A method, system and device for adjusting the operating state of a network device

Abstract

The application discloses a network device running state adjustment method, and relates to the technical field of communication. A first network device receives a performance threshold value sent by a second network device, the performance threshold value indicating a performance condition that needs to be met by the first network device during running, and the performance threshold value comprising a throughput threshold value and a transmission performance threshold value. The first network device determines energy consumption, throughput and transmission performance information corresponding to each energy saving strategy in a plurality of energy saving strategies. The first network device determines a target energy saving strategy from the plurality of energy saving strategies according to the performance threshold value, the energy consumption, the throughput and the transmission performance information corresponding to the energy saving strategies, the target energy saving strategy being an energy saving strategy that meets the performance threshold value and has the minimum energy consumption. The first network device adjusts a running state according to the target energy saving strategy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, and in particular to a method, system and device for adjusting the running state of a network device. BACKGROUND

[0002] With the continuous development of network technology, people's demand for network services is growing rapidly, which leads to the rapid increase in the number and scale of network devices providing network services. The expansion of the network scale leads to the increase in network energy consumption, which not only increases the cost of network operation, but also produces a large amount of carbon emissions. SUMMARY

[0003] The present application provides a method, system and device for adjusting the running state of a network device, to ensure the performance of the network device and reduce the energy consumption of the network device by adjusting the running parameters of the network device.

[0004] In a first aspect, the present application provides a method for adjusting the running state of a network device. A first network device receives a performance threshold value sent by a second network device. The performance threshold value includes a throughput threshold value and a transmission performance threshold value. The transmission performance threshold value includes one or more of a time delay threshold value, a jitter threshold value and a packet loss threshold value. The first network device determines the energy consumption, throughput and transmission performance information corresponding to each energy saving strategy in a plurality of energy saving strategies. The transmission performance information includes one or more of time delay, jitter and packet loss. Each energy saving strategy includes a device configuration parameter corresponding to a device in the first network device. The first network device determines a target energy saving strategy according to the performance threshold value, the energy consumption, throughput and transmission performance information corresponding to each energy saving strategy. The target energy saving strategy is the energy saving strategy with the minimum energy consumption among the energy saving strategies that meet a preset condition. The preset condition includes one or more of the time delay indicated by the transmission performance information being less than or equal to the time delay threshold value, the jitter indicated by the transmission performance information being less than or equal to the jitter threshold value, the packet loss indicated by the transmission performance information being less than or equal to the packet loss threshold value, and the throughput being greater than or equal to the throughput threshold value. The first network device adjusts the running state of the first network device according to the target energy saving strategy.

[0005] In this scheme, the first network device performs optimization according to the performance threshold value issued by the second network device and the performance and energy consumption corresponding to each energy saving strategy, so that the performance value of the determined energy saving strategy meets the performance threshold value, and the energy consumption of the energy saving strategy is the minimum. Therefore, the first network adjusts the running state according to the energy saving strategy, which can not only meet the performance requirement but also reduce the energy consumption.

[0006] In a possible implementation, the first network device sends first traffic information to the second network device, the first traffic information indicating the value of the traffic processed by the first network device in a first time period, and the first traffic information is used to determine the throughput threshold value.

[0007] In a possible implementation, for each energy-saving strategy, the first network device inputs the energy-saving strategy into an energy consumption prediction model to obtain energy consumption corresponding to the energy-saving strategy output by the energy consumption prediction model. The energy consumption prediction model corresponds to the device type of the first network device. The energy consumption prediction model is generated according to energy consumption training samples. Each energy consumption training sample includes an energy consumption value and a device configuration parameter corresponding to the energy consumption value.

[0008] In a possible implementation, for each energy-saving strategy, the first network device inputs the energy-saving strategy into a throughput prediction model to obtain throughput corresponding to the energy-saving strategy output by the throughput prediction model. The throughput prediction model corresponds to the device type of the first network device. The throughput prediction model is generated according to throughput training samples. Each throughput training sample includes throughput and a device configuration parameter corresponding to the throughput.

[0009] In a possible implementation, for each energy-saving strategy, the first network device inputs the energy-saving strategy into a transmission performance prediction model to obtain transmission performance information corresponding to the energy-saving strategy output by the transmission performance prediction model. The transmission performance prediction model corresponds to the device type of the first network device. The transmission performance prediction model is generated according to transmission performance training samples. Each transmission performance training sample includes transmission performance information, a device configuration parameter corresponding to the transmission performance information, and throughput corresponding to the transmission performance information. The transmission performance prediction model includes one or more of a delay prediction model, a jitter prediction model, and a packet loss prediction model.

[0010] In a possible implementation, when the first network device has a local constraint, the target energy-saving strategy meets the local constraint in addition to the preset condition. The local constraint indicates that one or more devices in the first network device operate according to preset parameters, and / or the on-off states of multiple devices of the first network device remain consistent. In this implementation, the first network device can also consider the local constraint when determining the target energy-saving strategy, so that the determined target energy-saving strategy meets both the preset condition and the local constraint.

[0011] In a second aspect, the present application provides a method for adjusting the running state of a network device. A second network device receives first traffic information sent by a first network device. The first traffic information indicates the value of traffic processed by the first network device in a first time period. The second network device predicts second traffic information corresponding to the first network device in a second time period according to the first traffic information. The second time period is later than the first time period. The second network device obtains a transmission performance threshold and determines a throughput threshold according to the second traffic information. The transmission performance threshold includes one or more of a delay threshold, a jitter threshold, and a packet loss threshold. The second network device sends the throughput threshold and the transmission performance threshold to the first network device, so that the first network device adjusts the running state of the first network device according to the throughput threshold and the transmission performance threshold.

[0012] In a possible implementation, the second network device inputs the first traffic information into a traffic prediction model to obtain the second traffic information output by the traffic prediction model. The traffic prediction model is generated by training according to historical traffic information of the first network device.

[0013] In a possible implementation, the second network device receives the above-mentioned traffic prediction model. In this implementation, the second network device can send the historical traffic information of the first network device to a cloud device, and the cloud device trains and generates the traffic prediction model by using the historical traffic information, and sends the traffic prediction model to the second network device.

[0014] In a possible implementation, the second network device receives the throughput prediction model, the energy consumption prediction model, and the transmission performance prediction model sent by the cloud device, and sends the throughput prediction model, the energy consumption prediction model, or the transmission performance prediction model to the first network device.

[0015] In a possible implementation, the throughput prediction model, the energy consumption prediction model, or the transmission performance prediction model corresponds to the device type of the first network device. The energy consumption prediction model is generated according to energy consumption training samples. Each energy consumption training sample includes an energy consumption value and a device configuration parameter corresponding to the energy consumption value. The throughput prediction model is generated according to throughput training samples. Each throughput training sample includes a throughput and a device configuration parameter corresponding to the throughput. The transmission performance prediction model is generated according to transmission performance training samples. Each transmission performance training sample includes transmission performance information, a device configuration parameter corresponding to the transmission performance information, and a throughput corresponding to the transmission performance information.

[0016] In a third aspect, the present application provides a network system. The system comprises a first network device and a second network device. The first network device is configured to perform the method in the first aspect or any implementation manner of the first aspect. The second network device is configured to perform the method in the second aspect or any implementation manner of the second aspect.

