An antenna weight optimization method, device and equipment of a cell

Abstract

The application discloses a cell antenna weight optimization method, device and equipment, the method comprises the following steps: acquiring cell data information of at least one cell in a preset area; dividing the preset area into at least one sub-area according to the cell data information; and optimizing the antenna weight of the cell in the at least one sub-area to obtain a processing result. Through the above method, the application realizes multi-cell weight optimization for each sub-area, thereby realizing the optimization of large-scale cells.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and specifically to a method, apparatus, and device for optimizing antenna weights in a cell. Background Technology

[0002] Massive MIMO (Multiple-Input Multiple-Output) antennas possess powerful beamforming technology, providing flexible and versatile options for wireless signal coverage in 4G / 5G networks, thereby meeting the coverage requirements of various complex scenarios. Currently, since the number of 5G users is still relatively small compared to 4G users, for reasons of technological evolution and backward compatibility, many 5G cells in the existing network are being reverse-engineered as 4G cells for use. This reduces network construction costs while facilitating subsequent equipment upgrades to 5G.

[0003] Therefore, there are currently a large number of Massive MIMO antennas in 4G / 5G networks, but these antennas cannot achieve coverage optimization or traffic activation. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a method, apparatus and device for optimizing antenna weights in a cell to overcome or at least partially solve the above problems.

[0005] According to one aspect of the present invention, a method for optimizing antenna weights in a cell is provided, the method comprising:

[0006] Obtain cell data information for at least one cell within a preset area;

[0007] Based on the cell data information, the preset area is divided into at least one sub-area;

[0008] The antenna weights of the cells in the at least one sub-region are optimized to obtain the processing result.

[0009] According to another aspect of the present invention, a cell antenna weight optimization apparatus is provided, the apparatus comprising:

[0010] The acquisition module is used to acquire cell data information of at least one cell within a preset area;

[0011] The partitioning module is used to divide the preset area into at least one sub-area based on the cell data information;

[0012] The processing module is used to optimize the antenna weights of cells in the at least one sub-region to obtain the processing result.

[0013] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0014] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-described cell antenna weight optimization method.

[0015] According to another aspect of the present invention, a computer storage medium is provided, the storage medium storing at least one executable instruction, the executable instruction causing a processor to perform an operation corresponding to the above-described cell antenna weight optimization method.

[0016] According to the solution provided in the above embodiments of the present invention, cell data information of at least one cell within a preset area is obtained; based on the cell data information, the preset area is divided into at least one sub-region; and the antenna weights of the cells in the at least one sub-region are optimized to obtain the processing result. Within a reasonable computation time and computational resource range, multi-cell weight contiguous optimization for each sub-region can be completed, thereby achieving contiguous optimization of large-scale cells.

[0017] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more obvious and understandable, specific implementation methods of the embodiments of the present invention are described below. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0019] Figure 1 A flowchart of the antenna weight optimization method for a cell provided in an embodiment of the present invention is shown;

[0020] Figure 2 A flowchart of the particle swarm optimization algorithm in a cell antenna weight optimization method provided in another embodiment of the present invention is shown;

[0021] Figure 3 This diagram illustrates the structure of the antenna weight optimization device for a cell provided in an embodiment of the present invention.

[0022] Figure 4A schematic diagram of the structure of a computing device provided in an embodiment of the present invention is shown. Detailed Implementation

[0023] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0024] Figure 1 A flowchart of the antenna weight optimization method for a cell provided in an embodiment of the present invention is shown. Figure 1 As shown, the method includes the following steps:

[0025] Step 11: Obtain cell data information from at least one cell within a preset area; the cell data information includes at least one of the following: mobile data terminal MDT data; cell engineering parameter data. MDT data is the terminal's minimum drive test data, which can be collected every 15 minutes. Cell engineering parameter data may include information such as cell location information.

[0026] Step 12: Based on the cell data information, divide the preset area into at least one sub-area;

[0027] Step 13: Optimize the antenna weights of the cells in the at least one sub-region to obtain the processing result.

[0028] In this embodiment, cell data information of at least one cell within a preset area is obtained; based on the cell data information, the preset area is divided into at least one sub-region; and the antenna weights of the cells in the at least one sub-region are optimized to obtain the processing result. Within a reasonable computation time and resource limit, multi-cell weight contiguous optimization for each sub-region can be completed, thereby achieving contiguous optimization of large-scale cells.

