JP2019080143A - Wireless environment condition prediction system, wireless environment condition prediction method, and program - Google Patents

Abstract

To realize a wireless environment condition prediction system for predicting a wireless environment condition with high accuracy even in a complex wireless environment changing condition.SOLUTION: In a wireless environment condition prediction system 1000, since prediction processing (inference processing) can be performed on the basis of data acquired at a plurality of points (points corresponding to positions where wireless devices A1 to A3 are installed), it is possible to predict the wireless environment condition with high accuracy even in a complex wireless environment changing condition caused by effects of shadowing, multipath, interference, reflected waves, etc. in a narrow space, in an environment where radio waves fly.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a wireless environment situation prediction technique using a plurality of information elements.

  For example, a system has been developed for efficiently grasping and controlling an operation status of a factory, managing work, and the like by using technologies related to Machine-to-Machine (M2M) and Internet of Things (IoT). In such a system, for example, equipment such as a sensor is attached to a robot, a manufacturing apparatus, a tool or the like in order to improve the productivity in the factory, and the operation status of the factory is grasped based on data acquired by the equipment. And control of each device / equipment and management of work in the factory.

  In the above-mentioned system, in order to realize correspondence to a moving apparatus and simplification of wiring, radio-ization of an apparatus used for the above-mentioned system is expected. On the other hand, in a narrow space such as a factory, there is a problem that wireless communication is destabilized because the wireless environment changes momentarily from moment to moment due to interference or reflection of radio waves or movement of equipment etc.

  In order to realize stable wireless communication in such an environment, it is necessary to appropriately control the wireless device in accordance with the ever-changing wireless environment. In order to do so, a technique is required to accurately predict changes in propagation conditions and radio resource utilization conditions.

  For example, Non-Patent Document 1 discloses a technique for predicting the busy / idle state of a wireless channel using an autoregressive model. In the technique of Non-Patent Document 1, an autoregressive model is learned by using the busy / idle state of a radio channel in a predetermined period in the past as learning data, and the future radio channel state is accurately calculated using the learned autoregression model. It can be predicted. According to the technique of Non-Patent Document 1, for example, in an anechoic chamber in which there is no reflected wave of a wireless signal, it is possible to predict future wireless channel conditions with high accuracy.

Y. Hou, J. Webber, K. Yano, and T. Kumagai, “Channel busy / idle duration prediction using auto-regressive predictor for WLAN system,” Proceedings of the 2017 Annual Conference of the Institute of Electronics, Information and Communication Engineers Collection 1, p.483, B-5-147, March 2017.

  However, since the technique of Non-Patent Document 1 has one measurement point of the state of the wireless channel, for example, in a narrow space where there are many reflected waves of the wireless signal, it is possible to predict the future wireless channel state with high accuracy. Have difficulty. In a narrow space where there are many reflected waves of the wireless signal, the movement of objects in the space etc. causes the wireless environment to change in a complex manner. In such a complex radio environment changing situation, as in the technique of Non-Patent Document 1, in a system in which the measurement point of the state of the radio channel is one point, sufficient learning data (radio channel for a predetermined period in the past) It is difficult to acquire the learning data indicating the busy / idle state of the <RTIgt; I </ RTI> and as a result, it is difficult to acquire a highly accurate learned autoregressive model. Therefore, it is difficult to predict future radio channel conditions with high accuracy in a complex radio environment changing situation.

  Therefore, in view of the above problems, it is an object of the present invention to realize a wireless environment situation prediction system that predicts a wireless environment situation with high accuracy even in a situation where the wireless environment changes in a complex manner.

  In order to solve the above problems, the first invention relates to first to Nth wireless communication devices each of which is N (N: natural number, N) 2) wireless communication devices installed at predetermined positions in a predetermined space. A wireless environment situation prediction system including a communication device and a server.

  Each of the first to N-th wireless communication apparatuses includes a transmitter, a receiver, a channel availability monitoring unit, and a first interface unit of a channel state data acquisition unit.

  The server includes a second interface unit and a prediction unit.

  The transmission unit generates a wireless signal by performing transmission processing on data.

  The receiving unit performs reception processing on the wireless signal to acquire data carried by the wireless signal.

  The channel use status observation unit controls at least one of the transmission unit and the reception unit to observe the use status of the channel used for the communication of the wireless signal.

  The channel state data acquisition unit is based on the signal acquired by at least one of the transmission unit, the reception unit, and the channel usage state observation unit, and the propagation state of the point where the wireless communication device is installed in the first period. And / or data indicating radio resource utilization status is acquired as channel state data.

  The first interface unit is an interface for transmitting channel state data acquired by the channel state data acquisition unit to the server.

  The second interface unit is an interface for receiving channel state data from the first to Nth wireless communication devices.

  The prediction unit executes prediction processing for predicting future data of a point where the first to N-th wireless communication devices are installed, based on two or more channel state data received by the second interface unit.

In this wireless environment situation prediction system, it is possible to execute prediction processing (inference processing) based on data acquired at a plurality of points (points corresponding to positions where the first to Nth wireless communication devices are installed). Therefore, in an environment where radio waves fly in a narrow space, it is possible to predict the wireless environment situation with high accuracy even in a situation where the wireless environment changes complexly due to the effects of shadowing, multipath, interference, reflected waves, etc. .
Note that the notation "first to Nth wireless communication devices" means the total N of the first wireless communication device, the second wireless communication device, ..., the kth wireless communication device, ..., the Nth wireless communication device. It is a notation representing a number of wireless communication devices.

  A second invention is the first invention, wherein the first period is a period from sample time t-p + 1 (p: natural number) to sample time t.

The data acquired in the sample time i in channel state data acquisition unit and _{X i,} the k-th wireless communication device (k: natural number, 1 ≦ k ≦ N) of data obtained in the first period in _{Data_Ak (X} t- _p + 1: If _{X t)} to the prediction unit, data _{Data_A1} an N data _{(X t-p + 1:} X t) ~ data _{Data_AN (X t-p + 1} : two or more data from the _{X t)} The prediction process is performed using this.

  In this wireless environment situation prediction system, it is possible to execute prediction processing (inference processing) based on data acquired at a plurality of points (points corresponding to positions where the first to Nth wireless communication devices are installed). Therefore, in an environment where radio waves fly in a narrow space, it is possible to predict the wireless environment situation with high accuracy even in a situation where the wireless environment changes complexly due to the effects of shadowing, multipath, interference, reflected waves, etc. .

