Information processing device and method, terminal device for determining communication parameters in a target area

Abstract

An information processing device, comprising processing circuitry configured to receive input information regarding wireless environment characteristics of a plurality of source areas and a target area, determine at least one learning area from among a plurality of source areas based on a similarity between the wireless environment characteristics of each source area and the target area, acquire measurement data regarding communication characteristics from the at least one learning area, and determine communication parameters for wireless communication in the target area based on the measurement data.

Description

INFORMATION PROCESSING DEVICE AND METHOD, TERMINAL DEVICE FOR DETERMINING COMMUNICATION PARAMETERS IN A TARGET AREA

[0001] The present disclosure relates to an information processing device, a terminal device, an information processing method, and a program.

[0002] In wireless communication, a technology for realizing more suitable communication by appropriately controlling radio resources and communication parameters is known. For example, suitable communication can be realized by adaptively controlling a communication parameter according to a situation of a propagation path between a base station and a terminal device.

[0003] For example, the base station transmits a known signal, and the terminal device receives the known signal, so that the terminal device can estimate the situation of the propagation path. Furthermore, the base station can set a suitable communication parameter for the terminal device by feeding back the situation of the propagation path estimated by the terminal device to the base station.

[0004] In addition, in a case where there is no feedback regarding the situation of the propagation path from the terminal device, the base station can recognize an average situation of the propagation path by using a statistical propagation model (for example, a path loss model, an interference model, or the like) according to a distance to the terminal device.

[0005] International Patent Application Publication No. 2024 / 053559

[0006] However, radio wave propagation in wireless communication greatly changes depending on, for example, whether there is an obstacle between a base station as a transmission point and a terminal device as a reception point. In addition, in consideration of interference with the neighboring cell or the neighboring base station, the base station determines the communication parameter based on statistical information such as a propagation model so as to minimize the interference.

[0007] Therefore, when communication is performed with the communication parameter determined by the base station, suitable wireless communication may not be performed depending on an obstacle existing in a space (hereinafter, also referred to as a real space) in which the base station and the terminal device actually perform wireless communication. For example, when the base station determines the minimum transmission power so as to minimize interference, if there is an obstacle between the base station and the terminal device, a signal transmitted by the base station may not reach the terminal device due to the obstacle.

[0008] In order to avoid this, for example, a technology for determining a communication parameter using an estimation model generated in advance using a machine learning technology or the like is known. When the estimation model is used to determine a communication parameter, improvement in estimation accuracy of the estimation model contributes to more suitable wireless communication control, that is, the determination of the communication parameter.

[0009] Therefore, the present disclosure proposes an information processing device, a terminal device, an information processing method, and a program capable of further improving estimation accuracy of an estimation model used for determining a communication parameter.

[0010] Note that the aforementioned problem or object is merely one of a plurality of problems or objects that can be solved or achieved by the plurality of embodiments disclosed in the present specification.

[0011] An information processing device, comprising processing circuitry configured to receive input information regarding wireless environment characteristics of a plurality of source areas and a target area, determine at least one learning area from among a plurality of source areas based on a similarity between the wireless environment characteristics of each source area and the target area, acquire measurement data regarding communication characteristics from the at least one learning area, and determine communication parameters for wireless communication in the target area based on the measurement data.

[0012] Fig. 1 is a diagram illustrating an example of radio wave propagation according to a proposed technology of the present disclosure.Fig. 2 is a diagram illustrating an example of a learning area and an example of a prediction area.Fig. 3 is a diagram illustrating another example of a learning area and another example of a prediction area.Fig. 4 is a diagram illustrating an example of a learning area according to an embodiment of the present disclosure.Fig. 5 is a diagram illustrating an example of a prediction area according to an embodiment of the present disclosure.Fig. 6 is a diagram illustrating an example of communication processing according to an embodiment of the present disclosure.Fig. 7 is a diagram illustrating an example of statistical processing according to an embodiment of the present disclosure.Fig. 8 is a diagram illustrating a configuration example of a wireless communication system according to an embodiment of the present disclosure.Fig. 9 is a block diagram illustrating a configuration example of a base station according to an embodiment of the present disclosure.Fig. 10 is a block diagram illustrating a configuration example of a terminal device according to an embodiment of the present disclosure.Fig. 11 is a diagram illustrating a configuration example of a control station according to an embodiment of the present disclosure.Fig. 12 is a diagram illustrating an example of a candidate area and an example of a prediction area in a first selection method according to an embodiment of the present disclosure.Fig. 13 is a diagram illustrating an example of a candidate area and an example of a prediction area in a second selection method according to an embodiment of the present disclosure.Fig. 14 is a diagram illustrating an example of a candidate area and an example of a prediction area in a third selection method according to an embodiment of the present disclosure.Fig. 15 is a diagram illustrating an example of a candidate area and an example of a prediction area in the fourth selection method according to an embodiment of the present disclosure.Fig. 16 is a diagram illustrating an example of a first candidate area in a fifth selection method according to an embodiment of the present disclosure.Fig. 17 is a diagram illustrating an example of a second candidate area in the fifth selection method according to an embodiment of the present disclosure.Fig. 18 is a diagram illustrating an example of a prediction area in the fifth selection method according to an embodiment of the present disclosure.Fig. 19 is a diagram illustrating an example of a first comparison method according to an embodiment of the present disclosure.Fig. 20 is a diagram illustrating an example of a second comparison method according to an embodiment of the present disclosure.Fig. 21 is a diagram illustrating another example of a second comparison method according to an embodiment of the present disclosure.Fig. 22 is a diagram illustrating an extraction example in which a divided area is extracted from a learning area according to an embodiment of the present disclosure.Fig. 23 is a diagram illustrating another example of a second comparison method according to an embodiment of the present disclosure.Fig. 24 is a flowchart illustrating an example of a flow of information generation processing according to an embodiment of the present disclosure.Fig. 25 is a diagram illustrating an example of a hardware configuration of a device or the like.

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Note that, in the present specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numeral, and redundant description will be omitted.

[0014] In addition, in the present specification and the drawings, similar components of the embodiments may be distinguished by adding different alphabets and / or numbers after the same reference numeral. However, in a case where it is not necessary to particularly distinguish the similar components, only the same reference numeral is assigned. For example, a plurality of components having substantially the same functional configuration are distinguished as a terminal device 400_1 and a terminal device 400_2 as necessary. For example, in a case where it is not necessary to particularly distinguish the terminal device 400_1 and the terminal device 400_2, they are simply referred to as a terminal device 400.

[0015] One or more embodiments (including examples, modifications, and application examples) described below can each be implemented independently. Meanwhile, at least some of the plurality of embodiments described below may be appropriately combined with at least some of the other embodiments. The plurality of embodiments may include novel features different from each other. Therefore, the plurality of embodiments can contribute to solving different objects or problems, and can exhibit different effects.

[0016] <<1. Introduction>><1-1. Background>In wireless communication, it is known that communication characteristics such as reception power, throughput, interference power, signal-to-interference power ratio (SIR), and signal-to-interference and noise power ratio (SINR) strongly depend on radio wave propagation characteristics between a base station and a terminal device.

[0017] In order to improve communication characteristics, the base station is required to adaptively design communication parameters such as a modulation scheme and a coding rate according to radio wave propagation characteristics around a communication area.

[0018] For example, when the reception power in the terminal device is high, the base station may improve transmission efficiency by using a higher-order modulation scheme. On the other hand, when the reception power is low, an increase in bit error rate, symbol error rate, or the like can be suppressed by using a lower-order modulation scheme.

[0019] In the conventional radio wave propagation characteristic prediction, an empirical rule model including the Okumura Hata model has been used. The empirical rule model is constructed by statistically processing data actually measured in a representative environment such as a large city. The empirical rule model is used to estimate global radio wave propagation characteristics (such as path loss) from transmission / reception distance information and the like.

[0020] Meanwhile, in the actual environment, the radio wave propagation characteristics stochastically fluctuate due to shadowing, multipath fading, or the like. It is difficult for the empirical rule model to predict propagation characteristics having such stochastic fluctuations. Therefore, a new propagation prediction method is required to replace the empirical rule model.

[0021] <1-2. Problem>However, radio wave propagation characteristics (communication characteristics) in wireless communication may vary greatly depending on whether there is an obstacle between a base station (transmission point) and a terminal device (reception point). This point will be described with reference to Fig. 1.

[0022] Fig. 1 is a diagram illustrating an example of radio wave propagation according to a proposed technology of the present disclosure. Fig. 1(a) is a diagram illustrating an example of radio wave propagation when there is no obstacle 600. Fig. 1(b) is a diagram illustrating an example of radio wave propagation when there is an obstacle 600.

[0023] For example, it is assumed that a base station 300 transmits a signal with transmission power Ptx. When there is no obstacle 600 (see Fig. 1(a)), radio waves reach farther than when there is an obstacle 600 (see Fig. 1(b)).

[0024] In a case where communication parameters are determined by using the statistical propagation model described above, the base station determines the communication parameters so as to minimize interference with adjacent cells and surrounding base stations. This is because the statistical propagation model is different from the actual propagation path situation.

[0025] Here, the statistical propagation model is generated in a communication environment limited to a representative propagation environment such as a free space or an urban area. Therefore, if a radio wave intensity is estimated using a statistical propagation model in a specific environment, the estimation accuracy may deteriorate.

[0026] Therefore, in conventional interference design, the base station adds a large margin to interference power in consideration of the fluctuations in radio wave intensity due to obstacles, thereby avoiding interference with adjacent cells and surrounding base stations.

[0027] If the communication parameters are determined with the large margin added to minimize interference, the radio resource utilization efficiency is limited, which may cause a significant deterioration in communication performance.

[0028] In addition, when a terminal device estimates a situation of a propagation path and performs feedback, the base station 300 can determine more accurate communication parameters according to the actual situation of the transmission path. However, the base station 300 can grasp only a situation of a propagation path at a position of the terminal device where the feedback has been performed.

[0029] Therefore, when a terminal device is moving, it is not possible to more accurately grasp a propagation path situation at a destination of movement. In addition, it is not possible to more accurately grasp a propagation path situation at a place where no terminal device exists.

[0030] In addition, in a case where each of a large number of terminal devices feeds back about a propagation path situation, communication resources for the feedback becomes overhead, which causes a reduction in radio resource utilization efficiency of the entire communication system.

[0031] In addition, in a certain use case, there is a risk that a base station may not be able to obtain sufficient feedback about a propagation path situation from a terminal device. For example, the base station may obtain no or little feedback from the terminal device.

[0032] In such a situation (environment, place, or area), the communication system is required to estimate a propagation path situation of the terminal device and / or the base station with high accuracy. The propagation path situation may include, for example, communication characteristics and wireless communication environments.

[0033] Therefore, there has conventionally been known a technology using an estimation model (also referred to as a communication characteristic estimation model) that estimates (or predicts) a communication characteristic using data actually measured in a predetermined communication area. For example, the communication system generates an estimation model by using the data actually measured in the predetermined communication area, and predicts communication characteristics in the predetermined communication area by using the generated estimation model.

[0034] In this case, a communication area for which actual measurement data is acquired for generating an estimation model (hereinafter, also referred to as a learning area) and a communication area for which communication characteristics are predicted (hereinafter, referred to as a prediction area) are the same predetermined area. Therefore, it is expected that the wireless environments in the learning area and the prediction area have a certain degree or more of correlation.

[0035] This correlation increases the probability that the communication characteristics between the learning area and the prediction area are similar. Therefore, by using this estimation model, the communication system can predict the communication characteristics (e.g., communication parameters) in the prediction area with higher accuracy.

[0036] Here, an example of the estimation model is a radio environment map (REM). The REM is a map that visualizes a spatial distribution of communication characteristics in an arbitrary communication area. In recent years, the REM has been used in various fields such as an unmanned aerial vehicle (UAV) and dynamic spectrum access (DSA).

[0037] The REM is generated, for example, on the basis of data acquired measured at one or more reception points in the learning area regarding communication characteristics. That is, in order to create the REM, it is required to acquire data acquired measured at one or more reception points in the learning area regarding communication characteristics.

[0038] Here, the communication system of PTL 1 generates a communication characteristic estimation model (an example of an estimation model) using data actually measured in a certain learning area, and predicts communication characteristics in the learning area using the generated communication characteristic model. That is, in PTL 1, it is assumed that the learning area and the prediction area are the same.

[0039] Fig. 2 is a diagram illustrating an example of a learning area and an example of a prediction area. Fig. 2 illustrates an example of a case where the learning area and the prediction area are the same.

[0040] In Fig. 2, a hatched portion indicates a point where data actually measured regarding communication characteristics is acquired. The communication system generates an estimation model using the actual measurement data acquired at this point. Thereafter, the communication system predicts communication characteristics in the hatched portion using this estimation model.

[0041] In the example of Fig. 2, the learning area and the prediction area are geographically completely matched.

[0042] Fig. 3 is a diagram illustrating another example of a learning area and another example of a prediction area. Fig. 3 illustrates an example of a case where the prediction area is a part of the learning area. Even in a case where the learning area and the prediction area are not geographically completely matched, if the prediction area is a part of the learning area, it is assumed that the learning area and the prediction area are the same.

[0043] In this case, the communication system generates an estimation model using actual measurement data acquired at a hatched portion in the learning area. Using this estimation model, the communication system communication characteristics of the hatched portion in the prediction area.

[0044] The prediction in a case where the prediction area is included in the learning area as illustrated in Fig. 3 is generally called spatial interpolation. Conventionally, many studies on REMs have only assumed this spatial interpolation.

[0045] In the examples of Figs. 2 and 3, the prediction area is included in the learning area. Therefore, it is expected that the prediction area and the learning area are similar to each other to some extent, in other words, the wireless environment of the prediction area and the wireless environment the learning area have a certain degree or more of correlation.

[0046] It is known that communication characteristics strongly depend on a wireless environment in a communication area. Therefore, in a case where there is a certain degree or more of correlation in wireless environment between the learning area and the prediction area, there is a high probability that the communication characteristics between both areas are similar.

[0047] Therefore, in a case where the prediction area is included in the learning area, that is, in a case where the prediction area and the learning area are the same, it is considered that the estimation model generated using the data actually measured in the learning area can accurately predict communication characteristics of the prediction area.

[0048] On the other hand, there may be a case where the prediction area and the learning area are not the same. Fig. 4 is a diagram illustrating an example of a learning area according to an embodiment of the present disclosure. Fig. 5 is a diagram illustrating an example of a prediction area according to an embodiment of the present disclosure. Figs. 4 and 5 illustrate an example in which the learning area and the prediction area are completely different areas.

[0049] Here, in the present embodiment, the learning area and the prediction area being "different areas" means that the prediction area is not included in the learning area. That is, in the present embodiment, in a case where the learning area and the prediction area are "different areas", this means that the learning area and the prediction area are not completely the same and the prediction area is not included in the learning area.

