector 121 in the intelligent lossless network management platform 120 .

[0020] The collector 121 can combine the traffic status information of the network node device 110 at the current time point with the traffic status information of the network node device 110 at other time points within a specified time length before the current time point to obtain the current traffic status information sequence of the network node device 110, and send the traffic status information sequence to the ECN threshold configuration automatic generation component 122 in the intelligent lossless network management platform 120.

[0021] The ECN threshold configuration automatic generation component 122 can detect whether the traffic state information sequence is a traffic model already in the traffic model file based on the traffic model file of the network node device 110. When the traffic state information sequence is not a traffic model already in the traffic model file, the traffic state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device and returned to the network node device 110.

[0022] The network node device 110 may configure the ECN threshold of its virtual channel based on the current ECN threshold configuration information of the network node device to perform congestion control on its virtual channel.

[0023] Figure 2 1 is a flow chart of a method for generating ECN threshold configuration information provided by some embodiments of the present application. Figure 2 , the method for generating the ECN threshold configuration information provided in the embodiment of the present application is described in detail.

[0024] like Figure 2 As shown, in some embodiments of the present application, the method for generating ECN threshold configuration information includes: S201, receiving the current flow status information sequence of the network node device.

[0025] In the embodiment of the present application, the current flow status information sequence of the network node device is a time sequence composed of the flow status information of the network node device at each time point within a specified time length ending at the current time point, and the flow status information at each time point includes: the flow status information of each virtual channel of the network node device at that time point. The flow status information may include: cache space size, cache occupancy, bandwidth throughput and other information.

[0026] For example, assuming that network node device 1 has 3 virtual channels, the current flow state information sequence of network node device 1 may be:

[0027] in, Represents the traffic status information of network node 1 at the Tth time point.

[0028]

[0029] in, Represents the traffic status information of the third virtual channel of network node 1 at time point T.

[0030] S202: Based on the traffic model file of the network node device, identify whether the traffic state information sequence is a traffic model already in the traffic model file.

[0031] In the embodiment of the present application, the traffic model file stores multiple existing traffic models, and each traffic model is a traffic state information sequence.

[0032] In a specific implementation, the current traffic status information sequence of the network node device can be compared with the existing traffic model in the traffic model file. If the current traffic status information sequence is the same as a certain traffic model already in the traffic model file, it is determined that the current traffic status information sequence is the traffic model already in the traffic model file. If the current traffic status information sequence is different from each existing traffic model in the traffic model file, it is determined that the current traffic status information sequence is not the traffic model already in the traffic model file.

[0033] S203, when the traffic state information sequence is not a traffic model already in the traffic model file, input the traffic state information sequence into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and determine the ECN threshold configuration information predicted by the ECN threshold prediction model as the current ECN threshold configuration information of the network node device.

[0034] In the embodiment of the present application, the ECN threshold configuration information of the network node device includes the ECN threshold value of each virtual channel of the network node device.

[0035] For example, following the above example, the current traffic state information sequence of the network node device 1 is input into the ECN threshold prediction model 1 of the network node device 1, and the ECN threshold configuration information output by the ECN threshold prediction model 1 is:

[0036] in, Indicates the ECN threshold value of the first virtual channel of network node device 1, Indicates the ECN threshold value of the second virtual channel of network node device 1, Indicates the ECN threshold value of the second virtual channel of network node device 1.

[0037] In an embodiment of the present application, the ECN threshold prediction model corresponding to the network node device takes the sample traffic status information sequence of the network node device as input, and takes the sample ECN threshold configuration information corresponding to the sample traffic status information sequence as an output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, which is ECN threshold configuration information that can take into account both mouse flow and elephant flow.

[0038] During specific implementation, the flow state information sequence can be input into the ECN threshold prediction model corresponding to the network node device. After receiving the flow state information sequence, the ECN threshold prediction model can predict the ECN threshold configuration information based on the flow state information sequence to obtain the predicted ECN threshold configuration information, and then output the predicted ECN threshold configuration information. Afterwards, the predicted ECN threshold configuration information output by the ECN threshold prediction model can be determined as the current ECN threshold configuration information of the network node device. By continuously receiving the current flow state information sequence of the network node device, inputting the flow state information sequence into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and determining the predicted ECN threshold configuration information as the current ECN threshold configuration information of the network node device, the ECN threshold configuration information of the network node device can be made dynamic ECN threshold configuration information.

