Base station site selection method, system and device and storage medium

Abstract

The invention discloses a base station site selection method, system and device and a storage medium. The base station site selection method comprises the steps that the 5G user migration probability is calculated based on the grid user density, the grid reference signal receiving power, the cell flow and the user information; calculating a 5G user activeness index based on the grid user density, the grid reference signal receiving power, the cell flow and the user information, and calculating a competition demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate and the second grid 5G coverage rate, calculating a user dissatisfaction imbalance index value, a competition cooperation coefficient value, an active demand compensation factor and a migration coverage gap ratio based on the 5G user migration probability, the 5G user activeness index and the competition demand imbalance index value so as to calculate a closeness score; and the base station site selection is carried out based on the close degree score, so that the base station site selection efficiency and the resource utilization rate are improved.

Description

Technical Field

[0001] The present application relates to the technical field related to base station site selection, and in particular to a base station site selection method, system, device and storage medium. Background Art

[0002] With the large-scale commercialization of 5G networks and the advanced deployment of 6G technologies, mobile communication systems are continuously evolving towards ultra-dense networking and intelligent collaboration. Traditionally, base station site selection involves conducting simulations based on wireless propagation models. This is combined with wireless quality metrics, historical traffic peaks, and user complaint heat maps collected by the operator's system to manually set parameters such as static coverage radius and capacity thresholds. In the context of 4G low-frequency band networks, this approach can still meet relevant requirements based on empirical rules.

[0003] At present, when faced with complex scenarios such as the sharp increase in penetration loss in the high-frequency band of 5G millimeter waves and the three-dimensional networking of 6G non-terrestrial networks, the current base station site selection method mainly relies on the operator's wireless network key indicators and complaint data. These data can only reflect the status of its own network and lack the integration of data from friendly competitors. Moreover, the current base station site selection method relies too much on past experience and lacks dynamic analysis of the time dimension. Summary of the Invention

[0004] This application aims to at least solve the technical problems existing in the prior art. To this end, this application proposes a base station site selection method, system, device and storage medium that can integrate multimodal data to achieve objective sorting and real-time adjustment of base station site selection, thereby improving the efficiency and resource utilization of base station site selection.

[0005] In a first aspect of the present application, a base station site selection method is provided, comprising the following steps:

[0006] Obtain first grid data and second grid data for the target area, wherein the first grid data includes grid user density, grid reference signal received power, cell traffic, user information, first user occupancy rate, and first grid 5G coverage rate of the base station site operator, and the second grid data includes second user occupancy rate and second grid 5G coverage rate of other competing operators;

[0007] Calculating a 5G user migration probability based on the grid user density, grid reference signal received power, cell traffic, and user information; calculating a 5G user activity index based on the grid user density, grid reference signal received power, cell traffic, and user information;

[0008] Calculating a competition demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate;

[0009] Calculating a user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; calculating a competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; calculating an active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and calculating a migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value.

[0010] A proximity score is calculated based on the user dissatisfaction imbalance index value, the competition synergy coefficient value, the active demand compensation factor, and the migration coverage gap ratio; and a base station site is selected based on the proximity score.

[0011] The control method according to the embodiment of the present application has at least the following beneficial effects:

[0012] This method obtains the first grid data and the second grid data of the target area, wherein the first grid data includes the grid user density, grid reference signal receiving power, cell traffic, user information, first user occupancy rate and first grid 5G coverage rate of the base station site operator, and the second grid data includes the second user occupancy rate and second grid 5G coverage rate of other competing operators. This application improves the data accuracy and diversity by fusing multi-source data, and calculates the 5G user migration probability based on grid user density, grid reference signal receiving power, cell traffic and user information; calculates the 5G user activity index based on grid user density, grid reference signal receiving power, cell traffic and user information, and calculates the 5G user activity index based on the first user occupancy rate, first grid 5G coverage rate, The competitive demand imbalance index value is calculated based on the second user occupancy rate and the second grid 5G coverage rate, and the user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the competitive synergy coefficient value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the active demand compensation factor is calculated based on the 5G user activity index and the competitive demand imbalance index value; the migration coverage gap ratio is calculated based on the 5G user migration probability and the competitive demand imbalance index value. This application realizes the objective sorting and real-time adjustment of base station site selection, calculates the proximity score based on the user dissatisfaction imbalance index value, the competitive synergy coefficient value, the active demand compensation factor and the migration coverage gap ratio; and performs base station site selection based on the proximity score, thereby improving the efficiency of base station site selection and resource utilization.

[0013] According to some embodiments of the present application, calculating the 5G user migration probability based on the grid user density, grid reference signal received power, cell traffic, and user information includes:

[0014] Obtain historical user 5G migration ratio and grid 5G coverage;

[0015] The cell grid weight is calculated based on the grid user density and the grid reference signal received power using the following formula:

[0016]

[0017] f(RSRP g )=RSRP g +140

[0018] Among them, Weight c,g is the grid weight of the cth cell in the gth grid, α is the preset received power coefficient, β is the preset user density coefficient, f(RSRP g ) is the normalized grid reference signal received power of the g-th grid, RSRP g is the grid reference signal received power of the g-th grid, U g is the grid user density of the g-th grid, G c is the set of all grids covered by the cth cell, U g' is the grid user density of the g'th grid, f(RSRP g' ) is the normalized grid reference signal received power of the g'th grid, RSRP g' is the grid reference signal received power of the g'th grid;

[0019] The grid flow is calculated based on the cell grid weight and the cell flow using the following formula:

[0020] Traffic c,g =Traffic c ×Weight c,g

[0021] Among them, Traffic c,g is the grid flow of the cth cell of the gth grid, Traffic c is the cell traffic of the cth cell;

[0022] The historical user 5G migration ratio, the grid 5G coverage rate, and the grid traffic are input into the trained LSTM-Transformer model for prediction to obtain the 5G user migration probability, wherein the grid traffic includes grid 5G traffic and grid 4G traffic.

[0023] According to some embodiments of the present application, the calculating of the 5G user activity index based on the grid user density, grid reference signal received power, cell traffic, and user information includes:

[0024] Input the historical user 5G migration ratio, the grid 5G coverage rate, and the grid traffic into the trained LSTM-Transformer model for prediction to obtain the original value of the grid 5G user activity;

[0025] The 5G user activity index is calculated based on the original grid 5G user activity value using the following formula:

[0026]

[0027] Among them, A activity is the 5G user activity index, A raw is the original value of grid 5G user activity, A min is the minimum value of the original value of grid 5G user activity, A max It is the maximum value of the original values of 5G user activity in the grid.

