US-20260128955-A1 - AUTOMATIC DEPLOYMENT SYSTEM AND METHOD THEREOF

US20260128955A1US 20260128955 A1US20260128955 A1US 20260128955A1US-20260128955-A1

Abstract

The invention relates to an automatic deployment system and a method thereof. The automatic deployment system includes an input unit, a simulation unit, and a deployment unit. The input unit receives a first actual transmission information of a user device in the absence of signal path redistributors. The simulation unit receives a simulation parameter and generates a first simulation information and a second simulation information based on the simulation parameter. The deployment unit trains and generates a prediction deployment model using the first actual transmission information, the first simulation information, and the second simulation information. The prediction deployment model generates a prediction deployment information based on the second actual transmission information. The method for automatic deployment involves steps related to utilizing an automatic deployment signal path redistribution system to generate the prediction deployment information.

Inventors

Li-Hsiang SHEN
Tung-Min YANG
Ming-Wei Li
Po-Chen Wu
Kai-Ten Feng
Chun-Chieh Kuo
Hua-Pei Chiang
Chyi-Dar Jang
Chi-Hung Lin
Che-Yu Liao
Wei-Di HUANG

Assignees

FAR EASTONE TELECOMMUNICATIONS CO., LTD.

Dates

Publication Date: 20260507
Application Date: 20241220
Priority Date: 20241105

Claims (20)