[0039] In an embodiment of the present application, by taking the sample flow state information sequence of the network node device as input, the sample ECN threshold configuration information corresponding to the sample flow state information sequence that can take into account both the mouse flow and the elephant flow as the output label, the LSTM model is trained to obtain the ECN threshold prediction model of the network node device, so that the ECN threshold prediction model can predict the appropriate ECN threshold configuration information that can take into account both the mouse flow and the elephant flow. After receiving the current flow state information sequence of the network node device, the current flow state information sequence of the network node device is input into the ECN threshold prediction model to perform ECN threshold configuration information prediction, and the current appropriate ECN threshold configuration information of the network node device can be obtained, taking into account both the mouse flow and the elephant flow. By continuously inputting the current flow state information sequence of the network node device into the ECN threshold prediction model to perform ECN threshold configuration information prediction, the dynamic appropriate ECN threshold configuration information of the network node device can be obtained to cope with the burst traffic in the Incast scenario.

[0040] Figure 3 Schematic diagram of the training process of the ECN threshold prediction model provided by some embodiments of the present application. Figure 3 As shown, in some embodiments of the present application, the ECN threshold prediction model of the network node device can be trained by the following method.

[0041] S301, inputting the sample traffic state information sequence of the current sample in the training data set of the network node device into the LSTM model to obtain the predicted ECN threshold configuration information output by the LSTM model.

[0042] In the embodiment of the present application, the current sample is the sample of this iteration, which is updated in each iteration. For example, in the first iteration, the current sample is the first sample in the training data set, and in the second iteration, the current sample is the second sample in the training data set.

[0043] In the embodiment of the present application, before step S301, a training data set of the network node device may be obtained. Figure 4 Schematic diagram of the process of obtaining a training data set provided in some embodiments of the present application. Figure 4 As shown, the training data set of the network node device can be obtained by the following method.

[0044] S401, filtering the historical ECN threshold configuration information of the network node device based on the threshold filtering condition to obtain target historical ECN threshold configuration information that can take into account both mouse flows and elephant flows.

[0045] In the embodiment of the present application, the threshold configuration screening condition is used to screen out ECN threshold configuration information that can take into account both delay-sensitive mouse flows and throughput-sensitive elephant flows. In some embodiments, the threshold configuration screening condition may specifically include the following conditions: Condition 1: The sum of the PFC threshold values ​​of the virtual channels in the input direction of all the uplink ports of the network node device is greater than the ECN threshold value of the virtual channels in the output direction of the downlink ports of the network node device. That is:

[0046] in, Indicates the PFC threshold value of the virtual channel in the input direction of all upstream ports of the node device. Indicates the ECN threshold value of the virtual channel corresponding to the output direction of the downstream port of the node device.

[0047] By setting this condition, the filtered ECN threshold configuration information can ensure that before the virtual channel in the output direction of the downlink port of the network node device triggers the ECN congestion mark, the PFC flow control of the virtual channel in the input direction of all the uplink ports of the network node device will not be triggered, thereby reducing the number of times the PFC flow control is triggered. In addition, the filtered ECN threshold configuration information will not trigger ECN frequently, resulting in a large number of CNP (Congestion Notification Packets) congestion notification packets and too low throughput.

[0048] Condition 2: The Service cache threshold of the output direction virtual channel of the downlink port of the network node device is greater than the sum of the PFC threshold value of the input direction virtual channel of all uplink ports of the network node device and the Headroom cache threshold of the cache space of the input direction virtual channel of all uplink ports of the network node device. That is:

[0049] in Indicates the Service cache threshold of the virtual channel in the output direction of the downstream port of the node device. Indicates the PFC threshold value of the virtual channel in the input direction of all upstream ports of the node device. Indicates the headroom buffer threshold of the buffer space of the virtual channel in the input direction of all uplink ports of the node device.

[0050] By setting this condition, the filtered ECN threshold configuration information can ensure that before all the upstream port input direction virtual channels of the network node device trigger PFC flow control, the cache space of the downstream port output direction virtual channels of the network node device is sufficient and no packet loss occurs.

[0051] Condition 3: The value of the buffer interval size ECN-PFC Buffer Gap between the ECN threshold and the PFC threshold of each virtual channel of the network node device is set so that the traffic in the virtual channel will not trigger the PFC threshold within the effective time of the ECN threshold (that is, the time difference from marking ECN to source end speed reduction).

