Tilt angle optimization device, tilt angle optimization method, and program

Abstract

The purpose of the present disclosure is to achieve a better area quality by optimizing the tilt angles of the antennas in base stations constituting a cellular network.　For this purpose, the present disclosure is a tilt angle optimizing device that optimizes the tilt angle of each of a plurality of antennas constituting a cellular network and that comprises: a performance model configuring unit that configures a performance model by modeling the relationship between the number of active users at each antenna and the performance that each antenna can provide; a user distribution estimating unit that estimates the user distribution of the active users in the periphery of each base station on the basis of respective pieces of statistical data observed at each base station; and a tilt angle optimizing unit that, on the basis of the configured performance model and the estimated user distribution, determines a tilt angle of each antenna for maximizing the area quality in a designated target area.

Description

[Technical Field]

[0001] The present disclosure relates to an invention for optimizing tilt angles of base stations that make up a cellular network. [Background technology]

[0002] A cellular network is generally composed of many base stations, each of which covers a surrounding area, allowing users to communicate via the surrounding base stations. The coverage area of ​​each base station is determined by the settings of various parameters, one of the most representative parameters being the tilt angle of the base station's antenna. The tilt angle of each antenna is often changed to eliminate coverage holes, overlapping, and improve area quality (Non-Patent Document 1). Recently, a method has been proposed for optimizing communication in cooperation with surrounding base stations (Non-Patent Document 2). [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Ferhad Kasem, Abdullah Haskou, and Zaher Dawy:On Antenna Parameters Self Optimization in LTE Cellular Networks, 2013 Third International Conference on Communications and Information Technology (ICCIT), p.44-48. [Non-patent document 2] Hasan Farooq, Ahmad Asghar: Mobility Prediction Based Proactive Dynamic Network Orchestration for Load Balancing With QoS Constraint (OPERA), IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 69, NO. 3, MARCH 2020, p.3370-3383. Summary of the Invention [Problem to be solved by the invention]

[0004] However, the invention disclosed in Non-Patent Document 1 performs optimization for each base station and does not cooperate with surrounding base stations, which raises concerns about the occurrence of coverage holes and excessive overlapping, and does not sufficiently improve area quality.

[0005] Furthermore, although the invention disclosed in Non-Patent Document 2 is a method for performing optimization in cooperation with surrounding base stations, it utilizes speed information of user terminals such as mobile phones and frequently optimizes the tilt angle in accordance with the movement of the user, making it difficult to apply to a real network where the tilt angle cannot be changed frequently for operational reasons.

[0006] The present invention has been made in view of the above points, and has as its object to achieve better area quality. [Means for solving the problem]

[0007] In order to achieve the above object, the invention of claim 1 is a tilt angle optimization device that optimizes the tilt angle of each antenna in each base station that constitutes a cellular network, comprising: a performance model construction unit that constructs a performance model by modeling the relationship between the number of active users in each antenna and the performance that each antenna can provide; a user distribution estimation unit that estimates a user distribution of active users around each base station based on each statistical data observed in each base station; and a tilt angle optimization unit that determines the tilt angle of each antenna in order to maximize area quality in a specified target area based on the constructed performance model and the estimated user distribution. the performance model construction unit uses a plurality of data sets of the number of active users and the performance observed at each actual antenna, divides the number of active users into arbitrary bins, and constructs the performance model by using the maximum value in each bin as a representative point. This is a tilt angle optimization device. [Effects of the Invention]

[0008] As described above, according to the present invention, the tilt angle of each antenna is optimized in cooperation with the antenna, thereby achieving better area quality. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a functional configuration diagram of a tilt angle optimization device according to an embodiment. [Figure 2] FIG. 1 is a hardware configuration diagram of a tilt angle optimization device according to an embodiment. [Figure 3] 10 is a flowchart illustrating a tilt angle optimization process according to an embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing attribute information. [Figure 5] FIG. 1 is a conceptual diagram showing observation information. [Figure 6] 10 is a flowchart showing detailed processing for constructing a performance model. [Figure 7] 10 is a flowchart showing detailed processing for optimizing the tilt angle. [Figure 8] FIG. 10 is a diagram illustrating the meaning of each parameter. [Figure 9] FIG. 10 is a diagram illustrating the meaning of each parameter. DETAILED DESCRIPTION OF THE INVENTION

[0010] [Functional configuration of the tilt angle optimization device] An embodiment of the present invention will be described below. The tilt angle optimization device 1 of this embodiment uses statistics already observed in an actual network to construct a performance model for the antenna of a base station and estimate the user distribution around the base station, and based on the performance model and user distribution, optimizes the antenna tilt angle in cooperation with antennas of multiple base stations to achieve better area quality. In the following, as an example, we will use antenna c i (i=1,2,…,N c ) Observation information

[0011]

number

[0012] This embodiment assumes that one base station has multiple antennas. Antenna tilt angles include fixed mechanical tilt and variable electrical tilt, but this embodiment determines the tilt angle to be changed for an antenna with remotely variable electrical tilt.

