Traffic transmission method, apparatus, system, and network device

Abstract

The application provides a traffic transmission method, device, system and network equipment. The method is applied to a first network equipment, the first network equipment comprises a physical interface, the physical interface transmits traffic through at least one channel, according to the traffic transmitted in a first time period, first period information of the traffic transmitted in a second time period is predicted, the first period information is used for indicating traffic values of the traffic at different time in a first period, and the second time period is located after the first time period; and according to the first period information, a switch state of the channel used for transmitting the traffic is determined. Therefore, dynamic control of the channel switch state can be realized, so that the energy consumption of traffic transmission is reduced.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a traffic transmission method, apparatus, system and network device. Background Technology

[0002] With the development of science and technology, global environmental problems have become more serious. Therefore, it is crucial to achieve green and low-carbon development and protect the environment while advancing technology.

[0003] Currently, with the deepening of digital transformation and the popularization of emerging technologies (such as cloud computing, big data, and artificial intelligence models), traffic has also exploded, resulting in a significant increase in the operating time and load of network communication equipment, which in turn increases the energy consumption of network communication.

[0004] Therefore, reducing the energy consumption of network communication is of paramount importance. Summary of the Invention

[0005] This application provides a traffic transmission method, apparatus, system, and network device. By predicting the period of traffic transmitted by the network device in advance, the on / off state of the traffic transmission channel can be determined based on the period, thereby enabling timely control of the traffic transmission channel's transmission state, improving the timeliness of traffic transmission, and dynamically determining the on / off state of the channel at different times based on the traffic value at different times, thereby reducing the energy consumption of network communication.

[0006] In a first aspect, embodiments of this application provide a traffic transmission method applied to a first network device, the first network device including a physical interface, the physical interface transmitting traffic through at least one channel, the method including:

[0007] Based on the traffic transmitted in the first time period, the first period information of the traffic transmitted in the second time period is predicted. The first period information is used to indicate the traffic value at different times in the first period. The second time period is located after the first time period.

[0008] Based on the information from the first cycle, determine the on / off state of the channel used for transmitting traffic.

[0009] In the above scheme, the first network device predicts the first periodic information of the traffic transmitted in the second time period based on the traffic transmitted in the first time period. This allows it to predict the periodic variation pattern of the traffic in the second time period, i.e., the traffic value at different times within the period. Thus, the first network device can determine the on / off state of the transmission channel in advance based on the first periodic information, thereby achieving timely control of the channel's on / off state and improving traffic transmission efficiency. Furthermore, the first network device can determine the channel's on / off state based on the traffic value at different times, enabling dynamic control of the channel's on / off state and reducing energy consumption during traffic transmission.

[0010] In one possible implementation, the first network device includes a first means for predicting first periodic information of the traffic transmitted in a second time period based on the traffic transmitted in a first time period, including:

[0011] The first device predicts the second period information of the traffic transmitted in the second period based on the traffic transmitted in the first time period. The second period information is used to indicate the traffic value at different times in the second period.

[0012] The first device determines the first cycle information based on the second cycle information.

[0013] In this way, the on / off state of transmission traffic can be controlled in a timely manner, thereby improving the transmission efficiency and realizing dynamic control of the channel's on / off state, reducing the energy consumption of network communication.

[0014] In one possible implementation, the first network device further includes a second means, and the method further includes:

[0015] The second device predicts the third period information of the traffic transmitted in the third time period based on the traffic transmitted in the third time period. The first time period is shorter than the third time period. The third period information is used to indicate the traffic value at different times in the third period.

[0016] The first device determines the first cycle information based on the second cycle information, including:

[0017] The first device determines the first period information from the second period information and the third period information, and the third period information is sent from the second device to the first device.

[0018] Thus, by combining the second cycle information predicted by the first device and the second cycle information predicted by the second device, the final first cycle information can be determined, enabling timely control of the switching state of the transmission flow, thereby improving the transmission efficiency of the flow and realizing dynamic control of the switching windows of the channel, reducing the energy consumption of network communication.

[0019] In one possible implementation, when the second cycle and the third cycle are the same, the first cycle is equal to the second cycle, and the information of the first cycle is the information of the second cycle.

[0020] When the second cycle is less than the third cycle, the first cycle is equal to the third cycle, and the information of the first cycle is the information of the third cycle.

[0021] In one possible implementation, the first device predicts second-period information of the traffic transmitted in a second time period based on the traffic transmitted in a first time period, including:

[0022] The first device predicts the second period information based on N fourth periods of the traffic transmitted within the first time period, where N is a positive integer.

[0023] This can improve the accuracy of cycle prediction.

[0024] In one possible implementation, the second device predicts third-cycle information of the traffic transmitted within the second time period based on the traffic transmitted within the third time period, including:

[0025] The second device predicts the third cycle information based on M fifth cycles of the traffic transmitted within the third time period.

[0026] Where M is a positive integer and N is less than M.

[0027] This can improve the accuracy of cycle prediction.

[0028] In one possible implementation, based on the traffic transmitted in the first time period, the first period information for predicting the traffic transmitted in future time periods includes:

[0029] Based on the traffic transmitted in the first time period, determine the traffic level of the traffic at multiple times in the second time period. The traffic level is used to indicate the numerical range of the traffic value.

[0030] The first period information is determined based on the traffic level of multiple times within the second time period.

[0031] The first period information refers to the traffic levels at different times within the first period.

[0032] In this way, by classifying traffic into traffic levels, it is unnecessary to control channels based on the traffic value at every moment; control is only required based on the traffic levels at different times. If the traffic levels are the same within a certain period, data caching and the use of computing resources can be reduced.

[0033] In one possible implementation, the switching state of the channel used for transmitting traffic is determined based on the first cycle information, including:

[0034] Based on the flow level at different times within the first cycle, determine the flow level corresponding to the first time. The first time is the moment when the flow level changes from the first flow level to the second flow level.

[0035] Based on the traffic level at the first moment, determine the on / off state of the channel used for traffic transmission.

[0036] In this way, controlling the switching state of the channel by changing the flow level can reduce the consumption of computing resources.

[0037] In one possible implementation, the switching state of the channel used for transmitting traffic is determined based on the traffic level corresponding to the first moment, including:

[0038] If the current time is the first time, and the traffic level corresponding to the current time matches the traffic level corresponding to the first time, then a control command is sent to the physical interface. The control command is used to indicate the on / off state of the channel at the first time.

[0039] In one possible implementation, the method also includes:

[0040] If the current time is the first time, and the traffic level corresponding to the current time does not match the traffic level corresponding to the first time, then the information for the first cycle is re-predicted based on the real-time traffic.

[0041] This improves the accuracy of controlling the switching status of the channel.

[0042] In one possible implementation, control commands are sent to the physical interface to enable all channels.

[0043] In this way, all channels are open during the prediction of the first period of information to avoid insufficient bandwidth and reduced traffic transmission efficiency when there are no prediction results.

[0044] In one possible implementation, the control command includes the channel's energy-saving type. When the energy-saving type is non-energy-saving, the channel's switch state is on, and when the energy-saving type is energy-saving, the channel's switch state is off.

[0045] Alternatively, the control instructions may include the number of channels to be opened;

[0046] Alternatively, control commands may include clock gating or power gating of the channel, with clock gating or gating used to indicate that the channel is closed.

[0047] In one possible implementation, the first device is a physical layer chip, which includes a physical interface;

[0048] Alternatively, the first device is a chip that manages the physical layer chip, and the communication distance between the first device and the physical layer chip is less than the communication distance between the second device and the physical layer chip.

[0049] Thus, since the channel interface is located on the physical layer chip, when the first device is a physical layer chip, or when the communication distance between the first device and the physical layer chip is relatively short, the switching state of the channel can be quickly controlled, thereby improving the transmission efficiency of traffic.

[0050] In one possible implementation, if the first device is a chip that manages the physical layer chip, the second device is the central processing unit (CPU) chip of the first network device.