[0052] By setting this condition, the filtered ECN threshold configuration information can ensure that the traffic of the network node device will not trigger the PFC threshold within the time difference from marking ECN to speed reduction at the source end, thereby avoiding reduction of RDMA throughput.

[0053] In specific implementation, the historical ECN threshold configuration information of the network node device may be screened based on the above threshold screening conditions, and the historical ECN threshold configuration information satisfying all the above conditions may be determined as the target historical ECN threshold configuration information.

[0054] S402: Determine the target historical ECN threshold configuration information as sample ECN threshold configuration information, and determine the historical traffic state information sequence corresponding to the target historical ECN threshold configuration information as the sample traffic state information sequence corresponding to the sample ECN threshold configuration information.

[0055] S403: Obtain a total data set of the network node device based on the sample ECN threshold configuration information and a sample traffic state information sequence corresponding to the sample ECN threshold configuration information.

[0056] In an embodiment of the present application, there are multiple sample ECN threshold configuration information that meet the threshold screening conditions, and each sample ECN threshold configuration information and its corresponding sample traffic status information sequence are a sample, so that there are multiple samples obtained based on the threshold screening conditions, and the set composed of multiple samples is the total data set of the network node device.

[0057] S404, performing data cleaning on the total data set, and obtaining a training data set for the node device based on the total data set after data cleaning.

[0058] In some embodiments of the present application, in order to ensure the diversity and standardization of samples in the data set and facilitate the subsequent model training, the above-mentioned multiple samples can be further cleaned by removing duplicate, missing and abnormal data, and a total data set can be established based on the multiple samples after data cleaning.

[0059] For example, the samples can be deduplicated based on their unique identifiers; missing values ​​in the samples can be filled using mean interpolation to process missing data in the samples; standard deviation can be used to detect whether the data is abnormal based on a threshold, and the detected abnormal data can be removed to process abnormal samples.

[0060] After the above processing, the total data set after the network node device data cleaning can be obtained. Afterwards, a training data set can be obtained based on the total data set. For example, 80% of the data in the total data set can be divided into a training data set to obtain a training data set for the network node device. The training data set can contain multiple samples, each of which contains a sample flow state information sequence and its corresponding sample ECN threshold configuration information.

[0061] In addition, the remaining 20% ​​of the data in the total data set may be divided into a test data set to test the ECN threshold prediction model.

[0062] S302: Calculate, based on a target loss function, a loss value of the predicted ECN threshold configuration information compared to the sample ECN threshold configuration information of the current sample.

[0063] In the embodiment of the present application, the target loss function may be a mean square error (MSE). The predicted ECN threshold configuration information and the sample ECN threshold configuration information of the current sample may be substituted into the target loss function to calculate the loss value corresponding to the current sample.

[0064] S303: Update the weight of the LSTM model based on the loss value.

[0065] In the embodiment of the present application, the gradient descent method based on the neural network is used to find the optimal weight parameters of the LSTM model that minimize the objective function. The gradient descent optimization algorithm can select the adam optimizer to improve the learning speed of the traditional gradient descent (optimizer = 'adam'). Each sample in the training data set can be used as the current sample, and the above processing S301 to S303 is iterated until the weight of the LSTM model minimizes the objective loss function.

[0066] S304: Determine the LSTM model whose weight minimizes the target loss function as the ECN threshold prediction model of the network node device.

[0067] In an embodiment of the present application, the LSTM model whose weight minimizes the target loss function is the optimal weight model after the above iterations. The optimal weight model can be verified based on a test data set, and the verified model is determined as the ECN threshold configuration prediction model of the network node device.

[0068] Through the above processing, the ECN threshold prediction model of the network node device can be obtained. In specific implementation, the above processing can be performed before step S201 to obtain the ECN threshold prediction model of the network node device in advance.

[0069] In the above, a method for generating ECN threshold configuration information provided by an embodiment of the present application is described in detail by taking a network node device as an example. In a specific implementation, there may be multiple network node devices in the intelligent lossless network. For each network node device in the intelligent lossless network, the method for generating ECN threshold configuration information provided by the above embodiment can be used to generate its ECN threshold configuration information for each network node device. Since the principle is the same, it will not be repeated here.

[0070] In addition, based on the same inventive concept, the embodiment of the present application also provides a congestion control system, such as Figure 5 shown. Figure 5 Schematic diagram of the structure of the congestion control system provided by some embodiments of the present application. Figure 5 As shown, in some embodiments of the present application, the congestion control system 500 includes: a network node device 501, a collector 502 and an ECN threshold configuration automatic generation component 503.