[0029] In an optional embodiment of the present invention, step 12 may include:

[0030] Step 121: Obtain the cell heat information based on the MDT data of the cell; here, the cell heat information can be the cell density information. In practice, due to data drift issues with MDT data (i.e., due to signal and network latency, some MDT data may appear outside the effective coverage area of ​​the cell), it is necessary to first clean the MDT data. Specifically, for integrated grid-level MDT data (MDT data that does not distinguish between cells) or grid cell-level MDT data (i.e., MDT data that distinguishes between cells), the data should be cleaned within a 60° radius to the left and right of the mechanical azimuth angle of each cell, using the mechanical azimuth angle of each cell as the normal direction. The MDT data within a sector of meters is used as the MDT data for that cell, while the MDT data outside this sector is discarded.

[0031] Step 122: Sort the cells in the preset area according to the cell heat information to obtain a cell sequence; specifically, for each cell... i The summation of the MDT data within its 120° sector effective range is denoted as Density. i This serves as a measure of the density of users within a residential community; all communities are categorized according to Density. i The numbers are s1, s2, ..., in descending order of size.

[0032] Step 123: Based on the cell engineering parameter data, cluster the cells in the cell sequence to obtain at least one cell subsequence; specifically, based on the location information in the cell engineering parameter data of each cell in the cell sequence, obtain at least one second cell in the neighborhood of the first cell; based on the ratio of the heat of at least one second cell to the heat of the first cell, cluster the cells in the cell sequence to obtain at least one cell subsequence.

[0033] Step 124: Based on the at least one cell subsequence, obtain at least one sub-region, wherein one sub-region corresponds to one cell subsequence, and the cell heat at the junction of the at least one sub-region is lower than a preset value.

[0034] Here, the specific implementation process corresponding to steps 123 and 124 includes:

[0035] 1) For each cell i Transform the latitude and longitude coordinates in its engineering parameter data into two-dimensional xy coordinate system coordinates (x i ,y i ), that is, for Cell i longitude i and latitude lat i have,

[0036] xi =lon i *20037508.34 / 180;

[0037]

[0038] 2) All unprocessed cells i Marked as unvisited;

[0039] 3) Select the cells marked as unvisited in ascending order of their serial numbers and begin the traversal calculation:

[0040] 31) Mark the selected cell p as visited;

[0041] 32) If there is at least one cell q (the second cell mentioned above) in the ε neighborhood of p (i.e., the first cell mentioned above), then:

[0042] 321) Create a new cluster i and put p into the Cluster i middle;

[0043] 322) Iterate through each cell q in descending order of density;

[0044] 323) Determine the ratio of the density of each cell q to that of cell p:

[0045] If density ratio And Cluster i The number of elements in the cluster satisfies count{Cluster i If q ≤ SizeMax, then add cell q to the Cluster. i In the middle; otherwise, cell q will not be added to the Cluster. i In the middle, q is labeled as noise;

[0046] 324) If Cluster i If it is an empty set, then cell q is marked as noise;

[0047] 325) If Cluster i Not an empty set, for Cluster i Each cell r in the range:

[0048] If cell r is unvisited: mark r as visited;

[0049] If r has at least one cell v in its ε neighborhood, and s is not a member of any cluster, determine the density ratio between the two:

[0050] if And Cluster i The number of elements in the set satisfies

[0051] count{Cluster i If}≤SizeMax, then add cell v to the Cluster. i In the middle; conversely, do not add cell v to the cluster. i In the middle, v is labeled as noise;

[0052] 326) Save Cluster i ;

[0053] 33) Otherwise, mark p as noise;

[0054] 4) Iterate through all noisy cells n;

[0055] For each noisy cell n, find the three nearest cells x, y, and z based on their distance;

[0056] If x, y, and z belong to the same cluster i Then n is directly put into the Cluster. i middle;

[0057] If x, y, and z belong to different clusters, then n is directly placed into the cluster with fewer elements;

[0058] 5) Output set {Cluster} i}, where each Cluster i This represents a set containing multiple cells;

