Tunnel environment Mesh network optimal energy consumption communication method based on signal intensity

Abstract

The invention relates to the technical field of communication, and discloses a tunnel environment Mesh network optimal energy consumption communication method based on signal intensity, which comprises the following steps of: fixedly arranging a plurality of Mesh sites in a tunnel, and dividing a calibration position of each Mesh site according to a set distance; acquiring the correction speed of the mobile terminal at each calibration position; acquiring current temperature, humidity and signal intensity at each calibration position through a sensor arranged on the mobile terminal; training the neural network model by taking the correction speed, the temperature, the humidity and the signal intensity at each calibration position as a training data set; and adjusting the transmitting power of the mobile terminal according to the distance factor output by the neural network model. According to the invention, the signal intensity and the energy consumption are balanced in the tunnel environment.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a tunnel environment Mesh network optimal energy consumption communication method based on signal strength. Background Art

[0002] During tunnel construction, vehicles frequently enter and exit the tunnel, and there is no stable 220V power supply in the tunnel, so any wired power supply and communication solution is unrealistic. In addition, when the antenna is low, the wireless propagation distance is relatively short, and the multipath effect is particularly obvious. Therefore, a Mesh network with directional antennas is needed to establish a communication link in the construction tunnel.

[0003] In a Mesh network, each mobile terminal and sensor can be used as a node. Due to the difference in energy consumption of different nodes, after working for a period of time, the core energy-consuming nodes in the network are prone to premature death, causing the entire network to be paralyzed. Therefore, Mesh network communications using directional antennas face the problems of signal strength attenuation and energy consumption optimization. Summary of the invention

[0004] The purpose of the present invention is to balance signal strength and energy consumption in a tunnel environment and to provide a tunnel environment Mesh network optimal energy consumption communication method based on signal strength.

[0005] In order to achieve the above-mentioned object of the invention, the embodiment of the present invention provides the following technical solutions:

[0006] A tunnel environment Mesh network optimal energy consumption communication method based on signal strength, comprising the following steps:

[0007] Step 1: multiple Mesh sites are fixedly set up in the tunnel, and for each Mesh site, its calibration position is divided according to the set distance;

[0008] Step 2, obtaining the correction speed of the mobile terminal at each calibration position;

[0009] Step 3, obtaining the current temperature, humidity, and signal strength at each calibration location through a sensor set on the mobile terminal;

[0010] Step 4, using the correction speed, temperature, humidity, and signal strength at each calibration position as a training data set to train the neural network model;

[0011] Step 5: Adjust the transmission power of the mobile terminal according to the distance factor output by the neural network model.

[0012] Furthermore, the step 2 specifically includes the following steps:

[0013] The average speed is:

[0014] in, represents the average speed; R1 is the signal strength of the mobile terminal at the last calibration position, and R2 is the signal strength of the mobile terminal at the current calibration position, which is sent by the Mesh site to the mobile terminal; P T is the transmission power of the Mesh site; It represents the time taken by the mobile terminal to reach the current calibration position from the last calibration position; n represents the propagation factor, which depends on the environment of wireless signal propagation; is the angle between the last calibrated position and the current calibrated position;

[0015] The acceleration a of the mobile terminal is obtained by the acceleration sensor set on the mobile terminal, and the acceleration a and time are calculated according to the acceleration a and time. , calculate the instantaneous velocity:

[0016] in, , t1 represents the time when the mobile terminal departs from the last calibrated position, and t0 represents the time when the mobile terminal arrives at the current calibrated position; v t1 represents the speed at time t1, v t0 represents the velocity at time t0; a represents the acceleration;

[0017] After obtaining the average speed and instantaneous speed, calculate the corrected speed:

[0018] Where, v` represents the correction speed; v t1 Indicates instantaneous speed; represents the correction factor; It represents the difference between average speed and instantaneous speed.

[0019] Furthermore, the step 4 specifically includes the following steps:

[0020] At a calibration position, the correction speed, temperature, humidity, and signal strength are obtained according to the sampling interval t, and the training data set X = {X s , X 2s , X 3s , ..., X Ms}, where X js represents the data collected at the jth calibration position, j=1,2,...,M, s represents the distance interval of the calibration position, and M represents the total number of distance intervals;

[0021] X js ={x js,t , x js,2t , ..., x js,Nt}, where x js,it represents the data collected at the i-th sampling interval at the j-th calibration position, i=1,2,...,N, t represents the sampling interval at a calibration position, and N represents the total number of sampling intervals;

