A method, apparatus, and related equipment for adjusting the operating status of network devices.

Abstract

This application discloses a method, apparatus, and related equipment for adjusting the operating state of a network device, relating to the field of communication technology. A second network device sends first traffic information processed within a first time period to a first network device. The first network device predicts second traffic information corresponding to the second network device within a second time period, which is later than the first time period, based on the first traffic information. The first network device determines the energy consumption corresponding to each energy-saving strategy based on the second traffic information, and identifies the energy-saving strategy corresponding to energy consumption that meets preset conditions as the target energy-saving strategy. The first network device sends the target energy-saving strategy to the second network device, causing the second network device to operate according to the configuration parameters of the target energy-saving strategy to adjust its operating state. The second network device operates according to the configuration parameters corresponding to the energy-saving strategy matching the traffic to be processed, ensuring that the energy consumption of the second network device meets the preset conditions.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus and related equipment for adjusting the operating status of network devices. Background Technology

[0002] With the continuous development of network technology, people's demand for network services is growing rapidly, leading to a rapid increase in the number and scale of network equipment providing these services. This expansion of network scale results in increased network energy consumption, which not only increases network operating costs but also generates significant carbon emissions. Summary of the Invention

[0003] This application provides a method, apparatus, and related equipment for adjusting the operating status of network devices, so as to reduce the energy consumption of network devices by adjusting their operating parameters.

[0004] In a first aspect, this application provides a method for adjusting the operating state of a network device. A first network device receives first traffic information sent by a second network device, the first traffic information indicating the value of traffic processed by the second network device within a first time period. The first network device predicts second traffic information corresponding to the second network device within a second time period based on the first traffic information. The second time period is later than the first time period. The first network device determines the energy consumption value corresponding to each of a plurality of energy-saving strategies based on the second traffic information. Each energy-saving strategy includes configuration parameters corresponding to devices in the second network device. The first network device determines the energy-saving strategy corresponding to the energy consumption value that meets preset conditions as a target energy-saving strategy and sends the target energy-saving strategy to the second network device, so that the second network device operates according to the configuration parameters in the target energy-saving strategy.

[0005] The first network device predicts the second traffic information that the second network device needs to process during a second time period, determines a target energy-saving strategy matching this traffic information, and sends this target energy-saving strategy to the second network device. This causes the second network device to configure the parameters of its internal components according to the target energy-saving strategy matching the traffic to be processed. Therefore, this scheme enables the second network device to consume less energy during low-traffic periods, reducing the overall energy consumption of the network device.

[0006] The preset conditions include the energy consumption value corresponding to the target energy-saving strategy being the minimum among the multiple energy consumption values ​​corresponding to multiple energy-saving strategies, or the energy consumption value corresponding to the target energy-saving strategy being less than or equal to the energy consumption threshold.

[0007] In one possible implementation, the first network device can also determine the planned execution time corresponding to the target energy-saving strategy based on the second traffic information and the target energy-saving strategy, and send the planned execution time to the second network device so that the second network device can execute the target energy-saving strategy within the time period corresponding to the planned execution time.

[0008] In one possible implementation, the first network device may further determine a wake-up value based on the target energy-saving strategy. This wake-up value indicates the conditions under which the second network device terminates the execution of the target energy-saving strategy. The wake-up value may include a traffic threshold and / or a performance threshold. If the wake-up value includes a traffic threshold and the traffic processed by the second network device exceeds the traffic threshold, the execution of the target energy-saving strategy is terminated. If the wake-up value includes a performance threshold and the performance value of the traffic processed by the second network device exceeds the performance threshold, the execution of the target energy-saving strategy is terminated. The traffic threshold may include a throughput threshold, and the performance threshold may include a latency threshold, a jitter threshold, a packet loss rate threshold, etc.

[0009] In one possible implementation, the first network device can use a traffic prediction model to predict the traffic information corresponding to the first network device in a second time period. Specifically, the first network device inputs first traffic information into the traffic prediction model to obtain second traffic information output by the traffic prediction model. This traffic prediction model is trained and generated based on the historical traffic information of the second network device.

[0010] In one possible implementation, the first network device can use an energy consumption prediction model to determine the energy consumption corresponding to each energy-saving strategy. Specifically, for each energy-saving strategy, the first network device inputs the second traffic information and the configuration parameters corresponding to the energy-saving strategy into the energy consumption prediction model to obtain the energy consumption output by the energy consumption prediction model corresponding to the energy-saving strategy. The energy consumption prediction model is generated based on training samples. Each training sample includes traffic information, energy consumption value, and the configuration parameters corresponding to the energy consumption value.

[0011] The energy consumption prediction model corresponds to the equipment type. Before determining the energy consumption corresponding to the energy-saving strategy using the energy consumption prediction model, the first network device can determine the energy consumption prediction model corresponding to the equipment type of the second network device. For example, the network devices may have the same model number.

[0012] In one possible implementation, when the second network device is running according to the target energy-saving strategy, an abnormal situation may occur, causing the second network device to prematurely terminate the execution of the target energy-saving strategy. In this case, the first network device can also receive the actual execution time of the target energy-saving strategy sent by the second network device. The first network device updates the target energy-saving strategy based on the actual execution time. The execution duration corresponding to the actual execution time is less than the execution duration corresponding to the planned execution time.

[0013] In one possible implementation, the first network device can also receive third traffic information sent by the second network device, where the statistical value corresponding to the third traffic information exceeds the wake-up value. The first network device optimizes the traffic prediction model based on the third traffic information. That is, when the statistical value of the second network device exceeds the wake-up value due to the occurrence of sudden traffic information, it can send sudden traffic information to the first network device, so that the first network device can optimize the traffic prediction model based on the sudden traffic information and improve the accuracy of the traffic prediction model.

[0014] In one possible implementation, a first network device sends local training samples to a third network device and receives an energy consumption prediction model from the third network device. The local training samples include historical traffic information, historical energy consumption values, and corresponding configuration parameters of the network devices managed by the first network device. The energy consumption prediction model is trained and generated by the third network device using the local training samples. For example, the first network device could be a controller, and the third network device could be a cloud device.

[0015] In one possible implementation, a first network device generates a first energy consumption prediction model using local training samples, sends the model parameters of the first energy consumption prediction model to a third network device, and receives the energy consumption prediction model sent by the third network device. This energy consumption prediction model is determined by the third network device based on the model parameters of the first energy consumption prediction models sent by multiple first network devices. The local training samples include historical traffic information, historical energy consumption values, and configuration parameters corresponding to the historical energy consumption values ​​of the network devices managed by the first network device. In this implementation, each first network device first performs preliminary training using local training samples to obtain the model parameters of the first energy consumption prediction model and then sends the obtained model parameters to the third network device. The third network device uses the model parameters sent by multiple first network devices to determine the final model parameters corresponding to the energy consumption prediction model, thereby improving both training efficiency and the accuracy of the energy consumption prediction model.

[0016] Secondly, this application provides a method for adjusting the operating state of a network device. A second network device sends first traffic information to a first network device, the first traffic information indicating the value of traffic processed by the second network device within a first time period. The second network device receives a target energy-saving strategy sent by the first network device and applies the configuration parameters corresponding to the target energy-saving strategy. The target energy-saving strategy is determined by the first network device based on second traffic information. The second traffic information is the traffic volume of the second network device within a second time period predicted by the first network device based on the first traffic information, the second time period being later than the first time period. The target energy-saving strategy includes configuration parameters corresponding to devices in the second network device, and the energy consumption corresponding to the target energy-saving strategy meets preset conditions. The preset conditions include the energy consumption value corresponding to the target energy-saving strategy being the minimum value among multiple energy consumption values ​​corresponding to multiple energy-saving strategies, or the energy consumption value corresponding to the target energy-saving strategy being less than or equal to an energy consumption threshold.

[0017] In one possible implementation, the second network device may also receive a planned execution time sent by the first network device. This planned execution time indicates the execution time of the target energy-saving strategy and is determined by the first network device based on the second traffic information and the target energy-saving strategy.

[0018] In one possible implementation, the second network device may also receive a wake-up value sent by the first network device. This wake-up value indicates the conditions under which the second network device terminates the execution of the target power-saving strategy. The wake-up value is determined by the first network device based on the target power-saving strategy.

