Network configuration analysis system, network configuration analysis method, and network configuration analysis program

Abstract

To provide a network configuration analysis system, a network configuration analysis method, and a network configuration analysis program that are capable of quickly estimating a network configuration.SOLUTION: A network configuration analysis system according to the present disclosure includes a signal feature quantity extraction unit that extracts signal feature quantities of a plurality of signals contained in received radio waves, a cluster analysis unit that performs cluster analysis on the plurality of signal feature quantities to classify signals of the plurality of signal feature quantities into a forward link group and a return link group, and a combination optimization unit that estimates communication pairs for communication via relays, which are combinations between signals contained in the forward link group and signals contained in the return link group.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a network configuration analysis system, a network configuration analysis method, and a network configuration analysis program. [Background technology]

[0002] Systems have been proposed that use radio wave sensors and traffic monitors to analyze wireless frames and traffic from target terminals to estimate the transmission content and the configuration of the network being analyzed. Examples of transmission content include voice calls, video transmissions, telemetry data transmissions, satellite communications, and satellite broadcasting. Examples of network configurations include tree, star, ring, mesh, bus, and full-connect configurations, as well as combinations of these.

[0003] Furthermore, as one method for analyzing network configuration, a method has been proposed in which frame features such as the amount of data transferred per unit time, the number of transferred data items, the number of transfers, the transfer frequency, and the transfer time are extracted and analyzed.

[0004] For example, in bands where radio waves of multiple communication methods are transmitted, such as the ISM band, different operators each build their own networks. As a result, there is a possibility of radio interference between networks built and operated by other operators. In such an environment, by estimating the network configuration of other operators, it becomes possible to change the settings of one's own network so as not to interfere with the networks of other companies. As a result, it is expected that the setup time when building a private wireless network that shares frequencies will be shortened, and even spatial frequency utilization efficiency will be improved through optimal settings.

[0005] For example, Patent Document 1 discloses a method for reducing the number of samples required for analysis, i.e., shortening the analysis time, by performing clustering processing on frame features, determining reliability based on the calculated inter-cluster distance of the clusters, and determining the number of frame feature samples to be worked on depending on the reliability.

[0006] Furthermore, Patent Document 2 discloses a method for determining whether a transmitting terminal is a relay terminal or a standard terminal by separating received traffic for each transmitting terminal, separating it into control signals and user information, and extracting periodicity by performing autocorrelation processing on the control information. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Publication No. 2022-74302 [Patent Document 2] Patent No. 6091378 Summary of the Invention [Problem to be solved by the invention]

[0008] As described above, by estimating the network configuration of others, it becomes possible to change the settings of one's own network, and it is expected that the efficiency of frequency utilization will be improved. However, since it takes time to estimate communication pairs (combinations of forward links and return links) in other networks using the radio wave sensors of one's own system, there has been a problem in that it takes time to estimate the network configuration of others.

[0009] Patent Document 1 discloses a method for shortening analysis time, but does not disclose a method for estimating the role of each node in the network. Patent Document 2 discloses a technique for estimating the role of each node in an ad hoc network. However, because it is based on the premise of an ad hoc network, it does not disclose a method for estimating communication pairs (forward link and return link) in a situation where there are multiple communication pairs via the network.

[0010] An object of the present disclosure is to provide a network configuration analysis system, a network configuration analysis method, and a network configuration analysis program that solve the above-mentioned problems. [Means for solving the problem]

[0011] The network configuration analysis system according to the present disclosure includes a signal feature extraction unit that extracts signal features of a plurality of signals contained in received radio waves; a cluster analysis unit that performs cluster analysis on the plurality of signal features to classify the signals of the plurality of signal feature values ​​into a forward link group and a return link group; and a combination optimization unit that estimates communication pairs for communication via relays, which are combinations between signals contained in the forward link group and signals contained in the return link group.

[0012] The network configuration analysis method according to the present disclosure involves a computer extracting signal features of multiple signals contained in received radio waves, performing cluster analysis on the multiple signal features to classify the signals of the multiple signal features into either a forward link group or a return link group, and estimating communication pairs for communication via relays, which are combinations of signals contained in the forward link group and signals contained in the return link group.