[0028] According to some embodiments of the present application, the calculating the competitive demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate includes:

[0029] Obtain the number of user reports and the number of users of the base station site selection operator;

[0030] Calculating a grid activity demand value based on the number of user reports and the number of users;

[0031] Calculate a grid competition coverage gap value based on the first grid 5G coverage and the second grid 5G coverage;

[0032] Calculating a grid competing user gap value based on the first user occupancy rate and the second user occupancy rate;

[0033] The coverage gap is calculated based on the grid competition coverage gap value using the following formula:

[0034]

[0035] Among them, N cr is the coverage gap, cr is the grid competition coverage gap value, cr min is the minimum value of the grid coverage gap value, cr max is the maximum value of the grid coverage gap value;

[0036] The user gap is calculated based on the grid competition user gap value using the following formula:

[0037]

[0038] Among them, N m is the user gap, mmax is the maximum value of the grid competing user gap value, m min is the minimum value of the gap between grid competing users, and m is the gap between grid competing users;

[0039] The activity demand degree is calculated based on the grid activity demand value using the following formula:

[0040]

[0041] Among them, N A is the active demand degree, A is the grid active demand value, A min is the minimum value of the grid active demand value, A max is the maximum value among the grid active demand values;

[0042] The coverage gap weight value is calculated based on the grid activity demand value using the following formula:

[0043]

[0044] Among them, W cr is the coverage gap weight value;

[0045] The user gap weight value is calculated based on the grid activity demand value using the following formula:

[0046]

[0047] Among them, W m is the user gap weight value;

[0048] The active demand weight value is calculated based on the grid active demand value using the following formula:

[0049]

[0050] Among them, W A is the active demand weight value;

[0051] The competitive demand imbalance index value is calculated based on the coverage gap, the user gap, the active demand, the coverage gap weight value, the user gap weight value, and the active demand weight value using the following formula:

[0052]

[0053]

[0054] in, is the competition demand imbalance index value, and Penalty is the collaborative penalty item.

[0055] According to some embodiments of the present application, the calculating of the user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; the calculating of the competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; the calculating of the active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and the calculating of the migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value include:

[0056] Get the number of grid user complaints;

[0057] The user dissatisfaction imbalance index value is calculated based on the number of grid user complaints, the 5G user migration probability and the competition demand imbalance index value using the following formula:

[0058] UDCII=ln(Compla int count +1)×CDII Score ×P mig

[0059] Among them, UDCII is the user dissatisfaction imbalance index value, Complaint count is the number of grid user complaints, P mig Migration probability for 5G users;

[0060] The competition coordination coefficient value is calculated based on the 5G user migration probability and the competition demand imbalance index value using the following formula:

[0061] k syn =P mig ×CDII score

[0062] Among them, k syn is the competitive synergy coefficient value;

[0063] The active demand compensation factor is calculated based on the 5G user activity index and the competitive demand imbalance index value using the following formula:

[0064]

[0065] Among them, F comp is the active demand compensation factor, ε is the preset denominator coefficient;

[0066] The user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competition demand imbalance index value using the following formula:

[0067]

[0068] Among them, R gap It is the user dissatisfaction imbalance index value.

[0069] According to some embodiments of the present application, the calculating a proximity score based on the user dissatisfaction imbalance index value, the competition coordination coefficient value, the active demand compensation factor, and the migration coverage gap ratio; and performing base station site selection based on the proximity score includes:

[0070] The user dissatisfaction imbalance index value is normalized by the following formula to obtain the first indicator:

[0071]

[0072] Among them, N1 is the first indicator, UDCII min is the minimum value of the user dissatisfaction imbalance index value, UDCII max The maximum value of the user dissatisfaction imbalance index;

[0073] The competitive synergy coefficient value is normalized by the following formula to obtain the second indicator:

[0074]

[0075] Where I is the total number of grids, is the competitive coordination coefficient value of the i-th grid, is the mean value of the competitive synergy coefficient, is the standard deviation of the competitive synergy coefficient value, N2 is the second indicator;

[0076] The active demand compensation factor is normalized using the following formula to obtain the third indicator:

[0077]

[0078] Among them, N3 is the third indicator;

[0079] The migration coverage gap ratio is normalized by the following formula to obtain the fourth indicator:

[0080]

[0081] Among them, N4 is the fourth indicator;

[0082] Based on the first indicator, the second indicator, the third indicator and the fourth indicator, the corresponding proportion of the indicator is calculated using the following formula:

[0083]

[0084] Among them, P ij is the corresponding weight of the jth indicator of the i-th grid, N ijis the jth indicator of the i-th grid. When j is equal to 1, it corresponds to the first indicator, when j is equal to 2, it corresponds to the second indicator, when j is equal to 3, it corresponds to the third indicator, and when j is equal to 4, it corresponds to the fourth indicator;

[0085] Based on the corresponding weights of the indicators, the information entropy corresponding to the indicators is calculated using the following formula:

[0086]

[0087] Among them, e j The information entropy corresponding to the index of the j-th index;

[0088] Based on the information entropy corresponding to the indicator, the corresponding weight of the indicator is calculated using the following formula:

[0089]

[0090] Among them, w j is the indicator weight of the j-th indicator, and J is the total number of indicators;

[0091] The proximity score is calculated based on the first indicator, the second indicator, the third indicator, the fourth indicator and the corresponding weights of the indicators; and a base station site is selected based on the proximity score.

[0092] According to some embodiments of the present application, calculating the proximity score based on the first indicator, the second indicator, the third indicator, the fourth indicator, and the corresponding weights of the indicators; and performing base station site selection based on the proximity score includes:

[0093] Based on the first indicator, the second indicator, the third indicator, the fourth indicator and the corresponding weights of the indicators, the ideal value of the corresponding indicator is calculated using the following formula:

[0094] v ij =N ij ×w j

[0095] Among them, v ij is the ideal value of the corresponding indicator of the jth indicator of the i-th grid;

[0096] Obtain the maximum value of the first indicator of the i-th grid, the maximum value of the second indicator of the i-th grid, and the maximum value of the fourth indicator of the i-th grid, and use the three maximum values as the ideal solution of the forward indicator;

[0097] The forward distance is calculated based on the ideal solution of the forward indicator using the following formula:

[0098]

[0099] in, is the positive distance of the i-th grid, is the ideal solution for the jth positive indicator;

[0100] Get the minimum value of the third indicator of the i-th grid and use it as the ideal solution of the negative indicator;

[0101] The negative distance is calculated based on the ideal solution of the negative indicator using the following formula:

[0102]

[0103] in, is the negative distance of the i-th grid, is the ideal solution for the jth negative indicator;

[0104] The closeness score is calculated based on the positive distance and the negative distance using the following formula:

[0105]

[0106] Among them, C i is the closeness score of the i-th grid;

[0107] Arrange the proximity scores in descending order to obtain a candidate base station deployment priority list;

[0108] Base station site selection is performed based on the candidate base station deployment priority list.

