Network equipment energy-saving method and device, network equipment and electronic equipment

Abstract

The invention provides a network equipment energy-saving method and device, network equipment and electronic equipment, and relates to the technical field of wireless communication. The method comprises the following steps: in a current energy-saving period, performing aggregation scheduling processing based on respective original data transmission scheduling time of a plurality of similar terminals of network equipment, and obtaining total data transmission scheduling time of the plurality of similar terminals after aggregation scheduling processing; wherein the plurality of similar terminals are terminals with similar network attributes and / or service types in the current energy-saving period, and the service types of the plurality of similar terminals in the current energy-saving period all belong to low-priority service types; determining non-service time in the current energy-saving period according to the total data transmission scheduling time; and controlling the radio frequency channel of the network equipment to be closed in the non-service time. According to the invention, on the premise of not influencing service awareness, the energy overhead of a radio frequency channel is reduced, and the energy consumption of network equipment is reduced.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a network device energy saving method, device, network device and electronic device. Background Art

[0002] With the rapid development and widespread application of 5G technology, the number of 5G base stations continues to increase, and its energy consumption problem has become increasingly prominent. High energy consumption not only increases the operating costs of operators, but also has a certain impact on the environment. Therefore, how to reduce the energy consumption of 5G base stations has become an urgent problem to be solved in the 5G communication field. Summary of the invention

[0003] The embodiments of the present invention provide a network device energy saving method, device, network device and electronic device, which are used to solve the technical problem of high energy consumption of base stations.

[0004] In a first aspect, an embodiment of the present invention provides a network device energy saving method, comprising: in a current energy saving cycle, performing convergence scheduling processing based on the original data transmission scheduling time of each of multiple similar terminals of the network device, and obtaining the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy saving cycle, and the service types of the multiple similar terminals in the current energy saving cycle are all low priority service types; according to the total data transmission scheduling time, determining the non-service time in the current energy saving cycle; and controlling the radio frequency channel of the network device to be closed during the non-service time.

[0005] In some embodiments, the multiple similar terminals are terminals with similar network attributes and service types in the current energy-saving cycle; the multiple similar terminals are determined based on the following method: based on the network information of the multiple terminals in a preset time period and the service type of each terminal in the current energy-saving cycle, a user characteristic graph is constructed; wherein the user characteristic graph takes each of the terminals as a node, the characteristics of each of the nodes are determined based on the network information and the service type, and the edge weights between the nodes are determined based on the network information; the service types of the multiple terminals all belong to the low-priority service types in the current energy-saving cycle; node clustering is performed based on the user characteristic graph to obtain the multiple terminal groups; wherein each of the terminal groups includes multiple terminals with similar network attributes and service types; based on the multiple terminal groups, the multiple similar terminals are determined.

[0006] In some embodiments, performing node clustering based on the user feature graph to obtain the multiple terminal groups includes: based on a graph convolution operation, fusing the node features of the individual nodes with edge weights to obtain fused features of the individual nodes; determining a similarity matrix based on the fused features of the individual nodes; and performing spectral clustering based on the similarity matrix to obtain the multiple terminal groups.

[0007] In some embodiments, determining the multiple similar terminals based on the multiple terminal groups includes: determining the similarity between any two terminals in each of the terminal groups based on the network information and the service type; filtering the terminals in each of the terminal groups based on the similarity to obtain multiple target terminals in each of the terminal groups; determining a target terminal group from the multiple terminal groups based on the number of target terminals in each of the terminal groups; and determining the multiple target terminals in the target terminal group as the multiple similar terminals.

[0008] In some embodiments, in the current energy-saving cycle, convergence scheduling processing is performed based on the original data transmission scheduling time of each of the multiple similar terminals of the network device to obtain the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing, including: determining the convergence scheduling start time of the current energy-saving cycle, and performing data transmission of each of the multiple similar terminals at the convergence scheduling start time; determining the convergence scheduling end time of the current energy-saving cycle based on the original data transmission time of each of the multiple similar terminals, and frequency domain resource information; and determining the total data transmission scheduling time based on the convergence scheduling start time and the convergence scheduling end time.

