Estimation program, estimation method, and information processing device

Abstract

To make it possible to accurately estimate traffic distribution.SOLUTION: An estimation program according to an embodiment causes a computer to execute a setting process and an estimation process. The setting process sets a plurality of predetermined positions, the position of a base station, and the communication volume of the base station for each predetermined time in a target area. The estimation process, when estimating the communication volume at each predetermined position at a predetermined time on the basis of the settings in assuming a terminal communicating with the base station at each predetermined position, estimates the communication volume of each predetermined position on the basis of at least one of a first correlation between the communication volumes based on the predetermined position and another predetermined position and a second correlation between the communication volumes of the predetermined position based on time.SELECTED DRAWING: Figure 8

Description

[Technical Field]

[0001] The present invention relates to an estimation program, an estimation method, and an information processing device. [Background technology]

[0002] Conventionally, in designing a Radio Access Network (RAN), a simulator is used to input the locations of base stations (BS) and user equipment (UE), as well as the traffic demands of each UE, to simulate the connection between each UE and the BS and calculate indicators such as communication quality and power consumption. This simulation requires the spatial distribution of traffic in the target area.

[0003] Regarding this spatial traffic distribution, there is a conventional technology that sets up a grid and determines the traffic of each grid according to the overlap between the BS coverage area and the grid, based on Performance Management data (PM data) obtained during BS operation. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2010 / 110187 [Patent Document 2] Special Publication No. 2022-502902 [Patent Document 3] US Patent Application Publication No. 2018 / 0254979 [Patent Document 4] US Patent Application Publication No. 2002 / 0013152 [Non-patent literature]

[0005] [Non-Patent Document 1] G. Barlacchi, MD Nadai, R. Larcher, A. Casella, C. Chitic, G. Torrisi, F. Antonelli, A. Vespignani, A. Pentland, and B. Lepri, “A multi-source dataset of urban life in the city of Milan and the province of Trentino”, Scientific Data, vol. 2, 150055, Oct. 2015. Summary of the Invention [Problem to be solved by the invention]

[0006] However, the above-mentioned conventional techniques have a problem in that the accuracy of reproducing traffic distribution is low because they assume that traffic occurs evenly within the coverage area of ​​one BS.

[0007] In one aspect, an object of the present invention is to provide an estimation program, an estimation method, and an information processing device that can accurately estimate traffic distribution. [Means for solving the problem]

[0008] In one proposal, the estimation program causes a computer to execute a setting process and an estimation process. The setting process sets a plurality of predetermined positions, the positions of base stations, and the communication volume of the base stations for each predetermined time in a target area. The estimation process, when estimating the communication volume of each predetermined position at a predetermined time based on the settings and assuming a terminal communicating with the base station for each predetermined position, estimates the communication volume of each predetermined position based on at least one of a first correlation of communication volume based on a predetermined position and another predetermined position and a second correlation based on time of the communication volume of the predetermined position. [Effects of the Invention]

[0009] According to one embodiment, traffic distribution can be estimated with high accuracy. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is an explanatory diagram for explaining the assumption of UE at each grid point. [Figure 2] FIG. 2 is an explanatory diagram for explaining an overview of the traffic of the BS. [Figure 3] FIG. 3 is an explanatory diagram illustrating the relationship between elements. [Figure 4] FIG. 4 is an explanatory diagram illustrating an overview of BS traffic taking into account the relationships between elements. [Figure 5] FIG. 5 is a block diagram illustrating an example of a functional configuration of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of the operation of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of the traffic distribution generation process. [Figure 8] FIG. 8 is an explanatory diagram for explaining a calculation example. [Figure 9] FIG. 9 is an explanatory diagram for explaining a calculation example. [Figure 10] FIG. 10 is an explanatory diagram illustrating an outline of the traffic of the BS according to the modified example. [Figure 11] FIG. 11 is a flowchart showing an example of the operation of the information processing device according to the modified example. [Figure 12] FIG. 12 is a flowchart illustrating an example of the traffic distribution generation process. [Figure 13] FIG. 13 is an explanatory diagram illustrating an example of a computer configuration. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an estimation program, an estimation method, and an information processing device according to embodiments will be described with reference to the drawings. Components having the same functions in the embodiments will be assigned the same reference numerals, and duplicated descriptions will be omitted. Note that the estimation program, the estimation method, and the information processing device described in the following embodiments are merely examples and do not limit the embodiments. Furthermore, the following embodiments may be combined as appropriate within a range that does not cause contradictions.