[0050] For example, cases other than the examples of Figs. 2 and 3 corresponds to cases in which the learning area and the prediction area are "different areas". For example, as illustrated in Fig. 4, in a case where the prediction area and the learning area are geographically separated and discontinuous, it is assumed that the learning area and the prediction area are different areas.

[0051] Predicting a wireless environment when the learning area and the prediction area are different areas is generally classified as a task of spatial extrapolation.

[0052] The spatial extrapolation is different from the spatial interpolation in that it is highly likely that there is a difference in wireless environment between the learning area and the prediction area. This may result in a decrease in correlation between communication characteristics in both areas. As a result, it is generally considered that the spatial extrapolation has lower communication characteristic prediction accuracy than the spatial interpolation.

[0053] Therefore, even in a case where the learning area and the prediction area are different from each other, that is, in a case where the learning area and the prediction area are different areas, it is required to predict communication characteristics with higher accuracy.

[0054] <1-3. Outline of Proposed Technology>Fig. 6 is a diagram illustrating an example of communication processing according to an embodiment of the present disclosure. The communication processing illustrated in Fig. 6 is executed in a communication system. The communication system includes a control station 100, a base station 300, and terminal devices 400_1 to 400_3. As will be described later, the base station 300 may be a base station of a cellular wireless communication system, a wireless LAN router such as an access point for Wi-Fi (registered trademark), or the like.

[0055] Here, it is assumed that the terminal device 400_1 is a device existing in the prediction area, and the terminal devices 400_2 and 400_3 are devices existing in the learning area. Note that the number of control stations 100 included in the communication system is not limited to one, and may be two or more. The number of base stations 300 included in the communication system is not limited to one, and may be two or more. In addition, the number of terminal devices 400 existing in the prediction area is not limited to one, and may be two or more. The number of terminal devices 400 existing in the learning area is not limited to two, and may be one or four or more.

[0056] First, the base station 300 transmits a signal to the terminal devices 400_2 and 400_3 at a constant cycle or an aperiodic cycle (Step S1). This signal is, for example, a reference signal for measuring communication characteristics.

[0057] The terminal devices 400_2 and 400_3 actually measure the signal to generate actual measurement data, and transmit the generated actual measurement data to the control station 100 (Step S2). The actual measurement data includes, for example, information regarding communication characteristics. Examples of the information regarding communication characteristics include information regarding at least one of reception power (e.g., reference signal received power (RSRP), received signal strength indicator (RSSI), and reference signal received quality (RSRQ)), interference power, a signal-to-noise ratio (SNR), a signal-to-interference power ratio (SIR), a signal and interference-to-noise ratio (SINR), a throughput, a delay amount, Ping, and a position of the terminal device 400.

[0058] At this time, the terminal device 400 may transmit the actual measurement data to the control station 100 via the base station 300, or may transmit the actual measurement data to the control station 100 without passing through the base station 300. That is, the terminal device 400 can transmit the actual measurement data to the control station 100 via a cellular network.

[0059] Alternatively, the terminal device 400 may transmit the actual measurement data to the control station 100 via Wi-Fi, the Internet, or the like. Alternatively, the terminal device 400 may be directly connected to the control station 100 via a cable to transmit the actual measurement data to the control station 100.

[0060] The control station 100 is, for example, a cloud server or a database server having a calculation function. The control station 100 may be, for example, a frequency management system such as a spectrum access system (SAS) in a citizens broadband radio service (CBRS) in the United States.

[0061] The control station 100 executes statistical processing using the acquired actual measurement data (Step S3). The statistical processing will be described later with reference to Fig. 7.

[0062] The control station 100 notifies the base station 300 and / or the terminal device 400_1 of statistical information on the result of the statistical processing (Step S4).

[0063] Here, the statistical processing is processing using at least the actual measurement data. For example, the statistical processing according to the present embodiment includes processing of generating an estimation model for estimating radio wave propagation characteristics between the base station 300 and the terminal device 400. In addition, the statistical processing may include processing of estimating radio wave propagation characteristics using the estimation model.

[0064] The control station 100 may notify the base station 300 and / or the terminal device 400 of the estimated radio wave propagation characteristics as the statistical information. Alternatively, the control station 100 may notify the base station 300 and / or the terminal device 400 of communication parameters (e.g., control information for communication between the base station 300 and the terminal device 400) calculated on the basis of the estimated radio wave propagation characteristics as the statistical information.

[0065] The control station 100 may calculate statistical information in accordance with a request from the base station 300 and / or the terminal device 400. In other words, the base station 300 and / or the terminal device 400 may transmit a request for calculating statistical information to the control station 100. The base station 300 and / or the terminal device 400 requests the control station 100 to transmit statistical information, for example, by using a communication unit included in the base station 300 and / or the terminal device 400, which will be described later. The control station 100 notifies the base station 300 and / or the terminal device 400 of the statistical information in response to the request.

[0066] Here, the terminal devices 400_2 and 400_3 that transmit the actual measurement data and the terminal device 400_1 that acquires the statistical information are different devices, but these devices may be the same. That is, the terminal device 400 may transmit actual measurement data and acquire statistical information generated using the actual measurement data.

[0067] Fig. 7 is a diagram illustrating an example of statistical processing according to an embodiment of the present disclosure. The statistical processing illustrated in Fig. 7 is executed, for example, in the control station 100.

[0068] For example, the control station 100 compares at least one candidate area that is a candidate for learning area with the prediction area (Step S11). In the example of Fig. 7, the control station 100 compares a first candidate area with the prediction area, and compares a second candidate area with the prediction area.

[0069] The control station 100 selects a learning area according to the comparison result (Step S12). For example, the control station 100 selects one or more candidate areas similar to the prediction area as the learning area.

[0070] The control station 100 generates an estimation model using actual measurement data acquired in the selected learning area (Step S13).

[0071] The control station 100 estimates the estimation model, for example, using at least one of the following methods.- Statistical analysis method for linear regression analysis and multiple regression analysis- AI / ML (artificial intelligence, machine learning, deep learning)- Deep Learning- Multilayer perceptron (MLP)- Convolutional neural network (CNN)- Stochastic gradient descent- Decision tree- Random forest- Support vector machine- k-nearest neighbors- Naive bayes classifier

[0072] In addition to the aforementioned methods, there are many other methods for generating an estimation model. The estimator desirably selects an appropriate method in consideration of the principle of each method and the like. Furthermore, communication characteristics of the estimation target (i.e., the prediction area) can be used as objective variables when using AI / ML. Examples of explanatory variables include various parameters, data, and information (e.g., communication environment information) to be described later.

[0073] In addition, although the case where the control station 100 generates an estimation model as the statistical processing has been described here, the control station 100 may predict communication characteristics using the estimation model, as well as generating the estimation model, as the statistical processing.

[0074] Furthermore, the control station 100 may execute determination processing of determining whether to execute the statistical processing according to the technology proposed here before executing the statistical processing.

[0075] For example, the control station 100 determines whether the learning area and the prediction area are the same before statistical processing is performed, and determines whether to perform statistical processing according to the determination result. For example, when it is determined that the learning area and the prediction area are not the same, that is, when it is determined that the learning area and the prediction area are different, the control station 100 determines to perform statistical processing.

[0076] For example, the control station 100 plots position information (e.g., latitude and longitude information) of the learning area and the prediction area on a map, and determines whether the learning area and the prediction area are the same.

[0077] In this manner, using data regarding communication characteristics (e.g., actual measurement data) in a learning area (an example of a first area), the control station 100 according to the proposed technology generates an estimation model for estimating data regarding communication characteristics (e.g., communication parameters) in a prediction area (an example of a second area).

[0078] The control station 100 generates the estimation model using the data regarding communication characteristics in one or more learning areas similar to the prediction area. For example, the control station 100 compares candidate areas that are candidates for the learning areas with the prediction area, and selects a learning area similar to the prediction area according to the comparison result.

[0079] When the prediction area and the learning area are similar to each other, it is considered that the correlation between the wireless environments of both areas is high. Therefore, the control station 100 generates an estimation model using data regarding communication characteristics acquired in one or more learning areas similar to the prediction area, so that the estimation model can be generated using the data obtained in a learning area of which the wireless environment has a high correlation with that of the prediction area.

[0080] As a result, the control station 100 can generate an estimation model capable of predicting (estimating) data regarding the communication characteristics (e.g., communication parameters or the like) with higher accuracy.

[0081] <<2. Configuration Example of Communication System>><2-1. Overall Configuration Example of Communication System>Fig. 8 is a diagram illustrating a configuration example of a wireless communication system according to an embodiment of the present disclosure. The wireless communication system illustrated in Fig. 8 includes a control station 100, core networks 200A and 200B, base stations 300A1, 300A2, 300B1, and 300B2, and terminal devices 400A1, 400A2, 400B1, and 400B2.

[0082] The control station 100 is connected to the core network 200A in a local network N1_A via a network N1_P. The control station 100 is connected to the core network 200B in a local network N1_B via the network N1_P.

[0083] The network N1_P is, for example, a communication network such as a local area network (LAN), a wide area network (WAN), a cellular network, a fixed telephone network, a regional Internet protocol (IP) network, or the Internet. The network N1_P may include a wired network or a wireless network. Furthermore, the network N1_P may be a data network connected to the core network 200. The data network may be a service network of a telecommunications carrier, e.g., an IP multimedia subsystem (IMS) network. Furthermore, the data network may be a private network such as an intra-company network. Although only one network N1_P is illustrated in the example of Fig. 8, the number of networks N1_P is not limited to one.

[0084] Although two local networks N1_A and N1_B are illustrated in the example of Fig. 8, the number of local networks is not limited to two. The number of local networks may be one or three or more.

[0085] In the local network N1_A, the core network 200A is connected to the base stations 300A1 and 300A2. The number of base stations 300A to which the core network 200A is connected is not limited to two. The number of base stations 300A may be one or three or more.

[0086] The base station 300A1 is connected to the terminal device 400A1 by wireless communication. The base station 300A2 is connected to the terminal device 400A2 by wireless communication. The number of terminal devices 400A connected to the base station 300A is not limited to one, and may be two or more. In addition, the number of terminal devices 400A1 connected to the base station 300A1 and the number of terminal devices 400A2 connected to the base station 300A2 may be different.

[0087] The configuration of the local network N1_B is similar to that of the local network N1_A, and thus, the description thereof will be omitted.

[0088] For example, the control station 100 is an information processing device that controls a dynamic spectrum access (DSA) system. The control station 100 can control radio resources and communication parameters for at least one of the local networks N1_A and N1_B, the core networks 200A and 200B, and the base stations 300A and 300B connected to the DSA. Here, the radio resource means a resource in at least one of a time, a frequency, a MIMO layer, and a spatial domain used for wireless communication.

[0089] Note that the core networks 200A and 200B may not be installed. In this case, the control station 100 is directly connected to the base stations 300A and 300B.

[0090] The core network 200 may be disposed in one of the control station 100 and the base station 300. The core network 200 may be disposed in a distributed manner in both the control station 100 and the base station 300.

[0091] The local networks N1_A and N1_B are also referred to as private networks, and are, for example, networks having communication coverages (an example of a communication area) in predetermined areas or sites. In the local networks N1_A and N1_B, only terminal devices 400 registered in advance may be connected to at least one of the base station 300, the control station 100, and the core network 200.

[0092] Furthermore, examples of a radio access technology (RAT) used for wireless communication between the base station 300 and the terminal device 400 include cellular communication systems such as a 4G system, a 5G system, a 6G system, long term evolution (LTE), and new radio (NR). In addition, the radio access technology is not limited to the cellular communication systems. Examples of the radio access technology also include various wireless communication systems such as a wireless LAN, Bluetooth (registered trademark), and a low power wide area (LPWA) system.

[0093] In the example of Fig. 8, the control station 100 is connected to the local networks N1_A and N1_B, but the network to which the control station 100 is connected may be a public network to which subscribers are allowed to be connected.

[0094] As described above, the core network 200 may be omitted or located in the control station 100 and / or the base station 300.

[0095] Therefore, in the following description, for the sake of simplicity, it is assumed that the wireless communication system is a system in which the core network 200 is omitted. That is, the wireless communication system of the present embodiment includes the control station 100, the base station 300, and the terminal device 400.

[0096] <2-2. Configuration Example of Base Station>Next, the base station 300 will be described. The base station 300 is a communication device that operates a cell and provides a wireless communication service to one or more terminal devices 400 located inside the coverage of the cell. The cell is operated according to an arbitrary wireless communication scheme such as LTE or NR. The base station 300 is connected to the core network 200. The core network 200 is connected to a packet data network (not illustrated) via a gateway device (not illustrated). Furthermore, the base station 300 operates a beam identifiable by synchronization signal / PBCH block (SSB), and can transmit and receive data to and from one or more terminal devices 400 via one or more beams.

[0097] Note that the base station 300 may include a set of a plurality of physical or logical devices. For example, in the present embodiment, the base station 300 may be divided into a plurality of devices, a baseband unit (BBU) and an RU, and may be interpreted as an assembly of the plurality of devices. Additionally or alternatively, in the present embodiment, the base station 300 may be either or both of a BBU and an RU. The BBU and the RU may be connected by a predetermined interface (e.g., eCPRI). Additionally or alternatively, the RU may be referred to as a remote radio unit (RRU) or a radio DoT (RD). Additionally or alternatively, the RU may correspond to a gNB-DU to be described later. Additionally or alternatively, the BBU may correspond to a gNB-CU to be described later. Alternatively, the RU may be connected to a gNB-DU to be described later. Further, the BBU may correspond to a combination of the gNB-CU and the gNB-DU to be described later. Additionally or alternatively, the RU may be a device integrally formed with an antenna. The antenna (e.g., the antenna integrally formed with the RU) included in the base station 300 may adopt an advanced antenna system and support MIMO (e.g., FD-MIMO) or beamforming. In the advanced antenna system, the antenna (e.g., the antenna integrally formed with the RU) included in the base station 300 may include, for example, 64 transmission antenna ports and 64 reception antenna ports.