[0019] In one possible implementation, during the execution of the target energy-saving strategy, if the statistical value of the second network device exceeds the wake-up value, the second network device terminates the execution of the target energy-saving strategy. In this implementation, when the statistical value of the second network device exceeds the wake-up value, it indicates that the traffic currently being processed by the second network device does not match the predicted traffic information, resulting in a sudden traffic surge. To better handle the sudden traffic surge, the second network device can terminate the execution of the target energy-saving strategy in advance.

[0020] In one possible implementation, when the second network device executes the target energy-saving strategy, it can calculate its own corresponding transmission performance value. If the transmission performance value exceeds a transmission performance threshold, the second network device terminates the execution of the target energy-saving strategy.

[0021] In one possible implementation, the second network device sends the actual execution time of the target energy-saving strategy to the first network device, thereby enabling the first network device to know that the second network device will terminate the execution of the target energy-saving strategy ahead of schedule. The execution duration corresponding to the actual execution time is less than the execution duration corresponding to the planned execution time.

[0022] In one possible implementation, the second network device can also send third traffic information to the first network device, enabling the first network device to optimize the traffic prediction model using the third traffic information and improve the prediction accuracy of the traffic prediction model. This third traffic information indicates the traffic that triggers the termination of the target energy-saving strategy, i.e., burst traffic.

[0023] Thirdly, this application provides a network system. The system includes a first network device and a second network device. The first network device is used to perform the method described in the first aspect or any possible implementation thereof. The second network device is used to perform the method described in the second aspect or any possible implementation thereof.

[0024] In one possible implementation, the network system further includes a third network device. The third network device receives local training samples sent by the first network device, trains and generates an energy consumption prediction model based on the local training samples, and sends the energy consumption prediction model back to the first network device. The local training samples include historical traffic information, historical energy consumption values, and configuration parameters corresponding to the historical energy consumption values ​​of the network devices managed by the first network device.

[0025] Fourthly, this application provides a device for adjusting the operating state of a network device. This device is applied to a first network device and includes a receiving unit, a prediction unit, a determining unit, and a transmitting unit. The receiving unit receives first traffic information transmitted by a second network device. The first traffic information indicates the value of traffic processed by the second network device within a first time period. The prediction unit predicts second traffic information corresponding to the second network device within a second time period, where the second time period is later than the first time period, based on the first traffic information. The determining unit determines the energy consumption value corresponding to each of a plurality of energy-saving strategies based on the second traffic information. Each energy-saving strategy includes configuration parameters corresponding to the operation of devices in the second network device according to the energy-saving strategy. The determining unit is further configured to determine the energy-saving strategy corresponding to the energy consumption value that meets preset conditions as a target energy-saving strategy. The transmitting unit transmits the target energy-saving strategy to the second network device, so that the second network device operates according to the configuration parameters in the target energy-saving strategy.

[0026] In one possible implementation, the determining unit is further configured to determine the planned execution time corresponding to the target energy-saving strategy based on the second traffic information and the target energy-saving strategy. The sending unit is further configured to send the planned execution time to the second network device, so that the second network device executes the target energy-saving strategy within the time period corresponding to the planned execution time.

[0027] In one possible implementation, the determining unit is further configured to determine a wake-up value based on the target power-saving strategy. This wake-up value indicates the conditions under which the second network device terminates the execution of the target power-saving strategy. The sending unit is further configured to send the wake-up value to the second network device.

[0028] In one possible implementation, the prediction unit is used to input first traffic information into a traffic prediction model to obtain second traffic information output by the traffic prediction model. The traffic prediction model is trained and generated based on historical traffic information from a second network device.

[0029] In one possible implementation, the determining unit is used to input the second traffic information and the configuration parameters corresponding to the energy-saving strategy into the energy consumption prediction model for each energy-saving strategy, so as to obtain the energy consumption output by the energy consumption prediction model corresponding to the energy-saving strategy. The energy consumption prediction model is generated based on training samples. Each training sample includes traffic information, an energy consumption value, and the configuration parameters corresponding to that energy consumption value.

[0030] In one possible implementation, the determining unit is further configured to determine the energy consumption prediction model based on the device type of the second network device before inputting the second traffic information and the configuration parameters corresponding to the energy-saving strategy into the energy consumption prediction model. The device type corresponds to the energy consumption prediction model.

[0031] In one possible implementation, the device further includes an updating unit. The receiving unit is also configured to receive the actual execution time of the target energy-saving policy sent by the second network device. The updating unit is configured to update the target energy-saving policy based on the actual execution time. The execution duration corresponding to the actual execution time is less than the execution duration corresponding to the planned execution time.

[0032] In one possible implementation, the device further includes an optimization unit. The receiving unit is also configured to receive third traffic information sent by the second network device. The optimization unit is configured to optimize the traffic prediction model based on the third traffic information. The statistical value corresponding to the third traffic information exceeds a wake-up value.

[0033] In one possible implementation, the sending unit is further configured to send local training samples to the third network device. The receiving unit is further configured to receive the energy consumption prediction model sent by the third network device. This energy consumption prediction model is generated by the third network device using the local training samples. The local training samples include historical traffic information, historical energy consumption values, and configuration parameters corresponding to the historical energy consumption values ​​of the network devices managed by the first network device.

[0034] In one possible implementation, the apparatus further includes a generation unit. This generation unit is used to generate a first energy consumption prediction model using local training samples. The sending unit is further used to send the model parameters of the first energy consumption prediction model to a third network device. The receiving unit is further used to receive the energy consumption prediction model sent by the third network device. This energy consumption prediction model is determined by the third network device based on the model parameters of the first energy consumption prediction models sent by multiple first network devices respectively. The local training samples include historical traffic information, historical energy consumption values, and configuration parameters corresponding to the historical energy consumption values ​​of the network devices managed by the first network devices.

[0035] In one possible implementation, the preset conditions include the energy consumption value corresponding to the target energy-saving strategy being the minimum among the multiple energy consumption values ​​corresponding to multiple energy-saving strategies, or the energy consumption value corresponding to the target energy-saving strategy being less than or equal to the energy consumption threshold.

[0036] Fifthly, this application provides a device for adjusting the operating state of a network device. This device is applied to a second network device. The device includes a transmitting unit, a receiving unit, and an application unit. The transmitting unit is used to transmit first traffic information to a first network device. The first traffic information indicates the value of traffic processed by the second network device within a first time period. The receiving unit is used to receive a target energy-saving strategy sent by the first network device. The target energy-saving strategy is determined by the first network device based on second traffic information. The second traffic information is the traffic corresponding to the second network device within a second time period predicted by the first network device based on the first traffic information. The second time period is later than the first time period. The target energy-saving strategy includes configuration parameters corresponding to the operation of devices in the second network device according to the target energy-saving strategy. The energy consumption corresponding to the target energy-saving strategy meets preset conditions. The application unit is used to apply the configuration parameters corresponding to the target energy-saving strategy.

[0037] In one possible implementation, the receiving unit is further configured to receive a planned execution time sent by the first network device. This planned execution time indicates the execution time of the target energy-saving strategy. The planned execution time is determined by the first network device based on the second traffic information and the target energy-saving strategy.

[0038] In one possible implementation, the receiving unit is further configured to receive a wake-up value sent by the first network device. This wake-up value indicates the conditions under which the second network device terminates the execution of the target power-saving strategy. This wake-up value is determined by the first network device based on the target power-saving strategy.

[0039] In one possible implementation, the device further includes a termination unit. The termination unit is used to terminate the execution of the target power-saving strategy when the second network device executes the target power-saving strategy and the statistical value of the second network device exceeds the wake-up value.

[0040] In one possible implementation, the apparatus further includes a determining unit. This determining unit is used to determine the transmission performance value of the second network device when executing the target energy-saving strategy. The terminating unit is used to terminate the execution of the target energy-saving strategy when the transmission performance value exceeds a transmission performance threshold.

[0041] In one possible implementation, the sending unit is further configured to send the actual execution time of the target energy-saving strategy to the first network device. The execution duration corresponding to this actual execution time is less than the execution duration corresponding to the planned execution time.

[0042] In one possible implementation, the sending unit is further configured to send third traffic information to the first network device. This third traffic information indicates the traffic that triggers the termination of the target power-saving strategy.

[0043] Sixthly, this application provides a network device. The network device includes a processor and a memory. The memory stores instructions or computer programs. The processor executes the instructions or computer programs in the memory to cause the network device to perform the network device operating state adjustment method described in the first aspect or any possible implementation thereof, or to perform the network device operating state adjustment method described in the second aspect or any possible implementation thereof.

