WO2021203810A1 - 识别问题小区的方法、电子设备、计算机可读介质 - Google Patents

识别问题小区的方法、电子设备、计算机可读介质 Download PDF

Info

Publication number
WO2021203810A1
WO2021203810A1 PCT/CN2021/074431 CN2021074431W WO2021203810A1 WO 2021203810 A1 WO2021203810 A1 WO 2021203810A1 CN 2021074431 W CN2021074431 W CN 2021074431W WO 2021203810 A1 WO2021203810 A1 WO 2021203810A1
Authority
WO
WIPO (PCT)
Prior art keywords
cell
performance index
cells
subnet
abnormal
Prior art date
Application number
PCT/CN2021/074431
Other languages
English (en)
French (fr)
Inventor
陈力
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to JP2022560979A priority Critical patent/JP7474864B2/ja
Priority to US17/995,884 priority patent/US20230130378A1/en
Priority to EP21783685.7A priority patent/EP4132074A4/en
Publication of WO2021203810A1 publication Critical patent/WO2021203810A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/0268—Traffic management, e.g. flow control or congestion control using specific QoS parameters for wireless networks, e.g. QoS class identifier [QCI] or guaranteed bit rate [GBR]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/16—Threshold monitoring
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/04—Arrangements for maintaining operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/06—Reselecting a communication resource in the serving access point

