Device energy-saving method and system, electronic device, and storage medium

Abstract

Provided in the embodiments of the present disclosure are a device energy-saving method and system, an electronic device, and a storage medium. The method comprises: acquiring a network state diagram sequence, wherein the network state diagram sequence comprises network state diagrams of a network device at a plurality of moments, the network state diagrams at the plurality of moments being used for representing a network topology structure of the network device at the plurality of moments, and the plurality of moments comprising the current moment; on the basis of the network state diagram sequence, determining a first energy-saving risk value of the network device, wherein the first energy-saving risk value is used for representing the risk degree of energy saving of the network device under the network topology structure at the current moment; and sending the first energy-saving risk value to the network device.

Description

Device energy-saving method and system, electronic device and storage medium

[0001] This disclosure claims priority to Chinese patent application No. 202410031239.9, filed on January 9, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the field of communication technology, and in particular to a device energy-saving method and system, an electronic device, and a storage medium. Background Art

[0003] Currently, network equipment energy consumption accounts for a significant portion of operators' expenses. Under the dual-carbon policy's energy conservation and emission reduction requirements, operators have clearly stated the need to reduce network equipment power consumption. Energy-saving operations on network equipment often come with certain energy-saving risks. Minor energy-saving risks may result in decreased processing performance, while severe energy-saving risks may lead to network service interruptions. Therefore, it is necessary to determine a more accurate energy-saving strategy to balance the benefits and risks of energy-saving network equipment. Summary of the Invention

[0004] In a first aspect, an embodiment of the present disclosure provides a device energy saving method, which is applied to a management device connected to a network device, and includes:

[0005] Acquire a network status graph sequence, wherein the network status graph sequence includes network status graphs of the network device at multiple moments, and the network status graphs at the multiple moments are used to characterize the network topology structure of the network device at the multiple moments, and the multiple moments include the current moment; determine a first energy-saving risk value of the network device based on the network status graph sequence, and the first energy-saving risk value is used to characterize the risk level of energy saving of the network device under the network topology structure at the current moment; and send the first energy-saving risk value to the network device.

[0006] In a second aspect, an embodiment of the present disclosure provides a device energy saving method, which is applied to a network device connected to a management device, and includes:

[0007] Receive a first energy-saving risk value sent by a management device, where the first energy-saving risk value is used to characterize the risk level of energy saving for the network device under the current network topology structure; determine an energy-saving strategy based on the operating status of the network device and the first energy-saving risk value; and perform energy-saving operations on the network device based on the energy-saving strategy and load prediction information of the network device.

[0008] In a third aspect, an embodiment of the present disclosure provides a device energy-saving apparatus, which is applied to manage devices and includes: an acquisition unit, a processing unit, and a sending unit.

[0009] The acquisition unit is used to acquire a network status diagram sequence; the network status diagram sequence includes network status diagrams of the network device at multiple moments, and the network status diagrams at multiple moments are used to represent the network topology structure of the network device at multiple moments, and the multiple moments include the current moment.

[0010] The processing unit is used to determine a first energy-saving risk value of the network device based on the network state diagram sequence, where the first energy-saving risk value is used to characterize the risk level of energy saving of the network device under the network topology structure at the current moment.

[0011] The sending unit is configured to send the first energy-saving risk value to the network device.

[0012] In a fourth aspect, an embodiment of the present disclosure provides a device energy-saving apparatus, which is applied to a network device and includes a communication unit and a processing unit.

[0013] The communication unit is configured to receive a first energy-saving risk value sent by a management device, where the first energy-saving risk value is used to characterize a risk level of energy saving of the network device under a current network topology.

[0014] The processing unit is configured to determine an energy-saving strategy based on an operating state of the network device and a first energy-saving risk value.

[0015] The processing unit is further configured to perform energy-saving operations on the network device based on the energy-saving strategy and load prediction information of the network device.

[0016] In the fifth aspect, an embodiment of the present disclosure provides a device energy-saving system, which includes a management device and a network device. Here, the management device is used to execute the device energy-saving method provided by the first aspect above, and the network device is used to execute the device energy-saving method provided by the second aspect above.

[0017] In the sixth aspect, an embodiment of the present disclosure provides an electronic device, comprising: a memory and one or more processors; the memory stores instructions executable by one or more processors; when the one or more processors are configured to execute instructions, the electronic device implements the device energy saving method provided in any one of the first or second aspects above.

[0018] In a seventh aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer executes the device energy-saving method provided in either the first aspect or the second aspect.

[0019] In an eighth aspect, an embodiment of the present disclosure provides a computer program product comprising computer instructions, which, when executed on a computer, enables the computer to execute the device energy-saving method provided in either the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to provide a further understanding of the technical solution of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the technical solution of the present disclosure and do not constitute a limitation to the technical solution of the present disclosure.

[0021] FIG1 is a schematic diagram showing the composition of a device energy-saving system according to some embodiments of the present disclosure;

[0022] FIG2 is a flow chart of a device energy-saving method according to some embodiments of the present disclosure;

[0023] FIG3 is a flow chart of another device energy-saving method according to some embodiments of the present disclosure;

[0024] FIG4 is a flow chart of another device energy-saving method according to some embodiments of the present disclosure;

[0025] FIG5 is a schematic diagram showing the composition of a management device and a network device according to some embodiments of the present disclosure;

[0026] FIG6 is a block diagram of a device energy-saving apparatus according to some embodiments of the present disclosure;

[0027] FIG7 is a block diagram of another device energy saving apparatus according to some embodiments of the present disclosure;

[0028] FIG8 is a block diagram of an electronic device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0029] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present disclosure.

