Base station out-of-service warning method, device and computer-readable storage medium

Through the pre-trained prediction model for server withdrawal and resource consumption analysis, a warning method for 5G base station withdrawal is provided, which solves the problem of lack of early warning in the existing technology, and realizes timely prevention of server withdrawal and controls resource consumption of base station withdrawal and controls.

CN113692009BActive Publication Date: 2024-11-01CHINA TELECOM CORP LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202010417393.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-05-18
Publication Date
2024-11-01
Estimated Expiration
2040-05-18

AI Technical Summary

Technical Problem

The existing technology lacks effective early warning methods for 5G base station withdrawal, resulting in timely prevention of base station withdrawal, resulting in increased resource consumption and service interruption.

Method used

The pre-trained server-rejection number prediction model (such as the LSTM model) is used to predict the number of server-rejection base stations in the future through historical data, and determine the warning strategy based on the resource consumption growth, including calculating the resource consumption of server-rejection base stations on non-rejection base stations Increases and sends reminders when resource consumption exceeds the preset value.

Benefits of technology

By predicting the number of base stations and resource consumption growth in the future, operators can take timely measures to reduce the occurrence of base station service withdrawal accidents and reduce the risk of resource consumption and service interruption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113692009B_ABST
    Figure CN113692009B_ABST
Patent Text Reader

Abstract

The present invention discloses a base station decommissioning warning method, device and computer-readable storage medium, and relates to the field of communication technology. The base station decommissioning warning method includes: inputting a sequence consisting of the number of decommissioned base stations in each of multiple historical time periods into a pre-trained decommissioning number prediction model, and determining the number of decommissioned base stations in future time periods output by the decommissioning number prediction model; determining, based on the number of decommissioned base stations in future time periods, the increase in resource consumption caused by decommissioned base stations for non-decommissioned base stations in the event of future decommissioning; and determining a warning strategy based on the increase in resource consumption. The embodiment of the present invention measures the increase in resource consumption caused by possible decommissioning situations and issues corresponding warnings. Thus, the operator can focus on prevention based on the reminder to reduce resource consumption caused by base station decommissioning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a base station out-of-service warning method, device and computer-readable storage medium. Background Art

[0002] The construction and maintenance of base stations are important factors in the commercialization of 5G technology. During the operation process, 5G base stations may be affected by various factors such as weather and transmission, and the base stations may go offline. In severe cases, the base stations may even be dropped or decommissioned. The most serious system failure in the decommissioning of base stations will interrupt all services, causing users to be unable to use mobile phones and other communication devices. For 5G users, the decommissioning of base stations will cause the unavailability of technical services such as mobile payments, smart cities, and artificial intelligence, causing losses to operators. It is very important to conduct a comprehensive analysis of the decommissioning of 5G base stations and estimate the costs after decommissioning. However, there is no early warning method for the decommissioning of base stations in related technologies. Summary of the invention

[0003] A technical problem to be solved by the embodiments of the present invention is: how to provide an early warning method for base station decommissioning.

[0004] According to a first aspect of some embodiments of the present invention, a base station deservice warning method is provided, comprising: inputting a sequence consisting of the number of deservice base stations in each of multiple historical time periods into a pre-trained deservice number prediction model, and determining the number of deservice base stations in future time periods output by the deservice number prediction model; determining, based on the number of deservice base stations in future time periods, an increase in resource consumption caused by the deservice base stations for non-deservice base stations in the event of future deservice; and determining a warning strategy based on the increase in resource consumption.

[0005] In some embodiments, the decommissioning quantity prediction model is a long short-term memory network (LSTM) model.

[0006] In some embodiments, based on the number of deserving base stations in a future time period, determining the increase in resource consumption caused by the deserving base stations to non-deserving base stations in the event of deserving in the future includes: for each deserving base station, determining the business load that the deserving base station transfers to the non-deserving base station in the event of deserving in the future; determining the increase in resource consumption caused by the deserving base station to the non-deserving base station based on the increased business load of the non-deserving base stations; and determining the sum of the increase in resource consumption caused by each deserving base station to the non-deserving base stations.

[0007] In some embodiments, the increase in power consumption caused by the decommissioned base station to the non-decommissioned base station is determined based on the increased service load of the non-decommissioned base station and the functional relationship between the service load of the base station and the power consumption of the base station.