Definitions

  • the embodiments of the present disclosure relate to the technical field of mobile communication networks, and in particular to methods, electronic devices, and computer-readable media for identifying problem cells.
  • a mobile communication network such as mobile broadband network MBB
  • KPI Key Performance Indicator
  • the embodiments of the present disclosure provide a method, electronic equipment, and computer-readable medium for identifying problem cells.
  • an embodiment of the present disclosure provides a method for identifying problematic cells, which includes: determining the abnormal contribution degree of each cell of the subnet; and determining at least one cell as the problem cell according to the abnormal contribution degree of each cell of the subnet; wherein, The abnormal contribution degree of each cell is the degree of correlation between the performance index of the cell and the abnormality when the performance index of the subnet is abnormal; if the performance index of the subnet is abnormal, it means that the performance index of the subnet exceeds the first threshold. Range; the performance index of the subnet is determined according to the parameter statistics of each cell; the performance index of the cell is determined according to the parameter statistics.
  • embodiments of the present disclosure provide an electronic device, which includes: one or more processors; a memory, on which one or more programs are stored, when the one or more programs are Is executed by two processors, so that the one or more processors implement any one of the above-mentioned methods for identifying problem cells; one or more I/O interfaces are connected between the processor and the memory, and are configured to implement the Information interaction between the processor and the memory.
  • embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, any one of the above-mentioned methods for identifying problem cells is realized.
  • FIG. 1 is a schematic block diagram of the composition of a mobile communication network to which an embodiment of the disclosure is applicable;
  • FIG. 2 is a schematic diagram of the real-time value of the uplink rate performance index and the first threshold value range in an embodiment of the disclosure
  • FIG. 3 is a flowchart of a method for identifying problem cells provided by an embodiment of the disclosure
  • FIG. 5 is a flowchart of some steps in another method for identifying problem cells provided by an embodiment of the present disclosure
  • FIG. 6 is a flowchart of some steps in another method for identifying problem cells provided by an embodiment of the disclosure.
  • FIG. 7 is a logical process diagram of another method for identifying problem cells provided by an embodiment of the present disclosure.
  • FIG. 8 is a block diagram of an electronic device provided by an embodiment of the disclosure.
  • FIG. 9 is a block diagram of the composition of a computer-readable medium provided by an embodiment of the disclosure.
  • a mobile communication network refers to a network that realizes communication between mobile users and fixed users, or between mobile users.
  • the mobile communication network may specifically be a global mobile communication network (GSM), a universal mobile communication network (UMTS), a long-term evolution technology network (LTE), a code division multiple access network (CDMA), a new air interface network (NR), etc.
  • GSM global mobile communication network
  • UMTS universal mobile communication network
  • LTE long-term evolution technology network
  • CDMA code division multiple access network
  • NR new air interface network
  • a cell which refers to the smallest area that can be independently controlled in a mobile communication network.
  • a cell may be an area covered by a base station, or an area covered by an antenna in the base station.
  • a subnet refers to an area integrated with multiple cells for unified management, and it may include multiple cells corresponding to one network element device.
  • Performance indicators refer to parameters that are derived based on parameter statistics in the mobile communication network and can represent the performance of the mobile communication network.
  • performance indicators may include call-through rate, call drop rate, congestion rate, handover success, traffic, speed, and so on.
  • the parameter statistics refer to the direct statistical values of the parameters generated during the operation of the mobile communication network, but do not include further numerical values (such as ratio-based performance indicators) calculated based on the direct statistical values.
  • the parameter statistics may include traffic, rate, number of connections, number of attempts to connect, number of dropped calls, number of calls, number of congestion, number of data transmissions, number of successful handovers, number of attempts to handover, and so on.
  • the embodiments of the present disclosure are used in a mobile communication network environment.
  • the mobile communication network to which the embodiment of the present disclosure is applicable may include: wireless network equipment, core network equipment, network equipment network management server, network performance monitoring server, etc.
  • the network performance monitoring server may periodically obtain the performance index related data of the subnet and the cell from the network equipment network management server, so as to implement the embodiments of the present disclosure.
  • the main management area is a subnet, and each subnet is divided into multiple cells. Therefore, the performance indicators (KPI) such as the connection rate, the call drop rate, the congestion rate, the handover success rate, the flow rate, and the speed in each subnet are actually a combination of the performance indicators of all the cells.
  • KPI performance indicators
  • the abnormality of the subnet is usually caused by problems in one or more of the cells. These cells are called problem cells, or cells with poor topN, and are usually cells with relatively poor performance indicators.
  • the problem cell is directly determined based on the ranking of performance indicators. For example, a cell with a higher drop rate can be directly used as a problem cell.
  • the performance indicators of the cells with lower traffic fluctuate widely. Therefore, the pure performance indicators often cannot reflect the true performance of the cell. Performance indicators may not necessarily be able to analyze the actual cells that cause the subnet to be abnormal.
  • performance indicators and artificially set absolute times are used as conditions for screening problem cells.
  • the staff such as on-site network optimization engineers or customers
  • the threshold according to the geographic environment of the community and the frequently complained problems, that is, the number of calls must be greater than the corresponding threshold, and The cell whose call drop rate is greater than the corresponding threshold is the problem cell.
  • this method is subject to human subjective judgment, has a lot of human factors, cannot guarantee accuracy, and is time-consuming and difficult to generalize.
  • an embodiment of the present disclosure provides a method for identifying a problem cell, which includes:
  • the abnormal contribution degree of each cell is the degree of correlation between the performance index of the cell and the abnormality when the performance index of the subnet is abnormal; when the performance index of the subnet is abnormal, the performance index of the subnet exceeds the first threshold range;
  • the performance index of the subnet is determined according to the parameter statistics of each cell; the performance index of the cell is determined according to the parameter statistics.
  • the abnormal contribution of each cell can be determined according to the performance index of the subnet at this time and the performance index of each cell in it.
  • Degree that is, the degree of correlation between the performance index of each cell and the abnormality in the subnet, or the possibility of the abnormality caused by the cells of the subnet.
  • the first threshold range is also different, that is, each performance indicator should have its own corresponding first threshold range.
  • S102 Determine at least one cell as a problem cell according to the abnormal contribution degree of each cell of the subnet.
  • the problem cell can be determined, that is, the cell that actually caused the abnormality can be determined.
  • the method of the embodiment of the present disclosure is calculated for the situation when the subnet is abnormal, so it can be calculated in real time when the subnet is abnormal, but it does not mean that the method of the embodiment of the present disclosure must be performed in real time.
  • the relevant data when the subnet is abnormal can also be saved, and then processed in a unified manner according to the embodiment of the present disclosure.
  • the abnormal contribution of each cell of the subnet is determined according to the performance indicators of the subnet and the cell (or the parameter statistics of all cells) when the abnormality occurs, that is, the abnormal contribution of each cell of the subnet is determined. possibility. Therefore, compared with the related technology that determines the abnormal contribution degree solely based on the performance index of each cell of the subnet, the method of the embodiment of the present disclosure can more accurately determine the problem cell (that is, the cell that actually causes the abnormality) based on the abnormal contribution degree. In order to follow-up targeted network optimization and improve user experience.
  • embodiments of the present disclosure can be implemented completely in an automated manner, without manual intervention, and are not affected by human factors, and are fast, intelligent, and accurate.
  • the first threshold range includes: a lower limit of the first threshold range, and/or an upper limit of the first threshold range.
  • the first threshold range for judging whether the subnet is abnormal may include an upper limit and a lower limit, that is, if the performance index is too large or too small, it may be abnormal. For example, when the rate is too high or too small, it may mean abnormality.
  • the first threshold value range may also include only one of the upper limit value and the lower limit value, that is, the performance index may only be abnormal due to one of the excessively large or the excessively small. For example, when the drop rate is greater than a certain value, it is obviously abnormal, but even if the drop rate is the minimum value of 0, it should not be regarded as abnormal.
  • the first threshold range is determined by dynamic threshold detection technology.
  • the above first threshold range may be a real-time value calculated according to a dynamic threshold detection technology (such as an automatic learning Holtwinters algorithm).
  • the dark line is the real-time value of the uplink rate performance index
  • the light-colored areas on the upper and lower sides are the value range of the first threshold range at each time. It can be seen that the first threshold range is based on time. Changes in real time.
  • the process of determining the normal range (the first threshold range) of the performance index by using the dynamic threshold detection technology can be implemented according to some related technologies, and will not be described in detail here.
  • the following describes a specific method for determining the problem cell when the ratio-based performance index is abnormal.
  • the ratio-based performance index refers to the ratio formed by two different parameter statistics, such as a percentage, that is, the ratio-based performance index is the ratio of the first parameter statistics to the second parameter statistics.
  • ratio-based performance indicators may include the call-through rate, call-drop rate, congestion rate, handover success rate, etc.; correspondingly, the first parameter statistics corresponding to the call-through rate, call drop rate, congestion rate, and handover success rate are respectively It is the number of connected times, the number of dropped calls, the number of congestion, the number of successful handovers, etc.; and the second parameter statistics are the number of attempts to connect, the number of calls, the number of data transmissions, the number of attempts to switch, and so on.
  • the performance index (ratio-type performance index) of the i-th cell can be calculated by the following formula:
  • the performance index of the i-th cell the first parameter statistics of the i-th cell/the second parameter statistics of the i-th cell.
  • the performance index (ratio-type performance index) of each subnet is equal to the ratio of the first parameter statistics to the second parameter statistics of all the cells, that is,
  • n is the total number of cells in the subnet.
  • the performance indicators of the subnets are not the sum of the performance indicators of the individual cells.
  • the abnormal contribution of each cell indicates that after the cell is removed from the subnet, the performance indicators of the subnet deviate from the performance indicators of the subnet before the removal within the first threshold range. Degree.
  • Contrast ratio performance index the abnormal contribution degree of each cell expresses:
  • the remaining cells in the subnet can obtain a new subnet performance index, and the performance index of the new subnet is within the first threshold range relative to the original performance index of the subnet before the removal
  • the degree of deviation is the abnormal contribution of the cell.
  • the degree of shift to the first threshold range means that if the new performance index after removal is closer to the first threshold range than the original performance index before removal, the degree of shift is positive (that is, to the first threshold). Offset within a threshold range); conversely, if the new performance index after removal is farther from the first threshold range than the original performance index before removal, the degree of offset is negative (ie, shifts away from the first threshold range ).
  • the current performance index of the subnet must exceed the first threshold range. Therefore, when the new performance index after the above removal is closer to the first threshold range than the original performance index before removal, it indicates that the degree of deviation of the new performance index after removal from the original performance index within the first threshold range is " Positive value”; that is, after removing a cell, the performance index becomes closer to the first threshold range or even enters the first threshold range (that is, biased toward normal), so the function of the "removed" cell should be to keep the performance index away The first threshold range. Therefore, the abnormal contribution degree of the cell at this time is "positive contribution", or in other words, the role of the cell is to make the subnet abnormal.
  • the new performance index after the above removal is farther from the first threshold range than the original performance index before removal, it indicates that the degree of deviation of the new performance index after removal from the original performance index within the first threshold range is "Negative value"; that is, after removing a certain cell, the performance index becomes farther away from the first threshold range (ie, biased abnormally), so the function of the "removed" cell should be to bring the performance index closer to the first threshold range. Therefore, the abnormal contribution degree of the cell at this time is "negative contribution", in other words, the role of the cell is to avoid abnormalities in the subnet.
  • the new performance index after the above removal may also be equal to the original performance index.
  • the abnormal contribution degree of the cell is 0, that is, the cell has no influence on the abnormality generated by the subnet.
  • the abnormal contribution degree of the j-th cell can be calculated by the following formula:
  • n is the total number of cells in the subnet
  • D is the abnormal direction, which is defined as:
  • the performance index can of course only exceed the first threshold range from one direction, so the abnormal direction can be a fixed value.
  • the absolute value of the abnormal direction is not necessarily 1, as long as it has two positive and negative values with the same absolute value.
  • the abnormal contribution of the cell is not calculated only based on the performance indicators and parameter statistics (such as times) of the cell, but based on the first parameter statistics and the first parameter statistics of the cell itself.
  • the two-parameter statistics, as well as the first parameter statistics and the second parameter statistics of other cells in the subnet, are calculated; thus, the abnormal contribution degree can be compared to reflect the true correlation degree of the abnormality of the cell and the subnet according to the abnormal contribution
  • the problem cell determined by the degree is also more accurate, which can achieve better network optimization and improve user experience.
  • the step S102 of determining at least one cell as a problem cell according to the abnormal contribution degree of each cell of the subnet includes:
  • the optimized performance index is the difference between the performance index of the subnet and the temporary performance index of the subnet.
  • the temporary performance index is the overall remaining cells in the subnet after removing the top N cells in the sequence to be screened Performance indicators.
  • the optimized performance index is within the first threshold range, determine that the top N cells in the sequence to be screened are candidate cells; if the optimized performance index exceeds the first threshold range, increase N by 1 and return to the step of determining the optimized performance index .