  The “sample time” refers to, for example, a time at which data is sampled in discrete time. The sample time is determined by the frequency (clock frequency) of a clock signal that samples data.

  A third aspect of the invention is the first or second aspect of the invention, wherein the data indicating the propagation status is (1) received power, (2) propagation path value, (3) delay profile, (4) data on delay dispersion Data including at least one of

  Thus, in the wireless environment situation prediction system, at least one of (1) received power, (2) propagation path value, (3) delay profile, and (4) delay dispersion data as data indicating the propagation situation Processing using the included data can be performed.

  A fourth invention is the invention according to any one of the first to third inventions, wherein the data indicating the radio resource utilization status is (1) radio resource utilization rate, (2) number of retransmissions, (3) frame error rate, (4) It is data including at least one of data relating to a used transmission rate.

Thus, in the wireless environment status prediction system, data indicating the wireless resource usage status is (1) the wireless resource usage rate, (2) the number of retransmissions, (3) the frame error rate, and (4) the data regarding the used transmission rate. Processing using data including at least one of them can be performed.
A fifth invention includes first to Nth wireless communication devices that are N (N: natural number, N ≧ 2) wireless communication devices installed at predetermined positions in a predetermined space, and a server. It is a wireless environment condition prediction method used for a wireless environment condition prediction system.

  Each of the first to N-th wireless communication apparatuses includes a transmitting unit, a receiving unit, and a channel use status observing unit.

The transmission unit generates a wireless signal by performing transmission processing on data.
The receiving unit performs reception processing on the wireless signal to acquire data carried by the wireless signal.

  The channel use status observation unit controls at least one of the transmission unit and the reception unit to observe the use status of the channel used for the communication of the wireless signal.

  The wireless environment situation prediction method comprises a channel state data acquisition step, a data transmission step, a data reception step, and a prediction step.

  The channel state data acquisition step is performed in the first period based on a signal acquired by at least one of the transmission unit, the reception unit, and the channel use status observation unit in each of the first to Nth wireless communication devices. Data of at least one of data indicating the propagation status of the point where the wireless communication apparatus is installed and data indicating the wireless resource utilization status is acquired as channel state data.

  The data transmission step transmits channel state data acquired by the channel state data acquisition step to the server in each of the first to Nth wireless communication devices.

  In the data receiving step, the server receives channel state data from the first to Nth wireless communication devices.

  The prediction step executes, in the server, prediction processing for predicting future data of a point where the first to N-th wireless communication devices are installed, based on the two or more channel state data received in the data reception step. .

  As a result, it is possible to realize a wireless environment situation prediction method that has the same effect as that of the first invention.

  A sixth invention is a program for causing a computer to execute the wireless environment situation prediction method of the fifth invention.

  As a result, a program for causing a computer to execute a wireless environment situation prediction method having the same effect as that of the first invention can be realized.

  According to the present invention, it is possible to realize a wireless environment situation forecasting system, a wireless environment situation forecasting method, and a program for predicting a wireless environment situation with high accuracy even in a situation where the wireless environment changes complicatedly.

FIG. 1 is a schematic configuration diagram of a wireless environment situation prediction system 1000 according to a first embodiment. BRIEF DESCRIPTION OF THE DRAWINGS The schematic block diagram of radio | wireless apparatus A1 which concerns on 1st Embodiment. The schematic block diagram of server Svr which concerns on 1st Embodiment. The figure for demonstrating operation | movement of the learning mode of the radio | wireless environment situation prediction system 1000 which concerns on 1st Embodiment. The figure for demonstrating the operation | movement of the inference mode of the radio | wireless environment situation prediction system 1000 which concerns on 1st Embodiment. The figure which shows CPU bus composition.

First Embodiment
The first embodiment will be described below with reference to the drawings.

<1.1: Configuration of wireless environment situation prediction system>
FIG. 1 is a schematic configuration diagram of a wireless environment situation prediction system 1000 according to the first embodiment. FIG. 1 is a view schematically showing a case where the wireless environment situation prediction system 1000 is installed in a space SP1 surrounded by a wall Wall1 (a view from above).

  FIG. 2 is a schematic configuration diagram of the wireless device A1 according to the first embodiment.

  FIG. 3 is a schematic configuration diagram of the server Svr according to the first embodiment.

  As shown in FIG. 1, the wireless environment situation prediction system 1000 includes wireless devices A1 to A3 and a server Svr. Although FIG. 1 shows the case where there are three wireless devices, the present invention is not limited to this. The number of wireless devices may be two or more, and may be another number. Below, for convenience of explanation, as shown in FIG. 1, the case where the number of wireless devices is three will be described. The wireless devices A1 to A3 are respectively connected to the server Svr by a wired or wireless network, and the wireless devices A1 to A3 and the server Svr can communicate with each other.

(1.1.1: Configuration of wireless device)
Since the wireless devices A1 to A3 have the same configuration, the configuration of the wireless device A1 will be described below.

  As illustrated in FIG. 2, the wireless device A1 includes, as illustrated in FIG. 2, a transmitter 1, a receiver 2, a channel usage status observation unit 3, a channel state data acquisition unit 4, a first interface unit 5, and a prediction data processing unit 6. , A transmitting antenna Ant_tx, a receiving antenna Ant_rx, a transmitting oscillator Ocr1, and a receiving oscillator Ocr2.

  As shown in FIG. 2, the transmission unit 1 includes an ECC unit 11, an interleaving unit 12, a radio frame generation unit 13, a transmission RF unit 14, and an access control unit 15.

  The ECC unit 11 receives the data Din, and executes an error correction coding process on the data Din. Then, the ECC unit 11 outputs the data after the error correction coding process to the interleave unit 2 as data Dt1.

  The interleaving unit 12 receives the data Dt1 output from the ECC unit 11 and performs interleaving processing on the data Dt1. Then, the interleaving unit 12 outputs the data after interleaving processing to the radio frame generation unit 13 as data Dt2.

  The radio frame generation unit 13 receives the data Dt 2 output from the interleaving unit 12 and the control signal CTL 1 output from the access control unit 15. The radio frame generation unit 13 performs baseband processing (baseband processing of OFDM) on the data Dt2 based on the control signal CTL1. That is, the wireless frame generation unit 13 obtains a baseband OFDM signal by performing serial / parallel conversion, mapping processing, inverse FFT conversion, guard interval (GI) addition processing, and D / A conversion on data Dt 2. Do. Then, the radio frame generation unit 13 outputs the acquired baseband OFDM signal as the signal Dt3 to the transmission side RF unit.