[0013] The network configuration analysis program according to the present disclosure causes a computer to execute the following processes: extracting signal features of multiple signals contained in received radio waves; classifying signals of the multiple signal features into either a forward link group or a return link group by performing cluster analysis on the multiple signal features; and estimating communication pairs of communication via relays, which are combinations between signals contained in the forward link group and signals contained in the return link group. [Effects of the Invention]

[0014] The present disclosure can provide a network configuration analysis system, a network configuration analysis method, and a network configuration analysis program that can quickly estimate a network configuration. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a block diagram illustrating an overview of a network configuration analysis apparatus according to the present disclosure. [Figure 2] FIG. 1 is a diagram illustrating an application example of a network configuration analysis device according to the present disclosure. [Figure 3] 1 is a block diagram illustrating an example configuration of a network configuration analysis device according to the present disclosure. [Figure 4] 10 is a flowchart illustrating an operation of a network configuration analysis device according to the present disclosure. [Figure 5] 10 is a flowchart illustrating details of an analysis process of a network configuration analysis device according to the present disclosure. [Figure 6] FIG. 10 is a diagram illustrating an example of cluster analysis performed by a network configuration analysis device according to the present disclosure. [Figure 7] 1 is a block diagram illustrating an example configuration of a network configuration analysis device according to the present disclosure. [Figure 8] 10 is a flowchart illustrating an operation of a network configuration analysis device according to the present disclosure. [Figure 9] FIG. 10 is a diagram illustrating an example of a pairing result obtained by the network configuration analysis device according to the present disclosure. [Figure 10] 1 is a block diagram illustrating an example configuration of a network configuration analysis system according to the present disclosure. [Figure 11] FIG. 2 is a sequence diagram illustrating the operation of the network configuration analysis system according to the present disclosure. [Figure 12] FIG. 2 is a block diagram illustrating an example of a hardware configuration for implementing an analysis function of a network configuration analysis apparatus according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, embodiments will be described with reference to the drawings. Note that the drawings are simplified, and the technical scope of the embodiments should not be narrowly interpreted based on the description in the drawings. Furthermore, identical elements are given the same reference numerals, and duplicate explanations will be omitted.

[0017] In the following embodiments, when necessary for convenience, the description will be divided into multiple sections or embodiments. However, unless otherwise specified, they are not unrelated to each other, and one is a partial or complete modification, application example, detailed explanation, supplementary explanation, etc. of the other. Furthermore, in the following embodiments, when the number of elements (including the number, numerical value, amount, range, etc.) is mentioned, it is not limited to that specific number, and may be more or less than the specific number, unless otherwise specified or when it is clearly limited to a specific number in principle.

[0018] Furthermore, in the following embodiments, the components (including operational steps, etc.) are not necessarily essential unless otherwise specified or considered to be clearly essential in principle. Similarly, in the following embodiments, when referring to the shape, positional relationship, etc. of components, etc., it is intended to include those that are substantially similar or approximate to the shape, etc., unless otherwise specified or considered to be clearly not essential in principle. The same applies to the above numbers, etc. (including numbers, numerical values, amounts, ranges, etc.).

[0019] <First Embodiment> 1 is a block diagram showing an overview of a network configuration analysis device according to the present disclosure. Network configuration analysis device 1 is a device that estimates, for example, the network configuration of other parties. The estimation results are used to adjust the settings of one's own network so as to avoid interference from the network configuration of other parties.

[0020] Specifically, the network configuration analysis device 1 includes a receiver 11, a signal feature extraction unit 12, a cluster analysis unit 13, and a combination optimization unit 14. In this embodiment, the receiver 11, the signal feature extraction unit 12, the cluster analysis unit 13, and the combination optimization unit 14 are implemented in a single device, but this is not limitative and each may be implemented in a different device. Therefore, the receiver 11, the signal feature extraction unit 12, the cluster analysis unit 13, and the combination optimization unit 14 can be said to be a network configuration analysis system implemented in one or more devices.

[0021] The receiver 11 receives radio waves used for communication on another network, for example. The signal feature extractor 12 extracts signal features of multiple signals contained in the received radio waves. The cluster analyzer 13 performs cluster analysis on the extracted signal features to classify the signals of the multiple signal features into a forward link group and a return link group. The combinatorial optimizer 14 estimates communication pairs for communication via relays, which are combinations between signals included in the forward link group and signals included in the return link group.

