Base station network quitting method and device and readable storage medium

Abstract

The invention provides a base station network quitting method and device and a readable storage medium. The method comprises the following steps: S1, determining a coverage range of a plurality of base stations to be screened in a target area and user resident position data; s2, importing the coverage ranges of the plurality of base stations to be screened and the user resident position data into a GIS system, and constructing a geography model based on the base station coverage and the user resident position; s3, based on the geography model, calculating an influence score of each base station to be screened by taking the optimal geographic coverage and the minimum influence as targets; and S4, selecting the to-be-screened base station with the lowest influence score as an optimal network quitting site, and completing network quitting. The method, the device and the medium can solve the problems that low-efficiency or redundant base stations cannot be accurately positioned by the existing base station network quitting method, and signal blind areas are easy to appear after network quitting operation due to lack of scientific evaluation on the coverage capability of the base stations in a network quitting sequence decision-making process; and the signal quality and the network service experience of the user are severely influenced.

Description

Technical Field

[0001] The present invention relates to the field of network technologies, and in particular, to a base station decommissioning method, apparatus, and readable storage medium. Background Art

[0002] Focusing on building a high-quality communication network with leading perception and perfect coverage, as the scale of 4G and 5G networks continues to expand and various types of mobile communication devices are increasing, the need for cost reduction and efficiency improvement in mobile networks has become increasingly urgent. Therefore, operators closely follow the development trend of the communication industry, and in combination with the actual situation of network coverage, promote the work of streamlining and decommissioning old networks and reducing frequencies in batches in appropriate areas. For example, gradually implement the streamlining and decommissioning of 3G networks; in the future, as the scale of 5G and 6G networks expands and technology iterates, similar decommissioning and frequency reduction operations will also be carried out on the replaced networks (such as 4G) to reduce network complexity and cut operation and maintenance costs.

[0003] In the refined streamlining process of old networks, it is necessary to make decisions according to the time and comprehensively take multiple measures such as reducing equipment, reducing frequencies, reducing cells, and reducing stations to achieve single-frequencyization of the entire network and gradually promote the decommissioning work.

[0004] However, the existing base station decommissioning methods have serious defects in the base station evaluation and screening mechanism and cannot accurately locate low-efficiency or redundant base stations. At the same time, due to the lack of scientific evaluation of the base station coverage ability in the process of making decommissioning sequence decisions, signal blind spots are likely to occur after decommissioning operations, which will seriously affect the signal quality of users and the network service experience. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a base station decommissioning method, apparatus, and readable storage medium for the above-mentioned deficiencies of the existing technology, so as to solve the problems that the existing base station decommissioning methods cannot accurately locate low-efficiency or redundant base stations, and due to the lack of scientific evaluation of the base station coverage ability in the process of making decommissioning sequence decisions, signal blind spots are likely to occur after decommissioning operations, which will seriously affect the signal quality of users and the network service experience.

[0006] In a first aspect, the present invention provides a base station decommissioning method, and the method includes:

[0007] S1, determining the coverage ranges of multiple base stations to be screened in a target area and user resident location data;

[0008] S2, importing the coverage ranges of the multiple base stations to be screened and the user resident location data into a Geographic Information System (GIS) to construct a geographical model based on base station coverage and user resident locations;

[0009] S3, based on the geographic model, with the goal of optimal geographic coverage and minimized impact, calculating the impact score of each base station to be screened;

[0010] S4, selecting the to-be-screened base station with the lowest impact score as the optimal de-networking site, and completing the de-networking;

[0011] S5, determine whether the number of de-networked base stations has reached the preset total target number of de-networked sites. If so, end this process. If not, remove the current de-networked base station from the multiple base stations to be screened, and return to step S1.

[0012] Further, the determining of the coverage ranges of the multiple base stations to be screened in the target area specifically includes:

[0013] Establishing a coverage model for each of the base stations to be screened according to the base station basic information of the plurality of base stations to be screened;

[0014] Performing outlier detection on the pre-collected measurement report MR data, and removing outliers in the MR data;

[0015] The coverage model is corrected using the received signal strength indication RSSI and the signal to interference plus noise ratio SINR in the MR data after the outliers are removed, and the coverage ranges of the multiple base stations to be screened are determined.

[0016] Furthermore, before establishing a coverage model for each of the base stations to be screened according to the base station basic information of the multiple base stations to be screened, the method further includes:

[0017] Collecting the MR data and user resident location data in the target area, and basic base station information of a plurality of base stations to be screened;

[0018] Mapping the MR data to the GIS system according to a preset data model;

[0019] The base station basic information is standardized, and multiple base stations to be screened in the GIS system are marked according to the standardized base station basic information.

[0020] Furthermore, the base station basic information includes geographical location, transmission power, transmission antenna gain, and receiving antenna gain, and establishing a coverage model for each base station to be screened based on the base station basic information of the plurality of base stations to be screened specifically includes:

[0021] Selecting a corresponding propagation model for each base station to be screened according to the environmental characteristics corresponding to the geographical location of each base station to be screened;

[0022] Calculate the received signal strength of the signal transmitted outward by each base station to be screened at different distances according to the selected propagation model, the transmit power, transmit antenna gain, and receive antenna gain of each base station to be screened;

[0023] Obtain the corresponding coverage model based on the received signal strength of the signal transmitted outward by each base station to be screened at different distances.

[0024] Further, based on the geographical model, with the goal of optimal geographical coverage and minimizing impact, calculate the impact score of each base station to be screened, specifically including:

[0025] Based on the geographical model, with the goal of optimal geographical coverage and minimizing impact, weigh the user coverage requirements and the impact of base station decommissioning through a genetic multi-objective optimization algorithm, and comprehensively consider the coverage rate and the number of affected users to calculate the impact score of each base station to be screened.

[0026] Further, the comprehensive consideration of the coverage rate and the number of affected users to calculate the impact score of each base station to be screened specifically includes:

[0027] Calculate the impact score of each base station to be screened according to the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station.

[0028] Further, the calculation of the impact score of each base station to be screened according to the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station specifically includes:

[0029] Obtain the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station;

[0030] Perform normalization processing on the coverage rate reduction value and the number of affected users to obtain the normalized coverage rate reduction value and the number of affected users;

[0031] Calculate the impact score of each base station to be screened according to the following formula:

[0032] impact_score = W1 * normalized_coverage_decrease + W2 *

[0033] normalized_affected_users

[0034] Wherein, normalized_coverage_decrease represents the decreased value of the coverage rate after normalization, normalized_affected_users represents the number of affected users after normalization, W1 and W2 respectively represent the weights of the decreased value of the coverage rate and the number of affected users after normalization, and impact_score represents the impact score.

[0035] In a second aspect, the present invention provides a base station decommissioning device, and the device includes:

[0036] A data determination module, configured to determine the coverage range of multiple base stations to be screened in a target area and the user resident location data;

[0037] A geographical model construction module, connected to the data determination module, configured to import the coverage range of multiple base stations to be screened and the user resident location data into a Geographic Information System (GIS) system to construct a geographical model based on the base station coverage and the user resident location;

[0038] An impact score calculation module, connected to the geographical model construction module, configured to calculate the impact score of each base station to be screened based on the geographical model with the goal of optimal geographical coverage and minimization of impact;

[0039] An optimal decommissioning module, connected to the impact score calculation module, configured to select the base station to be screened with the lowest impact score as the optimal decommissioning site and complete the decommissioning;

[0040] A loop iteration module, connected to the optimal decommissioning module, configured to determine whether the number of decommissioned base stations has reached a preset total target number of decommissioned sites. If so, end this process. If not, remove the currently decommissioned base station from multiple base stations to be screened and return to execute the steps of the data determination module.

[0041] In a third aspect, the present invention provides a base station decommissioning device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to implement the base station decommissioning method described in the first aspect above.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the base station decommissioning method described in the first aspect above.