[0044] In a seventh aspect, this application provides a computer-readable storage medium. The storage medium includes instructions. When executed on a computer, the instructions cause the computer to perform the network device operating state adjustment method described in the first aspect or any possible implementation thereof, or to perform the network device operating state adjustment method described in the second aspect or any possible implementation thereof.

[0045] Eighthly, this application provides a computer program product. The computer program product includes a program or code. When the program or code is run on a computer, it causes the computer to implement the network device operating state adjustment method as described in the first aspect or any possible implementation thereof, or to implement the network device operating state adjustment method as described in the second aspect or any possible implementation thereof.

[0046] The technical solution provided in this application allows a second network device to send traffic information (i.e., first traffic information) processed within a first time period to a first network device. Upon receiving the first traffic information, the first network device predicts the corresponding second traffic information for the second network device within a second time period, where the second time period is later than the first time period. After predicting the second traffic information, the first network device determines the energy consumption corresponding to each of multiple energy-saving strategies based on the second traffic information. Each energy-saving strategy includes the configuration parameters corresponding to the operation of the devices in the second network device according to the energy-saving strategy. After determining the energy consumption corresponding to each energy-saving strategy, the first network device identifies the energy-saving strategy corresponding to the energy consumption that meets preset conditions as the target energy-saving strategy and sends it to the second network device, enabling the second network device to operate according to the configuration parameters of the target energy-saving strategy. In other words, the first network device predicts the second traffic information that the second network device needs to process within the second time period, determines the target energy-saving strategy matching the traffic information, and sends the target energy-saving strategy to the second network device, thereby enabling the second network device to configure the parameters of its internal devices according to the target energy-saving strategy matching the traffic to be processed. Therefore, this solution enables the second network device to consume less energy during periods of low traffic, thus reducing energy consumption. Attached Figure Description

[0047] Figure 1 A flowchart illustrating a method for adjusting the operating status of a network device, as provided in an embodiment of this application;

[0048] Figure 2 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0049] Figure 3 A schematic diagram of a network device operation status adjustment device provided in an embodiment of this application;

[0050] Figure 4 A schematic diagram of another network device operation status adjustment device provided in an embodiment of this application;

[0051] Figure 5 This application provides a schematic diagram of the structure of a network device according to an embodiment of the present application.

[0052] Figure 6 This is a schematic diagram of another network device provided in an embodiment of this application. Detailed Implementation

[0053] To enable those skilled in the art to better understand the solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0054] As network construction continues to expand, the increased operating costs resulting from increased network energy consumption have become a thorny issue for operators. The energy consumption of network equipment is related to the configuration parameters of its components. However, network equipment is typically configured at high settings, leading to continuous high energy consumption.

[0055] Based on this, this application provides a method for adjusting the operating state of a network device. This method selects an energy-saving strategy from multiple energy-saving strategies that matches the traffic to be processed by the network device, and sends the matched energy-saving strategy to the network device, enabling the network device to operate according to the configuration parameters in the energy-saving strategy. By operating according to the configuration parameters matching the traffic to be processed, the network device can handle high traffic normally while reducing energy consumption when traffic decreases.

[0056] To facilitate understanding of the technical solutions provided in the embodiments of this application, the following description will be provided in conjunction with the accompanying drawings.

[0057] See Figure 1 The figure is a flowchart of a method for adjusting the operating status of a network device according to an embodiment of this application. Figure 1 As shown, the method includes:

[0058] S101: The second network device sends the first traffic information to the first network device.

[0059] In this embodiment, the second network device can collect the traffic information it processes within a first time period, i.e., the first traffic information, and send the first traffic information to the first network device. The first traffic information indicates the value of the traffic processed by the second network device within the first time period. Specifically, the first traffic information may include: the sending rate and / or receiving rate of the second network device within the first time period, or the amount of data received and / or sent by the second network device within the first time period, etc. The sending rate may be a statistical value such as the average sending rate or the maximum sending rate. The data amount may be the number of bits, bytes, or packets, etc.

[0060] In practical implementation, the first traffic information sent by the second network device can be device-level traffic information, board-level traffic information, or interface-level traffic information. For example, when the first traffic information includes the traffic information of a certain interface of the second network device, the first network device can adjust the parameters of that interface based on the traffic information of that interface, thereby achieving more accurate adjustment of the interface parameters.

[0061] S102: The first network device receives the first traffic information sent by the second network device, and predicts the second traffic information corresponding to the second network device in the second time period based on the first traffic information.

[0062] After receiving first traffic information from a second network device, the first network device predicts second traffic information for the second network device within a second time period based on this first traffic information. The second time period is later than the first time period. That is, the first network device can predict future traffic trends based on traffic information from historical time periods. Specifically, the first network device can input the first traffic information into a traffic prediction model to obtain the second traffic information output by the model. This traffic prediction model can be a pre-set model; for example, the first network device may receive a traffic prediction model. This received traffic prediction model can be trained by other network devices or configured by an administrator. Alternatively, the traffic prediction model can be pre-trained and generated by the first network device based on the historical traffic information of the second network device. When traffic prediction is needed, the first network device inputs the first traffic information into the traffic prediction model to obtain the second traffic information. Historical traffic information refers to the traffic values ​​processed by the second network device in different time periods within a historical time period.

[0063] The traffic prediction model can be a regression prediction model, a neural network model, etc. When the traffic prediction model is a neural network model, the first network device uses the acquired historical traffic information as training samples. Each training sample includes M traffic sequences and N traffic sequences. Each traffic sequence includes one or more traffic values ​​and the corresponding time for those traffic values. The time corresponding to the N traffic sequences is later than the time corresponding to the M traffic sequences. The N traffic sequences are labels. In each round of iterative training, the first network device can input a training sample into the neural network model, and the neural network model outputs the inference result (predicted traffic sequence / value) for the M traffic sequences in that training sample. Then, the first network device can calculate the loss value between the inference result output by the neural network model and the actual result (label) of that training sample using a corresponding loss function. Then, the first network device can calculate the gradient of the parameters in each network layer of the neural network model based on the calculated loss value. In this way, the first network device can calculate the adjustment value (also known as the parameter update amount) of a parameter during this round of iterative training based on the hyperparameters pre-set in the optimizer and the gradients of parameter changes in each network layer. This adjustment value can be, for example, the product of the gradient and the hyperparameter (such as the learning rate). The first network device can then update the parameter value based on the calculated adjustment values. After multiple training iterations, training stops when the loss value is less than a preset threshold, thus obtaining the traffic prediction model.

[0064] S103: The first network device determines the energy consumption corresponding to each of the multiple energy-saving strategies based on the second traffic information.

[0065] When the first network device predicts that the second network device may process traffic within a second time period, it determines the energy consumption corresponding to each of the multiple energy-saving strategies based on the second traffic information. Each energy-saving strategy includes configuration parameters corresponding to the operation of the devices in the second network device according to that strategy. For example, energy-saving strategies include, but are not limited to, various configuration parameters such as the on / off state of the central processing unit (CPU) core, the core frequency, the on / off state of ports / switches, and the sleep state of ports / switches.

[0066] Among these, multiple energy-saving strategies are pre-configured, and each of these strategies may have some or all of its configuration parameters different. Specifically, these multiple energy-saving strategies may be a set of energy-saving strategies selected from a pre-configured set of energy-saving strategies.

[0067] The first network device can determine the energy consumption corresponding to each energy-saving strategy in the following way: For each energy-saving strategy, the first network device inputs the second traffic information and the energy-saving strategy into the energy consumption prediction model to obtain the energy consumption of the corresponding energy-saving strategy output by the energy consumption prediction model. The energy consumption prediction model is generated based on training samples, and each training sample includes traffic information, energy consumption value, and configuration parameters corresponding to the energy consumption value. That is, the first network device can use the pre-trained energy consumption prediction model to determine the energy consumption corresponding to each energy-saving strategy. The training samples can come from the first network device or from other network devices. Other network devices have the same device type as the first network device, for example, other network devices have the same model as the first network device. A training sample includes traffic information processed by the network device in a historical time period, the energy consumption value corresponding to that historical time period, and the configuration parameters corresponding to that historical time period.