[0109] In a second aspect of the present application, a base station site selection system is provided, the base station site selection system comprising:

[0110] a data acquisition module, configured to acquire first grid data and second grid data of a target area, wherein the first grid data includes grid user density, grid reference signal received power, cell traffic, user information, first user occupancy rate, and first grid 5G coverage rate of the base station site operator, and the second grid data includes second user occupancy rate and second grid 5G coverage rate of other competing operators;

[0111] a 5G user data calculation module, configured to calculate a 5G user migration probability based on the grid user density, grid reference signal received power, cell traffic, and user information; and calculate a 5G user activity index based on the grid user density, grid reference signal received power, cell traffic, and user information;

[0112] a competition demand imbalance index value calculation module, configured to calculate a competition demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate;

[0113] an indicator calculation module, configured to calculate a user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; calculate a competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; calculate an active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and calculate a migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value;

[0114] A base station site selection module is used to calculate a proximity score based on the user dissatisfaction imbalance index value, the competition coordination coefficient value, the active demand compensation factor and the migration coverage gap ratio; and to select a base station site based on the proximity score.

[0115] This system obtains the first grid data and the second grid data of the target area, wherein the first grid data includes the grid user density, grid reference signal receiving power, cell traffic, user information, first user occupancy rate and first grid 5G coverage rate of the base station site operator, and the second grid data includes the second user occupancy rate and second grid 5G coverage rate of other competing operators. This application improves the data accuracy and diversity by fusing multi-source data, and calculates the 5G user migration probability based on grid user density, grid reference signal receiving power, cell traffic and user information; calculates the 5G user activity index based on grid user density, grid reference signal receiving power, cell traffic and user information, and calculates the 5G user activity index based on the first user occupancy rate, first grid 5G coverage rate, The competitive demand imbalance index value is calculated based on the second user occupancy rate and the second grid 5G coverage rate, and the user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the competitive synergy coefficient value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the active demand compensation factor is calculated based on the 5G user activity index and the competitive demand imbalance index value; the migration coverage gap ratio is calculated based on the 5G user migration probability and the competitive demand imbalance index value. This application realizes the objective sorting and real-time adjustment of base station site selection, calculates the proximity score based on the user dissatisfaction imbalance index value, the competitive synergy coefficient value, the active demand compensation factor and the migration coverage gap ratio; and performs base station site selection based on the proximity score, thereby improving the efficiency of base station site selection and resource utilization.

[0116] The third aspect of the present application provides a base station site selection electronic device, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the above-mentioned base station site selection method.

[0117] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned base station site selection method.

[0118] It should be noted that the beneficial effects between the second to fourth aspects of the present application and the prior art are the same as the beneficial effects between the above-mentioned base station site selection system and the prior art, and will not be described in detail here.

[0119] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0120] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0121] Figure 1 This is a flow chart of a base station site selection method according to an embodiment of the present application;

[0122] Figure 2 is a structural diagram of an embodiment of a base station site selection system provided by the present application;

[0123] Figure 3 It is a structural diagram of an embodiment of the electronic device provided by this application. DETAILED DESCRIPTION

[0124] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0125] In the description of this application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0126] In the description of this application, it should be understood that descriptions involving orientation, such as the orientation or positional relationship indicated by up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0127] In the description of this application, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technical personnel in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0128] With the large-scale commercialization of 5G networks and the advanced deployment of 6G technologies, mobile communication systems are continuously evolving towards ultra-dense networking and intelligent collaboration. Traditionally, base station site selection involves conducting simulations based on wireless propagation models. This is combined with wireless quality metrics, historical traffic peaks, and user complaint heat maps collected by the operator's system to manually set parameters such as static coverage radius and capacity thresholds. In the context of 4G low-frequency band networks, this approach can still meet relevant requirements based on empirical rules.

[0129] At present, when faced with complex scenarios such as the sharp increase in penetration loss in the high-frequency band of 5G millimeter waves and the three-dimensional networking of 6G non-terrestrial networks, the current base station site selection method mainly relies on the operator's wireless network key indicators and complaint data. These data can only reflect the status of its own network and lack the integration of data from friendly competitors. Moreover, the current base station site selection method relies too much on past experience and lacks dynamic analysis of the time dimension.

[0130] In order to solve the above technical defects, the embodiments of the present application provide a base station site selection method, system, device and storage medium.

[0131] See Figure 1 , is a flow chart of a base station site selection method provided by an embodiment of the present application, the method is applied to an electronic device, which may be a server, etc. Figure 1 As shown, the base station site selection method includes:

[0132] Step S101: Acquire first grid data and second grid data of a target area, wherein the first grid data includes grid user density, grid reference signal received power, cell traffic, user information, first user occupancy rate, and first grid 5G coverage rate of the base station site operator, and the second grid data includes second user occupancy rate and second grid 5G coverage rate of other competing operators;

[0133] Step S102: Calculate the 5G user migration probability based on the grid user density, grid reference signal received power, cell traffic, and user information; Calculate the 5G user activity index based on the grid user density, grid reference signal received power, cell traffic, and user information;

[0134] Step S103: Calculate a competitive demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate;

[0135] Step S104: Calculate a user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; calculate a competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; calculate an active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and calculate a migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value.

[0136] Step S105: Calculate a proximity score based on the user dissatisfaction imbalance index value, the competition coordination coefficient value, the active demand compensation factor, and the migration coverage gap ratio; and select a base station site based on the proximity score.

[0137] Specifically, the first grid data and the second grid data are derived from operator OMC data and third-party OTT data.

[0138] This method obtains the first grid data and the second grid data of the target area, wherein the first grid data includes the grid user density, grid reference signal receiving power, cell traffic, user information, first user occupancy rate and first grid 5G coverage rate of the base station site operator, and the second grid data includes the second user occupancy rate and second grid 5G coverage rate of other competing operators. This application improves the data accuracy and diversity by fusing multi-source data, and calculates the 5G user migration probability based on grid user density, grid reference signal receiving power, cell traffic and user information; calculates the 5G user activity index based on grid user density, grid reference signal receiving power, cell traffic and user information, and calculates the 5G user activity index based on the first user occupancy rate, first grid 5G coverage rate, The competitive demand imbalance index value is calculated based on the second user occupancy rate and the second grid 5G coverage rate, and the user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the competitive synergy coefficient value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the active demand compensation factor is calculated based on the 5G user activity index and the competitive demand imbalance index value; the migration coverage gap ratio is calculated based on the 5G user migration probability and the competitive demand imbalance index value. This application realizes the objective sorting and real-time adjustment of base station site selection, calculates the proximity score based on the user dissatisfaction imbalance index value, the competitive synergy coefficient value, the active demand compensation factor and the migration coverage gap ratio; and performs base station site selection based on the proximity score, thereby improving the efficiency of base station site selection and resource utilization.