[0051] Alternatively, if the first device is a physical layer chip, the second device is a chip that manages the physical layer chip.

[0052] In one possible implementation, the method also includes:

[0053] Send target information to the second network device. The target information is used to indicate the status information of the channel used for transmitting traffic in the second network device. The on / off status of the channel used for transmitting traffic in the second network device matches the on / off status of the channel used for transmitting traffic in the first network device.

[0054] In this way, the second network device, acting as the traffic receiver, can also control the switching status of the channel through the target information and synchronize with the first network device, acting as the sender, thereby reducing the energy consumption of traffic transmission while ensuring traffic transmission.

[0055] Secondly, this application provides a traffic transmission device applied to a first network device, the first network device including a physical interface, the physical interface transmitting traffic through at least one channel, the device comprising:

[0056] The prediction module is used to predict the first period information of the traffic transmitted in the second period based on the traffic transmitted in the first period. The first period information is used to indicate the traffic value at different times in the first period. The second period is located after the first period.

[0057] The determination module is used to determine the on / off state of the channel used for transmitting traffic based on the first cycle information.

[0058] In one possible implementation, the prediction module includes a first device;

[0059] The first device is used to predict the second period information of the traffic to be transmitted in the future time period based on the real-time transmission traffic. The second period information is used to indicate the traffic value at different times in the second period.

[0060] The determination module is used to determine the first cycle information based on the second cycle information.

[0061] In one possible implementation, the prediction module further includes a second device for predicting third period information of the traffic transmitted in the third time period based on the traffic transmitted in the third time period, wherein the first time period is shorter than the third time period, and the third period information is used to indicate the traffic value at different times in the third period.

[0062] The first device is used to determine the first period information from the second period information and the third period information, and the third period information is sent from the second device to the first device.

[0063] In one possible implementation, when the second cycle and the third cycle are the same, the first cycle is equal to the second cycle, and the information of the first cycle is the information of the second cycle.

[0064] When the second cycle is less than the third cycle, the first cycle is equal to the third cycle, and the information of the first cycle is the information of the third cycle.

[0065] In one possible implementation, the first device is used to predict second period information based on N fourth periods of traffic transmitted within a first time period, where N is a positive integer.

[0066] In one possible implementation, the second device is used to predict third period information based on M fifth periods of traffic transmitted within the third time period;

[0067] Where M is a positive integer and N is less than M.

[0068] In one possible implementation, based on the real-time transmitted traffic, the first period information of the traffic to be transmitted in the future time period is predicted, including:

[0069] Based on the real-time transmission traffic, determine the traffic level of traffic at multiple times within a future time period. The traffic level is used to indicate the numerical range of traffic values.

[0070] The first period information is determined based on the traffic levels at multiple points in the future time period.

[0071] The first period information refers to the traffic levels at different times within the first period.

[0072] In one possible implementation, the switching state of the channel used for transmitting traffic is determined based on the first cycle information, including:

[0073] Based on the flow level at different times within the first cycle, determine the flow level corresponding to the first time. The first time is the moment when the flow level changes from the first flow level to the second flow level.

[0074] Based on the traffic level at the first moment, determine the on / off state of the channel used for traffic transmission.

[0075] In one possible implementation, the switching state of the channel used for transmitting traffic is determined based on the traffic level corresponding to the first moment, including:

[0076] If the current time is the first time, and the traffic level corresponding to the current time matches the traffic level corresponding to the first time, then a control command is sent to the physical interface. The control command is used to indicate the on / off state of the channel at the first time.

[0077] In one possible implementation, the method also includes:

[0078] If the current time is the first time, and the traffic level corresponding to the current time does not match the traffic level corresponding to the first time, then the information for the first cycle is re-predicted based on the real-time traffic.

[0079] In one possible implementation, control commands are sent to the physical interface to enable all channels.

[0080] In one possible implementation, the control command includes the channel's energy-saving type. When the energy-saving type is non-energy-saving, the channel's switch state is on, and when the energy-saving type is energy-saving, the channel's switch state is off.

[0081] Alternatively, the control instructions may include the number of channels to be opened;

[0082] Alternatively, control commands may include clock gating or power gating of the channel, with clock gating or gating used to indicate that the channel is closed.

[0083] In one possible implementation, the first device is a physical layer chip, which includes a physical interface;

[0084] Alternatively, the first device is a chip that manages the physical layer chip, and the communication distance between the first device and the physical layer chip is less than the communication distance between the second device and the physical layer chip.

[0085] In one possible implementation, if the first device is a chip that manages the physical layer chip, the second device is the central processing unit (CPU) chip of the first network device.

[0086] Alternatively, if the first device is a physical layer chip, the second device is a chip that manages the physical layer chip.

[0087] In one possible implementation, the method also includes:

[0088] Send target information to the second network device. The target information is used to indicate the status information of the channel used for transmitting traffic in the second network device. The on / off status of the channel used for transmitting traffic in the second network device matches the on / off status of the channel used for transmitting traffic in the first network device.

[0089] Thirdly, this application provides a traffic transmission system, comprising:

[0090] A first network device is used to perform the method provided in the first aspect;

[0091] The second network device is used to receive target information sent by the first network device and, based on the target information, control the switching state of the channel used for transmitting traffic.

[0092] In this device, the switching state of the channel used for transmitting traffic in the second network device is matched with the switching state of the channel used for transmitting traffic in the first network device.

[0093] Fourthly, this application provides a network device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the method provided in the first aspect.

[0094] Fifthly, embodiments of this application provide a network device, characterized in that the device executes computer program instructions to perform the method provided in the first aspect. Exemplarily, the device may be a chip or a processor.

[0095] In one example, the device may include a processor that can be coupled to memory, read instructions from the memory, and execute the methods provided in the first aspect according to those instructions. The memory may be integrated into the chip or processor, or it may be independent of the chip or processor.

[0096] In a sixth aspect, embodiments of this application provide a computer storage medium storing instructions that, when executed on a computer, cause the computer to perform the method provided in the first aspect.

[0097] In a seventh aspect, embodiments of this application provide a computer program product containing instructions that, when executed on a computer, cause the computer to perform the method provided in the first aspect.

[0098] Any of the devices, computer storage media, or computer program products provided above are used to execute the methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding solutions in the corresponding methods provided above, and will not be repeated here. Attached Figure Description

[0099] Figure 1 This is a schematic diagram of the structure of an Ethernet circuit interface provided in an embodiment of this application;

[0100] Figure 2 This is a schematic diagram of the structure of a logical physical interface provided in an embodiment of this application;

[0101] Figure 3 This is a schematic diagram of the switching state of a logical communication link for transmitting traffic, provided in an embodiment of this application.

[0102] Figure 4 This is a schematic diagram of the switching state of the control logic communication link in the prior art provided in the embodiments of this application;

[0103] Figure 5 This is a schematic diagram of the architecture of a traffic transmission system provided in an embodiment of this application;

[0104] Figure 6 This is a schematic diagram of the structure of a network device provided in an embodiment of this application;

[0105] Figure 7 This is a flowchart illustrating a method for transmitting network device traffic according to an embodiment of this application;

[0106] Figure 8 This is a schematic flowchart illustrating an exemplary method for transmitting network device traffic, provided in an embodiment of this application.