[0030] Unless the context requires otherwise, throughout the specification and claims, the term "comprise" and its other forms, such as the third person singular form "comprises" and the present participle form "comprising", are to be interpreted as open and inclusive, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "example", "specific example" or "some examples" are intended to indicate that the particular features, structures, materials or characteristics associated with the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representation of the above terms does not necessarily refer to the same embodiment or example. In addition, the particular features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner.

[0031] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this disclosure, unless otherwise specified, "plurality" means two or more.

[0032] In the embodiments of the present disclosure, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present disclosure should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present the relevant concepts in an illustrative manner.

[0033] Additionally, the use of “based on” is meant to be open and inclusive, as a process, step, calculation, or other action “based on” one or more stated conditions or values ​​may, in practice, be based on additional conditions or values ​​beyond those stated.

[0034] Currently, the solutions and problems for energy saving methods for network equipment are as follows:

[0035] (1) The energy-saving strategies of network equipment are manually selected by operation and maintenance personnel, which places high demands on them and lacks a comprehensive energy-saving risk assessment. Network equipment in important network locations may be affected by aggressive energy-saving strategies and have poor controllability.

[0036] (2) Network devices use fixed energy-saving strategies. Since the service configuration and service load of network devices change over time, if network devices use fixed energy-saving strategies, there is a lack of real-time adjustment, and the energy-saving strategies cannot be matched with the service configuration and service load of network devices. This leads to poor flexibility and poor energy-saving effects of network devices.

[0037] (3) Operation and maintenance personnel often choose more conservative energy-saving strategies to avoid energy-saving risks that may arise from energy-saving operations. This makes the energy-saving effect of network equipment fail to meet expectations and the energy-saving effect is poor.

[0038] In summary, current energy-saving methods lack accuracy in determining energy-saving strategies and fail to effectively balance the energy-saving benefits and risks of network equipment, resulting in poor energy-saving performance. Improving the energy-saving performance of network equipment is an urgent issue to be addressed.

[0039] Based on this, embodiments of the present disclosure provide a device energy-saving method and system, an electronic device, and a storage medium. The device energy-saving method includes: a management device determining, based on a network state graph of the network device at multiple times including the current time (i.e., a sequence of network state graphs), the risk level (i.e., a first energy-saving risk value) for energy-saving for the network device under the current network topology. This improves the accuracy of determining the first energy-saving risk value, thereby helping to improve the energy-saving effect of the network device.

[0040] The technical solution of the present disclosure is described below with reference to the accompanying drawings.

[0041] Figure 1 is a schematic diagram of a device energy-saving system according to some embodiments of the present disclosure. Referring to Figure 1 , the device energy-saving system includes a management device 11 and at least one network device (eg, network device 21 , network device 22 , and network device 23 ).

[0042] Here, the management device 11 is connected to each network device in the at least one network device, and the connection may be through a wired network or a wireless network, which is not limited in the embodiment of the present disclosure.

[0043] In some embodiments, when the at least one network device includes multiple network devices, at least two network devices among the multiple network devices may also be connected via a wired network or a wireless network.

[0044] In some embodiments, the management device 11 can be an independent physical device, such as an electronic device with computing and processing capabilities, such as a server or a computer. Here, the server can be a single server, or it can be a server cluster composed of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. In some embodiments, the server can also be implemented on a cloud platform, that is, the server can also be a cloud server. For example, the cloud server can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, and a multi-cloud, etc., or any combination thereof.

[0045] In some embodiments, the management device 11 may be integrated with one of the at least one network device. That is, the functions of the management device 11 and the functions of one of the at least one network device or the network device may be integrated into the same physical device. For example, the management device 11 may be integrated with the network device 21, but this is not limited in the present embodiment.

[0046] In some embodiments, for each network device in at least one network device, the network device is a physical entity connected to the network. There are many types of network devices, and the types are increasing day by day. Network devices may include: hubs, switches, bridges, routers, gateways, packet transport network (PTN) devices, slicing packet network (SPN) devices, network interface cards (NICs), wireless access points (APs), modems, and fiber optic transceivers, etc. Network devices may also have other names, such as network elements, network element devices, communication devices, etc., which are not limited in the embodiments of the present disclosure.

[0047] In some embodiments, the management device 11 is configured to obtain a network state graph sequence, determine a first energy-saving risk value of a network device based on the network state graph sequence, and then send the first energy-saving risk value of the network device to the network device. The network device may be any one of the at least one network device.

[0048] In some embodiments, for any one of at least one network device, the network device is used to receive a first energy-saving risk value sent by a management device, and then determine an energy-saving strategy based on the operating status of the network device and the first energy-saving risk value, and then perform energy-saving operations on the network device based on the energy-saving strategy and load prediction information of the network device.

[0049] It should be understood that Figure 1 is an exemplary structural diagram, and the number of devices included in the device energy-saving system shown in Figure 1 is not limited. For example, the number of management devices and the number of network devices are not limited. Furthermore, in addition to the devices shown in Figure 1, the device energy-saving system shown in Figure 1 may also include other devices, which are not limited in the embodiments of the present disclosure.

[0050] Next, as shown in FIG2 , an embodiment of the present disclosure provides a device energy saving method, which is applied to a management device. The management device may be the management device 11 shown in FIG1 . The method may include S101 to S103 .

[0051] In S101 , a network status graph sequence is obtained.