[0009] In a second aspect, an embodiment of the present invention provides a network equipment energy-saving device, comprising: a convergence scheduling module, which is used to perform convergence scheduling processing based on the original data transmission scheduling time of multiple similar terminals of the network device in the current energy-saving period, and obtain the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy-saving period, and the service types of the multiple similar terminals in the current energy-saving period are all low-priority service types; a first determination module, which is used to determine the non-service time in the current energy-saving period according to the total data transmission scheduling time; and a control module, which is used to control the radio frequency channel of the network device to be closed during the non-service time.

[0010] In a third aspect, an embodiment of the present invention provides a network device, comprising a memory, a transceiver, and a processor; the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor implements the network device energy saving method described in the first aspect when executing the computer program.

[0011] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory storing a computer program, wherein when the processor executes the program, the network device energy saving method described in the first aspect is implemented.

[0012] In a fifth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the network device energy saving method described in the first aspect above is implemented.

[0013] In a sixth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the network device energy saving method described in the first aspect above.

[0014] The embodiments of the present invention provide a network device energy saving method, device, network device and electronic device. In the current energy saving period, the convergence scheduling process is performed based on the original data transmission scheduling time of each of the multiple similar terminals of the network device, and the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling process is obtained; wherein the multiple similar terminals are terminals with similar network attributes and / or service types, and the service types of the multiple similar terminals are all low-priority service types; according to the total data transmission scheduling time, the non-service time in the current energy saving period is determined; and the radio frequency channel of the network device is controlled to be closed during the non-service time. The present invention performs convergence scheduling processing on the data transmission time of similar terminals, shortens the time domain resources without affecting the service perception, and shuts down the radio frequency power transmission capacity during the non-service time, thereby reducing the energy overhead of the radio frequency channel, and further reducing the energy consumption of the network device. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 One of the flow charts of the network device energy saving method provided by the embodiment of the present invention; Figure 2 A second flowchart of a network device energy saving method provided by an embodiment of the present invention; Figure 3 A third flowchart of a network device energy saving method provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a network device energy saving device provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of a network device provided in an embodiment of the present invention; Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In the existing technology, the technical solutions for 5G base station energy saving mainly involve carrier shutdown energy saving after service migration in 4G / 5G co-coverage scenarios, carrier shutdown energy saving mode based on service prediction and MR data to judge overlapping coverage, and micro base station energy saving methods based on service prediction and macro base station collaboration. These methods do not take service types into consideration, and their applicability to differentiated service scenarios needs to be improved.

[0019] In order to solve the above problems, the embodiments of the present invention provide a network device energy saving method, apparatus, network device and electronic device.

[0020] Figure 1 This is one of the flow charts of the network device energy saving method provided by the embodiment of the present invention. It should be noted that the execution subject of this method can be a network device or other electronic devices. Figure 1 As shown, the method may include the following steps.

[0021] Step 101, in the current energy-saving cycle, aggregate scheduling processing is performed based on the original data transmission scheduling time of multiple similar terminals of the network device to obtain the total data transmission scheduling time of multiple similar terminals after the aggregate scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy-saving cycle, and the service types of the multiple similar terminals in the current energy-saving cycle are all low-priority service types.

[0022] In some embodiments, the energy-saving period may be divided according to the needs of actual scenarios. As an example, the energy-saving period may be determined based on the monitoring of the data transmission load, for example, a period of time when the data transmission load is low may be used as the energy-saving period. The energy-saving period is a period of time during which the network device needs to save energy, and its duration is usually relatively short, such as 10ms.

[0023] In some embodiments, the current energy-saving cycle refers to the energy-saving cycle of the current moment, and the current energy-saving cycle is a continuous period of time including the current moment. Multiple similar terminals refer to terminals that are connected to the network device and have similar network attributes and / or service types in the current energy-saving cycle.

[0024] It can be understood that if the services requested by some terminals are all time-sensitive services, then from the perspective of service quality and experience, these terminals are not suitable for participating in network device energy saving, while energy saving of network devices based on terminals with low time-sensitive services may not affect service perception. Therefore, the service types of similar terminals involved in the network device energy saving method in the embodiment of the present invention are all low-priority service types.

[0025] Specifically, the service types of the terminal may include high-priority service types such as VONR (Voice over New Radio, 5G voice service) service / signaling data / system message, uplink live broadcast, instant messaging, etc., as well as low-priority service types such as long video, short video, web browsing, etc.