  • the above abnormal contribution is a relative value. Although it can indicate the degree of correlation between each cell of the subnet and the abnormality, it cannot be directly determined how many cells should be selected as problem cells based on the magnitude of the abnormal contribution.
  • the cells with positive abnormal contribution degree can be selected to form the sequence to be screened. Because only the cell with a positive abnormal contribution degree may cause an abnormality, and the role of other cells is to eliminate the abnormality or has nothing to do with the abnormality, only the cell with a positive abnormal contribution degree may be a problem cell.
  • the temporary performance index of the subnet is calculated, that is, the performance index of the "small subnet" formed by the remaining cells in the subnet after the excluded cells are removed.
  • the performance index of the subnet calculates the difference between the performance index of the subnet and the temporary performance index of the subnet as the optimized performance index, that is, the performance index of the "atomic network” (the overall performance index of all cells) and the "small subnet” after the current number of cells is currently excluded.
  • the difference between the performance index that is, the overall performance index of the remaining cell after excluding the N cells with the largest anomaly contribution.
  • the optimized performance index can be calculated by the following formula:
  • n is the total number of cells in the subnet
  • N is the number of cells currently excluded.
  • the candidate cell is the problem cell (S1024).
  • the step S1024 of determining at least part of the candidate cells as problem cells includes:
  • each historical performance indicator is a performance indicator of the cell at a historical moment before the abnormality of the performance indicator of the subnet occurs.
  • the candidate cell identified above is the problem cell that caused the abnormality, but the candidate cell at this time does not consider the historical state.
  • the performance indicators of the cells with poor indicators have been poor for a long time, but the subnet has not been abnormal; this indicates that the abnormality at this time may not be caused by the cells with poor indicators, but the performance indicators of other cells suddenly "change. "Poor”. In other words, the final problem cell should be filtered out of the above-mentioned poor quality cell.
  • the performance indicators (historical performance indicators) of multiple historical moments before the abnormality of the subnet can be counted (the multiple historical moments may all be within a predetermined time range before the abnormality occurs). For example, if the statistics are performed every 15 minutes in the 5 hours before the abnormality, 20 historical performance indicators at 20 historical moments are obtained in total.
  • each historical performance indicator exceeds the first threshold range, that is, it is determined whether the performance indicator of the cell is poor at each historical moment.
  • the above first threshold value range may be a fixed value; and if the first threshold value range is the above real-time value, each historical performance indicator may be compared with the first threshold value range of its corresponding historical time.
  • the historical abnormal ratio of each candidate cell can be compared with the preset second threshold (such as 80%), and if the historical abnormal ratio of a certain cell (such as 90%) is greater than the second threshold (such as 80%), then confirm The candidate cell has poor long-term performance indicators and is a poor indicator cell, which can be filtered out of the candidate cells.
  • the cells with poor long-term performance indicators are filtered out, so that the remaining candidate cells should be the problem cells that substantially cause abnormalities, so that the resulting problem cells are more accurate.
  • the method further includes:
  • the remaining candidate cells can be directly used as the problem cell.
  • the specific cells that is, the first predetermined number of cells
  • the 3 cells with the largest abnormal contribution are selected as the problem cells (that is, the first predetermined number of bits is 3).
  • the following introduces a specific example of determining the problem cell with respect to the abnormality of the ratio-based performance index.
  • the cell availability performance index of a subnet 370801 of an LTE network is abnormal at 02:15 on 2019-12-05, that is, the cell availability is lower than the lower limit of the first threshold range, as shown in the following table:
  • the cell availability ratio is equal to the ratio of the actual available duration in the statistical period to the total duration of the statistical period.
  • the actual available time is 614700s
  • the total cycle time is 722700s. It can be obtained from this that the cell availability rate at this time is 0.85056, which is lower than the lower limit of the first threshold range.
  • the actual available duration and the total duration of the statistical period of each cell of the subnet are obtained, and their abnormal contribution degrees are calculated.
  • the actual available time of the cell is 0s, and the statistical period is 900 seconds, then:
  • the optimization performance index 0.958079 becomes larger than the lower limit of the first threshold range 0.957941, so that a total of 66 candidate cells can be obtained.
  • the cell availability rate of some cells is always 0, so the abnormal contribution rate alone cannot reflect the contribution of these cells to the abnormality.
  • the second threshold such as 80%
  • these problematic cells are basically not the long-term poor cell availability, but most of them are the cells where the cell availability suddenly and significantly deteriorated when the subnet is abnormal or in the short period before the subnet is abnormal.
  • the cell availability rate of this subnet is lower than the lower limit of the first threshold (this time anomaly).
  • the following describes a specific method for determining the problem cell when the numerical performance index is abnormal.
  • numerical performance indicators may include rate, flow, etc., and their corresponding parameter statistics are rate and flow.
  • first parameter statistics and the second parameter statistics used to calculate ratio-based performance indicators can also be regarded as numerical performance indicators, such as the number of connected times, the number of dropped calls, the number of congestion, the number of successful handovers, and the number of attempts to connect. The number of times, the number of calls, the number of data transmissions, the number of handover attempts, etc.
  • the performance index of the subnet at this time is directly equal to the sum of the performance indexes of all the cells in it.
  • the abnormal contribution degree of each cell is determined according to the ratio of the deviation value of the performance indicator of the cell to the deviation value of the performance indicator of the subnet.
  • the deviation value of the performance index of each cell is the difference between the performance index of the cell and the predicted performance index
  • the deviation value of the performance index of the subnet is the difference between the performance index of the subnet and the predicted performance index
  • the predicted performance index of each cell In order to predict the normal value of the performance index of the cell, the predicted performance index of the subnet is the sum of the predicted performance index of each cell.
  • the abnormal contribution of each cell can be calculated in the following way:
  • a predictive performance index is set for each cell, and the predictive performance index is the "normal value" of the predicted performance index of the cell.
  • the sum of the predicted performance indicators of all the cells in the subnet is the predicted performance indicator of the subnet, that is, the "normal value” of the predicted performance indicator of the subnet.
  • the performance index of the subnet will inevitably deviate from its predictive performance index (that is, deviate from the normal value); at the same time, the predictive performance index of at least some cells in the subnet deviates from its predictive performance index, that is, the performance of the subnet.
  • the deviation of the indicator from the normal value must be caused by the deviation of the performance indicator of the cell from the respective normal value.
  • the deviation value of the performance index of the cell can be obtained, that is, the degree to which the performance index of the cell deviates from the normal value.
  • the deviation value of the performance index of the subnet can be obtained, that is, the degree to which the performance index of the subnet deviates from the normal value.
  • the ratio of the deviation of the performance index of the cell to the deviation of the performance index of the subnet that is, the deviation of the performance index of the cell in the performance index of the subnet, or the deviation of the performance index of the subnet (that is, abnormal ) To what extent is caused by the cell, so it is the abnormal contribution of the cell.
  • the abnormal contribution degree of the i-th cell can be calculated by the following formula:
  • the abnormal contribution degree of the i-th cell (the performance index of the i-th cell-the predictive performance index of the i-th cell)/(the performance index of the subnet-the predictive performance index of the subnet).
  • the abnormal contribution degree of the cell is positive, it indicates that the cell has a "positive contribution" to the abnormality, or the role of the cell is to make the subnet abnormal.
  • the abnormal contribution degree of the cell is negative, it indicates that the cell has a "negative contribution" to the abnormality, or the role of the cell is to avoid the abnormality of the subnet.
  • the predicted performance index of each cell is an average value of the performance index of the cell within a predetermined time before the abnormality of the performance index of the subnet occurs.
  • the average value of the cell's performance indicators is used as the predicted performance indicator of the cell. For example, within 15 days before the occurrence of the abnormality, the average value of the performance indicators of the cell in the same time period as the occurrence of the abnormality each day may be taken as the predicted performance index of the cell.
  • the predicted performance index of the subnet is actually the average value of the performance index of the subnet in the above period.
  • the step S102 of determining at least one cell as a problem cell according to the abnormal contribution degree of each cell of the subnet includes:
  • S1025 Determine a third threshold value according to the abnormal contribution degree of all cells whose abnormal contribution degree is positive, and the third threshold value is a positive number.
  • the abnormal contribution degree of each cell of the subnet only represents the relative value of its correlation with the abnormality, but only based on the abnormal contribution degree of each cell of the subnet, it is impossible to directly determine how many cells should be selected as problem cells.
  • a third threshold can be calculated based on the abnormal contribution of all cells with a positive abnormal contribution (that is, all cells that may cause anomalies), and the cells with an abnormal contribution exceeding the third threshold (if any ) Is determined as the problem cell.
  • the third threshold is calculated by the following formula:
  • the third threshold average value of the abnormal contribution of all cells with positive abnormal contribution+k*standard deviation of the abnormal contribution of all cells with positive abnormal contribution; where k is a value greater than 0.
  • the average value and standard deviation of the abnormal contribution degrees of all cells with positive abnormal contribution degrees can be obtained, and the average value plus a certain multiple of the standard deviation can be used as the above third threshold.
  • the third threshold may be equal to the average value of the abnormal contribution of all cells with positive abnormal contribution.
  • the following introduces a specific example of determining the problem cell with respect to the abnormality of the numerical performance index.
  • a cell with an abnormal contribution degree exceeding 0.018652 can be selected as a problem cell.
  • the embodiment of the present disclosure needs to first obtain the performance index of the subnet to determine whether the performance index of the subnet is abnormal; Whether the performance indicator is a numerical performance indicator or a ratio-based performance indicator, it is processed according to the corresponding method.
  • the differences between the algorithms corresponding to the numerical performance indicators and the ratio performance indicators mainly include:
  • the calculation method of the abnormal contribution degree of the cell is different. This is because the ratio-based performance index of the subnet is not equal to the sum of the ratio-based performance indexes of each cell, so the ratio-based performance index of each cell cannot be added together for calculation.
  • the calculation of the abnormality corresponding to the numerical performance index does not include the step of filtering out "cells with poor index quality". This is because in the calculation process of abnormal contribution degree for numerical performance indicators, the historical performance indicators (predictive performance indicators) of the cell have been considered, while the calculation process of abnormal contribution degree for ratio-based performance indicators only considers the abnormal contribution of each cell. Data; Therefore, when the numerical performance index is abnormal, it is not necessary to filter out the cell with poor performance index in the history (the cell with poor index quality).
  • embodiments of the present disclosure can be implemented completely in an automated manner, without manual intervention, and are not affected by human factors, and are fast, intelligent, and accurate.
  • an electronic device which includes:
  • One or more processors are One or more processors;
  • a memory with one or more programs stored thereon, and when the one or more programs are executed by one or more processors, the one or more processors implement any one of the above-mentioned methods for identifying problem cells;
  • One or more I/O interfaces are connected between the processor and the memory, and are configured to implement information interaction between the processor and the memory.
  • the processor is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.
  • the memory is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically such as SDRAM). , DDR, etc.), read-only memory (ROM), charged erasable programmable read-only memory (EEPROM), flash memory (FLASH);
  • the I/O interface read and write interface
  • the information exchange of the processor includes, but is not limited to, a data bus (Bus), etc.
  • an embodiment of the present disclosure provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, any one of the above-mentioned methods for identifying problem cells is implemented.
  • the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may consist of several physical components. The components are executed cooperatively.
  • Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit (CPU), digital signal processor, or microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as Application specific integrated circuit.
  • a processor such as a central processing unit (CPU), digital signal processor, or microprocessor
  • Such software may be distributed on a computer-readable medium, and the computer-readable medium may include a computer storage medium (or a non-transitory medium) and a communication medium (or a transitory medium).
  • the term computer storage medium includes volatile and non-volatile memory implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Sexual, removable and non-removable media.
  • Computer storage media include, but are not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), charged erasable programmable read-only memory (EEPROM), flash memory (FLASH) or other disk storage ; CD-ROM, digital versatile disk (DVD) or other optical disk storage; magnetic cassette, tape, magnetic disk storage or other magnetic storage; any other that can be used to store desired information and can be accessed by a computer medium.
  • a communication medium usually contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium. .
  • the abnormal contribution of each cell of the subnet is determined according to the performance indicators of the subnet and the cell (or the parameter statistics of all cells) when the abnormality occurs, that is, the abnormal contribution of each cell of the subnet is determined. possibility. Therefore, compared with the related technology that determines the abnormal contribution degree solely based on the performance index of each cell of the subnet, the method of the embodiment of the present disclosure can more accurately determine the problem cell (that is, the cell that actually causes the abnormality) based on the abnormal contribution degree. In order to follow-up targeted network optimization and improve user experience.
  • embodiments of the present disclosure can be implemented completely in an automated manner, without manual intervention, and are not affected by human factors, and are fast, intelligent, and accurate.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

