Dormant cell wake-up method, apparatus, device, and storage medium

Abstract

This invention provides a method, apparatus, device, and storage medium for waking up a dormant cell. The method includes: acquiring a first collected value of a target wake-up indicator for a set of compensation cells of the dormant cell; and determining to wake up the dormant cell when the first collected value reaches a threshold of the target wake-up indicator. The correlation coefficient between the target wake-up indicator and the total number of users in the set of compensation cells is greater than a correlation coefficient threshold. This invention uses network indicators strongly correlated with the total number of users in the set of compensation cells as wake-up indicators for dormant cells, monitors these network indicators of the compensation cells of the dormant cell, and wakes up the dormant cell when the wake-up indicator threshold is reached, ensuring flexible and timely wake-up of dormant cells even with a large number of users accessing the network.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method, apparatus, device, and storage medium for waking up a dormant cell. Background Technology

[0002] To save energy and reduce operating costs, operators use various energy-saving technologies. One of the most common is shutting down AAU devices or cells during off-peak hours, a technique known as carrier shutdown. In this scenario, if a large number of 5G users suddenly connect and the AAU fails to wake up in time, it can cause service congestion, affecting user internet experience and potentially leading to user complaints. Therefore, it is necessary to wake up dormant AAU devices promptly.

[0003] However, in the existing technology, the method used to wake up the dormant AAU device cannot keep up with changes in the existing network services in a timely manner, and it lacks flexibility. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for waking up a dormant cell, which solves the shortcomings of existing methods for waking up dormant AAU devices, such as the inability to track changes in current network services in a timely manner and the lack of flexibility, and enables timely and flexible waking up of dormant AAU devices.

[0005] In a first aspect, the present invention provides a method for waking up a dormant cell, comprising:

[0006] Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cells;

[0007] If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up;

[0008] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0009] Optionally, in one embodiment, the target wake-up indicator is one or more of the candidate wake-up indicators, and the candidate wake-up indicators of any one of the compensation cells in the set of compensation cells include the cell signaling data indicators and / or hardware load indicators of the compensation cell.

[0010] Optionally, in one embodiment, the cell signaling data indicators of the compensated cell include any one or more of the following:

[0011] The ECGI of the compensation cell;

[0012] The number of first-category users corresponding to the ECGI;

[0013] The number of users corresponding to the ECGI is the sum of the number of users in the first category and the number of users in the second category.

[0014] The traffic carried by the first type of user corresponding to the ECGI;

[0015] The traffic carried by the second type of user corresponding to the ECGI;

[0016] The dormant cell serves the first type of users, and the compensating cell users of the dormant cell serve the first type of users and / or the second type of users.

[0017] Optionally, in one embodiment, the first type of user is a 5G terminal user, and the second type of user is a non-5G terminal user.

[0018] Optionally, in one embodiment, the hardware load indicators of the compensation cell include any one or more of the following:

[0019] The baseband load data of the compensation cell;

[0020] The load data of the AAU equipment in the compensation cell.

[0021] Optionally, in one embodiment, the method further includes:

[0022] The target wake-up indicator is determined from the candidate wake-up indicators.

[0023] Optionally, in one embodiment, determining the target wake-up indicator from the candidate wake-up indicators includes:

[0024] Obtain the second collected value of the candidate wake-up index of the compensated cell;

[0025] Based on the second collected value, obtain the correlation coefficient between each of the candidate wake-up indicators and the total number of users;

[0026] Candidate wake-up indicators with correlation coefficients greater than the correlation coefficient threshold are identified as the target wake-up indicators.

[0027] Optionally, in one embodiment, obtaining the correlation coefficient between each of the candidate wake-up indicators and the total number of users based on the second collected value includes:

[0028] Using the Pearson correlation coefficient algorithm, based on the second collected value, the correlation coefficients between each of the candidate wake-up indicators and the total number of users are obtained;

[0029] The correlation coefficient between the candidate wake-up metric and the total number of users is the quotient of the covariance and standard deviation between the second collected value of the candidate wake-up metric and the total number of users.

[0030] Optionally, in one embodiment, when the target wake-up indicator includes the cell signaling data indicator of the compensation cell, obtaining the first collected value of the target wake-up indicator of the set of compensation cells of the dormant cells includes:

[0031] Based on the first cycle length, the first collected value of the cell signaling data index of the compensated cell is periodically obtained.

[0032] Optionally, in one embodiment, the length of the first cycle is 5 minutes.

[0033] Optionally, in one embodiment, when the target wake-up indicator includes the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI, obtaining the first collected value of the target wake-up indicator of the compensating cell set of the dormant cells includes:

[0034] Based on the terminal device information database, determine the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI;

[0035] The terminal device information database is used to identify any user as either a first-class user or a second-class user.

[0036] Optionally, in one embodiment, the method further includes:

[0037] Before determining the number of first-type users and / or the number of users corresponding to the ECGI based on the terminal device information database, the terminal device information database is established.

[0038] Optionally, in one embodiment, establishing the terminal device information database includes:

[0039] An initial terminal device information database is established, which includes information on an initial first type of user and information on an initial second type of user.

[0040] Based on the information of the first type of users and the information of the second type of users initialized, machine learning is performed on the initialized terminal device information database to obtain the terminal device information database after machine learning.

[0041] Optionally, in one embodiment, when the candidate wake-up indicators of the compensation cell include the hardware load indicators of the compensation cell, the first collected value of the target wake-up indicator of the set of compensation cells of the dormant cells includes:

[0042] The first collected value of the hardware load index of the compensation cell is obtained in real time.

[0043] Optionally, in one embodiment, determining to wake up a dormant cell when the first collected value of the target wake-up indicator reaches the threshold of the target wake-up indicator includes any one or more of the following:

[0044] If the first collected value of any one of the target wake-up indicators reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up; or

[0045] If the first collected value of any multiple targets among all wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened; or

[0046] Once the first collected value of all target wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened.