[0022] x js,it ={V js,it , T js,it , H js,it , R js,it}, where V js,it represents the correction speed collected at the i-th sampling interval at the j-th calibration position, T js,it represents the temperature collected at the i-th sampling interval at the j-th calibration position, H js,it represents the humidity collected at the i-th sampling interval at the j-th calibration position, R js,it represents the signal strength collected at the i-th sampling interval at the j-th calibration position;

[0023] Take the training data set X as input and set the distance factor D={d s , d 2s , ..., d Ms} as output, the neural network model is trained, where d js represents the distance factor of the jth calibration position,

[0024] Furthermore, the hidden state of the neural network model is H={h t ,h 2t , ..., h Nt}, then the neural network model is:

[0025] in, represents the correction factor; h (i-1)t represents the hidden state corresponding to the i-1th time interval; g( ) represents the activation function; Represents the weight matrix connecting the hidden layer to the output layer; Represents the weight matrix connecting time (i-1)t to time it; Represents the weight matrix connecting the input layer to the hidden layer; Represents the hidden layer bias factor Represents the output layer bias factor.

[0026] Furthermore, the step 5 specifically includes the following steps:

[0027] The relationship between the distance factor output by the neural network model and the transmission power of the mobile terminal is:

[0028] Among them, PT k Indicates the transmission power of the mobile terminal at the previous location, PT k+1 Indicates the transmission power of the mobile terminal at the current location; d k Indicates the distance factor of the previous position, d k+1 Indicates the distance factor of the current position; represents the adjustment parameter for the far case, Indicates the adjustment parameters for the walk-in situation;

[0029] After the mobile terminal moves to the corresponding position, the distance factor of the position is output through the neural network model. At the same time, the mobile terminal automatically adjusts the transmission power to achieve the best balance between signal strength and energy consumption in the tunnel environment.

[0030] Compared with the prior art, the present invention has the following beneficial effects: after setting up the Mesh site, the present invention pre-divides the calibration positions in the tunnel, obtains the speed, current temperature, humidity, and signal strength of the mobile terminal at each calibration position, and trains the neural network model after arranging them into a training data set, so that the neural network model outputs a distance factor, and adjusts the position of the mobile terminal according to the relationship between the distance factor and the transmission power of the mobile terminal to balance the signal strength and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 is a flow chart of the method of the present invention;

[0033] Figure 2 This is a schematic diagram of node and Mesh site settings according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0035] It should be noted that similar numbers and letters represent similar items in the following figures, so once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance, or implying any such actual relationship or order between these entities or operations. In addition, the terms "connected", "connected", etc. can be directly connected between elements, or indirectly connected via other elements.

[0036] Embodiment 1:

[0037] The present invention is achieved through the following technical solutions: Figure 1 As shown, a tunnel environment Mesh network optimal energy consumption communication method based on signal strength includes the following steps:

[0038] Step 1: Set up multiple Mesh sites in the tunnel, and divide the calibration position of each Mesh site according to the set distance.

[0039] like Figure 2 As shown in the figure, since the tunnel environment is almost a straight line, the Mesh stations are set in a row according to the depth of the tunnel, and the distances between adjacent Mesh stations can be equal or unequal. When a node (referring to a mobile terminal, various sensors are set on the mobile terminal) enters the tunnel, it will form the following Figure 2The network topology shown in the figure shows that A1, B1, and C1 are Mesh sites, A2~A5, B2~B5, and C2~C5 are nodes, and the dotted circle is the network coverage of the Mesh site or node. According to such a network coverage, when A2 communicates with A3 and A4, it does not need to be transferred through A1; when A2 communicates with A5, it can be transferred through A1; when A3 communicates with B2, it can also communicate directly; when A3 communicates with B3, it can be transferred through A1 and B1. It can be seen that when the distance between nodes or between nodes and Mesh sites is longer, communication needs to go through multiple links, thereby increasing power consumption. In addition, in the tunnel environment, factors such as temperature and humidity will also affect power consumption. Therefore, this solution calibrates the influencing factors at multiple distances from the Mesh site, uses a neural network model to learn the influencing factors, and thus predicts the optimal solution between the distance relative to the Mesh site and power consumption.

[0040] For example, if the distance s is set to 1m, the Mesh site is used as a calibration position every 1m.

[0041] Step 2: Obtain the corrected speed of the mobile terminal at each calibration position.

[0042] The mobile terminal starts from the Mesh site, and the correction speed when the mobile terminal reaches the calibration position is calculated by the acceleration sensor set on the mobile terminal and the transmission power of the Mesh site.