[0059] This embodiment of the invention can divide a large area containing numerous cells into several sub-regions, each containing a number of cells. This achieves the following: 1) Maintaining a reasonable number of cells in each region, ensuring a balance between the number of cells in different sub-regions; 2) Aggregating cells based on their user activity, resulting in a distribution pattern where cluster centers have dense user populations (i.e., a large number of users) and cluster edges have sparse user populations. This facilitates decoupling between different clusters, as adjacent cells in two clusters are often sparsely populated areas (non-hotspot regions), allowing for independent optimization of the two clusters. Furthermore, considering slight differences in site planning across different regions, the hyperparameters ε, MinDens, and SizeMax in the algorithm can be adjusted to suit the cell and user distribution characteristics of different regions, demonstrating strong adaptability and practicality.

[0060] In an optional embodiment of the present invention, step 13 may include:

[0061] Step 131: Obtain the weight scheme from the weight library of cell antenna weights and encode it to obtain at least one weight scheme encoding;

[0062] Step 132 involves simulating the encoding of the at least one weighting scheme to obtain simulation results;

[0063] Step 133: Based on the simulation results, the particle swarm optimization algorithm is used to optimize the antenna weights of the cells in the at least one sub-region to obtain the processing result.

[0064] In this embodiment, the weight library can be encoded, and the specific encoding is shown in the rightmost column of Table 1 below. The rule is to sort and encode the antenna weights in the order of "electronic direction angle" -> "electronic downtilt angle" -> "horizontal beamwidth" -> "vertical beamwidth". For the electronic direction angle, it is encoded in a clockwise manner, that is, in the order of the electronic direction angle values ​​from smallest to largest.

[0065] For the electron downtilt angle, encoding is performed in ascending order of value, i.e., gradually decreasing the electron downtilt angle. For example, encoding starts from scene S1. Since the electron orientation angle is not adjustable at this time, the corresponding multiple weight schemes are encoded sequentially within the range of [1, 16] based on the electron downtilt angle value [-2°, 13°] with a step size of 1°. Then, default0 is encoded (the horizontal wavewidth is reduced by one stop compared to scene S1), also based on the electron downtilt angle value [-2°, 13°] with a step size of 1°, and the corresponding multiple weight schemes are encoded. The scheme is encoded sequentially within the range of [17,32], and then scenario S2 is encoded. Since the electron orientation angle has a higher priority than the electron downtilt angle, for an electron downtilt angle of -2°, the electron orientation angle is encoded sequentially within the range of [33,53] according to multiple weight schemes from [-10°,10°]. For an electron downtilt angle of -1°, the electron orientation angle is encoded sequentially within the range of [54,74] according to multiple weight schemes from [-10°,10°]. This process continues until all weight schemes are encoded as shown in the table below.

[0066] In this way, after encoding, the encoding of the weighting scheme changes continuously within a certain range, that is, it changes clockwise corresponding to the electronic orientation angle of the cell.

[0067] When the coding changes exceed a certain range, the electronic downtilt angle of the cell is adjusted accordingly.

[0068] When the coding changes exceed a certain range, the horizontal wavewidth is adjusted accordingly.

[0069] Finally, when the coding changes further exceed a certain magnitude, it corresponds to an adjustment of the vertical beamwidth.

[0070] Other manufacturers and other network standards (4G) use the same rules for weighting schemes.

[0071] Table 1A Manufacturer's 5G Maxive MIMO Default Weights and Corresponding Codes

[0072]

[0073]

[0074] When using simulation models to evaluate the coverage effect of each weighting scheme, it is necessary to build a simulation database for each weighting scheme. Simulation database building refers to the process of initially calculating the coverage effect of cell weights using simulation models and storing the calculation results in the database. When evaluating this weighting scheme again, it can be queried directly in the database. If a full database is built for all weighting schemes for each cell, it will consume a lot of computing resources, time resources, and storage resources. Moreover, the solution space formed by the combinatorial problem is exceptionally large, which will make the execution of the search algorithm very difficult.

[0075] To balance efficiency and accuracy, there are currently two practical methods for building a database of weighted simulation results:

[0076] 1) Reduce the order of the electron downtilt angle and electron azimuth angle in each default scenario by a large step size. For example, after reducing the order of the electron downtilt angle by a step size of 3° and the electron azimuth angle by a step size of 5°, for the S2 scenario shown in Table 1, it is equivalent to only calculating and storing the simulation results for the weight schemes coded as 33, 38, 43, 48, 53, 95, 100, ... etc. This not only greatly reduces the computational efficiency during the initial calculation (saving computational overhead and compressing computation time), but also saves a lot of storage resources when storing the results.