[0047] In a second aspect, the present invention provides a sleep cell wake-up device, comprising:

[0048] The acquisition module is used to acquire the first collected value of the target wake-up index of the compensation cell set of the dormant cell;

[0049] The determination module is used to determine the wake-up dormant cell when the first collected value reaches the threshold of the target wake-up indicator;

[0050] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0051] Thirdly, the present invention provides a network device, including a memory, a transceiver, and a processor;

[0052] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0053] Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cells;

[0054] If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up;

[0055] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0056] Fourthly, the present invention provides an electronic device, including a memory and a memory storing a computer program, wherein the processor executes the program to implement the steps of the hibernation cell wake-up method described in the first aspect.

[0057] Fifthly, the present invention provides a processor-readable storage medium storing a computer program for causing the processor to perform the steps of the hibernation cell wake-up method described in the first aspect.

[0058] The method, apparatus, device, and storage medium for waking up dormant cells provided by this invention use network indicators that are strongly correlated with the total number of users in the compensation cell set as wake-up indicators for dormant cells. These network indicators of the compensation cells of the dormant cell are monitored, and the dormant cell is woken up when the threshold of the wake-up indicator is reached, so as to ensure that the dormant cell can be woken up flexibly and timely when a large number of users access the network. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0060] Figure 1 This is a flowchart illustrating the hibernation cell wake-up method provided by the present invention;

[0061] Figure 2 This is one of the schematic diagrams for correlation judgment provided by the present invention;

[0062] Figure 3 This is the second schematic diagram of the correlation judgment provided by the present invention;

[0063] Figure 4 This is a schematic diagram of the hibernation cell wake-up method provided by the present invention;

[0064] Figure 5 This is a schematic diagram of the structure of the hibernation cell wake-up device provided by the present invention;

[0065] Figure 6 This is a schematic diagram of the structure of a network device according to an embodiment of the present invention;

[0066] Figure 7 A schematic diagram of the physical structure of an electronic device is provided. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0068] With the development of 5G technology, the power consumption of 5G base station equipment has increased significantly. Under the same coverage conditions, the energy consumption of a 5G base station is approximately 2.8 times that of a 4G base station. Among the base station equipment, the AAU (Active Audio Unit) accounts for approximately 90% of the total energy consumption of a 5G base station.

[0069] Therefore, various energy-saving technologies can be used to conserve energy. One of the most common methods is to shut down the AAU device or the cell during off-peak hours, a technique known as carrier shutdown. However, if a large number of 5G users suddenly connect and the AAU fails to wake up in time, it can cause service congestion, affecting the user's internet experience and even leading to user complaints. Therefore, how to wake up dormant AAU devices in a timely manner is a problem that urgently needs to be solved.

[0070] Existing base station predictive power-saving wake-up algorithms have the following drawbacks:

[0071] (1) The evaluation data volume is large and the time consumption is lengthy. If AI algorithms are used, long-term data needs to be collected from the existing network, including evaluation factors such as base station engineering parameters and indicators. The data has many dimensions, large scale, and high computational difficulty, and it is often impossible to track changes in the existing network services in a timely manner.

[0072] (2) Insufficient flexibility. Network congestion caused by sudden business interruptions often fails to wake up dormant AAU devices or cells in a timely manner by collecting indicators at a 15-minute granularity in dormant areas. This is because the generation, collection, and analysis of indicators take time, resulting in a wake-up delay of at least 15 minutes.

[0073] (3) Traditional prediction models have poor accuracy. Prediction algorithms are only highly accurate if the changes in cell services are regular. However, in reality, no prediction algorithm can accurately predict unpredictable service spikes. Cell services are dynamic and influenced by multiple factors; any sudden event, such as extreme weather or mass gatherings, can cause numerous unpredictable situations. Algorithm models can only extract patterns in cell service changes from historical data, and at most, can only determine the probability of sudden service spikes and set thresholds to decide whether to put the cell into a dormant state. Even the most intelligent algorithms cannot accurately predict the future and have certain limitations.

[0074] (4) High input costs. Whether it is big data analysis or AI algorithm training, massive amounts of data preprocessing and feeding are required to obtain the corresponding algorithm model. This type of algorithm has high requirements for hardware equipment and personnel, and the corresponding input costs also rise accordingly.

[0075] In order to overcome the shortcomings of existing technologies in waking up dormant AAU devices, such as the inability to track changes in current network services in a timely manner and the lack of flexibility, this invention provides a method, apparatus, device and storage medium for waking up dormant cells.

[0076] The following is combined Figures 1-7 The present invention describes a method, apparatus, device, and storage medium for waking up a dormant cell.

[0077] Figure 1 This is a flowchart illustrating the hibernation cell wake-up method provided by the present invention, as follows: Figure 1 As shown, the method includes the following steps 110 to 120:

[0078] Step 110: Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cell;

[0079] Step 120: If it is determined that the first collected value has reached the threshold of the target wake-up indicator, the dormant cell is determined to be woken up;

[0080] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0081] Specifically, after a 5G base station AAU device enters a dormant state, its associated 5G cell is also shut down, becoming a dormant cell. At this time, services can only be carried by the compensation cell. Therefore, based on data collection and real-time monitoring of the compensation cell, it is possible to accurately determine whether a dormant 5G cell needs to be woken up.

[0082] Optionally, the dormant cell can be a 5G cell;

[0083] Optionally, the compensation cell for a dormant cell may include any one or more of the following:

[0084] 2G cell; 3G cell; 4G cell; or 5G cell.

[0085] Optionally, the compensation cells for dormant cells may include 2G cells, 3G cells, 4G cells, and 5G cells.

[0086] Optionally, the compensating cells for a dormant cell may include 2G cells, 3G cells, 4G cells, and 5G cells.

[0087] Optionally, if the dormant cell is an NSA base station cell, the set of compensation cells may include the top three priority anchor station cells, shared AAU cells, and the set of the top five neighboring cells with the most successful handovers.

[0088] Optionally, if the dormant cell is an NSA base station cell, the compensation cell can be one of the top three priority anchor station cells, a shared AAU cell, or one of the top five neighbor cells with the most successful handovers.

[0089] Optionally, the top three priority anchor cells can be the top three priority cells among all possible anchor cells;

[0090] Optionally, the top five neighboring cells with the most successful handovers can be the top five cells with the most successful handovers among all cells that have successfully handed over from dormant cells.