  The transmitting side RF unit 14 mixes the baseband OFDM signal Dt3 output from the radio frame generation unit 13, the control signal CTL2 output from the access control unit 15, and the reference frequency signal fr_tx output from the transmission oscillator Ocr1. input. The transmission side RF unit 14 performs orthogonal modulation processing, up conversion processing, and power amplification processing on the baseband OFDM signal Dt3 based on the control signal CTL2 using the reference frequency signal fr_tx output from the transmission oscillator Ocr1. By carrying out, a carrier band OFDM signal is acquired. Then, the transmission side RF unit 14 outputs the acquired carrier band OFDM signal to the transmission antenna Ant_tx.

  Further, the transmitting side RF unit 14 is connected to the channel utilization condition observation unit 3 and executes carrier sense or channel sense according to a command from the channel utilization condition observation unit 3 and outputs a signal indicating the execution result. Output to the channel usage status observation unit 3.

  The transmission oscillator Ocr1 generates a reference frequency signal fr_tx, and outputs the generated reference frequency signal fr_tx to the transmission side RF unit 14.

  The access control unit 15 generates a control signal CTL1 for controlling the radio frame generation unit 13, and outputs the control signal CTL1 to the radio frame generation unit 13 at a predetermined timing. Further, the access control unit 15 generates a control signal CTL2 for controlling the transmission side RF unit 14, and outputs the control signal CTL2 to the transmission side RF unit 14 at a predetermined timing. Further, the access control unit 15 receives the control signal CTL3 from the prediction data processing unit 6, and generates control signals CTL1 and CTL12 based on the control signal CTL3.

  The transmitting antenna Ant_tx is an antenna for transmitting an RF signal (carrier band OFDM signal) to the outside. The transmitting antenna Ant_tx receives the carrier band OFDM signal from the transmitting side RF unit 14 and transmits the carrier band OFDM signal to the outside.

  The receiving antenna Ant_rx is an antenna for receiving an RF signal (carrier band OFDM signal) from the outside. The reception antenna Ant_rx outputs the received RF signal (carrier band OFDM signal) to the reception side RF unit 21 as a signal Dr1. Note that the receiving antenna Ant_rx may be shared with the transmitting antenna Ant_tx. That is, in the wireless device A1, instead of providing the transmitting antenna Ant_tx and the receiving antenna Ant_rx, one transmitting and receiving antenna may be provided.

  As shown in FIG. 2, the receiving unit 2 includes the receiving side RF unit 21, the receiving oscillator Ocr 2, the synchronization processing unit 22, the baseband processing unit 23, the deinterleaving unit 24, and the ECC unit 25. Prepare.

  The reception side RF unit 21 receives the carrier band OFDM signal Dr1 from the reception antenna Ant_rx and the reference frequency signal fr_rx output from the reception oscillator Ocr2. The reception side RF unit 21 performs amplification processing, down conversion processing based on the reference frequency signal fr_rx, automatic frequency control processing (AFC processing), orthogonal demodulation processing based on the reference frequency signal fr_rx, and carrier demodulation for the carrier band OFDM signal Dr1. By executing D conversion processing, a demodulation carrier band OFDM signal is acquired as a signal Dr2. Then, the reception side RF unit 21 outputs the demodulation carrier band OFDM signal Dr2 to the synchronization processing unit 22 and the baseband processing unit 23.

  Further, the receiving side RF unit 21 is connected to the channel availability monitoring unit 3 and executes carrier sensing or channel sensing according to a command from the channel availability monitoring unit 3 and outputs a signal indicating the execution result. Output to the channel usage status observation unit 3.

  The synchronization processing unit 22 receives the demodulation carrier band OFDM signal Dr2 output from the reception side RF unit 21, and executes synchronization processing based on the input demodulation carrier band OFDM signal Dr2. The synchronization processing unit 22 acquires synchronization timing signal Sig_Sync used for symbol timing synchronization or the like for detecting the beginning of the OFDM symbol by synchronization processing. Then, the synchronization processing unit 22 outputs the acquired synchronization timing signal Sig_Sync to the baseband processing unit 23. The synchronization processing unit 22 detects the frequency offset of the reception oscillator Ocr2 from the signal (preamble signal) of the preamble portion of the demodulation carrier band OFDM signal Dr2 and controls the oscillation frequency of the reception oscillator Ocr2 ( The oscillation frequency control signal fs_ctl is generated, and the generated oscillation frequency control signal fs_ctl is output to the reception oscillator Ocr2.

  Further, the synchronization processing unit 22 acquires data such as propagation path values and delay profiles by synchronization processing. Then, the synchronization processing unit 22 outputs data such as the acquired channel value and delay profile to the channel state data acquisition unit 4 as data Data2.

  The reception oscillator Ocr2 receives the oscillation frequency control signal fs_ctl output from the synchronization processing unit 22, and based on the oscillation frequency control signal fs_ctl, a reference frequency that is a clock signal serving as a reference for the processing operation of the reception RF unit 21. Generate signal fr_rx. Then, the reception oscillator Ocr2 outputs the generated reference frequency signal fr_rx to the reception side RF unit 21.

  The baseband processing unit 23 receives the demodulation carrier band OFDM signal Dr2 output from the reception side RF unit 21 and the synchronization timing signal Sig_Sync output from the synchronization processing unit 22. The baseband processing unit 23 acquires a demodulated baseband OFDM signal as the signal Dr3 by performing guard interval (GI) removal processing, FFT conversion, demapping processing, and parallel / serial conversion based on the synchronization timing signal Sig_Sync. . Then, the baseband processing unit 23 outputs the acquired demodulated baseband OFDM signal Dr3 to the deinterleave unit 24.

  The deinterleave unit 24 receives the demodulated baseband OFDM signal Dr3 output from the baseband processing unit 23. The de-interleaving unit 24 performs de-interleaving processing on the demodulated baseband OFDM signal Dr2 and acquires the signal (data) after the de-interleaving processing as a signal (data) Dr4. Then, the deinterleave unit 24 outputs the acquired data Dr4 to the ECC unit 25.