[0012] First, an overview of an information processing device according to an embodiment will be described. The information processing device according to an embodiment is a device that estimates traffic distribution in a target area based on the positions of each BS and PM data, and can be, for example, a personal computer (PC). Here, the target area is set in advance as a range for determining traffic distribution, and is set to, for example, an area of ​​several square kilometers.

[0013] The information processing device according to the embodiment sets, for example, a grid for the target area, and assumes that a terminal (UE) that communicates with the BS exists at each of a plurality of grid points of the grid. Hereinafter, the plurality of grid points in the target area will be referred to as a UEgrid. Note that the grid points are an example of predetermined positions.

[0014] The UEgrid may be set arbitrarily within the target area. For example, the density of grid points may be increased in densely populated areas and decreased in sparsely populated areas.

[0015] Fig. 1 is an explanatory diagram for explaining the assumption of UEs at each grid point. As shown in Fig. 1, the information processing device according to the embodiment assumes that a UE is present at each grid point and calculates the traffic between each UE grid and the BS. As a result, the spatial traffic distribution is calculated.

[0016] Here, the relationship between the UEgrid and the PM data of the BS is assumed as follows: First, the traffic of each UEgrid is distributed to each BS according to the intensity between the UEgrid and each BS. Also, the communication volume indicated by the PM data of a certain BS is the sum of the traffic distributed from all UEgrids.

[0017] For example, traffic1 of UEgrid1 is allocated according to the intensity between UEgrid1 and BS1, BS2, etc. The allocation ratio P1 of UEgrid1 is 1 for BS1, which has the highest intensity, and 0 for the other BSs. Therefore, all of traffic1 of UEgrid1 is allocated to BS1. Also, the communication volume indicated by the PM data of BS1 is calculated based on the UEgrid allocated to BS1. 1、 This is the sum of the traffic of UEgrid2...

[0018] 2 is an explanatory diagram illustrating an overview of BS traffic. As shown in FIG. 2, the information processing device according to the embodiment calculates intensity for all UE grids and BS combinations.

[0019] Specifically, the information processing device according to the embodiment calculates the intensity (s i,k ) is calculated.

[0020]

number

[0021] where p i is the transmission power of BS(i). i,k is the path loss between UEgrid(k) and BS(i), and is calculated based on the position, frequency, height, etc. of UEgrid(k) and BS(i) as specified in 3GPP (registered trademark) (3rd Generation Partnership Project) etc.

[0022] The information processing device according to the embodiment calculates the allocation ratio to each BS for each UEgrid based on the intensity of each combination of all UEgrids and BSs, and sets a matrix P as shown in the following equation (2).

[0023]

number

[0024] where r i,k indicates the distribution ratio of traffic of UEgrid(k) to BS(i). i,k is calculated, for example, as in the following equation (3):

[0025]

number

[0026] In this equation (3), the rule is that the UE connects to the BS with the maximum intensity, and for each UE, the BS with the maximum intensity is set to 1 and the other BSs are set to 0.

[0027] The calculation of the allocation ratio is not limited to Equation (3) and may be determined appropriately based on the connection rules during network operation. For example, a rule may be used in which a UE connects to multiple BSs in descending order of intensity. The index for calculating the intensity may also be changed as needed.

[0028] Here, let x be the traffic of UEgrid, and let [x1…x m ] T In addition, PM data (traffic for each BS) is expressed as y, [y 1 …y n ] T The relationship between the UEgrid and the PM data of the BS is Px=y.

[0029] The information processing device according to the embodiment obtains the traffic of each UEgrid, that is, the traffic distribution, by solving the optimization problem of the following equation (4) based on the PM data (traffic for each BS).

[0030]

number

[0031] Here, the size of matrix P is the number of BSs × the number of UEgrids. Therefore, if the number of UEgrids to be found is greater than the number of BSs, or if the rank of matrix P is low, the number of unknowns will be greater than the number of equations, and a single solution will not be found.

[0032] Therefore, the information processing device according to the embodiment adds a correlation between the elements of x to the relational equation (Px=y) between the UEgrid and the PM data of the BS, and solves an optimization problem including the added correlation to estimate the traffic of each UEgrid.

[0033] Here, the correlation between elements of x includes a correlation of communication volume based on the position of a grid point with respect to other grid points (first correlation), and a correlation of communication volume of a grid point based on time (second correlation). First, an embodiment in which the first correlation is added to the relational equation (Px=y) between UEgrid and PM data of BS will be described, and the case in which the second correlation is added will be described later as a modified example.