[0043] The base station network retirement method, device and readable storage medium provided by the present invention. First, determine the coverage ranges of multiple base stations to be screened in the target area and the user's permanent location data; and import the coverage ranges of the multiple base stations to be screened and the user's permanent location data into a Geographic Information System (GIS) to construct a geographical model based on base station coverage and user permanent locations; then, based on the geographical model, with the goal of optimal geographical coverage and minimal impact, calculate the impact score of each base station to be screened; then select the base station to be screened with the lowest impact score as the optimal network retirement site and complete the network retirement; finally, determine whether the number of retired base stations has reached the preset total target number of retired sites. If so, end this process. If not, remove the currently retired base station from the multiple base stations to be screened and return to execute the step of determining the coverage ranges of the multiple base stations to be screened in the target area and the user's permanent location data. The present invention constructs a geographical model with the aid of GIS technology and combines a scientific impact score evaluation mechanism to accurately locate low-efficiency or redundant base stations. On the premise of ensuring basic network coverage, it can achieve the orderly network retirement of base stations and effectively avoid the generation of signal blind spots after network retirement. At the same time, the present invention can ensure that users can still obtain good signal quality and network services after network retirement, thus significantly improving user satisfaction. It solves the problems that the existing base station network retirement methods cannot accurately locate low-efficiency or redundant base stations, and due to the lack of scientific evaluation of the base station coverage ability in the network retirement order decision-making process, signal blind spots are likely to occur after network retirement operations, which seriously affects the signal quality and network service experience of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flowchart of a base station network retirement method according to Embodiment 1 of the present invention;

[0045] Figure 2 It is a flowchart of another base station network retirement method according to Embodiment 1 of the present invention;

[0046] Figure 3 It is a schematic structural diagram of a base station network retirement device according to Embodiment 2 of the present invention;

[0047] Figure 4 It is a schematic structural diagram of a base station network retirement device according to Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] To enable those skilled in the art to better understand the technical solutions of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0049] It can be understood that the specific embodiments and drawings described herein are only for explaining the present invention and are not intended to limit the present invention.

[0050] It is understood that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0051] It is understood that, for ease of description, only the parts related to the present invention are shown in the drawings of the present invention, while the parts unrelated to the present invention are not shown in the drawings.

[0052] It is understood that each unit and module involved in the embodiments of the present invention may correspond to only one entity structure, or may be composed of multiple entity structures. Alternatively, multiple units and modules may also be integrated into one entity structure.

[0053] It is understood that the terms "first", "second", etc. in the embodiments of the present invention are used to distinguish different objects, or to distinguish different processes for the same object, rather than to describe the specific order of the objects.

[0054] It is understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in an order different from that marked in the drawings.

[0055] It is understood that in the flowcharts and block diagrams of the present invention, the possible system architectures, functions, and operations of the systems, devices, equipment, and methods according to the embodiments of the present invention are shown. Among them, each block in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified function. Moreover, each block or combination of blocks in the block diagram and flowchart may be implemented by a hardware-based system for implementing the specified function, or may be implemented by a combination of hardware and computer instructions.

[0056] It is understood that the units and modules involved in the embodiments of the present invention may be implemented in software or in hardware. For example, the units and modules may be located in the processor.

[0057] Embodiment 1:

[0058] This embodiment provides a method for a base station to withdraw from the network. As Figure 1 shown, the method includes:

[0059] S1. Determine the coverage ranges of multiple base stations to be screened in the target area and the user's permanent location data.

[0060] In this embodiment, the target area refers to a specific geographical range that needs to be optimized by streamlining base stations during the decision-making process of withdrawing from the old network; the base stations to be screened refer to the candidate base stations that need to be determined whether to withdraw from the network through comprehensive evaluation during the refined streamlining process of the old network.

[0061] Optionally, the determining the coverage ranges of multiple base stations to be screened in the target area specifically includes:

[0062] Establishing a coverage model for each of the base stations to be screened according to the base station basic information of the plurality of base stations to be screened;

[0063] Performing outlier detection on pre-collected MR (Measurement Report) data to remove outliers in the MR data;

[0064] The coverage model is corrected using RSSI (Received Signal Strength Indication) and SINR (Signal to Interference plus Noise Ratio) in the MR data after outliers are removed, and the coverage ranges of the multiple base stations to be screened are determined.

[0065] In this embodiment, in order to accurately predict the actual effective coverage of multiple base stations to be screened, a coverage model is first established to preliminarily estimate the base station signal coverage area, and then outlier detection and elimination are performed for various signal-related data in MR collected within the base station coverage area, and then the coverage model is corrected using RSSI and SINR in the MR data, so that it can more accurately fit the actual signal coverage situation, thereby improving the prediction accuracy of the base station signal coverage range and quality. Among them, in outlier detection, if the absolute difference between a certain measurement value and the average value is greater than 2 times the standard deviation, the measurement value can be considered to be an outlier, and those that meet the conditions will be eliminated.

[0066] Optionally, before establishing a coverage model for each of the base stations to be screened according to the base station basic information of the multiple base stations to be screened, the method further includes:

[0067] Collecting the MR data and user resident location data in the target area, and basic base station information of a plurality of base stations to be screened;

[0068] Mapping the MR data to the GIS system according to a preset data model;

[0069] The base station basic information is standardized, and multiple base stations to be screened in the GIS system are marked according to the standardized base station basic information.

[0070] In this embodiment, the collected MR data includes information such as base station cell coding, user location, RSSI, SINR, timestamp, etc. By analyzing the user location and timestamp in the MR data and aggregating them in the time dimension, user resident location data is generated. The basic information of the base station includes: data such as the geographical location (latitude and longitude), height, coverage radius, transmission power, transmission antenna gain, receiving antenna gain, base station type, and the number of currently connected users of the base station.

[0071] In this embodiment, the preset data model endows semantics to the MR data, enabling the GIS system to understand the meaning of the data, and matching and converting the location information collected in the MR data with the map projection, coordinate system, etc. in the GIS system. In this way, the MR data can be accurately located and displayed on the map of the GIS system, allowing users to intuitively see the geographical space location corresponding to the MR data and facilitating analysis in combination with the geographical environment.

[0072] In this embodiment, after mapping the collected MR data to the GIS system according to the data model, first, standardize the collected basic information of the base station to ensure consistent data formats, and then combine the processed basic information of the base station with the GIS. By marking other basic information such as the base station name and attributes, and analyzing the relationship between its coverage area and the surrounding environment, confirm and mark the precise location of the base station, making the information about the base station more complete and rich.

[0073] Optionally, establishing a coverage model for each of the to-be-screened base stations according to the basic information of the to-be-screened base stations specifically includes:

[0074] Selecting a corresponding propagation model for each of the to-be-screened base stations according to the environmental characteristics corresponding to the geographical location of each of the to-be-screened base stations;

[0075] Calculating the received signal strength of the signal transmitted outward by each of the to-be-screened base stations at different distances according to the selected propagation model and the transmission power, transmission antenna gain, and receiving antenna gain of each of the to-be-screened base stations;

[0076] Obtaining a corresponding coverage model based on the received signal strength of the signal transmitted outward by each of the to-be-screened base stations at different distances.

[0077] In this embodiment, by combining the processed basic information of the base station with the GIS, the GIS system can automatically identify the environmental characteristics (such as urban, rural, unobstructed open area, etc.) where the to-be-screened base station is located, and then select a corresponding propagation model (such as free space propagation model, Hata model, COST 231 model, ITU-R P.1546 model, etc.) for each of the to-be-screened base stations according to the environmental characteristics.

[0078] In this embodiment, according to the selected propagation model, the received signal strength of the signals transmitted outward by each base station to be screened at different distances is calculated, and the formula is as follows:

[0079] P r (d) = P t +G t +G r -L p (d)

[0080] Wherein, P r (d) represents the received signal strength (at d meters); P t represents the transmitted signal strength (base station transmit power); G t and G r respectively represent the gains of the transmitting antenna and the receiving antenna; L p (d) represents the propagation loss, which depends on the distance and environmental factors.

[0081] In this embodiment, the coverage model essentially uses features such as base station signal strength to generate a model for predicting the coverage range of base stations.

[0082] S2. Import the coverage ranges of multiple base stations to be screened and the user's permanent location data into the Geographic Information System (GIS) to construct a geographical model based on base station coverage and user's permanent location.

[0083] In this embodiment, the user's permanent location can reflect the locations where the user has long-term and high-frequency activities, such as residential areas, office areas, etc. These areas are the places where the base stations to be retired focus on signal coverage and affect the user's communication quality experience. By importing the coverage ranges of multiple base stations to be screened and the user's permanent location data into the GIS system, a geographical model based on base station coverage and user's permanent location is constructed, and the coverage range of the base stations is visualized in the GIS system to generate a graph representing the range.

[0084] S3. Based on the geographical model, with the goal of optimal geographical coverage and minimizing the impact, calculate the impact score of each base station to be screened.

[0085] In this embodiment, the goal is optimal geographical coverage and minimizing the impact. Among them, optimal geographical coverage means ensuring that the network can still provide the necessary service quality to meet the user's coverage requirements after the site is retired, and minimizing the impact means minimizing the negative impact on network services when selecting the retired site.