[0139] In some embodiments, calculating the 5G user migration probability based on grid user density, grid reference signal received power, cell traffic, and user information includes:

[0140] Step S201: Obtain historical user 5G migration ratio and grid 5G coverage;

[0141] Step S202: Calculate the cell grid weight based on the grid user density and the grid reference signal received power using the following formula:

[0142]

[0143] f(RSRP g )=RSRP g +140

[0144] Among them, Weight c,g is the grid weight of the cth cell in the gth grid, α is the preset received power coefficient, β is the preset user density coefficient, f(RSRP g ) is the normalized grid reference signal received power of the g-th grid, RSRP g is the grid reference signal received power of the g-th grid, U g is the grid user density of the g-th grid, G c is the set of all grids covered by the cth cell, U g' is the grid user density of the g'th grid, f(RSRP g' ) is the normalized grid reference signal received power of the g'th grid, RSRP g' is the grid reference signal received power of the g'th grid;

[0145] Step S203: Calculate the grid flow rate based on the cell grid weight and the cell flow rate using the following formula:

[0146] Traffic c,g =Traffic c ×Weight c,g

[0147] Among them, Traffic c,g is the grid flow of the cth cell of the gth grid, Traffic c is the cell traffic of the cth cell;

[0148] Step S204: Input the historical user 5G migration ratio, grid 5G coverage, and grid traffic into the trained LSTM-Transformer model for prediction to obtain the 5G user migration probability, where the grid traffic includes grid 5G traffic and grid 4G traffic.

[0149] This application implements a joint weight mapping rule between user density and RSRP from the cell level to the grid level. This framework can effectively break down the barriers between different data sources and provide comprehensive and accurate data support for global decision-making.

[0150] In some embodiments, calculating the 5G user activity index based on grid user density, grid reference signal received power, cell traffic, and user information includes:

[0151] Step S301: Input the historical user 5G migration ratio, grid 5G coverage, and grid traffic into the trained LSTM-Transformer model for prediction to obtain the original value of grid 5G user activity;

[0152] Step S302: Calculate the 5G user activity index based on the original grid 5G user activity value using the following formula:

[0153]

[0154] Among them, A activity is the 5G user activity index, A raw is the original value of grid 5G user activity, A min is the minimum value of the original value of grid 5G user activity, A max It is the maximum value of the original values of 5G user activity in the grid.

[0155] This application calculates the 5G user activity index in real time, thereby closely following the dynamic changes of the actual network and ensuring that decisions are always optimal.

[0156] In some embodiments, calculating the competitive demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate includes:

[0157] Step S401: Obtain the number of user reports and the number of users of the base station site selection operator;

[0158] Step S402: Calculate the grid activity demand value based on the number of user reports and the number of users;

[0159] Step S403: Calculate the grid competition coverage gap value based on the 5G coverage rate of the first grid and the 5G coverage rate of the second grid;

[0160] Step S404: Calculate the grid competing user gap value based on the first user occupancy rate and the second user occupancy rate;

[0161] Step S405: Calculate the coverage gap based on the grid competition coverage gap value using the following formula:

[0162]

[0163] Among them, N cr is the coverage gap, cr is the grid competition coverage gap value, cr min is the minimum value of the grid coverage gap value, crmax is the maximum value of the grid coverage gap value;

[0164] Step S406: Calculate the user gap based on the grid competition user gap value using the following formula:

[0165]

[0166] Among them, N m is the user gap, m max is the maximum value of the grid competing user gap value, m min is the minimum value of the gap between grid competing users, and m is the gap between grid competing users;

[0167] Step S407: Calculate the activity demand degree based on the grid activity demand value using the following formula:

[0168]

[0169] Among them, N A is the active demand degree, A is the grid active demand value, A min is the minimum value of the grid active demand value, A max is the maximum value among the grid active demand values;

[0170] Step S408: Calculate the coverage gap weight value based on the grid activity demand value using the following formula:

[0171]

[0172] Among them, W cr is the coverage gap weight value;

[0173] Step S409: Calculate the user gap weight value based on the grid activity demand value using the following formula:

[0174]

[0175] Among them, W m is the user gap weight value;

[0176] Step S410: Calculate the activity demand weight value based on the grid activity demand value using the following formula:

[0177]

[0178] Among them, W A is the active demand weight value;

[0179] Step S411: Calculate the competitive demand imbalance index value based on the coverage gap, user gap, active demand, coverage gap weight value, user gap weight value, and active demand weight value using the following formula:

[0180]

[0181]

[0182] in, is the competition demand imbalance index value, and Penalty is the collaborative penalty item.

[0183] This application calculates the competitive demand imbalance index value in real time, thereby closely following the dynamic changes of the actual network and ensuring that the decision is always in the optimal state.

[0184] In some embodiments, a user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competition demand imbalance index value; a competition synergy coefficient value is calculated based on the 5G user migration probability and the competition demand imbalance index value; an active demand compensation factor is calculated based on the 5G user activity index and the competition demand imbalance index value; and a migration coverage gap ratio is calculated based on the 5G user migration probability and the competition demand imbalance index value, including:

[0185] Step S501: Obtain the number of grid user complaints;

[0186] Step S502: Calculate the user dissatisfaction imbalance index value based on the number of grid user complaints, the 5G user migration probability, and the competition demand imbalance index value using the following formula:

[0187] UDCII=ln(Compla int count +1)×CDII Score ×P mig

[0188] Among them, UDCII is the user dissatisfaction imbalance index value, Complaint count is the number of grid user complaints, P mig Migration probability for 5G users;

[0189] Step S503: Calculate the competition coordination coefficient value based on the 5G user migration probability and the competition demand imbalance index value using the following formula:

[0190] k syn =P mig ×CDII score

[0191] Among them, k syn is the competitive synergy coefficient value;

[0192] Step S504: Calculate the active demand compensation factor based on the 5G user activity index and the competitive demand imbalance index using the following formula:

[0193]

[0194] Among them, F comp is the active demand compensation factor, ε is the preset denominator coefficient;

[0195] Step S505: Calculate the user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value using the following formula:

[0196]

[0197] Among them, R gap It is the user dissatisfaction imbalance index value.