[0008] In some embodiments, the decommissioned base station is a 5G base station, and the power consumption of the base station is the power consumption of the BBU and AAU of the base station.

[0009] In some embodiments, the increase in costs brought by the decommissioned base station to the non-decommissioned base station is determined based on the increased business load of the non-decommissioned base station, the functional relationship between the business load of the base station and the power consumption of the base station, and the cost consumed by a preset unit of power consumption.

[0010] In some embodiments, determining the service load that the deserving base station transfers to the non-deserving base station in the event of future deserving includes: dividing the area where the deserving base station is located into multiple sub-areas; and determining the service load that the deserving base station transfers to the non-deserving base station in the event of future deserving based on a preset load distribution ratio corresponding to each sub-area, wherein the load distribution ratio corresponding to the sub-area is positively correlated with the distance between the sub-area and the deserving base station.

[0011] In some embodiments, the following formula is used to determine the increase C of resource consumption caused by the deserving base station to the non-deserving base station in the event of deserving in the future:

[0012]

[0013] Wherein, T represents the period of time covered by the future decommissioning situation; P represents the cost consumed by the preset unit of power consumption; N represents the number of decommissioned base stations in the future period; m represents the number of sub-areas, i represents the identifier of the sub-area; n i represents the number of non-decommissioned base stations in the ith sub-area, j represents the identifier of the non-decommissioned base stations in the ith sub-area; the independent variable of f(·) is load and the dependent variable is power consumption; r i represents the load distribution ratio corresponding to the i-th sub-area; Q represents the load of the retired base station; q ij represents the original load of the jth non-decommissioned base station in the i-th sub-area.

[0014] In some embodiments, f(·) is a piecewise function composed of multiple linear functions, and the parameters of each linear function are determined according to historical data.

[0015] In some embodiments, determining the warning strategy based on the growth amount of resource consumption includes: sending a service withdrawal reminder when the growth amount of resource consumption is greater than a preset value.

[0016] In some embodiments, the base station decommissioning warning method further includes: inputting the status characteristics of the base station into a pre-trained neural network model to obtain a classification result output by the neural network model to determine whether the base station is a decommissioned base station; and generating warning information based on information of the base station whose classification result is a decommissioned base station.

[0017] According to a second aspect of some embodiments of the present invention, there is provided a base station de-service warning device, comprising: a quantity prediction module, configured to input a sequence consisting of the number of de-service base stations in each of multiple historical time periods into a pre-trained de-service quantity prediction model, and determine the number of de-service base stations in a future time period output by the de-service quantity prediction model; an increase amount determination module, configured to determine, based on the number of de-service base stations in the future time period, the increase amount of resource consumption caused by the de-service base stations for non-de-service base stations in the event of future de-service; and an early warning strategy determination module, configured to determine an early warning strategy based on the increase amount of resource consumption.

[0018] According to a third aspect of some embodiments of the present invention, there is provided a base station decommissioning warning device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the aforementioned base station decommissioning warning methods based on instructions stored in the memory.

[0019] According to a fourth aspect of some embodiments of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the aforementioned base station decommissioning warning methods.

[0020] Some embodiments of the above invention have the following advantages or beneficial effects: Through the method of the embodiment of the present invention, the decommissioned base stations in the future period can be predicted based on historical data, so as to measure the increase in resource consumption caused by the possible decommissioning and make corresponding warnings. Therefore, the operator can focus on prevention based on the reminder and actively take measures such as monitoring and maintenance of the base station to minimize the occurrence of base station decommissioning accidents and reduce the resource consumption caused by the decommissioning of the base station.

[0021] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 A schematic flow chart of a base station out-of-service warning method according to some embodiments of the present invention is shown.

[0024] Figure 2 A schematic flow chart of a method for determining an increase in resource consumption according to some embodiments of the present invention is shown.

[0025] Figure 3 A schematic flow chart of a method for determining a service load transfer situation according to some embodiments of the present invention is shown.

[0026] Figure 4 The schematic diagram of sub-area division is shown as an example.

[0027] Figure 5 A schematic flow chart of a method for predicting a decommissioned base station according to some embodiments of the present invention is shown.

[0028] Figure 6 A schematic structural diagram of a base station service decommissioning warning device according to some embodiments of the present invention is shown.

