Base station energy-saving wake-up method and device, computer device and storage medium

Through artificial intelligence models, predict and monitor key performance indicators of base stations, automatically analyze deviations and issue wake-up instructions, solving the problem of difficulty in deep energy saving and awakening of base stations, and realizing automatic, accurate and safe deep energy saving of base stations, which is suitable for large-scale applications.

CN114980184BActive Publication Date: 2024-11-22CHINA TELECOM CORP LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202110210472.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-02-25
Publication Date
2024-11-22
Estimated Expiration
2041-02-25

AI Technical Summary

Technical Problem

The prior art is difficult to wake up when the base station is deeply energy-saving, resulting in time-consuming and labor-consuming, complex configuration, which may affect business security, and is difficult to apply at scale.

Method used

Through artificial intelligence models, predict key performance indicator data of deep energy-saving cells and co-covered cells, monitor actual data, analyze deviation, and automatically issue wake-up instructions when the deviation exceeds the predetermined range, achieving automatic, accurate and safe deep energy-saving wake-up.

Benefits of technology

It realizes timely, accurate, safe and automatic deep energy-saving wake-up of the base station, reduces operational complexity and cost, improves efficiency, and is suitable for large-scale applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114980184B_ABST
    Figure CN114980184B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a base station energy-saving wake-up method and device, a computer device and a storage medium. The base station energy-saving wake-up method includes: predicting the key performance indicator data of deep energy-saving cells and co-covered cells; monitoring the actual key performance indicator data of deep energy-saving cells and co-covered cells; performing deviation analysis on the actual key performance indicator data and the predicted key performance indicator data; when the deviation of the actual key performance indicator data exceeds a predetermined range, issuing a wake-up instruction to the base station corresponding to the deep energy-saving cell. The present disclosure predicts the KPI data of the future continuous period of the current cell and the basic cell through AI, and can realize the automatic wake-up of deep energy saving in a timely, accurate, safe and automatic manner.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of information technology, and in particular to a base station energy-saving wake-up method and device, a computer device and a storage medium. Background Art

[0002] When the base station is deeply energy-saving, such as shutting down the carrier or entering deep sleep, it no longer processes services, and waking up becomes a major problem.

[0003] The related technical method mainly relies on manual observation of whether the services in the neighboring areas are abnormal, which is time-consuming and labor-intensive. The manufacturer's method is to regard the energy-saving cell C1 and the co-covered basic cell C2 as an energy-saving group, and to set fixed upper and lower limits of the KPI (Key Performance Indicator) threshold for C2 for protective wake-up. There are many parameters (for example, Huawei requires 8 instructions for a cell involving more than 30 parameters), which makes the operation difficult and may also require the purchase of a license. Summary of the invention

[0004] Improper configuration of related technologies may make most cells unable to enter energy saving or wake up, and even affect business security.

[0005] The relevant technologies still have the following technical problems: they are time-consuming and labor-intensive, and a one-size-fits-all configuration may not save energy properly in most communities, and may even affect business security, resulting in poor results and difficulty in large-scale application.

[0006] In view of at least one of the above technical problems, the present disclosure provides a base station energy-saving wake-up method and device, a computer device and a storage medium, which can realize automatic wake-up for deep energy saving in a timely, accurate, safe and automatic manner.

[0007] According to one aspect of the present disclosure, a base station energy-saving wake-up method is provided, including:

[0008] Predict key performance indicator data of deep energy-saving cells and shared coverage cells;

[0009] Monitor the actual key performance indicator data of deep energy-saving cells and shared coverage cells;

[0010] Conduct deviation analysis on actual key performance indicator data and predicted key performance indicator data;

[0011] When the deviation of the actual key performance indicator data exceeds a predetermined range, a wake-up instruction is sent to the base station corresponding to the deep energy-saving cell.

[0012] In some embodiments of the present disclosure, the predicted key performance indicator data of the deep energy-saving cell and the co-coverage cell include:

[0013] Determining predicted values ​​of key performance indicators for a first predetermined number of future forecast periods using an artificial intelligence model;

[0014] Calculate a moving average of the most recent second predetermined number of sliding window period prediction values, where the second predetermined number is less than the first predetermined number;

[0015] The predicted values ​​of the accumulated key performance indicators of the deep energy-saving cells and the co-coverage cells are calculated, and the predicted values ​​of the accumulated key performance indicators are used as predicted key performance indicator data.