[0098] Furthermore, a plurality of base stations 300 may be connected to each other. The one or more base stations 300 may be included in a radio access network (RAN). That is, the base station 300 may be simply referred to as a RAN, a RAN node, an access network (AN), or an AN node. The RAN in LTE is called an enhanced universal terrestrial RAN (EUTRAN). The RAN in NR is called NGRAN. The RAN in W-CDMA (UMTS) is called UTRAN. The base station 300 in LTE is referred to as an evolved node B (eNodeB) or an eNB. That is, the EUTRAN includes one or more eNodeBs (eNBs). Furthermore, the base station 300 in NR is referred to as a gNodeB or a gNB. That is, the NGRAN includes one or more gNBs. Further, the EUTRAN may include a gNB (en-gNB) connected to a core network (EPC) in an LTE communication system (EPS). Similarly, the NGRAN may include an ng-eNB connected to a core network 5GC in a 5G communications system (5GS). Additionally or alternatively, when the base station 300 is an eNB, a gNB, or the like, it may be referred to as a 3GPP access. Additionally or alternatively, when the base station 300 is a wireless access point (e.g., Wi-Fi (registered trademark) access point), it may be referred to as a non-3GPP access. Additionally or alternatively, the base station 300 may be an optical extension device called a remote radio head (RRH). Additionally or alternatively, in a case where the base station 300 is a gNB, the base station 300 may be referred to as a combination of the gNB CU (central unit) and the gNB DU (distributed unit), which are described above, or any one of them. The gNB CU hosts a plurality of higher layers (e.g., RRC, SDAP, and PDCP) among access strata for communication with UE. Meanwhile, the gNB-DU hosts a plurality of lower layers (e.g., RLC, MAC, and PHY) among access strata. That is, among messages and information to be described later, RRC signalling (e.g., various SIBs including a MIB and a SIB1, an RRCSetup message, and an RRCReconfiguration message) may be generated by the gNB CU, while DCI and various physical channels (e.g., PDCCH and PBCH) to be described later may be generated by the gNB-DU. Alternatively, in the RRC signalling, for example, some configurations (configuration information) such as IE:cellGroupConfig may be generated by the gNB-DU, and the remaining configurations may be generated by the gNB-CU. These configurations (configuration information) may be transmitted and received by an F1 interface to be described later. The base station 300 may be configured to be able to communicate with another base station 300. For example, in a case where the plurality of base stations 300 are eNBs or a combination of an eNB and an en-gNB, the base stations 300 may be connected by an X2 interface. Additionally or alternatively, in a case where the plurality of base stations 300 are gNBs or a combination of a gn-eNB and a gNB, the devices may be connected by an Xn interface. Additionally or alternatively, in a case where the plurality of base stations 300 are a combination of a gNB CU and a gNB DU, the devices may be connected by the above-described F1 interface. The message and information (RRC signalling or DCI information and physical channel) to be described later may be communicated between the plurality of base stations 300 (e.g. via the X2, Xn, or F1 interface).

[0099] Further, as described above, the base station 300 may be configured to manage a plurality of cells. The cells provided by the base station 300 are called serving cells. The serving cells include a primary cell (PCell) and a secondary cell (SCell). In a case where dual connectivity (e.g., EUTRA-EUTRA dual connectivity, EUTRA-NR dual connectivity (ENDC), EUTRA-NR dual connectivity with 5GC, NR-EUTRA dual connectivity (NEDC), and NR-NR dual connectivity) is provided to the UE (e.g., the terminal device 400), the PCell and zero or one or more SCells(s) provided by a master node (MN) are called a master cell group. Further, the serving cell may include a PSCell (primary secondary cell or primary SCG cell). In other words, in a case where the dual connectivity is provided to the UE, the PSCell and zero or one or more SCells(s) provided by a secondary node (SN) are called a secondary cell group (SCG). Unless specially configured (for example, PUCCH on SCell), a physical uplink control channel (PUCCH) is transmitted in the PCell and the PSCell, but is not transmitted in the SCell. In addition, a radio link failure is also detected in the PCell and the PSCell, but is not detected (does not need to be detected) in the SCell. In this manner, since the PCell and the PSCell have special roles among the serving cell(s), they are also called special cells (SpCells). One downlink component carrier and one uplink component carrier may be associated with one cell. In addition, a system bandwidth corresponding to one cell may be divided into a plurality of bandwidth parts. In this case, one or more bandwidth parts (BWP) may be configured for the UE, and one bandwidth part may be used for the UE as an active BWP. Furthermore, radio resources (e.g., frequency band, numerology (subcarrier spacing), and slot format (slot configuration)) that can be used by the terminal device 400 may differ for each cell, each component carrier, or each BWP.

[0100] Fig. 9 is a block diagram illustrating a configuration example of the base station 300 according to an embodiment of the present disclosure. The base station 300 is a wireless communication device that performs wireless communication with the terminal device 400. The base station 300 is a type of communication device. Furthermore, the base station 300 is a type of information processing device.

[0101] The base station 300 illustrated in Fig. 9 includes a communication unit 310, a storage unit 320, a network communication unit 330, and a control unit 340. Note that the configuration illustrated in Fig. 9 is a functional configuration, and the hardware configuration may be different from the functional configuration. Furthermore, the functions of the base station 300 may be implemented in a distributed manner in a plurality of physically separated configurations. For example, as described above, the functions of the base station 300 may be distributed to the CU and the DU, or the CU, the DU, and the RU.

[0102] The communication unit 310 is a signal processing unit for wirelessly communicating with other wireless communication devices (e.g., the terminal device 400 and the other base stations 300). The communication unit 310 operates under the control of the control unit 340. In a case where the other wireless communication device is a terminal devices 400, the communication unit 310 may be a wireless transceiver compatible with one or more wireless access schemes. For example, the communication unit 310 is compatible with both NR and LTE. The communication unit 310 may be compatible with W-CDMA or cdma2000 in addition to NR or LTE. Furthermore, the communication unit 310 may be compatible with communication using NOMA. When the other wireless communication device is another base station 300, the communication unit 310 may be an X2 interface, an Xn interface, or an F1 interface.

[0103] The communication unit 310 includes a reception processing unit 311, a transmission processing unit 312, and an antenna 313. The communication unit 310 may include a plurality of reception processing units 311, a plurality of transmission processing units 312, and a plurality of antennas 313. Note that, in a case where the communication unit 310 is compatible with a plurality of wireless access schemes, each unit of the communication unit 310 can be individually configured for each wireless access scheme. For example, the reception processing unit 311 and the transmission processing unit 312 may be individually configured for LTE and NR.

[0104] The reception processing unit 311 processes an uplink signal received via the antenna 313. The reception processing unit 311 operates as a reception unit that receives a reception signal. The reception processing unit 311 includes a wireless reception unit 311a, a demultiplexing unit 311b, a demodulation unit 311c, and a decoding unit 311d.

[0105] The wireless reception unit 311a performs, on the uplink signal, down-conversion, removal of an unnecessary frequency component, control of an amplification level, quadrature demodulation, conversion to a digital signal, removal of a guard interval (cyclic prefix), extraction of a frequency domain signal by fast Fourier transform, and the like. The demultiplexing unit 311b demultiplexes an uplink channel such as a physical uplink shared channel (PUSCH) or a physical uplink control channel (PUCCH) and an uplink reference signal from the signal output from the wireless reception unit 311a.

[0106] The demodulation unit 311c demodulates the received signal using a modulation scheme such as binary phase shift keying (BPSK) or quadrature phase shift keying (QPSK) with respect to the modulation symbol of the uplink channel. The modulation scheme used by the demodulation unit 311c may be 16 quadrature amplitude modulation (QAM), 64QAM, or 256QAM. In this case, the signal points on the constellation do not necessarily have to be equidistant. The constellation may be a non-uniform constellation (NUC).

[0107] The decoding unit 311d performs decoding processing on the encoded bits of the demodulated uplink channel. The decoded uplink data and uplink control information are output to the control unit 340.

[0108] The transmission processing unit 312 performs processing of transmitting downlink control information and downlink data. In this manner, the transmission processing unit 312 is an acquisition unit that acquires, for example, a bit sequence of downlink control information, downlink data, or the like from the control unit 340. The transmission processing unit 312 includes an encoding unit 312a, a modulation unit 312b, a multiplexing unit 312c, and a wireless transmission unit 312d.

[0109] The encoding unit 312a encodes the downlink control information and the downlink data input from the control unit 340 using an encoding scheme such as block encoding, convolutional encoding, or turbo encoding. Note that the encoding unit 312a may perform encoding using a polar code and encoding using a low density parity check code (LDPC code).

[0110] The modulation unit 312b modulates the encoded bits output from the encoding unit 312a using a predetermined modulation scheme such as BPSK, QPSK, 16QAM, 64QAM, or 256QAM. In this case, the signal points on the constellation do not necessarily have to be equidistant. The constellation may be a non-uniform constellation.

[0111] The multiplexing unit 312c multiplexes the modulation symbol of each channel and the downlink reference signal, and arranges them in a predetermined resource element. The wireless transmission unit 312d performs various types of signal processing on the signal from the multiplexing unit 312c. For example, the wireless transmission unit 312d performs processing such as conversion from a time domain to a frequency domain by fast Fourier transform, addition of a guard interval (cyclic prefix), generation of a baseband digital signal, conversion to an analog signal, quadrature modulation, up-conversion, removal of an extra frequency component, and power amplification. The signal generated by the transmission processing unit 312 is transmitted from the antenna 313.

[0112] The storage unit 320 is a data readable / writable storage device such as a dynamic random access memory (DRAM), a static random access memory (SRAM), a flash memory, or a hard disk. The storage unit 320 functions as a storage means of the base station 300.

[0113] The network communication unit 330 is a communication interface for communicating with a node (for example, a core network 200) positioned at a high level on the network. For example, the network communication unit 330 may be a local area network (LAN) interface such as a network interface card (NIC). Additionally or alternatively, the network communication unit 330 may be an S1 interface or an NG interface for connection to the core network node. The network communication unit 330 may be a wired interface or a wireless interface. The network communication unit 330 functions as a network communication means of the base station 300.

[0114] The control unit 340 is a controller that controls each unit of the base station 300. The control unit 340 is realized by, for example, a processor (hardware processor) such as a central processing unit (CPU) or a micro processing unit (MPU). For example, the control unit 340 is realized by the processor executing various programs stored in a storage device inside the base station 300 using a random access memory (RAM) or the like as a work area. Note that the control unit 340 may be realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). Any of the CPU, the MPU, the ASIC, and the FPGA can be regarded as the controller.

[0115] <2-3. Configuration Example of Terminal Device>　Next, a configuration example of the terminal device 400 according to an embodiment of the present disclosure will be described with reference to Fig. 10. Fig. 10 is a block diagram illustrating a configuration example of the terminal device 400 according to an embodiment of the present disclosure.

[0116] The terminal device 400 is a wireless communication device that wirelessly communicates with the base station 300. The terminal device 400 is, for example, a mobile phone, a smart device (smartphone or tablet), a personal digital assistant (PDA), or a personal computer. Furthermore, the terminal device 400 may be a device such as a business camera provided with a communication function, or may be a machine to machine (M2M) device or an Internet of things (IoT) device.

[0117] Furthermore, the terminal device 400 may be capable of sidelink communication with another terminal device 400. The terminal device 400 may be able to use an automatic retransmission technology such as hybrid automatic repeat request (HARQ) when performing sidelink communication. The terminal device 400 may be capable of non-orthogonal multiple access (NOMA) communication with the base station 300. Note that the terminal device 400 may also be capable of NOMA communication in communication (sidelink) with other terminal devices 400. Furthermore, the terminal device 400 may be capable of low power wide area (LPWA) communication with other communication devices (for example, the base station 300 and another terminal device 400). In addition, the wireless communication used by the terminal device 400 may be wireless communication using millimeter waves. Note that the wireless communication (including sidelink communication) used by the terminal device 400 may be wireless communication using radio waves or wireless communication (optical wireless communication) using infrared rays or visible light.

[0118] The terminal device 400 may be simultaneously connected to a plurality of base stations 300 or a plurality of cells to perform communication. For example, in a case where one base station 300 can provide a plurality of cells, the terminal device 400 may perform carrier aggregation by using one cell as a pCell and using another cell as an sCell. Furthermore, in a case where each of the plurality of base stations 300 can provide one or more cells, the terminal device 400 can realize dual connectivity (DC) by using one or more cells managed by one base station 300 (MN (e.g., MeNB or MgNB)) as the pCell or the pCell and the sCell(s) and using one or more cells managed by the other base station 300 (SN (e.g., the SeNB or the SgNB)) as the pCell (PSCell) or the pCell (PSCell) and the sCell(s). The DC may be referred to as multi connectivity (MC).

[0119] Note that, in a case where a communication area is supported via cells of different base stations 300 (a plurality of cells having different cell identifiers or the same cell identifier), it is possible to bundle the plurality of cells and communicate between the base station 300 and the terminal device 400 by a carrier aggregation (CA) technology, a dual connectivity (DC) technology, or a multi-connectivity (MC) technology. Alternatively, via cells of different base stations 300, the terminal device 400 and the plurality of base stations 300 can communicate with each other by a coordinated transmission and reception (CoMP: coordinated multi-point transmission and reception) technology.

[0120] The terminal device 400 includes a communication unit 410, a storage unit 420, a network communication unit 430, an input / output unit 440, and a control unit 450. Note that the configuration illustrated in Fig. 10 is a functional configuration, and the hardware configuration may be different from the functional configuration. Furthermore, the functions of the terminal device 400 may be implemented in a distributed manner in a plurality of physically separated configurations.

[0121] The communication unit 410 is a signal processing unit for wirelessly communicating with other wireless communication devices (e.g., the base station 300 and the other terminal devices 400). The communication unit 410 operates under the control of the control unit 450. The communication unit 410 may be a wireless transceiver compatible with one or more wireless access schemes. For example, the communication unit 410 is compatible with both NR and LTE. The communication unit 410 may be compatible with W-CDMA or cdma2000 in addition to NR or LTE. Furthermore, the communication unit 410 may be compatible with communication using NOMA.

[0122] The communication unit 410 includes a reception processing unit 411, a transmission processing unit 412, and an antenna 413. The communication unit 410 may include a plurality of reception processing units 411, a plurality of transmission processing units 412, and a plurality of antennas 413.

[0123] The configurations of the communication unit 410, the reception processing unit 411, the transmission processing unit 412, and the antenna 413 are similar to those of the communication unit 310, the reception processing unit 311, the transmission processing unit 312, and the antenna 313 of the base station 300.

[0124] The storage unit 420 is a data readable / writable storage device, such as a DRAM, an SRAM, a flash memory, or a hard disk. The storage unit 420 functions as a storage means of the terminal device 400.

[0125] The network communication unit 430 is a communication interface for communicating with other devices connected via a network. For example, the network communication unit 430 is a LAN interface such as an NIC. The network communication unit 430 may be a wired interface or a wireless interface. The network communication unit 430 functions as a network communication means of the terminal device 400. The network communication unit 430 communicates with other devices under the control of the control unit 450.

[0126] The input / output unit 440 is a user interface for exchanging information with the user. For example, the input / output unit 440 is an operation device for the user to perform various operations, such as a keyboard, a mouse, an operation key, and a touch panel. Alternatively, the input / output unit 440 is a display device such as a liquid crystal display or an organic electroluminescence (EL) display. The input / output unit 440 may be an acoustic device such as a speaker or a buzzer. The input / output unit 440 may be a lighting device such as a light emitting diode (LED) lamp. The input / output unit 440 functions as an input / output means (input means, output means, operation means, or notification means) of the terminal device 400.

[0127] The control unit 450 is a controller that controls each unit of the terminal device 400. The control unit 450 is realized by, for example, a processor such as a CPU, an MPU, or a GPU. For example, the control unit 450 is realized by the processor executing various programs stored in a storage device inside the terminal device 400 using a RAM or the like as a work area. Note that the control unit 450 may be realized by an integrated circuit such as an ASIC or an FPGA. Any of the CPU, the MPU, the GPU, the ASIC, and the FPGA can be regarded as a controller.