[0107] Figure 9 This is a schematic flowchart of a traffic transmission method provided in an embodiment of this application;

[0108] Figure 10 This is a flowchart illustrating a traffic analysis method provided in an embodiment of this application;

[0109] Figure 11 This is a flowchart illustrating a method for predicting first-period information provided in an embodiment of this application;

[0110] Figure 12 This is a schematic diagram illustrating traffic levels at different timestamps provided in an embodiment of this application;

[0111] Figure 13 This is a schematic diagram illustrating a change process in traffic flow level provided in an embodiment of this application;

[0112] Figure 14 This is an exemplary schematic diagram of a method for predicting first periodic information provided in an embodiment of this application;

[0113] Figure 15 This is a schematic diagram illustrating the synchronous control channel switch status of the transmitting and receiving ends according to an embodiment of this application;

[0114] Figure 16 This is a schematic diagram of the structure of a traffic transmission device provided in an embodiment of this application;

[0115] Figure 17 This is a schematic diagram of the structure of a network device provided in an embodiment of this application. Detailed Implementation

[0116] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0117] With the development of technology, global environmental problems have become increasingly serious. Therefore, it is crucial to achieve green and low-carbon development and environmental protection while advancing technology. Currently, with the deepening of digital transformation and the popularization of emerging technologies (such as cloud computing, big data, and artificial intelligence models), data traffic is also growing explosively, leading to a significant increase in the operating time and load of network communication equipment, and consequently increasing the energy consumption of network communication.

[0118] Ethernet is a common communication technology. Ethernet uses specific physical layer and data link layer specifications to define how data is transmitted in the network. The physical (PHY) layer defines the electrical and optical signals, line states, clock references, data encoding, and circuitry required for data transmission and reception, and provides a standard interface to data link layer devices. The data link layer provides functions such as addressing mechanisms, data frame construction, data error checking, transmission control, and providing a standard data interface to the network layer. In Ethernet, the chip at the data link layer is called a Medium Access Control (MAC) controller. The data link layer includes several sublayers, such as the MAC layer.

[0119] From a hardware perspective, the Ethernet circuit interface includes a MAC controller and a PHY interface. The MAC controller and PHY interface can be deployed on the same chip, or they can use separate chips, depending on the specific situation. This application does not impose specific limitations on this embodiment. Traffic is transmitted from the sending end to the receiving end; therefore, the Ethernet circuit interface deployed on the sending end and the Ethernet circuit interface deployed on the receiving end are the same. Taking the MAC controller and PHY interface deployed on the same chip, and the physical transmission medium connected to the PHY interface being optical fiber, as an example... Figure 1 As shown, both the transmitting and receiving ends of the chip include a MAC layer and a PHY layer. When transmitting data, the PHY layer encodes the data from the MAC layer, and the optical module converts the encoded data into an optical signal, which is then forwarded through the optical fiber. The MAC layer may include a Reconciliation Sublayer (RS), and the PHY layer includes a Physical Coding Sublayer (PCS) and a Physical Medium Attachment (PMA). The optical module includes a PMA and a Physical Medium Dependent (PMD) sublayer. The PMA of the optical module corresponds to the PMA of the PHY layer, and the optical module and the chip communicate through the PMA.

[0120] To reduce the energy consumption of network communication, related technologies divide the PHY interface into multiple logical communication links, with complete bandwidth isolation between these links. For example, such as... Figure 2 As shown, at the PCS layer, the PHY interface is divided into multiple logical communication links. In terms of hardware, to achieve complete isolation between these logical communication links, the chip and the optical module can be connected via multiple physical channels. There is a one-to-one correspondence between the physical channels and the logical communication links.

[0121] To achieve dynamic energy saving, related technologies employ dynamic energy saving based on actual traffic flow. Traffic is categorized into different traffic levels, with different logical communication links operating at different levels. The physical channels corresponding to operating logical communication links are open, while the physical channels corresponding to dormant logical communication links are closed. This allows for dynamic control of the switching on and off of physical channels, thereby reducing network communication energy consumption. For example, such as... Figure 3 As shown, with Figure 1 and Figure 2 Based on this, let's assume that traffic is divided into four levels, numbered 1 to 4, according to the amount of data transmitted. Traffic level 1 is 100GB or less; level 2 is 100GB or more but less than or equal to 200GB; level 3 is 200GB or more but less than or equal to 300GB; and level 4 is 300GB or more but less than or equal to 400GB. The PHY interface is divided into four logical communication links. At traffic level 1 (100GB), one of the four logical communication links is active, while the remaining three are in a dormant state. At traffic level 4 (400GB), all four logical communication links are active.

[0122] Currently, such as Figure 4 As shown, the state switching of the logical communication link relies on instructions from the upper-layer software to trigger dynamic power-saving functionality. Figure 3 and Figure 4It is known that the dynamic energy-saving function is deployed at the PHY layer. From a hardware perspective, the upper-layer software is geographically distant from the PHY layer. The dynamic energy-saving function is triggered by the upper-layer software sending commands to the PHY layer to switch the state of the logical communication link. However, this process is not timely, resulting in delayed state switching of the logical communication link. When traffic is high, the logical communication link needs to switch from a dormant state to an active state, but due to the distance between the upper-layer software and the logical communication link, the switching may be delayed, leading to low traffic transmission efficiency. Conversely, when traffic is low, the logical communication link needs to switch from an active state to a dormant state, but again, the distance may result in delayed switching, wasting communication link resources and increasing energy consumption.

[0123] Therefore, it is crucial to ensure timely switching of logical communication links so as to save transmission resources and reduce energy consumption while maintaining traffic transmission efficiency.

[0124] Based on the above problems, the inventors discovered that in some scenarios, such as high-performance computing (HPC) or artificial intelligence (AI) clusters, traffic exhibits periodic variations. For example, during model training using an AI cluster, each training iteration includes steps such as data loading, forward propagation, backpropagation, and gradient synchronization, which need to be repeated periodically. Moreover, within each step, the traffic variation is also periodic. For instance, the data loading step includes stages such as data input, data processing, and data output, which need to be repeated periodically, accompanied by periodic variations in traffic.

[0125] Based on this, embodiments of this application provide a traffic transmission method, apparatus, system, and network device. In this method, a first network device uses the traffic transmitted within a first time period to predict the first periodic information of the traffic transmitted within a second time period. This allows the device to predict the periodic variation pattern of the traffic within the second time period, i.e., the traffic value at different times within the period. Thus, the first network device can determine the on / off state of the traffic transmission channel in advance based on the first periodic information, thereby achieving timely control of the on / off state of the traffic transmission channel and improving traffic transmission efficiency. Furthermore, the first network device can determine the on / off state of the channel based on the traffic value at different times, enabling dynamic control of the channel on / off state and reducing the energy consumption of traffic transmission.

[0126] Before describing in detail the traffic transmission method provided in the embodiments of this application, the traffic transmission system provided in the embodiments of this application will be described in detail first.

[0127] Figure 5 This is a schematic diagram of the architecture of a traffic transmission system provided in an embodiment of this application. Figure 5 As shown, the traffic transmission system provided in this application embodiment includes a first network device 51 and a second network device 52. In some examples, the first network device 51 and the second network device 52 provided in this application embodiment may be network devices such as switches, routers, and base stations.

[0128] In this embodiment of the application, the first network device 51 and the second network device 52 respectively have the following features: Figure 2 The physical interface shown can be found in the above description. Figure 2 The detailed description of the physical interface shown will not be repeated here.

[0129] The first network device 51 can act as a traffic sender, through methods such as... Figure 2 The physical interface shown sends traffic to the second network device 52. The second network device 52 sends traffic through, as shown in... Figure 2 The physical interface shown receives traffic. In this embodiment, to save energy for both the first network device 51 and the second network device 52 during traffic transmission, the first network device 51 can determine the on / off state of the traffic transmission channel by executing the traffic transmission method provided in this embodiment. Specifically, the first network device 51 predicts the first periodic information of the traffic transmitted in the second time period based on the traffic transmitted in the first time period, thereby predicting the periodic change pattern of the traffic in the second time period, i.e., the traffic value at different times within the period. Thus, the first network device can determine the on / off state of the traffic transmission channel in advance based on the first periodic information, thereby achieving timely control of the on / off state of the traffic transmission channel and improving traffic transmission efficiency. Furthermore, the first network device can determine the on / off state of the channel based on the traffic value at different times. Then, when the periodic information of the traffic at the current time matches the first periodic information, the first network device 51 sends target information to the second network device 52. The second network device 52 controls the on / off state of the traffic transmission channel in the second network device based on the target information. The channel status used for transmitting traffic in the first network device 51 is matched with the channel status used for transmitting traffic in the second network device 52.