一种识别问题小区的方法、电子设备和计算机可读介质。该方法包括：确定子网各小区的异常贡献度(S101)；根据子网各小区的异常贡献度，确定至少一个小区为问题小区(S102)；其中，每个所述小区的异常贡献度为子网的性能指标发生异常时，该小区的性能指标与该异常的关联程度；所述子网的性能指标发生异常为子网的性能指标超出第一阈值范围；所述子网的性能指标根据其中各小区的参数统计量确定；所述小区的性能指标根据其中的参数统计量确定。

Description

识别问题小区的方法、电子设备、计算机可读介质 技术领域
本公开实施例涉及移动通信网络技术领域，特别涉及识别问题小区的方法、电子设备、计算机可读介质。
背景技术
在移动通信网络(例如移动宽带网络MBB)中，当子网的指接通率、掉话率、拥塞率、切换成功率、流量、速率等性能指标(KPI，Key Performance Indicator)超出预定范围时，称为子网发生异常。而子网异常通常主要是由其中一个或多个小区的问题导致的，这些小区称为问题小区，或者称为topN差小区，通常是各种性能指标比较差的小区。
因此，准确的找到引起异常的问题小区，对优化网络、改善用户体验等都是非常重要的。
发明内容
本公开实施例提供一种识别问题小区的方法、电子设备、计算机可读介质。
第一方面，本公开实施例提供一种识别问题小区的方法，其包括：确定子网各小区的异常贡献度；根据子网各小区的异常贡献度，确定至少一个小区为问题小区；其中，每个所述小区的异常贡献度为子网的性能指标发生异常时，该小区的性能指标与该异常的关联程度；所述子网的性能指标发生异常为子网的性能指标超出第一阈值范围；所述子网的性能指标根据其中各小区的参数统计量确定；所述小区的性能指标根据其中的参数统计量确定。
第二方面，本公开实施例提供一种电子设备，其包括：一个或多个处理器；存储器，其上存储有一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现上述任意一种识别问题小区的方法；一个或多个I/O接口，连接在所述处理器与存储器之间，配置为实现所述处理器与存储器的信息交互。
第三方面，本公开实施例提供一种计算机可读介质，其上存储有计算机程序，所述程序被处理器执行时实现上述任意一种识别问题小区的方法。
附图说明
附图用来提供对本公开实施例的进一步理解，并且构成说明书的一部分，与本公开实施例一起用于解释本公开，并不构成对本公开的限制。通过参考附图对详细示例实施例进行描述，以上和其它特征和优点对本领域技术人员将变得更加显而易见，在附图中：
图1为本公开实施例适用的移动通信网络的组成示意框图；
图2为本公开实施例中上行速率性能指标实时值与第一阈值范围的示意图；
图3为本公开实施例提供的一种识别问题小区的方法的流程图；
图4为本公开实施例提供的另一种识别问题小区的方法中部分步骤的流程图；
图5为本公开实施例提供的另一种识别问题小区的方法中部分步骤的流程图；
图6为本公开实施例提供的另一种识别问题小区的方法中部分步骤的流程图；
图7为本公开实施例提供的另一种识别问题小区的方法的逻辑过程图；
图8为本公开实施例提供的一种电子设备的组成框图；
图9为本公开实施例提供的一种计算机可读介质的组成框图。
具体实施方式
为使本领域的技术人员更好地理解本公开实施例的技术方案，下面结合附图对本公开实施例提供的识别问题小区的方法、电子设备、计算机可读介质进行详细描述。
在下文中将参考附图更充分地描述本公开实施例，但是所示的实施例可以以不同形式来体现，且不应当被解释为限于本公开阐述的实施例。反之，提供这些实施例的目的在于使本公开透彻和完整，并将使本领域技术人员充分理解本公开的范围。
本公开实施例可借助本公开的理想示意图而参考平面图和/或截面图进行描述。因此，可根据制造技术和/或容限来修改示例图示。
在不冲突的情况下，本公开各实施例及实施例中的各特征可相互组合。
本公开所使用的术语仅用于描述特定实施例，且不意欲限制本公开。如本公开所使用的术语“和/或”包括一个或多个相关列举条目的任何和所有组合。如本公开所使用的单数形式“一个”和“该”也意欲包括复数形式，除非上下文另外清楚指出。如本公开所使用的术语“包括”、“由……制成”，指定存在所述特征、整体、步骤、操作、元件和/或组件，但不排除存在或添加一个或多个其它特征、整体、步骤、操作、元件、组件和/或其群组。
除非另外限定，否则本公开所用的所有术语(包括技术和科学术语)的含义与本领域普通技术人员通常理解的含义相同。还将理解，诸如那些在常用字典中限定的那些术语应当被解释为具有与其在相关技术以及本公开的背景下的含义一致的含义，且将不解释为具有理想化或过度形式上的含义，除非本公开明确如此限定。
本公开实施例不限于附图中所示的实施例，而是包括基于制造工艺而形成的配置的修改。因此，附图中例示的区具有示意性属性，并且图中所示区的形状例示了元件的区的具体形状，但并不是旨在限制性的。
名词解释
本公开实施例中，如无特定说明，则以下技术术语应按照以下解释理解：
移动通信网络，其是指实现移动用户与固定用户之间，或移动用户之间的通信的网络。移动通信网络具体可为全球移动通信网络(GSM)、通用移动通信网络(UMTS)、长期演进技术网络(LTE)、码分多址网络(CDMA)、新空口网络(NR)等。
小区，其是指移动通信网络中可独立控制的最小区域。例如，小区可以是一个基站覆盖的区域，也可以是基站中一个天线覆盖的区域等。
子网，其是指多个小区集成的用于进行统一管理区域，其可包括一个网元设备对应的 多个小区。
性能指标，其是指根据移动通信网络中的参数统计量得出的，能表示移动通信网络的性能的参数。例如，性能指标可包括接通率、掉话率、拥塞率、切换成功、流量、速率等。
参数统计量，其是指对移动通信网络运行过程中产生的参数的直接统计值，但不包括根据直接统计值进行计算得到的进一步的数值(如比率型性能指标)。例如，参数统计量可包括流量、速率、接通次数、尝试连接的次数、掉话次数、通话次数、拥塞的次数、进行数据传输的次数、切换成功次数、尝试切换的次数等。
应用环境
本公开实施例用于移动通信网络环境中。
示例性的，参照图1，本公开实施例适用的移动通信网络可包括：无线网络设备、核心网络设备、网络设备网管服务器、网络性能监控服务器等。
其中，本公开实施例的具体运算可通过网络性能监控服务器实现。网络性能监控服务器可定期的从网络设备网管服务器上获取子网和小区的性能指标相关数据，以用于实现本公开实施例。
本公开的实施例
在移动通信网络(如移动宽带网络MBB)中，主要的管理区域为子网，每个子网又分为多个小区。由此，每个子网中的接通率、掉话率、拥塞率、切换成功率、流量、速率等性能指标(KPI)，实际是其中所有小区的性能指标的综合。
当子网的某性能指标超出预定范围时，表明该性能指标明显不合理，即子网出现异常，会严重影响用户体验。而子网的异常通常是由其中一个或多个小区的问题导致的，这些小区称为问题小区，或者称为topN差小区，通常是各种性能指标比较差的小区。
因此，准确的找到引起异常的问题小区，对优化网络、改善用户体验等都是非常重要的。
在一些相关技术中，直接以性能指标的排序确定问题小区。例如，可直接将掉话率较高的小区作为问题小区。但是，由于不同小区间的业务量(如通话量)存在很大差异，业务量较低的小区的性能指标波动范围很大，故单纯的性能指标往往不能反应小区的真实性能，仅根据小区的性能指标也不一定能分析出导致子网异常的实际小区。
另一种相关技术中，用性能指标和人为设定的绝对次数作为筛选问题小区的条件。例如，以掉话率为例，工作人员(如现场网优工程师或客户)根据小区的地理环境、经常倍投诉的问题等，人为设定阈值，即规定必须是掉话次数大于相应阈值，且掉话率大于相应阈值的小区才是问题小区。但是，这种方法存在人的主观判断，有很大的人为因素，无法保证准确率，且耗时长，难以通用性。
第一方面，参照图3，本公开实施例提供一种识别问题小区的方法，其包括：
S101、确定子网各小区的异常贡献度。
其中，每个小区的异常贡献度为子网的性能指标发生异常时，该小区的性能指标与该异常的关联程度；子网的性能指标发生异常为子网的性能指标超出第一阈值范围；子网的 性能指标根据其中各小区的参数统计量确定；小区的性能指标根据其中的参数统计量确定。
当子网的某性能指标出现异常(即子网整体的性能指标超出第一阈值范围)时，根据此时子网的性能指标和其中各小区的性能指标，可确定出每个小区的异常贡献度，即每个小区的性能指标与子网出现的该异常的相关联的程度，或者说是子网各小区引起该异常的可能性。
当然，应当理解，针对不同的性能指标，第一阈值范围也是不同的，即每个性能指标都应有自己对应的第一阈值范围。
S102、根据子网各小区的异常贡献度，确定至少一个小区为问题小区。
根据子网各小区引起该异常的可能性(异常贡献度)，可以确定出问题小区，也就是确定出实际引起该异常的小区。
当然，应当理解，本公开实施例的方法是针对子网异常时的情况计算的，故其可以在子网发生异常时实时的计算，但并不代表本公开实施例的方法必须实时进行。例如，也可将子网异常时的相关数据保存下来，待之后统一按照本公开实施例的方式处理。
本公开实施例中，根据发生异常时子网和小区的性能指标(或者说是所有小区的参数统计量)，确定出子网各小区的异常贡献度，也就是子网各小区引起该异常的可能性。从而，相对于单纯根据子网各小区的性能指标本身确定异常贡献度的相关技术，本公开实施例的方式可根据异常贡献度更准确的确定出问题小区(也就是实际导致异常的小区)，以便后续有针对性的进行网络优化，改善用户体验。
另外，本公开实施例可完全通过自动化的方式实现，而不需要人工干预，不受人为因素的影响，速度快，智能且精准。
在一些实施例中，第一阈值范围包括：第一阈值范围下限，和/或，第一阈值范围上限。
判断子网是否异常用的第一阈值范围可包括上限值和下限值，即性能指标过大或过小均可能是异常。例如，当速率过大或过小时，均可能代表不正常。
或者，第一阈值范围也可仅包括上限值和下限值中的一者，即性能指标只可能因过大或过小中的一者发生异常。例如，当掉线率大于一定值时显然是异常，但掉线率即使为最小值0，也不应视为异常。
在一些实施例中，第一阈值范围是通过动态阈值检测技术确定的。
也就是说，以上第一阈值范围可以是根据动态阈值检测技术(比如自动学习的holtwinters算法)计算得到的实时值。
例如，参照图2，其中深色线条为上行速率性能指标的实时值，而其上下两侧的浅色区域为各个时间的第一阈值范围的取值范围，可见该第一阈值范围就是根据时间实时变化的。
其中，利用动态阈值检测技术确定性能指标的正常范围(第一阈值范围)的过程可根据一些相关技术实现，在此不再详细描述。
作为本公开实施例的一种方式，下面介绍针对比率型性能指标异常时，确定问题小区的具体方式。
其中，比率型性能指标是指两个不同的参数统计量形成的比值，如为百分比，即比率型性能指标为第一参数统计量与第二参数统计量的比值。