[0052] In some embodiments, the management device executes a device energy saving method provided by an embodiment of the present disclosure after turning on the device energy saving function. Correspondingly, the management device does not execute or stops executing a device energy saving method provided by an embodiment of the present disclosure after turning off the device energy saving function.

[0053] In some embodiments, the management device enables the device energy saving function by default or periodically.

[0054] In other embodiments, the management device determines whether to turn on or off the energy-saving function of the device according to the user's instructions.

[0055] In some embodiments, after the management device turns on the device energy saving function, the management device obtains a network status diagram sequence.

[0056] In other embodiments, after receiving the energy-saving instruction, the management device obtains the network state diagram sequence in response to the energy-saving instruction. Here, the energy-saving instruction can be issued by the user or sent by the network device, which is not limited in the embodiments of the present disclosure.

[0057] In yet other embodiments, the management device obtains a network state graph sequence when detecting that the network device needs to perform an energy-saving operation. Here, the management device detecting that the network device needs to perform an energy-saving operation may be determining that the network device needs to perform an energy-saving operation when the management device detects that the energy consumption of the network device per unit time is greater than or equal to an energy consumption threshold.

[0058] In some embodiments, the network status graph sequence includes network status graphs of the network device at multiple times, and the network status graphs at multiple times are used to represent the network topology of the network device at multiple times. The network device can be any one of the at least one network device connected to the management device.

[0059] In some embodiments, as shown in FIG3 , step S101 may include steps S1011 to S1013 .

[0060] In S1011 , network topology information of the network device at each of a plurality of moments is obtained.

[0061] Here, the multiple moments may include the current moment and historical moments before the current moment. The current moment may be the moment when the management device obtains the network status graph sequence. It should be understood that the network topology information of the network device changes dynamically. Based solely on the network topology information of the network device at a particular moment, it may not be possible to comprehensively assess the risk of energy conservation of the network device. Therefore, the multiple moments may include the current moment and historical moments, thereby comprehensively assessing the risk of energy conservation of the network device. The network topology information of the network device at the current moment may be obtained by the management device at the current moment, while the network topology information of the network device at historical moments may be obtained by the management device in the cache queue.

[0062] In some embodiments, the network topology information includes at least one of the following: the network level of the network device, the network topology of the network device, the configuration information of the network device, or the link load status. It can be understood that the device energy-saving system shown in Figure 1 may include multiple network devices, and the network level of the network device can be used to indicate the level at which the network device is located in the device energy-saving system; the network topology of the network device can be used to indicate the connection relationship between the network devices in the device energy-saving system, which can be understood as how multiple network devices are connected together in the device energy-saving system; the configuration information of the network device indicates the settings and parameters of the network device, and the configuration information of the network device can be used to configure and manage the network device to achieve normal operation of the network device; the link refers to the physical channel connecting the network devices, which carries the task of data transmission; the link load status is used to characterize the data processing capability and data transmission efficiency of the link.

[0063] In some embodiments, the network topology information may further include an identification of a network device and performance data of the network device. Here, the performance data of the network device includes port traffic of the network device.

[0064] In S1012, based on the network topology information of the network device at each of the multiple moments, a network status graph of the network device at each of the multiple moments is obtained.

[0065] In some embodiments, after obtaining network topology information of network devices at each of multiple moments, the management device may aggregate the network topology information of the network devices at each of the multiple moments to simplify service connections between network devices and obtain a network status graph of the network devices at each of the multiple moments. Here, the network status graph at each moment represents static information of the network topology structure at that moment.

[0066] In S1013 , a network status graph sequence is obtained based on the network status graph of the network device at each of the multiple moments.

[0067] In some embodiments, after obtaining the network status graph of the network device at each of the multiple moments, the management device may aggregate the network status graph of the network device at each of the multiple moments to obtain a network status graph sequence.

[0068] In some embodiments, taking the current moment among multiple moments as an example, the mathematical model construction process of the network status graph at the current moment is as follows:

[0069] For the current time t, the feature vector v is formed according to the network topology information of the network device v t , v t As a node in the network state diagram, it represents the network state of the network device. Then, the feature vector is formed based on the bidirectional network topology information between network devices. As an edge in the network state graph, it represents the business relationship between network device v and network device v'. Network device v' is a network device connected to network device v in the device energy saving system.

[0070] For the current time t, all network devices v at the current time t (t) Composed of network device set V (t) , all edges Constituent edge set E (t) , then the network status graph at the current moment can be expressed as G (t) ={V (t) ,E (t)}.

[0071] Then, the management device can use the current network status graph G (t) And obtain the network state graph of the previous T-1 historical moments from the cache queue to form a network state graph sequence G (1:T) , G (1:T) The network status graph of T network devices is obtained by sampling the network topology information of the network devices at time intervals τ. The process of constructing the mathematical model of the network status graph at the T-1 historical moment can refer to the process of constructing the mathematical model of the network status graph at the current moment, and will not be described in detail in the present embodiment.

[0072] In S102 , a first energy-saving risk value of the network device is determined based on the network status graph sequence.

[0073] Here, the first energy-saving risk value of the network device is used to represent the risk level of energy saving of the network device under the current network topology.

[0074] In some embodiments, a management device pre-stores an energy-saving risk prediction model based on a graph neural network algorithm. Determining a first energy-saving risk value for a network device based on a network state graph sequence may involve inputting the network state graph sequence into the energy-saving risk prediction model based on a graph neural network algorithm to obtain the first energy-saving risk value for the network device.