[0017] In a possible implementation manner, the system further comprises a cloud device. The cloud device is configured to receive the statistical information sent by the second network device. The statistical information comprises historical traffic information of the network device managed by the second network device. The cloud device is further configured to train a traffic prediction model by using the historical traffic information, and send the traffic prediction model to the second network device.

[0018] In a possible implementation manner, the cloud device is further configured to send the throughput prediction model, the energy consumption prediction model, or the transmission time prediction model to the second network device.

[0019] In a fourth aspect, the present application provides a network device. The network device comprises a processor and a memory. The memory is configured to store instructions or computer programs. The processor is configured to execute the instructions or computer programs in the memory, so that the network device performs the method in the first aspect or any implementation manner of the first aspect, or performs the method in the second aspect or any implementation manner of the second aspect.

[0020] In a fifth aspect, the present application provides a computer readable storage medium. The computer readable storage medium comprises instructions. When the instructions are run on a computer, the computer is caused to perform the method in the first aspect or any implementation manner of the first aspect, or perform the method in the second aspect or any implementation manner of the second aspect.

[0021] In a sixth aspect, the present application provides a computer program product. When the computer program product is run on a computer, the computer is caused to perform the method in the first aspect or any implementation manner of the first aspect, or perform the method in the second aspect or any implementation manner of the second aspect. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A flow chart of a network device running state adjustment method provided by an embodiment of the present application;

[0023] Figure 2 An application scenario schematic diagram provided by an embodiment of the present application;

[0024] Figure 3 A network device running state adjustment device structure schematic diagram provided by an embodiment of the present application;

[0025] Figure 4Another network device running state adjustment device structure provided by the embodiment of the present application is shown in the figure.

[0026] Figure 5 A network device structure provided by the embodiment of the present application is shown in the figure.

[0027] Figure 6 Another network device structure provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0028] In order to enable personnel in the technical field to better understand the scheme in the present application, the technical scheme in the embodiment of the present application will be described clearly and completely below in combination with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiments of the present application, rather than all the embodiments.

[0029] With the continuous expansion of network construction scale, the increase of operating cost caused by the increase of network energy consumption has become a thorny problem faced by operators. The energy consumption of network equipment is related to the configuration parameters of each device in the network equipment. However, the configuration parameters of the network equipment are usually kept in a high configuration state, which leads to the continuous high energy consumption of the network equipment.

[0030] Based on this, the present application provides a network equipment running state adjustment method, so that the first network equipment can determine an energy-saving strategy meeting the performance requirement, and adjust the running state of the first network equipment according to the energy-saving strategy, so that the first network equipment can guarantee the processing performance while reducing the energy consumption.

[0031] In order to facilitate the understanding of the technical scheme provided by the embodiment of the present application, the following will be described in combination with the drawings.

[0032] Referring to Figure 1 , the figure is a network equipment running state adjustment method flow chart provided by the embodiment of the present application, as Figure 1 shown, the method comprises:

[0033] S101: The first network equipment sends first traffic information to the second network equipment, the first traffic information indicating the value of the traffic processed by the first network equipment in a first time period.

[0034] In the embodiment, the first network equipment can collect the traffic information processed by itself in the first time period, i.e. the first traffic information, and send the first traffic information to the second network equipment. Specifically, the first traffic information can include the sending rate and / or receiving rate of the first network equipment in the first time period, or the data amount received and / or sent by the first network equipment in the first time period, etc. Wherein, the sending rate can be an average sending rate, a maximum sending rate, etc. The data amount can be the number of bits, the number of bytes, the number of messages, etc.

[0035] In a specific implementation, the first traffic information sent by the first network device can be device-level traffic information, single-board-level traffic information, or interface-level traffic information. When the first traffic information includes traffic information of a specific device, the first network device can make targeted parameter adjustment on the specific device based on the traffic information of the specific device, so that the parameter adjustment for the specific device is more accurate.

[0036] S102: The second network device receives the first traffic information and predicts corresponding second traffic information of the first network device in a second time period according to the first traffic information, the second time period being later than the first time period.

[0037] After receiving the first traffic information sent by the first network device, the second network device performs traffic prediction according to the first traffic information to predict corresponding second traffic information of the second network device in a second time period. The second time period is later than the first time period. That is, the second network device can predict the trend of future traffic according to traffic information in a historical time period. Specifically, the second network device can input the first traffic information into a traffic prediction model to obtain second traffic information output by the traffic prediction model. The traffic prediction model can be a preset model, for example, the second network device receives a traffic prediction model. The received traffic prediction model can be trained by another network device or configured by an administrator. The traffic prediction model can also be generated by the second network device in advance according to historical traffic information of the first network device. The historical traffic information refers to traffic values processed by the first network device in different time periods in a historical time period. The traffic prediction model corresponds to the first network device one by one. When there are multiple first network devices in the network, the traffic prediction model corresponding to each first network device can be different.

[0038] 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 takes the obtained historical traffic information as training samples, and each training sample includes time and a traffic value, where the traffic value is taken as a label. In each round of iterative training, the first network device can input a group of training samples to the neural network model, and the neural network model outputs an inference result for the training sample. Then, the first network device can calculate a loss value between the inference result output by the neural network model and the actual result (label) of the group of training samples through a corresponding loss function. Then, the first network device can calculate the change gradient of the parameters in each network layer of the neural network model according to the calculated loss value. In this way, the first network device can calculate the adjustment value (also referred to as the parameter update amount) of the parameter in this round of iterative training based on the pre-set hyperparameters in the optimizer and the change gradient of the parameters in each network layer, which can be, for example, the product of the change gradient and the hyperparameters (such as the learning rate), so that the first network device can update the parameter value of the parameter based on the calculated adjustment value of each parameter. After the above training for multiple times, when the loss value is less than a preset threshold, the training is stopped, and the traffic prediction model is obtained.

[0039] The traffic prediction model can be trained and generated by the second network device according to the statistical information of the first network device, or generated by the cloud device according to the statistical information of the first network device. When trained and generated by the cloud device, the second network device sends the statistical information including the historical traffic information of the first network device to the cloud, and the cloud device trains and generates the traffic prediction model according to the historical traffic information and sends the traffic prediction model to the second network device.

[0040] S103: The second network device obtains a transmission performance threshold and determines a throughput threshold according to the second traffic information.

[0041] The second network device determines the throughput threshold according to the second traffic information after predicting the corresponding second traffic information of the first network device in the second time period. The second network device can also obtain the transmission performance threshold corresponding to the first network device. The transmission performance threshold includes one or more of a delay threshold, a jitter threshold, and a packet loss threshold. Specifically, the second network device can determine the maximum traffic value to be processed by the first network device in the second time period according to the second traffic information, and determine the throughput threshold according to the maximum traffic value, for example, the traffic value obtained by adding a preset increment to the maximum traffic value is determined as the throughput threshold. For example, the maximum traffic value is x, and the throughput threshold is x*130%. The unit of the throughput threshold is, for example, Mbps. The transmission performance threshold can be pre-configured by an administrator according to the transmission demand.

[0042] S104: The second network device sends a performance threshold to the first network device, the performance threshold including a throughput threshold and a transmission performance threshold.