[0128] <2-4. Configuration Example of Control Station>Fig. 11 is a diagram illustrating a configuration example of the control station 100 according to an embodiment of the present disclosure. As described above, the control station 100 is, for example, an information processing device that controls a dynamic spectrum access (DSA) system. As illustrated in Fig. 11, the control station 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0129] (Communication Unit 110)The communication unit 110 is a communication interface for communicating with another device (e.g., the base station 300). The communication unit 110 may be a network interface or a device connection interface. For example, the communication unit 110 may be a LAN interface such as an NIC, or may be a universal serial bus (USB) interface including a USB host controller, a USB port, and the like. Furthermore, the communication unit 110 may be a wired interface or a wireless interface. The communication unit 110 functions as a communication means of the control station 100. The communication unit 110 communicates with the base station 300 under the control of the control unit 130.

[0130] (Storage Unit 120)The storage unit 120 is a data readable / writable storage device, such as a DRAM, an SRAM, a flash memory, or a hard disk. The storage unit 120 functions as a storage means of the control station 100.

[0131] (Control Unit 130)　The control unit 130 is a controller that controls each unit of the control station 100. The control unit 130 is realized by, for example, a processor such as a CPU, an MPU, or a GPU.

[0132] For example, the control unit 130 is realized by the processor executing various programs stored in a storage device inside the control station 100 using a RAM or the like as a work area. Note that the control unit 130 may be realized by an integrated circuit such as an ASIC or an FPGA. Any of the CPU, the MPU, the GPU, the ASIC, and the FPGA can be regarded as a controller.

[0133] The control unit 130 includes a selection unit 131, an acquisition unit 132, a generation unit 133, a determination unit 134, and a notification unit 135. Each of the blocks (the selection unit 131 to the notification unit 135) constituting the control unit 130 is a functional block indicating a function of control unit 130.

[0134] These functional blocks may be software blocks or hardware blocks. For example, each of the functional blocks described above may be one software module realized by software (including a microprogram) or one circuit block on a semiconductor chip (die). Of course, each functional block may be one processor or one integrated circuit. The functional blocks may be configured in any manner.

[0135] Note that the control unit 130 may be configured by functional units different from the above-described functional blocks.

[0136] (Selection Unit 131)For example, the selection unit 131 selects a learning area for which data to be used for generating an estimation model is acquired. For example, the selection unit 131 selects a learning area to be used for generating an estimation model from among candidate areas that are one or more candidates for learning areas.

[0137] For example, the selection unit 131 selects a learning area similar to a prediction area for which data regarding communication characteristics is predicted using the estimation model. For example, the selection unit 131 selects an area having a similar communication environment, more specifically, an area having a high correlation in communication environment, as the learning area, from among the candidate areas.

[0138] The selection unit 131 notifies the generation unit 133 of the selected learning area.

[0139] Note that a method of selecting a learning area by the selection unit 131 will be described in detail later.

[0140] (Acquisition Unit 132)The acquisition unit 132 acquires information to be used by the generation unit 133 via the communication unit 110. For example, the acquisition unit 132 acquires data actually measured in the above-described predetermined area from the base station 300 and / or the terminal device 400 via the communication unit 110. Here, the acquisition unit 132 acquires data actually measured an estimation area from the base station 300 and / or the terminal device 400.

[0141] The acquisition unit 132 receives information that can be transmitted from at least one of the local network, the core network 200, the base station 300, the terminal device 400, and other communication nodes via the communication unit 110.

[0142] The acquisition unit 132 outputs the acquired information to the generation unit 133.

[0143] (Generation Unit 133)The generation unit 133 executes generation processing of generating an estimation model using the actual measurement data acquired by the acquisition unit 132.

[0144] The generation unit 133 generates the estimation model on the basis of data actually measured in at least one learning area. This estimation model is, for example, a communication characteristic estimation model used for estimating communication characteristics (radio wave propagation environment). The control station 100 generates the estimation model from the data actually measured in the learning area, for example, by machine learning.

[0145] Here, the actual measurement data used by the control station 100 to generate the estimation model is, for example, data regarding communication characteristics measured in the learning area selected by the selection unit 131.

[0146] The generation unit 133 outputs the generated estimation model to the determination unit 134.

[0147] (Determination Unit 134)The determination unit 134 estimates estimation data regarding communication characteristics in the prediction area by executing estimation processing using the estimation model. For example, the determination unit 134 determines communication parameters between the base station 300 and the terminal device 400 in the prediction area by using the estimation data.

[0148] For example, the determination unit 134 estimates the estimation data regarding communication characteristics in the prediction area using the estimation model generated on the basis of the data actually measured in the learning area regarding the communication characteristics.

[0149] For example, the determination unit 134 inputs area data regarding the prediction area to the estimation model. The determination unit 134 uses the output of the estimation model when the area data is input as the estimation data. The area data may include, for example, communication environment information to be described later.

[0150] In addition, the area data may include data actually measured in the prediction area. In this case, the number of pieces of the data actually measured in the prediction area may be smaller than, for example, the number of pieces of the data actually measured in the prediction area.

[0151] In this manner, the determination unit 134 may estimate the estimation data using the data actually measured in the prediction area. Alternatively, the determination unit 134 may correct the estimation data using the data actually measured in the prediction area. The determination unit 134 may correct (retrain) the estimation model using the data actually measured in the prediction area.

[0152] For example, the determination unit 134 determines communication parameters between the base station 300 and the terminal device 400 in the prediction area by using the estimation data. The determination unit 134 outputs the determined communication parameters to the notification unit 135.

[0153] (Notification Unit 135)The notification unit 135 notifies the base station 300 and / or the terminal device 400 of the communication parameters determined by the determination unit 134.

[0154] <<3. Method of Selecting Learning Area>>As described above, the control station 100 selects a learning area from among one or more candidate areas. For example, the control station 100 selects one or more learning areas by comparing the candidate areas with the prediction area. For example, the control station 100 selects one or more candidate areas whose communication environments are similar to that of the prediction area as the learning areas.

[0155] For example, the control station 100 calculates statistics regarding the communication environment in one or more candidate areas and one prediction area according to the unit spatial domain. The control station 100 determines a correlation (also referred to as a similarity) between each of the one or more candidate areas and one prediction area by comparing the statistics of each of the one or more candidate areas with the statistics of the prediction area. The control station 100 selects a learning area according to the determination result.

[0156] Hereinafter, examples of the selection method executed by the control station 100 will be described.

[0157] In the following description, for the sake of simplicity, it is assumed that the size of the prediction area and the size of the candidate area are the same.

[0158] <3-1. First Selection Method>For example, the control station 100 determines a correlation in wireless environment (communication environment) between a candidate area and a prediction area by using obstacle information regarding obstacles. For example, the control station 100 determines the correlation in wireless environment according to statistics of heights of the obstacles in the candidate area and the prediction area.

[0159] Note that the obstacles according to the present embodiment refer to obstacles that can affect communication characteristics in a wireless environment, such as a building, a tree, a wall, a signboard, a pillar, and a vehicle.

[0160] First, the control station 100 divides each of the candidate area and the prediction area into one or more unit spatial domains. For example, the control station 100 divides each of the candidate area and the prediction area into grids. Note that the grid is an example of the unit spatial domain.

[0161] Here, the control station 100 divides the candidate area and the prediction area into grids of the same size. As described above, since the size of the candidate area and the size of the prediction area are the same, the number of grids included in the candidate area and the number of grids included in the prediction area are the same.

[0162] Fig. 12 is a diagram illustrating an example of a candidate area and an example of a prediction area in the first selection method according to an embodiment of the present disclosure. Fig. 12(a) illustrates an example of a first candidate area, Fig. 12(b) illustrates an example of a second candidate area, and Fig. 12(c) illustrates an example of a prediction area.

[0163] Here, it is assumed that the candidate areas are two areas, the first candidate area and the second candidate area, but the number of candidate areas is not limited to two, and may be one or three or more. When the first candidate area and the second candidate area are not distinguished from each other, they are simply referred to as candidate areas. When the candidate area and the prediction area are not distinguished from each other, they are also simply referred to as areas.

[0164] As illustrated in Fig. 12, each area is divided into, for example, square grids. Each grid represents, for example, an arbitrary reception point in each area.

[0165] For example, the control station 100 calculates a statistic regarding heights of obstacles in a grid. The statistic may be, for example, an average value or a maximum value of the heights of the obstacles, or may be another statistic. For example, when a grid includes a plurality of obstacles having different heights, the control station 100 may set a statistic (e.g., an average value or a maximum value) of the heights of the plurality of obstacles as an obstacle height in the grid.

[0166] In Fig. 12, a difference in obstacle height between the grids is represented by a difference in hatching. For example, grids represented by the same hatching in each area include obstacles of the same or similar heights. Here, the heights of the obstacles being similar can mean that, for example, a difference between the heights of the obstacles in grids represented by the same hatching is smaller than a predetermined value.

[0167] Note that, here, the reception points in each area are represented by square grids, but the reception points may be represented in another way. For example, each area may be divided into grids (in other words, unit spatial domains) other than the square grids. Examples of the grids other than the square grids include rectangular and circular grids. Furthermore, the reception points may be represented by points. Examples of the points representing the reception points include grid intersections, points expressed by latitudes and longitudes, and the like.

[0168] Here, each area is divided into 25 grids, but the number of divisions of the area is not limited thereto. For example, the number of divisions of the area (in other words, the number of grids or reception points) may be 24 or less or 26 or more.

[0169] For example, the control station 100 compares the candidate areas with the prediction area, and selects a candidate area similar to the prediction area as a learning area. That is, when selecting a learning area, the control station 100 uses a similarity in obstacle height between the candidate area and the prediction area.

[0170] In the example of Fig. 12, between the first candidate area (see Fig. 12(a)) and the second candidate area (see Fig. 12(b)), the first candidate area is more similar to the prediction area (see Fig. 12(c)). Therefore, the control station 100 selects the first candidate area as the learning area, and generates an estimation model using the first candidate area.

[0171] For example, the control station 100 may calculate a similarity in obstacle height between the candidate area and the prediction area using a difference in average obstacle height. For example, the control station 100 calculates the similarity using the following Formula (1).

[0172]

[0173] Here, HXis an average value (for example, in meters) of obstacle heights in a candidate area X. For example, when the candidate area X is divided into N grids and an obstacle height is calculated for each grid, HXis an average value of obstacle heights in all the N grids.

[0174] Similarly, H is an average value (for example, in meters) of obstacle heights in a prediction area. For example, when the prediction area is divided into N grids and an obstacle height is calculated for each grid, H is an average value of obstacle heights in all the N grids.

[0175] DXis a difference in average obstacle height value between the candidate area X and the prediction area. The control station 100 determines that the smaller the DX, that is, the smaller the difference in average obstacle height value between the candidate area X and the prediction area, the more the candidate area X and the prediction area are similar, that is, the higher the similarity between the candidate area X and the prediction area is.

[0176] The control station 100 selects, for example, a candidate area having the smallest DX, in other words, a candidate area having the highest similarity, as a learning area. Alternatively, the control station 100 may select, as learning areas, for example, L candidate areas in ascending order from a candidate area having the smallest DX, in other words, in descending order from a candidate area having the highest similarity. For example, the control station 100 may select, as a learning area, a candidate area having DXsmaller than a predetermined threshold.

[0177] Here, HXand H are average values of obstacle heights in all the grids, but HXand H are not limited to the average values, and may be statistics other than the average value, such as maximum values.

[0178] Furthermore, the control station 100 may estimate a probability distribution of obstacle heights in the grids of each of the candidate areas and the prediction area, and calculate a similarity in distribution on the basis of KL divergence or the like. The control station 100 selects, as a learning area, a candidate area having the smallest calculated KL divergence, that is, a candidate area having the highest similarity. Alternatively, the control station 100 may select, as learning areas, L candidate areas in ascending order from a candidate area having the smallest KL divergence, that is, in descending order from a candidate area having the highest similarity. For example, the control station 100 may also select, as a learning area, a candidate area having KL divergence smaller than a predetermined threshold, that is, a candidate area having a similarity higher than a predetermined value.

[0179] Furthermore, for example, when calculating a statistic of an obstacle height in each area, the control station 100 may calculate the statistic in consideration of the altitude of each area.

[0180] Furthermore, the control station 100 may calculate the similarity between the candidate area and the prediction area, using an algorithm for calculating a similarity between images (hereinafter, also referred to as an image similarity algorithm), for example, with respect to images in which a grid of each area is regarded as a pixel, and a statistic (here, obstacle height) in the grid is regarded as a pixel value. Examples of the image similarity algorithm include mean square error (MSE), mean absolute error (MAE), normalized cross-correlation (NCC), peak signal-to-noise ratio (PSNR), and the like.

[0181] For example, the control station 100 can calculate the similarity using the image similarity algorithm, for example, with respect to candidate image information in which grids of a candidate area are regarded as pixels and obstacle heights in the grids are regarded as pixel values, and candidate image information in which grids of a prediction area are regarded as pixels and obstacle heights in the grids are regarded as pixel values.

[0182] Furthermore, for example, the control station 100 may generate an estimation model using the similarity as a weighting coefficient. For example, the control station 100 generates an estimation model using the DXas a weighting coefficient. For example, the control station 100 selects first to third learning areas R01, R02, and R03, and generates an estimation model that estimates an average RSRP at a certain point of the prediction area using RSRP data actually measured in the first to third learning areas R01, R02, and R03.

[0183] In this case, the control station 100 may calculate a weighted average using DXas a weighting coefficient as shown in the following Formula (2).

[0184]

[0185] Here, each of D1, D2, and D3is a difference in an average value of statistics regarding obstacle heights between each of the first to third learning areas R01, R02, and R03 and the prediction area (hereinafter, simply referred to as a difference in average value). Each of P1, P2, and P3(dBm) is an RSRP at an arbitrary point in each of the first to third learning areas R01, R02, and R03.

[0186] By using a reciprocal of a difference in average value as a weighting coefficient, the control station 100 can multiply an RSRP of a learning area having a smaller difference in average value by a larger weight, thereby predicting an RSRP of the prediction area with higher accuracy.

[0187] Although the control station 100 predicts the RSRP of the prediction area here, the communication characteristics predicted by the control station 100 are not limited to the RSRP. Other communication characteristics can be similarly calculated using DXas a weighting coefficient.

[0188] <3-2. Second Selection Method>For example, the control station 100 determines a correlation in wireless environment between a candidate area and a prediction area using obstacle densities as obstacle information of.

[0189] The control station 100 divides each area into grids similarly to the first selection method.

[0190] Fig. 13 is a diagram illustrating an example of a candidate area and an example of a prediction area in the second selection method according to an embodiment of the present disclosure. Fig. 13(a) illustrates an example of a first candidate area, Fig. 13(b) illustrates an example of a second candidate area, and Fig. 13(c) illustrates an example of a prediction area.

[0191] Here, it is assumed that the candidate areas are two areas, the first candidate area and the second candidate area, but the number of candidate areas is not limited to two, and may be one or three or more.