[0022] For example, the network configuration analysis device 1 is applied to a network as shown in FIG. 2. In FIG. 2, the radio wave sensor of the local system corresponds to the network configuration analysis device 1. In FIG. 2, the radio wave sensor B1 (network configuration analysis device 1) of the local system estimates, for example, the network configuration of another system. The other system is composed of a control station (fixed station) A1, a terminal station (mobile station) A2, and a relay station A3 that relays communication between the control station A1 and the terminal station A2. A signal line from the control station A1 to the terminal station A2 via the relay station A3 is called a forward link, and a signal line from the terminal station A2 to the control station A1 via the relay station A3 is called a return link. Furthermore, a signal line from the control station A1 or the terminal station A2 to the relay station A3 is called an uplink, and a signal line from the relay station A3 to the control station A1 or the terminal station A2 is called a downlink. Here, generally, the transmission power of the control station A1 is high, and the transmission power of the terminal station A2 is low. Furthermore, relay station A3 amplifies the signal using an amplitude amplifier. Therefore, the radio wave sensor B1 (network configuration analysis device 1) of the system itself can estimate the network configuration of other systems by monitoring the downlink radio waves of relay station A3, where the difference in received power is large. The estimation result can be used to adjust the settings of the system's own network to avoid interference from the network configuration of other systems, for example.

[0023] <Embodiment 2> FIG. 3 is a block diagram showing an example configuration of a network configuration analysis device according to the present disclosure. As shown in FIG. 3, the network configuration analysis device 2 includes a receiver 11, a signal feature extraction unit 12, an analyzer 16, a feature accumulation unit 15, and an output unit 17. The analyzer 16 includes a cluster analysis unit 13 and a combinatorial optimization unit 14. In other words, compared to the network configuration analysis device 1, the network configuration analysis device 2 further includes a feature accumulation unit 15 and an output unit 17. Note that the multiple functional units of the network configuration analysis device 2 do not necessarily need to be implemented in a single device, but may each be implemented in a different device. In other words, the multiple functional units of the network configuration analysis device 2 can be said to be a network configuration analysis system implemented in one or more devices.

[0024] The receiving unit 11 receives, for example, radio waves used for communication on another person's network via an antenna. The signal feature extraction unit 12 extracts signal features of multiple signals contained in the radio waves received by the receiving unit 11. The signal features include, for example, the bandwidth and power value of the received signal. The signal features of the multiple signals extracted by the signal feature extraction unit 12 are stored in the feature storage unit 15.

[0025] In the analysis unit 16, the cluster analysis unit 13 performs cluster analysis on the extracted multiple signal feature amounts (e.g., bandwidth and power value) to classify the signals of the multiple signal feature amounts into a forward link group and a return link group. The combination optimization unit 14 estimates, by mathematical optimization, communication pairs of communication via relays (relay stations), which are combinations between signals included in the forward link group and signals included in the return link group.

[0026] The output unit 50 outputs the estimation result of the communication pairs of the communication via the relay to the outside of the network configuration analysis device 2.

[0027] Next, the operation of the network configuration analysis device 2 will be described with reference to FIGS.

[0028] FIG. 4 is a flowchart showing the operation of the network configuration analysis device according to the present disclosure. As shown in FIG. 4, first, the network configuration analysis device 2 receives, via the antenna, radio waves used for communication in, for example, another party's network (step S11) at the receiver 11. Then, the network configuration analysis device 2 extracts signal features of multiple signals included in the received radio waves at the signal feature extractor 12 (step S12). Then, the network configuration analysis device 2 accumulates the extracted signal features of the multiple signals in the feature accumulation unit 15 (step S13). Then, the network configuration analysis device 2 analyzes the accumulated signal features at the analyzer 16 to estimate communication pairs in communication via relays (step S14). Then, the network configuration analysis device 2 outputs, via the output unit 17, the analysis result of the analyzer 16 (the estimated result of communication pairs in communication via relays) to the outside of the network configuration analysis device 2 (step S15).

[0029] Fig. 5 is a flowchart showing details of the analysis process by the network configuration analysis device according to the present disclosure. That is, Fig. 5 is a flowchart showing details of the analysis process (processing of step S14) by the analysis unit 16 of the network configuration analysis device 2. In the example of Fig. 5, the network configuration analysis device 2 performs analysis using the signal bandwidth and received power value included in the signal feature amount.