  The ECC unit 25 receives the data Dr4 output from the deinterleave unit 24 and performs an error correction process on the data Dr4. The ECC unit 25 outputs the data after the error correction process as data Dout. Further, the ECC unit 25 outputs data indicating the result of the error correction process to the channel state data acquisition unit 4 as data Rst_ECC.

  The channel usage status observation unit 3 performs carrier sense and / or, in order to monitor the usage status (such as the availability status of each wireless channel) of each frequency band (one or more radio channels in each frequency band). A command signal for performing channel sensing is generated. Then, the channel usage status observation unit 3 performs carrier sense and / or channel sense by outputting the generated command signal to the transmission side RF unit 14 and / or the reception side RF unit 21.

  Also, the channel usage status observation unit 3 outputs a command signal for acquiring the reception power to the transmission RF unit 14 and / or the reception RF unit 21 to acquire the reception power of the wireless device A1. Also, the radio resource utilization ratio (COR: channel occupancy ratio) is acquired by observing the value of the acquired reception power for a predetermined period. Then, the channel utilization status observation unit 3 outputs data including the acquired received power and the radio resource utilization rate COR to the channel state data acquisition unit 4 as data Data1.

The channel state data acquisition unit 4 outputs the data Data 1 output from the channel usage status observation unit 3, the data Data 2 output from the synchronization processing unit 22, the data Rst_ECC output from the ECC unit 25, and the output from the ECC unit 25. Data Dout to be input. The channel state data acquisition unit 4 acquires data for prediction processing X _t based on the input data. Further, the channel state data acquisition unit 4 acquires p (p: natural number) data for prediction processing acquired during a period (a period including p sample times) from time t−p + 1 to time t. obtained p number of prediction processing data data prediction processing data including Data_A1: as _{(X t-p + 1 X} t), if the inference mode is a mode for executing the first output to the interface unit 5 (prediction processing ).

The channel state data acquisition unit 4 acquires the teacher data R_A1 (X _{t + 1} ) from the data Data 1 and / or the data Data 2 in the learning mode, which is a mode in which learning is performed, to the first interface unit 5. Output.

The first interface unit 5, if the inference mode, the prediction processing data output from the channel state data acquisition unit _{4 Data_A1 (X t-p +} 1: X t) to enter. The first interface unit 5, the prediction process data Data_A1: a _{(X t-p + 1 X} t), and outputs to the server Svr via the network.

When the first interface unit 5 receives the prediction data Est_A1 (X _{t + 1} ) from the server Svr via the network, the first interface unit 5 outputs the prediction data Est_A1 (X _{t + 1} ) to the prediction data processing unit 6.

The first interface unit 5, if the learning mode, enter the teaching data R_A1 _{(X t + 1)} which is output from the channel state data acquisition unit 4, the teacher data R_A1 the _{(X t + 1)} via the network server Svr Output to

The prediction data processing unit 6 receives the prediction data Est_A1 (X _{t + 1} ) output from the first interface unit 5, and generates a control signal CTL3 based on the prediction data Est_A1 (X _{t + 1} ). Then, the predicted data processing unit 6 outputs the generated control signal CTL3 to the access control unit 15.

(1.1.2: Server configuration)
As shown in FIG. 3, the server Svr includes a second interface unit Sv1 and a prediction unit Sv2.

  The second interface unit Sv1 is a communication interface for communicating with each wireless device (wireless devices A1 to A3) via a network.

The second interface unit Sv1 a wireless device Ak (k: natural number, 1 ≦ k ≦ N) prediction processing data received from _{Data_Ak (X t-p + 1} : X t) and outputs to the prediction unit Sv2.

The second interface unit Sv1 the transmission type the predictive data Est_Ak the output from the prediction unit Sv2 wireless device Ak _{(X t + 1),} via a network, the wireless device Ak, prediction data Est_Ak the _{(X t + 1)} Do.

In the learning mode, the second interface unit Sv1 outputs the training data R_A1 (X _{t + 1} ) received from the wireless device Ak (k: natural number, 1 ≦ k ≦ N) to the prediction unit Sv2.

Prediction unit Svr2 the prediction processing data Data_Ak output from the second interface unit _{Sv1 (X t-p + 1} : X t) to enter.

Prediction unit Svr2 the case of the learning mode, two or more prediction processing data Data_Ak: and _{(X t-p + 1 X} t), teacher data R_A1 _{(X t + 1)} and using, learns, optimization model I do.

Prediction unit Svr2 the case of inference mode, two or more prediction processing data _{Data_Ak (X t-p + 1} : X t) was used to perform the prediction process, the time t + 1 of the predicted data Est_Ak wireless devices Ak (X _{Get t + 1} ). Then, the prediction unit Svr2 outputs the acquired prediction data Est_Ak (X _{t + 1} ) of the acquired wireless device Ak to the second interface unit Sv1.

<1.2: Operation of wireless environment situation prediction system>
The operation of the wireless environment situation prediction system 1000 configured as described above will be described below.

  As shown in FIG. 1, the wireless devices A1 to A3 are respectively installed at fixed positions in a space SP1 surrounded by the wall Wall1. The wireless device A1 is installed at the position Pos (A1), the wireless device A2 is installed at the position Pos (A2), and the wireless device A3 is installed at the position Pos (A3). For example, in the case where the movable wireless device B1 (movable device) is present at the position shown in FIG. 1 and in communication with the wireless devices A1 to A3, the transport vehicle v1 has the arrow Dir1 of FIG. The operation of the wireless environment situation prediction system 1000 will be described by taking the case of moving in the direction as an example. As shown in FIG. 1, the positions of the times t1, t2 and t3 of the transport vehicle v1 are set as positions Pos_v1 (t1), Pos_v1 (t2) and Pos_v1 (t3), respectively.

  4 is a diagram (a diagram of a learning mode) schematically showing the inside of the space SP1 as in FIG. 1, and (1) a graph G1 showing a relationship between reception power and time observed by the wireless device A1, 2) A graph G2 showing the relationship between received power and time observed by the wireless device A2, and (3) a graph G3 showing the relationship between received power and time observed by the wireless device A3. .

  FIG. 5 is a diagram schematically showing the inside of the space SP1 as in FIG. 1 (diagram of the inference mode), and (1) a graph G11 showing the relationship between received power and time observed by the wireless device A1, 2) A graph G12 showing the relationship between received power and time observed by the wireless device A2, and (3) A graph G13 showing the relationship between received power and time observed by the wireless device A3. .