[0130] For example, if three channels in the first network device used for transmitting traffic are open and the remaining channels are closed, then the target information is used to instruct the three channels to be open and the remaining channels to be closed. Thus, the number of channels in the first network device used for transmitting traffic is the same as the number of channels in the second network device used for transmitting that traffic.

[0131] Figure 6This is a schematic diagram of the structure of a network device provided in an embodiment of this application. The network device provided in this embodiment can be either the first network device or the second network device described in the above embodiments. Figure 6 As shown, the network device provided in this application embodiment includes a first chip 601, a second chip 602, and a third chip 603. The first chip 601, the second chip 602, and the third chip 603 are communicatively connected.

[0132] The first chip 601 manages the second chip 602 and the third chip 603. The third chip 603 has an Ethernet circuit interface deployed in it; that is, both the MAC layer and the PHY layer are deployed in the third chip 603. The third chip 603 can achieve the following: Figure 2 The interface shown is logicalized, thereby achieving energy-saving functions through flexible logical communication links. The second chip 602 is a chip that can directly manage and control the third chip 603. The first chip 601 is the computing and control core of the network device. The first chip 601 can be a processor such as a microprocessor or a central processing unit (CPU), depending on actual needs. This application embodiment does not make specific limitations.

[0133] From a network architecture perspective, the first chip 601 is the upper-layer chip of the second chip 602, and the second chip 602 is the upper-layer chip of the third chip 603. When the network device receives traffic, the third chip 603 parses the traffic and then transmits it to the first chip 601 via the second chip 602.

[0134] In the embodiments of this application, such as Figure 7 As shown, network devices can identify patterns in traffic flow and generate control commands based on these patterns. The third chip, 603, then executes energy-saving functions based on these control commands.

[0135] In some embodiments, in order to reduce the consumption of computing resources, such as Figure 7 As shown, before analyzing the periodic patterns of traffic flow, the traffic transmission system can collect and preprocess traffic data to reduce traffic volume.

[0136] The function to identify patterns in traffic changes is deployed in the chip. Next, based on... Figure 6 The network devices shown are described in terms of their deployment methods for analyzing the periodic patterns of traffic.

[0137] In some embodiments, such as Figure 8As shown, the buffer capacity of the first chip 601 is greater than that of the second chip 602. The first chip 601 can analyze the periodic pattern of the traffic to obtain periodic pattern 1, and the second chip 602 can analyze the periodic pattern of the traffic to obtain periodic pattern 2. The second chip 602 makes decisions based on periodic pattern 1 and periodic pattern 2 to generate control commands. Alternatively, the first chip 601 makes decisions based on periodic pattern 1 and periodic pattern 2 to generate control commands. The control commands are used to indicate the on / off state of each logical communication link.

[0138] For example, the first chip 601 may be a central processing unit (CPU), and the second chip may be a processor such as Mcore or Xcore. In another example, the first chip 601 may be Xcore, and the second chip may be Mcore.

[0139] In other embodiments, the second chip 602 analyzes the periodic pattern of the traffic flow and generates control commands based on this pattern. The second chip 602 sends the control commands to the third chip 603, which then controls the switching state of the logic communication link according to the commands, thereby achieving energy saving.

[0140] In some embodiments, based on the spatial location of the hardware, the second chip is the closest chip to the third chip among all chips. In other words, the signal transmission distance between the second chip and the third chip is the smallest, and the signal transmission speed is the fastest, thus ensuring high signal transmission timeliness.

[0141] It should be noted that, Figure 6 This is merely an illustrative example of a traffic transmission system. The system may also include other chips, and the chips capable of analyzing traffic are not limited to the first and second chips. The number of chips in the traffic transmission system can be set according to actual conditions, and the number of chips capable of analyzing traffic can be adjusted accordingly. This application does not impose specific limitations on this.

[0142] The technical solution provided in this application will be described in detail below.

[0143] Figure 9 This is a flowchart illustrating a traffic transmission method provided in an embodiment of this application. The traffic transmission method provided in this application is applied to the traffic sending end, wherein the sending end can be any network device in the network capable of acting as a sending end, such as... Figure 5 The first network device shown. (As shown) Figure 9 As shown, the traffic transmission method provided in this application includes the following steps S901 and S902.

[0144] S901, based on the traffic transmitted in the first time period, predict the first period information of the traffic transmitted in the second time period. The first period information is used to indicate the traffic value at different times in the first period. The second time period is located after the first time period.

[0145] The first time period refers to the period between a certain point in the past and the current point in time. After receiving traffic, network devices can buffer the traffic within the first time period. The first period information is used to indicate the traffic value at different times within the first period. Specifically, the first period is the period predicted by the network device based on the traffic within the first time period; that is, the network device predicts that the traffic will repeat in the first period within the second time period.

[0146] In some embodiments, the network device includes a first device. The first device is hardware deployed in the network device and has caching and computing capabilities. The first device is capable of predicting second-period information of the transmission traffic in a second time period based on the traffic in a first time period. The second-period information refers to the traffic values ​​at different times within the second period. The first device determines the first-period information based on the second-period information.

[0147] In one possible implementation of this application, the first periodic information is the second periodic information.

[0148] Since traffic flow itself has a certain periodicity, the first device can predict the second periodic information of the traffic flow in the second time period based on the traffic flow within the first time period. As one possible implementation, the first device predicts the second periodic information based on N fourth periods of the traffic flow transmitted within the first time period, where N is a positive integer. For example, if the first device analyzes that the traffic flow transmitted within the first time period repeats N times with a period of T = 5ms, the first device determines the first periodic information based on the N times the traffic flow has a period of T = 5ms.

[0149] In other embodiments, the network device further includes a second device. The second device is hardware deployed within the network device and possesses caching and computing capabilities. The second device is capable of predicting second-period information of the traffic within a third time period based on the traffic transmitted within that third time period. The third time period refers to the time interval between a past moment and the current moment. The third time period is longer than the second time period. The third-period information is used to indicate the traffic values ​​at different times within the third period. The third period is the period predicted by the network device based on the traffic within the third time period; that is, the network device predicts that the traffic will repeat in a first period within the second time period.

[0150] In this embodiment, the second device can send third periodic information to the first device, thereby allowing the first device to determine the first periodic information based on the second and third periodic information. The third periodic time is shorter than the second periodic time; in other words, the second device's buffering capacity is greater than the first device's buffering capacity. The first periodic information is predicted. To improve the accuracy of the first periodic information, when the second and third periods are the same, the first period is equal to either the second or third period, and the first periodic information is the second periodic information. When the second period is shorter than the third period, the first period is equal to the third period, and the first periodic information is the third periodic information.

[0151] In this embodiment, as one possible implementation, the second device is used to predict third period information based on M fifth periods of traffic transmitted within the third time period; where M is a positive integer and N is less than M.

[0152] For example, in the above embodiments, the first device may be Figure 6 The second chip or second device in the illustrated embodiment may be... Figure 6 The first chip in the illustrated embodiment.

[0153] In another exemplary embodiment, the first device is a physical layer chip, which includes a physical interface; or, the first device is a chip that manages the physical layer chip, and the communication distance between the first device and the physical layer chip is less than the communication distance between the second device and the physical layer chip. For example, if the first device is a chip that manages the physical layer chip, the second device is a central processing unit (CPU) chip of the first network device; or, if the first device is a physical layer chip, the second device is a chip that manages the physical layer chip.

[0154] In this embodiment of the application, time can be represented in the form of a timestamp.

[0155] In some embodiments, to reduce the consumption of computing resources and the occupation of storage resources, before S801, the method further includes sampling the traffic to reduce the amount of data cached in the network device. The network device collects traffic according to a sampling step size. The sampling step size can be pre-deployed, or it can be updated periodically or deployed in real time by the user through a network management platform, etc. In actual implementation, the size of the sampling step size can be specifically set according to the actual situation, and this application embodiment does not impose a specific limitation.