[0198] In some embodiments, a proximity score is calculated based on a user dissatisfaction imbalance index value, a competition coordination coefficient value, an active demand compensation factor, and a migration coverage gap ratio; and a base station site is selected based on the proximity score, including:

[0199] Step S601: Normalize the user dissatisfaction imbalance index value using the following formula to obtain the first indicator:

[0200]

[0201] Among them, N1 is the first indicator, UDCII min is the minimum value of the user dissatisfaction imbalance index value, UDCII max The maximum value of the user dissatisfaction imbalance index;

[0202] Step S602: Normalize the competitive synergy coefficient value using the following formula to obtain the second indicator:

[0203]

[0204] Where I is the total number of grids, is the competitive coordination coefficient value of the i-th grid, is the mean value of the competitive synergy coefficient, is the standard deviation of the competitive synergy coefficient value, N2 is the second indicator;

[0205] Step S603: Normalize the active demand compensation factor using the following formula to obtain the third indicator:

[0206]

[0207] Among them, N3 is the third indicator;

[0208] Step S604: Normalize the migration coverage gap ratio using the following formula to obtain the fourth indicator:

[0209]

[0210] Among them, N4 is the fourth indicator;

[0211] Step S605: Calculate the corresponding weight of the indicators based on the first indicator, the second indicator, the third indicator, and the fourth indicator using the following formula:

[0212]

[0213] Among them, P ij is the corresponding weight of the jth indicator of the i-th grid, N ij is the jth indicator of the i-th grid. When j is equal to 1, it corresponds to the first indicator, when j is equal to 2, it corresponds to the second indicator, when j is equal to 3, it corresponds to the third indicator, and when j is equal to 4, it corresponds to the fourth indicator;

[0214] Step S606: Calculate the information entropy corresponding to the indicator based on the corresponding weight of the indicator using the following formula:

[0215]

[0216] Among them, e j The information entropy corresponding to the index of the j-th index;

[0217] Step S607: Calculate the corresponding weight of the indicator based on the information entropy of the indicator using the following formula:

[0218]

[0219] Among them, w j is the indicator weight of the j-th indicator, and J is the total number of indicators;

[0220] Step S608: Calculate a proximity score based on the first indicator, the second indicator, the third indicator, the fourth indicator, and the corresponding weights of the indicators; and select a base station site based on the proximity score.

[0221] This application improves the real-time nature of the decision-making process through a dynamic weight adjustment mechanism, and can better cope with complex and changing network environments and market demands.

[0222] In some embodiments, calculating a proximity score based on the first indicator, the second indicator, the third indicator, the fourth indicator, and the corresponding weights of the indicators; and performing base station site selection based on the proximity score includes:

[0223] Step S701: Calculate the ideal value of the corresponding indicator based on the first indicator, the second indicator, the third indicator, the fourth indicator and the corresponding weight of the indicator using the following formula:

[0224] v ij =N ij ×wj

[0225] Among them, v ij is the ideal value of the corresponding indicator of the jth indicator of the i-th grid;

[0226] Step S702: Obtain the maximum value of the first indicator of the i-th grid, the maximum value of the second indicator of the i-th grid, and the maximum value of the fourth indicator of the i-th grid, and use the three maximum values as the ideal solution of the forward indicator;

[0227] Step S703: Calculate the forward distance based on the ideal solution of the forward indicator using the following formula:

[0228]

[0229] in, is the positive distance of the i-th grid, is the ideal solution for the jth positive indicator;

[0230] Step S704: Obtain the minimum value of the third indicator of the i-th grid and use it as the ideal solution of the negative indicator;

[0231] Step S705: Calculate the negative distance based on the ideal solution of the negative indicator using the following formula:

[0232]

[0233] in, is the negative distance of the i-th grid, is the ideal solution for the jth negative indicator;

[0234] Step S706: Calculate the closeness score based on the positive distance and the negative distance using the following formula:

[0235]

[0236] Among them, C i is the closeness score of the i-th grid;

[0237] Step S707: Arrange the proximity scores in descending order to obtain a candidate base station deployment priority list;

[0238] Step S708: Perform base station site selection based on the candidate base station deployment priority list.

[0239] This application provides scientific guidance for the precise allocation of resources based on the quantitative assessment of the pros and cons of candidate areas, effectively reducing the cost expenditure brought about by traditional trial and error methods, and improving the efficiency and success rate of resource allocation and deployment.

[0240] Specifically, to facilitate understanding by those skilled in the art, a set of best embodiments are provided below:

[0241] 1. Data Acquisition

[0242] Obtain first grid data and second grid data for the target area, where the first grid data includes the grid user density, grid reference signal received power, cell traffic, user information, first user occupancy rate, and first grid 5G coverage rate of the base station site operator, and the second grid data includes the second user occupancy rate and second grid 5G coverage rate of other competing operators;

[0243] 2. Calculation of 5G user indicators:

[0244] The 5G user migration probability is calculated based on the grid user density, grid reference signal received power, cell traffic, and user information. The 5G user activity index is calculated based on the grid user density, grid reference signal received power, cell traffic, and user information. Specifically, it is:

[0245] Calculate the 5G user migration probability based on grid user density, grid reference signal received power, cell traffic, and user information, including:

[0246] Obtain historical user 5G migration ratio and grid 5G coverage;

[0247] The cell grid weight is calculated based on the grid user density and the grid reference signal received power using the following formula:

[0248]

[0249] f(RSRP g )=RSRP g +140

[0250] Among them, Weight c,g is the grid weight of the cth cell in the gth grid, α is the preset received power coefficient, β is the preset user density coefficient, f(RSRP g ) is the normalized grid reference signal received power of the g-th grid, RSRP g is the grid reference signal received power of the g-th grid, U g is the grid user density of the g-th grid, G c is the set of all grids covered by the cth cell, U g' is the grid user density of the g'th grid, f(RSRP g' ) is the normalized grid reference signal received power of the g'th grid, RSRP g' is the grid reference signal received power of the g'th grid;

[0251] The grid flow is calculated based on the grid weight and the grid flow using the following formula:

[0252] Traffic c,g =Traffic c ×Weight c,g

[0253] Among them, Traffic c,g is the grid flow of the cth cell of the gth grid, Traffic c is the cell traffic of the cth cell;

[0254] The historical user 5G migration ratio, grid 5G coverage, and grid traffic are input into the trained LSTM-Transformer model for prediction to obtain the 5G user migration probability, where grid traffic includes grid 5G traffic and grid 4G traffic.

[0255] The historical user 5G migration ratio, grid 5G coverage, and grid traffic are input into the trained LSTM-Transformer model for prediction to obtain the original value of grid 5G user activity.

[0256] The 5G user activity index is calculated based on the original grid 5G user activity value using the following formula:

[0257]

[0258] Among them, A activity is the 5G user activity index, A raw is the original value of grid 5G user activity, A min is the minimum value of the original value of grid 5G user activity, A max It is the maximum value of the original values of 5G user activity in the grid.