[0086] Optionally, the calculating the impact score of each base station to be screened based on the geographical model with the goal of optimal geographical coverage and minimizing the impact specifically includes:

[0087] Based on the geographical model, with the goal of optimal geographical coverage and minimizing impacts, the genetic multi-objective optimization algorithm is used to balance the user coverage requirements and the impacts of base station decommissioning, and the impact score of each base station to be screened is calculated by comprehensively considering the coverage rate and the number of affected users.

[0088] In this embodiment, the genetic multi-objective optimization algorithm is used to balance the user coverage requirements and the impacts of base station decommissioning, and an objective function is established: to minimize the number of affected users after decommissioning while maintaining the coverage rate higher than a certain threshold. At the same time, the corresponding constraint conditions are determined. The constraint conditions include considering the user density in the area where the users are located, ensuring that the users can still receive sufficient signal strength after decommissioning, avoiding or reducing the blind areas caused by decommissioning, etc. The impact score of each base station to be screened is calculated by comprehensively considering the coverage rate and the number of affected users.

[0089] Optionally, the calculating the impact score of each base station to be screened by comprehensively considering the coverage rate and the number of affected users specifically includes:

[0090] Calculating the impact score of each base station to be screened according to the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station.

[0091] In this embodiment, when determining the base station decommissioning plan, it is necessary to evaluate the possibility of decommissioning each base station to be screened. To simulate the real decision-making scenario, each base station to be screened is regarded as a proposed decommissioned base station for in-depth analysis. A proposed decommissioned base station, that is, a base station currently being evaluated for decommissioning, analyzes its coverage rate reduction value and the number of affected users by simulating the situation after each proposed decommissioned base station is decommissioned, and then calculates the impact score to judge the feasibility of decommissioning this base station. Among them, the coverage rate reduction value is used to reflect the degree of influence of the decommissioning of this base station on the network coverage range. The number of affected users is used to reflect the total number of users whose communication quality deteriorates or who cannot use the network service normally due to the decommissioning of this base station.

[0092] Optionally, the calculating the impact score of each base station to be screened according to the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station specifically includes:

[0093] Obtaining the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station;

[0094] Performing normalization processing on the coverage rate reduction value and the number of affected users to obtain the normalized coverage rate reduction value and the number of affected users;

[0095] Calculating the impact score of each base station to be screened according to the following formula:

[0096] impact_score = W1 * normalized_coverage_decrease + W2 *

[0097] normalized_affected_users

[0098] Wherein, normalized_coverage_decrease represents the decreased value of the coverage rate after normalization processing, normalized_affected_users represents the number of affected users after normalization processing, W1 and W2 respectively represent the weights of the decreased value of the coverage rate and the number of affected users after normalization processing, and impact_score represents the impact score.

[0099] In this embodiment, the normalization formula: (original data - minimum value) / (maximum value - minimum value) can be adopted to perform normalization processing on the decreased value of the coverage rate and the number of affected users when each base station to be screened is used as the base station to be retired, so as to map data with different dimensions to the interval [0, 1], making different types of data comparable in subsequent calculation of the impact score.

[0100] In this embodiment, the impact score is calculated in a weighted manner, corresponding weights are assigned to the decreased value of the coverage rate and the number of affected users respectively (the weights are set according to the actual network situation and service requirements), and the two indicators are quantified and then comprehensively calculated. The impact score calculated in this way can intuitively and quantitatively reflect the comprehensive impact of the retirement of each base station to be screened on the overall network performance, and then judge the feasibility of the retirement of this base station based on this, providing strong support for finally determining a reasonable base station retirement plan.

[0101] S4. Select the base station to be screened with the lowest impact score as the optimal base station to be retired, and complete the retirement;

[0102] S5. Judge whether the number of retired base stations has reached the total target number of the preset exit sites. If so, end this process; if not, remove the currently retired base station from the multiple base stations to be screened, and return to execute step S1.

[0103] In this embodiment, the base station to be screened with the lowest impact score is the base station to be screened with the least impact on network coverage and service quality when it is retired, so it is retired first. After each optimal base station to be retired is retired, the coverage range and user impact of the remaining base stations will be re-evaluated. The information of the retired base stations can be used in each iteration to update the user's resident base station cell and the coverage range of the base station cell, and recalculate the impact score. Verify and continuously screen according to the above steps until the total target number of the final exit sites is reached.

[0104] In a specific embodiment, the general idea of the base station retirement method is as follows:

[0105] 1. Based on the collection of base station location data (latitude and longitude data of each base station, height information of the base station (such as the height of the antenna), etc.), combined with topographical and obstacle information that significantly affects signal propagation around the base station: such as the height and structure of surrounding buildings, altitude changes, etc., a coverage model based on the geographical location of the base station is constructed;

[0106] 2. Based on the collection of user MR data, the data includes cell information, location information (longitude, latitude), signal strength (RSSI), etc. of the users using the base station. Through comprehensive analysis and model calculation of the MR data, the cell coverage range of the base station can be measured more accurately.

[0107] 3. Obtain the user distribution related to the base station according to the user's permanent location, and associate the user distribution data with the base station coverage area.

[0108] 4. Score according to various factors such as the coverage area and user density of the base station. Sort all base stations based on the calculated comprehensive score to determine the only optimal base station;

[0109] 5. After the optimal selected base station retires, the following changing factors need to be considered:

[0110] (1) As some base stations retire, the network environment will change. For example, the user distribution will be readjusted due to the withdrawal of the base station. Users originally on the edge of the coverage of the optimal base station may be assigned to the coverage range of other base stations, resulting in changes in factors such as the user density of other base stations. At the same time, the signal propagation situation of the remaining base stations may also change due to the influence of the retired base station, such as the change of signal interference situation, which makes the previous scoring and ranking no longer fully applicable.

[0111] (2) The retirement of a base station may change the load of surrounding base stations. A base station that was not originally optimal may have its coverage range, cooperation with other base stations, etc. optimized after the retirement of a certain base station, thus becoming the new optimal choice. If only the initial ranking is used to select the retired base station, this dynamic interaction between base stations may be ignored, resulting in unreasonable subsequent retirement selection and affecting the overall network performance.

[0112] (3) After each determination of a base station to retire, the total number of target sites to be exited will decrease accordingly, and the network service requirements that the remaining base stations need to bear will also change. This means that when selecting the next base station to retire, it is necessary to comprehensively consider the new goals and the current network situation, and re-evaluate the comprehensive score of each base station to ensure that when the total number of target sites to be exited is finally reached, the network can still maintain good performance and service quality.

[0113] Therefore, it is necessary to re-determine the second optimizable site to be retired according to the data after excluding the deactivated base stations, following the above steps repeatedly until the total target number of sites to be retired is reached.

[0114] Based on the above overall idea, taking the orderly retirement of 3G base stations as an example, as Figure 2 shown, the method for retiring base stations may include the following steps:

[0115] I. Collection of MR data, user resident location data, and base station basic information data based on geographic information

[0116] (1). MR data collection

[0117] The mobile application of the operator is equipped with a user feedback function, allowing users to automatically obtain their locations through GPS (Global Positioning System), helping users quickly report network problems such as signal strength at their locations. The MR data involved in this step mainly focuses on information such as the location of the user and the corresponding base station cell code and signal strength received, and the user judges the area range that can be covered by the base station.

[0118] The following are the specific contents of the operator's MR data and its collection method:

[0119] The main components of MR data: including signal strength and coverage range, reflecting the effective area covered by the base station; the statistical data of the number of users in specific geographical grids, reflecting the resource utilization efficiency within the coverage range; the time record of collection, judging information such as faults according to the time continuity of data collection or whether there are interruptions.

[0120] Collection methods and steps: Through network management software, such as OSS (Operation Support System) / BSS (Business Support System) systems, automatically collect and integrate the intensity, location, and base station code data generated by the above MR. Then use geographic information system (GIS) tools to integrate terrain and environmental data, and map the collected MR data to the GIS system according to the data model. Specifically, the following work is completed:

[0121] (1) The originally possibly disorderly MR data can be stored and managed in the structure of 50m*50m grids, ensuring the orderliness of the data in the GIS system, facilitating subsequent query, analysis, and processing.

[0122] (2) Match and convert the location information collected from the MR data (e.g., the longitude and latitude of the collection device, the location of the scanned area in the geospatial space, etc.) with the map projection, coordinate system, etc. in the GIS system. In this way, the MR data can be accurately located and displayed on the map of the GIS system, enabling users to intuitively view the geospatial location corresponding to the MR data and facilitating analysis in combination with the geographical environment.