[0026] In some embodiments, multiple similar terminals can be determined from multiple first terminals whose service types belong to low priority in the current energy-saving cycle. For example, the similarity between each pair of first terminals can be calculated based on the network information of the multiple first terminals in a previous period of time and / or the service type of the current energy-saving cycle, and multiple first terminals whose similarity between each pair of first terminals is greater than or equal to a threshold are determined as multiple similar terminals.

[0027] It is understandable that the original data transmission scheduling times of multiple similar terminals may be scattered, so the required data transmission time is longer, and the frequency domain resources in each time period are not fully utilized, resulting in the network equipment needing to be in the RF power state all the time, causing energy consumption of the network equipment to be wasted.

[0028] In some embodiments, in order to shorten the data transmission scheduling time, the data transmission scheduling times of multiple similar terminals can be aggregated and scheduled, that is, multiple similar terminals can be scheduled at the same time, thereby shortening the time domain resources and making the total data transmission scheduling time much shorter than the total duration corresponding to the original data transmission scheduling times of multiple similar terminals.

[0029] As a possible implementation method, in the current energy-saving cycle, convergence scheduling processing is performed based on the original data transmission scheduling time of multiple similar terminals of the network device to obtain the total data transmission scheduling time of multiple similar terminals after the convergence scheduling processing. The following steps may be included: determining the convergence scheduling start time of the current energy-saving cycle, and performing data transmission of multiple similar terminals at the convergence scheduling start time; determining the convergence scheduling end time of the current energy-saving cycle based on the original data transmission time of multiple similar terminals and frequency domain resource information; determining the total data transmission scheduling time based on the convergence scheduling start time and the convergence scheduling end time.

[0030] That is to say, when spectrum resources are sufficient, data transmission of multiple similar terminals is carried out at the same time, so that the scheduling time can be reduced and time domain resources can be shortened by aggregating and scheduling multiple similar terminals, thereby achieving energy saving effect.

[0031] The total data transmission scheduling time is a time period, which may be a continuous time starting from the convergence scheduling start time and ending at the convergence scheduling end time.

[0032] It should be noted that in order to ensure the scheduling of terminals of high-priority service types in the current energy-saving cycle, the total data transmission scheduling time can be determined based on the time other than the common channel sending time in the current energy-saving cycle. In some embodiments, the common channel sending time in the current energy-saving cycle can be used for scheduling terminals of high-priority service types, and the common channel sending time in the current energy-saving cycle can start at the start time of the current energy-saving cycle, so the end time in the common channel sending time can be used as the convergence scheduling start time of the current energy-saving cycle, and any time after the common channel sending time in the current energy-saving cycle can also be determined as the convergence scheduling start time of the current energy-saving cycle.

[0033] In addition, if data transmission to multiple similar terminals at the same time will exceed the upper limit of frequency domain resources, the scheduling time of the similar terminals that exceed the upper limit of frequency domain resources can be delayed while meeting the frequency domain resource requirements.

[0034] In some embodiments, if the executor of the method is a network device, step 101 can be executed by the scheduler of the base station. If the executor of the method is other electronic devices, step 101 can be after the electronic device completes execution, and the convergence scheduling start time of multiple similar terminals is sent to the base station scheduler, so that the scheduler can schedule multiple similar terminals based on the convergence scheduling start time.

[0035] Step 102: Determine the non-business time in the current energy-saving period according to the total data transmission scheduling time.

[0036] In some embodiments, the total data transmission scheduling time and the transmission time of the common channel may be removed from the time of the current energy-saving cycle, and the remaining time is the non-service time of the current energy-saving cycle.

[0037] The non-business time may be one continuous time period or multiple continuous time periods.

[0038] It should be noted that, in the current energy-saving period, except for similar terminals, other low-priority terminals may be scheduled during the transmission time of the common channel or after the current energy-saving period.

[0039] Step 103: Control the radio frequency channel of the network device to be closed during non-business hours.

[0040] That is to say, it can be considered that there is no business demand during non-business hours, so the radio frequency channel of the network equipment can be closed during non-business hours to reduce the energy consumption of the radio frequency channel and achieve the purpose of energy saving of network equipment.