  For convenience of explanation, the case of performing prediction processing on received power in the wireless environment situation prediction system will be described.

  In the following, the operation of the wireless environment situation prediction system will be described by being divided into (1) learning mode and (2) inference mode.

(1.2.1: Learning mode)
In the wireless device A1, the channel usage monitoring unit 3 performs carrier sense or channel sense, and acquires data of received power in a period from time t0 to t21. The time t0 corresponds to the sample time t-p + 1, and the time t21 corresponds to the sample time t (the current time). That is, the wireless device A1, the period until time T0～t21, data _{X t-p} + 1 _{~X t} of p reception power is obtained. The data X _{t-p + 1} ~X _t of p reception power acquired by the wireless device A1 can be regarded as a data of the received power of the position Pos wireless device A1 is installed (A1).

Channel state data acquisition unit 4 of the wireless device A1 includes the acquired p reception power of data, data Data_A1: obtaining a _{(X t-p + 1 X} t). The acquired data _{Data_A1 (X t-p + 1} : X t) via the first interface unit 5 of the wireless device A1, is transmitted to the server Svr.

Furthermore, the channel state data acquisition unit 4 of the wireless device A1 receives training data R_A1 (X _{t + 1} ) on the data of the reception power acquired at the sample time t + 1 (the time (for example, time t3 included in the period of time t21 to _t4 ) Get as. Then, the wireless device A1 transmits the acquired teacher data R_A1 (X _{t + 1} ) to the server Svr via the first interface unit 5.

In the wireless device A2, the channel usage monitoring unit 3 performs carrier sense or channel sense, and acquires data of received power in a period from time t0 to t21. In the wireless device A2, the period until time T0～t21, data _{X t-p} + 1 _{~X t} of p reception power is obtained. The data X _{t-p + 1} ~X _t of p reception power acquired by the wireless device A2 can be regarded as a data of the received power of the position Pos wireless device A2 is installed (A2).

Channel state data acquisition unit 4 of the wireless device A2 is the acquired p reception power of data, data Data_A2: obtaining a _{(X t-p + 1 X} t). The acquired data _{Data_A2 (X t-p + 1} : X t) via the first interface unit 5 of the wireless device A2, is sent to the server Svr.

Furthermore, the channel state data acquisition unit 4 of the wireless device A2 receives training data R_A2 (X _{t + 1} ) of data of the reception power acquired at the sample time t + 1 (the time (for example, time t3 included in the period of time t21 to _t4 )). Get as. Then, the wireless device A2 transmits the acquired teacher data R_A2 (X _{t + 1} ) to the server Svr via the first interface unit 5.

In the wireless device A3, the channel usage monitoring unit 3 performs carrier sense or channel sense, and acquires data of received power in a period from time t0 to t21. In the wireless device A3, in the period up to time T0～t21, data _{X t-p} + 1 _{~X t} of p reception power is obtained. The data X _{t-p + 1} ~X _t of p reception power acquired by the wireless device A3 can be considered as a data of the received power of the position Pos wireless device A3 is installed (A3).

Channel state data acquisition unit 4 of the wireless device A3 is the acquired p reception power of data, data Data_A3: obtaining a _{(X t-p + 1 X} t). The acquired data _{Data_A3 (X t-p + 1} : X t) via the first interface unit 5 of the wireless device A3, are transmitted to the server Svr.

Furthermore, the channel state data acquisition unit 4 of the wireless device A3 receives training data R_A3 (X _{t + 1} ) of data of the received power acquired at the sample time t + 1 (the time (for example, time t3 included in the period of time t21 to _t4 )). Get as. Then, the wireless device A3 transmits the acquired teacher data R_A3 (X _{t + 1} ) to the server Svr via the first interface unit 5.

Server Svr is the second interface unit Sv1, data is transmitted from the wireless device _{A1~A3 Data_A1 (X t-p +} 1: X t), Data_A2 (X t-p + 1: X t), Data_A3 (X t-p + 1: X _t), and the teacher data _{R_A1 (X t + 1),} R_A2 (X t + 1), to obtain the R_A3 _{(X t + 1).}

Ｎ＝３
なお、上記数式において、Ｘ_ｔ＋１は、無線装置Ａ１のサンプル時刻ｔ＋１において取得されるデータ（例えば、受信電力）である。 Then, the prediction unit Sv2 of the server Svr performs learning for acquiring a learned model that performs prediction processing (inference processing) on the wireless device A1. Specifically, the prediction unit Sv2 uses the following data as input data and teacher data.
Input data:
_{Data_A1 (X t-p + 1} : X t)
_{Data_A2 (X t-p + 1} : X t)
_{Data_A3 (X t-p + 1} : X t)
Teacher data:
R_A1 (X _{t + 1} )
_{Maximum; | (θ X t):} : X t), ···, Data_AN (X t-p + 1 Data_A1 (X t-p + 1 X t + 1) and, the prediction unit Sv2 is, the parameters and θ, the conditional probability _P The parameter θ _opt to be set is determined. That is, the prediction unit Sv2 acquires the optimum parameter θ _opt by executing a process corresponding to the following formula.

N = 3
In the above equation, X _{t + 1} is data (for example, received power) acquired at sample time t + 1 of the wireless device A1.

Further, Data_Ak (Xt _{-p + 1} : Xt) is data (for example, received power) acquired at sample time t-P _{+ 1 to t} of the wireless device A1. _{That, Data_Ak (X t-p +} 1: X t) is data including the p number of data (e.g., vector data) is. Incidentally, X _i, here is the data of the received power (one-dimensional data), or may be vector data including a plurality of data. X _i, for example, (1) the received power, (2) channel value, (3) the delay profile, (4) a delay dispersion, (5) COR, (6) the number of retransmissions, (7) a frame error rate, ( 8) It may be vector data in which two or more data of the used transmission rate are factored.

Then, by setting the optimum parameter θ _opt acquired as described above as a learning model, a learned model that performs prediction processing (inference processing) for the wireless device A1 is acquired.