[0156] For example, the waveform data of the traffic acquired by the network device is as follows: Figure 10As shown in part (a), the flow rate appears in periods of 1.2 ms, and there are a total of 5 periods (6 ms) of flow rate in part (a). Assuming a sampling step size of 10 μs, after sampling the flow rate based on the sampling step size, 120 data points can be obtained in each period. Thus, the waveform data of the sampled flow rate is as follows: Figure 10 Part (b) shown contains 600 data points. The network device... Figure 10 The storage format of part (b) shown is as follows: Figure 10 Part (c) shown contains the flow rate value at each sampling point and the timestamp t_ corresponding to each sampling point.

[0157] In some embodiments, the first period information is used to indicate the traffic level at different times within the first period. In a specific implementation, the network device determines the traffic level of traffic at multiple times within a second time period based on the traffic transmitted within the first time period, whereby the traffic level indicates the numerical range of the traffic value; and determines the first period information based on the traffic level of traffic at multiple times within the second time period.

[0158] Before analyzing traffic, network devices can classify traffic based on traffic values. One possible implementation is that after sampling the traffic, the network device classifies the sampled traffic based on the traffic value at each sampling point. Figure 10 Based on this, the waveform of the sampled flow rate is as follows: Figure 11 As shown in part (a), for Figure 11 The flow rate is classified into different levels in section (a) shown below. The waveform diagram after the flow rate classification is as follows: Figure 11 As shown in section (b). To reduce storage resource consumption, the network device determines first information, which indicates the timestamp corresponding to the change in traffic value. For example, as Figure 11 As shown in section (c), each cycle has four transition edges, thus enabling the generation of multiple traffic levels and a corresponding timestamp t for each traffic level. The timestamp t represents the timestamp corresponding to each traffic value change, i.e., the timestamp corresponding to the transition edge. In this way, the network device can store data such as... Figure 11 The tuple shown in section (d) has a traffic level of 0 starting at timestamp t1, a change in traffic level from 0 to 1 at timestamp t2, and a change in traffic level from 1 to 2 at timestamp t3. Thus, the network device... Figure 11 The data shown in section (d) is used to make predictions and obtain information for the first period.

[0159] As one possible implementation, the network device can further process the first-cycle information by subtracting each pair of timestamps t, thereby obtaining... Figure 11 The data shown in section (e) is based on the network device. Figure 11 The data shown in section (e) is used to predict the period of the flow value, thus obtaining the first period information. For example, based on... Figure 11 The data shown in section (e) is the information for the first period, as shown in Table 1.

[0160] Table 1

[0161]

[0162]

[0163] S902, based on the first cycle information, determines the switching state of the channel used for transmitting traffic.

[0164] A channel refers to a pathway used to transmit traffic. Specifically, a channel can refer to, for example... Figure 2 The diagram shows multiple logical communication links.

[0165] In some embodiments, the first period information is used to indicate the traffic value at different times within the first period. Different traffic values ​​result in different channel on / off states. The network device determines the channel on / off state based on the traffic values ​​at different times.

[0166] In other embodiments, the first period information is used to indicate the traffic level at different times within the first period. Specifically, in the implementation process, the network device can determine the traffic level corresponding to the first moment based on the traffic levels at different times within the first period, where the first moment is the moment when the traffic level changes from a first traffic level to a second traffic level; and determine the on / off state of the channel used for transmitting traffic based on the traffic level corresponding to the first moment.

[0167] For example, the number of logical communication links opened varies depending on the traffic level. For instance, a traffic level of 1 indicates a traffic value less than or equal to 100G. Since the bandwidth of a logical communication link is 100G, only one logical communication link needs to be opened. The division of traffic levels and the number of logical communication links opened for different traffic levels can be deployed according to actual conditions, and this application does not specifically limit this. For example, when the traffic value is 0, the traffic level is 0, and 0 logical communication links are opened. When the traffic value is greater than 0 but less than or equal to 1G, the traffic level is 1, and one logical communication link is opened. When the traffic value is greater than 1G but less than or equal to 2G, the traffic level is 2, and two logical communication links are opened, and so on.

[0168] The network device controls the on / off state of the channel based on the first cycle information. Specifically, if the current time is the first time and the traffic level corresponding to the current time matches the traffic level corresponding to the first time, a control command is sent to the physical interface to indicate the on / off state of the channel at the first time.

[0169] In some embodiments, the control command includes the energy-saving type of the channel. The energy-saving type includes energy-saving and non-energy-saving; when the energy-saving type is non-energy-saving, the channel is on. When the energy-saving type is energy-saving, the channel is off. When the energy-saving type is energy-saving, the control command also includes the number of channels that are off. Alternatively, the control command can be used to indicate the energy-saving type of each channel, thereby controlling different channels according to their respective energy-saving types.

[0170] For example, when the traffic value is 0, the traffic level is 0, and 0 logical communication links are open. When the traffic value is greater than 0 and less than or equal to 1G, the traffic level is 1, and one logical communication link is open. When the traffic value is greater than 1G and less than or equal to 2G, the traffic level is 2, and two logical communication links are open, and so on. The information for the first cycle is shown in Table 2.

[0171] Table 2

[0172] Traffic level The timestamp t corresponding to the change in traffic level 0 2024-11-11T00:00:00.00000 1 2024-11-11T00:00:04.78552 0 2024-11-11T00:00:08.57042 1 2024-11-11T00:00:13.35594 2 2024-11-11T00:00:17.14084 4 2024-11-11T00:00:21.92636 …… ……

[0173] Based on the first cycle information shown in Table 2, control commands are generated as shown in Table 3.

[0174] Table 3

[0175] The timestamp t corresponding to the change in traffic level Energy saving type Number of closed channels 2024-11-11T00:00:00.00000 Energy saving 4 2024-11-11T00:00:04.78552 Energy saving 3 2024-11-11T00:00:08.57042 Energy saving 4 2024-11-11T00:00:13.35594 Energy saving 3 2024-11-11T00:00:17.14084 Energy saving 2 2024-11-11T00:00:21.92636 Non-energy-saving 0 ……

[0176] In other embodiments, the control instructions include the number of channels to be activated. For example, the first cycle information is shown in Table 1. Then the number of channels activated at different times is shown in Table 4.

[0177] Table 4

[0178] The timestamp t corresponding to the change in traffic level quantity 2024-11-11T00:00:00.00000 0 2024-11-11T00:00:04.78552 1 2024-11-11T00:00:08.57042 0 2024-11-11T00:00:13.35594 1 2024-11-11T00:00:17.14084 2 2024-11-11T00:00:21.92636 4 …… ……

[0179] In some other embodiments, the control commands include clock gating or power gating of the channel, the clock gating or gating being used to indicate that the channel is closed.

[0180] In some embodiments, if the current time is the first time and the traffic level corresponding to the current time does not match the traffic level corresponding to the first time, then the first period information is re-predicted based on the real-time traffic. Simultaneously, the network device also needs to send control commands to the communication interface to fully open all channels for traffic transmission. This avoids a decrease in traffic transmission efficiency during the re-prediction of the first period information.

[0181] Based on the above embodiments, the embodiments of this application will be described exemplarily below with the first device being chip 2 and the second device being chip 1.

[0182] Assume the network device includes chip 1 and chip 2, where chip 2 directly manages the physical layer chip. Chip 1 has a larger cache capacity than chip 2. Chip 1 can store 52 tuples consisting of traffic level and its corresponding duration, while chip 2 can store 6 tuples consisting of traffic level and its corresponding duration. Chip 1 has a sliding window 1, and chip 2 has a sliding window 2, with the duration of sliding window 1 being longer than that of sliding window 2. Assume the traffic level classification method is as follows: Figure 3 The traffic level classification method shown is as follows: After the network device classifies the traffic into traffic levels, the traffic level and the corresponding duration are shown in Table 1.