[0043] S105: The first network device determines energy consumption, throughput, and transmission performance information corresponding to each energy saving strategy in the plurality of energy saving strategies.

[0044] The first network device determines energy consumption, throughput, and transmission performance information corresponding to each energy saving strategy in the plurality of energy saving strategies. The transmission performance information includes one or more of latency, jitter, and packet loss. The energy saving strategy includes device configuration parameters corresponding to devices of the first network device. The device configuration parameters can include discrete configuration parameters of the devices, such as switch states of the devices, or non-discrete configuration parameters corresponding to the devices, such as operating frequencies of the devices. The plurality of energy saving strategies are preconfigured, and each energy saving strategy in the plurality of energy saving strategies includes different part or all of the device configuration parameters.

[0045] The first network device can determine the energy consumption corresponding to each energy saving strategy by the following method, specifically including: for each energy saving strategy, the first network device inputs the energy saving strategy into an 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 corresponds to the type of the first network device and is generated according to energy consumption training samples. Each energy consumption training sample includes an energy consumption value and device configuration parameters corresponding to the energy consumption value. That is, the first network device can determine the energy consumption of each energy saving strategy by using the pre-trained energy consumption prediction model. The energy consumption training sample can be the energy consumption value of the first network device and the device configuration parameters corresponding to the energy consumption value, or the energy consumption value of another network device and the device configuration parameters corresponding to the energy consumption value. The device type of the other network device is the same as that of the first network device. The same device type means that the two network devices have the same or similar constituent devices. For example, the same device type can mean that the two network devices have the same model.

[0046] The energy consumption prediction model can be trained by the second network device using the energy consumption training samples and then sent to the first network device, or trained by a cloud device using the energy consumption training samples and then sent to the first network device by the second network device.

[0047] The first network device can determine the throughput corresponding to each energy saving strategy in the following manner, specifically including: for each energy saving strategy, the first network device inputs the energy saving strategy into a throughput prediction model to obtain the throughput of the corresponding energy saving strategy output by the throughput prediction model. The throughput prediction model corresponds to the device type of the first network device and is generated according to throughput training samples. Each throughput training sample includes a throughput and a device configuration parameter corresponding to the throughput. That is, the first network device can determine the throughput corresponding to each energy saving strategy by using the throughput prediction model generated by pre-training. The throughput training sample can be the throughput of the first network device and the device configuration parameter corresponding to the throughput, or the throughput of another network device and the device configuration parameter corresponding to the throughput. The device type of the other network device is the same as that of the first network device. The same device type means that the two network devices have the same or similar constituent devices. For example, the same device type can mean that the two network devices have the same model.

[0048] The throughput prediction model can be trained by the second network device using the throughput training samples and delivered to the first network device, or trained by the cloud device using the throughput training samples and sent to the first network device through the second network device.

[0049] The first network device can determine the transmission performance information corresponding to each energy saving strategy in the following manner, specifically including: for each energy saving strategy, the first network device inputs the energy saving strategy and the throughput threshold into a transmission performance prediction model to obtain the transmission performance information of the corresponding energy saving strategy output by the transmission performance prediction model. The transmission performance prediction model corresponds to the device type of the first network device and is generated according to transmission performance training samples. Each transmission performance training sample includes transmission performance information, a device configuration parameter corresponding to the transmission performance information, and a throughput corresponding to the transmission performance information. That is, each transmission performance training sample represents the transmission performance information obtained by the network device processing the corresponding throughput with the corresponding device configuration parameter. The transmission performance prediction model includes one or more of a delay prediction model, a jitter prediction model, and a packet loss prediction model. That is, the first network device can determine the transmission performance information corresponding to each energy saving strategy by using the transmission performance prediction model generated by pre-training. The transmission performance training sample can be the transmission performance information of the first network device, the device configuration parameter corresponding to the transmission performance information, and the throughput corresponding to the transmission performance information, or the transmission performance information of another network device, the device configuration parameter corresponding to the transmission performance information, and the throughput corresponding to the transmission performance information. The device type of the other network device is the same as that of the first network device. The same device type means that the two network devices have the same or similar constituent devices. For example, the same device type can mean that the two network devices have the same model.

[0050] The transmission performance prediction model can be generated by the second network device using transmission performance training samples and then sent to the first network device, or it can be generated by the cloud device using transmission performance training samples and then sent to the first network device through the second network device.

[0051] It should be noted that the above prediction models (energy consumption prediction model, throughput prediction model, and transmission performance prediction model) can be linear models or neural network models. When the prediction model is a linear model, it will be determined through linear fitting during training; when the prediction model is a neural network model, it will be determined through neural network training. To facilitate understanding of the training process of neural network models, the training of an energy consumption prediction model will be used as an example.

[0052] A network device (a second network device or a cloud device) acquires energy consumption training samples. Each energy consumption training sample includes an energy consumption value and the corresponding device configuration parameters, with the energy consumption value serving as a label. During each round of iterative training, the network device can input a set of energy consumption training samples into a neural network model, which then outputs an inference result for that set of training samples. The network device can then calculate the loss between the inference result output by the neural network model and the actual result (label) of that set of training samples using a corresponding loss function. Based on the calculated loss value, the network device can then calculate the gradient of the parameters in each network layer of the neural network model. Thus, based on the hyperparameters pre-set in the optimizer and the gradients of the parameters in each network layer, the network device can calculate the adjustment value (also called the parameter update) of each parameter during this round of iterative training. This adjustment value can be, for example, the product of the gradient and a hyperparameter (such as the learning rate). The network device can then update the parameter value based on the calculated adjustment value of each parameter. After multiple training iterations, training stops when the loss value is less than a preset threshold, resulting in an energy consumption prediction model.

[0053] When the training process is executed by the cloud device, the first network device sends statistical information to the cloud device through the second network device. This statistical information includes throughput at different times, transmission performance information at each time, energy consumption at each time, and device configuration parameters at each time. The cloud device extracts energy consumption training samples, throughput training samples, and transmission performance training samples from the statistical information to train an energy consumption prediction model, a throughput prediction model, and a transmission time prediction model using the transmission performance training samples. The cloud device then sends these prediction models to the first network device through the second network device.

[0054] S106: The first network device determines a target energy saving strategy according to the performance threshold, the energy consumption corresponding to each energy saving strategy, the throughput, and the transmission performance information. The target energy saving strategy is the energy saving strategy with the minimum energy consumption among the energy saving strategies that meet the preset conditions.

[0055] After determining the energy consumption, the throughput, and the transmission performance information corresponding to each energy saving strategy, the first network device determines a target energy saving strategy from the multiple energy saving strategies according to the performance threshold and the energy consumption, the throughput, and the transmission performance information corresponding to each energy saving strategy. The target energy saving strategy is the energy saving strategy with the minimum energy consumption among the energy saving strategies that meet the preset conditions. The preset conditions include one or more of the following: the delay indicated by the transmission performance information is less than or equal to the delay threshold, the jitter indicated by the transmission performance information is less than or equal to the jitter threshold, the packet loss indicated by the transmission performance information is less than or equal to the packet loss threshold, and the throughput is greater than or equal to the throughput threshold.