[0030] 5, in the network configuration analysis device 2, the cluster analysis unit 13 of the analysis unit 16 performs a first cluster analysis to classify signals of a plurality of signal feature quantities stored in the feature quantity storage unit 15 into one or more classes according to bandwidth (step S141). Thereafter, in the network configuration analysis device 2, the cluster analysis unit 13 of the analysis unit 16 performs a second cluster analysis to classify a plurality of signals belonging to each of the one or more classes classified according to bandwidth into a forward link group and a return link group according to received power (step S142). For example, in the network configuration analysis device 2, the cluster analysis unit 13 of the analysis unit 16 performs the second cluster analysis to classify a plurality of signals belonging to each of the one or more classes classified according to bandwidth into a return link group and a forward link group having higher received power than the return link group. Thereafter, the network configuration analysis device 2 estimates, by mathematical optimization in the combination optimization unit 14 of the analysis unit 16, communication pairs of communication via relays, which are combinations between signals included in the forward link group and signals included in the return link group (step S143). If the network configuration analysis device 2 has not completed the processing of steps S142 and S143 for all of the one or more classes classified according to bandwidth (NO in step S144), it completes the processing of steps S142 and S143 for all of the one or more classes classified according to bandwidth (YES in step S144).

[0031] FIG. 6 is a diagram illustrating an example of cluster analysis performed by a network configuration analysis device according to the present disclosure.

[0032] FIG. 6(a) shows the relationship between the bandwidth and the received power of signals of multiple signal feature quantities stored in the feature quantity storage unit 15. In other words, FIG. 6(a) shows multiple plots representing signals of multiple signal feature quantities stored in the feature quantity storage unit 15 on a coordinate system where the horizontal axis represents bandwidth and the vertical axis represents received power. As shown in FIG. 6(a), there may be distributions in bandwidth and received power depending on the communication method. By performing a first cluster analysis on the signals (plots) of these signal feature quantities, the signals of these signal feature quantities are classified into one or more classes according to the bandwidth.

[0033] Figure 6(b) shows the results of a first cluster analysis performed on the signals (plots) of the multiple signal feature quantities shown in Figure 6(a). In the example of Figure 6(b), the signals are classified into three classes (areas surrounded by dotted lines) according to bandwidth. Furthermore, by performing a second cluster analysis on the signals (plots) belonging to each of the three classes classified according to bandwidth, the signals of these signal feature quantities are classified into two groups, a return link group and a forward link group, according to received power.

[0034] Figure 6(c) shows the results of a second cluster analysis performed on multiple signals (plots) belonging to each of the three classes shown in Figure 6(b). In the example of Figure 6(c), signals belonging to each of the three classes classified according to bandwidth are classified into two groups, a return link group and a forward link group, according to received power. Specifically, in each of the three classes classified according to bandwidth, signals with low received power are classified into the return link group, and signals with high received power are classified into the forward link group.

[0035] For the first cluster analysis, it is difficult to specify the number of clusters in advance, so methods that do not require specifying the number of clusters in advance, such as x-means or VBGMM (Variational Bayesian Gaussian Mixture), can be applied.In contrast, for the second cluster analysis, it is possible to specify the number of clusters in advance, so methods that do allow specifying the number of clusters in advance, such as k-means, can be applied.

[0036] In addition, although the present disclosure has described an example in which the bandwidth and received power included in the signal feature are used in the first cluster analysis and the second cluster analysis, the present disclosure is not limited to this. For example, the first cluster analysis and the second cluster analysis may use features included in the signal feature that represent the transmission mode of each transmitter, such as the amount of transmitted data, the frequency of transmission, the number of transmissions, the transmission time, the bandwidth utilization rate, the modulation method, and the transmission power.

[0037] Next, the processing by the combinatorial optimization unit 14 of the analysis unit 16 (processing of step S143) will be described in more detail. In this disclosure, an example will be described in which the combinatorial optimization unit 14 analyzes pairings (combinations of forward links and return links) as a mathematical optimization problem. Therefore, the combinatorial optimization unit 14 formulates the problem to be solved as "a problem of finding a solution that minimizes the value of an objective function under given constraint conditions." The objective function, decision variables, and constraint conditions are as follows:

[0038] The set to be optimized is the forward link group and return link group classified by the processing of steps S141 to S142. Here, the number of forward links is N_F, and the number of return links is N_R. The set of forward links is I, and its element is i. The set of return links is J, and its element is j. Furthermore, D is an i x j matrix whose elements are the differences between the received power values ​​of forward link i and return link j.