[0071] The network node device 501 is used to periodically push the traffic status information of the network node device at the current time point to the collector.

[0072] The collector 502 is used to combine the traffic status information of the network node device at the current time point with the traffic status information of the network node device at other time points within a specified time length before the current time point, obtain the current traffic status information sequence of the network node device, and send the traffic status information sequence to the ECN threshold configuration automatic generation component.

[0073] The ECN threshold configuration automatic generation component 503 is used to detect whether the traffic state information sequence is an existing traffic model in the traffic model file based on the traffic model file of the network node device. When the traffic state information sequence is not an existing traffic model in the traffic model file, the traffic state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device and returned to the network node device; wherein, the traffic model file stores multiple existing traffic models, each traffic model is a traffic state information sequence; the ECN threshold prediction model corresponding to the network node device uses the sample traffic state information sequence of the network node device as input, and uses the sample ECN threshold configuration information corresponding to the sample traffic state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow.

[0074] The network node device 504 is used to configure the ECN threshold of its virtual channel based on the current ECN threshold configuration information of the network node device to perform congestion control on its virtual channel.

[0075] In some embodiments of the present application, the network node device 501 specifically adopts the Telemetry push mode to push the traffic status information of the network node device at the current time point to the collector 502, so as to push the traffic status information of the current time point to the collector 502 at high speed and in real time.

[0076] In some embodiments of the present application, the ECN threshold configuration automatic generation component 503 is also used to store the traffic state information sequence as a traffic model and the ECN threshold configuration information predicted by the ECN threshold prediction model as the ECN threshold configuration information corresponding to the traffic model in the traffic model file.

[0077] In some embodiments of the present application, the ECN threshold configuration automatic generation component 503 is further used to: When the traffic state information sequence is an existing traffic model in the traffic model file, the ECN threshold configuration information corresponding to the traffic state information sequence in the traffic model file is determined as the current ECN threshold configuration information of the network node device and returned to the network node device.

[0078] The congestion control system provided by the embodiment of the present application uses the sample flow state information sequence of the network node device as input, and uses the sample ECN threshold configuration information corresponding to the sample flow state information sequence that can take into account both mouse flow and elephant flow as output label, and trains the LSTM model to obtain the ECN threshold prediction model corresponding to the network node device. When the current flow state information sequence of the network node device is received, based on the flow model file of the network node device, it is identified whether the flow state information sequence is a flow model already in the flow model file; when the flow state information sequence is not a flow model already in the flow model file, the flow state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device, and the ECN threshold prediction model of the network node device can dynamically generate suitable ECN threshold configuration information that can take into account both mouse flow and elephant flow for the network node device, so that the network node device can take into account both mouse flow and elephant flow based on the dynamic suitable ECN threshold configuration information, and deal with the burst traffic in the Incast scenario.

[0079] It should be noted that the congestion control system 500 provided in the embodiment of the present application and the method for generating ECN threshold configuration information provided in the aforementioned embodiment are based on the same inventive concept. Regarding the specific processing method in the congestion control system 500, please refer to the corresponding steps in the aforementioned embodiment, which will not be repeated here.

[0080] In addition, Figure 1 Corresponding to the method for generating ECN threshold configuration information shown in FIG. 1 , the embodiment of the present application further provides a device for generating ECN threshold configuration information, such as Figure 6 As shown. Figure 6 As shown, in some embodiments of the present application, the device 600 for generating ECN threshold configuration information includes: The information receiving module 601 is used to receive the current flow state information sequence of the network node device; wherein the flow state information sequence is a time sequence composed of the flow state information of the network node device at each time point within a specified time length ending at the current time point, and the flow state information at each time point includes: the flow state information of each virtual channel of the network node device at that time point; An identification module 602 is used to identify whether the flow state information sequence is an existing flow model in the flow model file based on the flow model file of the network node device; wherein the flow model file stores a plurality of existing flow models, each flow model being a flow state information sequence; The threshold prediction module 603 is used to input the traffic state information sequence into the ECN threshold prediction model corresponding to the network node device to perform ECN threshold configuration information prediction when the traffic state information sequence is not a traffic model already in the traffic model file, and determine the ECN threshold configuration information predicted by the ECN threshold prediction model as the current ECN threshold configuration information of the network node device; wherein the ECN threshold configuration information includes the ECN threshold value of each virtual channel of the network node device; the ECN threshold prediction model corresponding to the network node device uses the sample traffic state information sequence of the network node device as input, and the sample ECN threshold configuration information corresponding to the sample traffic state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow.