[0034] The correlation of communication volume based on the position of a grid point relative to other grid points (first correlation) reproduces the correlation that the traffic between UEgrids that are close to each other should have similar values, and the correlation value corresponds to the proximity of the UEgrids.

[0035] Specifically, a two-dimensional normal distribution centered on each UEgrid position is prepared, and the traffic at a certain position (UEgrid) is taken as the sum of all the two-dimensional normal distribution values ​​at that position.

[0036] FIG. 3 is an explanatory diagram illustrating the relationship between elements. As shown in FIG. 3, UE1,y UE1 The traffic d1 of UEgrid1 in (1) is the sum of two-dimensional normal distributions h1, h2, ... centered at each position. The calculation formula for this traffic d1 is as follows:

[0037]

number

[0038] Here, m is the number of UEgrids (number of positions). The two-dimensional normal distribution hk is expressed by the following equation (6).

[0039]

number

[0040] where z k is the vector of position coordinates of UEgrid(k) (z k1 ,z k2 ) where Σ is the variance-covariance matrix as shown in the following equation (7).

[0041]

number

[0042] As shown in equation (7), in the variance-covariance matrix, the diagonal term σ2 is the distance between UEgrids, and other elements are 0.

[0043] Fig. 4 is an explanatory diagram illustrating an overview of BS traffic taking into consideration the relationship between elements. As shown in Fig. 4, the information processing device according to the embodiment calculates the above-mentioned formulas (5) to (7) and creates a matrix H storing values ​​at each UEgrid position of a two-dimensional normal distribution centered at each UEgrid position. This matrix H is shown in the following formula (8).

[0044]

number

[0045] Next, the information processing device according to the embodiment solves the optimization problem of the following equation (9) by using the height of each normal distribution as a vector u and the PM data as a vector y. Note that the vector u is a vector [u1, ...u m ] T is equivalent to

[0046]

number

[0047] Next, the information processing device according to the embodiment obtains a vector x, which is the traffic of each UEgrid, as shown in the following equation (10).

[0048]

number

[0049] Next, the information processing device according to the embodiment will be described in detail below. Fig. 5 is a block diagram showing an example of the functional configuration of the information processing device according to the embodiment.

[0050] As shown in FIG. 5, the information processing device 1 includes a communication unit 10, an input unit 20, a display unit 30, a storage unit 40, and a control unit 50.

[0051] The communication unit 10 executes data communication with external devices etc. via a network. The input unit 20 accepts operations from a user. The display unit 30 displays the processing results of the control unit 50. For example, the display unit 30 displays the traffic distribution generated by the control unit 50.

[0052] The storage unit 40 has BS information 41, UEgrid information 42, and setting information 43. For example, the storage unit 40 is realized by a memory or the like.

[0053] The BS information 41 is information about each base station (BS). Specifically, the BS information 41 includes the transmission power, frequency, position, height, and traffic (PM data) of each BS.

[0054] The UEgrid information 42 is information about each UEgrid. Specifically, the UEgrid information 42 includes the location of each UEgrid. If there is an observed value of traffic in the UEgrid at a specific time and location, the UEgrid information 42 also includes that information.

[0055] The setting information 43 includes various setting values ​​used when determining the traffic distribution, etc. For example, the setting information 43 includes values ​​related to the diagonal terms (σ2) of the variance-covariance matrix of the normal distribution.

[0056] The control unit 50 includes a setting unit 51, a traffic distribution generating unit 52, and an output unit 53. For example, the control unit 50 is realized by a processor.

[0057] The setting unit 51 is a processing unit that performs various settings related to traffic distribution based on data input via the communication unit 10, the input unit 20, etc. Specifically, the setting unit 51 receives input from a user via the communication unit 10, the input unit 20, etc., and sets the positions of multiple grid points corresponding to the target area, the position of the base station, and the communication volume of the base station for each predetermined time period (PM data). The setting unit 51 stores the set contents in the storage unit 40 as BS information 41, UEgrid information 42, and setting information 43.

[0058] The traffic distribution generation unit 52 is a processing unit that estimates the communication volume of each UE grid at a predetermined time based on the settings made by the setting unit 51. Specifically, the traffic distribution generation unit 52 includes an intensity calculation unit 52a, an allocation ratio calculation unit 52b, an inter-element relationship value calculation unit 52c, and an optimization unit 52d.