[0029] Figure 7 A schematic structural diagram of a base station service decommissioning warning device according to some other embodiments of the present invention is shown.

[0030] Figure 8 A schematic structural diagram of a base station service decommissioning warning device according to some further embodiments of the present invention is shown. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. 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.

[0032] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0033] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0034] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0035] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0036] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0037] Figure 1 FIG. 2 is a flow chart showing a method for early warning of a base station service decommissioning according to some embodiments of the present invention. Figure 1 As shown, the base station service decommissioning warning method of this embodiment includes steps S102 to S106.

[0038] In step S102, a sequence consisting of the number of decommissioned base stations in each of a plurality of historical time periods is input into a pre-trained decommissioning number prediction model to determine the number of decommissioned base stations in a future time period output by the decommissioning number prediction model.

[0039] For example, the input sequence is T(i) = {x i ,x i+1 ,…,x i+t}, each element in the sequence represents the number of decommissioned base stations corresponding to time i, i+1, ..., i+t; the output is, for example, a sequence within a period of time after the current time, corresponding to the number of decommissioned base stations at each time in one or more future time periods. In some embodiments, the length of the period of time corresponding to the output may be less than or much less than the value of t.

[0040] In some embodiments, the decommissioning prediction model is a long short-term memory (LSTM) model. The LSTM model is a neural network model based on time cycles, a variant of the RNN model, and solves the problem of gradient disappearance in the RNN model.

[0041] In some embodiments, the retirement of base stations can be predicted on a regional basis. For example, historical data of a certain district in a certain city is used to predict the number of retired base stations in the district in the future. Since base stations in the same area are in similar geographical and weather environments and have similar establishment and maintenance rules, the retirement of base stations has more temporal regularity and is more suitable for prediction using recurrent neural networks such as LSTM.

[0042] In step S104, based on the number of de-serving base stations in the future period, the increase in resource consumption caused by the de-serving base stations for non-de-serving base stations in the event of future de-serving is determined.

[0043] After analysis, the inventors found that when a base station is decommissioned, the services of this base station will be transferred to other base stations, thereby increasing the load of other base stations around the decommissioned base station. The increase in the base station load will correspondingly increase the base station's consumption of power consumption, costs, electricity and other resources. Therefore, by analyzing the increase in resource consumption caused by the decommissioned base station for non-decommissioned base stations in the event of a base station decommissioning, the losses caused by the decommissioned base station can be evaluated.

[0044] In step S106, a warning strategy is determined based on the increase in resource consumption.

[0045] In some embodiments, when the increase in resource consumption is greater than a preset value, a service withdrawal reminder is sent. In addition, the increase can also be divided into multiple levels to provide service withdrawal reminders of different levels.

[0046] Through the method of the above embodiment, the decommissioned base stations in the future period can be predicted based on historical data, so as to measure the increase in resource consumption caused by the possible decommissioning and make corresponding warnings. Therefore, the operator can focus on prevention based on the reminder and actively take measures such as monitoring and maintenance of base stations to minimize the occurrence of base station decommissioning accidents and reduce the resource consumption caused by base station decommissioning.

[0047] In some embodiments, the base station is a 5G base station. Therefore, the embodiments of the present invention can predict the number of 5G base stations that are out of service, so as to promote better commercial use of 5G technology.

[0048] Reference below Figure 2 An embodiment of a method for determining an increase in resource consumption according to the present invention is described.

[0049] Figure 2 FIG. 2 is a flow chart showing a method for determining the growth amount of resource consumption according to some embodiments of the present invention. Figure 2 As shown, the method for determining the growth amount of resource consumption in this embodiment includes steps S202 to S206.

[0050] In step S202, for each decommissioned base station, it is determined that the service load of the decommissioned base station is transferred to a non-decommissioned base station in the event of a future decommissioning.

[0051] In some embodiments, the traffic load is a traffic load percentage.

[0052] In step S204, the increase in resource consumption caused by the decommissioned base station to the non-decommissioned base station is determined according to the increased service load of the non-decommissioned base station.

[0053] In some embodiments, the load of the decommissioned base station shared by each non-decommissioned base station may be calculated first, and then the increase in resource consumption of each non-decommissioned base station may be determined according to a preset correspondence between the service load and the resource consumption.