[0183] The waveforms corresponding to the data shown in Table 1 are as follows: Figure 12 As shown, the flow rate first appears 7 times in cycle P1, then 4 times in cycle P2. Overall, it can be considered to appear in a cycle of P3. In other words, cycle P3 includes 7 cycles of P1 and 4 cycles of P2. In cycle P1, the duration of flow rate level 0 is 4.78552s, and the duration of flow rate level 1 is 3.7849s. In cycle P2, the duration of flow rate level 0 is 2.40696s, the duration of flow rate level 1 is 3.92287s, and the duration of flow rate level 2 is 2.30856s.

[0184] like Figure 13 As shown, the data corresponding to Table 1 is input into chip 1 and chip 2 respectively, and chip 1 and chip 2 traverse the data corresponding to Table 1 respectively. Among them, when the starting point of sliding window 1 traverses to the position shown in (1), and the starting point of sliding window 2 traverses to the position shown in (1), as shown in (1), Figure 14 As shown, the periodic information output by both chip 1 and chip 2 is empty. In this case, the first periodic information is empty, and the network device adopts a non-energy-saving mode. When sliding window 1 traverses to the position shown in (2), and sliding window 2 traverses to the position shown in (2), it can be found that the traffic level appears in a periodic pattern of 0, 1, 0, 1, and the duration appears in a periodic pattern of 4.78552s, 3.7849s, 4.78552s, 3.7849s. At this time, as Figure 13As shown, chip 1 obtains periodic information 1, and chip 2 obtains periodic information 2. Periodic information 1 and periodic information 2 are identical, both occurring according to period P1, i.e., the period [(0, 4.78552s), (1, 3.7849s)]. Therefore, chips 1 and 2 can predict that the change in traffic level in the future will occur according to period P1. Thus, the network device obtains the first periodic information based on periodic information 1 and periodic information 2, as shown in Table 5. Based on the first periodic information shown in Table 5, the network device controls the switching states of multiple logical communication links, thereby achieving energy saving.

[0185] Table 2

[0186] Traffic level The timestamp t corresponding to the change in traffic level 0 2024-11-11T00:00:00.00000 1 2024-11-11T00:00:04.78552 0 2024-11-11T00:00:08.57042 1 2024-11-11T00:00:13.35594 0 2024-11-11T00:00:17.14084 1 2024-11-11T00:00:21.92636 …… ……

[0187] like Figure 13 As shown, when sliding window 1 traverses to the position shown in (3), and sliding window 2 traverses to the position shown in (3), the flow rate level changes again. To ensure that the prediction results in Table 5 are correct, it is necessary to compare the changed flow rate level and the timestamp corresponding to the flow rate level with Table 5. If the comparison results are consistent, chip 1 and chip 2 will refresh the output table. In the implementation process, chip 1 determines timestamp 1 after the flow rate level changes, and chip 2 determines timestamp 2 after the flow rate level changes. After the flow rate level changes, it is determined whether the flow rate level is consistent with the flow rate level in the third row of Table 5. If the flow rate level is consistent, it is compared whether timestamp 1 is consistent with the timestamp in the third row of Table 5, and whether timestamp 2 is consistent with the timestamp in the third row of Table 5. Figure 12 As can be seen from the examples, the prediction results shown in Table 5 are correct. Thus, as... Figure 14 As shown in Table 5, the first-cycle information indicates that traffic will change in a cycle P1 within a short period of time in the future. Therefore, network devices can control the operating status of multiple logical communication links based on the timestamps and traffic levels in Table 5. For example, at timestamp "2024-11-11T00:00:08.57042", the traffic level is 0, indicating that all logical communication links are closed. At timestamp "2024-11-11T00:00:13.35594", the traffic level is 1, one logical communication link is open, and the remaining logical communication links are closed. This allows for energy saving during traffic transmission.

[0188] like Figure 13 As shown, when sliding window 1 traverses to the position shown in (4), and sliding window 2 traverses to the position shown in (4), period P1 has appeared 7 times, and at this time, the period has changed. Among them, as Figure 14As shown, the timestamp when the traffic level changes does not match the previously identified first cycle information. Therefore, chips 1 and 2 cannot output cycle information; that is, the cycle information output by chip 1 is "empty," and the cycle information output by chip 2 is "empty." Consequently, the final first cycle information is also "empty." In this situation, chips 1 and 2 need to re-identify the first cycle information, and the network devices adopt a non-energy-saving mode, that is, all multiple logical communication links are open.

[0189] like Figure 13 As shown, when sliding window 1 traverses to the position shown in (5), and sliding window 2 traverses to the position shown in (5), both chip 1 and chip 2 can identify the new first cycle information. Chip 1 identifies cycle P2, that is, cycle information 1 appears with the cycle [(0, 2.40696s), (1, 3.92287s), (2, 2.30856s)], and chip 2 identifies cycle P2. Among them, cycle information 1 and cycle information 2 are the same, and the traffic changes according to cycle P2. In this way, the network device outputs the first cycle information based on cycle information 1 and cycle information 2. Figure 14 As shown, the first-cycle information indicates that traffic changes in a cycle P2 over a short period of time in the future. Network devices can control the operating status of multiple logical communication links based on this first-cycle information, thereby achieving energy savings.

[0190] like Figure 13 As shown, when sliding window 1 traverses to the position shown in (6), and sliding window 2 traverses to the position shown in (6), period P2 appears 4 times consecutively, and at this time the period changes. Among them, as Figure 14 As shown, the timestamp when the traffic level changes does not match the first cycle information identified earlier. Therefore, chips 1 and 2 cannot output cycle information; that is, cycle information 1 output by chip 1 is "empty," and cycle information 2 output by chip 2 is "empty." Consequently, the first cycle information is also "empty." Therefore, the network device adopts an energy-inefficient mode.

[0191] like Figure 13 As shown, when sliding window 1 traverses to the position shown in (8), and sliding window 2 traverses to the position shown in (8), both chip 1 and chip 2 can identify period P1. Both chip 1 and chip 2 identify period P1, meaning the traffic occurs according to the period [(0, 4.78552s), (1, 3.7849s)]. Thus, the network device refreshes the information of the first period based on period P1. Figure 14 As shown, the first cycle information indicates that traffic will change in a cycle P1 over a short period of time in the future. Network devices can control the operating status of multiple logical communication links based on this first cycle information, thereby achieving energy savings. And so on... Figure 13The processes shown in (8) to (12) are the same as those described above. For details, please refer to the descriptions of (1) to (7) above. They will not be repeated here.

[0192] like Figure 13 As shown, when sliding window 1 traverses to the position shown in (13), and sliding window 2 traverses to the position shown in (13), period P2 has appeared 4 times consecutively. However, at this time, the period changes. The timestamp when the flow rate level changes is different from the information in the first period, so chip 1 and chip 2 need to re-identify the information in the first period. For example... Figure 14 As shown, because chip 1 has a larger cache capacity than chip 2, chip 2 cannot perceive longer-term periodic information during the initial re-identification of the first cycle information. Therefore, the traffic level change pattern 1 output by chip 2 is empty, while chip 1 can perceive longer-term periodic information. Based on this, chip 1 can identify cycle information 1 based on the cached data, where cycle information 1 indicates that the traffic appears according to the pattern of cycle P3. Since the time domain that chip 1 can perceive is larger than that that that chip 2 can perceive, the first cycle information output by the network device indicates that the traffic will appear according to the pattern of cycle P3 in the future. The cycle information 1 of chip 1 matches the actual traffic level change, therefore, chip 1 does not need to run the prediction action of the first cycle information in the future. However, chip 2 can perceive a shorter time domain, therefore, it will frequently trigger the prediction action of the first cycle information in the future.