例如，比率型性能指标可包括接通率、掉话率、拥塞率、切换成功率等；相应的，与接通率、掉话率、拥塞率、切换成功率对应的第一参数统计量分别为接通次数、掉话次数、拥塞的次数、切换成功次数等；而第二参数统计量分别为尝试连接的次数、通话次数、进行数据传输的次数、尝试切换的次数等。
由此，第i个小区的性能指标(比率型性能指标)可通过以下公式计算：
第i个小区的性能指标＝第i个小区的第一参数统计量/第i个小区的第二参数统计量。
相应的，每个子网的性能指标(比率型性能指标)，则等于其中所有小区的第一参数统计量与第二参数统计量的比值，即，
Figure PCTCN2021074431-appb-000001
其中，n为子网中小区的总数。
可见，对比率型性能指标，子网的性能指标并非其中各小区的性能指标的和。
在一些实施例中，对比率型性能指标，每个小区的异常贡献度表示将该小区从子网去除后，子网的性能指标相对去除前子网的性能指标向第一阈值范围内偏移的程度。
对比率型性能指标，每个小区的异常贡献度表示：
将该小区从子网去除后，子网中剩余的小区可得到一个新的子网的性能指标，而该新的子网的性能指标相对去除前子网的原性能指标向第一阈值范围内偏移的程度就是该小区的异常贡献度。
其中，“向第一阈值范围内偏移的程度”是指，若去除后的新性能指标比去除前的原性能指标更接近第一阈值范围，则偏移的程度为正(即就是向第一阈值范围内偏移)；反之，若去除后的新性能指标比去除前的原性能指标更远离第一阈值范围，则偏移的程度为负(即向远离第一阈值范围的方向偏移)。
其中，因为当前是在异常状态下，故子网当前的性能指标必然超出第一阈值范围。从而，当以上去除后的新性能指标比去除前的原性能指标更加靠近第一阈值范围时，则表明去除后的新性能指标相对原性能指标向第一阈值范围内的偏移的程度为“正值”；即，去除某小区后，性能指标变的比较接近第一阈值范围甚至进入第一阈值范围内(即偏向正常)，从而该“被去除”的小区的作用应当是使性能指标远离第一阈值范围。故此时该小区的异常贡献度为“正贡献”，或者说，该小区的作用是使子网产生异常。
相对的，当以上去除后的新性能指标比去除前的原性能指标更加远离第一阈值范围时，则表明去除后的新性能指标相对原性能指标向第一阈值范围内的偏移的程度为“负值”；即，去除某小区后，性能指标变的更远离第一阈值范围(即偏向异常)，从而该“被去除”的小区的作用应当是使性能指标接近第一阈值范围。故此时该小区的异常贡献度为“负贡献”，或者说，该小区的作用是避免子网产生异常。
当然，以上去除后的新性能指标也可能与原性能指标相等，则此时该小区的异常贡献度为0，即该小区对子网产生的异常无影响。
具体的，此时第j个小区的异常贡献度可通过如下公式计算：
Figure PCTCN2021074431-appb-000002
其中，n为子网中小区的总数；D为异常方向，其定义为：
当子网的性能指标大于第一阈值范围上限时，D＝1；
当子网的性能指标小于第一阈值范围下限时，D＝-1。
当然，应当理解，当第一阈值范围仅有上限和下限中的一者时，则性能指标当然只能从一个方向超出第一阈值范围，故异常方向可为定值。
另外，异常方向的绝对值也不一定为1，只要其是绝对值相同的正负两个值即可。
可见，根据以上算法，比率型性能指标发生异常时，小区的异常贡献度不是仅根据该小区的性能指标和参数统计量(如次数)计算，而是根据小区自身的第一参数统计量、第二参数统计量，以及子网中其它小区的第一参数统计量、第二参数统计量计算得到；从而，该异常贡献度可比较真实的反应小区与子网异常的关联程度，根据该异常贡献度确定的问题小区也更准确，可实现更好的网络优化、改善用户体验的效果。
参照图4，在一些实施例中，根据子网各小区的异常贡献度，确定至少一个小区为问题小区的步骤S102包括：
S1021、将异常贡献度为正的小区降序排列得到待筛选序列，确定N为1。
S1022、确定优化性能指标；优化性能指标为子网的性能指标与子网的临时性能指标的差值，临时性能指标为去除待筛选序列中排名前N的小区后，子网中剩余小区的整体的性能指标。
S1023、若优化性能指标处于第一阈值范围内，确定待筛选序列中排名前N的小区为候选小区；若优化性能指标超出第一阈值范围，使N增大1并返回确定优化性能指标的步骤。
S1024、确定至少部分候选小区为问题小区。
在确定子网各小区的异常贡献度后，还需要进一步确定问题小区。但以上异常贡献度是相对值，虽然可表明子网各小区与异常的相关程度，却无法直接根据异常贡献度的大小确定应具体选取多少个小区为问题小区。
为此，可先选取异常贡献度为正的小区组成待筛选序列。因为只有异常贡献度为正的小区可能引起异常，其它小区的作用是消除异常或与异常无关，故只有异常贡献度为正的小区才可能是问题小区。
之后，按照异常贡献度为从大到小的顺序，开始排除小区，且排除的小区数量逐渐增 多，即，第一次排除异常贡献度最大的小区(N＝1)，第二次排除异常贡献度前两名的小区(N＝2)，第三次排除异常贡献度前三名的小区(N＝3)，依次类推。
在每次排除小区后，计算子网的临时性能指标，也就是除去被排除的小区后，子网中剩余的其它小区构成的“小子网”所具有的性能指标。
之后计算子网的性能指标与子网的临时性能指标的差值为优化性能指标，即“原子网”的性能指标(所有小区整体的性能指标)与按照当前数量当前排除小区后“小子网”的性能指标(即排除了N个异常贡献度最大的小区后剩余小区整体的性能指标)的差值。
例如，当排除了N个小区时，优化性能指标可通过以下公式计算：
Figure PCTCN2021074431-appb-000003
其中，n为子网中小区的总数，N为当前排除的小区数量。
而在任意一次排除后分以下情况进行处理：
(1)若优化性能指标不在以上第一阈值范围内，则多排除一个小区(N＝N+1)，并返回确定优化性能指标的步骤(S1022)重新计算优化性能指标；
(2)若优化性能指标处于以上第一阈值范围内，则排除过程结束，用当前被排除的N个小区(即异常贡献度最大的N个小区)为“候选小区”，并进一步确定至少部分候选小区为问题小区(S1024)。
应当理解，由于异常实际仅能由异常贡献度为正的小区引起，故最广域网在把所有异常贡献度为正的小区(即待筛选序列中的所有小区)排除完时，优化性能指标必然会处于第一阈值范围内，即候选小区最多是待筛选序列中的所有小区。
在一些实施例中，参照图5，确定至少部分候选小区为问题小区的步骤S1024包括：
S10241、确定每个候选小区的多个历史性能指标；每个历史性能指标为该小区在子网的性能指标发生异常前的一个历史时刻的性能指标。
S10242、确定每个候选小区的历史异常比例；每个小区的历史异常比例为该小区的所有历史性能指标中超出第一阈值范围的历史性能指标所占的比例。
S10243、将历史异常比例高于第二阈值的小区从候选小区中去除。
仅从异常贡献度看，以上确定的候选小区就是引起异常的问题小区，但是，此时的候选小区并未考虑历史状态。
例如，可能有部分小区的性能指标长期处于较差的状态(如性能指标经常超出第一阈值范围)，这些小区称为“指标质差小区”。对指标质差小区，其异常贡献度通常较大，故很可能被确定为候选小区。
但是，指标质差小区的性能指标长期较差，而子网却一直没有出现异常；这表明，此 时的异常反而可能不是指标质差小区导致的，而是由其它小区的性能指标突然“变差”导致的。也就是说，最终确定的问题小区，实际应当滤除以上指标质差小区。
为此，对每个候选小区，可统计其在子网异常之前的多个历史时刻(多个历史时刻可均在异常发生前的一个预定时间范围内)的性能指标(历史性能指标)。例如，在异常前的5个小时中每隔15分钟统计一次，则共得到20个历史时刻的20个历史性能指标。
之后，分别判断每个历史性能指标是否超出第一阈值范围，即确定在每个历史时刻，小区的性能指标是否较差。其中，以上第一阈值范围可以是定值；而若第一阈值范围是以上的实时值，则每个历史性能指标可与其对应的历史时刻的第一阈值范围进行比较。
在一些实施例中，还判断每个候选小区的所有历史性能指标中，超出第一阈值范围的历史性能指标所占的比例，即历史异常比例。例如，若某小区有20个历史性能指标，其中16个超出了第一阈值范围，则该小区的历史异常比例＝18/20＝90％。
显然，某个小区的历史异常比例越大，则代表小区在之前整体的性能指标越差，越可能属于指标质差小区。因此，可将各候选小区的历史异常比例与预设的第二阈值(如80％)进行比较，若某小区的历史异常比例(如90％)大于第二阈值(如80％)，则确认该候选小区长期性能指标较差，为指标质差小区，可将其从候选小区中滤除。
通过以上方式，将长期性能指标较差的小区过滤掉了，从而剩余的候选小区，应当就是实质上引起异常的问题小区，使得到的问题小区更加准确。
在一些实施例中，在将历史异常比例高于第二阈值的小区从候选小区中去除的步骤S10243后，还包括：
S10244、若存在剩余的候选小区，确定所有剩余的候选小区为问题小区；若无剩余的候选小区，确定异常贡献度最大的前第一预定位的小区为问题小区。
在排除指标质差小区后，若还有至少一个候选小区剩余下来(即没被滤除)，则可直接将剩余的候选小区作为问题小区。
但是，在排除指标质差小区后，若已经没有剩余的候选小区了，则表明以上滤除过程不合理，从而应直接从所有小区中(当然是滤除前的所有小区)选取异常贡献度最大的特定个小区(即前第一预定位个小区)为问题小区，例如选取异常贡献度最大的3个小区为问题小区(即第一预定位为3位)。
例如，以下介绍针对比率型性能指标的异常确定问题小区一个具体例子。
假设某LTE网络的子网370801在2019-12-05 02:15时刻发生小区可用率性能指标异常，即小区可用率低于第一阈值范围下限，如下表：
Figure PCTCN2021074431-appb-000004
其中，小区可用率等于统计周期内的实际可用时长与统计周期总时长的比值。其中， 异常发生时，实际可用时长为614700s，周期总时长为722700s，由此可得，此时的小区可用率为0.85056，低于第一阈值范围下限。
相应的，获取子网各小区的实际可用时长和统计周期总时长，计算它们的异常贡献度。以小区(210517,210517,12)为例，该小区实际可用时长为0s，统计周期时长为900秒，则可得：
小区(210517,210517,12)的异常贡献度＝-1*[614700/722700-(614700-0)/(722700-900)]＝0.106055*10 -2。
保留异常贡献度大于0的小区，并降序排列，得到待筛选序列如下：
Figure PCTCN2021074431-appb-000005
按照以上方式，从N＝1开始排除小区，排除不同数量的小区后得到的部分优化性能指标按顺序如下：
.....、0.903225、0.904352、0.90548、.....、0.956639、0.957359、0.958079
在排除66个小区后，优化性能指标0.958079变得大于第一阈值范围下限0.957941，从而可得候选小区共66个。
以上66个候选小区中，有一部分小区的小区可用率一直为0，故仅靠异常贡献度不能反应这些小区对异常的贡献。