[0054] After analysis, the inventors found that there is a certain correlation between the load and power consumption of the base station. Take the 5G base station as an example. The main equipment of the 5G base station mainly includes BBU (Building Base band Unit) and AAU (Active Antenna Unit), and the power consumption is also mainly generated by BBU and AAU. The main function of BBU is to process baseband digital signals. AAU can be regarded as RRU (Radio Remote Unit) in the 4G base station system plus an antenna. Its main function is to convert the baseband digital signal into an analog signal, modulate it into a high-frequency radio frequency signal, and then amplify the power through the power amplifier unit and the antenna to transmit the signal. The data shows that the power of BBU is relatively stable and is not greatly affected by the business load. As the load of AAU increases, the power consumption also increases significantly.

[0055] Therefore, in some embodiments, the increase in power consumption caused by the decommissioned base station to the non-decommissioned base station can be determined based on the increased service load of the non-decommissioned base station and the functional relationship between the service load of the base station and the power consumption of the base station.

[0056] Resource consumption may also refer to the cost consumption caused by power consumption. In some embodiments, the increase in costs caused by the decommissioned base station to the non-decommissioned base station is determined based on the increased service load of the non-decommissioned base station, the functional relationship between the service load of the base station and the power consumption of the base station, and the cost consumed by the preset unit of power consumption.

[0057] In step S206, the total amount of increase in resource consumption caused by each decommissioned base station for non-decommissioned base stations is determined.

[0058] Through the method of the above embodiment, the increase in resource consumption caused by the decommissioning base station can be determined by utilizing the characteristic that the services of the decommissioning base station will be transferred to other base stations, which increases the load of other base stations around the decommissioning base station. Thus, the impact of the decommissioning base station on other base stations can be determined more accurately.

[0059] After further analysis, the inventor found that within the radiation range of the decommissioned base station, the farther away the base station is, the less traffic it can bear from the decommissioned base station. Therefore, when determining the traffic load borne by the non-decommissioned base station, its distance from the decommissioned base station can be considered. Figure 3 An embodiment of a method for determining a service load transfer situation according to the present invention is described.

[0060] Figure 3 FIG. 2 is a flow chart showing a method for determining a service load transfer situation according to some embodiments of the present invention. Figure 3 As shown, the method for determining the service load transfer situation in this embodiment includes steps S302 to S304.

[0061] In step S302, the area where the decommissioned base station is located is divided into a plurality of sub-areas.

[0062] In step S304, based on the preset load distribution ratio corresponding to each sub-area, the service load of the deserving base station transferred to the non-deserving base station in the event of future deserving is determined, wherein the load distribution ratio corresponding to the sub-area is positively correlated with the distance between the sub-area and the deserving base station.

[0063] Figure 4 An exemplary division method of sub-areas is shown: the area where the retired base station is located is divided into a non-annular area (for example, area 1) and one or more annular areas (for example, area 2) surrounding the non-annular area. Figure 4 In FIG. 1 , the dotted line indicates the path for load transfer from the retired base station 40 to the non-retired base station, and the load ratio is marked on each path. The load ratio corresponding to area 1 is r 1 , that is, the load ratio of the non-decommissioned base stations 41 and 42 is r 1 ; The load ratio corresponding to area 2 is r 2 , that is, the load ratio of the non-decommissioned base stations 43, 44, 45, 46, and 47 is r 2 . And there is r 1 >r 2 .

[0064] By dividing the sub-areas and presetting different load distribution ratios for each sub-area according to the distance, the transfer of business load after the base station is retired can be determined more reasonably, thereby more accurately determining the impact of the retired base station.

[0065] Formula (1) exemplarily shows a calculation method for determining the resource consumption growth amount based on the sub-area in some embodiments. In this embodiment, the resource consumption growth amount is represented by the cost C.

[0066]

[0067] In formula (1), T represents the period of time covered by the decommissioning in the future; P represents the cost of power consumption per preset unit, such as electricity; N represents the number of decommissioned base stations in the future period; m represents the number of sub-areas, i represents the identifier of the sub-area; n irepresents the number of non-decommissioned base stations in the ith sub-area, j represents the identifier of the non-decommissioned base stations in the ith sub-area; the independent variable of f(·) is load and the dependent variable is power consumption; r i represents the load distribution ratio corresponding to the i-th sub-area; Q represents the load of the retired base station; q ij represents the original load of the jth non-decommissioned base station in the i-th sub-area.