[0039] First, the objective function is expressed as in Equation 1, which means minimizing the maximum value of the power difference.

[0040]

number

[0041] Here, the maximum value of the power difference when the combination of the forward link and the return link is provisionally determined is defined as z. The decision variable is represented by x_ij, which indicates "1" when the forward link i and the return link j are paired, and indicates "0" when they are not paired. In this case, the constraints are expressed as in the following Equations 2 to 6.

[0042]

number

[0043]

number

[0044]

number

[0045]

number

[0046]

number

[0047] Here, Equation 2 expresses a constraint that the maximum value z of the power difference is 0 or more. Equation 3 expresses a constraint that the number of return links paired with a forward link is 1 or less. Equation 4 expresses a constraint that the number of forward links paired with a return link is 1 or less. Equation 5 expresses a constraint that the number of layers of the pairing of forward links and return links is equal to the smaller of the number of forward links and the number of return links. Equation 6 expresses a constraint that all power differences after pairing are z or less.

[0048] The above-mentioned objective functions and constraints are merely examples, and the pairing of the forward link and the return link may be determined by other formulations.

[0049] In this way, the network configuration analysis device 2 according to the present disclosure classifies multiple signals into a forward group and a return link group through cluster analysis, and estimates communication pairs of communications via relays, which are combinations of signals belonging to the forward group and signals belonging to the return link group, through mathematical optimization. This allows the network configuration analysis device 2 according to the present disclosure to quickly estimate the network configuration.

[0050] The combination optimization unit 14 may add processing other than the above-described processing. For example, the combination optimization unit 14 can improve the pairing estimation accuracy of the forward link and the return link by performing optimization in two or more stages. In this case, in the optimization processing from the second stage onwards, the objective function can be the following equation (7), which means minimizing the total value of the power differences, instead of equation (1).

[0051]

number

[0052] <Third Embodiment> Fig. 7 is a block diagram showing an example configuration of a network configuration analysis device according to the present disclosure. As shown in Fig. 7, compared to network configuration analysis device 2, network configuration analysis device 3 includes a visualization unit 37 as output unit 17. The other configurations and operations of network configuration analysis device 3 are similar to those of network configuration analysis device 2, and therefore description thereof will be omitted.

[0053] In the network configuration analyzing device 3, the visualization unit 37 visualizes the analysis process and analysis results by the analysis unit 16 and displays them on a monitor or the like.

[0054] FIG. 8 is a flowchart illustrating the operation of the network configuration analysis device according to the present disclosure. As shown in FIG. 8, first, the network configuration analysis device 3 receives, via the antenna, radio waves used for communication in, for example, another network (step S11) at the receiver 11. Then, the signal feature extractor 12 extracts signal features from multiple signals included in the received radio waves (step S12). Then, the network configuration analysis device 3 stores the extracted signal features in the feature storage unit 15 (step S13). Then, the analysis unit 16 analyzes the stored signal features to estimate communication pairs in communication via relays (step S14). Details of the process of step S14 are similar to those shown in FIG. 3 , and therefore will not be described again. Then, the network configuration analysis device 3 visualizes the analysis process and analysis results (estimated communication pairs in communication via relays) by the analysis unit 16 and displays them on a monitor or the like (step S21).

[0055] In the visualization by the visualization unit 37, first, the cluster analysis results are visualized as the visualization of the analysis process in the analysis unit 40. For example, coordinates representing the process and results of the cluster analysis as shown in Fig. 6 are displayed on a monitor. At this time, the monitor may display, on a coordinate system in which the horizontal axis (first coordinate axis) represents bandwidth and the vertical axis (second coordinate axis) represents received power, multiple plots representing signals of multiple signal feature amounts, and frames (dotted frame in Fig. 6) surrounding the multiple plots indicating to which forward link group and return link group the signals of the multiple signal feature amounts belong.