[0016] In some embodiments of the present disclosure, the performing deviation analysis on the actual key performance indicator data and the predicted key performance indicator data includes:

[0017] Determine the ratio of actual key performance indicator data to predicted key performance indicator data;

[0018] determining whether the ratio is within a predetermined range;

[0019] When the ratio exceeds the predetermined range, it is determined that the deviation of the actual key performance indicator data exceeds the predetermined range.

[0020] In some embodiments of the present disclosure, the performing deviation analysis on the actual key performance indicator data and the predicted key performance indicator data further includes:

[0021] Determine the proportion of business volume that can be tolerated to decrease and the proportion of business volume that can be tolerated to increase suddenly;

[0022] The predetermined range is determined according to the proportion of the business volume that can be tolerated to decrease and the proportion of the business volume that can be tolerated to increase suddenly.

[0023] In some embodiments of the present disclosure, determining the predetermined range according to the proportion of the traffic volume that can be reduced and the proportion of the traffic volume that can be increased suddenly further includes:

[0024] Determine the lower limit of the predetermined range according to the difference between 1 and the tolerable reduction in the business volume ratio;

[0025] The upper limit of the predetermined range is determined according to the sum of 1 and the proportion of the traffic volume that tolerates a sudden increase.

[0026] In some embodiments of the present disclosure, the artificial intelligence model includes but is not limited to one or more model algorithms such as a neural network, a lightweight gradient boosting machine, a random forest model, and a differential autoregressive moving average model.

[0027] According to another aspect of the present disclosure, a base station energy-saving wake-up device is provided, including:

[0028] An indicator prediction module is configured to predict key performance indicator data of deep energy-saving cells and co-coverage cells;

[0029] An indicator monitoring module is configured to monitor actual key performance indicator data of the deep energy-saving cell and the co-coverage cell;

[0030] a deviation analysis module, configured to perform deviation analysis on actual key performance indicator data and predicted key performance indicator data;

[0031] The wake-up module is configured to send a wake-up instruction to the base station corresponding to the deep energy-saving cell when the deviation of the actual key performance indicator data exceeds a predetermined range.

[0032] In some embodiments of the present disclosure, the base station energy-saving awakening device is configured to execute operations to implement the base station energy-saving awakening method as described in any of the above embodiments.

[0033] According to another aspect of the present disclosure, there is provided a computer device, comprising:

[0034] a memory configured to store data and instructions;

[0035] The processor is configured to execute the instructions so that the computer device performs operations to implement the base station energy-saving wake-up method as described in any of the above embodiments.

[0036] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the base station energy-saving wake-up method as described in any of the above embodiments is implemented.

[0037] The present invention predicts the KPI data of the future continuous period of the current cell and the basic cell through AI (Artificial Intelligence), and can realize automatic wake-up for deep energy saving in a timely, accurate, safe and automatic manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present disclosure 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 disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 The present invention is a schematic diagram of some embodiments of the base station energy-saving wake-up method disclosed in the present invention.

[0040] Figure 2 Schematic diagram of other embodiments of the base station energy-saving wake-up method disclosed in the present invention.

[0041] Figure 3 It is a schematic diagram of some embodiments of the energy-saving wake-up device of the base station disclosed in the present invention.

[0042] Figure 4 It is a schematic diagram of the structure of some embodiments of the computer device disclosed in the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of 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 disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0044] Unless specifically stated otherwise, 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 disclosure.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] Figure 1 The following is a schematic diagram of some embodiments of the base station energy-saving wake-up method disclosed in the present invention. Preferably, this embodiment can be executed by the base station energy-saving wake-up device disclosed in the present invention or the computer device disclosed in the present invention. The method may include steps 11 to 14, wherein:

[0050] Step 11, predicting key performance indicator data of deep energy-saving cells and co-coverage cells.

[0051] In some embodiments of the present disclosure, step 11 may include steps 111 to 113, wherein:

[0052] Step 111, using an artificial intelligence model to determine predicted values ​​of key performance indicators within a first predetermined number of prediction periods in the future.

[0053] In some embodiments of the present disclosure, the key performance indicators may include KPI data such as resources, traffic, and the number of access users of the deep energy-saving cell and the co-coverage cell.