[0123] (3) The data model endows the MR data with semantics, enabling the GIS system to understand the meaning of the data. It defines the meaning represented by each field, attribute, and value of the data. Through this semantic definition, the GIS system can perform meaningful queries, classifications, and analyses on the MR data, ensuring a consistent understanding of the meaning of the data when using and processing it.

[0124] Among them, after mapping the collected MR data to the GIS system according to the data model, the content finally displayed by the GIS system usually includes the following aspects:

[0125] (1) Spatial location information: Based on the map, display the specific locations of the collection points related to the MR data, enabling users to intuitively understand the distribution of the data collection locations.

[0126] (2) Attribute information: In addition to spatial and visualization content, detailed attribute information related to the MR data will also be displayed. The attribute information includes the user's terminal used, traffic volume, whether it supports the volte (Voice over Long-Term Evolution) service, etc. This attribute information is usually presented in the form of a table, and users can view the detailed information by clicking on the relevant points or areas on the map.

[0127] (3) The GIS system can analyze based on the mapped MR data to generate corresponding analysis results of the base station coverage area, user aggregation degree, user change trend chart, etc., showing the variation laws of the data over time and space. Analyze and display the correlation between them to provide a more comprehensive basis for decision-making.

[0128] (2) Collection of user's resident location data

[0129] The operator collects and analyzes the activity patterns of users, and gathers trend data on the users' permanent locations (usually the permanent locations of each user over a period of time, such as a week or a month): extracts the user permanent location data for different time periods, and identifies the impact of seasonal changes or specific events (such as holidays, events, etc.) on user mobility. Identifies the peak (such as the office area on weekdays, the residence during rest time) and trough (such as shopping, entertainment) periods of the user's permanent location. By aggregating the user permanent location data, identifies locations with high network demand (such as commercial areas, schools, supermarkets, etc.), analyzes the changes in the user's permanent location, and identifies the long-term trends in user migration, providing a basis for determining the locations where users often use network services.

[0130] (III). Collection of Base Station Basic Information

[0131] 1. The base station basic information includes: location data such as the longitude, latitude, height, geographical coordinates, and coverage radius of the base station; base station types (such as macro base stations, micro base stations, and pico base stations, etc.); the frequency bands and systems used by the base station (such as 2G, 3G, 4G, and 5G, etc.); the signal transmission power and antenna gain of the base station; network load information such as the number of currently connected users, data traffic, and processing capacity.

[0132] 2. The collection methods include: on-site inspection, manually recording the basic information of the base station, including its geographical location, equipment status, and surrounding environment; during the installation and configuration of the base station, recording the equipment information and parameter settings; automatically collecting the operation status and performance data of the base station through the Operation Support System (OSS) and Business Support System (BSS), including traffic monitoring, fault records, and user connection situations.

[0133] 3. Data processing and analysis: Standardize the collected base station basic information to ensure consistent data formats for convenient subsequent analysis and storage. Combine the processed base station basic information with GIS, mark other basic information such as the base station name and attributes, and analyze the relationship between its coverage area and the surrounding environment to confirm and mark the precise location of the base station, making the information about the base station more complete and rich. At the same time, store the base station information in the GIS database for convenient centralized management and analysis.

[0134] II. Predict the Base Station Coverage Range Based on MR Data, Base Station Basic Information, and User Permanent Location

[0135] To accurately predict the actual effective coverage range of a base station and provide a basis for 3G streamlining, a coverage model is established based on the basic information of the base station (such as transmission power, antenna direction, height, etc.) to initially estimate the signal coverage area of the base station; at the same time, MR data (measurement report) is used to obtain the signal quality and neighboring base station conditions of users at different locations to reflect the actual coverage situation; finally, the user's permanent location is introduced to identify the main activity and stay areas of the users, and the coverage effects of these areas are analyzed and optimized key points.

[0136] 1. The influence of different environments on signal propagation varies greatly. For example, in the city center, with high-rise buildings standing in great numbers, signals will be subject to a large amount of reflection, refraction, and diffraction, while in open rural areas, signal propagation is relatively direct and mainly affected by distance and terrain. Selecting a propagation model suitable for a specific environment for different base stations can fully consider various characteristics and influencing factors of signal propagation in that environment, so as to more accurately predict key indicators such as signal strength and coverage range and provide a reliable basis for the base station coverage range. Select the signal propagation model according to the environmental characteristics (such as Hata model, COST 231 model, etc.) as follows:

[0137] 1.1 Free space propagation model: Applicable to open areas without obstacles. The basic principle is that the signal attenuates as the distance increases.

[0138] 1.2 Hata model: Commonly used in urban, suburban, and rural areas, which can better consider the influence of buildings and other obstacles.

[0139] 1.3 COST-231 model: An extension of the Hata model, applicable to scenarios with higher frequencies and different terrain conditions.

[0140] 1.4 ITU-R P.1546 model: Applicable to long-distance coverage calculations, especially under complex environmental conditions.

[0141] Ensure that the model is applicable to the current geographical and building environment. Input the corresponding values according to the specific parameters of the base station to calculate the signal propagation range.

[0142] 2. Calculate the cell coverage range of the base station based on signal propagation calculations and MR data analysis.

[0143] According to the selected propagation model, calculate the intensity attenuation of the signal transmitted outward by the base station to be streamlined at different distances. Usually, the formula for signal strength is used:

[0144] P r (d)=P t +G t +G r -L p (d)

[0145] Among them, P r (d) represents the received signal strength (at d meters); P t represents the transmitted signal strength (base station transmission power); G t and G r respectively represent the gains of the transmitting antenna and the receiving antenna; L p (d) represents the propagation loss, which depends on the distance and environmental factors.

[0146] 2.1. According to the collected MR data (such as the RSSI and SINR data provided by users), for various signal-related data in the MR within the base station coverage area, perform outlier detection and elimination. The data that requires outlier detection is as follows:

[0147] (1) Signal strength data: Such as the RSSI value, which can reflect the received strength of the base station signal at different positions. If the RSSI value in a certain area is significantly higher or lower than the average value of the area, there may be abnormal situations such as signal interference, base station failure, or the influence of special terrain.

[0148] (2) Signal quality data: For example, the SINR value, which can reflect the degree of signal interference. If there are concentrated data points with extremely low SINR values, it may mean that there are serious interference sources in this area, affecting the accuracy of the collected data.

[0149] (3) User location data: The location information uploaded by the user equipment, combined with the signal data, can analyze the relationship between user distribution and signal coverage. If it is found that a large number of users are far from their resident areas, it may be that the GPS data reported by the users is incorrect.

[0150] (4) Other MR data: Such as data like TA (Timing Advance), etc., which can assist in judging the distance between the user and the base station. If there are concentrated points with abnormal TA values, it may indicate that the timing advance setting of the base station is unreasonable or there are problems such as signal reflection.

[0151] Through spatial discrete value detection, outliers or unusual concentrated data points in the coverage area can be identified and analyzed. Commonly used methods include distance-based, density-based, and statistical detection methods, etc. In this embodiment, outlier detection (Outlier Detection) is preferably used to identify points that are significantly different from the surrounding points as outliers for elimination. The method used is to calculate the mean and standard deviation of the measured values through the postgis software and detect outliers according to the set threshold.

[0152] WITH stats AS(

[0153] SELECT AVG(measure_value)AS avg_value,

[0154] STDDEV(measure_value) AS stddev_value

[0155] FROM spatial_data

[0156] ) SELECT id, measure_value FROM spatial_data, stats WHERE abs(measure_value - avg_value) > 2 * stddev_value; -- Set the threshold to the mean ± 2 standard deviations

[0157] 2.2. Calibrate the coverage model, optimize and adjust the model parameters to improve the prediction accuracy.

[0158] In the process of coverage range prediction, first use the above propagation model formula and the corresponding propagation model parameters. Based on the MR data that has undergone outlier detection, use the propagation law formula to predict the base station coverage range in a specific environment. This coverage model essentially uses features such as base station signal strength to generate a model for predicting the base station coverage range. The steps are as follows:

[0159] (1) First, select a suitable propagation model according to the environmental characteristics and frequency band of the target area. For example, in an urban macrocell environment, the Okumura-Hata model can be selected;

[0160] Collect relevant parameter data, including the operating frequency of the base station, antenna height, mobile station antenna height (usually taking the average value), and environmental information of the target area, etc.; determine the minimum received signal strength threshold that can ensure communication quality, and this threshold is usually determined according to specific communication standards and service requirements.