[0068] The training of the energy consumption prediction model can be achieved in the following ways:

[0069] One approach involves a first network device acquiring local training samples and using these samples to train an energy consumption prediction model. The local training samples refer to training samples provided by one or more network devices managed by the first network device. Specifically, the local training samples include training samples provided by one or more network devices managed by the first network device. These network devices have the same or similar device types; for example, they may have the same model number. Network devices of the same device type correspond to one energy consumption prediction model, while network devices of different device types correspond to different energy consumption prediction models. A training sample includes traffic information processed by a network device over a historical time period, the energy consumption value corresponding to that historical time period, and the configuration parameters corresponding to that historical time period. That is, in this implementation, the first network device itself can train the energy consumption prediction model based on the acquired local training samples. The one or more network devices managed by the first network device may include a second network device; that is, the local training samples may include the second network device's historical traffic information, historical energy consumption values, and the configuration parameters corresponding to the historical energy consumption values.

[0070] One approach involves a first network device, after acquiring local training samples, sending these samples to a third network device. This allows the third network device to train an energy consumption prediction model using the received training samples. The first network device receives the energy consumption prediction model sent by the third network device. The local training samples include historical traffic information, historical energy consumption values, and corresponding configuration parameters of the network devices managed by the first network device. It should be noted that the network devices managed by the first network device may include a second network device; that is, the local training samples may include historical traffic information, historical energy consumption values, and corresponding configuration parameters of the second network device. In this implementation, the third network device trains the energy consumption prediction model using the local training samples reported by the first network device and sends the trained model to the first network device. The trained energy consumption prediction model learns the correlation between traffic information, configuration parameters, and energy consumption values. Therefore, when determining the energy consumption of each energy-saving strategy using the energy consumption prediction model, the second traffic information and the configuration parameters corresponding to the energy-saving strategy are input into the model, and the model determines the energy consumption value corresponding to that energy-saving strategy.

[0071] When a third network device corresponds to multiple first network devices, the third network device can receive local training samples sent by the multiple first network devices respectively, thereby using a large number of local training samples to train and generate an energy consumption prediction model, and improve the accuracy of the energy consumption prediction model.

[0072] Another approach involves a first network device training a first energy consumption prediction model using local training samples and sending the model parameters of this first energy consumption prediction model to a third network device. The third network device then determines a second energy consumption prediction model based on the model parameters of the first energy consumption prediction models sent by multiple first network devices. The first network device receives the second energy consumption prediction model from the third network device and uses it to predict the energy consumption of each energy-saving strategy. The local training samples include historical traffic information, historical energy consumption values, and corresponding configuration parameters of the network devices managed by the first network device. In this training method, each of the multiple first network devices managed by the third network device first generates a first energy consumption prediction model using the local training samples and sends the model parameters of this first energy consumption prediction model to the third network device. After receiving the model parameters sent by each of the multiple first network devices, the third network device determines the model parameters of the energy consumption prediction model based on these multiple model parameters, thereby generating the energy consumption prediction model. In other words, in this implementation, the third network device and multiple first network devices determine the energy consumption prediction model through federated learning.

[0073] In this model, network devices of the same type correspond to one energy consumption prediction model, while network devices of different types correspond to different energy consumption prediction models. For each energy consumption prediction model, the first or third network device trains the model based on training samples from network devices of the same type. A training sample includes traffic information processed by a network device of that type during a historical time period, the energy consumption value corresponding to that historical time period, and the configuration parameters corresponding to that historical time period. Based on this, before inputting the second traffic information and the configuration parameters corresponding to the energy-saving strategy into the energy consumption prediction model, the first network device determines the energy consumption prediction model corresponding to the device type of the second network device, and then uses this model to predict the energy consumption corresponding to the energy-saving strategy. Network devices of the same type are, for example, network devices with the same model number.

[0074] The energy consumption prediction model can be a regression prediction model, a neural network model, etc. When the energy consumption prediction model is a neural network, the network device (first network device or third network device) acquires local training samples. Each local training sample includes traffic information processed by the network device in a historical time period, the energy consumption value corresponding to that historical time period, and the configuration parameters corresponding to that historical time period, where the energy consumption value serves as the label. During each round of iterative training, the network device can input the traffic information and configuration parameters from a training sample into the neural network model, and the neural network model outputs the inference result (energy consumption value) for that training sample. Then, the network device can calculate the loss value between the inference result output by the neural network model and the actual result (label) of the training sample using a corresponding loss function. Then, the network device can calculate the gradient of parameter changes in each network layer of the neural network model based on the calculated loss value. In this way, the network device can calculate the adjustment value (also known as the parameter update amount) of a parameter during this round of iterative training based on the hyperparameters pre-set in the optimizer and the gradients of parameter changes in each network layer. This adjustment value can be, for example, the product of the gradient and the hyperparameter (such as the learning rate). The network device can then update the parameter value based on the calculated adjustment value. After multiple training iterations, training stops when the loss value is less than a preset threshold, resulting in an energy consumption prediction model.

[0075] The first network device can be a controller, and the third network device can be a cloud device. The controller and the cloud device can be integrated into the same hardware device, or they can be two independent hardware devices, or they can be two independent virtual devices.

[0076] S104: The first network device determines the energy-saving strategy corresponding to the energy consumption that meets the preset conditions as the target energy-saving strategy.

[0077] After the first network device determines the energy consumption corresponding to each of the multiple energy-saving strategies, it identifies the energy-saving strategy corresponding to the energy consumption that meets preset conditions as the target energy-saving strategy. These preset conditions can be set according to actual application conditions, such as energy consumption values ​​being less than a preset energy consumption threshold, or energy consumption values ​​being at their minimum. The identified target energy-saving strategy may include one or more energy-saving strategies. The first network device can divide the second time period into multiple sub-time periods and determine corresponding energy-saving strategies for each sub-time period. In this case, the target energy-saving strategy includes multiple energy-saving strategies. For example, if the second time period is from 1:00 AM to 7:00 AM, and each sub-time period is divided into two-hour intervals, then 1:00 AM to 3:00 AM corresponds to energy-saving strategy 1, 3:00 AM to 5:00 AM to energy-saving strategy 2, and 5:00 AM to 7:00 AM to energy-saving strategy 3. Therefore, the target energy-saving strategy includes energy-saving strategy 1, energy-saving strategy 2, and energy-saving strategy 3. Alternatively, the first network device can determine energy-saving strategies for multiple second time periods, i.e., determine one target energy-saving strategy for each second time period. For example, the period from 1:00 AM to 7:00 AM is the first second time period, 7:00 AM to 1:00 PM is the second second time period, and 1:00 PM to 7:00 PM is the third second time period. The first network device determines energy-saving strategies for each of these three second time periods. At this time, the target energy-saving strategy may include these three energy-saving strategies.

[0078] S105: The first network device sends the target energy-saving strategy to the second network device.

[0079] The first network device and the second network device can agree on the execution time of the target energy-saving policy. For example, the first network device and the second network device can agree to apply the energy-saving policy at the next full hour after receiving the policy. For example, if the second network device receives the energy-saving policy at 13:30, it will apply the energy-saving policy at 14:00.

[0080] Optionally, the first network device can also determine the planned execution time corresponding to the target energy-saving strategy based on the second traffic information and the target energy-saving strategy. For example, when the target energy-saving strategy includes only one energy-saving strategy, the first network device determines the time period corresponding to the second traffic information as the execution time of the target energy-saving strategy; when the target energy-saving strategy includes multiple energy-saving strategies, the first network device determines the time period corresponding to the traffic information of each energy-saving strategy in the target energy-saving strategy as the execution time of the corresponding energy-saving strategy. The first network device sends the planned execution time to the second network device so that the second network device executes the target energy-saving strategy within the time period corresponding to the planned execution time. The planned execution time may include the start time and end time of the second network device's execution of the target energy-saving strategy, or the planned execution time may include information such as the start time and execution duration. The start time indicates when the second network device begins executing the target energy-saving strategy, and the end time indicates when the second network device stops executing the target energy-saving strategy. The start time is earlier than the end time.

[0081] S106: The second network device receives the target energy-saving policy and applies the configuration parameters corresponding to the target energy-saving policy.

[0082] After the first network device determines the target energy-saving strategy, it sends the target energy-saving strategy to the second network device so that the second network device can apply the configuration parameters corresponding to the target energy-saving strategy.

[0083] When the second network device receives the target energy-saving policy, it can apply the configuration parameters corresponding to the target energy-saving policy according to the preset energy-saving time. Alternatively, the second network device can apply the configuration parameters corresponding to the target energy-saving policy according to the planned execution time sent by the first network device, and not apply the target energy-saving policy during the time period outside the planned execution time. The first network device can send the target energy-saving policy and the planned execution time through the same message, or through different messages.