[0077] 2) Connect with expert experience models, that is, use the several sets of weight schemes output by the expert experience models for each cell as input to the particle swarm algorithm during calculation. In other words, only the simulation results of these weight schemes need to be calculated and stored, which can further reduce the resources required for calculation and improve the calculation efficiency.

[0078] Comparing the two methods, method 1) is equivalent to a small-scale full database construction, which searches for as many weighting schemes as possible while expending certain resources. Method 2), on the other hand, directly constructs a database from several sets of weighting schemes output by the expert experience model. This approach offers stronger targeting and effectiveness, further reducing the search space and thus improving computational efficiency compared to method 1). However, the corresponding downside is a narrower search range, potentially missing better suboptimal solutions. Therefore, both implementation methods have their advantages and disadvantages in practical database construction. Since the coding rules for the particle swarm optimization algorithm in this invention support both implementation methods, the choice of database construction method can be determined based on the specific problem encountered in practical applications.

[0079] After completing the scheme coding and simulation library construction, the joint optimization problem consisting of multiple adjacent cells can be investigated simultaneously through the simulation model, examining their RSRP (Reference Signal Received Power) and SINR (Interference-Supported Noise Ratio), thus achieving rapid contiguous optimization of multiple cells.

[0080] In an optional embodiment of the present invention, step 133 may include:

[0081] Step 1331, for the number of iterations t of the particle swarm optimization algorithm, based on the current position vector x of particle i... i (t) Calculate the objective function f i (t), the objective function f i (t) represents the simulation result of a cell within a sub-region corresponding to the current particle i; specifically, for the current position vector x of particle i... i (t) Simulation is performed to obtain the reference signal received power (RSRP) and signal-to-interference-plus-noise ratio (SINR) of the current sub-region; based on the RSRP and SINR, the objective function f is obtained. i (t).

[0082] Step 1332, obtain the f i The position vector P corresponding to the historical best value of (t) i (t);

[0083] Step 1333: When the number of iterations t reaches the set maximum number of iterations T, based on the position vector P corresponding to all particles... i (t), to obtain the historical optimal position G(t) of all particles, where G(t) represents a set of weight scheme codes formed by the weight scheme codes corresponding to the cells in a sub-region;

[0084] Step 1334: Optimize the antenna weights of cells in a sub-region according to G(t), and use the setting result as the processing result.

[0085] like Figure 2 As shown, steps 1331 to 1334, when implemented, may specifically include:

[0086] Suppose that a fast contiguous optimization is performed on m cells in a sub-region. Since the quadruples of parameters (hbw, vbw, eazimuth, edowntilt) of each cell are encoded with integers and mapped to a set of weights in the weight library, the dimension of the vector to be optimized is d = m.

[0087] like Figure 2 The diagram shows the flowchart of the particle swarm optimization algorithm based on simulation. It assumes that the number of particles participating in the optimization is N, and each particle represents a solution to the optimization problem consisting of the weight scheme encoding of m cells to be optimized. It also assumes that the initial acceleration constants c1 = 2 and c2 = 2, and generates a random vector function r1(n) ~ U[0, r...]. 1, ],r2(n)~U[0,r 2, ], n∈[1,d](here let r) 1, =1, r 2, =3), and set the inertia weight ω (default ω = 0.5) and the maximum number of iterations T, and initialize the position vector x of each particle i. i and velocity vector v i .

[0088] Taking the simulation library construction using the weight scheme output by the expert experience model as an example, for each cell to be optimized, a set of weight schemes is randomly selected from several sets of weight schemes derived from the expert experience model to constitute the position vector x of each particle i. i and velocity vector v i .

[0089] Then, for each particle i's current position vector x i (t) is used for evaluation, that is, based on vector x i (t) The simulation results of the weighting scheme for each cell corresponding to each dimension are evaluated to obtain the RSRP and SINR values ​​of the coverage area, i.e., the grid evaluation index of weighted coverage is obtained using the simulation model. Simultaneously, to ensure that the evaluation range of the optimized area is fixed, the area of ​​the optimized area is first calculated and determined, i.e., ...