[0091] Optionally, if the dormant cell is an SA base station cell, the compensation cell set may include the combined AAU cells and the set of neighboring cells with the top five successful handovers.

[0092] Optionally, if the dormant cell is an SA base station cell, the compensation cell can be a shared AAU cell or a neighboring cell with the top five successful handovers.

[0093] Optionally, if a target wake-up indicator that is strongly correlated with the total number of users in the compensation cell set has been determined, a first collection value of the target wake-up indicator of the compensation cell set of the dormant cell can be obtained, and data collection and real-time monitoring of the compensation cell can be performed using the first collection value; if it is determined that the first collection value has reached the threshold of the target wake-up indicator, the dormant cell can be woken up.

[0094] This invention obtains the first collected value of the target wake-up index of the compensating cell set of dormant cells, given a target wake-up index that is strongly correlated with the total number of users in the compensating cell set. It then monitors whether these first collected values ​​are higher than a threshold. If they are higher than the threshold, it can be determined that the service load of the compensating cell is large, and thus the number of users is large in the near future. Therefore, it is necessary to activate the dormant cell to ensure customer experience. Since this invention does not determine the need to activate the dormant cell based on a predictive algorithm, the accuracy of wake-up is guaranteed. By monitoring the network load of the compensating cell in real time, the timeliness and flexibility of wake-up are also guaranteed when the compensating cell is overloaded or reaches a certain load.

[0095] The dormant cell wake-up method provided by this invention uses network indicators that are strongly correlated with the total number of users in the compensation cell set as wake-up indicators for dormant cells. It monitors these network indicators of the compensation cells of the dormant cell and wakes up the dormant cell when the threshold of the wake-up indicator is reached, so as to ensure that the dormant cell can be woken up flexibly and timely when a large number of users access the network.

[0096] Optionally, the target wake-up indicator is one or more of the candidate wake-up indicators, and the candidate wake-up indicators of any one of the compensation cells in the set of compensation cells include the cell signaling data indicators and / or hardware load indicators of the compensation cell.

[0097] Specifically, among all network-related data in the compensation cell, not all data are necessarily strongly correlated with the total number of users in the compensation cell set. In other words, not all data can be used as a basis for determining whether to activate a dormant cell. Therefore, some network-related data in the compensation cell that are considered to reflect the number of users can be used as candidate wake-up indicators. Based on the correlation with the total number of users in the compensation cell set, the target wake-up indicator that is strongly correlated with the total number of users in the compensation cell set can be determined.

[0098] That is, the target wake-up metric is one or more of the candidate wake-up metrics.

[0099] Specifically, in order to ensure the real-time nature of the wake-up judgment for dormant cells, the cell signaling data indicators and / or hardware load indicators of the compensation cell can be used as candidate wake-up indicators; each type of data indicator corresponds to its own wake-up threshold.

[0100] That is, when considering network-related data that may reflect the number of users as candidate wake-up indicators, both cell signaling data indicators and hardware load indicators are taken into account; in this invention, by considering both cell signaling data and the hardware load of the dormant cell when determining whether to activate the dormant cell, the real-time nature of wake-up is guaranteed.

[0101] Optionally, due to factors such as network instability, the first collected values ​​of cell signaling data indicators and / or hardware load indicators may not be obtained normally. Therefore, this invention can provide a correction mechanism to promptly determine whether to wake up the dormant cell upon obtaining any of these data. That is, it can promptly wake up the dormant AAU board, i.e., promptly wake up the dormant cell, when any category of data in the cell signaling data indicators and / or hardware load indicators reflects a large load.

[0102] In this invention, even if one type of data is missing, the system can still wake up the dormant cell when the first collected value of another type of indicator reaches the wake-up threshold of that indicator, thus ensuring the real-time nature of the wake-up and the robustness of the wake-up device.

[0103] Optionally, the cell signaling data indicators of the compensated cell include any one or more of the following:

[0104] The ECGI of the compensation cell;

[0105] The number of first-category users corresponding to the ECGI;

[0106] The number of users corresponding to the ECGI is the sum of the number of users in the first category and the number of users in the second category.

[0107] The traffic carried by the first type of user corresponding to the ECGI;

[0108] The traffic carried by the second type of user corresponding to the ECGI;

[0109] The dormant cell serves the first type of users, and the compensating cell users of the dormant cell serve the first type of users and / or the second type of users.

[0110] Specifically, the signaling data indicators for the compensation community include any one or more of the following:

[0111] The ECGI of the compensation cell; or

[0112] The number of users of the first type corresponding to the ECGI; or

[0113] The number of users corresponding to the ECGI is the sum of the number of users in the first category and the number of users in the second category; or

[0114] The traffic carried by the first type of user corresponding to the ECGI; or

[0115] The traffic carried by the second type of user corresponding to the ECGI; or

[0116] The dormant cell serves the first type of users, and the compensating cell users of the dormant cell serve the first type of users and / or the second type of users.

[0117] Optionally, the first type of user can be a 5G terminal user;

[0118] Optionally, the second type of user can be a 2G terminal user, a 3G terminal user, or a 4G terminal user;

[0119] Optionally, the second type of user can be a 4G terminal user;

[0120] Optionally, the second type of user can be both 3G terminal users and 4G terminal users;

[0121] Optionally, the second type of user can be 2G terminal users and 4G terminal users;

[0122] Optionally, the second type of user can be 2G terminal users and 3G terminal users;

[0123] Optionally, the second type of user can be a non-5G terminal user.

[0124] Specifically, the signaling data indicators for the compensation community include any one or more of the following:

[0125] The ECGI of the compensation cell; or

[0126] The number of 5G terminal users corresponding to the ECGI; or

[0127] The total number of users corresponding to the ECGI, including both 5G and non-5G users; or

[0128] The 5G terminal user's traffic corresponding to the ECGI; or

[0129] The traffic carried by non-5G terminal users corresponding to the ECGI.

[0130] Optionally, the first collected value of the cell signaling data indicator of the compensation cell can be obtained periodically, such as once every 5 minutes or once every 6 minutes. This invention does not limit this.