[0192] As illustrated in Fig. 13, each area is divided into, for example, square grids. Each grid represents, for example, an arbitrary reception point in each area.

[0193] For example, the control station 100 determines whether there is an obstacle for each grid. In Fig. 13, whether there is an obstacle is indicated by whether each grid is hatched. For example, a hatched grid in each area is a grid in which there is any obstacle. An unhatched white grid is a grid in which there is no obstacle.

[0194] For example, the control station 100 compares the candidate areas with the prediction area, and selects a candidate area similar to the prediction area as a learning area. That is, when selecting a learning area, the control station 100 uses a similarity in whether there is an obstacle between the candidate area and the prediction area.

[0195] In the example of Fig. 13, between the first candidate area (see Fig. 13(a)) and the second candidate area (see Fig. 13(b)), the first candidate area is more similar to the prediction area (see Fig. 13(c)). Therefore, the control station 100 selects the first candidate area as the learning area, and generates an estimation model using the first candidate area.

[0196] For example, the control station 100 may calculate a similarity in obstacle density between the candidate area and the prediction area using a difference in obstacle density. For example, the control station 100 calculates the similarity using the following Formula (3).

[0197]

[0198] Here, aXis an obstacle density in a candidate area X. bXis an obstacle density in the prediction area. ζXis a difference in obstacle density between the candidate area X and the prediction area.

[0199] The control station 100 determines that the smaller the ζX, that is, the smaller the difference in obstacle density between the candidate area X and the prediction area, the more the candidate area X and the prediction area are similar, that is, the higher the similarity between the candidate area X and the prediction area is.

[0200] The control station 100 selects, for example, a candidate area having the smallest ζXas a learning area. Alternatively, the control station 100 may select, as learning areas, for example, L candidate areas in ascending order from a candidate area having the smallest ζX. For example, the control station 100 may select, as a learning area, a candidate area having ζXsmaller than a predetermined threshold.

[0201] The obstacle density may be defined as, for example, the number of obstacles per unit area of each area. At this time, it is desirable that the unit area values of the candidate area and the prediction area are unified, that is, the same.

[0202] In addition, similarly to the first selection method, the control station 100 may estimate a probability distribution of obstacle densities in the grids of each of the candidate areas and the prediction area, and calculate a similarity in distribution on the basis of KL divergence or the like.

[0203] Similarly to the first selection method, for example, the control station 100 may calculate the similarity between the candidate area and the prediction area, using an algorithm for calculating a similarity between images, while a grid of each area is regarded as a pixel, and whether there is an obstacle in the grid is regarded as a binary pixel value.

[0204] Similarly to the first selection method, for example, the control station 100 may predict communication characteristics, while the control station 100 uses the above-described ζXas a weighting coefficient.

[0205] <3-3. Third Selection Method>For example, the control station 100 determines a correlation in wireless environment based on the propagation characteristics of the candidate area and the prediction area. For example, examples of the propagation characteristics include parameters that can affect communication characteristics, such as diffraction loss, clutter loss, reflectance, refractive index, distance attenuation and attenuation coefficient thereof, shadowing and average value thereof, standard deviation, fading deviation, and clearance coefficient.

[0206] The control station 100 estimates the propagation characteristics, for example, by simulation or the like. Alternatively, the control station 100 may actually measure propagation characteristics at some points in each area, and determine a correlation in wireless environment between the candidate area and the prediction area using the actually measured propagation characteristics.

[0207] Alternatively, the control station 100 may use actually measured propagation characteristics in the candidate area and use simulation-estimated propagation characteristics in the prediction area. In addition, the control station 100 may use simulation-estimated propagation characteristics in the candidate area and use actually measured propagation characteristics in the prediction area.

[0208] Alternatively, actually measured values and simulation values may be mixed in each area, for example, by using actually measured propagation characteristics at some points in each area, and using simulation-estimated propagation characteristics at the other points of each area.

[0209] Note that by determining a correlation in wireless environment between the candidate area and the prediction area using the propagation characteristics actually measured by the control station 100, it is possible to reduce the influence of the error in estimation by simulation, thereby further improving the correlation determination accuracy.

[0210] Fig. 14 is a diagram illustrating an example of a candidate area and an example of a prediction area in the third selection method according to an embodiment of the present disclosure. Fig. 14(a) illustrates an example of a first candidate area, Fig. 14(b) illustrates an example of a second candidate area, and Fig. 14(c) illustrates an example of a prediction area.

[0211] Here, it is assumed that the candidate areas are two areas, the first candidate area and the second candidate area, but the number of candidate areas is not limited to two, and may be one or three or more.

[0212] As illustrated in Fig. 14, each area is divided into, for example, square grids. Each grid represents, for example, an arbitrary reception point in each area.

[0213] For example, the control station 100 acquires propagation characteristics for each grid. In Fig. 14, a difference in propagation characteristic between the grids is represented by a difference in hatching. For example, grids having the same hatching in each area have the same or similar propagation characteristics. Here, the propagation characteristics being similar can mean that, for example, a difference in propagation characteristic between grids having the same hatching is smaller than a predetermined value.

[0214] For example, the control station 100 compares the candidate areas with the prediction area, and selects a candidate area similar to the prediction area as a learning area. That is, when selecting a learning area, the control station 100 uses a similarity in propagation characteristic between the candidate area and the prediction area.

[0215] In the example of Fig. 14, between the first candidate area (see Fig. 14(a)) and the second candidate area (see Fig. 14(b)), the first candidate area is more similar to the prediction area (see Fig. 14(c)). Therefore, the control station 100 selects the first candidate area as the learning area, and generates an estimation model using the first candidate area.

[0216] For example, the control station 100 may calculate a similarity in propagation characteristic between the candidate area and the prediction area using a difference in propagation characteristic. For example, the control station 100 calculates the similarity using the following Formula (4).

[0217]

[0218] Here, cXis an average value of propagation characteristics in a candidate area X. dXis an average value of propagation characteristics in the prediction area. λXis a difference in average propagation characteristic value between the candidate area X and the prediction area.

[0219] The control station 100 determines that the smaller the λX, that is, the smaller the difference in obstacle density between the candidate area X and the prediction area, the more the candidate area X and the prediction area are similar, that is, the higher the similarity between the candidate area X and the prediction area is.

[0220] The control station 100 selects, for example, a candidate area having the smallest λXas a learning area. Alternatively, the control station 100 may select, as learning areas, for example, L candidate areas in ascending order from a candidate area having the smallest λX. For example, the control station 100 may select, as a learning area, a candidate area having λXsmaller than a predetermined threshold.

[0221] Similarly to the first and second selection methods, the control station 100 may estimate a probability distribution of propagation characteristics in the grids of each of the candidate areas and the prediction area, and calculate a similarity in distribution on the basis of KL divergence or the like.

[0222] Similarly to the first and second selection methods, for example, the control station 100 may calculate the similarity between the candidate area and the prediction area, using an algorithm for calculating a similarity between images, while a grid of each area is regarded as a pixel, and a propagation characteristic in the grid is regarded as a pixel value.

[0223] Similarly to the first and second selection methods, for example, the control station 100 may predict communication characteristics, while the control station 100 uses the above-described λXas a weighting coefficient.

[0224] In addition, when estimating propagation characteristics, the control station 100 may use ray tracing or an existing propagation model as will be described below. In addition, the propagation model to be used is not limited to the following examples, and other propagation models may be used.- Okumura Hata formula- Extended Hata formula- Free space propagation loss- ITM Model- ITU-R P.452- ITU-R P.2108- Knife edge diffraction model- 3GPP (registered trademark) defined propagation model for macrocells or microcells

[0225] Furthermore, the control station 100 may estimate propagation characteristics in consideration of information regarding the antenna. Examples of the information regarding the antenna include an antenna pattern, more specifically, at least one of a height of the antenna, an antenna gain, a tilt angle, a beam direction, and the like.

[0226] <3-4. Fourth Selection Method>For example, the control station 100 determines a correlation in wireless environment based on LOS / NLOS information in the candidate area and the prediction area.

[0227] The control station 100 may determine LOS / NLOS for each grid of the area, for example, using information such as a height of a peripheral structure, a distance between transmission and reception, and a height of a transceiver.

[0228] The control station 100 may determine the LOS / NLOS, for example, using at least one of the following methods.- Ray-tracing simulation- Propagation model capable of determining LOS / NLOS, such as ITU-R P.452- Calculation of shielding rate of first Fresnel zone- Utilization of terrain / building data

[0229] In a case where LOS / NLOS is determined using a shielding rate of a first Fresnel zone, for example, if a first Fresnel radius at a certain reception point can be secured as r (%), the control station 100 regards the point as LOS. For example, when the first Fresnel radius is 10 m and 4 m, which is 60% (r=60) of the first Fresnel radius, can be secured, the control station 100 regards the reception point as LOS, and when the first Fresnel radius is shielded by longer than 4 m (in other words, 60% cannot be secured), the control station 100 regards the reception point as NLOS.

[0230] In addition, in a case where LOS / NLOS is determined by utilizing the terrain / building data, the control station 100 considers, for example, a path connecting transmission and reception points, and determines whether this path is shielded by terrain or a building.

[0231] For example, when the determination of LOS / NLOS is performed at a plurality of determination points in the grid, the control station 100 may perform LOS / NLOS determination for the grid according to the determination result at each determination point.

[0232] For example, concerning the determination points, when the number of determination points determined as LOS is larger than the number of determination points determined as NLOS, the control station 100 determines that the grid is an LOS grid. In addition, concerning the determination points, for example, when the number of determination points determined as LOS is smaller than the number of determination points determined as NLOS, the control station 100 determines that the grid is an NLOS grid. Concerning the determination points, for example, when the number of determination points determined as LOS is the same as the number of determination points determined as NLOS, the control station 100 determines that the grid is an LOS / NLOS mixed grid (hereinafter, also simply referred to as a mixed grid).

[0233] For example, when at least one of the determination points in the grid is determined as LOS, the control station 100 determines that the grid is an LOS grid. Alternatively, for example, when at least one of the determination points in the grid is determined as NLOS, the control station 100 determines that the grid is an NLOS grid.

[0234] For example, when the number of points determined as LOS in the grid is equal to or greater than a first threshold, the control station 100 determines that the grid is an LOS grid. When the number of points determined as LOS is smaller than the first threshold and the number of points determined as NLOS is equal to or greater than a second threshold, the control station 100 determines that the grid is an NLOS grid. In addition, when the number of points determined as LOS is smaller than the first threshold and the number of points determined as NLOS is smaller than the second threshold, the control station 100 determines that the grid is a mixed grid.

[0235] Note that the first threshold and the second threshold may be the same value or different values.

[0236] For example, when the number of points determined as NLOS in the grid is equal to or greater than the second threshold, the control station 100 may determine that the grid is an NLOS grid. In this case, when the number of points determined as NLOS is smaller than the second threshold and the number of points determined as LOS is equal to or greater than the first threshold, the control station 100 determines that the grid is an LOS grid. In addition, when the number of points determined as LOS is smaller than the first threshold and the number of points determined as NLOS is smaller than the second threshold, the control station 100 determines that the grid is a mixed grid.

[0237] Fig. 15 is a diagram illustrating an example of a candidate area and an example of a prediction area in the fourth selection method according to an embodiment of the present disclosure. Fig. 15(a) illustrates an example of a first candidate area, Fig. 15(b) illustrates an example of a second candidate area, and Fig. 15(c) illustrates an example of a prediction area.

[0238] Here, it is assumed that the candidate areas are two areas, the first candidate area and the second candidate area, but the number of candidate areas is not limited to two, and may be one or three or more.

[0239] As illustrated in Fig. 15, each area is divided into, for example, square grids. Each grid represents, for example, an arbitrary reception point in each area.

[0240] The control station 100 determines LOS / NLOS, for example, for a grid of each area. Here, it is assumed that the control station 100 determines not only LOS / NLOS grids but also LOS / NLOS mixed grids.

[0241] In Fig. 15, for example, a white grid indicates an NLOS grid. A coarsely hatched grid indicates an LOS grid. A finely hatched grid indicates a mixed grid.

[0242] Note that, here, the reception points in each area are represented by square grids, but the reception points may be represented in another way. For example, each area may be divided into grids (in other words, unit spatial domains) other than the square grids. Examples of the grids other than the square grids include rectangular and circular grids. Furthermore, the reception points may be represented by points. Examples of the points representing the reception points include grid intersections, points expressed by latitudes and longitudes, and the like.

[0243] Here, each area is divided into 25 grids, but the number of divisions of the area is not limited thereto. For example, the number of divisions of the area (in other words, the number of grids or reception points) may be 24 or less or 26 or more.

[0244] For example, the control station 100 compares the candidate areas with the prediction area, and selects a candidate area similar to the prediction area as a learning area. That is, when selecting a learning area, the control station 100 uses a similarity in LOS / NLOS determination result between the candidate area and the prediction area.

[0245] In the example of Fig. 15, between the first candidate area (see Fig. 15(a)) and the second candidate area (see Fig. 15(b)), the first candidate area is more similar to the prediction area (see Fig. 15(c)). Therefore, the control station 100 selects the first candidate area as the learning area, and generates an estimation model using the first candidate area.

[0246] For example, the control station 100 compares a difference in the number of NLOS grids between each of the candidate areas and the prediction area, and selects a candidate area having a small difference as a learning area. The control station 100 selects, for example, a candidate area having the smallest difference in the number of NLOS grids as a learning area.

[0247] Alternatively, the control station 100 may select, as learning areas, for example, L candidate areas in ascending order from a candidate area having the smallest difference in the number of NLOS grids. For example, the control station 100 may select, as a learning area, a candidate area having a difference in the number of NLOS grids smaller than a predetermined threshold.

[0248] Here, the control station 100 selects a learning area according to the number of NLOS grids, but the learning area may be selected according to the number of LOS grids instead of the number of NLOS grids.

[0249] In addition, similarly to the first to third selection methods, the control station 100 may estimate a probability distribution of LOS / NLOS determination results in the grids of each of the candidate area and the prediction area, and calculate a similarity of distribution on the basis of KL divergence or the like. The control station 100 selects a candidate area having the smallest calculated similarity as a learning area. Alternatively, the control station 100 may select L candidate areas in ascending order from a candidate area having the smallest similarity as learning areas, and may select, for example, a candidate area having a similarity smaller than a predetermined threshold as a learning area.

[0250] In addition, similarly to the first to third selection methods, for example, the control station 100 may calculate the similarity between the candidate area and the prediction area, using an algorithm for calculating a similarity between images, while a grid of each area is regarded as a pixel, and a numerical value representing an LOS / NLOS determination result is regarded as a pixel value.

[0251] Similarly to the first to third selection methods, for example, the control station 100 may predict communication characteristics using a difference in the number of NLOS grids (or LOS grids) as a weighting coefficient.