[0013] First, the functional configuration of a tilt angle optimization device 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a functional configuration diagram of the tilt angle optimization device according to this embodiment. As shown in Fig. 1, tilt angle optimization device 1 according to this embodiment has an input unit 11, a performance model construction unit 12, a user distribution estimation unit 13, a tilt angle optimization unit 14, and an output unit 15. Each of these units has a function that is realized by an instruction from a processor 101 in Fig. 2, which will be described later, based on a program.

[0014] The input unit 11 is i (i=1,2,…,N c ) attribute information and observation information.

[0015] In order to improve the area quality of the target area, the performance model construction unit 12 models the relationship between the number of active users simultaneously connected to the antenna for a group of base stations having antennas with adjustable tilt angles and the performance that can be provided to users connected to the antenna at that time, using statistical data observed at the group of base stations (for example, a circular area with a radius of 500 m or an area of ​​1 km square).

[0016] The "target area" refers to the area where the area quality is desired to be improved, and may be part or all of the geographical space divided into mesh units of any size, or may be arbitrarily designated by the operator of the telecommunications carrier.

[0017] "Area quality" refers to the quality that can be provided to all users within the target area, and may be the average value of the maximum throughput, the average value of the maximum CQI (Channel Quality Indicator), or the average value of the maximum connection completion rate.

[0018] The "number of active users" is the number of users who are actually communicating via the antenna of the base station.

[0019] The "performance that can be provided to users connected to an antenna" refers to the average throughput, the average CQI, the average connection completion rate, or the like.

[0020] In general, base station resources are limited, so the performance that can be provided to users connected to the antenna varies depending on the number of simultaneously connected active users. A performance model can be constructed by supervised learning using multiple statistical data on the number of active users and performance observed at the base station, or by assuming an appropriate function through data analysis and fitting it.

[0021] Similar to the performance model construction unit 12, the user distribution estimation unit 13 estimates the user distribution around the base station group by using statistical data observed at the base station group. The estimated user distribution is the distribution of the number of active users, and can be estimated using, for example, the technology described in Reference 1. By using this technology, the number of active users in each mesh unit can be estimated by applying a method that extends block kriging to the number of active users for each antenna observed at each base station. <Reference 1> Institute of Electronics, Information and Communication Engineers, IEICE Technical Report CQ2021-49(2021-09) "Extending Block Kriging for Estimating User Distribution in Cellular Networks" The tilt angle optimization unit 14 optimizes the tilt angle of each antenna included in the base station group based on the performance model and user distribution, with the goal of maximizing coverage quality. During optimization, the problem is treated as a black-box optimization problem, and a solution is obtained without explicitly expressing the relationship between the tilt angle setting value of each antenna and coverage quality. A black-box optimization problem is a problem of finding the maximum or minimum value of a function that has a complex input-output relationship and is difficult to express explicitly. This study can be considered a black-box optimization problem by inputting a combination of tilt angles of each antenna and outputting the coverage quality at that time. This black-box optimization problem may be solved using, for example, metaheuristic methods such as particle swarm optimization or genetic algorithms, or Bayesian optimization or reinforcement learning. Constraints may also be added, such as a constraint on the coverage of the target area or a constraint on minimum quality. For example, a coverage constraint may be a constraint that, when the target area is divided into meshes, the maximum value of RSRP (Reference Signal Received Power) in each mesh must be greater than or equal to a threshold. For example, a minimum quality constraint may be a constraint that the number of active users simultaneously connected to each antenna must be less than or equal to a threshold. When adding constraints, not only the area quality but also a penalty term that represents the penalty for not satisfying the constraints is added as the output. For example, when maximizing the output, an evaluation value that decreases according to the number of meshes where the RSRP is less than a threshold may be used, or an evaluation value that becomes 0 if the constraints are not satisfied may be used.