[0041] In some embodiments, if the execution subject is a network device, the baseband processing unit of the network device can notify the AAU (Active Antenna Unit) or RRU (Remote Radio Unit) to close the RF channel; if the execution subject is other electronic devices, and the electronic device has established a communication connection with the network device, the electronic device can send a RF channel closing instruction to the network device, and then the baseband processing unit of the network device can notify the AAU or RRU to close the RF channel.

[0042] According to the network equipment energy saving method of the embodiment of the present invention, in the current energy saving cycle, based on the original data transmission scheduling time of each of the multiple similar terminals of the network equipment, convergence scheduling processing is performed to obtain the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types, and the service types of the multiple similar terminals are all low-priority service types; according to the total data transmission scheduling time, the non-service time in the current energy saving cycle is determined; and the radio frequency channel of the network equipment is controlled to be closed during the non-service time. The present invention performs convergence scheduling processing on the data transmission time of similar terminals, shortens the time domain resources without affecting the service perception, and shuts down the radio frequency power transmission capacity during the non-service time, thereby reducing the energy overhead of the radio frequency channel, and further reducing the energy consumption of the network equipment.

[0043] Next, the process of determining multiple similar terminals will be introduced.

[0044] Figure 2The second flow chart of the network device energy saving method provided by the embodiment of the present invention. In the embodiment of the present invention, the multiple similar terminals are terminals with similar network attributes and service types in the current energy saving period. Figure 2 As shown, a plurality of similar terminals are determined based on the following method.

[0045] Step 201, constructing a user characteristic graph based on the network information of multiple terminals in a preset time period and the service type of each terminal in the current energy-saving cycle; wherein the user characteristic graph takes each terminal as a node, the characteristics of each node are determined based on the network information and the service type, and the edge weights between each node are determined based on the network information; the service types of multiple terminals are all low-priority service types in the current energy-saving cycle.

[0046] In some embodiments, the preset time period may be a continuous period of time closest to the current energy-saving cycle before the current energy-saving cycle. For example, the period of 15 minutes before the start of the current energy-saving cycle may be used as the preset time period.

[0047] In some embodiments, the network information may include: Cell RSRP (Cell Reference Signal Receiving Power), TA (Time Advance) value, strongest SSB (Synchronization Signal Block) beam ID, CQI (Channel Quality Indication), cache packet size, etc. Since the service types of multiple terminals are all low-priority service types in the current energy-saving cycle, the service type of each terminal can be a low-priority service type such as a long video service type, a short video service type, or a web browsing service type.

[0048] In some embodiments, the network information and service type of each terminal are better expressed by constructing a user feature graph, wherein each terminal is regarded as a node in the user feature graph, the node feature of the corresponding node is determined based on the network information and service type of each terminal, and the edge weights between nodes are determined based on the network information of multiple terminals.

[0049] As a possible implementation method, the network information of terminal 1 within a preset time period can be averaged to obtain the average value of each data in the network information, and then the average value of each data in the network information and the service type are spliced ​​and combined, and through encoding conversion, the node characteristics of the node corresponding to terminal 1 are obtained.

[0050] In some embodiments, the network information of each terminal may include Cell RSRP and TA value. Based on the network information of each of the multiple terminals, the implementation process of determining the edge weights between nodes may include: determining the edge weights between two nodes based on the Cell RSRP and TA value of each terminal. It can be understood that the edge weights here are used to characterize the proximity of the location of the two nodes to the base station and the quality of the wireless environment in which they are located. If the edge weight between the two nodes is close to 1, the probability that the attributes of the two nodes are similar is greater. If the edge weight between the two nodes is smaller, the probability that the attributes of the two nodes are similar is smaller.

[0051] As an example, based on the Cell RSRP and TA value of each terminal, determining the edge weights between two nodes can be implemented based on the following formula (1).

[0052] (1); in, is the edge weight between its own node j and its neighbor node i; is the average value of Cell RSRP of node i in the preset period; is the average value of Cell RSRP of node j in the preset period; is the average value of TA value of node i in the preset period; is the average value of TA value of node j in the preset period.

[0053] Step 202: Perform node clustering processing based on the user characteristic graph to obtain multiple terminal groups; wherein each terminal group includes multiple terminals with similar network attributes and service types.

[0054] In some embodiments, the user feature graph can be segmented using a clustering algorithm so that the features of the nodes in each subgraph after segmentation are most similar and the sum of the edge weights is maximized, and the multiple subgraphs obtained after segmentation correspond to multiple terminal groups, that is, the terminals corresponding to the nodes in each subgraph form a terminal group.