[0056] When the first network device has local constraints, the target energy saving strategy meets the local constraints in addition to the above-mentioned preset conditions. The local constraints indicate one or more of the following: one or more devices in the first network device operate according to preset parameters, the on-off states of multiple devices in the first network device remain consistent, and one or more devices in the first network device are in an on state or an off state.

[0057] The execution order of S105 is not limited by the above description. The first network device can execute S105 first, then receive the performance threshold sent by the second network device, or can receive the performance threshold sent by the second network device first, then execute S105, or can execute S105 at the same time as receiving the performance threshold sent by the second network device.

[0058] S107: The first network device adjusts the operating state of the first network device according to the target energy saving strategy.

[0059] After determining the target energy saving strategy, the first network device adjusts the device configuration parameters corresponding to the devices of the first network device according to the target energy saving strategy, thereby adjusting the operating state.

[0060] When the first network device operates according to the device configuration parameters corresponding to the target energy saving strategy, the first network device can also obtain statistical information corresponding to the first network device, and send the statistical information to the second network device or the cloud device, so that the second network device or the cloud device can update the parameters of the above-mentioned prediction models, thereby improving the prediction accuracy of the prediction models.

[0061] It can be seen that the first network device performs optimization according to the performance threshold value issued by the second network device and the performance value corresponding to each energy-saving strategy, so that the performance value of the determined energy-saving strategy is the smallest under the condition that the performance value meets the performance threshold value, thereby configuring each device according to the energy-saving strategy and saving energy consumption.

[0062] Figure 2 is an application scenario provided by an embodiment of the present application. Referring to the application scenario shown in Figure 2 The application scenario includes a cloud device, an analyzer, a controller, and a network device. The network device can include a forwarding device and a terminal device in a network. The controller can obtain statistical information from the network device and send the statistical information to the analyzer, so that the analyzer predicts traffic information processed by the network device according to the statistical information, and then determines a throughput threshold value corresponding to the network device. The analyzer sends the performance threshold value to the network device through the controller, and the network device determines a target energy-saving strategy according to the performance threshold value and the throughput, energy consumption, and transmission performance information corresponding to each energy-saving strategy, and adjusts the running state of the network device according to the device configuration parameters corresponding to the target energy-saving strategy.

[0063] In the Figure 2 application scenario, the controller sends the collected statistical information to the cloud device through the analyzer, and the cloud device trains a traffic prediction model, an energy consumption prediction model, a throughput prediction model, and a transmission time prediction model using the statistical information. After the cloud device trains and generates the models, the cloud device sends the traffic prediction model to the analyzer, so that the analyzer predicts the traffic information of the network device using the traffic prediction model. At the same time, the cloud device sends the energy consumption prediction model, the throughput prediction model, and the transmission time prediction model to the network device through the analyzer.

[0064] In actual application, the controller collects first traffic information corresponding to a first time period of the network device, and sends the first traffic information to the analyzer. The analyzer obtains second traffic information corresponding to a second time period of the network device using the first traffic information and the traffic prediction model. The analyzer obtains a throughput threshold value in the performance threshold value, determines the throughput threshold value according to the second traffic information, and sends the throughput threshold value and the transmission performance threshold value to the network device. The network device determines the throughput, transmission performance information (one or more of delay, jitter, and packet loss), and energy consumption corresponding to each energy-saving strategy, and determines a target energy-saving strategy according to the performance threshold value and the throughput, transmission performance information, and energy consumption corresponding to each energy-saving strategy, and then adjusts the running state of the network device according to the target energy-saving strategy to save energy consumption.

[0065] As described above, each prediction model can be a linear model or a neural network model. To facilitate the understanding of the generation of various models, each model will be described below.

[0066] (1) Linear model:

[0067] 1. Energy consumption prediction model:

[0068] Let s0, s1, …, s n denote the switch states of the relevant devices in the network equipment, such as service boards, fabric cards, serializer / deserializer (SERDES), etc. The following formula is used to fit the relationship between switch states and energy consumption:

[0069] E = e0s0 + e1s1 + … + e n s n

[0070] where E represents energy consumption, {e1, e2, …, e n} is a set of parameters describing the relationship between energy consumption and device switching, which can be fitted by energy consumption training samples (each sample contains device switching state and energy consumption) using optimization algorithms such as least squares or gradient descent. n

[0071] 2. Throughput prediction model

[0072] Let s0, s1, …, s n denote the switch states of the relevant devices in the network equipment, and the following formula is used to fit the relationship between switch states and throughput:

[0073] Throughput = t0s0 + t1s1 + … + t n s n

[0074] where Throughput represents throughput, {t0, t1, …, t n} is a set of parameters describing the relationship between throughput and device switching, which can be fitted by throughput training samples (each sample contains device switching state and throughput) using optimization algorithms such as least squares or gradient descent. n

[0075] 3. Delay prediction model

[0076] Similarly, a linear model is used to fit the relationship between device switching state, throughput, and delay:

[0077] Delay = d0s0 + d1s1 + … + d n s n + d n+1 x ​​

[0078] where x represents the traffic size processed by the network device based on the set of device switch states {s0, s1, … sn}, and Delay represents the latency of the network device when processing traffic x based on the set of device switch states, i.e., a training sample includes a set of switch states {s0, s1, … sn}, the traffic size x processed based on the switch states, the latency value of the network device when processing the traffic x based on the set of switch states, {d0, d1, …, d n ,d n+1} are parameters of the latency prediction model, and the model can also be trained based on multiple training samples using optimization algorithms such as the least squares method or the gradient descent method. The inputs needed when predicting the latency are the device switch states and the minimum throughput.

[0079] 4. Jitter prediction model

[0080] A linear model is used to fit the relationship between the device switch states, the throughput, and the jitter:

[0081] Jitter = j0s0 + j1s1 + … + j n s n + j n+1 x

[0082] where Jitter represents the jitter, {j0, j1, …, j n , j n+1} represent parameters of the jitter prediction model, and the model can also be trained using optimization algorithms such as the least squares method or the gradient descent method. The inputs needed when predicting the jitter are the device switch states and the minimum throughput.

[0083] 5. Loss prediction model

[0084] A linear model is used to fit the relationship between the device switch states, the traffic size, and the loss:

[0085] Loss = l0s0 + l1s1 + … + l n s n + l n+1 x

[0086] where Loss represents the loss, {l0, l1, …, l n , l n+1} represent parameters of the loss prediction model, and the model can also be trained using optimization algorithms such as the least squares method or the gradient descent method. The inputs needed when predicting the loss are the device switch states and the minimum throughput.