[0075] It should be understood that after the network status graph sequence is input into the energy-saving risk prediction model based on the graph neural network algorithm, the energy-saving risk prediction model based on the graph neural network algorithm aggregates the network status graph sequence through local information and time-varying information, and then calculates and infers the first energy-saving risk value of the network device based on the attention mechanism.

[0076] Here, local information aggregation refers to extracting the network topology information of the network device v, that is, the network status graph G at the current time t (t) , using message passing neural network to monitor network devices v (t) The network topology information of the network device v at the current moment is aggregated with the network topology information of its neighboring network devices. (t) The spatial eigenvector of Time-varying information aggregation refers to extracting the network state graph sequence G (1:T) Time-varying laws over time. Because the network topology of network devices changes dynamically, it may not be possible to fully evaluate the energy-saving risks of network devices based only on the network status diagram of the network devices at a certain moment. Therefore, it is necessary to conduct an analysis based on the network status diagram of the network devices at historical moments. (1:T) After local information aggregation, the spatial feature vector of network device v can be obtained Then use the loop processing unit to Processing is performed to obtain the hidden matrix Then, according to the attention mechanism A first energy-saving risk value R1 of the network device is obtained by calculation.

[0077] Here, neighbor network devices refer to other network devices that are directly connected to a local device (such as a local computer, server, network switch, etc.) or are adjacent to each other in the same local area network (LAN) or subnet.

[0078] In S103, a first energy-saving risk value is sent to the network device.

[0079] In some embodiments, after obtaining the first energy-saving risk value of the network device, the management device can send the first energy-saving risk value corresponding to the network device to the network device, so that the network device can determine a more accurate energy-saving strategy based on the corresponding first energy-saving risk value, thereby improving the energy-saving effect of the network device.

[0080] Based on the embodiment shown in FIG2 , the first energy-saving risk value of a network device is used to characterize the risk level of energy conservation for the network device under the current network topology. The first energy-saving risk value of the network device is determined based on network status graphs of the network device at multiple time points (i.e., a sequence of network status graphs). The network status graphs at multiple time points are used to characterize the network topology of the network device at multiple time points. In other words, the risk level of energy conservation for the network device under the current network topology (i.e., the first energy-saving risk value) is determined based on the network topology of the network device at multiple time points, including the current time point. This improves the accuracy of determining the first energy-saving risk value, thereby contributing to improved energy conservation for the network device.

[0081] In some embodiments, as shown in Figure 4, an embodiment of the present disclosure also provides a device energy-saving method, which is applied to a network device. The network device can be any one of the network devices shown in Figure 1 above. For example, the network device can be network device 21. The method can include steps S201 to S203.

[0082] In S201 , a first energy-saving risk value sent by a management device is received.

[0083] Here, the first energy-saving risk value is used to characterize the risk level of energy saving of the network device under the current network topology. For the description of the first energy-saving risk value, reference can be made to the corresponding description in the embodiment shown in FIG2 above, and the present embodiment will not be repeated here.

[0084] In S202 , an energy-saving strategy is determined based on the operating state of the network device and the first energy-saving risk value.

[0085] In some embodiments, determining an energy-saving strategy based on the operating state of a network device and a first energy-saving risk value may include determining a second energy-saving risk value for the network device based on the operating state of the network device, and then determining the energy-saving strategy based on the first energy-saving risk value and the second energy-saving risk value. Here, the second energy-saving risk value represents the risk level of energy conservation for the network device under the current operating state.

[0086] It should be understood that the above-mentioned first energy-saving risk value is determined by the management device based on the network status diagram sequence, which can be understood as being determined by the management device based on the overall situation of the network device in the device energy-saving system, and the second energy-saving risk value is determined by the network device based on the operating status of the network device, and then the energy-saving strategy determined based on the first energy-saving risk value and the second energy-saving risk value, that is, the energy-saving strategy of the network device is comprehensively determined from two levels: the device energy-saving system (that is, the network level) and the network device (that is, the device level), which improves the accuracy of determining the energy-saving strategy, thereby effectively balancing the relationship between the energy-saving benefits and energy-saving risks of the network device, and improving the energy-saving effect of the network device.

[0087] In some embodiments, the operating status of a network device includes at least load information of a board in the network device. Determining the second energy-saving risk value of the network device based on the operating status of the network device can be performed by obtaining the energy-saving risk value of the board in the network device based on the load information of the board in the network device and a timing prediction algorithm, and then obtaining the second energy-saving risk value of the network device based on the energy-saving risk value of the board in the network device. Here, the load information of the board is used to represent the traffic volume of the board. The load information of the board can be obtained by the network device aggregating port traffic information of each port on the board.

[0088] Here, a single board refers to the switching board that handles traffic distribution. A single board contains multiple components, which are independent integrated chips within a circuit. These include, but are not limited to, processors, memory, and forwarding chips. Multiple chips and their interconnects form a module, which is a circuit system composed of multiple chips and interconnects that together perform related functions. The three levels of granularity—board, chip, and module—complement each other, enabling refined management.

[0089] In some embodiments, the time series prediction algorithm may include but is not limited to at least one of the following: a time series prediction algorithm based on machine learning or a neural network time series prediction algorithm.

[0090] In some embodiments, different timing prediction algorithms correspond to different weight coefficients or the same weight coefficients. Based on the load information of the single board in the network device and the timing prediction algorithm, the energy-saving risk value of the single board in the network device is obtained. The network device can make predictions based on different timing prediction algorithms and the load information of the single board in the network device to obtain multiple prediction results, and then combine the weight coefficient of the timing prediction algorithm corresponding to each prediction result to perform weighted average calculation on the multiple prediction results, and then use the result of the weighted average calculation as the energy-saving risk value of the single board in the network device.