[0193] In some embodiments, to ensure synchronized energy saving between the receiver and transmitter, the network device acting as the transmitter sends target information to the receiver based on the first cycle information. The target information indicates the status information of the channel used for traffic transmission in the receiver, and the on / off state of the channel used for traffic transmission in the receiver matches the on / off state of the channel used for traffic transmission in the transmitter. For example, such as... Figure 15 As shown, chip 1 in the first network device analyzes the traffic and obtains periodic information 1, while chip 2 analyzes the traffic and obtains periodic information 2. Chip 1 sends periodic information 1 to chip 2. Chip 2 makes a decision based on periodic information 1 and periodic information 2 to obtain the first periodic information. Based on the first periodic information, it generates control commands and target information. The control command generated by the first network device is to open 3 channels; therefore, the target information is the same as the control command, with 3 channels opened. In this way, the receiving and transmitting ends can simultaneously achieve energy saving.

[0194] Based on the same concept as the embodiments of the method in this application, this application also provides a traffic transmission device. The traffic transmission device includes several modules, each module being used to execute various steps in the traffic transmission method provided in the embodiments of this application. The division of modules is not limited here. Those skilled in the art will clearly understand that in practical applications, the various steps in the traffic transmission method provided in the embodiments of this application can be assigned to different modules as needed, that is, the internal structure of the device can be divided into different modules to complete all or part of the functions described above. The modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0195] For example, the traffic transmission device is used to perform the traffic transmission method provided in the embodiments of this application. Figure 16 This is a schematic diagram of the traffic transmission device provided in an embodiment of this application. The traffic transmission device provided in this embodiment is applied to a first network device, which includes a physical interface that transmits traffic through at least one channel. Figure 16 As shown, the traffic transmission device provided in this application embodiment includes:

[0196] The prediction module 1601 is used to predict the first period information of the traffic transmitted in the second period based on the traffic transmitted in the first period. The first period information is used to indicate the traffic value at different times in the first period. The second period is located after the first period.

[0197] The determination module 1602 is used to determine the switching state of the channel used for transmitting traffic based on the first cycle information.

[0198] In one possible implementation, the prediction module includes a first device;

[0199] The first device is used to predict the second period information of the traffic to be transmitted in the future time period based on the real-time transmission traffic. The second period information is used to indicate the traffic value at different times in the second period.

[0200] The determination module is used to determine the first cycle information based on the second cycle information.

[0201] In one possible implementation, the prediction module further includes a second device for predicting third period information of the traffic transmitted in the third time period based on the traffic transmitted in the third time period, wherein the first time period is shorter than the third time period, and the third period information is used to indicate the traffic value at different times in the third period.

[0202] The first device is used to determine the first period information from the second period information and the third period information, and the third period information is sent from the second device to the first device.

[0203] In one possible implementation, when the second cycle and the third cycle are the same, the first cycle is equal to the second cycle, and the information of the first cycle is the information of the second cycle.

[0204] When the second cycle is less than the third cycle, the first cycle is equal to the third cycle, and the information of the first cycle is the information of the third cycle.

[0205] In one possible implementation, the first device is used to predict second period information based on N fourth periods of traffic transmitted within a first time period, where N is a positive integer.

[0206] In one possible implementation, the second device is used to predict third period information based on M fifth periods of traffic transmitted within the third time period;

[0207] Where M is a positive integer and N is less than M.

[0208] In one possible implementation, based on the real-time transmitted traffic, the first period information of the traffic to be transmitted in the future time period is predicted, including:

[0209] Based on the real-time transmission traffic, determine the traffic level of traffic at multiple times within a future time period. The traffic level is used to indicate the numerical range of traffic values.

[0210] The first period information is determined based on the traffic levels at multiple points in the future time period.

[0211] The first period information refers to the traffic levels at different times within the first period.

[0212] In one possible implementation, the switching state of the channel used for transmitting traffic is determined based on the first cycle information, including:

[0213] Based on the flow level at different times within the first cycle, determine the flow level corresponding to the first time. The first time is the moment when the flow level changes from the first flow level to the second flow level.

[0214] Based on the traffic level at the first moment, determine the on / off state of the channel used for traffic transmission.

[0215] In one possible implementation, the switching state of the channel used for transmitting traffic is determined based on the traffic level corresponding to the first moment, including:

[0216] If the current time is the first time, and the traffic level corresponding to the current time matches the traffic level corresponding to the first time, then a control command is sent to the physical interface. The control command is used to indicate the on / off state of the channel at the first time.

[0217] In one possible implementation, the method also includes:

[0218] If the current time is the first time, and the traffic level corresponding to the current time does not match the traffic level corresponding to the first time, then the information for the first cycle is re-predicted based on the real-time traffic.

[0219] In one possible implementation, control commands are sent to the physical interface to enable all channels.

[0220] In one possible implementation, the control command includes the channel's energy-saving type. When the energy-saving type is non-energy-saving, the channel's switch state is on, and when the energy-saving type is energy-saving, the channel's switch state is off.

[0221] Alternatively, the control instructions may include the number of channels to be opened;

[0222] Alternatively, control commands may include clock gating or power gating of the channel, with clock gating or gating used to indicate that the channel is closed.

[0223] In one possible implementation, the first device is a physical layer chip, which includes a physical interface;

[0224] Alternatively, the first device is a chip that manages the physical layer chip, and the communication distance between the first device and the physical layer chip is less than the communication distance between the second device and the physical layer chip.

[0225] In one possible implementation, if the first device is a chip that manages the physical layer chip, the second device is the central processing unit (CPU) chip of the first network device.

[0226] Alternatively, if the first device is a physical layer chip, the second device is a chip that manages the physical layer chip.

[0227] In one possible implementation, the method also includes:

[0228] Send target information to the second network device. The target information is used to indicate the status information of the channel used for transmitting traffic in the second network device. The on / off status of the channel used for transmitting traffic in the second network device matches the on / off status of the channel used for transmitting traffic in the first network device.

[0229] Based on the same concept as the method embodiments of this application, this application also provides a network device. This network device can be a data forwarding device such as a switch or router.

[0230] like Figure 17 As shown, the network device 1700 provided in this application embodiment includes a processor 1701, a memory 1702, and a communication interface 1703.

[0231] In this embodiment, the processor 1701 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0232] The memory 1702 may include a large-capacity memory for data or instructions, thereby providing storage space for the network device's operating system and executable program code, which may include, but is not limited to: Windows (an operating system), Linux (an operating system), HarmonyOS (an operating system), etc.

[0233] For example, and not as a limitation, memory 1702 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1702 may include removable or non-removable (or fixed) media. Where appropriate, memory 1702 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 1702 is a non-volatile solid-state memory.

[0234] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory may include one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software that may include computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to this application.

[0235] For example, a computer program may be stored on memory 1702, and when processor 1701 executes the computer program, it implements the steps in the above method embodiments. Alternatively, when processor 1701 executes the computer program, it implements the functions of each module in the above device embodiments. Exemplarily, the computer program may be divided into one or more modules / units, which may be a series of computer program instruction segments capable of performing a specific function. One or more modules / units are stored in memory 1702 and executed by processor 1701 to complete this application. For example, the computer program may be divided into multiple modules, as in the modules of the device described above.

[0236] The communication interface 1703 is used to send and receive data, for example, to send data processed by the processor 1701 to other network devices, or to receive data sent by other network devices.

[0237] Of course, for the sake of simplicity, Figure 17 Only some of the components of the network device 1700 relevant to this application are shown, omitting components such as buses, input / output interfaces, etc. In addition, the network device 1700 may include any other suitable components depending on the specific application. Furthermore, the network device can be a desktop computer, laptop, handheld computer, or cloud server, etc. Those skilled in the art will understand that... Figure 17 This is merely an example of network device 1700 and does not constitute a limitation on network devices. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, a network device may also include input devices, output devices, network access devices, buses, etc. For example, the input device may be a microphone array, and may also include, for example, a keyboard, mouse, etc. For example, the output device may output various information to the outside, and may include, for example, a monitor, speakers, printer, and communication networks and their connected remote output devices, etc.