[0054] In some embodiments of the present disclosure, the traffic data may include PDCP (Packet Data Convergence Protocol) traffic data, RRC (Radio Resource Control) instruction traffic data, and other traffic data.

[0055] In some embodiments of the present disclosure, the artificial intelligence model may include but is not limited to one or more model algorithms such as a neural network, a lightweight gradient boosting machine, a random forest model, and a differential autoregressive moving average model.

[0056] In some embodiments of the present disclosure, the first predetermined number may be n.

[0057] In some embodiments of the present disclosure, step 111 may include: obtaining K days of historical data of network PM (Performance Management), and outputting KPI prediction values ​​for a certain n periods in the future through AI algorithms, such as neural networks, LGBM (Light gradient boosting machine), random forests, ARIMA (AutoRegressive Integrated Moving Average) prediction models, etc., for example: outputting prediction values ​​of at least 14 days * 24 hours, and outputting prediction results Y[1 to n] (such as 24-hour downlink PDCP [1-24] = [1.0, 1.5, ..., 0.05]), where PDCP is Packet Data Convergence Protocol traffic data.

[0058] Step 112, calculating a moving average of the most recent second predetermined number m of sliding window period prediction values, wherein the second predetermined number m is smaller than the first predetermined number n.

[0059] In some embodiments of the present disclosure, m may be 2.

[0060] In some embodiments of the present disclosure, step 112 may include: calculating the moving average (smoothed bursts) Y'[t] of the latest m (recommendation 2) sliding window periods of the current period (hour), where Y'[t] = ∑Y[t](1 to m) / m, where t is the number of periods.

[0061] Step 113, calculate the predicted value of the accumulated key performance indicator of the energy-saving cell group composed of the deep energy-saving cell cell1 and the co-covered cell cell2 of the cell, and use the predicted value of the accumulated key performance indicator as the predicted key performance indicator data.

[0062] In some embodiments of the present disclosure, step 112 may include: determining the cumulative KPI of the current cell and the first co-covered cell energy-saving cell group according to formula (1).

[0063] Y'_group[t]=Y'_cell1[t]+Y'_cell2[t] (1)

[0064] Step 12, monitor the actual key performance indicator data R_group[t] of the deep energy-saving cell and the co-coverage cell.

[0065] Step 13: Perform deviation analysis on the actual key performance indicator data and the predicted key performance indicator data.

[0066] In some embodiments of the present disclosure, step 13 may include steps 131 to 135, wherein:

[0067] Step 131, determining the ratio of the actual key performance indicator data R_group[t] to the predicted key performance indicator data (R_group[t] / Y'_group[t]).

[0068] Step 132: Determine a tolerable decrease in the traffic volume ratio L1 and a tolerable sudden increase in the traffic volume ratio L2.

[0069] Step 133 , determining a predetermined range according to the tolerable decrease in the traffic volume ratio L1 and the tolerable sudden increase in the traffic volume ratio L2 .

[0070] In some embodiments of the present disclosure, step 133 may include: determining the lower limit (1-L1) of the predetermined range based on the difference between 1 and the proportion of business volume that can be tolerated to decrease; determining the upper limit (1+L2) of the predetermined range based on the sum of 1 and the proportion of business volume that can be tolerated to increase suddenly.

[0071] Step 134, determining whether the ratio is within a predetermined range.

[0072] Step 135, when the ratio exceeds a predetermined range (eg, R_group[t] / Y'_group[t]<(1-L1), or R_group[t] / Y'_group[t]>(1+L2)), it is determined that the deviation of the actual key performance indicator data exceeds a predetermined range.

[0073] Step 14: When the deviation of the actual key performance indicator data exceeds the predetermined range, that is, when the service increases or decreases sharply (network performance decreases), a deviation alarm is triggered, and a wake-up command is issued to the base station corresponding to the deep energy-saving cell.

[0074] In some embodiments of the present disclosure, the step of sending a wake-up instruction to the base station corresponding to the deep energy saving cell may include: for the cell with deviation alarm, the wake-up module determines the start-up instruction according to the shutdown instruction, and immediately sends it to the network management system.