[0091] In some embodiments, the network device includes one or more boards.

[0092] In some embodiments, when the network device includes one board, after obtaining the energy-saving risk value of the board in the network device, the energy-saving risk value of the board in the network device may be used as the second energy-saving risk value of the network device.

[0093] In other embodiments, when the network device includes multiple boards, the management device may determine the second energy-saving risk value for the network device based on the energy-saving risk values ​​of the multiple boards. For example, the management device may determine a target board from the multiple boards and then determine the energy-saving risk value of the target board as the second energy-saving risk value for the network device. Here, the target board may be the board with the highest energy-saving risk value among the multiple boards. For another example, the management device may determine the average of the energy-saving risk values ​​of the multiple boards as the second energy-saving risk value for the network device.

[0094] In some embodiments, the operating status of a network device may further include device performance data and device component status information. Here, the device performance data includes at least one of the following: port traffic information, central processing unit (CPU) utilization, or memory utilization. The device component status information includes at least one of the following: board operating status, chip operating status, inter-board communication connection status, or device performance indicators.

[0095] In some embodiments, the time prediction algorithm may be stored in an idle CPU of the network device. The idle CPU of the network device may be determined by the management device based on CPU utilization in the running state of the network device.

[0096] In some embodiments, after obtaining the second energy-saving risk value of the network device, the network device may determine an energy-saving strategy based on the second energy-saving risk value and the first energy-saving risk value.

[0097] In some embodiments, determining the energy-saving strategy based on the second energy-saving risk value and the first energy-saving risk value may include steps X1 to X3.

[0098] In X1, the second energy-saving risk value and the first energy-saving risk value are weightedly calculated to obtain a third energy-saving risk value.

[0099] Here, the third energy-saving risk value is used to represent the comprehensive risk level of energy saving for the network device in the current network topology and the current operating state. The third energy-saving risk value may also be called another name, such as a comprehensive risk index.

[0100] In X2, the energy-saving risk level of the network device is obtained based on the third energy-saving risk value and the first corresponding relationship.

[0101] Here, the first corresponding relationship is used to represent the corresponding relationship between the energy-saving risk value and the energy-saving risk level.

[0102] In some embodiments, a first correspondence is pre-stored in the network device. After obtaining the third energy-saving risk value, the network device can determine the energy-saving risk level corresponding to the third energy-saving risk value in the first correspondence based on the third energy-saving risk value and the first correspondence, and then use the energy-saving risk level as the energy-saving risk level of the network device.

[0103] In some embodiments, there is a positive correlation between the third energy-saving risk value and the energy-saving risk level, that is, the energy-saving risk level increases as the third energy-saving risk value increases.

[0104] In some embodiments, after obtaining the third energy-saving risk value, the network device may also perform bucket calculation on the third energy-saving risk value, and use the result of the bucket calculation as the energy-saving risk level of the network device.

[0105] In X3, an energy-saving strategy is determined according to the energy-saving risk level and the second corresponding relationship.

[0106] Here, the second corresponding relationship is used to represent the corresponding relationship between the energy-saving risk level and the energy-saving strategy.

[0107] In some embodiments, a second correspondence is pre-stored in the network device. After obtaining the energy-saving risk level of the network device, the network device can determine the energy-saving strategy corresponding to the energy-saving risk level in the second correspondence based on the energy-saving risk level and the second correspondence.

[0108] In some embodiments, the second correspondence can also be referred to by other names, such as a policy repository. Here, the policy repository, or the second correspondence, is designed based on hierarchical adjustments to protection policies and device resource adjustment granularity to create n-level energy-saving policies. As protection reservations decrease and hardware resource adjustment granularity increases, energy-saving policies become more aggressive, leading to greater energy-saving risks and benefits.

[0109] The aforementioned protection strategy reserves processing capacity for network device resources to prevent failures in the communication network, such as protection switching and service path recalculation, which could lead to a sudden surge in network traffic that could exceed the management device's current capacity and cause service damage. This protection strategy includes three levels of protection: device active / standby protection reservation, device balancing redundancy reservation, and network-level maximum service load reservation. Active / standby protection reservation divides network device resources into primary resources for operation and backup resources for emergency response. In the event of an error in the primary resource, the network device can switch to the backup resource to maintain normal operation. Device balancing redundancy reservation ensures load balancing of adjustable resources within the network device. For example, all ports on the same board share the same processor, memory, and other resources. Device balancing redundancy reservation provides significant redundancy for individual ports, minimizing the impact on overall network device performance when traffic on a single port increases unexpectedly. Network-level maximum service load reservation is calculated by the management device based on the overall link status and service conditions of the device's energy-saving system, analyzing the network device's expected maximum load and reserving it in advance.

[0110] In S203 , an energy-saving operation is performed on the network device based on the energy-saving policy and the load prediction information of the network device.

[0111] In some embodiments, after determining the energy-saving strategy based on the operating status of the network device and the first energy-saving risk value, the network device may determine the energy-saving operation based on the energy-saving strategy and load prediction information of the network device, and then perform the energy-saving operation on the network device.

[0112] Here, the load prediction information of the network device may be obtained by the network device based on the load information of the network device at the current moment, or may be issued by the management device, and the embodiments of the present disclosure do not limit this.