[0043] The average speed is:

[0044] in, represents the average speed; R1 is the signal strength of the mobile terminal at the last calibration position, and R2 is the signal strength of the mobile terminal at the current calibration position, which is sent by the Mesh site to the mobile terminal; P T is the transmission power of the Mesh site; It represents the time taken by the mobile terminal to reach the current calibration position from the last calibration position; n represents the propagation factor, which depends on the environment of wireless signal propagation; It is the angle between the last calibration position and the current calibration position.

[0045] The acceleration a of the mobile terminal is obtained by the acceleration sensor set on the mobile terminal, and the acceleration a and time are calculated according to the acceleration a and time. , calculate the instantaneous velocity:

[0046] in, , t1 represents the time when the mobile terminal departs from the last calibrated position, and t0 represents the time when the mobile terminal arrives at the current calibrated position; v t1represents the speed at time t1, v t0 represents the velocity at time t0; a represents the acceleration.

[0047] After obtaining the average speed and instantaneous speed, calculate the corrected speed:

[0048] Where, v` represents the correction speed; v t1 Indicates instantaneous speed; represents the correction factor; It represents the difference between average speed and instantaneous speed.

[0049] Step 3, at each calibration location, obtain the current temperature, humidity, and signal strength through a sensor set on the mobile terminal.

[0050] Since different locations in the tunnel environment have different temperatures, humidity, and signal strengths, in addition to obtaining the correction speed of the mobile terminal, it is also necessary to obtain the temperature T, humidity H, and signal strength R obtained by the mobile terminal through sensors set on the mobile terminal at each calibration position.

[0051] Step 4: Use the corrected speed, temperature, humidity, and signal strength at each calibration position as a training data set to train the neural network model.

[0052] At a calibration position, the correction speed, temperature, humidity, and signal strength are obtained according to the sampling interval t, and the training data set X = {X s , X 2s , X 3s , ..., X Ms}, where X js represents the data collected at the jth calibration position, j=1,2,...,M, s represents the distance interval of the calibration position, and M represents the total number of distance intervals.

[0053] X js ={x js,t , x js,2t , ..., x js,Nt}, where x js,it It represents the data collected at the i-th sampling interval at the j-th calibration position, i=1,2,...,N, t represents the sampling interval at a calibration position, and N represents the total number of sampling intervals.

[0054] x js,it ={V js,it , T js,it , H js,it , R js,it}, where V js,itrepresents the correction speed collected at the i-th sampling interval at the j-th calibration position, T js,it represents the temperature collected at the i-th sampling interval at the j-th calibration position, H js,it represents the humidity collected at the i-th sampling interval at the j-th calibration position, R js,it It represents the signal strength collected at the i-th sampling interval at the j-th calibration position.

[0055] It is easy to understand that when the mobile terminal moves from the first calibration position s to the Mth calibration position Ms, a total of M×N sets of data {V js,it , T js,it , H js,it , R js,it However, since the nodes do not move in a straight line in the tunnel, for a Mesh site, the mobile terminal can move in different directions and change the size of the distance interval s, so that more than M×N groups of data can be obtained, and the amount of data may be very large.

[0056] Take the training data set X as input and set the distance factor D={d s , d 2s , ..., d Ms} as output, the neural network model is trained, where d js represents the distance factor of the jth calibration position, and the hidden state of the neural network model is H={h t ,h 2t , ..., h Nt}, then the neural network model is:

[0057] in, represents the correction factor, which is determined by the tunnel environment; h (i-1)t represents the hidden state corresponding to the i-1th time interval; g( ) represents the activation function; Represents the weight matrix connecting the hidden layer to the output layer; Represents the weight matrix connecting time (i-1)t to time it; Represents the weight matrix connecting the input layer to the hidden layer; Represents the hidden layer bias factor Represents the output layer bias factor.

[0058] Step 5: Adjust the transmission power of the mobile terminal according to the distance factor output by the neural network model.

[0059] The relationship between the distance factor output by the neural network model and the transmission power of the mobile terminal is:

[0060] Among them, PT k Indicates the transmission power of the mobile terminal at the previous location, PT k+1 Indicates the transmission power of the mobile terminal at the current location; d k Indicates the distance factor of the previous position, d k+1 Indicates the distance factor of the current position; represents the adjustment parameter for the far case, Indicates adjustment parameters for the walk-in situation.

[0061] Since the neural network model can obtain the distance factors of several calibrated positions after being trained with a large amount of data, after the mobile terminal moves to the corresponding position in step 5, the distance factor of the position can be output through the neural network model. At the same time, the mobile terminal automatically adjusts the transmission power to achieve the best signal strength and energy consumption balance in the tunnel environment.