[0055] In some embodiments, the process of performing node clustering processing based on the user feature graph to obtain multiple terminal groups may include the following steps.

[0056] Step S1, based on the graph convolution operation, the node features of each node are fused with the edge weights to obtain the fused features of each node.

[0057] In some embodiments, the adjacency matrix Z can be determined based on the edge weights between each node, and the feature matrix Y={y1,y2,…yn} can be determined based on the node features of each node, where yi is the node feature of node i and n is the total number of nodes; based on the adjacency matrix Z, the degree matrix D is constructed; and a standardized Laplace matrix is ​​constructed ; Assume the graph convolution order k, and perform graph convolution on the user feature graph to fuse the edge weights between nodes with the node features to obtain the fusion feature matrix of each node Among them, the optimal value of the graph convolution order k can be determined through multiple iterations.

[0058] Step S2, determining a similarity matrix based on the fusion features of each node.

[0059] In some embodiments, the similarity matrix may be determined by the following formula (3).

[0060] (3); in, is a similarity matrix; is the second characteristic matrix.

[0061] Step S3: Perform spectral clustering based on the similarity matrix to obtain multiple terminal groups.

[0062] In some embodiments, the user feature graph can be segmented based on a similarity matrix by spectral clustering, so that the sum of edge weights between different subgraphs after segmentation is as low as possible, while the edge weights within the subgraph are as high as possible, and the terminals corresponding to each node in each subgraph are regarded as a terminal group.

[0063] In some embodiments, spectral clustering based on the similarity matrix can first calculate the eigenvector y corresponding to the first s largest eigenvalues ​​of the similarity matrix W, and form the s eigenvectors into an n×s feature matrix F, where s is the number of preset terminal groups; each row in F is used as an s-dimensional vector sample, with a total of n samples, and clustering is performed on the feature matrix F based on the K-means algorithm to obtain a matrix A, , is the i-th quasi-similar node set, each quasi-similar node set includes multiple nodes, and s terminal groups can be determined based on A.

[0064] In some embodiments, the graph convolution order k in step S1 may be determined by loop iteration, and the loop iteration process includes: calculating the distance within the set of quasi-similar nodes The distance between the quasi-similar node sets ,in It is defined as the mean of the average distances between samples in the set, for The i-th row vector of is the number of iterations. Based on the matrix A obtained in step S3, the distances within the set of quasi-similar nodes obtained in the current iteration are calculated respectively. The distance between the quasi-similar node sets The calculation formula is as follows (4).

[0065] (4); in, is the i-th node; is the jth node.

[0066] It is defined as the average value of the centroid distance between similar nodes, and the calculation formula is as follows (5).

[0067] (5); in, is the centroid of the quasi-similar node set i, and its calculation formula is as follows (6).

[0068] (6); Let r=r+1, k=r, return to step S1 until and ,or That is to say, the loop iteration termination condition is: the distance within the quasi-similar node set is no longer reduced compared with the previous iteration, and the distance between sets is no longer increased or the number of iterations is greater than s, and based on A obtained when the iteration is terminated, multiple quasi-similar node sets are determined to obtain multiple terminal groups.

[0069] Step 203: determine a plurality of similar terminals based on the plurality of terminal groups.

[0070] In some embodiments, similarity calculation may be performed based on terminals in multiple terminal groups, and multiple similar terminals may be determined based on the similarities of the terminals.

[0071] like Figure 3 As shown, the implementation process of determining multiple similar terminals based on multiple terminal groups includes the following steps.

[0072] Step 301: Determine the similarity between two terminals in each terminal group based on network information and service type.

[0073] In some embodiments, for each terminal group, the similarity between two terminals in the terminal group is calculated based on the network information of two terminals in the terminal group in a preset period and the service type in the current energy saving cycle. For example, the weight of the network information and the weight of the service type can be preset, and the similarity between two terminals is determined based on the difference in network information and service type of two terminals and their corresponding weight values.

[0074] As a possible implementation process, the process of determining the similarity between two terminals in each terminal group based on network information and service type is shown in the following formula (7).

[0075] (7); in, is the terminal in terminal group m With terminal The similarity between For Terminal Network information within a preset time period and service types within the current energy-saving cycle; For Terminal Network information within a preset time period and service types within the current energy-saving cycle.