[0081] In some embodiments of the present application, the device 600 further includes: The storage module is used to store the traffic state information sequence as a traffic model and the ECN threshold configuration information predicted by the ECN threshold prediction model as the ECN threshold configuration information corresponding to the traffic model in the traffic model file.

[0082] In some embodiments of the present application, the device 600 further includes: The threshold acquisition module is used to determine the ECN threshold configuration information corresponding to the traffic state information sequence in the traffic model file as the current ECN threshold configuration information of the network node device when the traffic state information sequence is a traffic model already in the traffic model file.

[0083] In some embodiments of the present application, the apparatus 600 further includes: a training module of an ECN threshold prediction model, which is used to: Inputting the sample flow state information sequence of the current sample in the training data set of the network node device into the LSTM model to obtain the predicted ECN threshold configuration information output by the LSTM model; the training data set includes multiple samples, each sample includes: the sample flow state information sequence of the network node device and the sample ECN threshold configuration information corresponding to the sample flow state information sequence; Based on the target loss function, calculating a loss value of the predicted ECN threshold configuration information compared to the sample ECN threshold configuration information of the current sample; Updating the weights of the LSTM model based on the loss value; Iterate the above steps until the weight of the LSTM model minimizes the target loss function; The LSTM model whose weight minimizes the target loss function is determined as the ECN threshold prediction model of the network node device.

[0084] In some embodiments of the present application, the apparatus 600 further includes: a training data set acquisition module, configured to: Filter the historical ECN threshold configuration information of the network node device based on the threshold screening condition to obtain the target historical ECN threshold configuration information that can take into account both mouse flow and elephant flow; Determine the target historical ECN threshold configuration information as sample ECN threshold configuration information, and determine the historical traffic state information sequence corresponding to the target historical ECN threshold configuration information as the sample traffic state information sequence corresponding to the sample ECN threshold configuration information; Obtaining a total data set of the network node device based on the sample ECN threshold configuration information and a sample traffic state information sequence corresponding to the sample ECN threshold configuration information; The total data set is cleaned, and a training data set of the node device is obtained based on the cleaned total data set.

[0085] In some embodiments of the present application, the threshold screening condition includes the following conditions: Condition 1: The sum of the PFC threshold values ​​of the virtual channels in the input direction of all the uplink ports of the network node device is greater than the ECN threshold value of the virtual channels in the output direction of the downlink ports of the network node device; Condition 2: The Service cache threshold of the virtual channel of the downlink port output direction of the network node device is greater than the sum of the PFC threshold value of the virtual channel of all uplink ports input direction of the network node device and the Headroom cache threshold of the cache space of the virtual channel of all uplink ports input direction of the network node device; Condition 3: The value of the buffer interval size ECN-PFC Buffer Gap between the ECN threshold and the PFC threshold of each virtual channel of the network node device is set so that the traffic in the virtual channel will not trigger the PFC threshold within the effective time of the ECN threshold.

[0086] The device for generating ECN threshold configuration information provided in the embodiment of the present application can be used as the above Figure 2 The execution subject of the method for generating the ECN threshold configuration information shown can realize Figure 2 The function of the method for generating the ECN threshold configuration information shown is not repeated here because the principle is the same.

[0087] In addition, based on the same inventive concept, an embodiment of the present application also provides an electronic device. Figure 7 is a schematic diagram of the structure of an electronic device 700 provided in some embodiments of the present application. Figure 7 As shown, the electronic device 700 includes a processor 701 and a memory 702 .

[0088] In some embodiments, the memory 702 stores a computer program, and the processor 701 executes the computer program to implement: Receive the current flow status information sequence of the network node device; wherein the flow status information sequence is a time sequence composed of the flow status information of the network node device at each time point within a specified time length ending at the current time point, and the flow status information at each time point includes: the flow status information of each virtual channel of the network node device at that time point; Based on the traffic model file of the network node device, identifying whether the traffic state information sequence is an existing traffic model in the traffic model file; wherein the traffic model file stores a plurality of existing traffic models, each traffic model being a traffic state information sequence; When the traffic state information sequence is not an existing traffic model in the traffic model file, the traffic state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device; wherein the ECN threshold configuration information includes the ECN threshold value of each virtual channel of the network node device; the ECN threshold prediction model corresponding to the network node device uses the sample traffic state information sequence of the network node device as input, and the sample ECN threshold configuration information corresponding to the sample traffic state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow.