因此，需要进行指标质差小区的滤除，判断在异常时刻前的一段时间范围内，每个小区的小区可用率不在第一阈值范围内的比例是否超过第二阈值(如80％)，若超过则将小区从候选小区中去除。
由此，可确定最后剩余的候选小区为问题小区。
而且，这些问题小区，基本都不是小区可用率长期较差的，而多是在子网异常时，或子网异常之前的较近时间内，小区可用率突然明显恶化的小区，也就是实际导致本次子网的小区可用率低于第一阈值下限(本次异常)的小区。
作为本公开实施例的另一种方式，下面介绍针对数值型性能指标异常时，确定问题小区的具体方式。
数值型性能指标直接就是参数统计量，而非通过参数统计量计算得到的。
例如，数值型性能指标可包括速率、流量等，其对应的参数统计量也就是速率、流量。
当然，计算比率型性能指标用的第一参数统计量和第二参数统计量本身，也可视为数值型性能指标，如接通次数、掉话次数、拥塞的次数、切换成功次数、尝试连接的次数、通话次数、进行数据传输的次数、尝试切换的次数等。
由此，此时子网的性能指标，就直接等于其中所有小区的性能指标的和。
在一些实施例中，针对数值型性能指标，每个小区的异常贡献度根据该小区的性能指标偏离值与子网的性能指标偏离值的比值确定。
其中，每个小区的性能指标偏离值为该小区的性能指标与预测性能指标的差，子网的性能指标偏离值为子网的性能指标与预测性能指标的差，每个小区的预测性能指标为预测得到的该小区的性能指标的正常值，子网的预测性能指标为其中各小区的预测性能指标的和。
也就是说，当性能指标为数值型性能指标时，每个小区的异常贡献度可通过以下方式计算：
为每个小区设定预测性能指标，该预测性能指标为预测的小区的性能指标的“正常值”。相应的，子网中所有小区的预测性能指标的和，就是子网的预测性能指标，也就是预测的子网的性能指标的“正常值”。
显然，当子网异常时，子网的性能指标必然偏离其预测性能指标(即偏离正常值)；同时，子网中也有至少一部分小区的预测性能指标偏离其预测性能指标，即子网的性能指标偏离正常值，必然是其中小区的性能指标偏离各自的正常值导致的。
从而，根据小区的性能指标与预测性能指标的差，可得到小区的性能指标偏离值，即小区的性能指标偏离正常值的程度。而根据子网的性能指标与预测性能指标的差，可得到子网的性能指标偏离值，即子网的性能指标偏离正常值的程度。
小区的性能指标偏离值与子网的性能指标偏离值的比值，即表示小区的性能指标偏离在子网的性能指标偏中所占的比例，或者说是子网的性能指标偏离(也就是异常)有多大程度是该小区导致的，故也就是小区的异常贡献度。
在一些实施例中，第i个小区的异常贡献度可通过如下公式计算：
第i个小区的异常贡献度＝(第i个小区的性能指标-第i个小区的预测性能指标)/(子网的性能指标-子网的预测性能指标)。
当然，应当理解，由于小区和子网的性能指标偏离各自的预测性能指标(正常值)的方向可能不同(可能偏大或偏小)，故以上计算得到的异常贡献度也可能为正、为负、为0。
相应的，若小区的异常贡献度为正，则表明小区对异常有“正贡献”，或者说小区的作用是使子网产生异常。
若小区的异常贡献度为负，则表明小区对异常有“负贡献”，或者说小区的作用是避免子网产生异常。
若小区的异常贡献度为0，则表明小区对子网产生的异常无影响.
在一些实施例中，每个小区的预测性能指标为该小区的性能指标在子网的性能指标发生异常前的预定时间内的平均值。
也就是说，可用子网发生异常之前一段时间内，小区的性能指标的平均值作为该小区的预测性能指标。例如，可取发生异常前15天内，每天与发生异常相同的时间段中，小区的性能指标的平均值，作为小区的预测性能指标。
相应的，子网的预测性能指标实际上也是以上时间内子网的性能指标的平均值。
当然，应当理解，如果采用根据经验人为设定等方式，确定子网各小区的预测性能指标，也是可行的。
在一些实施例中，参照图6，根据子网各小区的异常贡献度，确定至少一个小区为问题小区的步骤S102包括：
S1025、根据异常贡献度为正的所有小区的异常贡献度，确定第三阈值，第三阈值为正数。
S1026、若存在异常贡献度超过第三阈值的小区，确定所有异常贡献度超过第三阈值的小区为问题小区；若无异常贡献度超过第三阈值的小区，确定异常贡献度最大的前第二预定位的小区为问题小区。
如前，子网各小区的异常贡献度只是表示其与异常的相关程度的相对值，但仅根据子网各小区的异常贡献度本身，无法直接确定应选取多少个小区为问题小区。
为此，可根据异常贡献度为正的所有小区(即所有有可能导致异常的小区)的异常贡献度，计算得到一个第三阈值，并将异常贡献度超过该第三阈值的小区(如果存在)确定为问题小区。
当然，若发现实际没有小区的异常贡献度超过第三阈值，则可认为异常是由多个小区的普遍问题引起的，并直接确定异常贡献度最大的特定个(即前第二预定位个小区)的小区(即所有小区)为问题小区，例如选取异常贡献度最大的10个小区为问题小区(即第二预定位为10位)。
在一些实施例中，第三阈值通过以下公式计算：
第三阈值＝异常贡献度为正的所有小区的异常贡献度的平均值+k*异常贡献度为正的所有小区的异常贡献度的标准差；其中，k为大于0的值。
作为一种具体方式，可求出异常贡献度为正的所有小区的异常贡献度的平均值和标准差，并以平均值加上一定倍数的标准差，作为以上第三阈值。
例如，可规定异常贡献度超过以上平均值加3倍标准差(即k＝3)的小区为问题小区。
当然，应当理解，以上第三阈值的算法只是示例性的，其具体计算方式也可不同。例如，第三阈值可就等于异常贡献度为正的所有小区的异常贡献度的平均值。
例如，以下介绍针对数值型性能指标的异常确定问题小区一个具体例子。
假设某LTE网络的子网370400在2019-12-09 21:00这个时刻，用户面上行数据量的数值型性能指标异常。
首先按以上方式计算子网各小区的异常贡献度，保留正的异常贡献度并排序，结果如下：
Figure PCTCN2021074431-appb-000006
进而，确定以上异常贡献度为正的小区的异常贡献度的平均值和标准差，即确定：
第三阈值＝平均值+3*标准差＝0.018652；
从而，可选取异常贡献度超过0.018652的小区选取为问题小区。
可见，本公开实施例中，当数值型性能指标和比率型性能指标发生异常时，确定问题小区的具体算法是不同的。
因此，参照图7，从逻辑上看，本公开实施例需要先获取子网的性能指标，以判断子网的性能指标是否发生异常；当发生异常时，则需要先判断超出第一阈值范围的性能指标是数值型性能指标还是比率型性能指标，再根据相应的方式进行处理。
其中，对应数值型性能指标和比率型性能指标的算法的不同主要包括：
(1)小区的异常贡献度计算方法不同。这是因为子网的比率型性能指标并不等于其中各小区的比率型性能指标的和，故无法将各小区的比率型性能指标相加计算。
(2)对应数值型性能指标的异常的计算不包括滤除“指标质差小区”的步骤。这是因为针对数值型性能指标的异常贡献度计算过程中，已经考虑了小区的历史性能指标(预测性能指标)，而针对比率型性能指标的异常贡献度计算过程仅考虑了异常时各小区的数据；从而当数值型性能指标的异常时，不必再另外滤除历史上性能指标较差的小区(指标质差 小区)。
可见，本公开实施例中，针对数值型性能指标和比率型性能指标，分别提出了不同的确定问题小区的具体算法，每种算法都特别适用于相应的性能指标，从而对各种性能指标，均可得到准确的问题小区。
另外，本公开实施例可完全通过自动化的方式实现，而不需要人工干预，不受人为因素的影响，速度快，智能且精准。
第二方面，参照图8，本公开实施例提供一种电子设备，其包括：
一个或多个处理器；
存储器，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现上述任意一项的识别问题小区的方法；
一个或多个I/O接口，连接在处理器与存储器之间，配置为实现处理器与存储器的信息交互。
其中，处理器为具有数据处理能力的器件，其包括但不限于中央处理器(CPU)等；存储器为具有数据存储能力的器件，其包括但不限于随机存取存储器(RAM，更具体如SDRAM、DDR等)、只读存储器(ROM)、带电可擦可编程只读存储器(EEPROM)、闪存(FLASH)；I/O接口(读写接口)连接在处理器与存储器间，能实现存储器与处理器的信息交互，其包括但不限于数据总线(Bus)等。
第三方面，参照图9，本公开实施例提供一种计算机可读介质，其上存储有计算机程序，程序被处理器执行时实现上述任意一种识别问题小区的方法。
本领域普通技术人员可以理解，上文中所公开的全部或某些步骤、系统、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。
在硬件实施方式中，在以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分；例如，一个物理组件可以具有多个功能，或者一个功能或步骤可以由若干物理组件合作执行。
某些物理组件或所有物理组件可以被实施为由处理器，如中央处理器(CPU)、数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其它数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于随机存取存储器(RAM，更具体如SDRAM、DDR等)、只读存储器(ROM)、带电可擦可编程只读存储器(EEPROM)、闪存(FLASH)或其它磁盘存储器；只读光盘(CD-ROM)、数字多功能盘(DVD)或其它光盘存储器；磁盒、磁带、磁盘存储或其它磁存储器；可以用于存储期望的信息并且可以被计算机访问的任何其它的介质。此外，本领域普通技术人员公知的是，通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其它传输机制之类的调制数据信号中的其它数据，并且可包括任何信息递送介质。
本公开实施例中，根据发生异常时子网和小区的性能指标(或者说是所有小区的参数统计量)，确定出子网各小区的异常贡献度，也就是子网各小区引起该异常的可能性。从而，相对于单纯根据子网各小区的性能指标本身确定异常贡献度的相关技术，本公开实施例的方式可根据异常贡献度更准确的确定出问题小区(也就是实际导致异常的小区)，以便后续有针对性的进行网络优化，改善用户体验。
另外，本公开实施例可完全通过自动化的方式实现，而不需要人工干预，不受人为因素的影响，速度快，智能且精准。
本公开已经公开了示例实施例，并且虽然采用了具体术语，但它们仅用于并仅应当被解释为一般说明性含义，并且不用于限制的目的。在一些实例中，对本领域技术人员显而易见的是，除非另外明确指出，否则可单独使用与特定实施例相结合描述的特征、特性和/或元素，或可与其它实施例相结合描述的特征、特性和/或元件组合使用。因此，本领域技术人员将理解，在不脱离由所附的权利要求阐明的本公开的范围的情况下，可进行各种形式和细节上的改变。