[0084] Furthermore, the first network device can determine a wake-up value based on the target energy-saving strategy. This wake-up value indicates the conditions under which the second network device terminates the execution of the target energy-saving strategy. The wake-up value can be a traffic threshold; when the traffic processed by the second network device exceeds the traffic threshold, the execution of the target energy-saving strategy is terminated. Alternatively, the wake-up value can be a performance threshold, such as a latency threshold, jitter threshold, or packet loss rate threshold. When the performance value of the second network device when executing the target energy-saving strategy exceeds the performance threshold, the execution of the target energy-saving strategy is terminated. The traffic threshold can be the threshold corresponding to each interface in the second network device, or it can be the threshold for the entire second network device. The performance threshold can also be the threshold for each interface in the second network device, or it can be the threshold for the entire second network device.

[0085] In practical implementation, once the first network device determines the target energy-saving strategy, it can calculate the corresponding wake-up value based on the configuration parameters corresponding to the target energy-saving strategy. For example, if the second network device has 8 ports, and the target energy-saving strategy indicates that ports 1, 3, and 4 are closed, then the first network device calculates the throughput threshold based on the transmission bandwidth of the remaining ports. Alternatively, the association between each energy-saving strategy and its corresponding wake-up value can be pre-configured, and after determining the target energy-saving strategy, the matching wake-up value can be determined based on the above association.

[0086] In some application scenarios, when the second network device executes the target energy-saving strategy, abnormal traffic may occur, causing the statistical value of the second network device to exceed the wake-up threshold. In this case, the second network device will terminate the execution of the target energy-saving strategy prematurely. Simultaneously, the second network device can send the actual execution time of the target energy-saving strategy to the first network device. The execution duration corresponding to this actual execution time is less than the execution duration corresponding to the planned execution time. After the second network device terminates the execution of the target energy-saving strategy prematurely, it can continue operating according to the configuration parameters of each device before the execution of the target energy-saving strategy, or it can continue operating according to the pre-stored default configuration parameters.

[0087] After receiving the actual execution time from the second network device, the first network device can update the target energy-saving policy based on the actual execution time. Updating the target energy-saving policy can include updating the configuration parameters corresponding to the target energy-saving policy. For example, the previous energy-saving policy reduced the CPU frequency by 50%, while the updated policy reduces it by 45%; the previous policy was to disable a certain port, disable a certain switch board, and disable a certain CPU core, while the updated policy is to disable both the port and the switch board.

[0088] In addition, the second network device can also send third traffic information to the first network device, where the traffic value corresponding to this third traffic information exceeds the wake-up threshold. The first network device optimizes its traffic prediction model based on this third traffic information, thereby making the prediction results of the traffic prediction model more accurate. This third traffic information may include statistical values ​​such as time series indicating traffic volume, traffic mean, and traffic variance.

[0089] In one application scenario, the first network device may not send a wake-up value to the second network device. Instead, the second network device determines whether to terminate the execution of the target energy-saving strategy based on the current transmission performance value. Specifically, when the second network device executes the target energy-saving strategy, it determines the transmission performance value. If the transmission performance value is greater than a transmission performance threshold, the second network device terminates the execution of the target energy-saving strategy. The transmission performance value can reflect the transmission quality of the second network device and may include transmission latency, packet loss rate, etc. For example, when the transmission latency of the second network device is greater than a latency threshold, the second network device terminates the execution of the target energy-saving strategy. Another example is when the packet loss rate of the second network device is greater than a packet loss rate threshold. Yet another example is when the packet loss rate of the second network device is greater than a preset packet loss rate threshold and the transmission latency is also greater than a preset latency threshold, the second network device terminates the execution of the target energy-saving strategy. After terminating the execution of the target energy-saving strategy, the second network device sends the actual execution time of the target energy-saving strategy to the first network device so that the first network device can be aware of the early termination of the target energy-saving strategy. The second network device can also send third traffic information to the first network device, which indicates the traffic that triggers the termination of the target energy-saving strategy, so that the first network device can optimize the traffic prediction model based on the third traffic information.

[0090] As can be seen, the second network device can report the traffic information it processed within a first time period, i.e., the first traffic information, to the first network device. Upon receiving the first traffic information, the first network device predicts the corresponding second traffic information for the second network device within a second time period, where the second time period is later than the first time period. After predicting the second traffic information, the first network device determines the energy consumption corresponding to each of multiple energy-saving strategies based on the second traffic information. Each energy-saving strategy includes the configuration parameters of the devices in the second network device according to the energy-saving strategy's operation. After determining the energy consumption corresponding to each energy-saving strategy, the first network device identifies the energy-saving strategy corresponding to the energy consumption that meets preset conditions as the target energy-saving strategy and sends it to the second network device, enabling the second network device to operate according to the configuration parameters of the target energy-saving strategy. In other words, the first network device predicts the second traffic information processed by the second network device within a second time period, determines the target energy-saving strategy matching that traffic information, and sends the target energy-saving strategy to the second network device, thereby enabling the second network device to configure the parameters of its internal devices according to the target energy-saving strategy matching the traffic to be processed. Therefore, the second network device does not need to maintain a high configuration at all times, but can flexibly apply a configuration that matches the traffic to be processed, reducing energy consumption during low traffic periods.

[0091] Figure 2 This is a schematic diagram illustrating an application scenario provided in an embodiment of this application. See also... Figure 2 The illustration shows an application scenario that includes cloud devices, an analyzer, a controller, and network devices. Cloud devices can be deployed in public clouds, edge clouds, or distributed clouds. Network devices can include forwarding devices and terminal devices within the network. The controller collects data from the network devices and sends it to the analyzer, enabling the analyzer to predict the traffic information processed by the network devices based on the collected data, thereby determining energy-saving strategies and the timing for executing these strategies. The analyzer, through the controller, sends the determined energy-saving strategies and corresponding execution times to the network devices. The network devices then apply the configuration parameters corresponding to the energy-saving strategies, thereby reducing the energy consumption of the network devices.

[0092] exist Figure 2 In the illustrated application scenario, the controller can collect training samples and send them to a cloud device via an analyzer. The cloud device then uses these training samples to train an energy consumption prediction model. A training sample includes traffic information of a network device over a historical time period, the corresponding energy consumption value for that period, and configuration parameters for that period. The cloud device trains an energy consumption prediction model for that device type based on multiple training samples from network devices of the same type and sends this model to the analyzer. In practical applications, the controller collects first traffic information from the network device during the first time period and sends it to the analyzer. The analyzer uses this first traffic information and the traffic prediction model to obtain second traffic information for the network device during the second time period. The analyzer inputs the second traffic information and configuration parameters corresponding to an energy-saving strategy into the energy consumption prediction model to determine the energy consumption corresponding to that strategy. It then identifies the energy-saving strategy that meets preset conditions as the target energy-saving strategy. Simultaneously, the analyzer can also determine the planned execution time and wake-up value corresponding to the target energy-saving strategy and send these parameters to the network device. The strategy execution module in the network device executes the target energy-saving strategy according to the planned execution time to reduce energy consumption. During the execution of the target energy-saving strategy, the wake-up detection module in the network device determines whether the current traffic being processed by the network device exceeds the wake-up threshold. If so, it sends an exception message to the strategy execution module, causing the strategy execution module to terminate the execution of the target energy-saving strategy. The network device can also send the actual execution time and abnormal traffic information to the analyzer through the controller, allowing the analyzer to update the energy-saving strategy and traffic prediction model based on the actual execution time and abnormal traffic information.

[0093] The analyzer and controller can be the same physical device or two separate physical devices. Alternatively, the analyzer and cloud device can be the same physical device or two separate physical devices. In practical applications, the cloud device can collect training samples sent by multiple analyzers to train the energy consumption prediction model using a large number of training samples, thereby improving the accuracy of the energy consumption prediction model.

[0094] Based on the above method embodiments, this application also provides a device for adjusting the operating status of a network device, which will be described below in conjunction with the accompanying drawings.

[0095] See Figure 3 This figure is a schematic diagram of a network device operating status adjustment device 300 provided in an embodiment of this application. This device 300 can be used to implement the functions of the aforementioned first network device. Figure 3 As shown, the device 300 includes a receiving unit 301, a prediction unit 302, a determination unit 303, and a transmitting unit 304.

[0096] The receiving unit 301 is used to receive first traffic information sent by the second network device. The first traffic information indicates the value of traffic processed by the second network device within a first time period.

[0097] The prediction unit 302 is used to predict the second traffic information corresponding to the second network device in a second time period based on the first traffic information. The second time period is later than the first time period.