1 . An automatic deployment system, comprising: an input unit, receiving a first actual transmission information and a second actual transmission information in a communication environment without signal path redistributor; a simulation unit, connected to the input unit, the simulation unit receiving a plurality of simulation parameters and simulating to generate a first simulation information and a second simulation information according to the plurality of simulation parameters; and a deployment unit, connected to the simulation unit and the input unit, the deployment unit training to generate a prediction deployment model according to the first actual transmission information, the first simulation information, and the second simulation information and using the prediction deployment model to generate a prediction deployment information according to the second actual transmission information.
2 . The automatic deployment system according to claim 1 , wherein the deployment unit is provided with a simulation performance threshold; after the deployment unit generates the prediction deployment information, the deployment unit compares a performance of the prediction deployment information with the simulation performance threshold; when the performance of the prediction deployment information meets the simulation performance threshold, the deployment unit publishes the prediction deployment information to a signal path redistributor in the communication environment; when the performance of the prediction deployment information does not meet the simulation performance threshold, the plurality of simulation parameters are adjusted to regenerate a new prediction deployment information.
3 . The automatic deployment system according to claim 1 , wherein the deployment unit is provided with an actual performance threshold; after the deployment unit publishes the prediction deployment information to a signal path redistributor in the communication environment, the deployment unit receives a third actual transmission information responded by a user device in the communication environment after the signal path redistributor is deployed at the position, and the deployment unit compares a performance of the third actual transmission information with the actual performance threshold; when the performance of the third actual transmission information meets the actual performance threshold, a deployment is completed; when the performance of the third actual transmission information does not meet the actual performance threshold, the deployment is not completed, and the plurality of simulation parameters are adjusted to regenerate a new prediction deployment information.
4 . The automatic deployment system according to claim 1 , wherein the communication environment further comprises a base station and a user device, and the simulation unit generates the first simulation information by simulating a state in which only the base station and the user device are present in the communication environment; the first simulation information comprises a first simulation wireless channel and a first simulation transmission performance; the simulation unit simulates each channel for transmitting wireless data between the base station and the user device as the first simulation wireless channel, and the simulation unit simulates transmission performance in each of the first simulation wireless channels as the first simulation transmission performance.
5 . The automatic deployment system according to claim 4 , wherein the simulation unit generates the second simulation information in a state where the communication environment comprises the base station, the user device, and a signal path redistributor; the second simulation information comprises a second simulation wireless channel and a second simulation transmission performance; the simulation unit simulates each channel for transmitting wireless data between the base station and the signal path redistributor, between the user device and the signal path redistributor, and between the signal path redistributor and another signal path redistributor as the second simulation wireless channel, and the simulation unit simulates transmission performance in each of the second simulation wireless channels as the second simulation transmission performance.
6 . The automatic deployment system according to claim 5 , wherein the deployment unit comprises a first artificial intelligence model and a second artificial intelligence model; the deployment unit receives the first actual transmission information or the second actual transmission information, processes the first actual transmission information, the first simulation information, and the second simulation information via the first artificial intelligence model and the second artificial intelligence model to generate the prediction deployment model, and provides the second actual transmission information to the prediction deployment model to generate the prediction deployment information.
7 . The automatic deployment system according to claim 6 , wherein the first artificial intelligence model generates a simulation output data according to the first actual transmission information and the first simulation information, and the second artificial intelligence model generates the prediction deployment information according to the simulation output data and the second simulation information.
8 . The automatic deployment system according to claim 7 , wherein the first artificial intelligence model and the second artificial intelligence model are both autoencoder models, the first artificial intelligence model comprises a first encoder and a first decoder, and the first encoder and the first decoder are both composed of neurons; the first encoder receives the first actual transmission information and generates a first latent variable according to the first actual transmission information and the first simulation information, and the first decoder receives the first latent variable and generates the simulation output data according to the first latent variable as an input of the second artificial intelligence model.
9 . The automatic deployment system according to claim 8 , wherein the first latent variable and the simulation output data are respectively expressed by the following formula: v 1 = f ENC ⁢ 1 ( x in ; θ ENC ⁢ 1 ) o ^ 1 = f DEC ⁢ 1 ( v 1 ; θ DEC ⁢ 1 ) wherein v 1 represents the first latent variable, ô 1 represents the simulation output data, θ ENC1 and θ DEC1 are the model weights of the first encoder and the first decoder respectively, f ENC1 (x in ;θ ENC1 ) is a function form in which the first actual transmission information is encoded, f DEC1 (v 1 ;θ DEC1 ) is a function form in which the first latent variable is a reconstructed output, and x in represents the first actual transmission information.
10 . The automatic deployment system according to claim 9 , wherein for the first encoder, the higher the layer, the fewer neurons there are, and the lower the layer, the more neurons there are; for the first decoder, the lower the layer, the fewer neurons there are, and the higher the layer, the more neurons there are; the number of neurons in the last layer of the first encoder is the same as the number of neurons in the first layer of the first decoder, and the number of neurons in the first layer of the first encoder is the same as the number of neurons in the last layer of the first decoder; each of the neurons represents a weight, and all neurons constitute the model weight of the first encoder; the relationship between the layers of the first encoder is shown in the following formula: y t + 1 = f act ( W t ⁢ x t + b t ) wherein y t+1 represents the output of t+1 layers, x t represents the input of tth layer, W t is the model weight of tth layer, b t is the bias weight of tth layer, f act is the nonlinear activation function, and t is a positive integer.
11 . The automatic deployment system according to claim 9 , wherein a first loss function of the first artificial intelligence model may be designed according to the following formula: L 1 = ∑ i ( o ^ 1 , i - o 1 , i ) 2 wherein i represents the index of nth output, L 1 represents the first loss function, and ô 1,i −ô 1,i represents the difference between the simulation output data and the first simulation information.
12 . The automatic deployment system according to claim 9 , wherein the second artificial intelligence model comprises a second encoder and a second decoder; a data sequence of the second simulation information input into the second encoder is the same as a data sequence of the simulation output data output by the first artificial intelligence model, and the second encoder and the second decoder have the same number of sequence units; each of the sequence units is a neural network unit, and the output of the second encoder is a second latent variable, which is expressed by the following formula: v 2 = f ENC ⁢ 2 ( o ^ 1 ; θ ENC ⁢ 2 ) wherein f ENC2 is the mapping function, the input of f ENC2 is the simulation output data ô 1 , v 2 represents the second latent variable, θ ENC2 is a model weight of the second encoder, the second latent variable v 2 is the input of the second decoder, and ô 1 represents the simulation output data.