Claims (13)

  1. 一种识别问题小区的方法，包括：
    确定子网各小区的异常贡献度；
    根据子网各小区的异常贡献度，确定至少一个小区为问题小区；
    其中，
    每个所述小区的异常贡献度为子网的性能指标发生异常时，该小区的性能指标与该异常的关联程度；所述子网的性能指标发生异常为子网的性能指标超出第一阈值范围；所述子网的性能指标根据其中各小区的参数统计量确定；所述小区的性能指标根据其中的参数统计量确定。
  2. 根据权利要求1所述的方法，其中，所述第一阈值范围包括：
    第一阈值范围下限，和/或，第一阈值范围上限。
  3. 根据权利要求1所述的方法，其中，
    所述第一阈值范围是通过动态阈值检测技术确定的。
  4. 根据权利要求1所述的方法，其中，所述性能指标为比率型性能指标，所述比率型性能指标为第一参数统计量与第二参数统计量的比值；
    每个所述小区的异常贡献度表示将该小区从子网去除后，子网的性能指标相对去除前子网的性能指标向第一阈值范围内偏移的程度。
  5. 根据权利要求4所述的方法，其中，所述根据子网各小区的异常贡献度，确定至少一个小区为问题小区的步骤包括：
    将异常贡献度为正的小区降序排列得到待筛选序列，确定N为1；
    确定优化性能指标；所述优化性能指标为子网的性能指标与子网的临时性能指标的差值，所述临时性能指标为去除待筛选序列中排名前N的小区后，子网中剩余小区的整体的性能指标；
    若优化性能指标处于第一阈值范围内，确定待筛选序列中排名前N的小区为候选小区；若优化性能指标超出第一阈值范围，使N增大1并返回所述确定优化性能指标的步骤；
    确定至少部分候选小区为问题小区。
  6. 根据权利要求5所述的方法，其中，所述确定至少部分候选小区为问题小区的步骤包括：
    确定每个所述候选小区的多个历史性能指标；每个所述历史性能指标为该小区在子网的性能指标发生异常前的一个历史时刻的性能指标；
    确定每个所述候选小区的历史异常比例；每个所述小区的历史异常比例为该小区的所有历史性能指标中超出第一阈值范围的历史性能指标所占的比例；
    将历史异常比例高于第二阈值的小区从候选小区中去除。
  7. 根据权利要求6所述的方法，其中，在所述将历史异常比例高于第二阈值的小区从候选小区中去除的步骤后，还包括：
    若存在剩余的候选小区，确定所有剩余的候选小区为问题小区；
    若无剩余的候选小区，确定异常贡献度最大的前第一预定位的小区为问题小区。
  8. 根据权利要求1所述的方法，其中，所述性能指标为数值型性能指标，所述数值型性能指标为参数统计量；
    每个所述小区的异常贡献度根据该小区的性能指标偏离值与子网的性能指标偏离值的比值确定；
    其中，每个所述小区的性能指标偏离值为该小区的性能指标与预测性能指标的差，所述子网的性能指标偏离值为子网的性能指标与预测性能指标的差，每个所述小区的预测性能指标为预测得到的该小区的性能指标的正常值，所述子网的预测性能指标为其中各小区的预测性能指标的和。
  9. 根据权利要求8所述的方法，其中，
    每个所述小区的预测性能指标为该小区的性能指标在子网的性能指标发生异常前的预定时间内的平均值。
  10. 根据权利要求8所述的方法，其中，所述根据子网各小区的异常贡献度，确定至少一个小区为问题小区的步骤包括：
    根据所述异常贡献度为正的所有小区的异常贡献度，确定第三阈值，所述第三阈值为正数；
    若存在所述异常贡献度超过第三阈值的小区，确定所有异常贡献度超过第三阈值的小区为问题小区；
    若无所述异常贡献度超过第三阈值的小区，确定异常贡献度最大的前第二预定位的小区为问题小区。
  11. 根据权利要求10所述的方法，其中，所述第三阈值通过以下公式计算：
    第三阈值＝异常贡献度为正的所有小区的异常贡献度的平均值+k*异常贡献度为正的所有小区的异常贡献度的标准差；
    其中，k为大于0的值。
  12. 一种电子设备，包括：
    一个或多个处理器；
    存储器，其上存储有一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现根据权利要求1至11中任意一项所述的识别问题小区的方法；
    一个或多个I/O接口，连接在所述处理器与存储器之间，配置为实现所述处理器与存储器的信息交互。
  13. 一种计算机可读介质，其上存储有计算机程序，所述程序被处理器执行时实现根据权利要求1至11中任意一项所述的识别问题小区的方法。
PCT/CN2021/074431 2020-04-10 2021-01-29 识别问题小区的方法、电子设备、计算机可读介质 WO2021203810A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2022560979A JP7474864B2 (ja) 2020-04-10 2021-01-29 故障セルの識別方法、電子機器、及びコンピュータ読み取り可能な媒体
US17/995,884 US20230130378A1 (en) 2020-04-10 2021-01-29 Method for identifying problem cell, electronic device and computer-readable medium
EP21783685.7A EP4132074A4 (en) 2020-04-10 2021-01-29 METHOD OF IDENTIFYING A PROBLEM CELL, ELECTRONIC DEVICE AND COMPUTER READABLE MEDIA