[0089] In some embodiments of the present application, the memory 702 stores a computer program, and the processor 701 executes the computer program to further implement: The flow state information sequence is used as a flow model, and the ECN threshold configuration information predicted by the ECN threshold prediction model is used as the ECN threshold configuration information corresponding to the flow model and stored in the flow model file.

[0090] In some embodiments of the present application, the memory 702 stores a computer program, and the processor 701 executes the computer program to further implement: When the traffic state information sequence is an existing traffic model in the traffic model file, the ECN threshold configuration information corresponding to the traffic state information sequence in the traffic model file is determined as the current ECN threshold configuration information of the network node device.

[0091] In some embodiments of the present application, the memory 702 stores a computer program, and the processor 701 executes the computer program to further implement: Inputting the sample flow state information sequence of the current sample in the training data set of the network node device into the LSTM model to obtain the predicted ECN threshold configuration information output by the LSTM model; the training data set includes multiple samples, each sample includes: the sample flow state information sequence of the network node device and the sample ECN threshold configuration information corresponding to the sample flow state information sequence; Based on the target loss function, calculating a loss value of the predicted ECN threshold configuration information compared to the sample ECN threshold configuration information of the current sample; Updating the weights of the LSTM model based on the loss value; Iterate the above steps until the weight of the LSTM model minimizes the target loss function; The LSTM model whose weight minimizes the target loss function is determined as the ECN threshold prediction model of the network node device.

[0092] In some embodiments of the present application, the memory 702 stores a computer program, and the processor 701 executes the computer program to further implement: Filter the historical ECN threshold configuration information of the network node device based on the threshold screening condition to obtain the target historical ECN threshold configuration information that can take into account both mouse flow and elephant flow; Determine the target historical ECN threshold configuration information as sample ECN threshold configuration information, and determine the historical traffic state information sequence corresponding to the target historical ECN threshold configuration information as the sample traffic state information sequence corresponding to the sample ECN threshold configuration information; Obtaining a total data set of the network node device based on the sample ECN threshold configuration information and a sample traffic state information sequence corresponding to the sample ECN threshold configuration information; The total data set is cleaned, and a training data set of the node device is obtained based on the cleaned total data set.

[0093] In some embodiments of the present application, the threshold screening condition includes the following conditions: Condition 1: The sum of the PFC threshold values ​​of the virtual channels in the input direction of all the uplink ports of the network node device is greater than the ECN threshold value of the virtual channels in the output direction of the downlink ports of the network node device; Condition 2: The Service cache threshold of the virtual channel of the downlink port output direction of the network node device is greater than the sum of the PFC threshold value of the virtual channel of all uplink ports input direction of the network node device and the Headroom cache threshold of the cache space of the virtual channel of all uplink ports input direction of the network node device; Condition 3: The value of the buffer interval size ECN-PFC Buffer Gap between the ECN threshold and the PFC threshold of each virtual channel of the network node device is set so that the traffic in the virtual channel will not trigger the PFC threshold within the effective time of the ECN threshold.

[0094] In addition, based on the same inventive concept, one or more embodiments of the present application further provide a storage medium for storing a computer program. In a specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, etc. When the computer program stored in the storage medium is executed by a processor, it can achieve: Receive the current flow status information sequence of the network node device; wherein the flow status information sequence is a time sequence composed of the flow status information of the network node device at each time point within a specified time length ending at the current time point, and the flow status information at each time point includes: the flow status information of each virtual channel of the network node device at that time point; Based on the traffic model file of the network node device, identifying whether the traffic state information sequence is an existing traffic model in the traffic model file; wherein the traffic model file stores a plurality of existing traffic models, each traffic model being a traffic state information sequence; When the traffic state information sequence is not an existing traffic model in the traffic model file, the traffic state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device; wherein the ECN threshold configuration information includes the ECN threshold value of each virtual channel of the network node device; the ECN threshold prediction model corresponding to the network node device uses the sample traffic state information sequence of the network node device as input, and the sample ECN threshold configuration information corresponding to the sample traffic state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow.

[0095] In some embodiments of the present application, when the computer program stored in the storage medium is executed by the processor, it can achieve: The flow state information sequence is used as a flow model, and the ECN threshold configuration information predicted by the ECN threshold prediction model is used as the ECN threshold configuration information corresponding to the flow model and stored in the flow model file.