[0098] The determining unit 303 is used to determine the energy consumption value corresponding to each of the multiple energy-saving strategies based on the second traffic information. Each energy-saving strategy includes the configuration parameters corresponding to the operation of the devices in the second network device according to the energy-saving strategy.

[0099] The determining unit 303 is also used to determine the energy-saving strategy corresponding to the energy consumption value that meets the preset conditions as the target energy-saving strategy.

[0100] The sending unit 304 is used to send the target energy-saving policy to the second network device so that the second network device can operate according to the configuration parameters in the target energy-saving policy.

[0101] Optionally, the determining unit 303 is further configured to determine the planned execution time corresponding to the target energy-saving strategy based on the second traffic information and the target energy-saving strategy. The sending unit 304 is further configured to send the planned execution time to the second network device, so that the second network device executes the target energy-saving strategy within the time period corresponding to the planned execution time.

[0102] Optionally, the determining unit 303 is further configured to determine a wake-up value based on the target power-saving strategy. The wake-up value indicates the conditions under which the second network device terminates the execution of the target power-saving strategy. The sending unit 304 is further configured to send the wake-up value to the second network device.

[0103] Optionally, the prediction unit 302 is used to input the first traffic information into the traffic prediction model to obtain the second traffic information output by the traffic prediction model. The traffic prediction model is trained and generated based on the historical traffic information of the second network device.

[0104] Optionally, the determining unit 303 is configured to, for each energy-saving strategy, input the second traffic information and the configuration parameters corresponding to the energy-saving strategy into the energy consumption prediction model to obtain the energy consumption output by the energy consumption prediction model corresponding to the energy-saving strategy. The energy consumption prediction model is generated based on training samples. Each training sample includes traffic information of a network device within a historical time period, the energy consumption value of the network device corresponding to that historical time period, and the configuration parameters of the network device corresponding to that historical time period. The network device is a second network device, or a network device of the same device type as the second network device.

[0105] Optionally, the determining unit 303 is further configured to determine the energy consumption prediction model based on the device type of the second network device before inputting the second traffic information and the configuration parameters corresponding to the energy-saving strategy into the energy consumption prediction model. The device type corresponds to the energy consumption prediction model.

[0106] Optionally, the device 300 further includes an updating unit. The receiving unit 301 is further configured to receive the actual execution time of the target energy-saving strategy sent by the second network device. The execution duration corresponding to the actual execution time is less than the execution duration corresponding to the planned execution time of the target energy-saving measurement. The updating unit is configured to update the target energy-saving strategy based on the actual execution time.

[0107] Optionally, the device 300 further includes an optimization unit. The receiving unit 301 is also configured to receive third traffic information sent by the second network device. The statistical value corresponding to the third traffic information exceeds the wake-up value. The optimization unit is configured to optimize the traffic prediction model based on the third traffic information.

[0108] Optionally, the sending unit 304 is further configured to send training samples to the third network device. A training sample includes traffic information of a network device managed by the first network device within a historical time period, the energy consumption value of the network device corresponding to that historical time period, and the configuration parameters of the network device corresponding to that historical time period. The receiving unit 301 is further configured to receive an energy consumption prediction model sent by the third network device. This energy consumption prediction model is generated by the third network device using the aforementioned training samples.

[0109] Optionally, the device 300 further includes a generation unit. This generation unit is used to generate a first energy consumption prediction model using training samples. The sending unit 304 is further used to send the model parameters of the first energy consumption prediction model to a third network device. The receiving unit 301 is further used to receive the energy consumption prediction model sent by the third network device. This energy consumption prediction model is determined by the third network device based on the model parameters of the first energy consumption prediction models sent by multiple first network devices respectively.

[0110] Optionally, the preset conditions include the energy consumption value corresponding to the target energy-saving strategy being the minimum among the multiple energy consumption values ​​corresponding to multiple energy-saving strategies, or the energy consumption value corresponding to the target energy-saving strategy being less than or equal to the energy consumption threshold.

[0111] It should be noted that the implementation of each unit in this embodiment can be found in the relevant descriptions in the above method embodiments, and will not be repeated here.

[0112] See Figure 4 This figure is a schematic diagram of a network device operation status adjustment device 400 provided in an embodiment of this application. The device 400 can be used to implement the functions of a second network device. The device 400 includes a transmitting unit 401, a receiving unit 402, and an application unit 403.

[0113] The sending unit 401 is used to send first traffic information to the first network device. The first traffic information indicates the value of traffic processed by the second network device within a first time period.

[0114] The receiving unit 402 is used to receive a target energy-saving strategy sent by the first network device. This target energy-saving strategy is determined by the first network device based on second traffic information. The second traffic information is the traffic volume of the second network device predicted by the first network device within a second time period, based on the first traffic information. The second time period is later than the first time period. The target energy-saving strategy includes the configuration parameters corresponding to the operation of the devices in the second network device according to the target energy-saving strategy. The energy consumption corresponding to the target energy-saving strategy meets preset conditions.

[0115] Application unit 403 is used to configure the parameters corresponding to the target energy-saving strategy.

[0116] Optionally, the receiving unit 402 is further configured to receive the planned execution time sent by the first network device. The planned execution time indicates the execution time of the target energy-saving strategy. This planned execution time is determined by the first network device based on the second traffic information and the target energy-saving strategy.

[0117] Optionally, the receiving unit 402 is further configured to receive a wake-up value sent by the first network device. This wake-up value indicates the conditions under which the second network device terminates the execution of the target power-saving strategy. This wake-up value is determined by the first network device based on the target power-saving strategy.

[0118] Optionally, the device 400 further includes a termination unit. This termination unit is used to terminate the execution of the target power-saving strategy when the second network device executes the target power-saving strategy and the statistical value of the second network device exceeds the wake-up value.

[0119] Optionally, the device 400 further includes a determining unit. This determining unit is used to determine a transmission performance value when the second network device executes the target energy-saving strategy. The terminating unit is used to terminate the execution of the target energy-saving strategy when the transmission performance value is greater than a transmission performance threshold.

[0120] Optionally, the sending unit 401 is further configured to send the actual execution time of the target energy-saving strategy to the first network device. The execution duration corresponding to the actual execution time is less than the execution duration corresponding to the planned execution time.

[0121] Optionally, the sending unit 401 is further configured to send third traffic information to the first network device. The third traffic information indicates the traffic that triggers the termination of the target energy-saving strategy.

[0122] It should be noted that the implementation of each unit in this embodiment can be found in the relevant descriptions in the above method embodiments, and will not be repeated here.

[0123] Figure 5 This is a schematic diagram of the structure of a network device provided in an embodiment of this application. The network device may be, for example, the first network device, the second network device, or the third network device described in the above method embodiments, or it may be... Figure 3 The device implementation of apparatus 300 in the illustrated embodiment may also be... Figure 4 The device implementation of apparatus 400 in the illustrated embodiment.

[0124] The network device 500 includes a processor 510, a communication interface 520, and a memory 530. The network device 500 may have one or more processors 510. Figure 5 Taking a processor as an example. In this embodiment, the processor 510, communication interface 520, and memory 530 can be connected via a bus system or other means, wherein, Figure 5 Taking the connection between China and Israel via the 540 bus system as an example.

[0125] Processor 510 may be a CPU, a network processor (NP), or a combination of a CPU and an NP. Processor 510 may further include hardware chips. These hardware chips may be application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. The PLDs may be complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), generic array logic (GALs), or any combination thereof.

[0126] The memory 530 may include volatile memory, such as random-access memory (RAM); the memory 530 may also include non-volatile memory, such as flash memory, hard disk drive (HDD), or solid-state drive (SSD); the memory 530 may also include a combination of the above types of memory.

[0127] Optionally, the memory 530 stores an operating system and programs, executable modules, or data structures, or subsets thereof, or extended sets thereof. The programs may include various operation instructions for implementing various operations. The operating system may include various system programs for implementing various basic services and handling hardware-based tasks. The processor 510 can read the programs from the memory 530 to implement the methods provided in the embodiments of this application.

[0128] The memory 530 can be a storage device in the network device 500, or it can be a storage device independent of the network device 500.

[0129] The bus system 540 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus system 540 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0130] Figure 6 This is a schematic diagram of the structure of a network device 600 provided in an embodiment of this application. This network device may be, for example, the first network device, the second network device, or the third network device in the method embodiment, or it may be... Figure 3 The device implementation of the apparatus 300 in the embodiment can also be... Figure 4 The device implementation of apparatus 400 in the embodiment.