[0076] The core idea of ​​this step is to determine the similarity between two terminals in a terminal group based on the closeness of other attributes when the service types of the terminals are similar, so as to correct the quasi-similar terminals in each terminal group. In order to avoid obtaining a high similarity when the service types of two terminals are inconsistent but other attributes are close, a penalty term is introduced in the above similarity calculation formula, as shown in the following formula (8).

[0077] (8); Among them, M represents the terminal With terminal The weight value between them can be determined based on the similarity between the network information and the service types of the two terminals. For example, if the network information of the two terminals is similar but the service types are inconsistent, the M value is larger. If the network information of the two terminals is similar and the service types are similar, the M value is smaller.

[0078] Step 302: Filter the terminals in each terminal group based on the similarity to obtain multiple target terminals in each terminal group.

[0079] In some embodiments, for each terminal group, the similarity between any two terminals in the terminal group is compared with a preset similarity threshold, and multiple terminals whose similarities between any two terminals are higher than the similarity threshold are determined as target terminals.

[0080] Step 303: determining a target terminal group from multiple terminal groups based on the number of target terminals in each terminal group.

[0081] It can be understood that the convergence effect and energy saving efficiency can be improved by increasing the number of similar terminals participating in convergence scheduling. Therefore, when determining the target terminal group from multiple terminal groups, it can be determined based on the number of target terminals in each terminal group.

[0082] In some embodiments, a terminal group having the largest number of target terminals may be determined as the target terminal group.

[0083] Step 304: determine the multiple target terminals in the target terminal group as multiple similar terminals.

[0084] In the network device energy saving method of the embodiment of the present invention, a user characteristic graph is constructed based on the network information of multiple terminals in a preset time period and the service type of each terminal in the current energy saving period, and the nodes in the user characteristic graph are clustered based on the graph technology to obtain multiple terminal groups, and then multiple similar terminals are determined based on the multiple terminal groups to perform convergence scheduling processing on the data transmission time of the similar terminals, and the purpose of reducing the energy consumption of the network device is achieved by shutting down the radio frequency device power transmission function during non-service time.

[0085] The network device energy saving apparatus provided by an embodiment of the present invention is described below. The network device energy saving apparatus described below and the network device energy saving method described above can be referred to each other.

[0086] Figure 4 This is one of the structural diagrams of the network device energy saving device provided by the embodiment of the present invention. It should be noted that the device is deployed in the network device. Figure 4 As shown, the device includes: a convergence scheduling module 410, a first determination module 420 and a control module 430. The convergence scheduling module 410 is used to perform convergence scheduling processing based on the original data transmission scheduling time of multiple similar terminals of the network device in the current energy-saving period, and obtain the total data transmission scheduling time of multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy-saving period, and the service types of the multiple similar terminals in the current energy-saving period are all low-priority service types; the first determination module 420 is used to determine the non-service time in the current energy-saving period according to the total data transmission scheduling time; the control module 430 is used to control the radio frequency channel of the network device to be closed during the non-service time.

[0087] In some embodiments, multiple similar terminals are terminals with similar network attributes and service types in the current energy-saving cycle; the device may also include a second determination module 440, and the second determination module 440 is used to: construct a user characteristic graph based on the network information of each of the multiple terminals within a preset time period and the service type of each terminal in the current energy-saving cycle; wherein the user characteristic graph takes each terminal as a node, the characteristics of each node are determined based on the network information and the service type, and the edge weights between each node are determined based on the network information; the service types of multiple terminals are all low-priority service types in the current energy-saving cycle; node clustering is performed based on the user characteristic graph to obtain multiple terminal groups; wherein each terminal group includes multiple terminals with similar network attributes and service types; based on multiple terminal groups, multiple similar terminals are determined.

[0088] In some embodiments, the second determination module 440 is further used to: based on a graph convolution operation, fuse the node features of each node with the edge weight to obtain the fused features of each node; based on the fused features of each node, determine the similarity matrix; based on the similarity matrix, perform spectral clustering to obtain multiple terminal groups.

[0089] In some embodiments, the second determination module 440 is also used to: determine the similarity between two terminals in each terminal group based on network information and service type; filter the terminals in each terminal group based on the similarity to obtain multiple target terminals in each terminal group; determine the target terminal group from multiple terminal groups based on the number of target terminals in each terminal group; and determine the multiple target terminals in the target terminal group as multiple similar terminals.