[0075] The base station energy-saving wake-up method provided in the above embodiment of the present disclosure is an intelligent, personalized, safe, accurate, and versatile deep energy-saving automatic wake-up solution. The above embodiment of the present disclosure provides a wake-up strategy for each cell, and predicts the KPI data of the future continuous period of the cell and the basic cell through AI. The above embodiment of the present disclosure can be timely, accurate, safe, automatic, and large-scale, saving costs and improving efficiency, so that deep energy saving can be used on a large scale.

[0076] Figure 2 Schematic diagram of other embodiments of the base station energy-saving wake-up method disclosed in the present invention. Preferably, this embodiment can be executed by the base station energy-saving wake-up device disclosed in the present invention or the computer device disclosed in the present invention. The method may include steps 21 to 27, wherein:

[0077] Step 21, obtain K days of historical PM data from the network PM database, use the time series prediction model to output the KPI prediction value for a certain n periods in the future, for example: at least 14 days * 24 hours prediction, and output the prediction result Y[1 to n] (such as 24-hour downlink PDCP[1-24] = [1.0,1.5,...,0.05].

[0078] In some embodiments of the present disclosure, the time series prediction model may be one or more of model algorithms such as, but not limited to, a neural network, an LGBM model, a random forest model, an ARIMA model, etc.

[0079] In some embodiments of the present disclosure, the KPI prediction value may be a prediction value of PDCP or RRC traffic.

[0080] Step 22, performing data processing on the prediction result data.

[0081] In some embodiments of the present disclosure, step 22 may include: performing sliding window moving average on the prediction result data.

[0082] In some embodiments of the present disclosure, step 22 may include: calculating the moving average (smoothing out sudden situations) of the latest m (recommendation 2) sliding window periods of the current period (hour) according to formula (2), where t is the tth period among the m periods.

[0083] Y'[t]=∑Y[t](1 to m) / m (2)

[0084] Step 23: According to Y'_group[t]=Y'_cell1[t]+Y'_cell2[t], the cumulative KPI of the current cell and the first co-covered cell energy-saving cell group is calculated.

[0085] Step 24, when the cell is in deep energy saving (such as carrier shutdown, deep sleep), the indicator monitoring module monitors the actual value of KPI in each cycle by monitoring the current PM data and the co-coverage cell library automatically discovered based on co-operation and co-coverage.

[0086] In some embodiments of the present disclosure, step 23 may include: online monitoring of the KPI of the first co-coverage cell of the deep energy saving cell, assuming it to be R_group[t].

[0087] Step 25 , accumulating the actual KPI values ​​of the energy-saving cell and the basic cell it covers, and comparing them with the prediction result of step 23 .

[0088] Step 26, determine whether the actual key performance indicator data exceeds the predicted result range, that is, determine whether the business loss during the energy-saving period increases or decreases sharply. If the actual key performance indicator data exceeds the predicted result range, execute step 27; otherwise, if the actual key performance indicator data does not exceed the predicted result range, execute step 24.

[0089] In some embodiments of the present disclosure, step 26 may include: performing a deviation analysis: the actual deviation of the energy-saving cell group data exceeds the range, and a deviation alarm is triggered when the service increases or decreases sharply (network performance decreases), that is, R_group[t] / Y'_group[t]<(1-L1), or R_group[t] / Y'_group[t]>(1+L2), where L1 is the proportion of business volume that can be tolerated to decrease, and L2 is the proportion of business volume that can tolerate a sudden increase.

[0090] Step 27, the wake-up module checks the shutdown instruction to obtain the startup instruction to wake up the cell.

[0091] In some embodiments of the present disclosure, step 27 may include: for the cell that deviates from the alarm, the wake-up module determines the energy-saving start instruction according to the shutdown instruction, and immediately sends the energy-saving start instruction to the 4G / 5G network management system.

[0092] The above embodiments of the present disclosure provide a method for intelligent awakening of deep energy-saving base stations. In view of the problems that the current awakening mechanism cannot be personalized, intelligent, scalable and safely applied, based on AI prediction of KPI data such as resources, traffic, number of access users of deep energy-saving cells and co-covered cells, the KPI conditions of both are monitored, and the deviation is analyzed with the KPI data predicted by AI in advance. When the actual data deviation exceeds the predetermined range, a wake-up command is automatically issued to the base station.

[0093] The energy-saving wake-up method for a base station disclosed in the present invention is described below through specific embodiments.