[0252] <3-5. Fifth Selection Method>In the first to fourth selection methods described above, for example, the control station 100 divides an area into grids, and selects a learning area according to information for each grid. The selection of the learning area performed by the control station 100 is not limited to the method in which the area is divided into grids. For example, the control station 100 may select a learning area according to map information.

[0253] Fig. 16 is a diagram illustrating an example of a first candidate area in the fifth selection method according to an embodiment of the present disclosure. A part of map information illustrated in Fig. 16 is a first candidate area R01.

[0254] As illustrated in Fig. 16, the first candidate area R01 corresponds to a partial section of a large highway such as an expressway.

[0255] Fig. 17 is a diagram illustrating an example of a second candidate area in the fifth selection method according to an embodiment of the present disclosure. A part of map information illustrated in Fig. 17 is a second candidate area R02.

[0256] As illustrated in Fig. 17, the second candidate area R02 corresponds to a part of an area where buildings are densely located, such as a residential area in a suburb.

[0257] Fig. 18 is a diagram illustrating an example of a prediction area in the fifth selection method according to an embodiment of the present disclosure. A part of map information illustrated in Fig. 18 is a prediction area R11.

[0258] As illustrated in Fig. 18, the prediction area R11 corresponds to a partial section of a large highway such as an expressway.

[0259] For example, the control station 100 compares the map information of the candidate areas with the map information of the prediction area, and selects a candidate area similar to the prediction area as a learning area.

[0260] In the example of Figs. 16 to 18, between the first candidate area R01 (see Fig. 16) and the second candidate area R02 (see Fig. 17), the first candidate area R01 is similar to the prediction area R11 (see Fig. 18). Therefore, the control station 100 selects the first candidate area R01 as the learning area, and generates an estimation model using the first candidate area R01.

[0261] The control station 100 may select a learning area, for example, according to a difference in road shape between the candidate area and the prediction area, specifically, a difference in at least one of a road width, a road length, the number of intersections, and the like. Alternatively, the control station 100 may select a learning area, for example, according to a difference in obstacle between the candidate area and the prediction area, specifically, a difference in at least one of a shape of a building or a house, the number of trees, and the like.

[0262] The control station 100 may select a learning area similar to the prediction area, for example, using an image processing technology or the like, or may select a learning area according to an instruction of a user or the like.

[0263] <<4. Comparison Method According to Area Size>>In the first to fourth selection methods described above, the sizes of the candidate area and the prediction area are the same. The sizes of the candidate area and the prediction area may be different. Here, an example of a method of comparing a candidate area and a prediction area by the control station 100 in a case where the candidate area and the prediction area have different sizes will be described.

[0264] (First Comparison Method)Fig. 19 is a diagram illustrating an example of a first comparison method according to an embodiment of the present disclosure. In Fig. 19, a candidate area R03 and a prediction area R12 are illustrated. Although Fig. 19 illustrates a case where the prediction area R12 is larger than the candidate area R03, the candidate area R03 and the prediction area R12 may be interchanged. That is, the candidate area R03 may be larger than the prediction area R12.

[0265] In the first comparison method, for example, the control station 100 divides areas having different sizes into the same number of grids. That is, the control station 100 divides the areas in such a manner that they have the same number of grids.

[0266] When the areas are divided, the control station 100 compares the candidate areas with the prediction area according to one of the first to fourth selection methods described above, and selects a learning area.

[0267] (Second Comparison Method)Fig. 20 is a diagram illustrating an example of a second comparison method according to an embodiment of the present disclosure. In Fig. 20, a candidate area R03 and a prediction area R12 are illustrated. Although Fig. 20 illustrates a case where the prediction area R12 is larger than the candidate area R03, the candidate area R03 and the prediction area R12 may be interchanged. That is, the candidate area R03 may be larger than the prediction area R12.

[0268] In the second comparison method, for example, the control station 100 divides areas having different sizes into grids having the same size. When the areas are divided, the control station 100 compares the candidate areas with the prediction area according to one of the first to fourth selection methods described above, and selects a learning area.

[0269] Note that, here, in a case where a learning area is selected according to any of the first to fourth selection methods described above, it may be desirable that the number of grids in the candidate area and the number of grids in the prediction area be the same. In this case, the control station 100 may cut off a part of the large area to generate an area having the same size as the small area (hereinafter, also referred to as a divided area). The control station 100 selects a learning area by comparing the divided area with the prediction area (or the candidate area).

[0270] Fig. 21 is a diagram illustrating another example of a second comparison method according to an embodiment of the present disclosure. In Fig. 21, it is assumed that the candidate area R03 is larger than the prediction area R12. In this case, the control station 100 divides the candidate area R03 and extracts a divided area having the same size as the prediction area R12 from the candidate area R03.

[0271] Although Fig. 21 illustrates an example in which the control station 100 extracts a first divided area R21 and a second divided area R22 from the candidate area R03, the number of divided areas extracted by the control station 100 is not limited to two, and may be one or three or more.

[0272] In addition, the control station 100 may divide the candidate area R03 into grids and then extract a divided area, or may extract a divided area and then divide the divided area into grids.

[0273] In a case where a plurality of divided areas are extracted, the control station 100 may extract partially overlapping divided areas.

[0274] Furthermore, as described above, the case where the prediction area is included in the learning area (corresponding to the candidate area described above) is classified into the case where the learning area and the prediction area are the same. The selection method according to the present embodiment (e.g., any of the first to fifth selection methods) can also be applied to a case where a prediction area is included in a learning area.

[0275] In this case, the learning areas (corresponding to the candidate areas described above) are larger than the prediction area. Therefore, the control station 100 compares the learning areas (corresponding to the candidate areas described above) with the prediction area by applying either the first comparison method or the second comparison method, and selects a learning area to be used for generating an estimation model.

[0276] For example, the control station 100 may extract a divided area having the same size as the prediction area from the learning area, and generate an estimation model according to the divided area.

[0277] Fig. 22 is a diagram illustrating an extraction example in which a divided area is extracted from a learning area according to an embodiment of the present disclosure.

[0278] In the example of Fig. 22, in a case where a prediction area is included in a learning area (corresponding to the candidate area described above), the control station 100 extracts a first divided area R23 and a second divided area R24 from the learning area. The control station 100 selects a learning area to be used for training the estimation model from among the extracted divided areas.

[0279] Here, for example, the control station 100 can extract divided areas each having the same size as the prediction area from the candidate area larger than the prediction area, and can select a learning area by applying any of the first to fifth selection methods using the divided areas as candidate areas. In this case, for example, the control station 100 can randomly extract divided areas.

[0280] Alternatively, the control station 100 may extract the divided areas in consideration of the similarity, in other words, the degree of correlation, with respect to the prediction area, for example, similarly to the first to fifth selection methods. In this case, since the degree of correlation is already taken into consideration, the control station 100 can generate an estimation model using the extracted divided areas as they are as learning areas.

[0281] Alternatively, the control station 100 may extract divided areas similar to the prediction area (e.g., areas having high correlation in propagation characteristics or the like) from the candidate area using a pattern matching technology or the like.

[0282] Alternatively, the control station 100 may extract divided areas in consideration of the geographical continuity in the candidate area. For example, the control station 100 extracts geographically separated areas as divided areas. As a result, the control station 100 can further reduce bias in the wireless environment between the extracted divided areas.

[0283] The control station 100 generates an estimation model according to the extracted (or selected) divided areas.

[0284] Here, the divided areas are extracted from the candidate area, but the control station 100 may extract divided areas from the prediction area. In this case, the control station 100 may generate an estimation model limited to divided areas within the prediction area.

[0285] Alternatively, when comparing the candidate areas and the prediction area, the control station 100 may use a divided area instead of the prediction area. In this case, the control station 100 selects a learning area from among the candidate areas according to the result of comparison between the candidate areas and the divided area. The control station 100 generates an estimation model in the prediction area according to the selected learning area.

[0286] In addition, here, it is assumed that the control station 100 cuts off a part of the area having a large size and generates an area having the same size as the area having a small size (hereinafter, also referred to as a divided area). Alternatively, the control station 100 may integrate small areas and generate an area having the same size as the large area (hereinafter, also referred to as an integrated area).

[0287] Fig. 23 is a diagram illustrating another example of a second comparison method according to an embodiment of the present disclosure. In Fig. 23, it is assumed that a prediction area is larger than candidate areas. In this case, the control station 100 integrates a plurality of candidate areas to generate an integrated area having the same size as the prediction area.

[0288] Although Fig. 23 illustrates an example in which the control station 100 integrates candidate areas R04 to R08 to generate an integrated area R30, the number of candidate areas integrated by the control station 100 is not limited to five, and may be four or less or six or more. In addition, the candidate areas may all have the same shape and / or size, or at least some of the candidate areas may have different shapes and / or sizes.

[0289] Further, the control station 100 may generate an integrated area by integrating divided areas obtained by extracting at least parts of the candidate area.

[0290] In addition, the control station 100 may divide a candidate area into grids and then generate an integrated area, or may generate an integrated area and then divide the integrated area into grids.

[0291] <<5. Others>>Here, definitions (descriptions) and the like of terms used in the above-described embodiments will be described.

[0292] <5-1. Terms><5-1-1. Communication Characteristic>For example, the communication characteristic is any of the following or a combination thereof.- A characteristic based on radio wave propagation from a transmission point to a reception point (downlink, uplink, and sidelink)- A communication parameter at a transmission point, a reception point, a base station 300, a terminal device 400, and / or a communication node

[0293] The characteristic based on radio wave propagation from the transmission point to the reception point includes at least one of a characteristic related to reception power, a characteristic related to a communication speed (throughput), and a characteristic related to a delay.

[0294] The characteristic related to the reception power includes information related to at least one of reception power, interference power, RSRP, reference signal received quality (RSRQ), received signal strength indicator (RSSI), SNR, and SINR.

[0295] The characteristic related to the communication speed includes information related to at least one of a downlink throughput, an uplink throughput, and a sidelink throughput.

[0296] The characteristic related to the delay includes information related to at least one of latency, jitter, and a ping value.

[0297] The communication parameter at the transmission point, the reception point, the base station 300, the terminal device 400, and / or the communication node includes a dynamically determined parameter and / or a semi-statically determined parameter.

[0298] The dynamically determined parameter includes at least one type of the following information.- Information regarding modulation and coding scheme (MCS)- Information regarding transmission power- Information regarding beam control- Information regarding the number of multi input multi output (MIMO) multiplexing

[0299] The semi-statically determined parameter includes at least one of a range, a maximum value, a minimum value, an average value, and a median value of parameters selectable by the base station 300 or the terminal device 400 (permitted for the base station 300 or the terminal device 400). Examples of the semi-statically determined parameter include maximum transmission power.

[0300] <5-1-2. Area>The area (place or base) in the present embodiment can be given by any one of the following or a combination thereof. Note that this area corresponds to the above-described predetermined area (learning area, candidate area, and / or prediction area).- A coverage area of a predetermined base station 300, terminal device 400, or communication node- A site or building owned or managed by a predetermined business operator- An area set in advance by a predetermined business operator or administration- An area divided by a predetermined method

[0301] The area includes, for example, coverage that can be connected to one communication node (such as the base station 300 or the terminal device 400). Furthermore, for example, in a case where a plurality of base stations 300 are installed in one base, the base stations 300 are connected to one core network. In other words, the base may be defined as a coverage area covered by at least one base station 300 connected to one core network.

[0302] For example, a base station 300 of a private network or an access point name (APN) of a core network can be set as a prediction area for each base. In other words, the same access point name is set in the same base (learning area), and in a case where the access point names are different, they are recognized as different bases.

[0303] Examples of a predetermined method of dividing the area include a method based on position information. In this method, the area is divided by a predetermined distance, for example, on the basis of position information such as latitude and longitude.

[0304] <5-1-3. Communication Environment Information>The communication environment information is information that can be included in actual measurement data. The communication environment information may be used for statistical processing (e.g., generating an estimation model). The communication environment information may be used to generate estimation data using the estimation model. That is, the communication environment information can be an explanatory variable of the estimation model.

[0305] The communication environment information includes at least one of static or semi-static information and dynamic information. The static or semi-static information is fixed information or information having a low update frequency. Note that the static or semi-static information can be information in a higher communication layer (e.g., an application layer, a radio resource control (RRC) layer, or the like). The dynamic information is information having a high update frequency. Note that the dynamic information can be information in a lower communication layer (e.g., a physical layer or the like).

[0306] The communication environment information includes, for example, at least one type of the following information.- Map information- Structure information- Device information related to the base station 300 or the terminal device 400- Sensing information acquired through a sensing device- Wireless communication information related to wireless communication

[0307] (Map Information)The map information here is information capable of recognizing the positions, sizes, and the like of structures, the base station 300, the terminal device 400, and the like. The position may be, for example, absolute position information such as latitude and longitude or relative position information in the area.

[0308] The map information includes, for example, topographical information, an office layout diagram, an internal map, and the like.

[0309] (Structure Information)The structure information here includes information that affects radio wave propagation. Examples of the influence on radio wave propagation include reflection, diffraction, and transmission.

[0310] The structures include, for example, a construction, a wall surface, a plantation, a road, a signboard, a traffic light, a road sign, a pillar, a building, a ground, glass, a window, a desk, a cabinet, and the like.

[0311] The structure information includes, for example, positions, shapes, sizes, and materials of the structures, parameters (dielectric constant, conductivity, and the like) related to radio wave propagation in the structures, and the like.

[0312] The structure information is generated and constructed, for example, on the basis of the above-described map information. In addition, the structure information may be generated and constructed on the basis of information acquired from a sensing device or the like to be described later.

[0313] (Device Information Regarding Base Stations 300 or Terminal Devices 400)Here, the device information regarding the base stations 300 or the terminal devices 400 includes, for example, at least one type of the information listed below.- Antenna information regarding antennas- Capability information regarding functions and capabilities supported in wireless communication- Shape information regarding shapes and weights of the base stations 300 and / or the terminal devices 400- Position information of fixed base stations 300 and / or fixed terminal devices 400

[0314] Here, the antenna information regarding the antennas includes, for example, at least one of information regarding the antenna configuration, the beam pattern, the number of antenna elements, and the configuration of the antenna elements of the base stations 300 and / or the terminal devices 400.

[0315] (Sensing Information Acquired through Sensing Device)The sensing information acquired through the sensing device here includes object information regarding objects detected through the sensing device and / or influence information regarding fluctuations in and / or influences on wireless communication caused by the detected objects.

[0316] Here, the sensing device includes a camera, a sensor, or the like. The sensor includes a photoelectric sensor, a fiber sensor, a laser sensor, a color sensor, a proximity sensor, an overcurrent displacement sensor, a contact displacement sensor, an ultrasonic sensor, an image discrimination sensor, a pressure sensor, a vibration sensor, an inertial measurement sensor, or the like.

[0317] Three-dimensional spatial information (for example, the structure information described above) is generated from the sensing information acquired through the sensing device. For example, in a case where the sensing information is an image or a video acquired in real time by a camera, the three-dimensional spatial information is generated in real time using, for example, a photogrammetry technology or a volumetric capture technology.