[0131] Network device 600 includes: main control board 610 and interface board 630.

[0132] The main control board 610, also known as the main processing unit (MPU) or route processor card, is used to control and manage the various components in the network device 600, including route calculation, device management, device maintenance, and protocol processing. The main control board 610 includes a central processing unit 611 and a memory 612.

[0133] Interface board 630, also known as a line processing unit (LPU), line card, or service board, provides various service interfaces and enables packet forwarding. Service interfaces include, but are not limited to, Ethernet interfaces, POS (Packet over SONET / SDH) interfaces, etc. Ethernet interfaces include, for example, Ethernet ports, Gigabit Ethernet ports, and Flexible Ethernet Clients (FlexE Clients). Interface board 630 includes: a central processing unit 631, a network processor 632, a forwarding table entry memory 634, and a physical interface card (PIC) 633.

[0134] The central processing unit 631 on the interface board 630 is used to control and manage the interface board 630 and communicate with the central processing unit 611 on the main control board 610.

[0135] The network processor 632 is used to implement packet forwarding processing. The network processor 632 can be in the form of a forwarding chip. Specifically, uplink packet processing includes: processing of the packet ingress interface, forwarding table lookup; downlink packet processing includes forwarding table lookup, etc.

[0136] Physical interface card 633 is used to implement physical layer interfacing functions. Raw traffic enters interface board 630 through this card, and processed packets are sent out from the physical interface card 633. Physical interface card 633 includes at least one physical interface, also called a physical port. Physical interface card 633, also called a daughter card, can be installed on interface board 630 and is responsible for converting photoelectric signals into packets, performing validity checks on the packets, and forwarding them to network processor 632 for processing. In some embodiments, the central processing unit 631 of interface board 603 can also perform the functions of network processor 632, such as implementing software forwarding based on a general-purpose CPU, thus eliminating the need for network processor 632 in physical interface card 633.

[0137] Optionally, the network device 600 includes multiple interface boards. For example, the network device 600 also includes an interface board 640, which includes a central processing unit 641, a network processor 642, a forwarding table entry memory 644, and a physical interface card 643.

[0138] Optionally, the network device 600 also includes a switching fabric board 620. The switching fabric board 620 can also be referred to as a switch fabric unit (SFU). When the network device has multiple interface boards 630, the switching fabric board 620 is used to complete data exchange between the interface boards. For example, interface boards 630 and 640 can communicate through the switching fabric board 620.

[0139] The main control board 610 and the interface board 630 are coupled. For example, the main control board 610, interface board 630, interface board 640, and switching network board 620 communicate with each other via a system bus connected to the system backplane. In one possible implementation, an inter-process communication (IPC) channel is established between the main control board 610 and the interface board 630, and the main control board 610 and the interface board 630 communicate with each other through the IPC channel.

[0140] Logically, network device 600 includes a control plane and a forwarding plane. The control plane includes a main control board 610 and a central processing unit 631, while the forwarding plane includes various components that perform forwarding, such as a forwarding table entry memory 634, a physical interface card 633, and a network processor 632. The control plane performs functions such as router operation, generating forwarding tables, processing signaling and protocol messages, and configuring and maintaining the device's status. The control plane distributes the generated forwarding tables to the forwarding plane. In the forwarding plane, the network processor 632 uses the forwarding tables distributed by the control plane to look up and forward messages received by the physical interface card 633. The forwarding tables distributed by the control plane can be stored in the forwarding table entry memory 634. In some embodiments, the control plane and the forwarding plane can be completely separated and not on the same device.

[0141] It should be understood that the operation on interface board 640 in this embodiment is the same as the operation on interface board 630, and will not be described again for the sake of simplicity. It should be understood that the network device 600 in this embodiment can correspond to the network devices in the above method embodiments. The main control board 610, interface board 630 and / or interface board 640 in the network device 600 can implement the various steps in the above method embodiments, and will not be described again for the sake of simplicity.

[0142] It should be understood that a network device may have one or more main control boards, including a primary and a backup main control board. Similarly, it may have one or more interface boards; the more powerful the network device's data processing capabilities, the more interface boards it provides. Each interface board may also have one or more physical interface cards. A switching board may or may not exist; multiple switching boards can share the load and provide redundancy. In a centralized forwarding architecture, network devices may not need a switching board, as the interface boards handle the entire system's business data processing. In a distributed forwarding architecture, a network device can have at least one switching board, enabling data exchange between multiple interface boards and providing high-capacity data exchange and processing capabilities. Therefore, the data access and processing capabilities of a distributed architecture network device are greater than those of a centralized architecture device. Alternatively, network devices can also consist of a single board, without a switching board. The functions of the interface board and the main control board are integrated on this one board. In this case, the central processing unit (CPU) on the interface board and the CPU on the main control board can be combined into a single CPU to perform the combined functions. This type of device has lower data exchange and processing capabilities (e.g., low-end switches or routers). The specific architecture adopted depends on the specific network deployment scenario.

[0143] In some possible embodiments, the network device described above can be implemented as a virtualized device. For example, a virtualized device can be a virtual machine (VM) running a program for sending messages, deployed on hardware (e.g., a physical server). A virtual machine refers to a complete computer system simulated by software, possessing full hardware system functionality and running in a completely isolated environment. A virtual machine can be configured as a network device. For example, a network device can be implemented based on a general-purpose physical server combined with network functions virtualization (NFV) technology. The network device can be a virtual host, virtual router, or virtual switch. Those skilled in the art can virtualize a network device with the above-described functions on a general-purpose physical server using NFV technology by reading this application; further details are omitted here.

[0144] It should be understood that the network devices of the various product forms described above have any of the functions of the network devices in the above method embodiments, which will not be elaborated here.

[0145] This application also provides a chip, including a processor and an interface circuit. The interface circuit is used to receive instructions and transmit them to the processor. The processor, for example, may be... Figure 3 One specific implementation of the adjustment device 300 shown can be used to execute the above-described method for adjusting the operating state of a network device. The processor is coupled to a memory, which stores programs or instructions. When the processor executes the programs or instructions, the chip system implements the method described in any of the above-described method embodiments.

[0146] Optionally, the chip system may contain one or more processors. These processors can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0147] Optionally, the chip system may contain one or more memories. The memory may be integrated with the processor or disposed separately from it; this application does not limit this. For example, the memory may be a non-transient processor, such as a read-only memory (ROM), which may be integrated with the processor on the same chip or disposed separately on different chips. This application does not specifically limit the type of memory or the arrangement of the memory and processor.

[0148] For example, the chip system can be, for instance, an FPGA, an ASIC, a system-on-chip (SoC), a CPU, an NP, a digital signal processor (DSP), a microcontroller unit (MCU), a PLD, or other integrated chips.

[0149] This application also provides a computer-readable storage medium, including instructions or a computer program, which, when run on a computer, causes the computer to execute the network device operating state adjustment method provided in the above embodiments.

[0150] This application also provides a computer program product containing instructions or computer programs, which, when run on a computer, causes the computer to execute the network device operation state adjustment method provided in the above embodiments.

[0151] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0152] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0153] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical business division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0154] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] Furthermore, the various business units in the embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software business unit.

[0156] If the integrated unit is implemented as a software business unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0157] Those skilled in the art will recognize that, in one or more of the examples above, the services described in this application can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these services can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of computer programs from one place to another. Storage media can be any available medium accessible to general-purpose or special-purpose computers.

[0158] The above specific embodiments further illustrate the purpose, technical solution and beneficial effects of this application. It should be understood that the above are only specific embodiments of this application.

[0159] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for adjusting the operating status of a network device, characterized in that, The method includes: The first network device receives first traffic information sent by the second network device, wherein the first traffic information indicates the value of traffic processed by the second network device within a first time period; The first network device predicts the second network device's corresponding second traffic information within a second time period based on the first traffic information, where the second time period is later than the first time period; The first network device determines the energy consumption value corresponding to each of the multiple energy-saving strategies based on the second traffic information. Each energy-saving strategy includes the configuration parameters corresponding to the devices in the second network device when they are running according to the energy-saving strategy. The first network device determines the energy-saving strategy corresponding to the energy consumption value that meets the preset conditions as the target energy-saving strategy, and sends the target energy-saving strategy to the second network device so that the second network device operates according to the configuration parameters in the target energy-saving strategy.