[0087] In application, the network device, after receiving the minimum throughput X, the delay threshold D, the jitter threshold J, and the packet loss threshold L issued, constructs a calculation model in combination with local switch constraints. The calculation model minimizes energy consumption while guaranteeing the minimum throughput X, the delay threshold D, the jitter threshold J, the packet loss threshold L, and the local switch constraint. The variable of the calculation model is the switch state s0, s1, …, s n When the switch variable is 1, it represents that the device is turned on; when it is 0, it represents that the device is turned off. The specific form of the calculation model is as follows:

[0088] Min e0s0+e1s1+…+e n s n

[0089] S.T.X<t1s0+ts1+……t n s n

[0090] D>d0s0+d1s1+…+d n s n +d n+1 X

[0091] J>j0s0+j1s1+…+j n s n +j n+1 X

[0092] L>l0s0+l1s1+…+l n s n +l n+1 X

[0093] Local constraint: for example, s1=s0

[0094] (II) Neural network model

[0095] Let s0, s1, …, s n represent the switch state of the related device in the network device, and the relationship between the switch state and the energy consumption is fitted using a neural network:

[0096] Energy=E(s0,s1,…,s n )

[0097] Where E(.) is a set of relationships between energy consumption and switch state. For example, a backpropagation (BP) algorithm, a genetic algorithm (GA), etc. can be used to fit through energy consumption training samples (each sample contains a switch state and energy consumption).

[0098] For the throughput prediction model, the delay prediction model, and the jitter prediction model, the following is obtained:

[0099] Throughput = T (s0, s1,..., s n )

[0100] where T(.) is a set of relations describing the throughput and the switch states. The BP algorithm or GA can be used to fit the training samples (each sample contains switch states and traffic size) by throughput.

[0101] Delay = D (s0, s1,..., s n , x)

[0102] where D(.) is a set of relations describing the delay and the switch states of the device. The BP algorithm or GA can be used to fit the training samples (each sample contains switch states, traffic size, delay) by delay.

[0103] Jitter = J (s0, s1,..., s n , x)

[0104] where J(·) is a set of relations describing the jitter and the switch states of the device. The BP algorithm or GA can be used to fit the training samples (each sample contains switch states, traffic size, jitter) by training samples.

[0105] Loss = L (s0, s1,..., s n , x)

[0106] where L(·) is a set of relations describing the loss and the switch states of the device. The BP algorithm or GA can be used to fit the training samples (each sample contains switch states, throughput, loss) by training samples.

[0107] After the network device receives the throughput threshold and the transmission performance threshold (for example, delay threshold, jitter threshold, loss threshold) issued, combined with the local switch constraint, a calculation model is constructed. The calculation model minimizes the energy consumption while guaranteeing the throughput threshold, the transmission performance threshold and the local switch constraint, and the variable of the calculation model is each switch s0, s1,..., s n , if selected, it represents on, otherwise it represents off, and the specific form of the calculation model is as follows:

[0108] Min: E (S)

[0109] S.T.X < T (S)

[0110] D < D (S, X)

[0111] J < J (S, X)

[0112] L < L (S, X)

[0113] Local constraints: e.g. s1 = s0

[0114] Wherein, the calculation model can be solved iteratively by ant colony algorithm to obtain s0-s n After the specific values of s0-s

[0115] It should be noted that in the above embodiments, only the discrete states of the relevant devices in the network equipment (e.g. network board, service board, serial / parallel converter) are considered, while in actual applications, the non-discrete configuration parameters of the central processing unit (CPU), network processor (NP), heat dissipation device, etc. of the network equipment can also be considered. Therefore, when constructing the above prediction models, the relationship between energy consumption and non-discrete configuration parameters, the relationship between throughput and non-discrete configuration parameters, the relationship between delay and non-discrete configuration parameters, the relationship between jitter and non-discrete configuration parameters, and the relationship between packet loss and non-discrete configuration parameters can also be established. For example, s0, s1, …, s n represent the discrete state configuration parameters of the relevant devices, c0, c1, …, c m represent the continuous state configuration parameters of another part of the devices. Taking the delay model as an example:

[0116] Delay = d0s0 + d1s1 + … + d n s n + d n+1 c0 + … + d n+m c m + d n+m+1 X

[0117] For example, the discrete state s i represents the on-off state of a service board, which can be represented by (0, 1) respectively; c j represents the power of the cooling fan, which can be configured to a continuous range of 0%-100%, such as 53.2%. It can be understood that the non-discrete configuration parameters can also be converted to discrete configuration parameters through sampling. For example, the power of the cooling fan is sampled according to a granularity of 1%, then 101 power parameter value ranges [0, 1%, 2%, 3%, …, 100%] of the cooling fan can be obtained, and correspondingly, the parameter value range of cj in the above model is [0, 1%, 2%, 3%, …, 100%]. Other non-discrete configuration parameters can also be discretized in a similar manner. When all configuration parameters are discretized, the above model is converted into the relationship between the discretized configuration parameters and the delay.

[0118] Based on the above method embodiments, the application provides an adjusting device for the running state of a network device, which will be described below with reference to the accompanying drawings.

[0119] Referring to Figure 3 , the figure is a structure diagram of an adjusting device for the running state of a network device provided by the application, as shown in Figure 3 , the device 300 comprises a receiving unit 301, a first determining unit 302, a second determining unit 303 and an adjusting unit 304. The device 300 can be applied to a first network device.

[0120] The receiving unit 301 is configured to receive a performance threshold value sent by a second network device. The performance threshold value comprises a throughput threshold value and a transmission performance threshold value. The transmission performance threshold value comprises one or more of a time delay threshold value, a jitter threshold value and a packet loss threshold value.

[0121] The first determining unit 302 is configured to determine the energy consumption, throughput and transmission performance information corresponding to each energy saving strategy in a plurality of energy saving strategies. The transmission performance information comprises one or more of time delay, jitter and packet loss. Each energy saving strategy comprises the device configuration parameters corresponding to the devices in the first network device.

[0122] The second determining unit 303 is configured to determine a target energy saving strategy according to the performance threshold value, the energy consumption, throughput and transmission performance information corresponding to each energy saving strategy. The target energy saving strategy is the energy saving strategy with the minimum energy consumption among the energy saving strategies meeting the preset conditions. The preset conditions comprise one or more of the time delay indicated by the transmission performance information being less than or equal to the time delay threshold value, the jitter indicated by the transmission performance information being less than or equal to the jitter threshold value, the packet loss indicated by the transmission performance information being less than or equal to the packet loss threshold value, and the throughput being greater than or equal to the throughput threshold value.

[0123] The adjusting unit 304 is configured to adjust the running state of the first network device according to the target energy saving strategy.

[0124] Optionally, the device 300 further comprises a sending unit.

[0125] The sending unit is configured to send first traffic information to the second network device. The first traffic information indicates the value of the traffic processed by the first network device in a first time period. The first traffic information is used to determine the throughput threshold value. In this implementation, the first network device sends the traffic information processed by itself, i.e. the first traffic information, to the second network device, so that the second network device determines the throughput threshold value, i.e. the minimum throughput that the first network device should be able to process in a second time period, according to the first traffic information.

[0126] Optionally, the first determining unit 302 is further configured to, for each energy-saving strategy, input 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 corresponds to the device type of the first network device. The energy consumption prediction model is generated based on energy consumption training samples. Each energy consumption training sample includes an energy consumption value and the device configuration parameters corresponding to that energy consumption value.

[0127] Optionally, the first determining unit 302 is further configured to, for each energy-saving strategy, input the energy-saving strategy into the throughput prediction model to obtain the throughput output by the throughput prediction model corresponding to the energy-saving strategy. The throughput prediction model corresponds to the device type of the first network device. The throughput prediction model is generated based on throughput training samples. Each throughput training sample includes the throughput and the device configuration parameters corresponding to that throughput.