[0161] (2) Substitute the collected parameters and threshold into the propagation model formula, calculate the path loss at different distances d, and then, according to the transmit power and the received signal strength threshold, combined with the path loss formula, use an iterative calculation method to solve the maximum distance that satisfies. This distance is the theoretical coverage radius of the base station in this environment.

[0162] (3) In the actual environment, factors such as terrain, landform, and building distribution will affect signal propagation. Adjust the prediction results empirically according to the actual environmental factor adjustment situation. For example, when encountering obstacles such as mountains and large buildings, the coverage range can be appropriately reduced; in open areas, the coverage range can be appropriately increased.

[0163] It should be noted that in the application of the present invention, the propagation model mainly focuses on the theoretical description of the signal propagation mechanism, and on this basis, using the calibrated coverage model is more about calculating the base station coverage range from the perspective of the actual coverage effect.

[0164] The calibration coverage model mainly uses the RSSI and SINR data in the MR information. RSSI can directly reflect the strength of the received signal and obtain the actual strength of the base station signal at different positions. SINR reflects the signal quality. Combining with RSSI, it can judge the degree of interference suffered by the signal during propagation. The two provide key information for the calibration of the coverage model from different perspectives. However, in addition to these two key data, other MR information may also be used, such as TA (Timing Advance), which can reflect the distance information between the user and the base station, helping to further refine the judgment of the signal propagation distance and coverage range, making the calibration of the coverage model more accurate.

[0165] Using the collected MR information to calibrate the coverage model is actually to optimize and adjust the selected propagation model so that it can more accurately fit the actual signal coverage situation, thereby improving the prediction accuracy of the base station signal coverage range and quality.

[0166] 3. Build a geographical model based on the base station coverage and the user's permanent location

[0167] After standardizing the collected base station information in Step 1 and other work, it can ensure that various data of the base station, such as name, attributes, location, etc., are in a unified format. These data are the basis for predicting the coverage range of the base station cell and provide necessary parameters for signal strength calculation, such as the transmit power and antenna height of the base station. This helps to more accurately calculate the signal strength through the signal propagation model and then determine the assumed coverage range under a given signal acceptance threshold. In the process of combining the processed on-site measurement data of the base station with GIS, the exact location of the base station is confirmed and marked by analyzing the relationship between the coverage area and the surrounding environment. This provides accurate location information for predicting the coverage range of the base station cell, enabling the theoretical coverage range calculated based on signal strength to more accurately correspond to the actual geographical space and avoiding calculation deviations of the coverage range caused by inaccurate base station locations.

[0168] Based on the above data collection work, according to the calculation requirements of the coverage range accuracy, define the signal acceptance threshold, for example, set it to -85 dBm. In the calculated signal strength data, filter out the areas where the signal strength is greater than or equal to this threshold, and assume these areas as the coverage range of the base station. The coverage range data obtained here is the preliminary result calculated based on the signal propagation model and screened according to the threshold, which reflects the area where the base station signal can effectively cover under ideal conditions.

[0169] Use GIS tools to visually display the theoretical coverage range calculated based on the signal strength. In this process, it is necessary to import the previously calculated coverage range data (usually in the form of geographical coordinate ranges) into the GIS software. The GIS software will, based on this geographical coordinate information, identify the theoretical coverage range of the base station on the map with specific graphics (such as polygons, circles, etc.).

[0170] Meanwhile, collect data on the actual user distribution. These data generally also include geographical coordinate information and related attributes such as the number or density of users. Import the actual user distribution data into the GIS software as well and overlay it with the base station theoretical coverage range data. Through this comparison, combined with the calculation process, it is possible to intuitively see the matching degree between the base station theoretical coverage range and the actual user needs, thereby evaluating the prediction accuracy. For example, if a certain area is theoretically within the coverage range of the base station but there are very few actual user distributions, and a large number of users who can actually receive the base station are outside the predicted range, it may mean that there are unreasonable prediction configuration parameters in this area, and further parameter adjustment or separate local correction is required.

[0171] 3.1. First, import the cell coverage range of the measured base station and the user's permanent location data into the GIS system to construct a geographical model based on the base station coverage and the user's permanent location, including the base_station_coverage (base station coverage range) table and the user_locations (user location) table, which contain the following fields:

[0172] (1) The base_station_coverage (base station coverage range) table

[0173] Base station number (base_station_id): The number used to uniquely identify each base station, facilitating the association with other relevant data.

[0174] Base station name (base_station_name): The name of the base station, which is convenient for identification and management.

[0175] Latitude and longitude coordinates (latitude, longitude): Record the specific geographical location of the base station, usually including the latitude (latitude) and longitude (longitude) fields, which are used to accurately draw the base station location in the GIS system.

[0176] Coverage radius (coverage_radius): Represents the size of the base station's coverage range. The unit can be meters, kilometers, etc., and can be determined according to the signal propagation model and actual measurements.

[0177] Base station type (base_station_type): Such as macro base stations, micro base stations, pico base stations, etc. The coverage capabilities and application scenarios of different types of base stations vary.

[0178] Antenna height (antenna_height): The height of the base station antenna from the ground, which affects the signal propagation range and effect.

[0179] Transmission power (transmission_power): The magnitude of the transmission power of the base station, which has a direct impact on the coverage range.

[0180] Azimuth (azimuth): The orientation angle of the antenna, used to describe the main coverage direction of the base station signal.

[0181] Tilt angle (tilt_angle): The downward tilt angle of the antenna relative to the horizontal plane, which can adjust the signal coverage area and depth.

[0182] Operator (operator): Records the telecommunications operator to which the base station belongs.

[0183] Creation time (creation_time): Records the time when the base station data is created or entered into the system.

[0184] Update time (update_time): Records the time of the last update of the base station data to reflect changes in the base station status in a timely manner.

[0185] (2) user_locations (User location) table

[0186] User ID (user_id): A unique identifier for each user, facilitating the association with other user information.

[0187] User name (user_name): The real name or nickname of the user (if necessary).

[0188] Latitude and longitude coordinates (latitude, longitude): Records the location information of the user for positioning the user in the GIS system.

[0189] Location acquisition time (location_time): Records the specific time when the user location information is acquired, which can be used to analyze the user's location change pattern.

[0190] Location accuracy (location_accuracy): Represents the accuracy of the user location information, such as the accuracy range of GPS positioning, and the unit can be meters.

[0191] User type (user_type): Such as ordinary users, VIP users, etc., which can be used to distinguish the location characteristics of different types of users.

[0192] Resident flag (is_resident): Used to identify whether this location is the user's resident location, usually a boolean value (true / false).

[0193] Activity area type (activity_area_type): Such as residential area, commercial area, industrial area, etc., which can assist in analyzing the user's behavior patterns in different areas.

[0194] Associated base station number (associated_base_station_id): Records the base station number associated with the user's current location, which is used to analyze the relationship between the user and the base station.

[0195] Creation time (creation_time): Records the time when the user location data is created or entered into the system.

[0196] Update time (update_time): Records the time of the last update of the user location data to track changes in the user's location.

[0197] 3.2 Adjust the predicted base station coverage area in combination with the user's resident location

[0198] (1) Query users covered by base stations

[0199] To calculate whether a user's location is within the coverage area of a certain base station, the following query can be used:

[0200] SELECT u.user_id,b.name FROM user_locations uJOINconv_stations b ONST_DWithin(u.location,b.location,b.coverage_radius)WHEREu.user_id=1; -- Replace with the user ID you want to query

[0201] Explanation: The ST_DWithin function is used to check whether the user's location (u.location) is within the range of the base station's coverage radius (b.coverage_radius).

[0202] (2) Query the coverage areas of all users

[0203] If you want to query all users and the base stations they cover, you can perform the following operations:

[0204] SELECT u.user_id,b.name FROM user_locations u JOIN conv_stations b ON ST_DWithin(u.location,b.location,b.coverage_radius);

[0205] (3) Optimize and correct the base station coverage area by using the association relationship between the user's resident location and the base station:

[0206] Determine the main coverage area of 3G base stations: The user's resident location can reflect the locations where the user has long-term and high-frequency activities, such as residential areas and office areas. These areas are the key signal coverage areas of the 3G base stations to be withdrawn from the network and affect the user's communication quality experience. By analyzing the user's resident location, it is possible to clarify the areas where the base station coverage areas that need to prioritize meeting the communication needs based on the user's own experience, providing a basis for correcting the determination of the accurate base station coverage area.