[0094] Step 1: The cell starts and the carrier is turned off.

[0095] Step 2: Every day, AI algorithms such as neural networks, LGBM, random forests, and ARIMA are used to output KPI forecast values ​​for a certain number of n periods in the future. Taking the downlink traffic PDCP as an example, at least 14 days * 24 hours of forecasting are performed, and the future forecast result PDCP'[0-23] = [1.12, 1.58, ..., 0.05] (in GB) is output.

[0096] Step 3: Process the predicted value:

[0097] Step 3-1, calculate the moving average (smoothing out the sudden situation on the time axis) of the last two sliding windows (hours) in the current hour as PDCP'=(PDCP[this hour]+PDCP[last hour]) / 2.

[0098] Step 3-2, calculate PDCP'_group[t] of this energy-saving cell group

[0099] PDCP'_group[t]=PDCP'_cell1[t]+PDCP'_cell2[t], assuming that the current period is PDCP'_group=1GB.

[0100] Step 4, perform online monitoring: obtain the KPI of the current period's cell and its first co-coverage cell through online monitoring of the deep energy saving cell, where: PDCP_group = 1 (deep energy saving cell) + 1.5 (first co-coverage cell) = 2.5GB.

[0101] Step 5, perform deviation analysis: The actual deviation of the energy-saving cell group data exceeds the range, and a deviation alarm is triggered when the service suddenly increases or decreases (network performance degrades), PDCP_group < PDCP'_group * (1 - L1), or PDCP_group > PDCP'_group * (1 + L2), where L1 is the assumed service reduction ratio of 50%, and L2 is the service ratio of sudden increase and change trend of 50%. Then substitute PDCP_group = 2.5GB and PDCP'_group = 1GB into the above conditions, and the predicted data of the actual data 2.5 / 1 > (1 + 50%) = 1.5 (GB) is obtained, that is, an output deviation alarm is generated.

[0102] Step 6, wake up: For the cells with deviation alarms, the wake-up module determines the turn-on instruction according to the turn-off instruction and immediately sends it to the network management system.

[0103] The technical solutions proposed in the above embodiments of the present disclosure have the following advantages over the related technologies: automatic decision-making, large adaptation range, good versatility, strong flexibility, timeliness, security, high efficiency, precision, and can be deployed and applied on a large scale.

[0104] The deep energy-saving wake-up in the above embodiments of the present disclosure is safer: Since the cell has been turned off during deep turn-off, self-wake-up has become a problem. The traditional method requires manual configuration or continuous observation of its main neighboring cells. The instruction configuration is complex and the device often cannot effectively enter the energy-saving state, and it needs to be manually woken up regularly, with low security and difficult to be applied on a large scale. However, through this method, the adaptation range is large, simple, and safe, solving a major obstacle to deep energy saving and meeting the needs of large-scale applications.

[0105] The AI prediction personalized wake-up in the above embodiments of the present disclosure: Compared with the one-size-fits-all method of the related technology, it can flexibly adapt to the service change patterns of different base station cells, one cell, one case, with both versatility and flexibility.

[0106] The above embodiments of the present disclosure are accurate in analysis and timely in wake-up: Analyze by each cell and each cycle, timely, accurate, and efficient.

[0107] The above embodiments of the present disclosure can achieve automatic decision-making: automatic wake-up, without manual intervention, low cost, and high efficiency.

[0108] Figure 3 It is a schematic diagram of some embodiments of the base station energy-saving wake-up device of the present disclosure. As Figure 3 shown, the base station energy-saving wake-up device of the present disclosure may include an index prediction module 31, an index monitoring module 32, a deviation analysis module 33, and a wake-up module 34, where:

[0109] The index prediction module 31 is configured to predict the key performance index data of the deep energy-saving cell and the co-covered cell.

[0110] In some embodiments of the present disclosure, the indicator prediction module 31 can be configured to use an artificial intelligence model to determine the predicted values ​​of key performance indicators within a first predetermined number of prediction periods in the future; calculate the moving average of the predicted values ​​of the most recent second predetermined number of sliding window periods, where the second predetermined number is less than the first predetermined number; calculate the predicted values ​​of the cumulative key performance indicators of the deep energy-saving cells and the co-coverage cells, and use the predicted values ​​of the cumulative key performance indicators as predicted key performance indicator data.