[0259] 3. Calculation of the Competition Demand Imbalance Index:

[0260] The competitive demand imbalance index value is calculated based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate, specifically:

[0261] Obtain the number of user reports and the number of users of the base station site selection operator;

[0262] Calculate the grid activity demand value based on the number of user reports and the number of users;

[0263] Calculate the grid competition coverage gap value based on the 5G coverage of the first grid and the 5G coverage of the second grid;

[0264] Calculating a grid competing user gap value based on the first user occupancy rate and the second user occupancy rate;

[0265] The coverage gap is calculated based on the grid competition coverage gap value using the following formula:

[0266]

[0267] Among them, N cr is the coverage gap, cr is the grid competition coverage gap value, cr min is the minimum value of the grid coverage gap value, cr max is the maximum value of the grid coverage gap value;

[0268] The user gap is calculated based on the grid competition user gap value using the following formula:

[0269]

[0270] Among them, N m is the user gap, m max is the maximum value of the grid competing user gap value, m min is the minimum value of the gap between grid competing users, and m is the gap between grid competing users;

[0271] The active demand degree is calculated based on the grid active demand value using the following formula:

[0272]

[0273] Among them, N A is the active demand degree, A is the grid active demand value, A min is the minimum value of the grid active demand value, A max is the maximum value among the grid active demand values;

[0274] The coverage gap weight value is calculated based on the grid active demand value using the following formula:

[0275]

[0276] Among them, W cr is the coverage gap weight value;

[0277] The user gap weight value is calculated based on the grid activity demand value using the following formula:

[0278]

[0279] Among them, W m is the user gap weight value;

[0280] The active demand weight value is calculated based on the grid active demand value using the following formula:

[0281]

[0282] Among them, W A is the active demand weight value;

[0283] The competitive demand imbalance index is calculated based on the coverage gap, user gap, active demand, coverage gap weight, user gap weight, and active demand weight using the following formula:

[0284]

[0285]

[0286] in, is the competition demand imbalance index value, and Penalty is the collaborative penalty item.

[0287] 4. Calculation of indicator values:

[0288] The user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competition demand imbalance index value; the competition synergy coefficient value is calculated based on the 5G user migration probability and the competition demand imbalance index value; the active demand compensation factor is calculated based on the 5G user activity index and the competition demand imbalance index value; and the migration coverage gap ratio is calculated based on the 5G user migration probability and the competition demand imbalance index value, specifically:

[0289] Get the number of grid user complaints;

[0290] The user dissatisfaction imbalance index is calculated based on the number of grid user complaints, 5G user migration probability, and competition demand imbalance index using the following formula:

[0291] UDCII=ln(Compla int count +1)×CDII Score ×P mig

[0292] Among them, UDCII is the user dissatisfaction imbalance index value, Complaint count is the number of grid user complaints, P mig Migration probability for 5G users;

[0293] The competition synergy coefficient is calculated based on the 5G user migration probability and the competition demand imbalance index using the following formula:

[0294] k syn =P mig ×CDII score

[0295] Among them, k syn is the competitive synergy coefficient value;

[0296] The active demand compensation factor is calculated based on the 5G user activity index and the competitive demand imbalance index using the following formula:

[0297]

[0298] Among them, F comp is the active demand compensation factor, ε is the preset denominator coefficient;

[0299] The user dissatisfaction imbalance index is calculated based on the 5G user migration probability and the competition demand imbalance index using the following formula:

[0300]

[0301] Among them, R gap It is the user dissatisfaction imbalance index value.

[0302] 5. Base station site selection:

[0303] The proximity score is calculated based on the user dissatisfaction imbalance index value, the competitive synergy coefficient value, the active demand compensation factor, and the migration coverage gap ratio; and the base station site selection is carried out based on the proximity score, specifically:

[0304] The user dissatisfaction imbalance index value is normalized by the following formula to obtain the first indicator:

[0305]

[0306] Among them, N1 is the first indicator, UDCII min is the minimum value of the user dissatisfaction imbalance index value, UDCII max The maximum value of the user dissatisfaction imbalance index;

[0307] The second indicator is obtained by normalizing the competitive synergy coefficient value through the following formula:

[0308]

[0309] Where I is the total number of grids, is the competitive coordination coefficient value of the i-th grid, is the mean value of the competitive synergy coefficient, is the standard deviation of the competitive synergy coefficient value, N2 is the second indicator;

[0310] The third indicator is obtained by normalizing the active demand compensation factor using the following formula:

[0311]

[0312] Among them, N3 is the third indicator;

[0313] The migration coverage gap ratio is normalized using the following formula to obtain the fourth indicator:

[0314]

[0315] Among them, N4 is the fourth indicator;

[0316] Based on the first indicator, the second indicator, the third indicator and the fourth indicator, the corresponding proportion of the indicator is calculated using the following formula:

[0317]

[0318] Among them, P ij is the corresponding weight of the jth indicator of the i-th grid, N ij is the jth indicator of the i-th grid. When j is equal to 1, it corresponds to the first indicator, when j is equal to 2, it corresponds to the second indicator, when j is equal to 3, it corresponds to the third indicator, and when j is equal to 4, it corresponds to the fourth indicator;

[0319] The corresponding information entropy of the indicator is calculated based on the corresponding weight of the indicator using the following formula:

[0320]

[0321] Among them, e j The information entropy corresponding to the index of the j-th index;

[0322] The corresponding weight of the indicator is calculated based on the corresponding information entropy of the indicator using the following formula:

[0323]

[0324] Among them, w j is the indicator weight of the j-th indicator, and J is the total number of indicators;

[0325] Based on the first indicator, the second indicator, the third indicator, the fourth indicator and the corresponding weight of the indicator, the ideal value of the corresponding indicator is calculated using the following formula:

[0326] v ij =N ij ×w j

[0327] Among them, v ij is the ideal value of the corresponding indicator of the jth indicator of the i-th grid;

[0328] Get the maximum value of the first indicator of the i-th grid, the maximum value of the second indicator of the i-th grid, and the maximum value of the fourth indicator of the i-th grid, and take the three maximum values as the ideal solution of the positive indicator;

[0329] The forward distance is calculated based on the ideal solution of the forward indicator using the following formula:

[0330]

[0331] Among them, is the positive distance of the i-th grid, is the ideal solution for the jth positive indicator;

[0332] Get the minimum value of the third indicator of the i-th grid and use it as the ideal solution of the negative indicator;

[0333] The negative distance is calculated based on the ideal solution of the negative indicator using the following formula:

[0334]

[0335] in, is the negative distance of the i-th grid, is the ideal solution for the jth negative indicator;

[0336] The closeness score is calculated based on the positive distance and negative distance using the following formula:

[0337]

[0338] Among them, C i is the closeness score of the i-th grid;

[0339] Arrange the proximity scores in descending order to obtain a priority list of candidate base station deployments;

[0340] Base station site selection is performed based on a priority list of candidate base station deployments.

[0341] In addition, refer to Figure 2 One embodiment of the present application provides a base station site selection system, including a data acquisition module 1100, a 5G user data calculation module 1200, a competition demand imbalance index value calculation module 1300, an indicator calculation module 1400, and a base station site selection module 1500, wherein:

[0342] The data acquisition module 1100 is used to acquire first grid data and second grid data of the target area, wherein the first grid data includes the grid user density, grid reference signal received power, cell traffic, user information, first user occupancy rate, and first grid 5G coverage rate of the base station site operator, and the second grid data includes the second user occupancy rate and second grid 5G coverage rate of other competing operators;

[0343] The 5G user data calculation module 1200 is used to calculate the 5G user migration probability based on the grid user density, grid reference signal received power, cell traffic and user information; and calculate the 5G user activity index based on the grid user density, grid reference signal received power, cell traffic and user information;

[0344] The competition demand imbalance index value calculation module 1300 is used to calculate the competition demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate and the second grid 5G coverage rate;

[0345] The indicator calculation module 1400 is used to calculate a user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; calculate a competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; calculate an active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and calculate a migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value.