[0128] Optionally, the first determining unit 302 is further configured to, for each energy-saving strategy, input the energy-saving strategy into the transmission performance prediction model to obtain the transmission performance information corresponding to the energy-saving strategy output by the transmission performance prediction model. The transmission performance prediction model corresponds to the device type of the first network device. The transmission performance prediction model is generated based on transmission performance training samples. Each transmission performance training sample includes transmission performance information, device configuration parameters corresponding to the transmission performance information, and throughput corresponding to the transmission performance information. The transmission performance prediction model includes one or more of a latency prediction model, a jitter prediction model, and a packet loss prediction model.

[0129] Optionally, when the first network device has local constraints, the target energy-saving strategy, in addition to satisfying the aforementioned preset conditions, also satisfies the local constraints. The local constraints instruct one or more devices in the first network device to operate according to preset parameters, and / or for the switching states of multiple devices in the first network device to remain consistent. In this implementation, the first network device may also consider local constraints when determining the target energy-saving strategy, so that the determined target energy-saving strategy satisfies both the preset conditions and the local constraints.

[0130] It should be noted that the specific 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.

[0131] See Figure 4 This figure is a structural diagram of another network device operation status adjustment device provided in an embodiment of this application, such as... Figure 4 As shown, the device 400 includes a receiving unit 401, a prediction unit 402, an acquisition unit 403, and a sending unit 404. The device 400 can be applied to a second network device.

[0132] The receiving unit 401 is configured to receive first traffic information sent by the first network device. The first traffic information indicates a value of traffic processed by the first network device in a first time period.

[0133] The predicting unit 402 is configured to predict, according to the first traffic information, second traffic information corresponding to the first network device in a second time period. The second time period is later than the first time period.

[0134] The obtaining unit 403 is configured to obtain a transmission performance threshold and determine a throughput threshold according to the second traffic information. The transmission performance threshold includes one or more of a delay threshold, a jitter threshold, and a packet loss threshold.

[0135] The sending unit 404 is configured to send the throughput threshold and the transmission performance threshold to the first network device, so that the first network device adjusts an operation state of the first network device according to the throughput threshold and the transmission performance threshold.

[0136] Optionally, the predicting unit 402 is further configured to input the first traffic information into a traffic prediction model to obtain the second traffic information output by the traffic prediction model. The traffic prediction model is generated according to historical traffic information of the first network device.

[0137] Optionally, the receiving unit 401 is further configured to receive the traffic prediction model.

[0138] Optionally, the receiving unit 401 is further configured to receive a throughput prediction model, an energy consumption prediction model, or a transmission performance prediction model sent by the cloud device. The sending unit 404 is further configured to send the throughput prediction model, the energy consumption prediction model, or the transmission performance prediction model to the first network device.

[0139] Optionally, the throughput prediction model, the energy consumption prediction model, or the transmission performance prediction model corresponds to a device type of the first network device. The energy consumption prediction model is generated according to energy consumption training samples. Each energy consumption training sample includes an energy consumption value and a device configuration parameter corresponding to the energy consumption value. The throughput prediction model is generated according to throughput training samples. Each throughput training sample includes a throughput and a device configuration parameter corresponding to the throughput. The transmission performance prediction model is generated according to transmission performance training samples. Each transmission performance training sample includes transmission performance information, a device configuration parameter corresponding to the transmission performance information, and a throughput corresponding to the transmission performance information.

[0140] It should be noted that the implementation of each unit in this embodiment can refer to the related description in the above method embodiments, which will not be described here in detail.

[0141] Figure 5A structural schematic diagram of a network device is provided in the embodiments of the present application. The network device may, for example, be the first network device or the second network device in the method embodiments described above, or may also be Figure 3 The device implementation of the apparatus 300 in the embodiments shown, or may also be Figure 4 The device implementation of the apparatus 400 in the embodiments shown.

[0142] The network device 500 includes a processor 510, a communication interface 520, and a memory 530. The number of processors 510 in the network device 500 may be one or more, Figure 5 In the embodiments of the present application, the processor 510, the communication interface 520, and the memory 530 can be connected through a bus system or other means. In the embodiments of the present application, the processor 510, the communication interface 520, and the memory 530 are connected through the bus system 540 as an example. Figure 5

[0143] The processor 510 can be a CPU, an NP, or a combination of a CPU and an NP. The processor 510 can further include a hardware chip. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0144] The memory 530 can include a volatile memory such as a random-access memory (RAM), and can also include a non-volatile memory such as a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The memory 530 can also include a combination of the above-mentioned types of memories.

[0145] ​Optionally, the memory 530 stores an operating system and programs, executable modules or data structures, or subsets thereof, or extended sets thereof, wherein the programs can include various operation instructions for implementing various operations. The operating system can include various system programs for implementing various basic services and processing hardware-based tasks. The processor 510 can read the programs in the memory 530 to implement the method provided in the embodiments of the present application.

[0146] The memory 530 can be a storage device in the network device 500, or a storage device independent of the network device 500.

[0147] 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 an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0148] Figure 6 FIG. 6 is a structural schematic diagram of a network device 600 provided by the embodiments of the present application. The network device can be, for example, the first network device or the second network device in the method embodiments, or can also be Figure 3 The device implementation of the apparatus 300 in the embodiments can also be Figure 4 The device implementation of the apparatus 400 in the embodiments.

[0149] The network device 600 includes a main control board 610 and an interface board 630.

[0150] The main control board 610 is also called a main processing unit (MPU) or a route processor card. The main control board 610 controls and manages various components in the network device 600, including route calculation, device management, device maintenance, and protocol processing functions. The main control board 610 includes a central processing unit 611 and a memory 612.

[0151] The interface board 630 is also called a line processing unit (LPU), a line card, or a service board. The interface board 630 is configured to provide various service interfaces and implement forwarding of data packets. The service interfaces include, but are not limited to, an Ethernet interface, a POS (Packet over SONET / SDH) interface, and the like. The Ethernet interface is, for example, a Flexible Ethernet Client (FlexE Client). The interface board 630 includes a central processor 631, a network processor 632, a forwarding table entry memory 634, and a physical interface card (PIC) 633.

[0152] The central processor 631 on the interface board 630 is configured to control and manage the interface board 630 and communicate with the central processor 611 on the master control board 610.

[0153] The network processor 632 is configured to implement forwarding processing of a packet. The network processor 632 can be in the form of a forwarding chip. Specifically, processing of an uplink packet includes processing of a packet entry interface and forwarding table lookup, and processing of a downlink packet includes forwarding table lookup, and the like.

[0154] The physical interface card 633 is configured to implement a physical layer interface function. Raw traffic enters the interface board 630 through the physical interface card 633, and a processed packet is sent out from the physical interface card 633. The physical interface card 633 includes at least one physical interface, which is also called a physical port. The physical interface card 633, also called a daughter card, can be installed on the interface board 630 and is responsible for converting an optical signal into a packet and forwarding the packet to the network processor 632 for processing after performing a legality check. In some embodiments, the central processor 631 of the interface board 603 can also perform the function of the network processor 632, such as implementing software forwarding based on a general-purpose CPU, so that the network processor 632 is not needed in the physical interface card 633.