13 . The automatic deployment system according to claim 12 , wherein the second decoder comprises a start tag <SOS> and an end tag <EOS>, which respectively indicate the start and the end of the sequence; a prediction deployment data of each of the signal path redistributors is embedded between the start tag <SOS> and the end tag <EOS> in the form of {<SOS>, <Data1>, <Data2>, . . . <Data N>, <EOS>} to dynamically obtain the prediction deployment information by controlling the start tag <SOS> and the end tag <EOS>; the prediction deployment information may be expressed as {<SOS>, <deployment of SPR 1>, <deployment of SPR 2>, . . . <deployment of SPR N>, <system performance 1>, <system performance 2>, . . . <system performance N>, <EOS>}, wherein N may be a dynamic number and a positive integer, and the prediction deployment information comprises all the prediction deployment data.
14 . The automatic deployment system according to claim 13 , wherein in the communication environment, positions, orientations and heights of each base station, each user device, and each signal path redistributor are defined by Cartesian coordinates, as shown in the following formula: X n SPR ( x n SPR , y n SPR , h n SPR , ϑ n SPR , φ n SPR ) X k UE ( x k UE , y k UE , h k UE , ϑ k UE , φ k UE ) X l BS ( x l BS , y l BS , h l BS , ϑ l BS , φ l BS ) wherein n, k, l is a positive integer, SPR represents the signal path redistributor, UE represents the user device, BS represents the base station, X n SPR is nth signal path redistributor, x n SPR is the coordinate value of the nth signal path redistributor in the x axial direction, y n SPR is the coordinate value of the nth signal path redistributor in the y axial direction, h n SPR is the coordinate value of the nth signal path redistributor in the z axial direction, ϑ n SPR is the horizontal angle of the nth signal path redistributor, φ n SPR is the pitch angle of the nth signal path redistributor, X k UE is the kth user device, x k UE is the coordinate value of kth user device in the x axial direction, y k UE is the coordinate value of kth user device in the y axial direction, h k UE is the coordinate value of kth user device in the z axial direction, ϑ k UE is the horizontal angle of the kth user device, φ k UE is the pitch angle of the kth user device, X l BS is lth base station, x l BS is the coordinate value of the lth base station in the x axial direction, y l BS is the coordinate value of the lth base station in the y axial direction, h l BS is the coordinate value of the lth base station in the z axial direction, ϑ l BS is the horizontal angle of the lth base station, and φ l BS is the pitch angle of the lth base station; the <deployment of SPR 1>, <deployment of SPR 2>, . . . <deployment of SPR N> in the prediction deployment information comprise the corresponding position of the signal path redistributor, which is expressed as x n SPR , y n SPR , h n SPR , the direction of the signal path redistributor, which is expressed as ϑ n SPR , φ n SPR , and the phase shift matrix of the signal path redistributor, which is expressed as redistributor; the phase shift matrix of the signal path redistributor is shown as the following formula: Θ n = [ β n , 1 ⁢ e j ⁢ ϕ n , 1 0 … 0 0 β n , 2 ⁢ e j ⁢ ϕ n , 2  ⋮ ⋮  ⋱ 0 0 … 0 β n , M ⁢ e j ⁢ ϕ n , M ] wherein Θ n represents the phase shift matrix of the nth signal path redistributor, M represents the nth reflection unit of the signal path redistributor, 0≤β n,M ≤1 is the amplitude constraint of the nth reflection unit of the signal path redistributor, and 0≤φ n,M ≤2π is the phase constraint of the nth reflection unit of the signal path redistributor.
15 . The automatic deployment system according to claim 14 , wherein an output of the ith sequence in the sequence of the second decoder may be obtained through the previous layer (i.e., (i−1)th layer) of the lth sequence, and each of the sequences is a neuron layer and is expressed by the following formula: seq i = f DEC ⁢ 2 , i ( seq i - 1 ; θ DEC ⁢ 2 , i ) wherein θ DEC2,i is the model weight of the ith sequence, f DEC2,i represents the function of the ith neural network unit layer of the second decoder DEC 2 , seq i represents the output of the ith sequence, and i is a positive integer.
16 . The automatic deployment system according to claim 15 , wherein an input of the first sequence of the second decoder is the second latent variable v 2 , and under the condition that a sequence length of the second decoder is V, and V is a positive integer, the prediction deployment information of the second decoder is expressed by the following formula: o ^ 2 = [ seq v , … , seq v - 1 , … ⁢ seq 2 , seq 1 ] wherein ô 2 represents the prediction deployment information, and v represents the index of the sequence and is a positive integer from 1 to V.
17 . The automatic deployment system according to claim 16 , wherein a third actual transmission information and the prediction deployment information in each of the sequence units use a second loss function to measure an error between the third actual transmission information and the prediction deployment information, and the second loss function is shown in the following formula: L 2 = - ∑ v = 1 V ⁢ p DEC ⁢ 2 , v ⁢ log ⁡ ( p ^ DEC ⁢ 2 , v ) wherein L 2 represents the second loss function, p DEC2,v and {circumflex over (p)} DEC2,v are the vth third actual transmission information and the prediction deployment information respectively, and the third actual transmission information is collected through exhaustive search.
18 . The automatic deployment system according to claim 17 , wherein the first artificial intelligence model performs back propagation to update a first neural network weight, as shown in the following formula: θ 1 ← θ 1 - η · ∇ θ 1 L 1 wherein θ 1 is the first neural network weight of the first encoder and the first decoder of the first artificial intelligence model and comprises a first weight parameter W 1 and a first bias parameter b 1 , and the first weight parameter and the first bias parameter are optimized during the training process to minimize the first loss function; η: a learning rate is a hyperparameter that determines a step size of each update of the first weight parameter and the first bias parameter of the first artificial intelligence model, and controls a distance that the first artificial intelligence model should move each time a gradient descends; ∇ 74 L 1 : a gradient of the first loss function with respect to the first neural network weight of the first artificial intelligence model represents a direction and a rate of change of the first loss function when the first weight parameter and the first bias parameter change.
19 . The automatic deployment system according to claim 17 , wherein the second artificial intelligence model performs back propagation to update a second neural network weight, as shown in the following formula: θ 2 ← θ 2 - η · ∇ θ L 2 wherein θ 2 is the second neural network weight of the second artificial intelligence model and comprises a second weight parameter and a second bias parameter of the second encoder and the second decoder, and the second weight parameter and the second bias parameter are optimized during the training process to minimize the second loss function L 2 ; η: a learning rate is a hyperparameter that determines a step size of each update of the second weight parameter and the second bias parameter of the second artificial intelligence model, and controls a distance that the second artificial intelligence model should move each time a gradient descends; ∇ 74 L 2 : a gradient of the second loss function with respect to a gradient of the second neural network weight of the second artificial intelligence model represents a direction and a rate of change of the second loss function when the second weight parameter and the second bias parameter change.
20 . An automatic deployment method, applied to an automatic deployment system, the automatic deployment system comprising an input unit, a simulation unit and a deployment unit, the automatic deployment method comprising steps of: receiving, by the input unit, a first actual transmission information in a communication environment without signal path redistributor; receiving, by the simulation unit, a plurality of simulation parameters; simulating, by the simulation unit, to generate a first simulation information and a second simulation information according to the plurality of simulation parameters; training, by the deployment unit, to generate a prediction deployment model according to the first actual transmission information, the first simulation information, and the second simulation information and using the prediction deployment model to generate a prediction deployment information according to a second actual transmission information received by the input unit; publishing, by the deployment unit, the prediction deployment information to a signal path redistributor in the communication environment.