[0022] Output unit 15 outputs the tilt angle finally obtained by tilt angle optimization unit 14. Note that output unit 15 may output the tilt angle to any output destination. For example, output unit 15 may output the tilt angle to a server device or the like via a communication network such as the Internet, may output the tilt angle to a display or the like, or may output the tilt angle to an auxiliary storage device or the like.

[0023] [Hardware configuration of tilt angle optimization device] Next, the hardware configuration of the tilt angle optimization device 1 will be described with reference to Fig. 2. Fig. 2 is a diagram showing the hardware configuration of the tilt angle optimization device according to the embodiment.

[0024] 2, tilt angle optimization device 1 includes processor 101, memory 102, auxiliary storage device 103, connection device 104, communication device 105, and drive device 106. The hardware components constituting tilt angle optimization device 1 are connected to each other via bus 107.

[0025] The processor 101 serves as a control unit that controls the entire tilt angle optimization device 1, and includes various arithmetic devices such as a CPU (Central Processing Unit). The processor 101 reads various programs onto the memory 102 and executes them. The processor 101 may include a GPGPU (General-purpose computing on graphics processing units).

[0026] The memory 102 has a main storage device such as a ROM (Read Only Memory) and a RAM (Random Access Memory). The processor 101 and the memory 102 form a so-called computer, and the processor 101 executes various programs read onto the memory 102, thereby enabling the computer to realize various functions.

[0027] The auxiliary storage device 103 stores various programs and various information used when the processor 101 executes the various programs.

[0028] The connection device 104 is a connection device that connects the tilt angle optimization device 1 to an external device (for example, a display device 110, an operation device 111).

[0029] The communication device 105 is a communication device for transmitting and receiving various types of information to and from other devices.

[0030] The drive device 106 is a device for loading a (non-transitory) recording medium 130. The recording medium 130 here includes media that record information optically, electrically, or magnetically, such as a CD-ROM (Compact Disc Read-Only Memory), a flexible disk, or a magneto-optical disk. The recording medium 130 may also include semiconductor memory that records information electrically, such as a ROM (Read Only Memory) or flash memory.

[0031] The various programs to be installed in the auxiliary storage device 103 are installed, for example, by setting the distributed recording medium 130 in the drive device 106 and reading the various programs recorded on the recording medium 130 by the drive device 106. Alternatively, the various programs to be installed in the auxiliary storage device 103 may be installed by being downloaded from a network via the communication device 105.

[0032] [Tilt angle optimization process] Next, the tilt angle optimization process of this embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing the tilt angle optimization process according to this embodiment.

[0033] First, the input unit 11 receives the signal from the antenna c i (i=1,2,…,N c ) and input attribute information A and observation information D (S11). Figure 4 is a conceptual diagram showing attribute information. Note that "antenna ID" in Figure 4 is an example of antenna identification information for identifying an antenna. "Position" indicates a position on the earth (latitude, longitude). Figure 5 is a conceptual diagram showing observation information.

[0034] Next, the performance model construction unit 12 constructs a performance model based on the observation information D input by the input unit 11 (S12). As an example, the processing of the performance model construction unit will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of the processing in the performance model construction unit according to this embodiment.

[0035] Here, the process (S12) will be described in detail with reference to Fig. 6. The meaning of each parameter is shown in Fig. 8.

[0036] First, the performance model construction unit 12 calculates the number of active users held by the observation information D.

[0037]

number

[0038]

number

[0039]

number

[0040] Next, the performance model construction unit 12 calculates, for each bin classified in the process (S121), the maximum value of the performance values ​​held by the observation information D included in the bin.

[0041]

number

[0042] Specifically, if bin 1 contains observation information D1 and observation information D2, and the performance value held by observation information D1 is 1000 and the performance value held by observation information D2 is 2000, the performance model construction unit 12 extracts 2000 as the maximum performance value in bin 1.

[0043] Next, the performance model construction unit 12 calculates the representative value of the number of active users in the bins classified in the process (S121) and the maximum value of the performance in each bin extracted in the process (S122) as one data.

[0044]

number

[0045] As described above, in the process (S12), the performance model constructing unit 12 constructs a performance model based on the observation information input in the process (S11).

[0046] 3, the user distribution estimation unit 13 estimates a user distribution based on the attribute information and observation information input by the input unit 11 (S13). For example, the user distribution estimation unit 13 can estimate the number of active users in each mesh by using the technology described in Reference 1.