[0056] In the visualization by the visualization unit 37, next, the pairing results of the forward link and the return link obtained by combinatorial optimization are visualized as the visualization of the analysis results by the analysis unit 40. For example, coordinates representing the pairing results as shown in Fig. 9 are displayed on the monitor. At this time, the monitor may display plots representing the frequency spectra of multiple signals and lines connecting the two signals (frequency spectra) of the estimated communication pair on a coordinate system where the horizontal axis represents the center frequency and the vertical axis represents the received power.

[0057] In this way, the network configuration analysis device 3 according to the present disclosure can achieve effects comparable to those of the network configuration analysis device 2. Furthermore, the network configuration analysis device 3 according to the present disclosure can use the visualization unit 37 to visualize the analysis process and analysis results by the analysis unit 16 and display them on a monitor or the like. This allows the user to adjust the network configuration settings by referring to the analysis process and analysis results displayed on the monitor or the like.

[0058] <Fourth Embodiment> Fig. 10 is a block diagram showing an example configuration of a network configuration analysis system according to the present disclosure. As shown in Fig. 10, the network configuration analysis system 4 includes a plurality of radio wave monitoring units 41, a feature accumulation unit 15, an analysis unit 16, and a visualization unit 37. Each radio wave monitoring unit 41 includes a receiving unit 11 and a signal feature extraction unit 12. Each radio wave monitoring unit 41, the feature accumulation unit 15, the analysis unit 16, and the visualization unit 37 are provided separately and are connected to each other via a network.

[0059] The multiple radio wave monitoring units 41 each receive radio waves at a different site and extract signal features from the multiple signals contained in the received radio waves. The multiple signal features extracted by the multiple radio wave monitoring units 41 are stored in the feature storage unit 15 via the network. The configurations and operations of the feature storage unit 15, analysis unit 16, and visualization unit 37 in the network configuration analysis system 4 are similar to those of the feature storage unit 15, analysis unit 16, and visualization unit 37 in the network configuration analysis device 3, and therefore will not be described here.

[0060] Each radio wave monitoring unit 41, feature storage unit 15, analysis unit 16, and visualization unit 37 are also connected to an operation console (not shown) via a network. Network configuration analysis system 4 is remotely controlled by an operator operating the operation console.

[0061] 11 is a sequence diagram showing the operation of the network configuration analysis system according to the present disclosure. Note that the processing of steps S11 to S14 and S21 in FIG. 11 corresponds to the processing of steps S11 to S14 and S21 in FIG.

[0062] 11, an operator operates the console to instruct each radio wave monitoring unit 41 to collect data. As a result, each radio wave monitoring unit 41 receives radio waves at each site and extracts signal features from multiple signals contained in the received radio waves (steps S11 and S12). The signal features extracted by each radio wave monitoring unit 41 are stored in the feature storage unit 15 via the network (step S13). Thereafter, each radio wave monitoring unit 41 notifies the console that data collection has been completed.

[0063] Thereafter, an operator operates the console to instruct the analysis unit 16 and the visualization unit 37 to perform analysis. As a result, the analysis unit 16 analyzes the multiple signal features stored in the feature storage unit 15 (step S14). The analysis unit 16 then notifies the console that the analysis is complete. Then, the visualization unit 37 visualizes the analysis process (cluster analysis results) and analysis results (pairing results) performed by the analysis unit 16 and displays them on a monitor or the like (step S21).

[0064] In this way, network configuration analysis system 4 according to the present disclosure can achieve effects comparable to those of network configuration analysis device 3. Furthermore, because network configuration analysis system 4 according to the present disclosure receives radio waves from multiple sites and extracts signal features, it can estimate network configuration with greater accuracy than when receiving radio waves from a single site and extracting signal features. Furthermore, network configuration analysis system 4 according to the present disclosure can install radio wave monitoring unit 41, which is composed of receiver 11 and signal feature extractor 12, separately from analyzer 16 and visualization unit 37.

[0065] (Hardware configuration for realizing the analysis function of network configuration analysis device 1) The analysis process performed by the network configuration analyzing device 1 can be realized by a general-purpose computer system, which will be briefly explained below with reference to FIG.

[0066] 12 is a block diagram showing an example of a hardware configuration that realizes the analysis function of the network configuration analysis device 1. The computer 300 includes, for example, a central processing unit (CPU) 301, which is a control device, a random access memory (RAM) 302, and a read only memory (ROM) 303. The computer 300 further includes an interface (IF) 304, which is an interface with the outside, and a hard disk drive (HDD) 305, which is an example of a non-volatile storage device. The computer 300 may also include input devices such as a keyboard and a mouse, and a display device such as a display, as other components not shown.