[0155] Optionally, the network device 600 includes multiple interface boards. For example, the network device 600 further includes an interface board 640, which includes a central processor 641, a network processor 642, a forwarding table entry memory 644, and a physical interface card 643.

[0156] Optionally, the network device 600 further includes a switch fabric board 620. The switch fabric board 620 can also be called a switch fabric unit (SFU). In the case where the network device has multiple interface boards 630, the switch fabric board 620 is configured to complete data exchange between the interface boards. For example, the interface board 630 and the interface board 640 can communicate through the switch fabric board 620.

[0157] The master board 610 and the interface board 630 are coupled. For example, the master board 610, the interface board 630, and the interface board 640, and the switching network board 620 are connected to the system backboard through a system bus to realize intercommunication. In a possible implementation, an inter-process communication (IPC) channel is established between the master board 610 and the interface board 630, and the master board 610 and the interface board 630 communicate through the IPC channel.

[0158] In logic, the network device 600 includes a control plane and a forwarding plane. The control plane includes the master board 610 and the central processor 631, and the forwarding plane includes various components that perform forwarding, such as the forwarding table item storage 634, the physical interface card 633, and the network processor 632. The control plane performs functions such as generating a forwarding table, processing signaling and protocol packets, configuring and maintaining a state of the device, and the like. The control plane distributes the generated forwarding table to the forwarding plane, and in the forwarding plane, the network processor 632 performs table lookup and forwarding on a packet received by the physical interface card 633 based on the forwarding table distributed by the control plane. The forwarding table distributed by the control plane can be stored in the forwarding table item storage 634. In some embodiments, the control plane and the forwarding plane can be completely separated and not on the same device.

[0159] It should be understood that operations on the interface board 640 in the embodiments of the present application are consistent with operations of the interface board 630, and for brevity, will not be described again. It should be understood that the network device 600 in the embodiments can correspond to the network device in each of the method embodiments described above, and the master board 610, the interface board 630, and / or the interface board 640 in the network device 600 can implement various steps in each of the method embodiments described above, and for brevity, will not be described again.

[0160] It should be understood that the master board can have one or more, and when there are multiple, it can include a master master board and a backup master board. The interface board can have one or more, and the stronger the data processing capability of the network device, the more interface boards it provides. The physical interface card on the interface board can also have one or more. The switching network board can have none or one or more, and when there are multiple, they can collectively implement load sharing and redundant backup. Under the centralized forwarding architecture, the network device can not need a switching network board, and the interface board undertakes the processing function of the entire system of service data. Under the distributed forwarding architecture, the network device can have at least one switching network board, and the data exchange between multiple interface boards is realized through the switching network board, and a large-capacity data exchange and processing capability is provided. Therefore, the data access and processing capability of the network device of the distributed architecture is greater than that of the centralized architecture. Alternatively, the form of the network device can also be only one board card, that is, the functions of the interface board and the master control board are integrated on the one board card, at which time the central processor on the interface board and the central processor on the master control board can be combined into one central processor to execute the functions of the two superpositions. The data exchange and processing capability of such a form of device is relatively low (for example, low-end switches or routers and other network devices). Which architecture to use depends on the specific networking deployment scenario.

[0161] In some possible embodiments, the network device described above can be implemented as a virtualized device. For example, the virtualized device can be a virtual machine (VM) running a program for sending a packet function, and the virtual machine is deployed on a hardware device (for example, a physical server). The virtual machine refers to a complete computer system that is simulated by software and has complete hardware system functions and runs in a completely isolated environment. The virtual machine can be configured as a network device. For example, the network device can be implemented based on a general-purpose physical server combined with network function virtualization (NFV) technology. The network device is a virtual host, a virtual router, or a virtual switch. Those skilled in the art can virtualize a network device with the above functions on a general-purpose physical server by reading this application in combination with the NFV technology, and details are not repeated here.

[0162] It should be understood that the network device in the above various product forms has any function of the network device in the method embodiments described above, and details are not repeated here.

[0163] The embodiment of the present application also provides a chip, which comprises a processor and an interface circuit. The interface circuit is used to receive an instruction and transmit the instruction to the processor; and the processor, for example, can be a central processing unit (CPU), a microprocessor unit (MPU), a micro control unit (MCU), a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a complex programmable logic device (CPLD), a graphic processing unit (GPU), a tensor processing unit (TPU), a quantum computer, or the like. Figure 3The shown specific implementation form of the adjustment device 300 can be used to execute the above-mentioned running state adjustment method. The processor is coupled with the memory, and the memory is used to store programs or instructions, when the programs or instructions are executed by the processor, the chip system implements the method in any method embodiment.

[0164] Optionally, the processor in the chip system can be one or more. The processor can be implemented by hardware or software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented by software, the processor can be a general-purpose processor, which is implemented by reading software codes stored in the memory.

[0165] Optionally, the memory in the chip system can also be one or more. The memory can be integrated with the processor or separately arranged from the processor, which is not limited in the present application. For example, the memory can be a non-transient processor, such as a read-only memory (ROM), which can be integrated on the same chip as the processor or separately arranged on different chips, and the type of the memory and the arrangement of the memory and the processor are not limited in the present application.

[0166] For example, the chip system can be an FPGA, an ASIC, a system on chip (SoC), a CPU, an NP, a digital signal processor (DSP), a micro controller unit (MCU), a PLD or other integrated chips.

[0167] The present application also provides a network system. The system includes a first network device and a second network device.

[0168] The first network device is used to execute Figure 3 The execution steps of the first network device in the network device running state adjustment method shown.

[0169] The second network device is used to execute Figure 3 The execution steps of the second network device in the network device running state adjustment method shown.

[0170] Optionally, the system further includes a cloud device. The cloud device is used to receive the statistical information sent by the second network device. The statistical information includes historical traffic information of the network device managed by the second network device. The cloud device is also used to train a traffic prediction model using the historical traffic information, and send the traffic prediction model to the second network device.

[0171] Optionally, the cloud device is further configured to send the throughput prediction model, the energy consumption prediction model, or the transmission time prediction model to the second network device.

[0172] The embodiment of the present application further provides a computer readable storage medium comprising instructions or a computer program, which, when executed on a computer, causes the computer to perform the adjustment method of the running state of the network device provided in the above embodiment.

[0173] The embodiment of the present application further provides a computer program product comprising instructions or a computer program, which, when executed on a computer, causes the computer to perform the adjustment method of the running state of the network device provided in the above embodiment.

[0174] The terms "first", "second", "third", "fourth" and the like in the description and in the claims of the present application, if any, of the above-described drawings (if any) are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so construed can interchange, under appropriate circumstances, and that the embodiments described herein can operate in other sequences than the one illustrated or described herein. Furthermore, the terms "comprise", "comprising", "include", "including", and the like, as used with respect to this description and the claims of the present application, are intended to mean the underlying claimable subject matter without excluding additional subject matter. It is to be understood that the terms so construed can be interchangeable under appropriate circumstances, and that the embodiments described herein can operate or be used in other sequences than the one illustrated or described herein.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0176] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, and the division of units is only a logical business division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0177] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0178] In addition, each service unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software service unit.

[0179] If the integrated unit is realized in the form of a software service 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 solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, and various storage medium that can store program codes.