[0090]

[0091] Where x represents the Mercator x, y coordinates of the grid covered by all weight schemes of all cells to be optimized (i.e., m cells), and lenx and leny are the length and width of the grid. The area calculated here is the area of ​​the largest bounding rectangle (number of grid cells) enclosed by the entire optimization evaluation area (e.g., the area enclosed by 20 cells), which remains unchanged throughout the optimization process, thus facilitating the evaluation of different weight schemes.

[0092] Then, the initial value of the current iteration round t is set to 0, and the particle swarm algorithm is iterated until t>T, and the final optimization result G(t) is output.

[0093] Specifically, for each particle i, within the optimization region, the current weighting scheme of the corresponding cell for each dimension is evaluated as a whole, and the resulting evaluation score is f. i (t), and f i The larger the value of (t), the better the quality of the current plan and plan group, and the calculation formula is:

[0094]

[0095] Among them, grid k This represents the k-th grid cell within the optimization region. k .RSRP j This represents the RSRP value of the j-th cell with RSRP signal strength. That is, for each grid k, the RSRP of the cell with the strongest signal in that grid, i.e., the RSRP of the primary coverage cell, is selected as the RSRP value for that grid. Furthermore, for the k-th grid, we have...

[0096]

[0097] grid k .RSRP indicates that the grid coordinates belong to f i (t) represents the RSRP value of the k-th cell corresponding to the weight combination. Further, considering the area of ​​the entire region to be optimized, the RSRP and SINR indices of the optimized region are obtained, i.e.,

[0098]

[0099]

[0100] From the above formula, it can be seen that when RSRP varies within the range of [-140, -44], SINR correspondingly varies linearly in the same direction within the range of [-99.7, -5.2]. Therefore, after normalizing the values ​​of both, we obtain...

[0101]

[0102] Where a1∈(0,1), a2∈(0,1) and a1+a2=1.

[0103] The historical best position vector of particle i is recorded as P. i Given G(t), the historical best positions of all particles are G(t). The updated position and velocity vectors are:

[0104] v i (t+1)=ω*v i (t)+c1*r1*(P i (t)-x i (t))+c2*r2*(G(t)-x i (t))

[0105] x i (t+1)=x i (t)+v i (t+1)

[0106] x i (t) and v i (t) represent the position vector and velocity vector of particle i in iteration t, respectively. Since they are discrete values, during the update, the actual value closest to the currently updated theoretical value is directly taken as the result. For example, for x i In the expression G(t), one dimension takes the value 52.6 after the update. However, this dimension can only take the values ​​30, 66, and 139, corresponding to three sets of weight combinations. Therefore, we choose 66, which is closest to 52.6. When t > T, the weight combination corresponding to the output G(t) is the optimal weight combination.

[0107] The above embodiments of the present invention achieve rapid optimization of the weights of contiguous Massive MIMO antennas in large-scale cells. A density-based (heat) intelligent region partitioning algorithm divides a large area containing large-scale cells into several sub-regions according to user heat. The sub-regions are characterized by similar cell sizes and lower cell heat at the junctions of sub-regions, thus decoupling the sub-regions and allowing them to be treated as independent combinatorial optimization problems for simultaneous optimization. Flexible hyperparameter configuration allows the algorithm to adapt to different regions, enabling specific analysis of specific problems and improving the algorithm's practicality. The simulation-based particle swarm optimization algorithm uses a simulation model to evaluate the weights' coverage effect on the existing network, avoiding the use of existing network user data and thus avoiding the time and resources required for a series of user data collection, cleaning, and storage processes. The improved computational and storage resources significantly enhance the algorithm's computational efficiency, thereby increasing its practicality. Furthermore, the simulation-based particle swarm optimization algorithm employs a scientifically designed weighting scheme encoding rule, suitable not only for weight adjustment logic but also applicable to Massive MIMO antenna weight tables from different manufacturers and network standards. This high compatibility makes the algorithm highly valuable for widespread application. Depending on factors such as application scale, efficiency, resources, development costs, and development cycle, multi-threaded, multi-process, or distributed architectures can be implemented to implement the algorithm. This allows for the division of density-based intelligent regions into several sub-regions, while parallel computation using the simulation-based particle swarm optimization algorithm significantly improves the algorithm's actual computational efficiency. This effectively solves the problem of difficult Massive MIMO antenna patch optimization in existing networks.