[0131] Optionally, each cell signaling data indicator can correspond to its own wake-up threshold;

[0132] For example, if the target wake-up metric includes the number of 5G device users, and the threshold for the number of 5G device users can be 20, then it can be determined that the wake-up threshold of this target wake-up metric has been reached if the total number of 5G device users (i.e., the first collected value) of all compensation cells (i.e., the set of compensation cells) of the dormant cell is greater than or equal to 20. Among them, the total number of 5G device users of all compensation cells of the dormant cell can be the sum of the number of 5G device users corresponding to their respective ECGIs in each compensation cell.

[0133] If the target wake-up indicator includes other cell signaling data indicators, such as the traffic carried by 5G terminal users or the traffic carried by non-5G terminal users, the method for determining whether the cell signaling data indicator has reached the threshold can refer to the method for determining the number of 5G device users mentioned above, and will not be elaborated here.

[0134] Optionally, the first type of user is a 5G terminal user, and the second type of user is a non-5G terminal user.

[0135] Optionally, the hardware load indicators of the compensation cell include any one or more of the following:

[0136] The baseband load data of the compensation cell;

[0137] The load data of the AAU equipment in the compensation cell.

[0138] Specifically, the hardware load indicators of the compensation community include any one or more of the following:

[0139] The baseband load data of the compensation cell; or

[0140] The load data of the AAU equipment in the compensation cell.

[0141] Optionally, the AAU device load data can be the CPU and / or DSP load of the AAU device.

[0142] For example, if the target wake-up metric includes baseband board load data, and the threshold for baseband board load data can be 60%, then the wake-up threshold of this target wake-up metric can be determined to have been reached if the average proportion of the sum of the baseband board load data (i.e., the first collected value) of all compensated cells (i.e., the set of compensated cells) of the dormant cell to the total baseband board load data is greater than or equal to 60%.

[0143] For example, if the target wake-up metric includes AAU device load data, and the threshold for AAU device load data can be 60%, then the wake-up threshold of this target wake-up metric can be determined to have been reached if the average proportion of the sum of AAU device load data (i.e., the first collected value) of all compensated cells (i.e., the set of compensated cells) of the dormant cell to the total AAU devices is greater than or equal to 60%.

[0144] Optionally, the acquisition of hardware load indicators for the compensation cell is not limited by the minimum data collection granularity. Therefore, real-time board load status can be obtained by querying the command port without affecting network management.

[0145] That is, the first collected value of the hardware load index of the compensation community can be obtained in real time.

[0146] Therefore, it is possible to determine whether to wake up the dormant cell every minute, and the first collected value of the hardware load index of the compensation cell can be obtained in real time each time the dormant cell is woken up.

[0147] Optionally, it is possible to continuously determine whether to wake up a dormant cell, based on the first collected value of the most recently acquired cell signaling data indicator and / or the first collected value of the real-time acquired hardware load indicator.

[0148] Optionally, it can be determined every certain period of time, such as 1.5 minutes, whether to wake up the dormant cell. The determination can be based on the first collected value of the most recently acquired cell signaling data indicator and / or the first collected value of the hardware load indicator acquired in real time at the time of determination.

[0149] Optionally, the method further includes:

[0150] The target wake-up indicator is determined from the candidate wake-up indicators.

[0151] Specifically, among all network-related data in the compensation cell, not all data are necessarily strongly correlated with the total number of users in the compensation cell set. In other words, not all data can be used as a basis for determining whether to activate a dormant cell. Therefore, some network-related data in the compensation cell that are considered to reflect the number of users can be used as candidate wake-up indicators. Based on the correlation with the total number of users in the compensation cell set, the target wake-up indicator that is strongly correlated with the total number of users in the compensation cell set can be determined.

[0152] Therefore, before determining whether to wake up a dormant cell, the target wake-up indicator can be determined from the candidate wake-up indicators.

[0153] Optionally, after determining the target wake-up indicator from the candidate wake-up indicators, real-time judgment of long-term dormant cell wake-up can be continuously performed.

[0154] Optionally, as the base station hardware is adjusted, supplemented, or improved, or as the environment changes, the target wake-up index can be redefined and updated at regular intervals.

[0155] Optionally, determining the target wake-up indicator from the candidate wake-up indicators includes:

[0156] Obtain the second collected value of the candidate wake-up index of the compensated cell;

[0157] Based on the second collected value, obtain the correlation coefficient between each of the candidate wake-up indicators and the total number of users;

[0158] Candidate wake-up indicators with correlation coefficients greater than the correlation coefficient threshold are identified as the target wake-up indicators.

[0159] Optionally, in order to determine the target wake-up indicator with a strong correlation to the total number of users from the candidate wake-up indicators, the second collection value of the candidate wake-up indicators of the compensation cell can be obtained first. Based on the second collection value, the correlation coefficient between each candidate wake-up indicator and the total number of users can be obtained. That is, the correlation between multiple candidate wake-up indicators and the total number of users can be determined pairwise. For example, the correlation between 5G data carrying traffic and the total number of users can be determined, and the baseband board load data can be determined, and so on, until the correlation coefficient between all candidate wake-up indicators and the total number of users is determined. If the correlation is strong, the board wake-up algorithm model corresponding to the dormant cell can be configured using these indicators for wake-up judgment.

[0160] Therefore, candidate wake-up indicators with correlation coefficients greater than the correlation coefficient threshold are identified as the target wake-up indicators.

[0161] For example, correlation coefficients can be classified as follows:

[0162] 0.8-1.0 indicates a very strong correlation;

[0163] A value of 0.6-0.8 indicates a strong correlation;

[0164] 0.4-0.6 indicates a moderate degree of correlation;

[0165] 0.2-0.4 indicates a weak correlation;

[0166] 0.0-0.2 indicates a very weak correlation or no correlation;

[0167] Optionally, the correlation coefficient threshold can be set to 0.6;

[0168] Optionally, the correlation coefficient threshold can be preset or indicated by a higher level, and the present invention does not limit this.

[0169] Optionally, when obtaining the correlation coefficient between each of the candidate wake-up indicators and the total number of users, the Pearson correlation coefficient algorithm can be used to obtain the correlation between each of the candidate wake-up indicators and the total number of users.