[0207] Optimize the coverage area judgment accuracy: By combining the user's resident location with MR information (measurement report information, including signal strength, quality, etc.) and base station information (location, transmission power, etc.), it is possible to more accurately judge the coverage of the base station signal in different areas. For example, if a certain residential area is the resident point of a large number of users, although the MR information in this area shows weak signals, it does not mean that this range is not covered by this base station. The coverage area of the base station can be adjusted accordingly to improve the coverage prediction accuracy.

[0208] (4) Visualization range

[0209] Visualize the coverage area of the base station in the GIS software and generate a graph representing the range. The following query can be used to generate the buffer zone of the base station:

[0210] SELECT name,ST_Buffer(location,coverage_radius) AS coverage_area FROM conv_stations;

[0211] (5) Further analysis

[0212] Use PostGIS to perform more complex spatial queries and analyses, such as distance calculation, spatial aggregation, etc.:

[0213] Distance calculation: ST_Distance(geomA,geomB) calculates the distance between two geometric objects.

[0214] Coverage area analysis: ST_Area(geometry) calculates the area of a polygon and can be used to analyze the total area of the coverage area.

[0215] Spatial Index: A spatial index can be created for a geographical table to improve query performance:

[0216] CREATE INDEX idx_base_stations_location ON conv_stations USING GIST(location); CREATE INDEX idx_user_locations_location ON user_locations USING GIST(location);

[0217] The above operations store the standardized base station information in the GIS database, echoing the visualization work of base station cell coverage prediction. It can visually display information such as the theoretical coverage range of base stations, actual user distribution, and the location and attributes of base stations on a map, facilitating multi-dimensional analysis and comparison.

[0218] 3.3. Data Feedback and Continuous Optimization

[0219] (1) Combine actual test feedback (such as drive test surveys, CQT tests, etc.) with coverage data to periodically correct the model.

[0220] (2) Dynamically adjust cell parameters and base station settings according to changes in user behavior to ensure continuous optimization of prediction accuracy.

[0221] (3) Estimate the effective coverage radius of each base station based on equipment testing and network design.

[0222] III. Select the optimal site for network disconnection based on whether the optimal network disconnection conditions are met

[0223] During the process of sequential selection of 3G minimalist base stations, ensuring optimal geographical coverage while selecting the optimal site for network disconnection (i.e., selecting the most optimal point for the base station to be removed during network disconnection) is a complex issue. It is necessary to consider network coverage, user requirements, and the impact on service quality. The following are the steps and methods to achieve this goal.

[0224] 1. Define the goals and constraints

[0225] (1) Goals

[0226] Optimal geographical coverage: Provide the necessary service quality to meet the coverage requirements of users.

[0227] Minimize impact: Minimize the negative impact on network services when selecting the site for network disconnection.

[0228] (2) Constraints

[0229] User density: Consider the user density in the area where the users are located.

[0230] Signal strength requirement: Ensure that users can still receive sufficient signal strength after network disconnection.

[0231] Minimize blind spots: Avoid or reduce the blind spots caused by network disconnection.

[0232] 2. Analysis methods

[0233] (1) Signal coverage analysis

[0234] First, for the base station coverage range constructed above by building a geographical model based on base station coverage and user resident locations, use tools such as PostGIS for spatial analysis.

[0235] For example, the coverage intensity of each base station for users can be calculated:

[0236] SELECT b.id AS base_station_id,

[0237] COUNT(u.id) AS covered_users FROM base_stations b JOIN user_locations u ON ST_DWithin(b.location, u.location, b.coverage_radius) GROUP BY b.id;

[0238] (2) Impact assessment

[0239] When determining the base stations to be disconnected from the network, simulate the impact after each base station is disconnected from the network, and calculate the user blind spots and service impacts in each case.

[0240]

[0241] (3) Multi-objective optimization based on coverage rate and user requirements

[0242] Use the genetic multi-objective optimization algorithm to balance the user coverage requirements and the impact of base station disconnection from the network:

[0243] Establish an objective function: Minimize the number of users affected after network disconnection, while maintaining the coverage rate higher than a certain threshold.

[0244] Constraint conditions: Include the maximum acceptable blind spots where users cannot receive network signals due to signal fading, signal strength, etc.

[0245] The following is an example using Python, which depends on the numpy and matplotlib packages (the matplotlib package can be used for visualization). Suppose our goal is to minimize two objective functions f1 and f2.

[0246]

[0247]

[0248] Using the tournament selection method:

[0249]

[0250]

[0251] Integrate the above steps and run the genetic algorithm.

[0252] population = initialize_population(POPULATION_SIZE) for generation in range(GENERATIONS):

[0253] fronts = non_dominated_sort(population) # Fitness evaluation

[0254] population = generate_new_population(population) # Generate a new generation

[0255] # Visualize the final results

[0256] objectives = np.array([objective_function(ind) for ind in population])

[0257] plt.scatter(objectives[:,0], objectives[:,1])

[0258] plt.xlabel('Objective 1')

[0259] plt.ylabel('Objective 2')

[0260] plt.title('Pareto Front')

[0261] plt.show()

[0262] IV. Select the optimal site for withdrawing the website

[0263] Select one or more optimal sites for withdrawing the network according to the analysis results and the optimized problem solution:

[0264] 1. Implementation of genetic multi-objective optimization algorithm

[0265] (1) Individual coding: Each individual represents a base station network withdrawal plan, which is represented by a binary vector. Each element of the vector corresponds to a base station. A value of 1 indicates that the base station is retained, and a value of 0 indicates that the base station is withdrawn from the network.

[0266] (2) Initialize the population: Randomly generate a certain number of individuals as the initial population.

[0267] (3) Fitness evaluation: For each individual (base station network withdrawal plan), perform the following operations:

[0268] Signal coverage analysis: Use the signal propagation model to simulate the signal coverage under this network withdrawal plan, and calculate the coverage rate and the area of blind spots. Impact assessment: Calculate the impact of this network withdrawal plan on users, such as the number of affected users and the degree of service quality degradation. According to the above analysis results, calculate the two objective function values of each individual.

[0269] (4) Non-dominated sorting: Perform non-dominated sorting on the individuals in the population, divide the individuals into different fronts, and the individuals in each front are non-dominated with each other.

[0270] (5) Selection operation: Use the tournament selection method to select excellent individuals from the population as parents.

[0271] (6) Crossover and mutation operations: Perform crossover and mutation operations on the parent individuals to generate offspring individuals.

[0272] (7) Generate a new generation of population: Combine the parent and offspring individuals, perform non-dominated sorting, and select a certain number of individuals at the front as the new generation of population.

[0273] (8) Termination condition: When the preset number of iterations is reached or other termination conditions are met, the algorithm stops.

[0274] 2. Calculate the impact score of each base station: Comprehensively consider the coverage rate and the number of users to form an impact score.

[0275] (1) Extract the Pareto front: Extract the individuals on the Pareto front from the final population. These individuals represent the optimal base station network withdrawal plans.

[0276] (2) Count the occurrence frequency of base stations: For each individual on the Pareto front, count the occurrence frequency of each base station in the network withdrawal plan. The base station with a high occurrence frequency indicates that its withdrawal has a small impact on the overall objective.

[0277] (3) Calculate the impact score: Considering factors such as the coverage range of the base station and the number of users served, calculate the impact score for each base station. For example, the following formula can be used: Impact score = w1 * (Number of users served / Total number of users) + w2 * (Coverage range / Total coverage range). Here, w1 and w2 are weight coefficients, which are adjusted according to the actual situation.

[0278] Assume there are 3 base stations, and the relevant data after network retirement is as follows:

[0279] Base station number Coverage reduction value Number of affected users 1 0.1 100 2 0.2 200 3 0.15 150

[0280] Assume we set the weight w1 of the coverage rate reduction value to 0.6 and the weight w2 of the number of affected users to 0.4. According to the impact score, the impact score of base station 2 is the highest, indicating that the network retirement of this base station has the greatest comprehensive impact on the coverage rate and the number of users. When selecting the site for network retirement, base stations with lower impact scores can be considered first.