[0059] The intensity calculation unit 52a is a processing unit that calculates the intensity for all UEgrid and BS combinations based on the BS information 41 and UEgrid information 42 read from the storage unit 40. Specifically, the traffic distribution generation unit 52 calculates the intensity for each of all UEgrid and BS combinations by calculating the above-mentioned formula (1).

[0060] The allocation ratio calculation unit 52b is a processing unit that calculates the allocation ratio to each BS for each UE grid based on the intensity of each combination of all UE grids and BSs calculated by the intensity calculation unit 52a. Specifically, the allocation ratio calculation unit 52b calculates r i,k The matrix P shown in equation (2) is obtained by calculating

[0061] The inter-element relation value calculation unit 52c is a processing unit that calculates the relation (correlation) value between elements of the vector x, which is the traffic of each UEgrid. Specifically, the inter-element relation value calculation unit 52c calculates as shown in equations (5) to (8) to find a matrix H related to the correlation (first correlation) of the communication volume based on the position of the above-mentioned grid point and another grid point. The inter-element relation value calculation unit 52c also finds the correlation (second correlation) based on the time of the communication volume of the grid point (details are described in a modified example).

[0062] The optimization unit 52d is a processing unit that calculates (estimates) the traffic of each UEgrid, i.e., the traffic distribution, by solving the optimization problem of the above-mentioned equation (9) based on the PM data (traffic for each BS) included in the BS information 41. Specifically, the optimization unit 52d solves the optimization problem of equation (9) by using the height of each normal distribution as vector u and the PM data at a predetermined time as vector y. Next, the optimization unit 52d calculates vector x, which is the traffic of each UEgrid at a predetermined time, as shown in equation (10).

[0063] The output unit 53 is a processing unit that outputs the traffic (traffic distribution) for each UEgrid generated (estimated) by the traffic distribution generation unit 52. Specifically, the output unit 53 displays the traffic distribution generated by the traffic distribution generation unit 52 on the display unit 30.

[0064] 6 is a flowchart showing an example of the operation of the information processing device 1 according to the embodiment. As shown in FIG. 6, the setting unit 51 receives BS information such as the transmission power, frequency, position and height of each BS, and traffic (PM data) for each BS through input from a user, etc. The setting unit 51 also receives information such as the position of the UEgrid and the diagonal terms of the variance-covariance matrix of a normal distribution (S1). The setting unit 51 stores the received setting contents in the storage unit 40 as BS information 41, UEgrid information 42, and setting information 43.

[0065] Next, the traffic distribution generation unit 52 performs a traffic distribution generation process (S2) to generate traffic (traffic distribution) for each UEgrid based on the BS information 41, UEgrid information 42, and setting information 43 stored in the storage unit 40. Next, the output unit 53 outputs the traffic distribution, for example, by displaying the traffic distribution generated by the traffic distribution generation unit 52 on the display unit 30 (S3).

[0066] Fig. 7 is a flowchart showing an example of the traffic distribution generation process. As shown in Fig. 7, when the traffic distribution generation process starts, the intensity calculation unit 52a calculates the intensity for all combinations of UE grids and BSs (S21).

[0067] Next, the allocation ratio calculation unit 52b calculates an allocation ratio of traffic to each BS for each UEgrid according to the intensity calculated by the intensity calculation unit 52a, and sets the calculated ratio as a matrix P (S22).

[0068] Next, the inter-element relation value calculation unit 52c calculates the above-mentioned formulas (5) to (7) and creates a matrix H storing values ​​at each UEgrid position of a two-dimensional normal distribution centered at each UEgrid position (S23).

[0069] Next, the optimization unit 52d solves the optimization problem of equation (9) by using the height of each normal distribution as vector u and the PM data at a predetermined time as vector y (S24).

[0070] Next, the optimization unit 52d obtains a vector x, which is the traffic of each UEgrid at a predetermined time, as shown in equation (10) (S25).

[0071] 8 and 9 are explanatory diagrams for explaining calculation examples. As shown in Fig. 8 and Fig. 9, in calculation examples c1 and c2, PM data is obtained from original grid data based on actual traffic data.

[0072] The Original Grid data uses traffic data for Milan, obtained from the Telecom Italia Big Data Challenge. In the Original Grid data, traffic is given for each area, with each area being approximately 235m square.

[0073] The PM data was generated by simulation using the above original grid data. In the simulation, the connection between the UE and the BS was set so that the UE was connected to the BS with the highest intensity.

[0074] The calculation results R1 and R2 are the calculation results of the information processing device 1 based on this PM data, i.e., grid data (New grid) showing the traffic distribution. Here, the calculation results R1 and R2 are obtained by changing conditions such as the number of BSs, area size, and rank number of the matrix P.