[0062] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A tunnel environment Mesh network optimal energy consumption communication method based on signal strength, characterized by: The following steps are involved: Step 1: multiple Mesh sites are fixedly set up in the tunnel, and for each Mesh site, its calibration position is divided according to the set distance; Step 2, obtaining the correction speed of the mobile terminal at each calibration position; Step 3, obtaining the current temperature, humidity, and signal strength at each calibration location through a sensor set on the mobile terminal; Step 4, using the correction speed, temperature, humidity, and signal strength at each calibration position as a training data set to train the neural network model; Step 5: Adjust the transmission power of the mobile terminal according to the distance factor output by the neural network model.

2. According to claim 1, a tunnel environment Mesh network optimal energy consumption communication method based on signal strength is characterized by: The step 2 specifically includes the following steps: The average speed is: in, represents the average speed; R1 is the signal strength of the mobile terminal at the last calibration position, and R2 is the signal strength of the mobile terminal at the current calibration position, which is sent by the Mesh site to the mobile terminal; P T is the transmission power of the Mesh site; It represents the time taken by the mobile terminal to reach the current calibration position from the last calibration position; n represents the propagation factor, which depends on the environment of wireless signal propagation; is the angle between the last calibrated position and the current calibrated position; The acceleration a of the mobile terminal is obtained by the acceleration sensor set on the mobile terminal, and the acceleration a and time are calculated according to the acceleration a and time. , calculate the instantaneous velocity: in, , t1 represents the time when the mobile terminal departs from the last calibrated position, and t0 represents the time when the mobile terminal arrives at the current calibrated position; v t1 represents the speed at time t1, v t0 represents the speed at time t0; a represents the acceleration; After obtaining the average speed and instantaneous speed, calculate the corrected speed: Where, v` represents the correction speed; v t1 Indicates instantaneous speed; represents the correction factor; It represents the difference between average speed and instantaneous speed.

3. According to claim 2, a tunnel environment Mesh network optimal energy consumption communication method based on signal strength is characterized by: The step 4 specifically comprises the following steps: At a calibration position, the correction speed, temperature, humidity, and signal strength are obtained according to the sampling interval t, and the training data set X = {X s , X 2s , X 3s , ..., X Ms }, where X js represents the data collected at the jth calibration position, j=1,2,...,M, s represents the distance interval of the calibration position, and M represents the total number of distance intervals; X js ={x js,t , x js,2t , ..., x js,Nt }, where x js,it represents the data collected at the i-th sampling interval at the j-th calibration position, i=1,2,...,N, t represents the sampling interval at a calibration position, and N represents the total number of sampling intervals; x js,it ={V js,it , T js,it , H js,it , R js,it }, where V js,it represents the correction speed collected at the i-th sampling interval at the j-th calibration position, T js,it represents the temperature collected at the i-th sampling interval at the j-th calibration position, H js,it represents the humidity collected at the i-th sampling interval at the j-th calibration position, R js,it represents the signal strength collected at the i-th sampling interval at the j-th calibration position; Take the training data set X as input and set the distance factor D={d s , d 2s , ..., d Ms } as output, the neural network model is trained, where d js Represents the distance factor of the jth calibration position.

4. According to claim 3, a tunnel environment Mesh network optimal energy consumption communication method based on signal strength is characterized by: The hidden state of the neural network model is H={h t ,h 2t , ..., h Nt }, then the neural network model is: in, represents the correction factor; h (i-1)t represents the hidden state corresponding to the i-1th time interval; g( ) represents the activation function; Represents the weight matrix connecting the hidden layer to the output layer; Represents the weight matrix connecting time (i-1)t to time it; Represents the weight matrix connecting the input layer to the hidden layer; Represents the hidden layer bias factor Represents the output layer bias factor.

5. According to claim 4, the optimal energy consumption communication method for a tunnel environment Mesh network based on signal strength is characterized by: The step 5 specifically comprises the following steps: The relationship between the distance factor output by the neural network model and the transmission power of the mobile terminal is: Among them, PT k Indicates the transmission power of the mobile terminal at the previous position, PT k+1 Indicates the transmission power of the mobile terminal at the current location; d k Indicates the distance factor of the previous position, d k+1 Indicates the distance factor of the current position; represents the adjustment parameter for the far case, Indicates the adjustment parameters for the walk-in situation; After the mobile terminal moves to the corresponding position, the distance factor of the position is output through the neural network model. At the same time, the mobile terminal automatically adjusts the transmission power to achieve the best balance between signal strength and energy consumption in the tunnel environment.

Images