[0068] Thus, the impact of decommissioned base stations on non-decommissioned base stations and the increase in resource consumption caused by decommissioned base stations can be evaluated more accurately.

[0069] In some embodiments, f(·) is a piecewise function composed of multiple linear functions, and the parameters of each linear function are determined according to historical data. An exemplary calculation method of f(x) can refer to formula (2).

[0070]

[0071] In formula (2), x represents the service load; x 1 、x 2 、x 3 ... represents the segmented value of the business load; k 1 、b 1 , k 2 、b 2 ... represents preset parameters. The values ​​of these parameters can be determined according to historical data. For example, Table 1 exemplarily shows the corresponding relationship between service load and power consumption.

[0072] Table 1

[0073]

[0074] Therefore, the parameters in the piecewise function can be determined according to data similar to Table 1.

[0075] The above-mentioned embodiments determine the early warning strategy based on the macro prediction of the number of decommissioned base stations. In addition, the present invention also provides an embodiment of a method for accurately predicting decommissioned base stations.

[0076] Figure 5 FIG. 2 is a flow chart showing a method for predicting a decommissioned base station according to some embodiments of the present invention. Figure 5 As shown, the method for predicting a decommissioned base station in this embodiment includes steps S502 to S504.

[0077] In step S502, the state characteristics of the base station are input into a pre-trained neural network model to obtain a classification result output by the neural network model to determine whether the base station is a decommissioned base station. The neural network model includes an input layer, a hidden layer, and an output layer.

[0078] In some embodiments, the status characteristics of the base station include the temperature, current value, etc. of the base station.

[0079] In step S504, warning information is generated based on information of base stations classified as decommissioned base stations.

[0080] Through the method of the above embodiment, the possible outage can be located at a specific base station so that the staff can take preventive measures in time.

[0081] After receiving the service withdrawal warning, the operator can take various preventive measures. For example, strengthen the inspection of daily power supply equipment of base stations, conduct regular performance tests on the batteries of base stations, and timely grasp the health of batteries, replace problematic batteries, and reasonably configure the rectifier modules of power cabinets. Another example is to strengthen the quality inspection of base station lines. Many base stations are out of service due to aging lines, many joints, and high attenuation. Therefore, it is necessary to strengthen the monitoring of the lines. The quality control of the construction party can be strengthened by tracing the source, and timely repairs can be carried out when problems occur. Another example is to handle faults scientifically and promptly. By establishing a complete base station data monitoring platform, the actual situation of the base station can be understood in detail, so that the staff can accurately and reasonably dispatch personnel to handle base station faults. In addition, strengthen the dispatch and processing of fault work orders to improve the efficiency of alarm processing; mine the fault work order information to provide more targeted suggestions for future base station maintenance.

[0082] Reference below Figure 6 An embodiment of a base station out-of-service warning device of the present invention is described.

[0083] Figure 6 FIG. 2 shows a schematic diagram of the structure of a base station service decommissioning warning device according to some embodiments of the present invention. Figure 6 As shown, the base station de-service warning device 60 of this embodiment includes: a quantity prediction module 610, which is configured to input a sequence consisting of the number of de-service base stations in each of multiple historical time periods into a pre-trained de-service quantity prediction model, and determine the number of de-service base stations in a future time period output by the de-service quantity prediction model; an increase amount determination module 620, which is configured to determine, based on the number of de-service base stations in the future time period, the increase amount of resource consumption caused by the de-service base stations for non-de-service base stations in the event of de-service in the future; and an early warning strategy determination module 630, which is configured to determine an early warning strategy based on the increase amount of resource consumption.

[0084] In some embodiments, the decommissioning quantity prediction model is a long short-term memory network (LSTM) model.

[0085] In some embodiments, the growth amount determination module 620 is further configured to determine, for each deserving base station, the business load that the deserving base station will transfer to a non-deserving base station in the event of future deserving; determine the growth amount of resource consumption caused by the deserving base station to the non-deserving base station based on the increased business load of the non-deserving base station; and determine the sum of the growth amounts of resource consumption caused by each deserving base station to the non-deserving base stations.

[0086] In some embodiments, the increase amount determination module 620 is further configured to determine the increase in power consumption brought by the decommissioned base station to the non-decommissioned base station based on the increased business load of the non-decommissioned base station and the functional relationship between the business load of the base station and the power consumption of the base station.