The model to be optimized (the model for performing prediction processing (inference processing) for the wireless device A1) is (1) a neural network (for example, DNN (Deep Neural Network), CNN (Convolutional Neural Network), It may be a model according to RNN (Recurrent Neural Network), or (2) it may be a non-linear dynamic model based on multiple inputs. When performing processing using a non-linear dynamic model on the premise of multiple inputs, for example, the technology disclosed in the following document may be used.
Y. Matsubara and Y. Sakurai, “Regime shifts in streams: real-time forecasting of co-evolving time sequences,” Proc. Of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Aug. 2016.
That is, as disclosed in the above document, a nonlinear state space model in which a plurality of input variables, a plurality of output variables, and a plurality of state variables are set is set, and parameters for optimizing the set state space model are acquired By doing this, model optimization processing (model learning) may be performed.

The parameter θ and the optimum parameter θ _opt are scalars, vectors, or tensors.

Ｎ＝３
なお、上記数式において、Ｘ_ｔ＋１は、無線装置Ａ２のサンプル時刻ｔ＋１において取得されるデータ（例えば、受信電力）である。 Also, the prediction unit Sv2 of the server Svr performs learning for acquiring a learned model that performs prediction processing (inference processing) for the wireless device A2. Specifically, the prediction unit Sv2 uses the following data as input data and teacher data.
Input data:
_{Data_A1 (X t-p + 1} : X t)
_{Data_A2 (X t-p + 1} : X t)
_{Data_A3 (X t-p + 1} : X t)
Teacher data:
R_A2 (X _{t + 1} )
_{Maximum; | (θ X t):} : X t), ···, Data_AN (X t-p + 1 Data_A1 (X t-p + 1 X t + 1) and, the prediction unit Sv2 is, the parameters and θ, the conditional probability _P The parameter θ _opt to be set is determined. That is, the prediction unit Sv2 acquires the optimum parameter θ _opt by executing a process corresponding to the following formula.

N = 3
In the above equation, X _{t + 1} is data (for example, received power) acquired at sample time t + 1 of the wireless device A2.

Then, by setting the optimum parameter θ _opt acquired as described above as a learning model, a learned model to be subjected to prediction processing (inference processing) for the wireless device A2 is acquired.

Ｎ＝３
なお、上記数式において、Ｘ_ｔ＋１は、無線装置Ａ３のサンプル時刻ｔ＋１において取得されるデータ（例えば、受信電力）である。 Also, the prediction unit Sv2 of the server Svr performs learning for acquiring a learned model that performs prediction processing (inference processing) on the wireless device A3. Specifically, the prediction unit Sv2 uses the following data as input data and teacher data.
Input data:
_{Data_A1 (X t-p + 1} : X t)
_{Data_A2 (X t-p + 1} : X t)
_{Data_A3 (X t-p + 1} : X t)
Teacher data:
R_A3 (X _{t + 1} )
_{Maximum; | (θ X t):} : X t), ···, Data_AN (X t-p + 1 Data_A1 (X t-p + 1 X t + 1) and, the prediction unit Sv2 is, the parameters and θ, the conditional probability _P The parameter θ _opt to be set is determined. That is, the prediction unit Sv2 acquires the optimum parameter θ _opt by executing a process corresponding to the following formula.

N = 3
In the above equation, X _{t + 1} is data (for example, received power) acquired at sample time t + 1 of the wireless device A3.

Then, by setting the optimum parameter θ _opt acquired as described above as a learning model, a learned model to be subjected to prediction processing (inference processing) for the wireless device A3 is acquired.

  As described above, in the wireless environment situation prediction system 1000, processing in the learning mode is performed.

(1.2.2: Inference mode)
Next, the operation of the wireless environment situation prediction system 1000 in the inference mode will be described with reference to FIG. Also in the inference mode, the transport vehicle v1 performs the same operation (movement) as that in the learning mode shown in FIG.

In the wireless device A1, the channel usage monitoring unit 3 performs carrier sense or channel sense, and acquires data of received power in a period from time t0 to t21. The time t0 corresponds to the sample time t-p + 1, and the time t21 corresponds to the sample time t (the current time). That is, the wireless device A1, the period until time T0～t21, data _{X t-p} + 1 _{~X t} of p reception power is obtained. The data X _{t-p + 1} ~X _t of p reception power acquired by the wireless device A1 can be regarded as a data of the received power of the position Pos wireless device A1 is installed (A1).

Channel state data acquisition unit 4 of the wireless device A1 includes the acquired p reception power of data, data Data_A1: obtaining a _{(X t-p + 1 X} t). The acquired data _{Data_A1 (X t-p + 1} : X t) via the first interface unit 5 of the wireless device A1, is transmitted to the server Svr.

In the wireless device A2, the channel usage monitoring unit 3 performs carrier sense or channel sense, and acquires data of received power in a period from time t0 to t21. In the wireless device A2, the period until time T0～t21, data _{X t-p} + 1 _{~X t} of p reception power is obtained. The data X _{t-p + 1} ~X _t of p reception power acquired by the wireless device A2 can be regarded as a data of the received power of the position Pos wireless device A2 is installed (A2).

Channel state data acquisition unit 4 of the wireless device A2 is the acquired p reception power of data, data Data_A2: obtaining a _{(X t-p + 1 X} t). The acquired data _{Data_A2 (X t-p + 1} : X t) via the first interface unit 5 of the wireless device A2, is sent to the server Svr.

In the wireless device A3, the channel usage monitoring unit 3 performs carrier sense or channel sense, and acquires data of received power in a period from time t0 to t21. In the wireless device A3, in the period up to time T0～t21, data _{X t-p} + 1 _{~X t} of p reception power is obtained. The data X _{t-p + 1} ~X _t of p reception power acquired by the wireless device A3 can be considered as a data of the received power of the position Pos wireless device A3 is installed (A3).

Channel state data acquisition unit 4 of the wireless device A3 is the acquired p reception power of data, data Data_A3: obtaining a _{(X t-p + 1 X} t). The acquired data _{Data_A3 (X t-p + 1} : X t) via the first interface unit 5 of the wireless device A3, are transmitted to the server Svr.

Server Svr is the second interface unit Sv1, data is transmitted from the wireless device _{A1~A3 Data_A1 (X t-p +} 1: X t), Data_A2 (X t-p + 1: X t), Data_A3 (X t-p + 1: X _t), and the teacher data _{R_A1 (X t + 1),} R_A2 (X t + 1), to obtain the R_A3 _{(X t + 1).}

The prediction unit Sv2 of the server Svr performs processing of acquiring prediction data Est_A1 (X _{t + 1} ) using a learned model that performs prediction processing (inference processing) on the wireless device A1.