[0075] The vertical columns in the calculation results R1 and R2 indicate the calculation results using the (active constraint method), (trust region reflective), and (interior point method). The horizontal columns in the calculation results R1 and R2 indicate whether or not a spatial axis distribution (two-dimensional normal distribution centered on each UEgrid position) corresponding to the correlation of communication volume based on the position of a grid point and other grid points (first correlation) is introduced. When introducing a spatial axis distribution, the σ value is changed to 58.8m and 117.5m.

[0076] In calculation examples c1 and c2, we verify whether the PM data can be converted to grid data (new grid) with a small error compared to the original grid data. The results of this verification are shown in the table on the right, which shows the RMSE (root mean square error) calculated between the original grid and the new grid.

[0077] As shown in calculation examples c1 and c2, by introducing a spatial axis distribution with an appropriate σ, a traffic distribution (New grid) close to the Original Grid is obtained.

[0078] Next, a modified example of the information processing device 1 according to the embodiment will be described. In this modified example, a correlation (first correlation) of communication volume based on the position of a lattice point and another lattice point, as well as a correlation (second correlation) based on the time of communication volume of a lattice point, are added to the relational equation (Px=y) of the PM data of the BS.

[0079] The time-based correlation of the communication volume at grid points (second correlation) reproduces the correlation that traffic at close times at each grid point should have similar values, and the correlation value for the traffic at each UEgrid corresponds to the proximity of the time.

[0080] Specifically, when a second correlation is added along with the first correlation, a three-dimensional normal distribution centered on each UEgrid position and time is prepared. Then, traffic at a certain position (UEgrid) at a certain time is calculated as the sum of all three-dimensional normal distribution values ​​at that position and time. That is, in this modified example, the two-dimensional normal distribution used when adding the first correlation is expanded to a three-dimensional normal distribution with the addition of a time axis, and the calculation formula for traffic d1 in this modified example is as follows:

[0081]

number

[0082] In addition, when adding only the second correlation to the relational equation (Px=y) of the PM data of the BS, a one-dimensional normal distribution centered on each time is prepared for each UEgrid, and the sum of the values ​​of all the one-dimensional normal distributions is used.

[0083] Fig. 10 is an explanatory diagram illustrating an overview of BS traffic according to a modified example. As shown in Fig. 10, in the modified example, the information processing device 1 creates a tensor H that stores values ​​at each UEgrid position and time of a three-dimensional normal distribution centered at each UEgrid position and time.

[0084] Next, in the modified example, the information processing device 1 solves the optimization problem of equation (12) by using the height of each normal distribution as a vector u and the PM data of all time as a matrix Y.

[0085]

number

[0086] Next, in the modified example, the information processing device 1 obtains the matrix X, which is the traffic of UEgrid at all times, as shown in equation (13).

[0087]

number

[0088] Fig. 11 is a flowchart showing an example of the operation of the information processing device 1 according to the modified example. As shown in Fig. 11, the setting unit 51 receives BS information such as the transmission power, frequency, position and height, and traffic (PM data) for each BS through input from a user, etc. The setting unit 51 also receives information such as the position of the UEgrid and the diagonal terms of the variance-covariance matrix of a normal distribution (S11). The setting unit 51 stores the received setting contents in the storage unit 40 as BS information 41, UEgrid information 42, and setting information 43.

[0089] Next, the traffic distribution generation unit 52 performs a traffic distribution generation process to generate UEgrid for all times and traffic for each time (traffic distribution over all times) based on the BS information 41, UEgrid information 42, and setting information 43 stored in 40 (S12).

[0090] Next, the output unit 53 outputs the traffic distribution, for example, by displaying the UEgrid generated by the traffic distribution generating unit 52 and the traffic distribution for each time on the display unit 30 (S13).

[0091] Fig. 12 is a flowchart showing an example of the traffic distribution generation process. As shown in Fig. 12, in the traffic distribution generation process according to the modified example, the processes of S21 and S22 similar to those in Fig. 7 are performed.

[0092] Next, the inter-element relation value calculation unit 52c creates a tensor H that stores values ​​at each UEgrid position and time of a three-dimensional normal distribution centered at each UEgrid position and time (S23a).

[0093] Next, the optimization unit 52d solves the optimization problem (S24a) by using the height of each normal distribution as a vector u and the PM data at all times as a matrix Y. Next, the optimization unit 52d obtains the matrix X, which is the traffic of the UEgrid at all times, as shown in equation (13) (S25a).