[0108] like Figure 3 As shown, embodiments of the present invention also provide a cell antenna weight optimization device 30, the device 30 comprising:

[0109] The acquisition module 31 is used to acquire cell data information of at least one cell within a preset area;

[0110] The partitioning module 32 is used to divide the preset area into at least one sub-area based on the cell data information;

[0111] The processing module 33 is used to optimize the antenna weights of the cells in the at least one sub-region to obtain the processing result.

[0112] Optionally, the cell data information includes at least one of the following: mobile data terminal MDT data; cell engineering parameter data.

[0113] Optionally, based on the cell data information, the preset area is divided into at least one sub-area, including:

[0114] Based on the MDT data of the aforementioned community, the community's popularity information is obtained;

[0115] The cells in the preset area are sorted according to the cell popularity information to obtain a cell sequence;

[0116] Based on the cell engineering parameter data, the cells in the cell sequence are clustered to obtain at least one cell subsequence;

[0117] Based on the at least one cell subsequence, at least one sub-region is obtained, wherein one sub-region corresponds to one cell subsequence, and the cell heat at the junction of the at least one sub-region is lower than a preset value.

[0118] Optionally, based on the cell engineering parameter data, the cells in the cell sequence are clustered to obtain at least one cell subsequence, including:

[0119] Based on the location information in the cell engineering parameter data of each cell in the cell sequence, at least one second cell within the neighborhood of the first cell is obtained.

[0120] Based on the ratio of the heat intensity of at least one second cell to the heat intensity of the first cell, the cells in the cell sequence are clustered to obtain at least one cell subsequence.

[0121] Optionally, the antenna weights of the cells in the at least one sub-region are optimized to obtain a processing result, including:

[0122] Encode the weight schemes from the weight library of cell antenna weights to obtain at least one weight scheme encoding;

[0123] Simulations were performed on the encoding of the at least one weighting scheme to obtain simulation results;

[0124] Based on the simulation results, the antenna weights of the cells in the at least one sub-region are optimized using the particle swarm optimization algorithm to obtain the processing results.

[0125] Optionally, based on the simulation results, the antenna weights of the cells in the at least one sub-region are optimized using a particle swarm optimization algorithm to obtain the processing result, including:

[0126] For the number of iterations t in the particle swarm optimization algorithm, based on the current position vector x of particle i... i (t) Calculate the objective function f i (t), the objective function f i (t) represents the simulation result of a cell in a sub-region corresponding to the current particle i;

[0127] Obtain the f i The position vector P corresponding to the historical best value of (t)i (t);

[0128] When the number of iterations t reaches the set maximum number of iterations T, based on the position vector P corresponding to all particles... i (t), to obtain the historical optimal position G(t) of all particles, where G(t) represents a set of weight scheme codes formed by the weight scheme codes corresponding to the cells in a sub-region;

[0129] The antenna weights of cells in a sub-region are optimized according to G(t), and the optimization result is used as the processing result.

[0130] Optionally, based on the current position vector x of particle i i (t) Calculate the objective function f i (t), including:

[0131] The current position vector x of particle i i (t) is used to perform simulation to obtain the reference signal received power RSRP and the signal-to-interference-plus-noise ratio (SINR) of the current sub-region;

[0132] Based on the RSRP and SINR, the objective function f is obtained. i (t).

[0133] It should be noted that this device is the same as the method described above. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0134] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute the cell antenna weight optimization method in any of the above method embodiments.

[0135] Figure 4 The diagram shows a structural schematic of a computing device provided in an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0136] like Figure 4 As shown, the computing device may include a processor, a communications interface, memory, and a communications bus.

[0137] The processor, communication interface, and memory communicate with each other via a communication bus. The communication interface is used to communicate with other network elements, such as clients or other servers. The processor executes programs, specifically the relevant steps in the above-described embodiment of the antenna weight optimization method for calculating the cell of the computing device.

[0138] Specifically, the program may include program code, which includes computer operation instructions.