[0113] In some embodiments, a network device determines an energy-saving operation based on an energy-saving policy and load prediction information of the network device, and then performs the energy-saving operation on the network device. This may be the case where the network device determines the number of boards, modules, and chips in the network device that can meet service processing requirements based on the energy-saving policy and load prediction information of the network device, and then, based on the energy-saving status of the device, determines the device that needs to be energy-saving or shut down. The device then issues an energy-saving instruction to the device that needs energy-saving, instructing it to power off or sleep; and issues a stop energy-saving instruction to the device that needs to shut down energy-saving, instructing it to power on or wake up. The corresponding device receives the energy-saving instruction or stop energy-saving instruction and executes the operation corresponding to the energy-saving instruction or stop energy-saving instruction. In this way, the energy-saving operation on the network device is completed.

[0114] In some embodiments, energy-saving operations are performed on network devices based on energy-saving policies and load prediction information of network devices, or energy-saving operations are performed on network devices based on energy-saving policies, the operating status of network devices, and the load prediction information of network devices. For the description of the operating status of network devices, reference may be made to the corresponding description in the above-mentioned embodiments, which will not be elaborated on in the embodiments of the present disclosure. For the description of how to perform energy-saving operations on network devices based on energy-saving policies, the operating status of network devices, and load prediction information of network devices, reference may be made to the above-mentioned description of performing energy-saving operations on network devices based on energy-saving policies and load prediction information of network devices, which will not be elaborated on in the embodiments of the present disclosure.

[0115] Based on the embodiment shown in Figure 4, the network device determines the energy-saving strategy based on the first energy-saving risk value sent by the management device and the operating status of the network device, that is, the energy-saving strategy of the network device is comprehensively determined from two levels: the device energy-saving system (that is, the network level) and the network device (that is, the device level), thereby improving the accuracy of determining the energy-saving strategy, thereby effectively balancing the relationship between the energy-saving benefits and energy-saving risks of the network device, and improving the energy-saving effect of the network device.

[0116] The following describes an example of a device energy-saving method provided by an embodiment of the present disclosure, with reference to the structure of a management device and the structure of a network device.

[0117] Figure 5 is a schematic diagram of the composition of a management device and a network device according to some embodiments of the present disclosure. Referring to Figure 5, the management device includes a network-level information perception unit, and the network-level information perception unit includes a network perception module 101, a network-level risk prediction module 102 and an information transmission module 103.

[0118] Here, the network-level information perception unit is used to perceive and calculate the overall network traffic load information of the device energy-saving system, as well as to perceive the overall status of the device energy-saving system, providing network-level supplementary information for network devices to determine energy-saving strategies. The network perception module 101 is used to obtain network topology information of network devices at each of multiple time points. The network-level risk prediction module 102 is used to obtain a network state graph sequence based on the network topology information of network devices at each of multiple time points obtained by the network perception module 101. The network state graph sequence is input into an energy-saving risk prediction model based on a graph neural network algorithm. Through local information aggregation, time-varying information aggregation, and computational reasoning using an attention mechanism, a first energy-saving risk value for the network device is obtained. The information transmission module 103 is a data transmission channel between the management device and the network device, and is used to exchange data with the network device. For example, the information transmission module 103 transmits the first energy-saving risk value of the network device obtained by the network-level risk prediction module 102 to the network device, for example, to the policy generation module 106 of the network device.

[0119] The network device includes a device-level energy-saving control unit, which is used to perceive the internal information of the network device, predict energy-saving risks, predict business loads and make decisions on energy-saving operations. Continuing to refer to Figure 5, the device-level energy-saving control unit includes an information perception module 104, a device-level risk prediction module 105, a policy generation module 106, an action decision module 107, an action module 108 and an execution module 109.

[0120] Here, the information perception module 104 is used to obtain the operating status of the network device. The device-level risk prediction module 105 is used to predict the load information of the network device boards, as included in the network device's operating status, using a time series prediction algorithm to obtain a second energy-saving risk value for the network device. The policy generation module 106 is used to perform a weighted calculation based on the first and second energy-saving risk values ​​to obtain a third energy-saving risk value, and then perform a bucket calculation on the third energy-saving risk value to obtain the energy-saving risk level of the network device. Based on the hierarchical adjustment of protection strategies and hardware adjustment granularity, a multi-level energy-saving strategy is designed. Based on the energy-saving risk level, an energy-saving strategy that is appropriate to the energy-saving risk level is selected from the policy repository. The action decision module 107 is used to calculate idle device resources based on the network device's load prediction information, operating status information, and energy-saving strategy, and to generate energy-saving information or energy-saving stop information. The action module 108 is used to convert the energy-saving information or energy-saving stop information generated by the action decision module 107 into corresponding communication information (i.e., energy-saving instructions or energy-saving stop instructions) and forward the communication information to execution modules such as the device electromechanical management and drive management. The execution module 109 is used to receive communication information and control the corresponding device to perform energy-saving operations such as powering off or sleeping.

[0121] The above mainly introduces the solution provided by the embodiment of the present disclosure from the perspective of method. In order to realize the above functions, it includes at least one of the hardware structures or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0122] The present disclosure can divide the management device and network device into functional modules based on the above-mentioned method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into a processing module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the division of modules in this disclosure is schematic and is only a logical functional division. In actual implementation, other division methods may be used.

[0123] FIG6 is a block diagram of a device energy-saving apparatus according to some embodiments of the present disclosure. As shown in FIG6 , the device energy-saving apparatus 30 may include an acquisition unit 301 , a processing unit 302 , and a sending unit 303 .

[0124] The device energy-saving device 30 may be the aforementioned management device or a chip in the management device. When the device energy-saving device 30 is used to implement the functions of the management device in the aforementioned embodiment, each unit is used to implement the following functions.