[0090] In some embodiments, the convergence scheduling module 410 is specifically used to: determine the convergence scheduling start time of the current energy-saving cycle, and perform data transmission for multiple similar terminals at the convergence scheduling start time; determine the convergence scheduling end time of the current energy-saving cycle based on the original data transmission time of each of the multiple similar terminals, and frequency domain resource information; determine the total data transmission scheduling time based on the convergence scheduling start time and the convergence scheduling end time.

[0091] It should be noted that the above explanations and descriptions in the embodiment of the network device energy saving method are also applicable to the network device energy saving device in the embodiment of the present invention, and will not be repeated here.

[0092] The terminal involved in the embodiments of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem, etc. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called a user equipment (UE).

[0093] The network device involved in the embodiments of the present application may be a base station, which may include multiple cells providing services for terminals. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in an access network that communicates with a wireless terminal device through one or more sectors on an air interface, or other names.

[0094] Figure 5 A schematic diagram of the structure of a network device according to an embodiment of the present invention, referring to Figure 5 The embodiment of the present invention further provides a network device, which may include: a memory 510, a transceiver 520 and a processor 530.

[0095] The memory 510 is used to store computer programs; the transceiver 520 is used to send and receive data under the control of the processor 530; the processor 530 is used to read the computer program in the memory 510 and perform the following operations: in the current energy-saving period, based on the original data transmission scheduling time of each of the multiple similar terminals of the network device, convergence scheduling processing is performed to obtain the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy-saving period, and the service types of the multiple similar terminals in the current energy-saving period are all low-priority service types; according to the total data transmission scheduling time, the non-service time in the current energy-saving period is determined; and the radio frequency channel of the network device is controlled to be closed during the non-service time.

[0096] Among them, Figure 5 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 530 and memory represented by memory 510. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 520 may be a plurality of components, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 530 is responsible for managing the bus architecture and general processing, and the memory 510 may store data used by the processor 530 when performing operations.

[0097] Optionally, the processor 530 is also used to perform the following operations: construct a user characteristic graph based on the network information of each of the multiple terminals within a preset time period and the service type of each terminal in the current energy-saving cycle; wherein the user characteristic graph takes each of the terminals as a node, the characteristics of each of the nodes are determined based on the network information and the service type, and the edge weights between the nodes are determined based on the network information; the service types of the multiple terminals all belong to the low-priority service types in the current energy-saving cycle; perform node clustering processing based on the user characteristic graph to obtain the multiple terminal groups; wherein each of the terminal groups includes multiple terminals with similar network attributes and service types; and determine the multiple similar terminals based on the multiple terminal groups.

[0098] Optionally, the processor 530 is further used to perform the following operations: based on a graph convolution operation, fusing the node features of each node with the edge weight to obtain the fused features of each node; based on the fused features of each node, determining a similarity matrix; and performing spectral clustering based on the similarity matrix to obtain the multiple terminal groups.

[0099] Optionally, the processor 530 is further used to perform the following operations: based on the network information and the service type, determine the similarity between any two terminals in each of the terminal groups; based on the similarity, filter the terminals in each of the terminal groups to obtain multiple target terminals in each of the terminal groups; based on the number of target terminals in each of the terminal groups, determine a target terminal group from multiple terminal groups; and determine the multiple target terminals in the target terminal group as the multiple similar terminals.

[0100] Optionally, the processor 530 is also used to perform the following operations: determine the convergence scheduling start time of the current energy saving cycle, and perform data transmission of each of the multiple similar terminals at the convergence scheduling start time; determine the convergence scheduling end time of the current energy saving cycle based on the original data transmission time of each of the multiple similar terminals, and frequency domain resource information; determine the total data transmission scheduling time based on the convergence scheduling start time and the convergence scheduling end time.

[0101] It should be noted here that the network device provided in the embodiment of the present invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. The parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0102] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call a computer program in the memory 630 to execute the steps of the network device energy saving method.