Description

BACKGROUND OF THE INVENTION This application claims priority for the TW application No. 113142381 filed on 5 Nov. 2024, the content of which is incorporated by reference in its entirely. FIELD OF THE INVENTION The invention relates to a deployment system for signal path redistributors and a method thereof, in particular, to a system and method for automatically generating prediction deployment information for deploying signal path redistributors through transmission performance information between user devices and base stations before the actual deployment of signal path redistributors. DESCRIPTION OF THE PRIOR ART In the fifth generation of wireless communication technology, millimeter waves are widely used to achieve high-speed data transmission. However, due to the high-frequency characteristics of millimeter waves, they face serious obstruction and non-line-of-sight (NLoS) transmission problems during transmission, which limits the coverage and effectiveness of millimeter wave technology. In order to solve the problems, researchers have proposed a signal path redistributor (SPR) based on metamaterials. The technology can effectively reflect and redirect high-frequency signals (millimeter wave, sub THz, terahertz (THz), visible light) to the desired transmission direction. Since the signal path redistributor does not consume power, it is considered a potential solution to improve signal coverage and enhance throughput performance. However, the deployment process of the signal path redistributor presents certain technical challenges. First, to ensure the effectiveness of the signal path redistributor, precise measurements must be taken to determine the optimal mounting position and reflection angle. Second, these tuning processes are often time-consuming and require trial and error, which increases deployment complexity and cost. As the requirements in signals change in dynamic environments, the static configuration of signal path redistributors can hardly meet the needs of real-time adjustment, resulting in insufficient coverage or reduced signal performance. Therefore, there is still a problem in the prior art on how to dynamically and efficiently configure and deploy signal path redistributors. In particular, the problem includes how to achieve rapid and accurate deployment of signal path redistributors to cope with signal blocking and non-line-of-sight transmission challenges in different environments, and how to maximize signal coverage and throughput while reducing the time required for laborious measurement and adjustment of signal path redistributors during deployment. In addition, how to make the signal path redistributor adaptive to dynamic environmental changes to maintain stable signal performance is also a technical problem that needs to be solved urgently. SUMMARY OF THE INVENTION In view of the problems in the prior art, through dynamic and adaptive configuration in dynamic environments, the signal path redistributors may be deployed quickly and effectively to better meet the needs of modern high-speed wireless communications. According to the objective of the invention, an automatic deployment system is provided, which includes an input unit, a simulation unit, and a deployment unit. The input unit receives a first actual transmission information in the absence of signal path redistributors. The simulation unit receives a simulation parameter and simulates to generate a first simulation information and a second simulation information according to the simulation parameter. The deployment unit is connected to the simulation unit and the input unit. The deployment unit trains and generates a prediction deployment model according to the first actual transmission information, the first simulation information, and the second simulation information, using the prediction deployment model to generate a prediction deployment information according to the second actual transmission information. According to the objective of the invention, an automatic deployment method is provided, which is applied to the automatic deployment signal path redistributor system. The automatic deployment signal path redistributor system includes an input unit, a simulation unit, and a deployment unit. The automatic deployment method includes steps of: receiving, by the input unit, a first actual transmission information in the absence of signal path redistributors; receiving, by the simulation unit, a simulation parameter and simulating to generate a first simulation information and a second simulation information according to the simulation parameter; training and generating, by the deployment unit, a prediction deployment model according to the first actual transmission information, the first simulation information, and the second simulation information, and using the prediction deployment model to generate a prediction deployment information according to the first actual transmission information. According to the above