[0238] In addition to the methods, apparatus, and computing devices described above, embodiments of this application may also provide a computer program product, comprising computer program instructions. When executed by a processor, the computer program instructions cause the processor to perform the steps of the methods in the various embodiments of this application described in the "Method" section of this specification. The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The computer program code can be in source code form, object code form, executable file, or some intermediate form. The computer program code can be executed entirely on a user's computing device, partially on a user's device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0239] Furthermore, embodiments of this application may also provide a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the display control method according to various embodiments of this disclosure as described in the "Method" section above. The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. It should be noted that the content contained in a computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, a computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0240] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0241] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. It should be understood that in the embodiments of this application, the order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0242] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of this application.

Claims

1. A method for transmitting traffic, characterized in that, Applied to a first network device, the first network device including a physical interface, the physical interface transmitting traffic through at least one channel, the method includes: Based on the traffic transmitted in the first time period, the first period information of the traffic transmitted in the second time period is predicted. The first period information is used to indicate the traffic value at different times in the first period. The second time period is located after the first time period. Based on the first periodic information, the on / off state of the channel used to transmit the traffic is determined.

2. The method according to claim 1, characterized in that, The first network device includes a first apparatus, wherein the first periodic information for predicting the traffic transmitted in a second time period based on the traffic transmitted in a first time period includes: The first device predicts second periodic information of the traffic transmitted in the second time period based on the traffic transmitted in the first time period. The second periodic information is used to indicate the traffic value at different times in the second period. The first device determines the first period information based on the second period information.

3. The method according to claim 2, characterized in that, The first network device further includes a second device, and the method further includes: The second device predicts the third period information of the traffic transmitted in the third time period based on the traffic transmitted in the third time period. The first time period is shorter than the third time period. The third period information is used to indicate the traffic value at different times in the third period. The step of determining the first period information based on the second period information using the first device includes: The first periodic information is determined by the first device from the second periodic information and the third periodic information, and the third periodic information is sent from the second device to the first device.

4. The method according to claim 3, characterized in that, When the second period and the third period are the same, the first period is equal to the second period, and the first period information is the second period information. When the second period is less than the third period, the first period is equal to the third period, and the first period information is the third period information.

5. The method according to claim 3 or 4, characterized in that, The second periodic information for predicting the traffic transmitted in the second time period based on the traffic transmitted in the first time period using the first device includes: The first device predicts the second cycle information based on N fourth cycles of the traffic transmitted within the first time period, where N is a positive integer.

6. The method according to any one of claims 3-5, characterized in that, The step of predicting the third periodic information of the traffic transmitted in the second time period based on the traffic transmitted in the third time period using the second device includes: The second device predicts the third period information based on M fifth periods of traffic transmitted within the third time period; Where M is a positive integer and N is less than M.

7. The method according to any one of claims 1-6, characterized in that, The first periodic information for predicting traffic in future time periods based on traffic transmitted within a first time period includes: Based on the traffic transmitted during the first time period, the traffic level of the traffic at multiple times during the second time period is determined, and the traffic level is used to indicate the numerical range of the traffic value. The first period information is determined based on the traffic level of traffic at multiple times within the second time period; The first period information refers to the traffic flow level at different times within the first period.

8. The method according to claim 7, characterized in that, Determining the on / off state of the channel used for transmitting the traffic based on the first periodic information includes: Based on the flow rate at different times within the first cycle, the flow rate corresponding to the first time is determined, where the first time is the moment when the flow rate changes from the first flow rate to the second flow rate. Based on the traffic level corresponding to the first moment, determine the on / off state of the channel used to transmit the traffic.

9. The method according to claim 8, characterized in that, The step of determining the on / off state of the channel used to transmit the traffic based on the traffic level corresponding to the first time moment includes: If the current time is the first time, and the traffic level corresponding to the current time matches the traffic level corresponding to the first time, then a control command is sent to the physical interface. The control command is used to indicate the on / off state of the channel at the first time.

10. The method according to claim 9, characterized in that, The method further includes: If the current time is the first time, and the traffic level corresponding to the current time does not match the traffic level corresponding to the first time, then the first period information is re-predicted based on the real-time traffic.

11. The method according to claim 10, characterized in that, Send control commands to the physical interface to enable all channels.

12. The method according to any one of claims 9-11, characterized in that, The control command includes the energy-saving type of the channel. When the energy-saving type is non-energy-saving, the channel is in an on state; when the energy-saving type is energy-saving, the channel is in an off state. Alternatively, the control command may include the number of channels to be activated; Alternatively, the control commands may include clock gating or power gating of the channel, the clock gating or gating being used to instruct the channel to be turned off.

13. The method according to any one of claims 3-6, characterized in that, The first device is a physical layer chip, and the physical layer chip includes the physical interface; Alternatively, the first device is a chip that manages the physical layer chip, and the communication distance between the first device and the physical layer chip is less than the communication distance between the second device and the physical layer chip.

14. The method according to claim 13, characterized in that, In the case where the first device is a chip that manages the physical layer chip, the second device is the central processing unit (CPU) chip of the first network device; Alternatively, if the first device is the physical layer chip, the second device is a chip that manages the physical layer chip.

15. The method according to any one of claims 1-14, characterized in that, The method further includes: Send target information to the second network device, the target information being used to indicate the status information of the channel in the second network device used to transmit the traffic, the on / off status of the channel in the second network device used to transmit the traffic matching the on / off status of the channel in the first network device used to transmit the traffic.

16. A flow transmission device, characterized in that, Applied to a first network device, the first network device including a physical interface, the physical interface transmitting traffic through at least one channel, the apparatus comprising: The prediction module is used to predict the first period information of the traffic transmitted in the second period based on the traffic transmitted in the first period. The first period information is used to indicate the traffic value at different times in the first period. The second period is located after the first period. The determining module is used to determine the switching state of the channel used to transmit the traffic based on the first periodic information.

17. The apparatus according to claim 16, characterized in that, The prediction module includes the first device; The first device is used to predict second period information of the traffic transmitted in the future time period based on the real-time transmission traffic. The second period information is used to indicate the traffic value at different times in the second period. The determining module is used to determine the first period information based on the second period information.

18. The apparatus according to claim 17, characterized in that, The prediction module further includes a second device, which is used to predict the third period information of the traffic transmitted in the third time period based on the traffic transmitted in the third time period. The first time period is shorter than the third time period. The third period information is used to indicate the traffic value at different times in the third period. The first device is used to determine the first periodic information from the second periodic information and the third periodic information, wherein the third periodic information is sent from the second device to the first device.

19. The apparatus according to claim 18, characterized in that, When the second period and the third period are the same, the first period is equal to the second period, and the first period information is the second period information. When the second period is less than the third period, the first period is equal to the third period, and the first period information is the third period information.

20. The apparatus according to claim 18 or 19, characterized in that, The first device is used to predict the second period information based on N fourth periods of the traffic transmitted within the first time period, where N is a positive integer.

21. The apparatus according to claim 20, characterized in that, The second device is used to predict the third period information based on M fifth periods of traffic transmitted within the third time period; Where M is a positive integer and N is less than M.

22. A flow transmission system, characterized in that, include: A first network device, configured to perform the method according to any one of claims 1-15; The second network device is used to receive target information sent by the first network device and control the switching state of the channel used for transmitting traffic according to the target information. The switching state of the channel used to transmit the traffic in the second network device matches the switching state of the channel used to transmit the traffic in the first network device.

23. A network device, characterized in that, include: Memory, used to store executable code; A processor, configured to implement the method of any one of claims 1-15 when executing the executable code.

24. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed in a computer, causes the computer to perform the method described in any one of claims 1-15.

25. A computer program product containing instructions, characterized in that, When the instructions are executed on a computer, the computer causes the computer to perform the method as described in any one of claims 1-15.

Images