[0346] The base station site selection module 1500 is used to calculate the proximity score based on the user dissatisfaction imbalance index value, the competition coordination coefficient value, the active demand compensation factor and the migration coverage gap ratio; and perform base station site selection based on the proximity score.

[0347] This system obtains the first grid data and the second grid data of the target area, wherein the first grid data includes the grid user density, grid reference signal receiving power, cell traffic, user information, first user occupancy rate and first grid 5G coverage rate of the base station site operator, and the second grid data includes the second user occupancy rate and second grid 5G coverage rate of other competing operators. This application improves the data accuracy and diversity by fusing multi-source data, and calculates the 5G user migration probability based on grid user density, grid reference signal receiving power, cell traffic and user information; calculates the 5G user activity index based on grid user density, grid reference signal receiving power, cell traffic and user information, and calculates the 5G user activity index based on the first user occupancy rate, first grid 5G coverage rate, The competitive demand imbalance index value is calculated based on the second user occupancy rate and the second grid 5G coverage rate, and the user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the competitive synergy coefficient value is calculated based on the 5G user migration probability and the competitive demand imbalance index value; the active demand compensation factor is calculated based on the 5G user activity index and the competitive demand imbalance index value; the migration coverage gap ratio is calculated based on the 5G user migration probability and the competitive demand imbalance index value. This application realizes the objective sorting and real-time adjustment of base station site selection, calculates the proximity score based on the user dissatisfaction imbalance index value, the competitive synergy coefficient value, the active demand compensation factor and the migration coverage gap ratio; and performs base station site selection based on the proximity score, thereby improving the efficiency of base station site selection and resource utilization.

[0348] It should be noted that this system embodiment and the above-mentioned method embodiment are based on the same inventive concept, so the relevant content of the above-mentioned method embodiment is also applicable to this system embodiment and will not be repeated here.

[0349] Figure 3 A schematic diagram of the hardware structure of the base station site selection provided in an embodiment of the present application is shown.

[0350] The base station site selection device may include a processor 301 and a memory 302 storing computer program instructions.

[0351] Specifically, the processor 301 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0352] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 302 may include removable or non-removable (or fixed) media. Where appropriate, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 302 is a non-volatile solid-state memory.

[0353] In some embodiments, the memory 302 may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0354] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any one of the base station site selection methods in the above embodiments.

[0355] In one example, the base station site selection device may further include a communication interface 303 and a bus 310. Figure 3As shown, the processor 301 , the memory 302 , and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0356] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0357] Bus 310 includes hardware, software or both, and the parts of base station site selection equipment are coupled to each other. For example, and not limitation, bus can include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 310 can include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0358] The base station site selection device can execute the base station site selection method in the embodiment of the present application based on the three-dimensional design model, thereby realizing the combination of Figure 1 and Figure 2 Described is a base station site selection method and system.

[0359] In addition, in conjunction with the base station site selection method in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the base station site selection methods in the above embodiments is implemented.

[0360] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0361] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0362] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0363] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0364] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A base station site selection method, characterized in that: The base station site selection method includes: Obtain first grid data and second grid data for the target area, wherein the first grid data includes grid user density, grid reference signal received power, cell traffic, user information, first user occupancy rate, and first grid 5G coverage rate of the base station site operator, and the second grid data includes second user occupancy rate and second grid 5G coverage rate of other competing operators; Calculating a 5G user migration probability based on the grid user density, grid reference signal received power, cell traffic, and user information; calculating a 5G user activity index based on the grid user density, grid reference signal received power, cell traffic, and user information; Calculating a competition demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate; Calculating a user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; calculating a competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; calculating an active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and calculating a migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value. A proximity score is calculated based on the user dissatisfaction imbalance index value, the competition synergy coefficient value, the active demand compensation factor, and the migration coverage gap ratio; and a base station site is selected based on the proximity score.

2. A base station site selection method according to claim 1, characterized in that: Calculating a 5G user migration probability based on the grid user density, the grid reference signal received power, the cell traffic, and the user information, including: Obtain historical user 5G migration ratio and grid 5G coverage; The cell grid weight is calculated based on the grid user density and the grid reference signal received power using the following formula: f(RSRP g )=RSRP g +140 Among them, Weight c,g is the grid weight of the cth cell in the gth grid, α is the preset received power coefficient, β is the preset user density coefficient, f(RSRP g ) is the normalized grid reference signal received power of the g-th grid, RSRP g is the grid reference signal received power of the g-th grid, U g is the grid user density of the g-th grid, G c is the set of all grids covered by the cth cell, U g' is the grid user density of the g'th grid, f(RSRP g' ) is the normalized grid reference signal received power of the g'th grid, RSRP g' is the grid reference signal received power of the g'th grid; The grid flow is calculated based on the cell grid weight and the cell flow using the following formula: Traffic c,g =Traffic c ×Weight c,g Among them, Traffic c,g is the grid flow of the cth cell of the gth grid, Traffic c is the cell traffic of the cth cell; The historical user 5G migration ratio, the grid 5G coverage rate, and the grid traffic are input into the trained LSTM-Transformer model for prediction to obtain the 5G user migration probability, wherein the grid traffic includes grid 5G traffic and grid 4G traffic.

3. A base station site selection method according to claim 2, characterized in that: The calculating of the 5G user activity index based on the grid user density, the grid reference signal received power, the cell traffic and the user information includes: Input the historical user 5G migration ratio, the grid 5G coverage rate, and the grid traffic into the trained LSTM-Transformer model for prediction to obtain the original value of the grid 5G user activity; The 5G user activity index is calculated based on the original grid 5G user activity value using the following formula: Among them, A activity is the 5G user activity index, A raw is the original value of grid 5G user activity, A min is the minimum value of the original value of grid 5G user activity, A max It is the maximum value of the original values of 5G user activity in the grid.