[0094] As described above, the information processing device 1 sets the positions of multiple grid points (UEgrid) corresponding to the target area, the positions of base stations (BS), and the communication volume of the base stations for each predetermined time. Based on the settings, the information processing device 1 estimates the communication volume of each grid point for a predetermined time by assuming a terminal (UE) that communicates with the base station for each grid point. In this estimation, the information processing device 1 estimates the communication volume of each grid point based on at least one of a first correlation of communication volume based on the position of the grid point and other grid points and a second correlation based on time of the communication volume of the grid point.

[0095] As a result, the information processing device 1 can take into account at least one of the first correlation and the second correlation and estimate the communication volume at each grid point, that is, the traffic distribution in the target area, with higher accuracy.

[0096] Furthermore, the information processing device 1 estimates the communication volume of each grid point by solving an optimization problem of distributing the communication volume of the base station to each grid point by including at least one of the first correlation and the second correlation in the optimization problem. As a result, at least one of the first correlation and the second correlation becomes a constraint in solving the optimization problem, and the information processing device 1 can obtain a more appropriate optimal solution (communication volume of each grid point).

[0097] Furthermore, in the information processing device 1, the first correlation is a correlation value according to the proximity of the distance between one lattice point and another lattice point, which allows the information processing device 1 to estimate the communication volume for each lattice point so that the communication volume is correlated according to the proximity of the distance between the lattice point and another lattice point.

[0098] In addition, in the information processing device 1, the second correlation is a correlation value according to the proximity of the time to the predetermined time, which allows the information processing device 1 to estimate the communication volume for each lattice point so that the communication volume is correlated according to the proximity of the time to the predetermined time.

[0099] The information processing device 1 also sets the locations of multiple base stations and the communication volume of each base station for each predetermined time. The information processing device 1 estimates the communication volume with one or more base stations among the multiple base stations set at each grid point. This allows the information processing device 1 to estimate the traffic distribution when there are multiple base stations in the target area.

[0100] Note that the components of each device shown in the figure do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0101] For example, the solution may be further restricted by adding constraints and conditions other than the first correlation and second correlation described above to solve the optimization problem. As an example, a range may be set for the traffic value of the UEgrid. Also, if the observed traffic value of the UEgrid at a specific time and location is included in the UEgrid information 42, that value may be applied to the optimization problem. Also, for a UEgrid with zero UEs, the traffic value may be set to zero.

[0102] Furthermore, since the traffic of the UEgrid is expressed by superimposing a distribution function (normal distribution), it is also possible to calculate traffic at locations other than the defined UEgrid and at times other than the time when the PM data was collected.

[0103] Furthermore, the normal distribution may be substituted with a radial basis function. The UEgrid may not be arranged in a grid pattern, but may be arranged at predetermined positions (for example, dots with varying densities corresponding to population density) that cover the entire target area and allow traffic distribution to be obtained. This embodiment is also applicable to cases where the coverage of macro BSs and small BSs overlap, such as in a heterogeneous network.

[0104] Furthermore, the various processing functions of the setting unit 51, traffic distribution generation unit 52, and output unit 53 performed by the control unit 50 of the information processing device 1 may be executed in whole or in part on a CPU (or a microcomputer such as an MPU or MCU (Micro Controller Unit)). Needless to say, the various processing functions may be executed in whole or in part on a program analyzed and executed by the CPU (or a microcomputer such as an MPU or MCU), or on hardware using wired logic. The various processing functions performed by the information processing device 1 may be executed by multiple computers working together using cloud computing.

[0105] The various processes described in the above embodiments can be realized by executing a program prepared in advance on a computer. Therefore, an example of a computer configuration (hardware) that executes a program having the same functions as those of the above embodiments will be described below. Fig. 13 is an explanatory diagram illustrating an example of a computer configuration.

[0106] 13, computer 200 includes CPU 201 for executing various types of arithmetic processing, input device 202 for receiving data input, monitor 203, and speaker 204. Computer 200 also includes medium reading device 205 for reading programs and the like from a storage medium, interface device 206 for connecting with various devices, and communication device 207 for connecting with external devices via wired or wireless communication. Computer 200 also includes RAM 208 for temporarily storing various types of information, and hard disk drive 209. Each unit (201 to 209) within computer 200 is connected to bus 210.