[0170] Optionally, if no target wake-up indicator with a strong correlation to the total number of users is found among the candidate wake-up indicators, it indicates that the board corresponding to the dormant cell is not suitable for the energy-saving wake-up algorithm. A more flexible wake-up strategy should be adopted, such as timed wake-up or fixed threshold wake-up.

[0171] For example, the second collection data of a set of compensated cells for a dormant AAU is shown in Table 1 below:

[0172] Table 1. Second collection data of the compensated cell set of dormant AAUs

[0173] Community A 12 105 43 Community B 8 76 15 Community C 23 59 32 Community D 17 231 28

[0174] The Pearson correlation coefficient algorithm can be used. Let the number of 4 / 5G users X be a vector containing the data in the table above: X = (117, 84, 82, 248). Let Y be the board load: Y = (43, 15, 32, 28).

[0175] The cosine of the angle between these two centered vectors, i.e., the Pearson correlation coefficient r, is cosθ. Substituting this into the formula, we can see that for the dormant cell corresponding to this AAU, the number of 4 / 5G users (total number of users) and the board load r value (baseband board load data) are between 0.5 and 0.6. Figure 2 This is one of the schematic diagrams of correlation judgment provided by the present invention, such as... Figure 2 As shown, the correlation is generally low, but the fluctuations are large.

[0176] This indicates that the number of users in the dormant cell corresponding to this AAU is not sufficiently correlated with the board and is not a target for system adjustments. The algorithm model excludes candidate wake-up indicators with such low correlation.

[0177] Optionally, when there is a strong correlation between board load and the total number of users, the correlation coefficient between each of the candidate wake-up indicators and the total number of users can be obtained based on the second collected value using the Pearson correlation coefficient algorithm. For example, the correlation between data traffic and board load can be calculated, with specific data as follows:

[0178] Community A 43 42 Community B 15 9 Community C 32 35 Community D 28 25

[0179] Figure 3 This is the second schematic diagram of the correlation judgment provided by the present invention, as shown below. Figure 3 As shown, the correlation coefficient r is between 0.8 and 0.9, indicating a strong correlation; flexible wake-up algorithm thresholds can be set. For example, when the number of 5G users is greater than 20, the wake-up condition is met when the total number of users is greater than 100 or the board load is greater than 60%. A wake-up command is output in real time to activate the AAU device in sleep mode at the 5G base station.

[0180] Optionally, obtaining the correlation coefficient between each of the candidate wake-up indicators and the total number of users based on the second collected value includes:

[0181] Using the Pearson correlation coefficient algorithm, based on the second collected value, the correlation coefficients between each of the candidate wake-up indicators and the total number of users are obtained;

[0182] The correlation coefficient between the candidate wake-up metric and the total number of users is the quotient of the covariance and standard deviation between the second collected value of the candidate wake-up metric and the total number of users.

[0183] The Pearson correlation coefficient is widely used to measure the degree of correlation between two variables, and its value ranges between -1 and 1. The Pearson correlation coefficient between two variables is defined as the quotient of their covariance and standard deviation:

[0184]

[0185] The above formula defines the population correlation coefficient, commonly represented by the lowercase Greek letter ρ. By estimating the sample covariance and standard deviation, the Pearson correlation coefficient can be obtained, commonly represented by the lowercase English letter r.

[0186]

[0187] r can also be estimated from the mean of the standard scores of the (Xi, Yi) sample points, yielding an expression equivalent to the above formula:

[0188]

[0189] in and σ X These are the standard score, sample mean, and sample standard deviation for the Xi sample, respectively. r describes the strength of the linear correlation between the two variables. r ranges from -1 to +1. If r > 0, it indicates a positive correlation, meaning the larger the value of one variable, the larger the value of the other. If r < 0, it indicates a negative correlation, meaning the larger the value of one variable, the smaller the value of the other.

[0190] Geometrically, the Pearson correlation coefficient is the cosine of the angle between two n-dimensional vectors after data digitization.

[0191] In this invention, by real-time monitoring of changes in existing network services, collecting signaling data, and real-time CPU / DSP load of the board, and using the Pearson correlation coefficient algorithm for rapid analysis, it is possible to determine in almost real time whether the dormant 5G base station AAU board needs to be woken up to provide services, thus achieving the goal of not affecting the user's internet experience.

[0192] Optionally, when the target wake-up indicator includes the cell signaling data indicator of the compensation cell, the first collected value of the target wake-up indicator for the set of compensation cells of the dormant cells includes:

[0193] Based on the first cycle length, the first collected value of the cell signaling data index of the compensated cell is periodically obtained.

[0194] Optionally, the first collected value of the cell signaling data indicator of the compensation cell can be obtained periodically, such as once every 5 minutes or once every 6 minutes. This invention does not limit this.

[0195] Optionally, the second collected value of the cell signaling data indicator of the compensation cell can also be acquired periodically, such as once every 5 minutes or once every 6 minutes. This invention does not limit this.

[0196] Optionally, the length of the first cycle is 5 minutes.

[0197] Optionally, when the target wake-up indicator includes the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI, the first collected value of the target wake-up indicator for obtaining the set of compensated cells of the dormant cells includes:

[0198] Based on the terminal device information database, determine the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI;

[0199] The terminal device information database is used to identify any user as either a first-class user or a second-class user.

[0200] Optionally, the first type of user can be a 5G device user;

[0201] Optionally, the second type of user can be a non-5G device user;

[0202] Optionally, when determining the number of 5G device users or the total number of users in the compensation cell set of the dormant cell, the accessed devices can be identified first to determine whether they are 5G mobile phones.

[0203] Alternatively, identification can be performed using a terminal device information database;

[0204] Optionally, the terminal device information database can be used to identify any user as a 5G user or a non-5G user;

[0205] For example, information about one or more device users can be entered into the terminal device information database. The terminal device information database can determine whether each device user is a 5G user or a non-5G user, and thus obtain the number of 5G users and the number of non-5G users.

[0206] Optionally, the method further includes:

[0207] Before determining the number of first-type users and / or the number of users corresponding to the ECGI based on the terminal device information database, the terminal device information database is established.