2. The method according to claim 1, characterized in that, The method further includes: The first network device determines the planned execution time corresponding to the target energy-saving strategy based on the second traffic information and the target energy-saving strategy; The first network device sends the planned execution time to the second network device, so that the second network device executes the target energy-saving strategy within the time period corresponding to the planned execution time.

3. The method according to claim 1 or 2, characterized in that, The method further includes: The first network device determines a wake-up value based on the target power-saving strategy, and the wake-up value indicates the conditions under which the second network device terminates the execution of the target power-saving strategy; The first network device sends the wake-up value to the second network device.

4. The method according to any one of claims 1-3, characterized in that, The first network device predicts the second traffic information corresponding to the second network device in the second time period based on the first traffic information, including: The first network device inputs the first traffic information into the traffic prediction model to obtain the second traffic information output by the traffic prediction model, which is trained and generated based on the historical traffic information of the second network device.

5. The method according to any one of claims 1-4, characterized in that, The first network device determines the energy consumption corresponding to each of the multiple energy-saving strategies based on the second traffic information, including: For each energy-saving strategy, the first network device inputs the second traffic information and the energy-saving strategy into the energy consumption prediction model to obtain the energy consumption corresponding to the energy-saving strategy output by the energy consumption prediction model. The energy consumption prediction model is generated based on training samples, and each training sample includes traffic information, energy consumption value, and configuration parameters corresponding to the energy consumption value.

6. The method according to claim 5, characterized in that, Before the first network device inputs the second traffic information and the energy-saving strategy into the energy consumption prediction model, the method further includes: The first network device determines the energy consumption prediction model based on the device type of the second network device, and the device type corresponds to the energy consumption prediction model.

7. The method according to claim 2, characterized in that, The method further includes: The first network device receives the actual execution time of the target energy-saving strategy sent by the second network device, wherein the execution duration corresponding to the actual execution time is less than the execution duration corresponding to the planned execution time; The first network device updates the target energy-saving strategy based on the actual execution time.

8. The method according to claim 4, characterized in that, The method further includes: The first network device receives third traffic information sent by the second network device, wherein the statistical value corresponding to the third traffic information exceeds the wake-up value; The first network device optimizes the traffic prediction model based on the third traffic information.

9. The method according to claim 5, characterized in that, The method further includes: The first network device sends local training samples to the third network device. The local training samples include historical traffic information, historical energy consumption values, and configuration parameters corresponding to the historical energy consumption values ​​of the network devices managed by the first network device. The first network device receives the energy consumption prediction model sent by the third network device, the energy consumption prediction model being trained and generated by the third network device using the local training samples.

10. The method according to claim 5, characterized in that, The method further includes: The first network device generates a first energy consumption prediction model using local training samples and sends the model parameters of the first energy consumption prediction model to the third network device. The local training samples include historical traffic information, historical energy consumption values, and configuration parameters corresponding to the historical energy consumption values ​​of the network devices managed by the first network device. The first network device receives the energy consumption prediction model sent by the third network device. The energy consumption prediction model is determined by the third network device based on the model parameters of the first energy consumption prediction models sent by multiple first network devices respectively.

11. The method according to any one of claims 1-10, characterized in that, The preset conditions include the energy consumption value corresponding to the target energy-saving strategy being the minimum among the multiple energy consumption values ​​corresponding to the multiple energy-saving strategies, or the energy consumption value corresponding to the target energy-saving strategy being less than or equal to the energy consumption threshold.

12. A method for adjusting the operating status of a network device, characterized in that, The method includes: The second network device sends first traffic information to the first network device, the first traffic information indicating the value of traffic processed by the second network device within a first time period; The second network device receives a target energy-saving strategy sent by the first network device. The target energy-saving strategy is determined by the first network device based on second traffic information. The second traffic information is the traffic of the second network device in a second time period predicted by the first network device based on the first traffic information. The second time period is later than the first time period. The target energy-saving strategy includes the configuration parameters of the devices in the second network device when they run according to the target energy-saving strategy. The energy consumption corresponding to the target energy-saving strategy meets preset conditions. The second network device applies the configuration parameters corresponding to the target energy-saving strategy.

13. The method according to claim 12, characterized in that, The method further includes: The second network device receives a planned execution time sent by the first network device. The planned execution time indicates the execution time of the target energy-saving strategy. The planned execution time is determined by the first network device based on the second traffic information and the target energy-saving strategy.

14. The method according to claim 12 or 13, characterized in that, The method further includes: The second network device receives a wake-up value sent by the first network device. The wake-up value indicates the conditions under which the second network device terminates the execution of the target power-saving strategy. The wake-up value is determined by the first network device according to the target power-saving strategy.

15. The method according to claim 14, characterized in that, The method further includes: When the second network device executes the target power saving policy and the statistical value of the second network device exceeds the wake-up value, the second network device terminates the execution of the target power saving policy.

16. The method according to claim 12 or 13, characterized in that, The method further includes: When the second network device executes the target energy-saving strategy, the second network device determines the transmission performance value; When the transmission performance value is greater than the transmission performance threshold, the second network device terminates the execution of the target energy-saving strategy.

17. The method according to claim 15 or 16, characterized in that, The method further includes: The second network device sends the actual execution time of the target energy-saving strategy to the first network device. The execution duration corresponding to the actual execution time is less than the execution duration corresponding to the planned execution time. The planned execution time is determined by the first network device based on the second traffic information and the target energy-saving strategy.

18. The method according to any one of claims 15-17, characterized in that, The method further includes: The second network device sends third traffic information to the first network device, the third traffic information indicating the traffic that triggers the termination of the target energy-saving strategy.

19. A device for adjusting the operating status of a network device, characterized in that, The device is applied to a first network device and includes: A receiving unit is configured to receive first traffic information sent by a second network device, wherein the first traffic information indicates the value of traffic processed by the second network device within a first time period. The prediction unit is used to predict the second traffic information corresponding to the second network device in a second time period based on the first traffic information, wherein the second time period is later than the first time period; The determining unit is configured to determine the energy consumption value corresponding to each of the multiple energy-saving strategies based on the second traffic information, wherein each energy-saving strategy includes the configuration parameters corresponding to the device in the second network device when it is running according to the energy-saving strategy; The determining unit is further configured to determine the energy-saving strategy corresponding to the energy consumption value that meets the preset conditions as the target energy-saving strategy; The sending unit is configured to send the target energy-saving strategy to the second network device, so that the second network device operates according to the configuration parameters in the target energy-saving strategy.

20. A device for adjusting the operating status of a network device, characterized in that, The device is applied to a second network device and includes: A sending unit is configured to send first traffic information to a first network device, wherein the first traffic information indicates the value of traffic processed by the second network device within a first time period; A receiving unit is configured to receive a target energy-saving strategy sent by the first network device. The target energy-saving strategy is determined by the first network device based on second traffic information. The second traffic information is the traffic of the second network device in a second time period predicted by the first network device based on the first traffic information. The second time period is later than the first time period. The target energy-saving strategy includes the configuration parameters of the devices in the second network device when they run according to the target energy-saving strategy. The energy consumption corresponding to the target energy-saving strategy meets preset conditions. The application unit is used to apply the configuration parameters corresponding to the target energy-saving strategy.

21. A network system, characterized in that, The system includes: a first network device and a second network device; The first network device is configured to perform the method according to any one of claims 1-11; The second network device is configured to perform the method according to any one of claims 12-18.

22. The system according to claim 21, characterized in that, The system also includes: a third network device; The third network device is used to receive local training samples sent by the first network device. The local training samples include historical traffic information, historical energy consumption values, and configuration parameters corresponding to the historical energy consumption values ​​of the network devices managed by the first network device. The third network device is further configured to train and generate an energy consumption prediction model based on the local training samples, and send the energy consumption prediction model to the first network device.

23. A network device, characterized in that, The network device includes: a processor and a memory; The memory is used to store instructions or computer programs; The processor is configured to execute the instructions or computer program in the memory to cause the network device to perform the network device operating state adjustment method according to any one of claims 1-11, or to perform the network device operating state adjustment method according to any one of claims 12-18.

24. A computer-readable storage medium, characterized in that, The instructions, when executed on a computer, cause the computer to perform the network device operating state adjustment method according to any one of claims 1-11, or to perform the network device operating state adjustment method according to any one of claims 12-18.

25. A computer program product, characterized in that, The computer program product includes a program or code that, when run on a computer, implements the network device operating state adjustment method as described in any one of claims 1 to 11, or implements the network device operating state adjustment method as described in any one of claims 12 to 18.

Images