[0125] The acquisition unit 301 is used to acquire a network status diagram sequence; the network status diagram sequence includes network status diagrams of the network device at multiple moments, and the network status diagrams at multiple moments are used to represent the network topology structure of the network device at multiple moments, including the current moment.

[0126] The processing unit 302 is configured to determine a first energy-saving risk value of the network device based on the network state diagram sequence, where the first energy-saving risk value is used to represent a risk level of energy saving of the network device under the current network topology.

[0127] The sending unit 303 is configured to send the first energy-saving risk value to the network device.

[0128] In some embodiments, the acquisition unit 301 is used to: acquire network topology information of the network device at each of multiple moments; obtain a network status diagram of the network device at each of multiple moments based on the network topology information of the network device at each of multiple moments; and obtain a network status diagram sequence based on the network status diagram of the network device at each of multiple moments.

[0129] In some embodiments, the network topology information includes at least one of the following: a network level of the network device, a network topology structure of the network device, configuration information of the network device, or link load status.

[0130] In some embodiments, the processing unit 302 is used to input the network status graph sequence into an energy-saving risk prediction model based on a graph neural network algorithm to obtain a first energy-saving risk value of the network device.

[0131] FIG7 is a block diagram of another device energy-saving apparatus according to some embodiments of the present disclosure. As shown in FIG7 , the device energy-saving apparatus 40 may include a communication unit 401 and a processing unit 402 .

[0132] The device energy-saving device 40 may be the aforementioned network device or a chip in the network device. When the device energy-saving device 40 is used to implement the functions of the network device in the aforementioned embodiment, each unit is used to implement the following functions.

[0133] The communication unit 401 is configured to receive a first energy-saving risk value sent by a management device, where the first energy-saving risk value is used to represent a risk level of energy saving for the network device under a current network topology.

[0134] The processing unit 402 is configured to determine an energy-saving strategy based on the operating state of the network device and the first energy-saving risk value.

[0135] The processing unit 402 is further configured to perform energy-saving operations on the network device based on the energy-saving strategy and load prediction information of the network device.

[0136] In some embodiments, the processing unit 402 is used to: obtain a second energy-saving risk value of the network device based on the operating status of the network device, the second energy-saving risk value is used to characterize the risk level of energy saving of the network device in the operating status at the current moment; determine the energy-saving strategy based on the second energy-saving risk value and the first energy-saving risk value.

[0137] In some embodiments, the operating status of the network device includes at least the load information of a single board in the network device, and the processing unit 402 is further used to: obtain the energy-saving risk value of the single board in the network device based on the load information of the single board in the network device and the timing prediction algorithm; and obtain a second energy-saving risk value of the network device based on the energy-saving risk value of the single board in the network device.

[0138] In some embodiments, the network device includes multiple single boards, and the processing unit 402 is further used to determine a target single board from the multiple single boards, and determine the energy-saving risk value of the target single board as the second energy-saving risk value of the network device; the target single board is the single board with the largest energy-saving risk value among the multiple single boards.

[0139] In some embodiments, the processing unit 402 is further used to: perform weighted calculation on the second energy-saving risk value and the first energy-saving risk value to obtain a third energy-saving risk value; obtain the energy-saving risk level of the network device based on the third energy-saving risk value and the first correspondence, and the first correspondence is used to characterize the correspondence between the energy-saving risk value and the energy-saving risk level; determine the energy-saving strategy based on the energy-saving risk level and the second correspondence, and the second correspondence is used to characterize the correspondence between the energy-saving risk level and the energy-saving strategy.

[0140] It should be noted that the units in Figures 6 and 7 may also be referred to as modules. For example, the sending unit may be referred to as a sending module. In addition, in the embodiments shown in Figures 6 and 7, the names of the units may not be those shown in the figures. For example, the acquiring unit may be referred to as a communication unit, and the sending unit may be referred to as a communication unit.

[0141] If the various units in Figures 6 and 7 are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the various embodiments of the present disclosure. The storage medium for storing computer software products includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0142] When the energy-saving device 30 or 40 implements the functions of the integrated modules in hardware, the present disclosure provides a block diagram of an electronic device. As shown in FIG8 , the electronic device 50 includes a processor 502 , a communication interface 503 , and a bus 504 . In some embodiments, the electronic device 50 may also include a memory 501 .

[0143] The processor 502 may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure herein. The processor 502 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. The processor 502 may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure herein. The processor 502 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor (DSP) and a microprocessor, and the like.

[0144] The communication interface 503 is used to connect to other devices via a communication network, such as Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0145] The memory 501 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0146] In some embodiments, the memory 501 may exist independently of the processor 502 and may be connected to the processor 502 via a bus 504 for storing instructions or program codes. When the processor 502 calls and executes the instructions or program codes stored in the memory 501, the device energy saving method provided in the embodiments of the present disclosure can be implemented.

[0147] In other embodiments, the memory 501 may also be integrated with the processor 502 .

[0148] Bus 504 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 504 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, FIG8 shows only one thick line, but this does not mean that there is only one bus or only one type of bus.

[0149] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the base station or terminal can be divided into different functional modules to complete all or part of the functions described above.