[0208] Optionally, in order to identify whether a user is a 5G user or a non-5G user, the terminal device information database can be established before determining the number of first-type users and / or the number of users corresponding to the ECGI based on the terminal device information database.

[0209] Optionally, establishing the terminal device information database includes:

[0210] An initial terminal device information database is established, which includes information on an initial first type of user and information on an initial second type of user.

[0211] Based on the information of the first type of users and the information of the second type of users initialized, machine learning is performed on the initialized terminal device information database to obtain the terminal device information database after machine learning.

[0212] Optionally, when establishing the terminal device information database, an initial terminal device information database can be established first, which includes information on an initial first type of user and information on an initial second type of user. Then, machine learning can be performed on the initial terminal device information database based on the initial information on the first type of user and the initial information on the second type of user, and the learned model can be used as the terminal device information database.

[0213] Optionally, when the candidate wake-up indicators of the compensation cell include the hardware load indicators of the compensation cell, the first collected value of the target wake-up indicator of the set of compensation cells of the dormant cells includes:

[0214] The first collected value of the hardware load index of the compensation cell is obtained in real time.

[0215] Optionally, the acquisition of hardware load indicators for the compensation cell is not limited by the minimum data collection granularity. Therefore, without affecting network management, real-time board load status can be obtained by querying the command port. That is, the first collected value of the hardware load indicators for the compensation cell can be obtained in real time.

[0216] Optionally, the second collected value of the hardware load index of the compensation cell can also be obtained in real time.

[0217] Optionally, determining to wake up a dormant cell when the first collected value of the target wake-up indicator reaches the threshold of the target wake-up indicator includes any one or more of the following:

[0218] If the first collected value of any one of the target wake-up indicators reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up; or

[0219] If the first collected value of any multiple targets among all wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened; or

[0220] Once the first collected value of all target wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened.

[0221] Optionally, the sleep cell can be woken up if the first collected value of any one of the target wake-up indicators reaches the threshold of the target wake-up indicator.

[0222] For example, if the target wake-up criteria include the number of 5G users in the compensation cell set and the board load, then the dormant cell can be woken up only when the number of 5G users in the compensation cell set is greater than a threshold, such as 20. Alternatively, the dormant cell can be woken up when the number of 5G users in the compensation cell set is greater than the wake-up threshold, such as 20, and the board load is greater than the wake-up threshold, such as 60%.

[0223] Optionally, the wake-up of a dormant cell can be determined if the first collected value of any of the target wake-up indicators has reached its respective threshold.

[0224] For example, if the target wake-up indicators include the number of 5G users in the compensation cell set, the total number of users, and the board load, then the dormant cell can be woken up when the number of 5G users in the compensation cell set is greater than the wake-up threshold, for example, 20, the total number of users is greater than the threshold, for example, 100, and the board load is greater than the wake-up threshold, for example, 60%. Alternatively, the dormant cell can be woken up when the number of 5G users in the compensation cell set is greater than the wake-up threshold, for example, 20, and the total number of users is greater than the threshold, for example, 100.

[0225] Optionally, the sleep cell can be woken up if the first collected value of all target wake-up indicators has reached its respective threshold.

[0226] For example, if the target wake-up criteria include the number of 5G users in the compensation cell set, the total number of users, and the board load, then the dormant cell can be woken up only when the number of 5G users in the compensation cell set is greater than the wake-up threshold, for example, 20, the total number of users is greater than the threshold, for example, 100, and the board load is greater than the wake-up threshold, for example, 60%.

[0227] In one embodiment, Figure 4 This is a schematic diagram of the hibernation cell wake-up method provided by the present invention, as shown below. Figure 4 As shown, the target of the data collection can be a compensating cell for a dormant 5G cell;

[0228] This includes the ability to collect the first-level hardware load indicators of the compensation cell in real time, such as the baseband board and AAU device CPU / DSP load bound to the compensation cell. This data acquisition is not limited by the minimum data collection granularity. Real-time board load information can be obtained by querying the command port without affecting network management.

[0229] Specifically, the system can periodically collect and save the first collected values ​​of cell signaling data indicators for compensating cells in dormant 5G cells every 5 minutes (the minimum collection granularity). Cell signaling data indicators mainly include the cell's ECGI (Electronic Control Group Identity), and its corresponding number of 4 / 5G terminal devices, traffic volume, etc.

[0230] Optionally, it is possible to continuously determine whether to wake up a dormant cell, based on the first collected value of the most recently acquired cell signaling data indicator and / or the first collected value of the real-time acquired hardware load indicator.

[0231] Optionally, it can be determined every certain period of time, such as 1.5 minutes, whether to wake up the dormant cell. The determination can be based on the first collected value of the most recently acquired cell signaling data indicator and / or the first collected value of the hardware load indicator acquired in real time at the time of determination.

[0232] The method, apparatus, device, and storage medium for waking up dormant cells provided by this invention use network indicators that are strongly correlated with the total number of users in the compensation cell set as wake-up indicators for dormant cells. These network indicators of the compensation cells of the dormant cell are monitored, and the dormant cell is woken up when the threshold of the wake-up indicator is reached, so as to ensure that the dormant cell can be woken up flexibly and timely when a large number of users access the network.

[0233] The dormant cell wake-up device provided by the present invention is described below. The dormant cell wake-up device described below can be referred to in correspondence with the dormant cell wake-up method described above.

[0234] Figure 5 This is a schematic diagram of the structure of the hibernation cell wake-up device provided by the present invention, as shown below. Figure 5 As shown, the device includes: an acquisition module 510 and a determination module 520; wherein:

[0235] The acquisition module 510 is used to acquire the first collected value of the target wake-up index of the compensation cell set of the dormant cell;

[0236] The determination module 520 is used to determine the wake-up dormant cell when it is determined that the first collected value has reached the threshold of the target wake-up index;

[0237] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0238] The dormant cell wake-up device can acquire the first collected value of the target wake-up index of the compensation cell set of the dormant cell through the acquisition module 510, and then determine the dormant cell to be woken up through the determination module 520 when it is determined that the first collected value has reached the threshold of the target wake-up index.