[0281] For example, the Python code to implement the calculation of the impact score can be as follows:

[0282] import numpy as np

[0283] # Original data

[0284] coverage_decrease = np.array([0.1, 0.2, 0.15])

[0285] affected_users = np.array([100, 200, 150])

[0286] # Normalization processingdef normalize(data):

[0287] return (data - np.min(data)) / (np.max(data) - np.min(data))

[0288] normalized_coverage_decrease = normalize(coverage_decrease)

[0289] normalized_affected_users = normalize(affected_users)

[0290] # Weight

[0291] w1 = 0.6

[0292] w2 = 0.4

[0293] # Calculate the impact score

[0294] impact_score = w1 * normalized_coverage_decrease + w2 * normalized_affected_users

[0295] # Output the resultsfor i in range(len(impact_score)):

[0296] print(f"Impact score of base station {i + 1}: {impact_score[i]}")

[0297] 3. Select the base station with the lowest score as the optimal site to be retired. After each optimal site to be retired is taken out of service, the coverage of the remaining base stations and the impact on users will be re-evaluated. In each iteration, the information of the retired base stations can be used to update the cells of the base stations where users are resident and the coverage of the base station cells, and the impact score will be recalculated. Verify and continuously screen according to the above steps until the total target number of the final retired sites is reached.

[0298] For example, an example of circularly selecting the sites to be retired is as follows:

[0299] # Assume we have prepared all the necessary dataimport pandas as pd

[0300] # DataFrame of base station information

[0301] base_stations = pd.DataFrame(data) # including columns such as 'id',

[0302] 'covered_users', 'total_distance', etc.

[0303] # Set the target number of retired stations

[0304] target_retired_stations = 3 # Example target

[0305] retired_stations = [] # Remember the retired base stations

[0306] retired_count = 0

[0307] while retired_count < target_retired_stations:

[0308] # Calculate the impact score of each base station (the scoring logic can be customized)

[0309] base_stations['impact_score'] =

[0310] base_stations['covered_users'] / base_stations['total_distance']

[0311] # Select the base station with the lowest impact score (i.e., the base station to be retired first)

[0312] station_to_retire =

[0313] base_stations.loc[base_stations['impact_score'].idxmin()]

[0314] # Record the retired base station

[0315] retired_stations.append(station_to_retire['id'])

[0316] # Remove the retired base station from the original DataFrame to ensure it won't be selected repeatedly

[0317] base_stations = base_stations[base_stations['id']!=

[0318] station_to_retire['id']]

[0319] # Update the retired count

[0320] retired_count += 1

[0321] # Optionally, perform coverage analysis after each iteration to update the coverage of base stations

[0322] # Here, information such as user coverage can be recalculated based on the new base station status

[0323] After all retirements are completed, the network performance can be simulated to check the user coverage and ensure that the quality of service of the network is within an acceptable range:

[0324] SELECT u.id AS user_id, COUNT(*) AS remaining_services FROM user_locations u LEFT JOIN base_stations b ON ST_DWithin(b.location, u.location, b.coverage_radius) WHERE b.is_retired = FALSE -- Assume a new field is added to record whether the base station has been retired from the network GROUP BY u.id HAVING COUNT(*) = 0; -- Find users without coverage.

[0325] It should be noted that the base station retirement method provided by the present invention has the following beneficial effects:

[0326] a) By identifying and shutting down low-efficiency or redundant base stations, the operator can demolish 3G base stations or reallocate them to more critical areas, improving the overall network utilization rate and return on investment, significantly reducing the network maintenance burden, lowering operating costs, and optimizing the overall expenditure structure. At the same time, with the change of market demand, flexibly adjusting the network structure, a reasonable retirement order can help the operator better adapt to market competition and improve market agility.

[0327] b) When determining the retirement order, by evaluating the coverage ability of each base station, it is ensured that users can still obtain good signal quality and network services after the base station is retired. Through logical analysis and comparison operations, effective signal coverage is ensured, and signal blind spots are avoided.

[0328] c) Ensure that the user experience in terms of network service quality is not affected and improve user satisfaction. Base stations that do not cause coverage blind spots may be given priority for shutdown to ensure that user satisfaction does not decline.

[0329] d) By evaluating the impact of base station retirement, orderly retirement is ensured under the condition of basic network coverage, which conforms to the market development trend of gradually decreasing users and traffic volume in the retirement procedure. The operator can reduce potential risks caused by retirement, such as user churn and brand impact. A reasonable order can help gradually adapt to the changes, thereby reducing negative impacts.

[0330] The base station retirement method provided by the embodiment of the present invention first determines the coverage ranges of multiple base stations to be screened in the target area and the user's permanent location data; and imports the coverage ranges of the multiple base stations to be screened and the user's permanent location data into a Geographic Information System (GIS) to construct a geographical model based on base station coverage and user's permanent location; then, based on the geographical model, with the goal of optimal geographical coverage and minimal impact, calculates the impact score of each base station to be screened; then selects the base station to be screened with the lowest impact score as the optimal retirement site and completes the retirement; finally, determines whether the number of retired base stations has reached the preset total target number of exit sites. If so, ends this process. If not, removes the currently retired base station from the multiple base stations to be screened and returns to execute the step of determining the coverage ranges of the multiple base stations to be screened in the target area and the user's permanent location data. The present invention constructs a geographical model with the help of GIS technology and combines a scientific impact score evaluation mechanism to accurately locate low-efficiency or redundant base stations. On the premise of ensuring basic network coverage, it can achieve the orderly retirement of base stations and effectively avoid the generation of signal blind spots after retirement. At the same time, the present invention can ensure that users can still obtain good signal quality and network services after retirement, thus significantly improving user satisfaction. It solves the problems that the existing base station retirement methods cannot accurately locate low-efficiency or redundant base stations, and due to the lack of scientific evaluation of the base station coverage ability in the process of making retirement order decisions, it is easy to cause signal blind spots after retirement operations, which seriously affects the signal quality and network service experience of users.

[0331] Embodiment 2:

[0332] As Figure 3 shown, the present embodiment provides a base station retirement device for executing the above base station retirement method, including:

[0333] A data determination module 11, configured to determine the coverage ranges of multiple base stations to be screened in the target area and the user's permanent location data;

[0334] A geographical model construction module 12, connected to the data determination module 11, configured to import the coverage ranges of the multiple base stations to be screened and the user's permanent location data into a Geographic Information System (GIS) to construct a geographical model based on base station coverage and user's permanent location;

[0335] An impact score calculation module 13, connected to the geographical model construction module 12, configured to calculate the impact score of each base station to be screened based on the geographical model with the goal of optimal geographical coverage and minimal impact;

[0336] An optimal retirement module 14, connected to the impact score calculation module 13, configured to select the base station to be screened with the lowest impact score as the optimal retirement site and complete the retirement;

[0337] The loop iteration module 15 is connected to the optimal de-networking module 14, and is used to determine whether the number of de-networked base stations has reached the preset total target number of de-networked sites. If so, the current process is terminated; if not, the current de-networked base station is removed from the multiple base stations to be screened, and the process returns to execute the steps of the data determination module 11.

[0338] Optionally, the data determination module 11 includes:

[0339] A coverage model establishing unit, configured to establish a coverage model for each of the base stations to be screened according to the base station basic information of the base stations to be screened;

[0340] An outlier detection unit, used to perform outlier detection on the pre-collected measurement report MR data, and remove outliers in the MR data;

[0341] The model correction unit is used to correct the coverage model using the received signal strength indication RSSI and the signal to interference plus noise ratio SINR in the MR data after the outliers are removed, and determine the coverage range of the multiple base stations to be screened.

[0342] Optionally, the device further comprises:

[0343] A data collection module, used for collecting the MR data and user resident location data in the target area, and basic base station information of a plurality of base stations to be screened;

[0344] A data mapping module, used to map the MR data to a GIS system according to a preset data model;

[0345] The marking module is used to standardize the base station basic information and mark multiple base stations to be screened in the GIS system according to the standardized base station basic information.

[0346] Optionally, the base station basic information includes geographical location, transmit power, transmit antenna gain, and receive antenna gain, and the coverage model building unit specifically includes:

[0347] A propagation model selection unit, configured to select a corresponding propagation model for each base station to be screened according to environmental characteristics corresponding to the geographical location of each base station to be screened;

[0348] A strength calculation unit, used to calculate the received signal strength of the signal transmitted outward by each base station to be screened at different distances according to the selected propagation model and the transmission power, transmission antenna gain and receiving antenna gain of each base station to be screened;

[0349] A coverage model obtaining unit is configured to obtain a corresponding coverage model based on the received signal strengths of the signals transmitted outward by each base station to be screened at different distances.