[0318] The objects detected by the sensing device include various devices such as the sensing device, a device different from the sensing device, and the terminal device 400 that transmits information acquired by the sensing device. In addition, the objects detected by the sensing device include the above-described structures and objects other than the structures.

[0319] The terminal device 400 that transmits the sensing information acquired by the sensing device may or may not be equipped with the sensing device. In a case where the terminal device 400 and the sensing device are different devices, the terminal device 400 preferably acquires sensing information from the sensing device by, for example, wired or wireless communication.

[0320] Note that the sensing information acquired by sensing (the sensing information acquired through the sensing device) may include various sensing information in addition to the object detection information. For example, the sensing information acquired by sensing includes beam information (e.g., information regarding beam patterns, beam angles, and the like) regarding beams transmitted from the base station 300 and / or the terminal device 400.

[0321] The sensing device described above can detect moving objects such as persons or robots in addition to stationary objects such as structures. The sensing device transmits, for example, information regarding the detected moving objects as sensing information via the terminal device 400.

[0322] The sensing device can transmit the sensing information at a timing when the moving objects are detected and / or at a timing when the moving objects are no longer detected. Alternatively, the sensing device may transmit the sensing information at a constant cycle.

[0323] (Wireless Communication Information Regarding Wireless Communication)The wireless communication information regarding the wireless communication here includes, for example, at least one type of the information listed below.- Communication information regarding radio access technology (RAT) or frequency- Information regarding transmission power of the base station 300 or the terminal device 400- Scenario information regarding communication environment scenario- Constraint information regarding conditions and constraints related to wireless communication available in local networks- Quality information regarding communication quality in wireless communication

[0324] The communication information regarding the RAT includes, for example, information regarding LTE, NR, wireless LAN, Bluetooth (registered trademark), and the like. The communication information regarding the frequency includes information regarding at least one of a frequency band, a center frequency, and a frequency bandwidth.

[0325] The information regarding the transmission power of the base station 300 or the terminal device 400 includes, for example, information (ss-PBCH-BlockPower) indicating transmission power of a synchronization signal and physical broadcast channel (SS / PBCH) block included in a system information block type 1 (SIB1), which is control information broadcast from the base station 300.

[0326] The scenario information regarding the communication environment scenario includes, for example, information regarding urban areas, sub-urban areas, rural areas, indoor offices, indoor factories, and the like.

[0327] The scenario information may further include information regarding a radio wave propagation model (e.g., a path loss model) corresponding to the communication environment scenario. Note that the radio wave propagation model may correspond to each of the LOS environment and the NLOS environment.

[0328] The constraint information here includes information regarding conditions and constraints related to wireless communication permitted in local networks.

[0329] The conditions and constraints may include, for example, information regarding an available RAT, an area where wireless communicable is possible (geographic information (such as two-dimensional planar information and / or spatial information including a three-dimensional height)), an upper limit of the amount of interference power outside the area, maximum transmission power that can be transmitted, transmittable frequency information, transmittable time information, an installation place of the base station 300, and the like.

[0330] The conditions and constraints are set and defined, for example, in advance. In addition, the conditions and constraints can be determined and / or changed on the basis of information notified from a predetermined server or storage device (e.g., a spectrum access system (SAS) server or the like).

[0331] The quality information regarding the communication quality in the wireless communication includes, for example, at least one type of the following information measured or estimated by the terminal device 400 in the wireless communication.- Reception power- Interference power- RSRP- RSRQ- RSSI- SNR- Downlink throughput- Uplink throughput- Latency- Jitter- Ping value

[0332] <5-1-4. Position Information>The information regarding the position is position information of the base station 300 and / or the terminal device 400. For example, actual measurement data measured in an area may include position information.

[0333] The information regarding the position includes absolute position information such as latitude, longitude, and / or altitude acquired by, for example, a global positioning system (GPS), a global navigation satellite system (GNSS), or the like.

[0334] Alternatively, the information regarding the position includes relative position information acquired by a beacon, ultra-wideband (UWB), or the like.

[0335] The absolute position information or the relative position information may be an area divided by a predetermined distance or method.

[0336] Note that the information (actual measurement data or the like) according to the present embodiment can be information associated with the position information.

[0337] <5-2. Virtual Space Estimation Information>The virtual space estimation information includes, for example, information regarding radio wave propagation of at least one of the base station 300 and the terminal device 400. The virtual space estimation information is, for example, data (information) obtained by simulation.

[0338] The virtual space estimation information may be used as necessary when generating an estimation model. For example, the virtual space estimation information can be used for generating an estimation model in addition to or instead of the actual measurement data.

[0339] The virtual space estimation information may be used as an explanatory variable of the estimation model. Alternatively, the virtual space estimation information may be used as an objective variable of the estimation model. For example, the virtual space estimation information can be used as student data and teacher data of the estimation model.

[0340] The virtual space estimation information includes, for example, at least one type of the information listed below.- LOS / NLOS information- Simulation information- Calculation information calculated based on the LOS / NLOS information, the simulation information, and the like

[0341] (LOS / NLOS Information)The LOS / NLOS information is information indicating whether the environment between the base station 300 and the terminal device 400 is an LOS environment or an NLOS environment.

[0342] The LOS environment is also referred to as a line-of-sight environment. The LOS environment indicates a situation in which there is no obstacle 600 such as a structure or a person on a straight line between the base station 300 and the terminal device 400, and the base station 300 and the terminal device 400 can transmit and receive a direct wave therebetween. In this case, wireless communication between the base station 300 and the terminal device 400 is performed through a reflected wave, a diffracted wave, or the like in addition to a direct wave.

[0343] The NLOS environment is also referred to as a non-line-of-sight environment. The NLOS environment indicates a situation in which there is an obstacle 600 such as a structure or a person on a straight line between the base station 300 and the terminal device 400, and the base station 300 and the terminal device 400 cannot transmit and receive a direct wave therebetween. In this case, wireless communication between the base station 300 and the terminal device 400 is performed through a reflected wave, a diffracted wave, or the like other than a direct wave.

[0344] (Simulation Information)The simulation information includes information related to a simulation result of radio wave propagation in wireless communication between the base station 300 and the terminal device 400. The simulation information includes, for example, path information regarding one or more paths (transmission waves, arriving waves, rays) obtained by ray tracing simulation.

[0345] This path includes a direct wave, a reflected wave, a diffracted wave, a transmitted wave, and the like between the base station 300 and the terminal device 400. Generally, there are various structures between the base station 300 and the terminal device 400. Therefore, a signal (radio wave) transmitted from a transmission point (e.g., the base station 300) travels through various routes, becoming multiple paths, and reaches a reception point (e.g., the terminal device 400).

[0346] The path information regarding the paths may include, for example, at least one type of the following information.- Reception power at a reception point- Transmission power at a transmission point- Pass loss- Propagation distance- Number of times of reflection- Number of times of diffraction- Number of times of transmission- Phase fluctuation- Angle of emission at the transmission point- Angle of arrival at the reception point- Order of arrival of path (What is temporal order of arrival among the plurality of paths?)- Number of paths

[0347] (Calculation Information)The calculation information is information generated / calculated on the basis of the above-described LOS / NLOS information, simulation information, or the like. The calculation information may include, for example, at least one type of the following information.- Path loss at a reception point- Reception power- Interference power- RSRP- RSRQ- RSSI- SNR- Downlink throughput- Uplink throughput- Latency- Jitter- Ping value

[0348] Here, an example of virtual space estimation information generation processing (information generation processing) according to the present embodiment will be described with reference to Fig. 24. Fig. 24 is a flowchart illustrating an example of a flow of information generation processing according to an embodiment of the present disclosure.

[0349] The information generation processing illustrated in Fig. 24 can be executed by the control station 100, for example, when virtual space estimation information (simulation data) is used for generating ab estimation model and / or generating estimation data.

[0350] The control station 100 first constructs a virtual communication environment related to an area (prediction area and / or learning area) (Step S101).

[0351] For example, the virtual communication environment is a three-dimensional virtual space of the area. For example, the virtual communication environment is generated on the basis of communication environment information in the area. For example, the virtual communication environment includes a structure (a building, a ground surface, or the like) in the area.

[0352] Next, the control station 100 performs radio wave propagation simulation between the base station 300 and the terminal device 400 in the virtual communication environment (Step S102). The radio wave propagation simulation may use various methods such as LOS environment / NLOS environment determination in the virtual space or ray tracing simulation.

[0353] The control station 100 generates virtual space estimation information based on the simulation result (Step S103).

[0354] Note that the information generation processing may be executed by a device other than the control station 100. In this case, the control station 100 acquires virtual space estimation information (simulation data) from the device that executes the information generation processing. Furthermore, the timing of performing the information generation processing is not limited to the time of generating the estimation model and / or generating the estimation data. The control station 100 can execute the information generation processing at any timing.

[0355] <5-3. Estimation Accuracy>For example, in a case where the control station 100 estimates actual communication characteristics using the estimation model, estimation accuracy can be given. Alternatively, estimation accuracy may be given to the estimation model. This estimation accuracy can be further used when data estimated by the communication characteristic estimation model is used (utilized).

[0356] The communication characteristics in the prediction area and / or the estimation accuracy of the estimation model can be given by any of the following or a combination thereof.- Number of learning areas- Accuracy in determining correlation in wireless environment between each learning area and the prediction area- Method of selecting a learning area- Method of selecting a measurement point- Accuracy in generating an estimation model- Correlation (similarity) in wireless environment between the prediction area and the learning area- Accuracy of simulation data in the prediction area and / or the learning area- Accuracy (measurement accuracy) in observing actual measurement data in the prediction area and / or the learning area

[0357] Examples of the correlation (similarity) in communication environment may include similarity in the average of heights of structures in each area, the density of the structures, and the height of the base station 300 (including installation position (altitude), building height, antenna height, etc.).

[0358] For example, the accuracy of the simulation data can be determined based on the accuracy (accuracy or precision) of the communication environment information in simulation for generating simulation data.

[0359] The accuracy in observing actual measurement data can include at least one of accuracy in communication characteristic and accuracy in position information. For example, the error in the actual measurement data includes an error in actually measuring RSRP and / or an error in position information by the GPS.

[0360] Furthermore, in a case where an observation error specific to the terminal device 400 occurs, information indicating the terminal device 400 can be included in the accuracy in observing actual measurement data.

[0361] <5-4. Use Case>The statistical information according to the above-described embodiment can be used in various types of processing, controls, use cases, and the like.

[0362] For example, data on communication characteristics estimated in a prediction area (e.g., predicted values as statistical information) can be used for designing cells (setting a location of a transmission point, maximum transmission power at transmission point, and the like) in the prediction area.

[0363] The design of the cells may further be performed based on the accuracy in estimating communication characteristics in the prediction area. In addition, the design of the cells may be performed by the control station 100 or may be performed by the base station 300. Alternatively, the design of the cells may be performed in a core network or the like.

[0364] For example, data on communication characteristics estimated in a prediction area (e.g., predicted values as statistical information) can be used to control communication parameters (transmission power, modulation and coding scheme (MCS), beam, and the like) at a transmission point and / or a reception point in the prediction area.

[0365] The control of the communication parameters may further be performed based on the accuracy in estimating communication characteristics in the prediction area. Furthermore, the control of the communication parameters may be performed by the control station 100 or may be performed by the base station 300. Alternatively, the control of the communication parameters may be performed in a core network or the like.

[0366] The statistical information according to the present embodiment can be utilized for designing interference power and separation distance, for example, in frequency sharing. By estimating interference power by utilizing statistical information on communication characteristics, the control station 100 can effectively use temporal and spatial free frequencies while avoiding interference with the protection target system.

[0367] Furthermore, the technology according to the present embodiment may be applied to 6G joint communication and sensing.

[0368] <5-5. Normalization of Actual Measurement Data>In the present embodiment, in a case where there are a plurality of learning areas, the simulation data and / or the actual measurement data in the learning areas are normalized (offset is given), for example, by a predetermined method.

[0369] The predetermined method may be performed on the basis of communication environment information (e.g., information regarding transmission power from the base station 300 and the like) in each learning area.

[0370] Here, the communication environment information is the information described above. The communication environment information includes, for example, information regarding transmission power of the base station 300, information regarding a frequency used for communication (a carrier frequency, a frequency bandwidth, etc.), information regarding a learning area (coverage area, indoor / outdoor information, etc.), and the like.

[0371] For example, the normalization is performed such that the learning areas have the same communication environment information.

[0372] The simulation data on communication characteristics in a predetermined area (one of the plurality of learning areas) is normalized such that the communication environment information in the predetermined area becomes the same as the communication environment information in each learning area (each of the learning areas other than the predetermined area).

[0373] The data on communication characteristics in a predetermined area (one of the plurality of learning areas) is estimated in consideration of the above-described normalization.

[0374] The actual measurement data on communication characteristics in a predetermined area (one of the plurality of learning areas) is normalized such that the communication environment information in the predetermined area becomes the same as the communication environment information in each learning area (each of the learning areas other than the predetermined area).

[0375] The above-described normalization is performed such that communication environment information in each learning area becomes the communication environment information in the above-described predetermined area (one of the plurality of learning areas).

[0376] The normalization is performed by, for example, a device (the control station 100 in the present embodiment) that generates an estimation model. Note that the device that performs normalization and the device that generates an estimation model may be different.

[0377] Hereinafter, a specific example of normalization will be described.

[0378] For example, consider a case where the communication characteristic of the simulation data and / or the actual measurement data in the learning area R01 is downlink RSRP.

[0379] Consider a case where the transmission power of the base station 300 in the learning area R01 is B1 (dBm), the transmission power of the base station 300 in the learning area R02 is B2 (dBm), and the transmission power of the base station 300 in the learning area R03 is B3 (dBm).

[0380] In a case where the transmission power is normalized to S (dBm), the control station 100 gives an offset of S-B1 (dBm) to RSRP in the learning area R01. The control station 100 gives an offset of S-B2 (dBm) to RSRP in the learning area R02. The control station 100 gives an offset of S-B3 (dBm) to RSRP in the learning area R03. In this manner, the control station 100 performs normalization by giving an offset to each RSRP (each piece of data).

[0381] Here, S (dBm) may be the transmission power of the base station 300 in the prediction area where estimation is performed.

[0382] <<6. Example of Hardware Configuration>>Fig. 25 is a diagram illustrating an example of a hardware configuration of a device or the like. The control station 100 described above is realized by, for example, a computer 1000 illustrated in Fig. 25.

[0383] The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, a hard disk drive (HDD) 1400, a communication interface 1500, and an input / output interface 1600. The units of the computer 1000 are connected to each other by a bus 1050.

[0384] The CPU 1100 operates based on programs stored in the ROM 1300 or the HDD 1400, and controls each unit. For example, the CPU 1100 develops the programs stored in the ROM 1300 or the HDD 1400 into the RAM 1200, and executes processing corresponding to the various programs.

[0385] The ROM 1300 stores a boot program such as a basic input output system (BIOS) executed by the CPU 1100 when the computer 1000 is activated, a program depending on the hardware of the computer 1000, and the like.