[0107] The hard disk drive 209 stores a program 211 for executing various processes in the functional configuration (e.g., the setting unit 51, the traffic distribution generation unit 52, and the output unit 53) described in the above embodiment. The hard disk drive 209 also stores various data 212 referenced by the program 211. The input device 202, for example, accepts input of operation information from an operator. The monitor 203, for example, displays various screens operated by the operator. The interface device 206 is connected to, for example, a printing device. The communication device 207 is connected to a communication network such as a LAN (Local Area Network), and exchanges various information with external devices via the communication network.

[0108] The CPU 201 reads out the program 211 stored in the hard disk drive 209, expands it in the RAM 208, and executes it to perform various processes related to the above-described functional configuration (for example, the setting unit 51, the traffic distribution generation unit 52, and the output unit 53). The program 211 does not have to be stored in the hard disk drive 209. For example, the program 211 stored in a storage medium readable by the computer 200 may be read out and executed. Examples of the storage medium readable by the computer 200 include portable storage media such as CD-ROMs, DVD discs, USB (Universal Serial Bus) memory, semiconductor memories such as flash memory, and hard disk drives. The program 211 may also be stored in a device connected to a public line, the Internet, a LAN, or the like, and the computer 200 may read out and execute the program 211 from the device.

[0109] The following additional notes are provided regarding the above-described embodiments.

[0110] (Supplementary Note 1) In a target area, a plurality of predetermined locations, a location of a base station, and a communication volume of the base station for each predetermined time are set, When estimating the communication volume of each of the predetermined positions at the predetermined time based on the setting, assuming a terminal that communicates with the base station for each of the predetermined positions, estimating the communication volume of each of the predetermined positions based on at least one of a first correlation of communication volume based on the predetermined position and another predetermined position and a second correlation based on time of communication volume of the predetermined position; An estimation program that causes a computer to execute processing.

[0111] (Appendix 2) The estimation program of Appendix 1, characterized in that the predetermined position is a position that corresponds to a lattice point when the target area is divided into a lattice.

[0112] (Supplementary Note 3) The estimating process estimates the communication traffic of each of the predetermined locations by solving an optimization problem of distributing the communication traffic of the base station to each of the predetermined locations, by including at least one of the first correlation and the second correlation in the optimization problem. 2. The estimation program according to claim 1,

[0113] (Note 4) The first correlation is a correlation value according to the proximity of the distance between the predetermined position and the other predetermined position. 2. The estimation program according to claim 1,

[0114] (Supplementary Note 5) The second correlation is a correlation value according to the proximity of the time to the predetermined time. 2. The estimation program according to claim 1,

[0115] (Supplementary Note 6) The setting process further sets the positions of the plurality of base stations and the communication volume of each of the base stations for each of the predetermined time periods; the estimating process estimates communication volumes with one or more of the base stations at each of the predetermined locations; 2. The estimation program according to claim 1,

[0116] (Supplementary Note 7) In a target area, a plurality of predetermined positions, a position of a base station, and a communication volume of the base station for each predetermined time are set, When estimating the communication volume at each of the predetermined positions at the predetermined time based on the setting and assuming a terminal that communicates with the base station for each of the predetermined positions, the communication volume at each of the predetermined positions is estimated based on at least one of a first correlation of communication volume based on the predetermined position and another predetermined position and a second correlation based on time of communication volume at the predetermined position. An estimation method characterized in that the processing is performed by a computer.

[0117] (Appendix 8) The estimation method of appendix 7, characterized in that the predetermined position is a position that corresponds to a lattice point when the target area is divided into a lattice.

[0118] (Supplementary Note 9) The estimating process estimates the communication traffic of each of the predetermined locations by solving an optimization problem of distributing the communication traffic of the base station to each of the predetermined locations, by including at least one of the first correlation and the second correlation in the optimization problem. 8. The estimation method according to claim 7,

[0119] (Supplementary Note 10) The first correlation is a correlation value according to the proximity of the distance between the predetermined position and the other predetermined position. 8. The estimation method according to claim 7,

[0120] (Supplementary Note 11) The second correlation is a correlation value according to the proximity of the time to the predetermined time. 8. The estimation method according to claim 7,

[0121] (Supplementary Note 12) The setting process further sets the positions of the plurality of base stations and the communication volume of each of the base stations per the predetermined time period; the estimating process estimates communication volumes with one or more of the base stations at each of the predetermined locations; 8. The estimation method according to claim 7,

[0122] (Supplementary Note 13) In a target area, a plurality of predetermined positions, a position of a base station, and a communication volume of the base station for each predetermined time are set, When estimating the communication volume at each of the predetermined positions at the predetermined time based on the setting and assuming a terminal that communicates with the base station for each of the predetermined positions, the communication volume at each of the predetermined positions is estimated based on at least one of a first correlation of communication volume based on the predetermined position and another predetermined position and a second correlation based on time of communication volume at the predetermined position. An information processing device comprising: a control unit that executes processing.