[0103] For example, the method includes: in the current energy-saving cycle, performing convergence scheduling processing based on the original data transmission scheduling time of each of the multiple similar terminals of the network device, and obtaining the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy-saving cycle, and the service types of the multiple similar terminals in the current energy-saving cycle are all low-priority service types; according to the total data transmission scheduling time, determining the non-service time in the current energy-saving cycle; and controlling the radio frequency channel of the network device to be closed during the non-service time.

[0104] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the 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 a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0105] On the other hand, an embodiment of the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the steps of the network device energy saving method provided in the above embodiments.

[0106] On the other hand, an embodiment of the present invention further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the steps of the network device energy saving method provided in the above embodiments.

[0107] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0108] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0109] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A network device energy saving method, characterized in that: include: In the current energy-saving cycle, performing convergence scheduling processing based on the original data transmission scheduling time of each of the multiple similar terminals of the network device, and obtaining the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy-saving cycle, and the service types of the multiple similar terminals in the current energy-saving cycle are all low-priority service types; Determining the non-business time within the current energy-saving period according to the total data transmission scheduling time; The radio frequency channel of the network device is controlled to be closed during the non-business time.

2. The method according to claim 1, characterized in that: The multiple similar terminals are terminals with similar network attributes and service types in the current energy-saving period; the multiple similar terminals are determined based on the following method: Based on the network information of each of the multiple terminals in a preset time period and the service type of each terminal in the current energy-saving period, a user characteristic graph is constructed; wherein the user characteristic graph takes each of the terminals as a node, the characteristics of each of the nodes are determined based on the network information and the service type, and the edge weights between the nodes are determined based on the network information; the service types of the multiple terminals are all low-priority service types in the current energy-saving period; Perform node clustering processing based on the user characteristic graph to obtain the multiple terminal groups; wherein each of the terminal groups includes multiple terminals with similar network attributes and service types; Based on the plurality of terminal groups, the plurality of similar terminals are determined.

3. The method according to claim 2, characterized in that The performing node clustering processing based on the user characteristic graph to obtain the multiple terminal groups includes: Based on the graph convolution operation, the node features of each node are fused with the edge weights to obtain the fused features of each node; Determine a similarity matrix based on the fusion features of each node; A spectral clustering process is performed based on the similarity matrix to obtain the multiple terminal groups.

4. The method according to claim 2, characterized in that: The determining the plurality of similar terminals based on the plurality of terminal groups comprises: Based on the network information and the service type, determining the similarity between any two terminals in each terminal group; Based on the similarity, filtering the terminals in each of the terminal groups to obtain a plurality of target terminals in each of the terminal groups; Determining a target terminal group from the plurality of terminal groups based on the number of target terminals in each of the terminal groups; A plurality of target terminals in the target terminal group are determined as the plurality of similar terminals.

5. The method according to claim 1, characterized in that The method of performing convergence scheduling processing based on the original data transmission scheduling time of each of the multiple similar terminals of the network device in the current energy-saving cycle to obtain the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing includes: Determine a convergence scheduling start time of the current energy-saving period, and perform data transmission of each of the multiple similar terminals at the convergence scheduling start time; Determining the convergence scheduling end time of the current energy saving period based on the original data transmission time of each of the multiple similar terminals and the frequency domain resource information; The total data transmission scheduling time is determined based on the convergence scheduling start time and the convergence scheduling end time.

6. A network equipment energy saving device, characterized in that: include: A convergence scheduling module is used to perform convergence scheduling processing based on the original data transmission scheduling time of each of the multiple similar terminals of the network device in the current energy-saving period, and obtain the total data transmission scheduling time of the multiple similar terminals after the convergence scheduling processing; wherein the multiple similar terminals are terminals with similar network attributes and / or service types in the current energy-saving period, and the service types of the multiple similar terminals in the current energy-saving period are all low-priority service types; A first determining module, configured to determine the non-business time in the current energy-saving period according to the total data transmission scheduling time; The control module is used to control the radio frequency channel of the network device to be closed during the non-business time.

7. A network device, characterized in that: It comprises a memory, a transceiver, and a processor; the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the network device energy saving method described in any one of claims 1 to 5 is implemented when the processor executes the computer program.

8. An electronic device, characterized in that: The invention comprises a processor and a memory storing a computer program, wherein when the processor executes the program, the network device energy saving method according to any one of claims 1 to 5 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the network device energy saving method according to any one of claims 1 to 5 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the network device energy saving method according to any one of claims 1 to 5 is implemented.

Images