[0087] In some embodiments, the decommissioned base station is a 5G base station, and the power consumption of the base station is the power consumption of the BBU and AAU of the base station.

[0088] In some embodiments, the increase amount determination module 620 is further configured to determine the increase in costs brought by the decommissioned base station to the non-decommissioned base station based on the increased business load of the non-decommissioned base station, the functional relationship between the business load of the base station and the power consumption of the base station, and the cost consumed by a preset unit of power consumption.

[0089] In some embodiments, the growth amount determination module 620 is further configured to divide the area where the decommissioned base station is located into multiple sub-areas; based on the preset load distribution ratio corresponding to each sub-area, determine the business load of the decommissioned base station transferred to the non-decommissioned base station in the event of future decommissioning, wherein the load distribution ratio corresponding to the sub-area is positively correlated with the distance between the sub-area and the decommissioned base station.

[0090] In some embodiments, the growth amount determination module 620 is further configured to use the following formula to determine the growth amount C of resource consumption caused by the deserving base station to the non-deserving base station in the event of deserving in the future:

[0091]

[0092] Wherein, T represents the period of time covered by the future decommissioning situation; P represents the cost consumed by the preset unit of power consumption; N represents the number of decommissioned base stations in the future period; m represents the number of sub-areas, i represents the identifier of the sub-area; n i represents the number of non-decommissioned base stations in the ith sub-area, j represents the identifier of the non-decommissioned base stations in the ith sub-area; the independent variable of f(·) is load and the dependent variable is power consumption; r i represents the load distribution ratio corresponding to the i-th sub-area; Q represents the load of the retired base station; q ij represents the original load of the jth non-decommissioned base station in the i-th sub-area.

[0093] In some embodiments, f(·) is a piecewise function composed of multiple linear functions, and the parameters of each linear function are determined according to historical data.

[0094] In some embodiments, the early warning strategy determination module 630 is further configured to send a service withdrawal reminder when the increase in resource consumption is greater than a preset value.

[0095] In some embodiments, the base station decommissioning warning device also includes: a classification module 640, which is configured to input the state characteristics of the base station into a pre-trained neural network model to obtain a classification result output by the neural network model to determine whether the base station is a decommissioned base station; the warning strategy determination module 630 is further configured to generate warning information based on information of base stations whose classification results are decommissioned base stations.

[0096] Figure 7 FIG. 2 shows a schematic diagram of a structure of a base station service decommissioning warning device according to some other embodiments of the present invention. Figure 7 As shown, the base station decommissioning warning device 70 of this embodiment includes: a memory 710 and a processor 720 coupled to the memory 710, and the processor 720 is configured to execute the base station decommissioning warning method in any of the aforementioned embodiments based on the instructions stored in the memory 710.

[0097] The memory 710 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0098] Figure 8 FIG. 2 shows a schematic diagram of a structure of a base station service outage warning device according to some other embodiments of the present invention. Figure 8 As shown, the base station decommissioning warning device 80 of this embodiment includes: a memory 810 and a processor 820, and may also include an input / output interface 830, a network interface 840, a storage interface 850, etc. These interfaces 830, 840, 850 and the memory 810 and the processor 820 may be connected, for example, via a bus 860. Among them, the input / output interface 830 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 840 provides a connection interface for various networked devices. The storage interface 850 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0099] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the aforementioned base station decommissioning warning methods.

[0100] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A base station out-of-service early warning method, comprising: Inputting a sequence consisting of the number of decommissioned base stations in each of a plurality of historical time periods into a pre-trained decommissioning number prediction model, and determining the number of decommissioned base stations in a future time period output by the decommissioning number prediction model; Determining, according to the number of deserving base stations in the future time period, an increase in resource consumption caused by the deserving base station for non-deserving base stations in the event of deserving in the future, including: determining, for each deserving base station, a service load transferred from the deserving base station to the non-deserving base station in the event of deserving in the future; determining, according to the increased service load of the non-deserving base station, an increase in resource consumption caused by the deserving base station for the non-deserving base station; and determining the sum of the increase in resource consumption caused by each deserving base station for the non-deserving base station; Based on the growth amount of the resource consumption, an early warning strategy is determined.

2. The base station out-of-service warning method according to claim 1, wherein: The decommissioning quantity prediction model is a long short-term memory network LSTM model.