[0239] The dormant cell wake-up device provided by the present invention uses network indicators that are strongly correlated with the total number of users in the compensation cell set as wake-up indicators for dormant cells, monitors these network indicators of the compensation cells of the dormant cell, and wakes up the dormant cell when the threshold of the wake-up indicator is reached, so as to ensure that the dormant cell can be woken up flexibly and timely when a large number of users access the network.

[0240] The terminal device involved in the embodiments of the present invention may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem, etc. The name of the terminal device may differ in different systems; for example, in a 5G system, the terminal device may be called User Equipment (UE).

[0241] The network device involved in the embodiments of the present invention can be a base station, which may include multiple cells providing services to terminals. Depending on the specific application, a base station may also be called an access point, or a device in an access network that communicates with wireless terminal devices through one or more sectors on the air interface, or other names.

[0242] Figure 6 This is a schematic diagram of the structure of a network device according to an embodiment of the present invention, such as... Figure 6 As shown, this embodiment of the invention also provides a network device, which may include: a memory 610, a transceiver 620, and a processor 630;

[0243] The memory 610 is used to store computer programs; the transceiver 620 is used to send and receive data under the control of the processor 630; the processor 630 is used to read the computer program in the memory 610 and perform the following operations:

[0244] Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cells;

[0245] If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up;

[0246] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0247] The network device provided by this invention uses network indicators that are strongly correlated with the total number of users in the compensation cell set as wake-up indicators for dormant cells. It monitors these network indicators of the compensation cells of the dormant cells and wakes up the dormant cells when the threshold of the wake-up indicator is reached, thus ensuring that the dormant cells can be woken up flexibly and in a timely manner when a large number of users are accessing the network.

[0248] Among them, Figure 6 In this context, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 630) and memory (memory 610). The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface. Transceiver 620 may be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium. Processor 630 is responsible for managing the bus architecture and general processing, and memory 610 may store data used by processor 630 during operation.

[0249] Optionally, the target wake-up indicator is one or more of the candidate wake-up indicators, and the candidate wake-up indicators of any one of the compensation cells in the set of compensation cells include the cell signaling data indicators and / or hardware load indicators of the compensation cell.

[0250] Optionally, the cell signaling data indicators of the compensated cell include any one or more of the following:

[0251] The ECGI of the compensation cell;

[0252] The number of first-category users corresponding to the ECGI;

[0253] The number of users corresponding to the ECGI is the sum of the number of users in the first category and the number of users in the second category.

[0254] The traffic carried by the first type of user corresponding to the ECGI;

[0255] The traffic carried by the second type of user corresponding to the ECGI;

[0256] The dormant cell serves the first type of users, and the compensating cell users of the dormant cell serve the first type of users and / or the second type of users.

[0257] Optionally, the first type of user is a 5G terminal user, and the second type of user is a non-5G terminal user.

[0258] Optionally, the hardware load indicators of the compensation cell include any one or more of the following:

[0259] The baseband load data of the compensation cell;

[0260] The load data of the AAU equipment in the compensation cell.

[0261] Optionally, the processor 630 is also used to perform the following operations:

[0262] The target wake-up indicator is determined from the candidate wake-up indicators.

[0263] Optionally, the processor 630 is also used to perform the following operations:

[0264] Obtain the second collected value of the candidate wake-up index of the compensated cell;

[0265] Based on the second collected value, obtain the correlation coefficient between each of the candidate wake-up indicators and the total number of users;

[0266] Candidate wake-up indicators with correlation coefficients greater than the correlation coefficient threshold are identified as the target wake-up indicators.

[0267] Optionally, the processor 630 is also used to perform the following operations:

[0268] Using the Pearson correlation coefficient algorithm, based on the second collected value, the correlation coefficients between each of the candidate wake-up indicators and the total number of users are obtained;

[0269] The correlation coefficient between the candidate wake-up metric and the total number of users is the quotient of the covariance and standard deviation between the second collected value of the candidate wake-up metric and the total number of users.

[0270] Optionally, if the target wake-up indicator includes the cell signaling data indicator of the compensation cell, the processor 630 is further configured to perform the following operations:

[0271] Based on the first cycle length, the first collected value of the cell signaling data index of the compensated cell is periodically obtained.

[0272] Optionally, the length of the first cycle is 5 minutes.

[0273] Optionally, if the target wake-up metric includes the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI, the processor 630 is further configured to perform the following operations:

[0274] Based on the terminal device information database, determine the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI;

[0275] The terminal device information database is used to identify any user as either a first-class user or a second-class user.

[0276] Optionally, the processor 630 is also used to perform the following operations:

[0277] Before determining the number of first-type users and / or the number of users corresponding to the ECGI based on the terminal device information database, the terminal device information database is established.

[0278] Optionally, the processor 630 is also used to perform the following operations:

[0279] An initial terminal device information database is established, which includes information on an initial first type of user and information on an initial second type of user.

[0280] Based on the information of the first type of users and the information of the second type of users initialized, machine learning is performed on the initialized terminal device information database to obtain the terminal device information database after machine learning.

[0281] Optionally, if the candidate wake-up indicators of the compensation cell include the hardware load indicators of the compensation cell, the processor 630 is further configured to perform the following operations:

[0282] The first collected value of the hardware load index of the compensation cell is obtained in real time.

[0283] Optionally, if the processor 630 determines that the first collected value of the target wake-up indicator has reached the threshold of the target wake-up indicator, it is further configured to perform the following operations:

[0284] If the first collected value of any one of the target wake-up indicators reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up; or

[0285] If the first collected value of any multiple targets among all wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened; or

[0286] Once the first collected value of all target wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened.

[0287] The network device provided by this invention uses network indicators that are strongly correlated with the total number of users in the compensation cell set as wake-up indicators for dormant cells. It monitors these network indicators of the compensation cells of the dormant cells and wakes up the dormant cells when the threshold of the wake-up indicator is reached, thus ensuring that the dormant cells can be woken up flexibly and in a timely manner when a large number of users are accessing the network.

[0288] It should be noted that the network device provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiments and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiments will not be described in detail here.