Specifically, the prediction unit Sv2 sets the following data as input data to a learned model that performs prediction processing (inference processing) on the wireless device A1, and outputs an output from the learned model to the prediction data Est_A1 (X _{t + 1} Get as).
Input data:
_{Data_A1 (X t-p + 1} : X t)
_{Data_A2 (X t-p + 1} : X t)
_{Data_A3 (X t-p + 1} : X t)
The predicted data Est_A1 (X _{t + 1} ) acquired as described above is, for example, data of the period t21 to t4 of the graph G11 in the situation of FIG. 5. Since data approximating that in the learning mode shown in FIG. 4 is input to the prediction unit Sv2, prediction data Est_A1 (X _{t + 1} ) output from the prediction unit Sv2 (learned model) is teacher data R_A1 (X _{t + 1} ). The data approximate to That is, the predicted data Est_A1 (X _{t + 1} ) at the sample time t + 1 in the state shown in FIG. 5 is highly accurate.

And prediction data Est_A1 (Xt _{+ 1} ) acquired by the above is transmitted to radio equipment A1 via the 2nd interface part Sv1.

Then, the wireless device A1 receives the prediction data Est_A1 (X _{t + 1} ) via the first interface unit 5. Then, the prediction data processing unit 6 appropriately generates the control signal CTL3 based on the prediction data Est_A1 (X _{t + 1} ), and controls the transmission unit 1 of the wireless device A1 so that appropriate processing is performed.

Further, the prediction unit Sv2 of the server Svr performs processing of acquiring prediction data Est_A2 (X _{t + 1} ) using a learned model that performs prediction processing (inference processing) on the wireless device A2.

Specifically, the prediction unit Sv2 sets the following data as input data to a learned model that performs prediction processing (inference processing) for the wireless device A2, and outputs an output from the learned model as prediction data Est_A2 (X _{t + 1} Get as).
Input data:
_{Data_A1 (X t-p + 1} : X t)
_{Data_A2 (X t-p + 1} : X t)
_{Data_A3 (X t-p + 1} : X t)
The predicted data Est_A2 (X _{t + 1} ) acquired as described above is, for example, data of the period t21 to t4 of the graph G12 in the situation of FIG. 5. Since data approximate to that in the learning mode shown in FIG. 4 is input to the prediction unit Sv2, prediction data Est_A2 (X _{t + 1} ) output from the prediction unit Sv2 (learned model) is teacher data R_A1 (X _{t + 1} ). The data approximate to That is, the predicted data Est_A2 (X _{t + 1} ) at the sample time t + 1 in the state shown in FIG. 5 is highly accurate.

And prediction data Est_A2 (Xt _{+ 1} ) acquired by the above is transmitted to radio equipment A2 via the 2nd interface part Sv1.

Then, the wireless device A2 receives the prediction data Est_A2 (X _{t + 1} ) via the first interface unit 5. Then, the prediction data processing unit 6 appropriately generates the control signal CTL3 based on the prediction data Est_A2 (X _{t + 1} ), and controls the transmission unit 1 of the wireless device A2 so that appropriate processing is performed.

Further, the prediction unit Sv2 of the server Svr performs a process of acquiring prediction data Est_A3 (X _{t + 1} ) using a learned model that performs a prediction process (inference process) on the wireless device A3.

Specifically, the prediction unit Sv2 sets the following data as input data to a learned model that performs a prediction process (inference process) on the wireless device A3, and outputs an output from the learned model to a prediction data Est_A3 (X _{t + 1} Get as).
Input data:
_{Data_A1 (X t-p + 1} : X t)
_{Data_A2 (X t-p + 1} : X t)
_{Data_A3 (X t-p + 1} : X t)
The predicted data Est_A3 (X _{t + 1} ) acquired as described above is, for example, data of the period t21 to t4 of the graph G13 in the situation of FIG. 5. Since data approximate to that in the learning mode shown in FIG. 4 is input to the prediction unit Sv2, prediction data Est_A3 (X _{t + 1} ) output from the prediction unit Sv2 (learned model) is teacher data R_A1 (X _{t + 1} ) The data approximate to That is, the prediction data Est_A3 (X _{t + 1} ) at the sample time t + 1 in the state shown in FIG. 5 is highly accurate.

Then, the prediction data Est_A3 (X _{t + 1} ) acquired as described above is transmitted to the wireless device A3 via the second interface unit Sv1.

Then, the wireless device A3 receives the prediction data Est_A3 (X _{t + 1} ) through the first interface unit 5. Then, the prediction data processing unit 6 appropriately generates the control signal CTL3 based on the prediction data Est_A3 (X _{t + 1} ), and controls the transmission unit 1 of the wireless device A3 so that appropriate processing is performed.

  As described above, the wireless environment situation prediction system 1000 can execute prediction processing (inference processing) using a learned model that has been learned based on data acquired at a plurality of points, so in a narrow space. In an environment where radio waves fly, it is possible to predict the wireless environment situation with high accuracy even in a situation where the wireless environment changes complicatedly due to the effects of shadowing, multipath, interference, reflected waves and the like.

  Although the target of the prediction process has been described above as reception power, the present invention is not limited to this, and for example, data such as the following (data indicating propagation status and data indicating wireless resource utilization status) May be the target of the prediction process.

<< Data showing propagation status >>
(1) Received power (2) Propagation path value (3) Delay profile (4) Delay distribution << Data indicating radio resource usage status >>
(5) COR
(6) Number of times of retransmission (7) Frame error rate (8) Transmission rate used Note that (2) propagation path value and (3) data of delay profile are based on data Data 2 acquired by the synchronization processing unit 22. , And can be acquired by the channel state data acquisition unit 4.

  (4) The delay dispersion is calculated by the channel state data acquisition unit 4 from (2) propagation path values or (3) data of delay profiles.

  (5) The COR is acquired by monitoring the received power for a predetermined period (compared with a predetermined threshold) by the channel usage condition observation unit 3.

  (6) The number of retransmissions is acquired by executing ACK detection processing by the receiving unit 2 using the data Dout after processing by the ECC unit 25 and counting the number of retransmission processings executed when ACK can not be detected. Be done.

  (7) The frame error rate is acquired by the channel state data acquisition unit 4 examining data Rst_ECC indicating the result of the error correction process acquired by the ECC unit 25.

  (8) The transmission rate in use is acquired by the channel state data acquisition unit 4 using the data Dout processed by the ECC unit 25 to check the header information.