[0350] Optionally, the impact score calculation module 13 is specifically configured to:

[0351] Based on the geographical model, aiming at optimal geographical coverage and minimizing impact, trade off the user coverage requirements and the impact of base station decommissioning through a genetic multi-objective optimization algorithm, and comprehensively consider the coverage rate and the number of affected users to calculate the impact score of each base station to be screened.

[0352] Optionally, the impact score calculation module 13 includes:

[0353] A score calculation unit is configured to calculate the impact score of each base station to be screened according to the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station.

[0354] Optionally, the score calculation unit includes:

[0355] A data acquisition unit is configured to acquire the coverage rate reduction value and the number of affected users when each base station to be screened is a proposed decommissioned base station;

[0356] A normalization unit is configured to perform normalization processing on the coverage rate reduction value and the number of affected users to obtain the normalized coverage rate reduction value and the number of affected users;

[0357] A first calculation unit is configured to calculate the impact score of each base station to be screened according to the following formula:

[0358] impact_score = W1 * normalized_coverage_decrease + W2 *

[0359] normalized_affected_users

[0360] In the formula, normalized_coverage_decrease represents the normalized coverage rate reduction value, normalized_affected_users represents the normalized number of affected users, W1 and W2 respectively represent the weights of the normalized coverage rate reduction value and the normalized number of affected users, and impact_score represents the impact score.

[0361] Embodiment 3:

[0362] Reference Figure 4, this embodiment provides a base station network retirement device, including a memory 21 and a processor 22. A computer program is stored in the memory 21, and the processor 22 is configured to run the computer program to execute the base station network retirement method in Embodiment 1.

[0363] Among them, the memory 21 is connected to the processor 22. The memory 21 can adopt flash memory, read-only memory or other memories, and the processor 22 can adopt a central processing unit or a single-chip microcomputer.

[0364] Embodiment 4:

[0365] This embodiment provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the base station network retirement method in Embodiment 1 above.

[0366] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules, or other data). The computer-readable storage medium includes, but is not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), digital versatile disc (DVD) or other optical disc storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0367] In summary, for the base station network retirement method, device, and readable storage medium provided by the embodiments of the present invention, first, the coverage ranges of multiple base stations to be screened in the target area and the user's permanent location data are determined; and the coverage ranges of the multiple base stations to be screened and the user's permanent location data are imported into a Geographic Information System (GIS) to construct a geographical model based on base station coverage and user permanent locations; then, based on the geographical model, with the goals of optimal geographical coverage and minimization of impact, the impact score of each base station to be screened is calculated; next, the base station to be screened with the lowest impact score is selected as the optimal network retirement site, and the network retirement is completed; finally, it is determined whether the number of retired base stations has reached the preset total target number of retired sites. If so, this process ends. If not, the currently retired base station is removed from the multiple base stations to be screened, and the steps of determining the coverage ranges of the multiple base stations to be screened in the target area and the user's permanent location data are returned and executed. The present invention constructs a geographical model with the aid of GIS technology and combines a scientific impact score evaluation mechanism to accurately locate low-efficiency or redundant base stations. On the premise of ensuring basic network coverage, it can achieve the orderly network retirement of base stations and effectively avoid the generation of signal blind spots after network retirement. At the same time, the present invention can ensure that users can still obtain good signal quality and network services after network retirement, thus significantly improving user satisfaction. It solves the problems that the existing base station network retirement methods cannot accurately locate low-efficiency or redundant base stations, and due to the lack of a scientific evaluation of the base station coverage ability in the network retirement order decision-making process, signal blind spots are likely to occur after network retirement operations, which seriously affects the signal quality and network service experience of users.

[0368] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principles of the present invention, and the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also regarded as the protection scope of the present invention.

Claims

1. A base station network retirement method, characterized in that, The method comprises: S1, determining the coverage of multiple base stations to be screened in the target area and the user's permanent location data; S2, importing the coverage of the plurality of base stations to be screened and the user's permanent location data into a geographic information system (GIS) system, and constructing a geographic model based on base station coverage and user's permanent location; S3, based on the geographic model, with the goal of optimal geographic coverage and minimized impact, calculating the impact score of each base station to be screened; S4, selecting the to-be-screened base station with the lowest impact score as the optimal de-networking site, and completing the de-networking; S5, determine whether the number of de-networked base stations has reached the preset total target number of de-networked sites. If so, end this process. If not, remove the current de-networked base station from the multiple base stations to be screened, and return to step S1.

2. The method according to claim 1, characterized in that The determining of the coverage ranges of the plurality of base stations to be screened in the target area specifically includes: Establishing a coverage model for each of the base stations to be screened according to the base station basic information of the plurality of base stations to be screened; Performing outlier detection on the pre-collected measurement report MR data, and removing outliers in the MR data; The coverage model is corrected using the received signal strength indication RSSI and the signal to interference plus noise ratio SINR in the MR data after the outliers are removed, and the coverage ranges of the multiple base stations to be screened are determined.

3. The method according to claim 2, wherein Before establishing a coverage model for each of the base stations to be screened according to the base station basic information of the plurality of base stations to be screened, the method further includes: Collecting the MR data and user resident location data in the target area, and basic base station information of a plurality of base stations to be screened; Mapping the MR data to the GIS system according to a preset data model; The base station basic information is standardized, and multiple base stations to be screened in the GIS system are marked according to the standardized base station basic information.

4. The method according to claim 2, wherein The base station basic information includes geographical location, transmission power, transmission antenna gain, and receiving antenna gain. The establishing of a coverage model for each base station to be screened based on the base station basic information of the plurality of base stations to be screened specifically includes: Selecting a corresponding propagation model for each base station to be screened according to the environmental characteristics corresponding to the geographical location of each base station to be screened; Calculate the received signal strength of the signal transmitted outward by each base station to be screened at different distances according to the selected propagation model and the transmit power, transmit antenna gain and receive antenna gain of each base station to be screened; A corresponding coverage model is obtained based on the received signal strength of the signal transmitted outward by each of the base stations to be screened at different distances.

5. The method according to claim 1, wherein The step of calculating the impact score of each base station to be screened based on the geographic model with the goal of optimal geographic coverage and minimization of impact specifically includes: Based on the geographic model, with the goal of optimal geographic coverage and minimized impact, the user coverage requirements and the impact of base station network withdrawal are weighed through a genetic multi-objective optimization algorithm, and the impact score of each base station to be screened is calculated by comprehensively considering the coverage rate and the number of affected users.

6. The method according to claim 5, wherein Calculating the impact score of each base station to be screened by comprehensively considering the coverage rate and the number of affected users, specifically including: Calculating the impact score of each base station to be screened according to the coverage rate reduction value and the number of affected users when each base station to be screened is a base station to be retired.

7. The method according to claim 6, characterized in that The calculating the impact score of each base station to be screened according to the coverage rate reduction value and the number of affected users when each base station to be screened is a base station to be retired specifically includes: Obtaining the coverage rate reduction value and the number of affected users when each base station to be screened is a base station to be retired; Performing normalization processing on the coverage rate reduction value and the number of affected users to obtain the normalized coverage rate reduction value and the number of affected users after normalization; Calculating the impact score of each base station to be screened according to the following formula: impact_score = W1 * normalized_coverage_decrease + W2 * normalized_affected_users In the formula, normalized_coverage_decrease represents the normalized coverage rate reduction value, normalized_affected_users represents the number of affected users after normalization, W1 and W2 respectively represent the weights of the normalized coverage rate reduction value and the number of affected users, and impact_score represents the impact score.

8. A base station network withdrawal device, characterized in that, The device includes: A data determination module, configured to determine the coverage ranges of multiple base stations to be screened in the target area and the user resident location data; A geographical model construction module, connected to the data determination module, configured to import the coverage ranges of the multiple base stations to be screened and the user resident location data into a geographic information system (GIS) system to construct a geographical model based on base station coverage and user resident locations; An impact score calculation module, connected to the geographical model construction module, configured to calculate the impact score of each base station to be screened based on the geographical model with the goals of optimal geographical coverage and minimized impact; An optimal retirement module, connected to the impact score calculation module, configured to select the base station to be screened with the lowest impact score as the optimal retirement site and complete the retirement; A loop iteration module, connected to the optimal retirement module, configured to determine whether the number of retired base stations has reached the preset total target number of retirement sites. If so, end this process. If not, remove the currently retired base station from the multiple base stations to be screened and return to execute the steps of the data determination module.

9. A base station network retirement device, characterized in that, Including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to implement the base station retirement method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements the base station retirement method according to any one of claims 1-7.

Images