[0067] The HDD 305 stores an OS (Operating System) (not shown) and a control program 306. The control program 306 is a computer program (network configuration analysis program) that implements the analysis processing of the network configuration analysis device 1.

[0068] CPU 301 controls various processes in computer 300, access to RAM 302, ROM 303, IF 304, and HDD 305, etc. In computer 300, CPU 301 reads and executes an OS and control program 306 stored in HDD 305. In this way, computer 300 realizes the analysis function of network configuration analysis device 1.

[0069] The above-mentioned program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in this disclosure. The program may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable medium or tangible storage medium includes RAM, ROM, flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0070] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0071] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one particular embodiment, but also to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0072] Furthermore, some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0073] (Appendix 1) a receiving unit that receives radio waves; a signal feature extraction unit that extracts signal feature quantities of a plurality of signals included in the received radio wave; a cluster analysis unit that performs cluster analysis on the plurality of signal feature amounts to classify the signals of the plurality of signal feature amounts into a forward link group and a return link group; a combination optimization unit that estimates a communication pair of a communication via a relay, which is a combination between a signal included in the forward link group and a signal included in the return link group; A network configuration analysis system comprising:

[0074] (Appendix 2) the signal features include a bandwidth and a received power value; The cluster analysis unit classifying the signals of the plurality of signal feature quantities into one or more classes according to bandwidth; classifying a plurality of signals belonging to each of one or more classes classified according to bandwidth into a forward link group and a return link group according to received power; 2. The network configuration analysis system of claim 1.

[0075] (Appendix 3) The cluster analysis unit classifying a plurality of signals belonging to each of one or more classes classified according to bandwidth into a return link group and a forward link group having higher received power than the return link group; 3. The network configuration analysis system of claim 2.

[0076] (Appendix 4) The cluster analysis unit classifying the signals of the plurality of signal feature quantities into one or more classes according to bandwidth using one of x-means and VBGMM (Variational Bayesian Gaussian Mixture); classifying a plurality of signals belonging to each of one or more classes classified according to bandwidth into a forward link group and a return link group according to received power using a k-means method; 3. The network configuration analysis system of claim 2.

[0077] (Appendix 5) the combination optimization unit estimates the communication pairs such that a maximum value of a power difference between signals to be combined between the signals included in the forward link group and the signals included in the return link group is minimized. 3. The network configuration analysis system of claim 2.

[0078] (Appendix 6) the signal features include a bandwidth and a received power value; the combination optimization unit estimates the communication pairs such that a maximum value of a power difference between signals to be combined between the signals included in the forward link group and the signals included in the return link group is minimized. 2. The network configuration analysis system of claim 1.

[0079] (Appendix 7) the signal features include a bandwidth and a received power value; Further comprising a visualization unit, the visualization unit displays, on a coordinate system in which a first coordinate axis represents a bandwidth and a second coordinate axis orthogonal to the first coordinate axis represents a received power, a plurality of plots representing signals of the plurality of signal feature amounts and frames surrounding the plurality of plots representing whether the signals of the plurality of signal feature amounts belong to the forward link group or the return link group. 2. The network configuration analysis system of claim 1.

[0080] (Appendix 8) the signal features include a bandwidth and a received power value; Further comprising a visualization unit, The visualization unit a plot representing the frequency spectrum of the plurality of signals and a line segment connecting the two signals of the estimated communication pair are displayed on a coordinate system in which a first coordinate axis represents a center frequency and a second coordinate axis perpendicular to the first coordinate axis represents a received power; 2. The network configuration analysis system of claim 1.

[0081] (Appendix 9) The computer Receives radio waves, Extracting signal features of multiple signals contained in the received radio waves, classifying signals of the plurality of signal feature amounts into either a forward link group or a return link group by performing cluster analysis on the plurality of signal feature amounts; Estimating a communication pair of communication via a relay, which is a combination between a signal included in the forward link group and a signal included in the return link group; Network configuration analysis methods.