3. The base station out-of-service warning method according to claim 1, wherein: The increase in power consumption caused by the decommissioned base station to the non-decommissioned base station is determined according to the increased service load of the non-decommissioned base station and the functional relationship between the service load of the base station and the power consumption of the base station.

4. The base station out-of-service warning method according to claim 1, wherein: The decommissioned base station is a 5G base station, and the power consumption of the base station is the power consumption of the indoor baseband processing unit BBU and the active antenna processing unit AAU of the base station.

5. The base station out-of-service warning method according to claim 1, wherein: The increase in costs brought by the decommissioned base station to the non-decommissioned base station is determined based on the increased business load of the non-decommissioned base station, the functional relationship between the business load of the base station and the power consumption of the base station, and the cost consumed by a preset unit of power consumption.

6. The base station service decommissioning warning method according to any one of claims 1 to 5, wherein: The determining that, in the event of a future de-service, the service load transferred from the de-serviced base station to the non-de-serviced base station includes: Dividing the area where the decommissioned base station is located into multiple sub-areas; According to the preset load distribution ratio corresponding to each sub-area, the business load of the deserving base station transferred to the non-deserving base station in the event of future deserving is determined, wherein the load distribution ratio corresponding to the sub-area is positively correlated with the distance between the sub-area and the deserving base station.

7. The base station out-of-service warning method according to claim 6, wherein: The following formula is used to determine the increase in resource consumption C caused by the decommissioned base station for the non-decommissioned base stations in the event of decommissioning in the future: Wherein, T represents the period of time covered by the decommissioning in the future; P represents the cost consumed by the preset unit of power consumption; N represents the number of decommissioning base stations in the future period; m represents the number of sub-areas, and i represents the identifier of the sub-area; represents the number of non-decommissioned base stations in the ith sub-area, and j represents the identifier of the non-decommissioned base station in the ith sub-area; The independent variable is load and the dependent variable is power consumption; represents the load distribution ratio corresponding to the i-th sub-area; Q represents the load of the retired base station; represents the original load of the jth non-decommissioned base station in the i-th sub-area.

8. The base station out-of-service warning method according to claim 7, wherein: It is a piecewise function composed of multiple linear functions, and the parameters of each linear function are determined according to historical data.

9. The base station out-of-service warning method according to claim 1, wherein: The determining of the early warning strategy based on the growth amount of the resource consumption includes: When the increase in resource consumption is greater than a preset value, a service withdrawal reminder is sent.

10. The base station decommissioning warning method according to claim 1, further comprising: Inputting the state characteristics of the base station into a pre-trained neural network model to obtain a classification result output by the neural network model for determining whether the base station is a decommissioned base station; Based on the information of the base station classified as a decommissioned base station, warning information is generated.

11. A base station out-of-service warning device, comprising: A quantity prediction module is configured to input a sequence consisting of the number of decommissioned base stations in each of a plurality of historical time periods into a pre-trained decommissioned quantity prediction model, and determine the number of decommissioned base stations in a future time period output by the decommissioned quantity prediction model; The growth amount determination module is configured to determine, according to the number of deserving base stations in the future time period, the growth amount of resource consumption caused by the deserving base station to the non-deserving base station in the case of deserving in the future, including: for each deserving base station, determining the service load transferred from the deserving base station to the non-deserving base station in the case of deserving in the future; determining the growth amount of resource consumption caused by the deserving base station to the non-deserving base station according to the increased service load of the non-deserving base station; determining the sum of the growth amount of resource consumption caused by each deserving base station to the non-deserving base station; The early warning strategy determination module is configured to determine an early warning strategy based on the growth amount of the resource consumption.

12. A base station out-of-service warning device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the base station service decommissioning warning method according to any one of claims 1 to 10 based on instructions stored in the memory.

13. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the base station decommissioning warning method according to any one of claims 1 to 10 is implemented.

Citation Information

Patent Citations

  • Method and apparatus for controlling base station overloading

    CN101437265A

  • Large-area base station out-of-service alarm monitoring method and system

    CN102075990A

  • Apparatus and method for reducing energy consumption in wireless communication system

    CN102196460A

  • Method and device for supplying power for base station

    CN107706953A

  • Method and device for handling out-of-service alarm of base station

    CN111083721A