[0111] In some embodiments of the present disclosure, the artificial intelligence model may include but is not limited to one or more of the model algorithms such as a neural network, a lightweight gradient boosting machine, a random forest model, and a differential autoregressive moving average model.

[0112] The indicator monitoring module 32 is configured to monitor actual key performance indicator data of the deep energy-saving cells and the co-coverage cells.

[0113] The deviation analysis module 33 is configured to perform deviation analysis on the actual key performance indicator data and the predicted key performance indicator data.

[0114] In some embodiments of the present disclosure, the deviation analysis module 33 can be configured to determine the ratio of actual key performance indicator data to predicted key performance indicator data; determine whether the ratio is within a predetermined range; and if the ratio exceeds the predetermined range, determine that the deviation of the actual key performance indicator data exceeds the predetermined range.

[0115] In some embodiments of the present disclosure, the deviation analysis module 33 may also be configured to determine a tolerable reduction in the business volume ratio and a tolerable surge in the business volume ratio; and determine a predetermined range based on the tolerable reduction in the business volume ratio and the tolerable surge in the business volume ratio.

[0116] In some embodiments of the present disclosure, the deviation analysis module 33 may also be configured to determine the lower limit of the predetermined range according to the difference between 1 and the tolerable reduction in the business volume ratio; and determine the upper limit of the predetermined range according to the sum of 1 and the tolerable surge in the business volume ratio.

[0117] The wake-up module 34 is configured to send a wake-up instruction to the base station corresponding to the deep energy saving cell when the deviation of the actual key performance indicator data exceeds a predetermined range.

[0118] In some embodiments of the present disclosure, the base station energy-saving awakening device is configured to perform any of the above embodiments (for example Figure 1 or Figure 2 Operation of the base station energy-saving wake-up method described in Example).

[0119] Based on the base station energy-saving wake-up device provided by the above embodiments of the present disclosure, the base station energy-saving application is promoted to mature, the energy-saving effect is enhanced, and OPEX (Operating Expense, daily expenses such as enterprise management expenses, office expenses, employee salary expenses and advertising expenses) is reduced.

[0120] The above-mentioned embodiments of the present disclosure belong to the field of emerging information technology, and belong to the field of big data and AI technology.

[0121] The above-mentioned embodiments of the present disclosure are also applicable to intelligent predictive maintenance of network services.

[0122] The above-mentioned embodiments of the present disclosure can be used in the fields of 4G / 5G base station energy saving, network autonomous driving, automatic decision-making, etc.

[0123] Figure 4 Schematic diagram of the structure of some embodiments of the computer device disclosed in the present invention. Figure 4 As shown, the computer device includes a memory 41 and a processor 42 .

[0124] The memory 41 is used to store data and instructions. The processor 42 is coupled to the memory 41. The processor 42 is configured to execute the above-mentioned embodiments (for example, Figure 1 or Figure 2 Embodiment) relates to the method.

[0125] like Figure 4 As shown, the computer device also includes a communication interface 43 for information exchange with other devices. At the same time, the computer device also includes a bus 44, through which the processor 42, the communication interface 43, and the memory 41 communicate with each other.

[0126] The memory 41 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory. The memory 41 may also be a memory array. The memory 41 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

[0127] In addition, the processor 42 may be a central processing unit (CPU), or may be an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present disclosure.

[0128] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, any of the above embodiments (for example Figure 1 or Figure 2 The base station energy-saving wake-up method described in Example).

[0129] Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure 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 codes.

[0130] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and 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 produce 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.

[0131] 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.

[0132] 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 The steps for the functions specified in one or more boxes.

[0133] The base station energy-saving wake-up device described above can be implemented as a general-purpose processor, a programmable logic controller (PLC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component or any appropriate combination thereof for performing the functions described in this application.