[0180] Those skilled in the art should realize that in the above one or more examples, the services described in the present application can be realized by hardware, software, firmware or any combination thereof. When realized by software, these services can be stored in a computer readable medium or transmitted as one or more instructions or codes on a computer readable medium. The computer readable medium includes a computer storage medium and a communication medium, wherein the communication medium includes any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0181] The above detailed description of the specific embodiments, the purpose, technical solutions and beneficial effects of the present application are further described in detail. It should be understood that the above is only a specific embodiment of the present application.

[0182] The above, the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for adjusting a running state of a network device, characterized in that, The method comprises: The first network device receives the performance threshold value sent by the second network device, wherein the performance threshold value comprises a throughput threshold value and a transmission performance threshold value, and the transmission performance threshold value comprises one or more of a time delay threshold value, a jitter threshold value and a packet loss threshold value; The first network device determines the energy consumption, throughput and transmission performance information corresponding to each energy saving strategy in the plurality of energy saving strategies, wherein the transmission performance information comprises one or more of time delay, jitter and packet loss, and each energy saving strategy comprises device configuration parameters corresponding to devices in the first network device; The first network device determines a target energy saving strategy according to the performance threshold value, the energy consumption, throughput and transmission performance information corresponding to each energy saving strategy, wherein the target energy saving strategy is the energy saving strategy with the minimum energy consumption among the energy saving strategies meeting a preset condition, and the preset condition comprises one or more of the time delay indicated by the transmission performance information being less than or equal to the time delay threshold value, the jitter indicated by the transmission performance information being less than or equal to the jitter threshold value, the packet loss indicated by the transmission performance information being less than or equal to the packet loss threshold value, and the throughput being greater than or equal to the throughput threshold value; The first network device adjusts the operating state of the first network device according to the target energy saving strategy.

2. The method of claim 1, wherein, The method further comprises: The first network device sends first traffic information to the second network device, wherein the first traffic information indicates the value of the traffic processed by the first network device in a first time period, and the first traffic information is used to determine the throughput threshold value.

3. The method according to claim 1 or 2, characterized in that, The first network device determines the energy consumption corresponding to each energy saving strategy in the plurality of energy saving strategies, comprising: For each energy saving strategy, the first network device inputs the energy saving strategy into an energy consumption prediction model to obtain the energy consumption corresponding to the energy saving strategy output by the energy consumption prediction model, wherein the energy consumption prediction model corresponds to the device type of the first network device, and the energy consumption prediction model is generated according to energy consumption training samples, and each energy consumption training sample comprises an energy consumption value and device configuration parameters corresponding to the energy consumption value.

4. The method according to claim 1 or 2, characterized in that, The first network device determines the throughput corresponding to each energy saving strategy in the plurality of energy saving strategies, comprising: For each energy saving strategy, the first network device inputs the energy saving strategy into a throughput prediction model to obtain the throughput corresponding to the energy saving strategy output by the throughput prediction model, wherein the throughput prediction model corresponds to the device type of the first network device, and the throughput prediction model is generated according to throughput training samples, and each throughput training sample comprises a throughput and device configuration parameters corresponding to the throughput.

5. The method according to claim 1 or 2, characterized in that, The first network device determines the transmission performance information corresponding to each energy saving strategy in the plurality of energy saving strategies, comprising: The first network device inputs the energy-saving strategy into a transmission performance prediction model to obtain transmission performance information corresponding to the energy-saving strategy output by the transmission performance prediction model, the transmission performance prediction model corresponding to the device type of the first network device, the transmission performance prediction model being generated according to transmission performance training samples, each transmission performance training sample including transmission performance information, device configuration parameters corresponding to the transmission performance information, and throughput corresponding to the transmission performance information, the transmission performance prediction model including one or more of a delay prediction model, a jitter prediction model, and a packet loss prediction model.

6. The method of claim 1 or 2, wherein, When the first network device has a local constraint, the target energy-saving strategy meets the local constraint in addition to the preset condition, the local constraint indicating that one or more devices in the first network device operate according to preset parameters and / or the on-off states of multiple devices in the first network device remain consistent.

7. A method for adjusting a running state of a network device, characterized in that, The method comprises: The second network device receives first traffic information sent by the first network device, the first traffic information indicating a value of traffic processed by the first network device in a first time period; The second network device predicts second traffic information corresponding to the first network device in a second time period according to the first traffic information, the second time period being later than the first time period; The second network device obtains a transmission performance threshold and determines a throughput threshold according to the second traffic information, the transmission performance threshold including one or more of a delay threshold, a jitter threshold, and a packet loss threshold; The second network device sends the throughput threshold and the transmission performance threshold to the first network device, so that the first network device adjusts the operating state of the first network device according to the throughput threshold and the transmission performance threshold.

8. The method of claim 7, wherein, The second network device predicts second traffic information corresponding to the first network device in a second time period according to the first traffic information, comprising: The second network device inputs the first traffic information into a traffic prediction model to obtain the second traffic information output by the traffic prediction model, the traffic prediction model being generated by training historical traffic information of the first network device.

9. The method of claim 8, wherein, The method further comprises: The second network device receives the traffic prediction model.

10. The method of claim 9, wherein, The method further comprises: The second network device receives a throughput prediction model, an energy consumption prediction model, and a transmission performance prediction model sent by a cloud device, and sends the throughput prediction model, the energy consumption prediction model, or the transmission performance prediction model to the first network device.

11. The method of claim 10, wherein, The throughput prediction model, the energy consumption prediction model, or the transmission performance prediction model corresponds to the device type of the first network device, The energy consumption prediction model is generated according to energy consumption training samples, each energy consumption training sample including an energy consumption value and device configuration parameters corresponding to the energy consumption value; The throughput prediction model is generated according to throughput training samples, each throughput training sample including throughput and device configuration parameters corresponding to the throughput; The transmission performance prediction model is generated according to a transmission performance training sample, each transmission performance training sample including transmission performance information, device configuration parameters corresponding to the transmission performance information, and throughput corresponding to the transmission performance information.

12. A network system characterized by comprising: The system includes a first network device and a second network device; The first network device is configured to perform the method in any one of claims 1-6; The second network device is configured to perform the method in any one of claims 7-11.

13. The system of claim 12, wherein, The system further includes a cloud device; The cloud device is configured to receive statistical information sent by the second network device, the statistical information including historical traffic information of network devices managed by the second network device; The cloud device is further configured to train a traffic prediction model using the historical traffic information, and send the traffic prediction model to the second network device.

14. The system of claim 13, wherein, The cloud device is further configured to send a throughput prediction model, an energy consumption prediction model, or a transmission performance prediction model to the second network device.

15. A network device, comprising: The network device includes a processor and a memory; The memory is configured to store instructions or computer programs; The processor is configured to execute the instructions or computer programs in the memory, so that the network device performs the method in any one of claims 1-6, or performs the method in any one of claims 7-11.

16. A computer readable storage medium characterized by: The instructions, when executed on a computer, cause the computer to perform the method in any one of claims 1-6, or perform the method in any one of claims 7-11.

17. A computer program product, characterised in that, The computer program product, when executed on a computer, causes the computer to perform the method in any one of claims 1-6, or perform the method in any one of claims 7-11.

Images