[0047] Next, tilt angle optimization unit 14 optimizes the tilt angle (S14) for the purpose of maximizing area quality based on the performance model constructed in process (S12) and the user distribution estimated in process (S13). As an example of this process (S14), the processing of the tilt angle optimization unit will be described in detail with reference to FIG. 7. FIG. 7 is a flowchart showing an example of the processing in the tilt angle optimization unit according to this embodiment. The meaning of each parameter is shown in FIG. 9.

[0048] First, the tilt angle optimization unit 14 calculates an estimated value of the tilt angle.

[0049]

number

[0050] Next, the tilt angle optimization unit 14 calculates the estimated value of the tilt angle

[0051]

number

[0052]

number

[0053] Next, the tilt angle optimization unit 14 uses a Bayesian optimization technique to find candidate solutions for the tilt angle.

[0054]

number

[0055]

number

[0056]

number

[0057]

number

[0058]

number

[0059]

number

[0060]

number

[0061]

number

[0062]

number

[0063] Next, if the termination condition is met (S147; YES), the process of FIG. 7 ends, and if the termination condition is not met (S147; NO), the process returns to the process (S143). In this case, the termination condition is when the number of repetitions of returning to the process (S143) reaches the upper limit, or when the area quality

[0064]

number

[0065] As described above, in the process (S14), tilt angle optimization unit 14 optimizes the tilt angle.

[0066] Next, in FIG. 3, the output unit 15 outputs the estimated value of the tilt angle obtained in the above-mentioned process (S14).

[0067] [Major Effects of the Embodiments] As described above, according to this embodiment, the tilt angle optimization device 1 uses statistics that have already been observed in an actual network to construct a performance model for the antenna of a base station and estimate the user distribution around the antenna of the base station, and based on the performance model and the user distribution, it is possible to optimize the tilt angle to achieve better area quality in cooperation with the antennas of multiple base stations.

[0068] Furthermore, the tilt angles of not only a single antenna but also multiple antennas can be optimized simultaneously while satisfying constraints. That is, in this embodiment, the tilt angles are not determined independently for each antenna, but are determined in cooperation with multiple antennas, thereby enabling optimization.

[0069] 〔supplement〕 The present invention is not limited to the above-described embodiment, and may have the following configurations or processes (operations).

[0070] Each functional configuration of the tilt angle optimization device 1 can be realized by a computer and a program as described above, but this program can also be provided by recording it on a (non-temporary) recording medium or via a network such as the Internet. [Explanation of symbols]

[0071] 1 Tilt angle optimization device 11 Input section 12 Performance Model Building Department 13 User distribution estimation unit 14 Tilt angle optimization section 15 Output section

Claims

1. A tilt angle optimization device that optimizes the tilt angle of each antenna in each base station that constitutes a cellular network, comprising: a performance model construction unit that constructs a performance model by modeling the relationship between the number of active users at each of the antennas and the performance that each of the antennas can provide; a user distribution estimation unit that estimates a user distribution of active users around each of the base stations based on each statistical data observed at each of the base stations; a tilt angle optimization unit that calculates a tilt angle of each of the antennas to maximize area quality in a specified target area based on the constructed performance model and the estimated user distribution; and The tilt angle optimization device, wherein the performance model construction unit uses a plurality of data pairs of the number of active users and the performance observed at each actual antenna, divides the number of active users into arbitrary bins, and constructs the performance model by using the maximum value in each bin as a representative point.

2. The tilt angle optimization device according to claim 1 , wherein the performance model construction unit constructs the performance model by applying Gaussian process regression.

3. The tilt angle optimization device according to claim 1 , wherein the tilt angle optimization unit outputs the tilt angle of each of the antennas to maximize area quality in the target area under a constraint condition.

4. The tilt angle optimization device according to claim 3 , wherein the constraint is a constraint on coverage of the target area or a constraint on a minimum area quality.

5. A tilt angle optimization method executed by a tilt angle optimization device that optimizes the tilt angle of each antenna in each base station that constitutes a cellular network, comprising: The tilt angle optimization device includes: a performance model construction process for constructing a performance model by modeling the relationship between the number of active users at each of the antennas and the performance that each of the antennas can provide; a user distribution estimation process for estimating a user distribution of active users around each base station based on each statistical data observed at each base station; a tilt angle optimization process for determining a tilt angle of each antenna to maximize area quality in a specified target area based on the constructed performance model and the estimated user distribution; Run The tilt angle optimization method includes a process of constructing the performance model by using multiple data sets of the number of active users and the performance observed at each actual antenna, dividing the number of active users into arbitrary bins, and using the maximum value in each bin as a representative point.

6. A program causing a computer to execute the method according to claim 5.

Images