[0139] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0140] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0141] Specifically, the program can be used to cause the processor to execute the antenna weight optimization method for the cell in any of the above method embodiments. The specific implementation of each step in the program can be found in the corresponding descriptions of the steps and units in the above-described cell antenna weight optimization method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0142] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the embodiments of the present invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the embodiments of the present invention.

[0143] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0144] Similarly, it should be understood that, in order to streamline the embodiments of the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0145] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0146] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0147] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The embodiments of the present invention can also be implemented as device or apparatus programs (e.g., computer programs and computer program products) for performing part or all of the methods described herein. Such programs implementing the embodiments of the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0148] It should be noted that the above embodiments are illustrative of the present invention and not restrictive of the invention, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the present invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for optimizing antenna weights in a cell, characterized in that, The method includes: Acquire cell data information of at least one cell within a preset area; the cell data information includes mobile data terminal MDT data and cell operating parameter data; Based on the MDT data of the cell, the cell popularity information is obtained; based on the cell popularity information, the cells in the preset area are sorted to obtain a cell sequence; based on the cell engineering parameter data, the cells in the cell sequence are clustered to obtain at least one cell subsequence; based on the at least one cell subsequence, at least one sub-region is obtained, wherein one sub-region corresponds to one cell subsequence, and the cell popularity at the junction of the at least one sub-region is lower than a preset value; Encode the weight schemes in the weight library of cell antenna weights to obtain at least one weight scheme encoding; simulate the at least one weight scheme encoding to obtain simulation results; based on the simulation results, use the particle swarm optimization algorithm to optimize the antenna weights of cells in the at least one sub-region to obtain the processing results.

2. The antenna weight optimization method for a cell according to claim 1, characterized in that, Based on the cell engineering parameter data, the cells in the cell sequence are clustered to obtain at least one cell subsequence, including: Based on the location information in the cell engineering parameter data of each cell in the cell sequence, at least one second cell within the neighborhood of the first cell is obtained. Based on the ratio of the heat intensity of at least one second cell to the heat intensity of the first cell, the cells in the cell sequence are clustered to obtain at least one cell subsequence.

3. The antenna weight optimization method for a cell according to claim 1, characterized in that, Based on the simulation results, the antenna weights of the cells in the at least one sub-region are optimized using a particle swarm optimization algorithm to obtain the following processing results: For the number of iterations t in the particle swarm optimization algorithm, based on the current position vector of particle i... Calculate the objective function The objective function The simulation results are obtained for a cell within a sub-region corresponding to the current particle i; Obtain the The position vector corresponding to the historical best value ; When the number of iterations t reaches the set maximum number of iterations T, based on the position vectors of all particles... This yields the historical best positions of all particles. The This represents a set of weight scheme codes formed by the weight scheme codes corresponding to the cells in a sub-region; According to the above The antenna weights of cells in a sub-region are optimized, and the optimization result is used as the processing result.

4. The antenna weight optimization method for a cell according to claim 3, characterized in that, Based on the current position vector of particle i Calculate the objective function ,include: The current position vector of particle i Simulation was performed to obtain the reference signal received power of the current sub-region. Signal-to-interference-plus-noise ratio ; According to the above and The objective function is obtained. .

5. A device for optimizing antenna weights in a cell, characterized in that, The device includes: The acquisition module is used to acquire cell data information of at least one cell within a preset area; the cell data information includes mobile data terminal MDT data and cell operating parameter data; The segmentation module is used to obtain the heat information of the cells based on the MDT data of the cells; sort the cells in the preset area according to the heat information of the cells to obtain a cell sequence; cluster the cells in the cell sequence according to the cell engineering parameter data to obtain at least one cell subsequence; and obtain at least one sub-region according to the at least one cell subsequence, wherein one sub-region corresponds to one cell subsequence, and the heat of the cells at the junction of the at least one sub-region is lower than a preset value. The processing module is used to obtain weight schemes from the weight library of cell antenna weights and encode them to obtain at least one weight scheme encoding; to simulate the at least one weight scheme encoding to obtain simulation results; and to optimize the antenna weights of cells in the at least one sub-region using a particle swarm optimization algorithm based on the simulation results to obtain processing results.

6. A computing device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the antenna weight optimization method of the cell as described in any one of claims 1-4.

7. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the antenna weight optimization method for a cell as described in any one of claims 1-4.

Images