[0134] So far, the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0135] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a non-transitory computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0136] The description of the present disclosure is given for the purpose of illustration and description, and is not intended to be exhaustive or to limit the present disclosure to the disclosed form. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present disclosure, and to enable those of ordinary skill in the art to understand the present disclosure and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. A base station energy-saving wake-up method, characterized in that: include: Predict key performance indicator data of deep energy-saving cells and shared coverage cells; Monitor the actual key performance indicator data of deep energy-saving cells and shared coverage cells; Conduct deviation analysis on actual key performance indicator data and predicted key performance indicator data; When the deviation of the actual key performance indicator data exceeds the predetermined range, a wake-up command is issued to the base station corresponding to the deep energy-saving cell; The predicted key performance indicator data of the predicted deep energy-saving cells and the co-coverage cells include: Determining predicted values ​​of key performance indicators for a first predetermined number of future forecast periods using an artificial intelligence model; Calculating a moving average of predicted values ​​of the key performance indicator of a second predetermined number of sliding window periods in the most recent period, wherein the second predetermined number is less than the first predetermined number; According to the moving average of the deep energy-saving cell and the moving average of the co-covered cell, the predicted values ​​of the accumulated key performance indicators of the deep energy-saving cell and the co-covered cell are calculated, and the predicted values ​​of the accumulated key performance indicators are used as predicted key performance indicator data.

2. The base station energy-saving wake-up method according to claim 1, characterized in that: The deviation analysis of the actual key performance indicator data and the predicted key performance indicator data includes: Determine the ratio of actual key performance indicator data to predicted key performance indicator data; determining whether the ratio is within a predetermined range; When the ratio exceeds the predetermined range, it is determined that the deviation of the actual key performance indicator data exceeds the predetermined range.

3. The base station energy-saving wake-up method according to claim 2, characterized in that: The deviation analysis of the actual key performance indicator data and the predicted key performance indicator data also includes: Determine the proportion of business volume that can be tolerated to decrease and the proportion of business volume that can be tolerated to increase suddenly; The predetermined range is determined according to the proportion of the business volume that can be tolerated to decrease and the proportion of the business volume that can be tolerated to increase suddenly.

4. The base station energy-saving wake-up method according to claim 3, characterized in that: The determining of the predetermined range according to the proportion of the business volume that can be reduced and the proportion of the business volume that can be increased may also include: Determine the lower limit of the predetermined range according to the difference between 1 and the tolerable reduction in the business volume ratio; The upper limit of the predetermined range is determined according to the sum of 1 and the proportion of the traffic volume that tolerates a sudden increase.

5. The base station energy-saving wake-up method according to any one of claims 1 to 4, characterized in that: The artificial intelligence model includes at least one of a neural network, a lightweight gradient boosting machine, a random forest model, and a differential autoregressive moving average model.

6. A base station energy-saving wake-up device, characterized in that: include: An indicator prediction module is configured to predict key performance indicator data of deep energy-saving cells and co-coverage cells; An indicator monitoring module is configured to monitor actual key performance indicator data of the deep energy-saving cell and the co-coverage cell; a deviation analysis module, configured to perform deviation analysis on actual key performance indicator data and predicted key performance indicator data; A wake-up module is configured to send a wake-up instruction to a base station corresponding to the deep energy-saving cell when the deviation of the actual key performance indicator data exceeds a predetermined range; The indicator prediction module is configured to use an artificial intelligence model to determine the predicted value of the key performance indicator within a first predetermined number of prediction periods in the future; Calculate the moving average of the predicted values ​​of the key performance indicators of the second most recent predetermined number of sliding window cycles, where the second predetermined number is less than the first predetermined number; calculate the predicted values ​​of the cumulative key performance indicators of the deep energy saving cells and the co-coverage cells based on the moving average of the deep energy saving cells and the moving average of the co-coverage cells, and use the predicted values ​​of the cumulative key performance indicators as predicted key performance indicator data.

7. The base station energy-saving wake-up device according to claim 6, characterized in that: The base station energy-saving awakening device is configured to execute operations to implement the base station energy-saving awakening method according to any one of claims 2 to 5.

8. A computer device, characterized in that: include: a memory configured to store instructions; The processor is configured to execute the instructions so that the computer device performs operations to implement the base station energy-saving wake-up method according to any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the base station energy-saving wake-up method according to any one of claims 1 to 5 is implemented.

Citation Information

Patent Citations

  • Base station power saving method and device thereof

    CN103369640A

  • Adaptive, anomaly detection based predictor for network time series data

    CN107409075A

  • LTE base station energy-saving method and device

    CN108616906A

  • Traffic prediction-based base station hibernation method in heterogeneous network

    WO2017000557A1