[0386] The HDD 1400 is a computer-readable storage medium that non-transiently stores a program executed by the CPU 1100, data used by the program, and the like. Specifically, the HDD 1400 is a storage medium that stores a program for the information processing method according to the present disclosure, which is an example of program data 1450.

[0387] The communication interface 1500 is an interface for the computer 1000 to be connected to an external network 1550 (e.g., the Internet). For example, the CPU 1100 receives data from another device or transmits data generated by the CPU 1100 to another device via the communication interface 1500.

[0388] The input / output interface 1600 is an interface for connecting the computer 1000 with an input / output device 1650. For example, the CPU 1100 receives data from an input device such as a keyboard or a mouse via the input / output interface 1600. In addition, the CPU 1100 transmits data to an output device such as a display, a speaker, or a printer via the input / output interface 1600. Furthermore, the input / output interface 1600 may function as a media interface that reads a program and the like stored in a predetermined computer-readable storage medium. The medium is, for example, an optical storage medium such as a digital versatile disc (DVD) or a phase change rewritable disk (PD), a magneto-optical storage medium such as a magneto-optical disk (MO), a tape medium, a magnetic storage medium, a semiconductor memory, or the like.

[0389] In a case where the computer 1000 functions as the control station 100 described above, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing programs loaded onto the RAM 1200. The programs may be stored in the HDD 1400. The CPU 1100 reads the program data 1450 from the HDD 1400 for execution, but may acquire the programs from other devices via the external network 1550 as another example.

[0390] Each of the above-described components may be configured using a general-purpose member, or may be configured by hardware specialized for the function of each component. Such a configuration can be appropriately changed according to the level of technology at the time of implementation.

[0391] <<7. Other Embodiments>>The processing according to the above-described embodiment may be performed in various different modes other than the above-described embodiment.

[0392] For example, in each of the above-described embodiments, the control station 100 performs, as statistical processing, a learning area selection process, an estimation model generation process, and a prediction process using the estimation model, but the device that performs these processes is not limited to the control station 100. For example, the base station 300 may perform at least one of these processes. In this case, the base station 300 acquires information for executing at least one of these processes from the control station 100 and / or the terminal device 400.

[0393] Alternatively, at least one of these processes may be executed by the terminal device 400. In this case, the terminal device 400 acquires information for executing at least one of these processes from the control station 100 and / or the base station 300.

[0394] Furthermore, in each of the above-described embodiments, the same one device (e.g., the control station 100) executes all of the learning area selection process, the estimation model generation process, and the prediction process using the estimation model, but these processes may be performed by different devices.

[0395] For example, the control station 100 may execute the selection process and the generation process, and the base station 300 may execute the prediction process. In this case, the control station 100 acquires information to be used for the selection process and the generation process from the base station 300 and / or the terminal device 400. The base station 300 acquires information to be used for the prediction process from the control station 100 and / or the terminal device 400.

[0396] Alternatively, for example, the control station 100 may execute the selection process, the base station 300 may execute the generation process, and the terminal device 400 may execute the prediction process. In this case, the control station 100 acquires information to be used for the selection process from the base station 300 and / or the terminal device 400. The base station 300 acquires information to be used for the generation process from the control station 100 and / or the terminal device 400. The terminal device 400 acquires information to be used for the prediction process from the control station 100 and / or the base station 300.

[0397] Alternatively, for example, the base station 300 may execute the selection process and the generation process, and the terminal device 400 may execute the prediction process. In this case, the base station 300 acquires information to be used for the selection process and the generation process from the control station 100 and / or the terminal device 400. The terminal device 400 acquires information to be used for the prediction process from the control station 100 and / or the base station 300. Note that the terminal device 400 may execute the selection process and the generation process, and the base station 300 may execute the prediction process.

[0398] In other words, in the present embodiment, the control station 100 can be appropriately replaced with the base station 300 or the terminal device 400. The base station 300 can be appropriately replaced with the control station 100 or the terminal device 400. The terminal device 400 can be appropriately replaced with the control station 100 or the base station 300.

[0399] For example, the control devices that control the control station 100, the base station 300, and the terminal device 400 of the above-described embodiments may be realized by a dedicated computer system or a general-purpose computer system.

[0400] For example, a communication program for executing the above-described operation is stored and distributed in a computer-readable recording medium such as an optical disk, a semiconductor memory, a magnetic tape, or a flexible disk. Then, for example, the program is installed in a computer, and the above-described processes are executed to configure the control devices. At this time, the control devices may be devices (e.g., personal computers) outside the control station 100, the base station 300, and the terminal device 400. Furthermore, the control device may be devices (e.g., the control units 130, 340, and 450) inside the control station 100, the base station 300, and the terminal device 400.

[0401] In addition, the communication program may be stored in a disk device included in a server device on a network such as the Internet so that the communication program can be downloaded to a computer. In addition, the above-described functions may be realized by cooperation between an operating system (OS) and application software. In this case, a portion other than the OS may be stored in a medium and distributed, or a portion other than the OS may be stored in a server device and downloaded to a computer.

[0402] Among the processes described in each of the above embodiments, all or some of the processes described as being automatically performed can be manually performed, or all or some of the processes described as being manually performed can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various types of data and parameters described hereinabove and illustrated in the drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each of the drawings are not limited to the illustrated information.

[0403] In addition, each component of each device illustrated in the drawings is functionally conceptual, and is not necessarily physically configured as illustrated in the drawings. That is, the specific form of distribution / integration between the devices is not limited to the illustrated form, and all or some of the devices can be functionally or physically distributed / integrated in any unit according to various loads, usage situations, and the like.

[0404] In addition, the above-described embodiments and modifications can be appropriately combined as long as the processing details are not contradictory.

[0405] Furthermore, the effects described in the present specification are merely examples and are not limited, and other effects may be provided.

[0406] Furthermore, for example, the present embodiment can be implemented as any configuration constituting a device or a system, for example, a processor as a system large scale integration (LSI) or the like, a module using a plurality of processors or the like, a unit using a plurality of modules or the like, a set in which other functions are added to the unit, or the like (that is, a configuration of a part of the device).

[0407] Note that, in the present embodiment, the system means a set of a plurality of components (devices, modules (parts), or the like), and it does not matter whether all the components are in the same housing. Therefore, a plurality of devices housed in separate housings and connected via a network and one device with a plurality of modules housed in one housing are both systems.

[0408] Furthermore, for example, the present embodiment can adopt a cloud computing configuration in which one function is shared and processed by a plurality of devices in cooperation via a network.

[0409] In the embodiment described above, the case where the control station 100 determines the control information for the base station 300 and / or the terminal device 400 has been described, but the determination of the control information is not limited thereto. Each of the embodiments described above can be used for the purpose of determining or designing a transmission parameter and / or a reception parameter, the number of base stations 300 and / or terminal devices 400 to be installed (upper limit number of installations), installation locations, and / or installation directions (horizontal direction, tilt angle, etc.).

[0410] <<8. Conclusion>>The effects described in the present disclosure are merely examples, and are not limited to the disclosed contents. Other effects may be provided.

[0411] Although the embodiments of the present disclosure have been described above, the technical scope of the present disclosure is not limited to the above-described embodiments, and various modifications can be made without departing from the gist of the present disclosure. In addition, components of different embodiments and modifications may be appropriately combined.

[0412] Note that the present technology can also have the following configurations.(1) An information processing device, comprising: processing circuitry configured to: receive input information regarding wireless environment characteristics of a plurality of source areas and a target area, determine at least one learning area from among a plurality of source areas based on a similarity between the wireless environment characteristics of each source area and the target area, acquire measurement data regarding communication characteristics from the at least one learning area, and determine communication parameters for wireless communication in the target area based on the measurement data.(2) The information processing device according to (1), wherein the plurality of source areas are candidate areas for learning, and the target area is a prediction area.(3) The information processing device according to (1), wherein the measurement data includes actual measurement data acquired from terminal devices in the determined at least one learning area.(4) The information processing device according to (1), wherein the measurement data includes virtual space estimation information obtained by simulation of the at least one learning area.(5) The information processing device according to (1), wherein the measurement data includes actual measurement data and virtual space estimation obtained by simulation of information from the at least one learning area.(6) The information processing device according to (1), wherein the circuitry is further configured to generate an estimation model for determining the communication characteristics in the target area using the measurement data acquired from the at least one learning area.(7) The information processing device according to (1), wherein the wireless environment characteristics include obstacle information regarding obstacles that affect communication characteristics, and the processing circuitry is further configured to determine the similarity based on the obstacle information.(8) The information processing device according to (7), wherein the obstacle information includes heights of obstacles in each of the plurality of source areas and the target area.　(9) The information processing device according to (7), wherein the obstacle information includes densities of obstacles in each of the plurality of source areas and the target area.　(10) The information processing device according to (1), wherein the wireless environment characteristics include propagation characteristics, and the processing circuitry is further configured to determine the similarity based on propagation characteristics in each of the plurality of source areas and the target area.　(11) The information processing device according to (1), wherein the wireless environment characteristics include line-of-sight (LOS) and non-line-of-sight (NLOS) information, and the processing circuitry is further configured to determine the similarity based on the LOS and the NLOS information in each of the plurality of candidate areas and the prediction area.　(12) The information processing device according to (1), wherein the processing circuitry is further configured to divide each of the plurality of source areas and the target area into a plurality of unit spatial domains and compare statistics calculated for each unit spatial domain.　(13) The information processing device according to (6), wherein the processing circuitry is further configured to transmit the determined communication parameters to at least one of a base station and a terminal device.　(14) The information processing device according to (13), wherein the communication parameters include at least one of modulation and coding scheme information, transmission power information, beam control information, and multiple input multiple output multiplexing information.　(15) The information processing device according to (6), wherein the processing circuitry is further configured to determine the communication parameters by inputting area data regarding the target area to the estimation model.　(16) The information processing device according to (6), wherein the processing circuitry is further configured to generate the estimation model using the similarity between each learning area and the target area as a weighting coefficient for measurement data from each respective learning area.　(17) The information processing device according to (6), wherein the processing circuitry is further configured to normalize the measurement data from multiple learning areas based on communication environment information before generating the estimation model.　(18) The information processing device according to (6), wherein the communication characteristics include at least one of reception power, interference power, signal-to-noise ratio, signal-to-interference power ratio, throughput, and delay characteristics.　(19) A terminal device, comprising: processing circuitry configured to: wirelessly communicate with a base station, measure communication characteristics and generate measurement data, and transmit the measurement data to an information processing device, wherein the measurement data is used by the information processing device to determine communication parameters for wireless communication in a target area based on the measurement data.　(20) An information processing method, comprising: receiving input information regarding wireless environment characteristics of a plurality of source areas and a target area, determining at least one learning area from among a plurality of source areas based on a similarity between the wireless environment characteristics of each source area and the target area, acquiring measurement data regarding communication characteristics from the at least one learning area, determining communication parameters for wireless communication in the target area based on the measurement data, and transmitting the determined communication parameters to at least one of a base station and a terminal device.

[0413] 100 Control station110, 310, 410 Communication unit120, 320, 420 Storage unit130, 340, 450 Control unit300 Base station330, 430 Network communication unit400 Terminal device440 Input / output unit

Claims

1. An information processing device, comprising:　processing circuitry configured to　receive input information regarding wireless environment characteristics of a plurality of source areas and a target area,　determine at least one learning area from among a plurality of source areas based on a similarity between the wireless environment characteristics of each source area and the target area,　acquire measurement data regarding communication characteristics from the at least one learning area, and　determine communication parameters for wireless communication in the target area based on the measurement data.

2. The information processing device according to claim 1, wherein the plurality of source areas are candidate areas for learning, and the target area is a prediction area.

3. The information processing device according to claim 1, wherein the measurement data includes actual measurement data acquired from terminal devices in the determined at least one learning area.

4. The information processing device according to claim 1, wherein the measurement data includes virtual space estimation information obtained by simulation of the at least one learning area.

5. The information processing device according to claim 1, wherein the measurement data includes actual measurement data and virtual space estimation obtained by simulation of information from the at least one learning area.

6. The information processing device according to claim 1, wherein the circuitry is further configured to　generate an estimation model for determining the communication characteristics in the target area using the measurement data acquired from the at least one learning area.

7. The information processing device according to claim 1, wherein the wireless environment characteristics include obstacle information regarding obstacles that affect communication characteristics, and　the processing circuitry is further configured todetermine the similarity based on the obstacle information.

8. The information processing device according to claim 7, wherein the obstacle information includes heights of obstacles in each of the plurality of source areas and the target area.

9. The information processing device according to claim 7, wherein the obstacle information includes densities of obstacles in each of the plurality of source areas and the target area.

10. The information processing device according to claim 1, wherein the wireless environment characteristics include propagation characteristics, and　the processing circuitry is further configured todetermine the similarity based on propagation characteristics in each of the plurality of source areas and the target area.

11. The information processing device according to claim 1, wherein the wireless environment characteristics include line-of-sight (LOS) and non-line-of-sight (NLOS) information, and　the processing circuitry is further configured todetermine the similarity based on the LOS and the NLOS information in each of the plurality of candidate areas and the prediction area.

12. The information processing device according to claim 1, wherein the processing circuitry is further configured to　divide each of the plurality of source areas and the target area into a plurality of unit spatial domains and compare statistics calculated for each unit spatial domain.

13. The information processing device according to claim 6, wherein the processing circuitry is further configured to　transmit the determined communication parameters to at least one of a base station and a terminal device.

14. The information processing device according to claim 13, wherein the communication parameters include at least one of modulation and coding scheme information, transmission power information, beam control information, and multiple input multiple output multiplexing information.

15. The information processing device according to claim 6, wherein the processing circuitry is further configured to　determine the communication parameters by inputting area data regarding the target area to the estimation model.

16. The information processing device according to claim 6, wherein the processing circuitry is further configured to　generate the estimation model using the similarity between each learning area and the target area as a weighting coefficient for measurement data from each respective learning area.

17. The information processing device according to claim 6, wherein the processing circuitry is further configured to　normalize the measurement data from multiple learning areas based on communication environment information before generating the estimation model.

18. The information processing device according to claim 6, wherein the communication characteristics include at least one of reception power, interference power, signal-to-noise ratio, signal-to-interference power ratio, throughput, and delay characteristics.

19. A terminal device, comprising:　processing circuitry configured to　wirelessly communicate with a base station,　measure communication characteristics and generate measurement data, and　transmit the measurement data to an information processing device, wherein the measurement data is used by the information processing device to determine communication parameters for wireless communication in a target area based on the measurement data.

20. An information processing method, comprising:　receiving input information regarding wireless environment characteristics of a plurality of source areas and a target area;　determining at least one learning area from among a plurality of source areas based on a similarity between the wireless environment characteristics of each source area and the target area;　acquiring measurement data regarding communication characteristics from the at least one learning area;determining communication parameters for wireless communication in the target area based on the measurement data; and　transmitting the determined communication parameters to at least one of a base station and a terminal device.

Images