[0123] (Appendix 14) The information processing device of appendix 13, characterized in that the predetermined position is a position that corresponds to a lattice point when the target area is divided into a lattice.

[0124] (Supplementary Note 15) The estimating process estimates the communication traffic of each of the predetermined locations by solving an optimization problem of distributing the communication traffic of the base station to each of the predetermined locations, by including at least one of the first correlation and the second correlation in the optimization problem. 14. The information processing device according to claim 13,

[0125] (Supplementary Note 16) The first correlation is a correlation value according to the proximity of the distance between the predetermined position and the other predetermined position. 14. The information processing device according to claim 13,

[0126] (Supplementary Note 17) The second correlation is a correlation value according to the proximity of the time to the predetermined time. 14. The information processing device according to claim 13,

[0127] (Supplementary Note 18) The setting process further sets the positions of the plurality of base stations and the communication volume of each of the base stations per the predetermined time period; the estimating process estimates communication volumes with one or more of the base stations at each of the predetermined locations; 14. The information processing device according to claim 13, [Explanation of symbols]

[0128] 1...Information processing device 10. Communications Department 20...Input section 30...Display section 40...Storage section 41…BS information 42...UEgrid information 43...Setting information 50...Control unit 51...Settings section 52...Traffic distribution generation unit 52a...intensity calculation section 52b...Allocation ratio calculation section 52c...Inter-element relationship value calculation section 52d...Optimization section 53...Output section c1, c2…calculation example H...Matrix R1, R2…calculation results 200...Computer 201...CPU 202...input device 203...Monitor 204...Speaker 205...Media reader 206...Interface device 207...Communication equipment 208...RAM 209...Hard disk drive 210...bus 211…Program 212...Various data

Claims

1. In a target area, a plurality of predetermined positions, a position of a base station, and a communication volume of the base station for each predetermined time are set; When estimating the communication volume at each of the predetermined positions at the predetermined time based on the setting, assuming a terminal that communicates with the base station for each of the predetermined positions, the communication volume at each of the predetermined positions is estimated based on at least one of a first correlation of communication volume based on the predetermined position and another predetermined position and a second correlation based on time of communication volume at the predetermined position. An estimation program that causes a computer to execute processing.

2. 2. The estimation program according to claim 1, wherein the predetermined positions are positions that correspond to lattice points when the target area is divided into a lattice.

3. the estimating process estimates the communication traffic of each of the predetermined locations by solving an optimization problem of distributing the communication traffic of the base station to each of the predetermined locations, with at least one of the first correlation and the second correlation included in the optimization problem; 2. The estimation program according to claim 1, wherein:

4. the first correlation is a correlation value according to the proximity of the distance between the predetermined position and the other predetermined position; 2. The estimation program according to claim 1, wherein:

5. the second correlation is a correlation value according to the proximity of the time to the predetermined time; 2. The estimation program according to claim 1, wherein:

6. The setting process further includes setting positions of the plurality of base stations and the communication volume of each of the base stations for each predetermined time period; the estimating process estimates communication volumes with one or more of the base stations at each of the predetermined locations; 2. The estimation program according to claim 1, wherein:

7. In a target area, a plurality of predetermined positions, a position of a base station, and a communication volume of the base station for each predetermined time are set; When estimating the communication volume at each of the predetermined positions at the predetermined time based on the setting and assuming a terminal that communicates with the base station for each of the predetermined positions, the communication volume at each of the predetermined positions is estimated based on at least one of a first correlation of communication volume based on the predetermined position and another predetermined position and a second correlation based on time of communication volume at the predetermined position. An estimation method characterized in that the processing is performed by a computer.

8. In a target area, a plurality of predetermined positions, a position of a base station, and a communication volume of the base station for each predetermined time are set; When estimating the communication volume at each of the predetermined positions at the predetermined time based on the setting and assuming a terminal that communicates with the base station for each of the predetermined positions, the communication volume at each of the predetermined positions is estimated based on at least one of a first correlation of communication volume based on the predetermined position and another predetermined position and a second correlation based on time of communication volume at the predetermined position. An information processing device comprising: a control unit that executes processing.

Images