4. A base station site selection method according to claim 3, characterized in that: The calculating the competition demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate includes: Obtain the number of user reports and the number of users of the base station site selection operator; Calculating a grid activity demand value based on the number of user reports and the number of users; Calculate a grid competition coverage gap value based on the first grid 5G coverage and the second grid 5G coverage; Calculating a grid competing user gap value based on the first user occupancy rate and the second user occupancy rate; The coverage gap is calculated based on the grid competition coverage gap value using the following formula: Among them, N cr is the coverage gap, cr is the grid competition coverage gap value, cr min is the minimum value of the grid coverage gap value, cr max is the maximum value of the grid coverage gap value; The user gap is calculated based on the grid competition user gap value using the following formula: Among them, N m is the user gap, m max is the maximum value of the grid competing user gap value, m min is the minimum value of the gap between grid competing users, and m is the gap between grid competing users; The activity demand degree is calculated based on the grid activity demand value using the following formula: Among them, N A is the active demand degree, A is the grid active demand value, A min is the minimum value of the grid active demand value, A max is the maximum value among the grid active demand values; The coverage gap weight value is calculated based on the grid activity demand value using the following formula: Among them, W cr is the coverage gap weight value; The user gap weight value is calculated based on the grid activity demand value using the following formula: Among them, W m is the user gap weight value; The active demand weight value is calculated based on the grid active demand value using the following formula: Among them, W A is the active demand weight value; The competitive demand imbalance index value is calculated based on the coverage gap, the user gap, the active demand, the coverage gap weight value, the user gap weight value, and the active demand weight value using the following formula: in, is the competition demand imbalance index value, and Penalty is the collaborative penalty item.

5. A base station site selection method according to claim 4, characterized in that: The calculating of the user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; the calculating of the competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; the calculating of the active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and the calculating of the migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value include: Get the number of grid user complaints; The user dissatisfaction imbalance index value is calculated based on the number of grid user complaints, the 5G user migration probability and the competition demand imbalance index value using the following formula: UDCII=ln(Complaint count +1)×CDII Score ×P mig Among them, UDCII is the user dissatisfaction imbalance index value, Complaint count is the number of grid user complaints, P mig Migration probability for 5G users; The competition coordination coefficient value is calculated based on the 5G user migration probability and the competition demand imbalance index value using the following formula: k syn =P mig ×CDII score Among them, k syn is the competitive synergy coefficient value; The active demand compensation factor is calculated based on the 5G user activity index and the competitive demand imbalance index value using the following formula: Among them, F comp is the active demand compensation factor, ε is the preset denominator coefficient; The user dissatisfaction imbalance index value is calculated based on the 5G user migration probability and the competition demand imbalance index value using the following formula: Among them, R gap It is the user dissatisfaction imbalance index value.

6. A base station site selection method according to claim 1, characterized in that: The closeness score is calculated based on the user dissatisfaction imbalance index value, the competition synergy coefficient value, the active demand compensation factor and the migration coverage gap ratio; The base station site selection is performed based on the proximity score, including: The user dissatisfaction imbalance index value is normalized by the following formula to obtain the first indicator: Among them, N1 is the first indicator, UDCII min is the minimum value of the user dissatisfaction imbalance index value, UDCII max The maximum value of the user dissatisfaction imbalance index; The competitive synergy coefficient value is normalized by the following formula to obtain the second indicator: Where I is the total number of grids, is the competitive coordination coefficient value of the i-th grid, is the mean value of the competitive synergy coefficient, is the standard deviation of the competitive synergy coefficient value, N2 is the second indicator; The active demand compensation factor is normalized using the following formula to obtain the third indicator: Among them, N3 is the third indicator; The migration coverage gap ratio is normalized by the following formula to obtain the fourth indicator: Among them, N4 is the fourth indicator; Based on the first indicator, the second indicator, the third indicator and the fourth indicator, the corresponding proportion of the indicator is calculated using the following formula: Among them, P ij is the corresponding weight of the jth indicator of the i-th grid, N ij is the jth indicator of the i-th grid. When j is equal to 1, it corresponds to the first indicator. When j is equal to 2, it corresponds to the second indicator. When j is equal to 3, it corresponds to the third indicator. When j is equal to 4, it corresponds to the fourth indicator. Based on the corresponding weights of the indicators, the information entropy corresponding to the indicators is calculated using the following formula: Among them, e j The information entropy corresponding to the index of the j-th index; Based on the information entropy corresponding to the indicator, the corresponding weight of the indicator is calculated using the following formula: Among them, w j is the indicator weight of the j-th indicator, and J is the total number of indicators; The proximity score is calculated based on the first indicator, the second indicator, the third indicator, the fourth indicator and the corresponding weights of the indicators; and a base station site is selected based on the proximity score.

7. A base station site selection method according to claim 6, characterized in that: Calculating the closeness score based on the first indicator, the second indicator, the third indicator, the fourth indicator and the corresponding weights of the indicators; The base station site selection is performed based on the proximity score, including: Based on the first indicator, the second indicator, the third indicator, the fourth indicator and the corresponding weights of the indicators, the ideal value of the corresponding indicator is calculated using the following formula: v ij =N ij ×w j Among them, v ij is the ideal value of the corresponding indicator of the jth indicator of the i-th grid; Obtain the maximum value of the first indicator of the i-th grid, the maximum value of the second indicator of the i-th grid, and the maximum value of the fourth indicator of the i-th grid, and use the three maximum values as the ideal solution of the forward indicator; The forward distance is calculated based on the ideal solution of the forward indicator using the following formula: in, is the positive distance of the i-th grid, is the ideal solution for the jth positive indicator; Get the minimum value of the third indicator of the i-th grid and use it as the ideal solution of the negative indicator; The negative distance is calculated based on the ideal solution of the negative indicator using the following formula: in, is the negative distance of the i-th grid, is the ideal solution for the jth negative indicator; The closeness score is calculated based on the positive distance and the negative distance using the following formula: Among them, C i is the closeness score of the i-th grid; Arrange the proximity scores in descending order to obtain a candidate base station deployment priority list; Base station site selection is performed based on the candidate base station deployment priority list.

8. A base station site selection system, characterized in that: The base station site selection system includes: a data acquisition module, configured to acquire first grid data and second grid data of a target area, wherein the first grid data includes grid user density, grid reference signal received power, cell traffic, user information, first user occupancy rate, and first grid 5G coverage rate of the base station site operator, and the second grid data includes second user occupancy rate and second grid 5G coverage rate of other competing operators; a 5G user data calculation module, configured to calculate a 5G user migration probability based on the grid user density, grid reference signal received power, cell traffic, and user information; and calculate a 5G user activity index based on the grid user density, grid reference signal received power, cell traffic, and user information; a competition demand imbalance index value calculation module, configured to calculate a competition demand imbalance index value based on the first user occupancy rate, the first grid 5G coverage rate, the second user occupancy rate, and the second grid 5G coverage rate; an indicator calculation module, configured to calculate a user dissatisfaction imbalance index value based on the 5G user migration probability and the competition demand imbalance index value; calculate a competition synergy coefficient value based on the 5G user migration probability and the competition demand imbalance index value; calculate an active demand compensation factor based on the 5G user activity index and the competition demand imbalance index value; and calculate a migration coverage gap ratio based on the 5G user migration probability and the competition demand imbalance index value; A base station site selection module is used to calculate a proximity score based on the user dissatisfaction imbalance index value, the competition coordination coefficient value, the active demand compensation factor and the migration coverage gap ratio; and to select a base station site based on the proximity score.

9. A base station site selection device, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute a base station site selection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the base station site selection method according to any one of claims 1 to 7.

Images