The channel state data acquisition unit 4 generates data X _i (scalar or vector) including the one or more data described above as Data X _i (scalar or vector), and Data_Ak (X _{t −p + 1} : X _t ) including p data X _i It may be transmitted to the server Svr via the first interface unit 5.

[Other embodiments]
Although the radio environment condition prediction system 1000 adopting OFDM has been described in the above embodiment, the present invention is not limited to this, and another modulation scheme may be used.

  Furthermore, in the wireless environment situation prediction system described in the above embodiment, each block may be individually made into one chip by a semiconductor device such as an LSI, or may be made into one chip so as to include a part or all. good.

  Although the term "LSI" is used here, the term "IC," "system LSI," "super LSI," or "ultra LSI" may be used depending on the degree of integration.

  Further, the method of circuit integration is not limited to LSI's, and implementation using dedicated circuitry or general purpose processors is also possible. After the LSI is manufactured, a programmable field programmable gate array (FPGA) may be used, or a reconfigurable processor that can reconfigure connection and setting of circuit cells in the LSI may be used.

  Further, part or all of the processing of each functional block in each of the above embodiments may be realized by a program. And a part or all of processing of each functional block of each above-mentioned embodiment is performed by central processing unit (CPU) in a computer. Further, programs for performing respective processing are stored in a storage device such as a hard disk or a ROM, and are read out from the ROM or to the RAM and executed.

  Further, each process of the above-described embodiment may be realized by hardware or may be realized by software (including a case where it is realized with an OS (Operating System), middleware, or a predetermined library). Furthermore, it may be realized by mixed processing of software and hardware.

  For example, when each functional unit of the above embodiment is realized by software, the hardware configuration shown in FIG. 6 (for example, a hardware configuration in which a CPU, a ROM, a RAM, an input unit, an output unit, etc. are connected by a bus Bus) Each functional unit may be realized by software processing using

  Further, the order of execution of the processing method in the above embodiment is not necessarily limited to the description of the above embodiment, and the order of execution can be interchanged without departing from the scope of the invention.

  A computer program that causes a computer to execute the above-described method and a computer readable recording medium recording the program are included in the scope of the present invention. Here, examples of the computer-readable recording medium include a flexible disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD, a DVD-ROM, a DVD-RAM, a large capacity DVD, a next-generation DVD, and a semiconductor memory. .

  The computer program is not limited to one recorded in the recording medium, but may be transmitted via a telecommunication line, a wireless or wired communication line, a network represented by the Internet, or the like.

  The specific configuration of the present invention is not limited to the above-described embodiment, and various changes and modifications can be made without departing from the scope of the invention.

1000 wireless environment status prediction system A1 to A3 wireless device Svr server 1 transmitter 2 receiver 2 channel usage status observation unit 4 channel state data acquisition unit 5 first interface unit Sv1 second interface unit Sv2 prediction unit

Claims (6)

A wireless environment situation prediction system including first to Nth wireless communication devices that are N (N: natural number, N22) wireless communication devices respectively installed at predetermined positions in a predetermined space, and a server There,
The first to Nth wireless communication devices are respectively
A transmitter configured to generate a wireless signal by performing transmission processing on data;
A reception unit that acquires data carried by the wireless signal by performing reception processing on the wireless signal;
A channel use status observing unit that observes a use status of a channel used for communication of the wireless signal by controlling at least one of the transmission unit and the reception unit;
Data indicating the propagation status of the point where the wireless communication apparatus is installed in the first period, based on the signal acquired by at least one of the transmission unit, the reception unit, and the channel utilization status observation unit; A channel state data acquisition unit that acquires at least one data of data indicating a radio resource use state as channel state data;
A first interface unit for transmitting the channel state data acquired by the channel state data acquisition unit to the server;
Equipped with
The server is
A second interface unit for receiving the channel state data from the first to Nth wireless communication devices;
A prediction unit that executes prediction processing for predicting future data of points where the first to Nth wireless communication devices are installed, based on two or more of the channel state data received by the second interface unit; ,
A wireless environment situation forecasting system comprising: The first period is a period from sample time t−p + 1 (p: natural number) to sample time t,
The data acquired in the sample time i by the channel state data acquisition unit and X _i,
The k wireless communication device (k: natural number, 1 ≦ k ≦ N) the data acquired in the first period Data_Ak: If _{(X t-p + 1 X} t) that,
The prediction unit
Data _{Data_A1} is N data _{(X t-p + 1:} X t) ~ Data Data_AN: executing the predictive processing using two or more data among the _{(X t-p + 1 X} t),
The wireless environment situation prediction system according to claim 1. The data indicating the propagation status is
(1) received power, (2) propagation path value, (3) delay profile, (4) data including at least one of data on delay dispersion,
The wireless environment situation prediction system according to claim 1 or 2. The data indicating the radio resource usage status is
(1) radio resource utilization rate, (2) number of retransmissions, (3) frame error rate, (4) data including at least one of data relating to a used transmission rate,
The wireless environment situation prediction system according to any one of claims 1 to 3. A wireless environment situation prediction system including first to Nth wireless communication devices which are N (N: natural number, N ≧ 2) wireless communication devices respectively installed at predetermined positions in a predetermined space, and a server A radio environment condition prediction method to be used,
The first to Nth wireless communication devices are respectively
A transmitter configured to generate a wireless signal by performing transmission processing on data;
A reception unit that acquires data carried by the wireless signal by performing reception processing on the wireless signal;
A channel use status observing unit that observes a use status of a channel used for communication of the wireless signal by controlling at least one of the transmission unit and the reception unit;
Equipped with
In each of the first to Nth wireless communication devices, the wireless communication device in a first period based on a signal acquired by at least one of the transmitting unit, the receiving unit, and the channel usage status observing unit. A channel state data acquisition step of acquiring, as channel state data, data of at least one of data indicating a propagation state of a point where the wireless communication system is installed and data indicating a radio resource utilization state;
A data transmission step of transmitting the channel state data acquired in the channel state data acquisition step to the server in each of the first to Nth wireless communication devices;
Receiving, at the server, the channel state data from the first to Nth wireless communication devices;
The server executes prediction processing for predicting future data of a point where the first to Nth wireless communication devices are installed, based on the two or more pieces of the channel state data received in the data receiving step. Prediction step,
A wireless environment situation forecasting method comprising:   A program for causing a computer to execute the wireless environment situation prediction method according to claim 5.

Images