[0096] In some embodiments of the present application, the memory 702 stores a computer program, and the processor 701 executes the computer program to further implement: When the traffic state information sequence is an existing traffic model in the traffic model file, the ECN threshold configuration information corresponding to the traffic state information sequence in the traffic model file is determined as the current ECN threshold configuration information of the network node device.

[0097] In some embodiments of the present application, when the computer program stored in the storage medium is executed by the processor, it can achieve: Inputting the sample flow state information sequence of the current sample in the training data set of the network node device into the LSTM model to obtain the predicted ECN threshold configuration information output by the LSTM model; the training data set includes multiple samples, each sample includes: the sample flow state information sequence of the network node device and the sample ECN threshold configuration information corresponding to the sample flow state information sequence; Based on the target loss function, calculating a loss value of the predicted ECN threshold configuration information compared to the sample ECN threshold configuration information of the current sample; Updating the weights of the LSTM model based on the loss value; Iterate the above steps until the weight of the LSTM model minimizes the target loss function; The LSTM model whose weight minimizes the target loss function is determined as the ECN threshold prediction model of the network node device.

[0098] In some embodiments of the present application, when the computer program stored in the storage medium is executed by the processor, it can achieve: Filter the historical ECN threshold configuration information of the network node device based on the threshold screening condition to obtain the target historical ECN threshold configuration information that can take into account both mouse flow and elephant flow; Determine the target historical ECN threshold configuration information as sample ECN threshold configuration information, and determine the historical traffic state information sequence corresponding to the target historical ECN threshold configuration information as the sample traffic state information sequence corresponding to the sample ECN threshold configuration information; Obtaining a total data set of the network node device based on the sample ECN threshold configuration information and a sample traffic state information sequence corresponding to the sample ECN threshold configuration information; The total data set is cleaned, and a training data set of the node device is obtained based on the cleaned total data set.

[0099] In some embodiments of the present application, the threshold screening condition includes the following conditions: Condition 1: The sum of the PFC threshold values ​​of the virtual channels in the input direction of all the uplink ports of the network node device is greater than the ECN threshold value of the virtual channels in the output direction of the downlink ports of the network node device; Condition 2: The Service cache threshold of the virtual channel of the downlink port output direction of the network node device is greater than the sum of the PFC threshold value of the virtual channel of all uplink ports input direction of the network node device and the Headroom cache threshold of the cache space of the virtual channel of all uplink ports input direction of the network node device; Condition 3: The value of the buffer interval size ECN-PFC Buffer Gap between the ECN threshold and the PFC threshold of each virtual channel of the network node device is set so that the traffic in the virtual channel will not trigger the PFC threshold within the effective time of the ECN threshold.

[0100] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0101] In short, the above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0102] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0103] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0104] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0105] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

Claims

1. A method for generating ECN threshold configuration information, characterized in that: The method comprises: Receive the current flow status information sequence of the network node device; wherein the flow status information sequence is a time sequence composed of the flow status information of the network node device at each time point within a specified time length ending at the current time point, and the flow status information at each time point includes: the flow status information of each virtual channel of the network node device at that time point; Based on the traffic model file of the network node device, identifying whether the traffic state information sequence is an existing traffic model in the traffic model file; wherein the traffic model file stores a plurality of existing traffic models, each traffic model being a traffic state information sequence; When the traffic state information sequence is not an existing traffic model in the traffic model file, the traffic state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device; wherein the ECN threshold configuration information includes the ECN threshold value of each virtual channel of the network node device; the ECN threshold prediction model corresponding to the network node device uses the sample traffic state information sequence of the network node device as input, and the sample ECN threshold configuration information corresponding to the sample traffic state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow.

2. The method according to claim 1, characterized in that The method further comprises: The flow state information sequence is used as a flow model, and the ECN threshold configuration information predicted by the ECN threshold prediction model is used as the ECN threshold configuration information corresponding to the flow model and stored in the flow model file.

3. The method according to claim 1, characterized in that The method further comprises: When the traffic state information sequence is an existing traffic model in the traffic model file, the ECN threshold configuration information corresponding to the traffic state information sequence in the traffic model file is determined as the current ECN threshold configuration information of the network node device.