[0289] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 can call a computer program in the memory 730 to execute the steps of a hibernation cell wake-up method, such as including:

[0290] Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cells;

[0291] If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up;

[0292] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0293] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0294] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the hibernation cell wake-up method provided by the above methods, the method comprising:

[0295] Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cells;

[0296] If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up;

[0297] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0298] On the other hand, embodiments of the present invention also provide a processor-readable storage medium storing a computer program for causing the processor to execute the methods provided in the above embodiments, such as including:

[0299] Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cells;

[0300] If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up;

[0301] The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

[0302] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0303] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0304] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0305] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dormant cell wake-up method, the method comprising: include: Obtain the first collected value of the target wake-up index of the compensation cell set of the dormant cells; If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up; Wherein, the correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold; The method further includes: Obtain the second collected value of the candidate wake-up index of the compensated cell; Based on the second collected value, obtain the correlation coefficient between each of the candidate wake-up indicators and the total number of users; Candidate wake-up indicators with correlation coefficients greater than the correlation coefficient threshold are identified as the target wake-up indicators.

2. The method for waking up a dormant cell according to claim 1, characterized in that, The target wake-up indicator is one or more of the candidate wake-up indicators. The candidate wake-up indicators for any one of the compensation cells in the set of compensation cells include the cell signaling data indicators and / or hardware load indicators of the compensation cell.

3. The method for waking up a dormant cell according to claim 2, characterized in that, The cell signaling data indicators of the compensation cell include any one or more of the following: The ECGI of the compensation cell; The number of first-category users corresponding to the ECGI; The number of users corresponding to the ECGI is the sum of the number of users in the first category and the number of users in the second category. The traffic carried by the first type of user corresponding to the ECGI; The traffic carried by the second type of user corresponding to the ECGI; The dormant cell serves the first type of users, and the compensating cell users of the dormant cell serve the first type of users and / or the second type of users.

4. The method for waking up a dormant cell according to claim 3, characterized in that, The first category of users are 5G terminal users, and the second category of users are non-5G terminal users.

5. The method for waking up a dormant cell according to claim 2, characterized in that, The hardware load indicators of the compensation cell include any one or more of the following: The baseband load data of the compensation cell; The load data of the AAU equipment in the compensation cell.

6. The method for waking up a dormant cell according to claim 1, characterized in that, The step of obtaining the correlation coefficient between each of the candidate wake-up indicators and the total number of users based on the second collected value includes: Using the Pearson correlation coefficient algorithm, based on the second collected value, the correlation coefficients between each of the candidate wake-up indicators and the total number of users are obtained; The correlation coefficient between the candidate wake-up metric and the total number of users is the quotient of the covariance and standard deviation between the second collected value of the candidate wake-up metric and the total number of users.

7. The method for waking up a dormant cell according to claim 3 or 4, characterized in that, When the target wake-up indicator includes the cell signaling data indicator of the compensation cell, the first collected value of the target wake-up indicator of the set of compensation cells of the dormant cells includes: Based on the first cycle length, the first collected value of the cell signaling data index of the compensated cell is periodically obtained.

8. The method for waking up a dormant cell according to claim 7, characterized in that, The first cycle lasts for 5 minutes.

9. The method for waking up a dormant cell according to claim 7, characterized in that, When the target wake-up indicator includes the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI, the first collected value of the target wake-up indicator for the set of compensated cells of the dormant cells includes: Based on the terminal device information database, determine the number of first-type users corresponding to the ECGI and / or the number of users corresponding to the ECGI; The terminal device information database is used to identify any user as either a first-class user or a second-class user.

10. The method for waking up a dormant cell according to claim 9, characterized in that, The method further includes: Before determining the number of first-type users and / or the number of users corresponding to the ECGI based on the terminal device information database, the terminal device information database is established.

11. The method for waking up a dormant cell according to claim 10, characterized in that, The establishment of the terminal device information database includes: An initial terminal device information database is established, which includes information on an initial first type of user and information on an initial second type of user. Based on the information of the first type of users and the information of the second type of users initialized, machine learning is performed on the initialized terminal device information database to obtain the terminal device information database after machine learning.

12. The method for waking up a dormant cell according to claim 2, 3, or 4, characterized in that, When the candidate wake-up indicators of the compensated cell include the hardware load indicators of the compensated cell, the first collected value of the target wake-up indicator of the compensated cell set of the dormant cells includes: The first collected value of the hardware load index of the compensation cell is obtained in real time.

13. The method for waking up a dormant cell according to any one of claims 1 to 6 or any one of claims 8 to 11, characterized in that, The step of determining to wake up a dormant cell when the first collected value of the target wake-up indicator reaches the threshold of the target wake-up indicator includes any one or more of the following: If the first collected value of any one of the target wake-up indicators reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up; or If the first collected value of any multiple targets among all wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened; or Once the first collected value of all target wake-up indicators has reached its respective threshold, the dormant cell is determined to be awakened.

14. A dormant cell wake-up device, characterized in that, Using the dormant cell wake-up method according to any one of claims 1 to 13, the dormant cell wake-up device comprises: The acquisition module is used to acquire the first collected value of the target wake-up index of the compensation cell set of the dormant cell; The determination module is used to determine the wake-up dormant cell when the first collected value reaches the threshold of the target wake-up indicator; The correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold.

15. A network device, characterized in that, Includes memory, transceiver, and processor; A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: Obtain the first collected value of the target wake-up index for the set of compensated cells in dormant cells; If the first collected value reaches the threshold of the target wake-up indicator, the dormant cell is determined to be woken up; Wherein, the correlation coefficient between the target wake-up metric and the total number of users in the compensation cell set is greater than the correlation coefficient threshold; The processor is also used to perform the following operations: Obtain the second collected value of the candidate wake-up index of the compensated cell; Based on the second collected value, obtain the correlation coefficient between each of the candidate wake-up indicators and the total number of users; Candidate wake-up indicators with correlation coefficients greater than the correlation coefficient threshold are identified as the target wake-up indicators.

16. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the hibernation cell wake-up method according to any one of claims 1 to 13.

17. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program for causing the processor to perform the steps of the sleep cell wake-up method according to any one of claims 1 to 13.

Images