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010284448.6 2020-04-10
CN202010284448.6A CN113518373A (zh) 2020-04-10 2020-04-10 识别问题小区的方法、电子设备、计算机可读介质

Publications (1)

Publication Number Publication Date
WO2021203810A1 true WO2021203810A1 (zh) 2021-10-14

Family

ID=78022615

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/074431 WO2021203810A1 (zh) 2020-04-10 2021-01-29 识别问题小区的方法、电子设备、计算机可读介质

Country Status (5)

Country Link
US (1) US20230130378A1 (zh)
EP (1) EP4132074A4 (zh)
JP (1) JP7474864B2 (zh)
CN (1) CN113518373A (zh)
WO (1) WO2021203810A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114339852B (zh) * 2021-12-31 2023-08-01 中国联合网络通信集团有限公司 小区故障分析方法、装置、电子设备及存储介质
CN114615689A (zh) * 2022-04-13 2022-06-10 浪潮通信信息系统有限公司 网络优化方法及装置
TWI806573B (zh) * 2022-04-27 2023-06-21 台灣大哥大股份有限公司 偵測及抑制行動網路干擾的方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011070492A (ja) * 2009-09-28 2011-04-07 Nec Corp 防災システムおよび防災システムの制御方法
CN104469833A (zh) * 2015-01-08 2015-03-25 西安电子科技大学 一种基于用户感知的异构网络运维管理方法
CN105517021A (zh) * 2016-01-22 2016-04-20 安徽电信工程有限责任公司 基于异常小区的移动通信网络用户感知主动优化分析方法
CN109951856A (zh) * 2017-12-20 2019-06-28 中国电信股份有限公司 网元状态的检测方法、装置以及计算机可读存储介质
CN109963301A (zh) * 2017-12-22 2019-07-02 中国移动通信集团北京有限公司 一种网络结构干扰的分析方法及装置
CN109995599A (zh) * 2019-04-28 2019-07-09 武汉烽火技术服务有限公司 一种网络性能异常的智能告警方法
CN110635952A (zh) * 2019-10-14 2019-12-31 中兴通讯股份有限公司 通信系统的故障根因分析方法、系统和计算机存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4730532B2 (ja) 2005-09-20 2011-07-20 日本電気株式会社 無線アクセスシステム、ネットワーク管理装置、プログラム、および品質管理方法
US7933214B2 (en) 2008-08-29 2011-04-26 Telefonaktiebolaget Lm Ericsson Fault detection in a transport network
JP5601585B2 (ja) 2009-02-03 2014-10-08 日本電気株式会社 通信システム、情報収集制御装置、情報収集制御プログラム、及び情報測定制御方法
EP2997756B1 (en) 2013-05-14 2017-12-06 Nokia Solutions and Networks Oy Method and network device for cell anomaly detection
EP3525507B1 (en) * 2018-02-07 2021-04-21 Rohde & Schwarz GmbH & Co. KG Method and test system for mobile network testing as well as prediction system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011070492A (ja) * 2009-09-28 2011-04-07 Nec Corp 防災システムおよび防災システムの制御方法
CN104469833A (zh) * 2015-01-08 2015-03-25 西安电子科技大学 一种基于用户感知的异构网络运维管理方法
CN105517021A (zh) * 2016-01-22 2016-04-20 安徽电信工程有限责任公司 基于异常小区的移动通信网络用户感知主动优化分析方法
CN109951856A (zh) * 2017-12-20 2019-06-28 中国电信股份有限公司 网元状态的检测方法、装置以及计算机可读存储介质
CN109963301A (zh) * 2017-12-22 2019-07-02 中国移动通信集团北京有限公司 一种网络结构干扰的分析方法及装置
CN109995599A (zh) * 2019-04-28 2019-07-09 武汉烽火技术服务有限公司 一种网络性能异常的智能告警方法
CN110635952A (zh) * 2019-10-14 2019-12-31 中兴通讯股份有限公司 通信系统的故障根因分析方法、系统和计算机存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4132074A4 *

Also Published As

Publication number Publication date
JP7474864B2 (ja) 2024-04-25
EP4132074A1 (en) 2023-02-08
EP4132074A4 (en) 2023-08-09
JP2023520801A (ja) 2023-05-19
US20230130378A1 (en) 2023-04-27
CN113518373A (zh) 2021-10-19

Similar Documents

Publication Publication Date Title
WO2021203810A1 (zh) 识别问题小区的方法、电子设备、计算机可读介质
CN107204894B (zh) 网络业务质量的监控方法及装置
US10548032B2 (en) Network anomaly detection and network performance status determination
US9503919B2 (en) Wireless communication network using multiple key performance indicators and deviations therefrom
CN111126824B (zh) 多指标关联模型训练方法及多指标异常分析方法
CN109195170A (zh) 小区扩容方法、装置及存储介质
CN111263403B (zh) Lte网络下多频小区间负荷均衡方法和装置
US9596609B2 (en) Methods and systems for determining radio coverage in wireless communication networks
US9030983B2 (en) Power saving method and device for a cellular radio system
CN107438264B (zh) 小区性能分析方法及装置
US10517007B2 (en) Received signal strength based interferer classification of cellular network cells
CN114978956B (zh) 智慧城市网络设备性能异常突变点检测方法及装置
CN109981234A (zh) 双载波和载波聚合的自适应调整方法、装置、设备及介质
CN111954224B (zh) 一种同频干扰的处理方法及装置
CN114071525B (zh) 基站优化次序确定方法、装置及存储介质
CN113673822B (zh) 一种弹性调度方法及系统
US9451482B2 (en) Method for tracking and utilizing operational run time of a network element
CN112512057B (zh) 网络切片异常识别方法、装置、设备及计算机存储介质
EP3849231A1 (en) Configuration of a communication network
WO2020215282A1 (en) Method and apparatus for evaluate data traffic depressed by radio issues
CN115442832B (zh) 投诉问题定位方法、装置及电子设备
CN116319251A (zh) 无线侧网络根因定位方法、运行控制装置及存储介质
CN109993388B (zh) 劣化小区主因判断方法、装置、设备及介质
CN114630365B (zh) 小区健康状态检测的方法及装置
CN111385814A (zh) 小区网络负荷的评估方法、装置、设备及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21783685

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022560979

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2021783685

Country of ref document: EP

Effective date: 20221102

NENP Non-entry into the national phase

Ref country code: DE