[0150] The embodiments of the present disclosure also provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium). All or part of the processes in the above-mentioned method embodiments can be completed by computer instructions to instruct the relevant hardware, and the program can be stored in the above-mentioned computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The computer-readable storage medium can be the memory of any of the aforementioned embodiments. The above-mentioned computer-readable storage medium can also be an external storage device of the above-mentioned management device or network device, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. equipped on the above-mentioned management device or network device. In some embodiments, the above-mentioned computer-readable storage medium can also include both the internal storage unit of the above-mentioned management device or network device and an external storage device. The above-mentioned computer-readable storage medium is used to store the above-mentioned computer program and other programs and data required by the above-mentioned management device or network device. The above-mentioned computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0151] An embodiment of the present disclosure further provides a computer program product, which includes a computer program. When the computer program product is run on a computer, the computer is enabled to execute any one of the device energy-saving methods provided in the above embodiments.

[0152] Although the present disclosure is described herein in conjunction with various embodiments, in the process of implementing the disclosure for which protection is claimed, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, "a" or "an" does not exclude a plurality. A single processor or other unit may implement several of the functions listed in the claims. The fact that certain measures are recited in mutually different dependent claims does not mean that these measures cannot be combined to produce good results.

[0153] Although the present disclosure has been described in conjunction with example features and embodiments thereof, it will be apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely illustrative of the present disclosure as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. It will be apparent that those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, the present disclosure is intended to encompass such modifications and variations as would fall within the scope of the claims of the present disclosure and their equivalents.

[0154] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or replacements within the technical scope disclosed in the present disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. An energy-saving method for a device, which is applied to a management device. The management device is connected to a network device. The method includes: Obtaining a sequence of network state diagrams; The sequence of network state diagrams includes network state diagrams of the network device at multiple moments. The network state diagrams at the multiple moments are used to represent the network topology of the network device at the multiple moments. Among them, the multiple moments include the current moment; Based on the sequence of network state diagrams, determining a first energy-saving risk value of the network device. The first energy-saving risk value is used to represent the risk degree of energy saving of the network device under the network topology at the current moment; Sending the first energy-saving risk value to the network device.

2. The method according to claim 1, wherein The obtaining of the sequence of network state diagrams includes: Obtaining the network topology information of the network device at each of the multiple moments; Based on the network topology information of the network device at each of the multiple moments, obtaining the network state diagram of the network device at each of the multiple moments; Based on the network state diagrams of the network device at each of the multiple moments, obtaining the sequence of network state diagrams.

3. The method according to claim 1 or 2, wherein The network topology information includes at least one of the following: The network level of the network device, the network topology of the network device, the configuration information of the network device, or the link load condition.

4. The method according to claim 1, wherein The determining of the first energy-saving risk value of the network device based on the sequence of network state diagrams includes: Inputting the sequence of network state diagrams into an energy-saving risk prediction model based on a graph neural network algorithm to obtain the first energy-saving risk value of the network device.

5. An energy-saving method for a device, which is applied to a network device. The network device is connected to a management device. The method includes: Receiving the first energy-saving risk value sent by the management device. The first energy-saving risk value is used to represent the risk degree of energy saving of the network device under the network topology at the current moment; Based on the operating state of the network device and the first energy-saving risk value, determining an energy-saving strategy; Based on the energy-saving strategy and the load prediction information of the network device, performing an energy-saving operation on the network device.

6. The method according to claim 5, wherein The determining of the energy-saving strategy based on the operating state of the network device and the first energy-saving risk value includes: Based on the operating state of the network device, obtaining a second energy-saving risk value of the network device. The second energy-saving risk value is used to represent the risk degree of energy saving of the network device under the operating state at the current moment; Based on the second energy-saving risk value and the first energy-saving risk value, determining the energy-saving strategy.

7. The method according to claim 6, wherein, The operating state of the network device at least includes the load information of the single boards in the network device. The obtaining of the second energy-saving risk value of the network device based on the operating state of the network device includes: According to the load information of the single boards in the network device and a time series prediction algorithm, obtaining the energy-saving risk value of the single boards in the network device; Based on the energy-saving risk value of the single boards in the network device, obtaining the second energy-saving risk value of the network device.

8. The method according to claim 7, wherein, The network device includes multiple single boards. Obtaining the second energy-saving risk value of the network device based on the energy-saving risk values of the single boards in the network device includes: Determining a target single board from the multiple single boards, and determining the energy-saving risk value of the target single board as the second energy-saving risk value of the network device; wherein, the target single board is the single board with the largest energy-saving risk value among the multiple single boards.

9. The method according to claim 6, wherein, Determining an energy-saving strategy based on the second energy-saving risk value and the first energy-saving risk value includes: Performing weighted calculation on the second energy-saving risk value and the first energy-saving risk value to obtain a third energy-saving risk value; Obtaining the energy-saving risk level of the network device based on the third energy-saving risk value and a first correspondence relationship; wherein, the first correspondence relationship is used to represent the correspondence relationship between the energy-saving risk value and the energy-saving risk level; Determining the energy-saving strategy according to the energy-saving risk level and a second correspondence relationship; wherein, the second correspondence relationship is used to represent the correspondence relationship between the energy-saving risk level and the energy-saving strategy.

10. An equipment energy-saving system, including a management device and a network device, the management device is connected to the network device; The management device is configured to execute the method according to any one of claims 1 to 4; The network device is configured to execute the method according to any one of claims 5 to 9.

11. An electronic device, comprising: A memory and one or more processors; The memory stores instructions executable by the one or more processors; When the one or more processors are configured to execute the instructions, the electronic device is caused to implement the method according to any one of claims 1 to 4, or, the method according to any one of claims 5 to 9.

12. A computer-readable storage medium, wherein, The computer-readable storage medium includes computer instructions, when the computer instructions run on a computer, the computer is caused to execute the method according to any one of claims 1 to 4, or, the method according to any one of claims 5 to 9.

Images