[0082] (Appendix 10) A process of receiving radio waves; A process of extracting signal features of a plurality of signals contained in the received radio waves; A process of classifying signals of the plurality of signal feature amounts into either a forward link group or a return link group by performing cluster analysis on the plurality of signal feature amounts; a process of estimating a communication pair of a communication via a relay, which is a combination between a signal included in the forward link group and a signal included in the return link group; A network configuration analysis program that causes a computer to execute the following.

[0083] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Notes 9 and 10 in the same dependency relationship as Supplementary Notes 2 to 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods. [Explanation of symbols]

[0084] 1. Network configuration analysis device 2. Network configuration analysis equipment 3. Network Configuration Analysis Device 4. Network Configuration Analysis System 11 Receiving unit 12 Signal feature extraction unit 13 Cluster Analysis Department 14 Combinatorial Optimization Department 15 Feature accumulation unit 16 Analysis Department 17 Output section 37 Visualization section 41 Radio monitoring department 300 Computers 301 CPU 302 RAM 303 ROM 304 IF 305 HDD 306 Control Program

Claims

1. a receiving unit that receives radio waves; a signal feature extraction unit that extracts signal feature quantities of a plurality of signals included in the received radio wave; a cluster analysis unit that performs cluster analysis on the plurality of signal feature amounts to classify the signals of the plurality of signal feature amounts into a forward link group and a return link group; a combination optimization unit that estimates a communication pair of a communication via a relay, which is a combination between a signal included in the forward link group and a signal included in the return link group; A network configuration analysis system comprising:

2. the signal features include a bandwidth and a received power value; The cluster analysis unit classifying the signals of the plurality of signal feature quantities into one or more classes according to bandwidth; classifying a plurality of signals belonging to each of one or more classes classified according to bandwidth into a forward link group and a return link group according to received power; The network configuration analysis system according to claim 1 .

3. The cluster analysis unit classifying a plurality of signals belonging to each of one or more classes classified according to bandwidth into a return link group and a forward link group having higher received power than the return link group; The network configuration analysis system according to claim 2 .

4. The cluster analysis unit classifying the signals of the plurality of signal feature quantities into one or more classes according to bandwidth using any one of x-means and VBGMM (Variational Bayesian Gaussian Mixture); classifying a plurality of signals belonging to each of one or more classes classified according to bandwidth into a forward link group and a return link group according to received power using a k-means method; The network configuration analysis system according to claim 2 .

5. the combination optimization unit estimates the communication pairs such that a maximum value of a power difference between signals to be combined between the signals included in the forward link group and the signals included in the return link group is minimized. The network configuration analysis system according to claim 2 .

6. the signal features include a bandwidth and a received power value; the combination optimization unit estimates the communication pairs such that a maximum value of a power difference between signals to be combined between the signals included in the forward link group and the signals included in the return link group is minimized. The network configuration analysis system according to claim 1 .

7. the signal features include a bandwidth and a received power value; Further comprising a visualization unit, the visualization unit displays, on a coordinate system in which a first coordinate axis represents a bandwidth and a second coordinate axis orthogonal to the first coordinate axis represents a received power, a plurality of plots representing signals of the plurality of signal feature amounts, and frames surrounding the plurality of plots representing whether the signals of the plurality of signal feature amounts belong to the forward link group or the return link group. The network configuration analysis system according to claim 1 .

8. the signal features include a bandwidth and a received power value; Further comprising a visualization unit, The visualization unit a plot representing the frequency spectrum of the plurality of signals and a line segment connecting the two signals of the estimated communication pair are displayed on a coordinate system in which a first coordinate axis represents a center frequency and a second coordinate axis perpendicular to the first coordinate axis represents a received power; The network configuration analysis system according to claim 1 .

9. The computer Receives radio waves, Extracting signal features of multiple signals contained in the received radio waves, classifying signals of the plurality of signal feature amounts into either a forward link group or a return link group by performing cluster analysis on the plurality of signal feature amounts; Estimating a communication pair of communication via a relay, which is a combination between a signal included in the forward link group and a signal included in the return link group; Network configuration analysis methods.

10. A process of receiving radio waves; A process of extracting signal features of a plurality of signals contained in the received radio waves; A process of classifying signals of the plurality of signal feature amounts into either a forward link group or a return link group by performing cluster analysis on the plurality of signal feature amounts; a process of estimating a communication pair of a communication via a relay, which is a combination between a signal included in the forward link group and a signal included in the return link group; A network configuration analysis program that causes a computer to execute the following.

Images