4. The method according to claim 1, characterized in that: The ECN threshold prediction model is trained by the following method: Inputting a sample flow state information sequence of a current sample in a training data set of the network node device into an LSTM model to obtain predicted ECN threshold configuration information output by the LSTM model; The training data set includes a plurality of samples, each sample including: a sample flow state information sequence of the network node device and sample ECN threshold configuration information corresponding to the sample flow state information sequence; Based on the target loss function, calculating a loss value of the predicted ECN threshold configuration information compared to the sample ECN threshold configuration information of the current sample; Updating the weights of the LSTM model based on the loss value; Iterate the above steps until the weight of the LSTM model minimizes the target loss function; The LSTM model whose weight minimizes the target loss function is determined as the ECN threshold prediction model of the network node device.

5. The method according to claim 4, characterized in that The training data set is obtained by the following method: Filter the historical ECN threshold configuration information of the network node device based on the threshold screening condition to obtain the target historical ECN threshold configuration information that can take into account both mouse flow and elephant flow; Determine the target historical ECN threshold configuration information as sample ECN threshold configuration information, and determine the historical traffic state information sequence corresponding to the target historical ECN threshold configuration information as the sample traffic state information sequence corresponding to the sample ECN threshold configuration information; Obtaining a total data set of the network node device based on the sample ECN threshold configuration information and a sample traffic state information sequence corresponding to the sample ECN threshold configuration information; The total data set is cleaned, and a training data set of the node device is obtained based on the cleaned total data set.

6. The method according to claim 5, characterized in that The threshold screening conditions include the following conditions: Condition 1: The sum of the PFC threshold values ​​of the virtual channels in the input direction of all the uplink ports of the network node device is greater than the ECN threshold value of the virtual channels in the output direction of the downlink ports of the network node device; Condition 2: The Service cache threshold of the virtual channel of the downlink port output direction of the network node device is greater than the sum of the PFC threshold value of the virtual channel of all uplink ports input direction of the network node device and the Headroom cache threshold of the cache space of the virtual channel of all uplink ports input direction of the network node device; Condition 3: The value of the buffer interval size ECN-PFC Buffer Gap between the ECN threshold and the PFC threshold of each virtual channel of the network node device is set so that the traffic in the virtual channel will not trigger the PFC threshold within the effective time of the ECN threshold.

7. A congestion control system, characterized in that: The system includes: a network node device, a collector, and an ECN threshold configuration automatic generation component; The network node device is used to periodically push the traffic status information of the network node device at the current time point to the collector; The collector is used to combine the flow status information of the network node device at the current time point with the flow status information of the network node device at other time points within a specified time length before the current time point to obtain the current flow status information sequence of the network node device, and send the flow status information sequence to the ECN threshold configuration automatic generation component; The ECN threshold configuration automatic generation component is used to detect whether the flow state information sequence is an existing flow model in the flow model file based on the flow model file of the network node device. When the flow state information sequence is not an existing flow model in the flow model file, the flow state information sequence is input into the ECN threshold prediction model corresponding to the network node device to predict the ECN threshold configuration information, and the ECN threshold configuration information predicted by the ECN threshold prediction model is determined as the current ECN threshold configuration information of the network node device and returned to the network node device; wherein, the flow model file stores a plurality of existing flow models, each flow model is a flow state information sequence; the ECN threshold prediction model corresponding to the network node device uses the sample flow state information sequence of the network node device as input, and uses the sample ECN threshold configuration information corresponding to the sample flow state information sequence as output label, and trains the LSTM model to obtain the sample ECN threshold configuration information, and the sample ECN threshold configuration information is the ECN threshold configuration information that can take into account both mouse flow and elephant flow; The network node device is used to configure the ECN threshold of its virtual channel based on the current ECN threshold configuration information of the network node device to perform congestion control on its virtual channel.

8. The system according to claim 7, characterized in that The network node device specifically adopts the Telemetry push mode to push the traffic status information of the network node device at the current time point to the collector.

9. The system according to claim 7, characterized in that The ECN threshold configuration automatic generation component is also used to store the traffic state information sequence as a traffic model and the ECN threshold configuration information predicted by the ECN threshold prediction model as the ECN threshold configuration information corresponding to the traffic model in the traffic model file.

10. The system according to claim 7, characterized in that The ECN threshold configuration automatic generation component is also used to: When the traffic state information sequence is an existing traffic model in the traffic model file, the ECN threshold configuration information corresponding to the traffic state information sequence in the traffic model file is determined as the current ECN threshold configuration information of the network node device and returned to the network node device.

Images