CN116707688A - Bias self-adaptive visible light communication system channel modeling method and system - Google Patents
Bias self-adaptive visible light communication system channel modeling method and system Download PDFInfo
- Publication number
- CN116707688A CN116707688A CN202310768508.5A CN202310768508A CN116707688A CN 116707688 A CN116707688 A CN 116707688A CN 202310768508 A CN202310768508 A CN 202310768508A CN 116707688 A CN116707688 A CN 116707688A
- Authority
- CN
- China
- Prior art keywords
- signal
- visible light
- neural network
- bias
- light communication
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004891 communication Methods 0.000 title claims abstract description 39
- 238000013528 artificial neural network Methods 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 16
- 230000005540 biological transmission Effects 0.000 claims description 20
- 238000006243 chemical reaction Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 13
- 230000003287 optical effect Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000007493 shaping process Methods 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims 4
- 238000012360 testing method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/11—Arrangements specific to free-space transmission, i.e. transmission through air or vacuum
- H04B10/114—Indoor or close-range type systems
- H04B10/116—Visible light communication
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/0202—Channel estimation
- H04L25/024—Channel estimation channel estimation algorithms
- H04L25/0254—Channel estimation channel estimation algorithms using neural network algorithms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Power Engineering (AREA)
- Optical Communication System (AREA)
Abstract
The invention discloses a bias self-adaptive visible light communication system channel modeling method and system, which use BPSK modulated random signals to learn nonlinear characteristics of a visible light communication system. Training data used by the neural network are visible light system transmitting signals with different transmitting powers and different LED bias currents, and reference data are corresponding receiving signals. And learning the relation between the transmitted signal and the received signal by using a neural network to finally obtain the nonlinear characteristics of the visible light channel. And because the transmitting power of the training data and the magnitude of the LED bias current are different, the finally trained neural network is suitable for transmitting signals with various powers and channels under various LED bias currents.
Description
Technical Field
The invention relates to a bias self-adaptive visible light communication system nonlinear channel modeling method and system based on a neural network, and belongs to the field of visible light communication.
Background
Future mobile communication networks will no longer use a single band as a channel and require high throughput, very low latency, strong connectivity and high reliability. Thus, visible Light Communication (VLC) technology at terahertz is considered as an important complementary technology to 6G data transmission. The VLC technology utilizes the bright and dark scintillation signals emitted by Light Emitting Diodes (LEDs) and other objects to achieve message transmission, and uses visible light instead of radio frequency electromagnetic waves as a carrier for wireless communication signal transmission, which plays an important role in the 6G network due to its extremely high data transmission capacity, reliable security and low energy consumption.
However, the conversion relation between the driving current and the luminous intensity of the LED has a serious nonlinear characteristic, and the bandwidth is limited, which adversely affects the high-speed data transmission and restricts the transmission rate of the system. The neural network can be used for establishing an accurate model for the nonlinear channel of the visible light communication, and the nonlinear influence is reduced, so that the reliability and the effectiveness of the whole system are improved.
Disclosure of Invention
The invention discloses a bias self-adaptive visible light communication system nonlinear channel modeling method and system completed by utilizing a neural network. The trained network can reproduce the nonlinear characteristics of the visible light channel and is suitable for the visible light channel under the emission signals of various powers and various LED bias currents.
The above purpose is achieved by the following technical scheme:
a bias self-adaptive visible light communication system channel modeling method utilizes a neural network to model a nonlinear channel of visible light communication, training data used by the neural network are visible light system transmitting signals with different transmitting powers and different bias currents, and reference data are corresponding receiving signals. The invention can finish accurate estimation on the nonlinearity and the memory of the visible light channel, and the channel after modeling is finished is suitable for different transmitting powers and LED bias currents with different magnitudes.
The method comprises the following steps:
step 1: generating a random signal, performing BPSK modulation on the random signal, enabling the modulated BPSK signal to be called an initial signal, up-sampling the initial signal, and over-shaping a filter to generate a transmission signal;
step 2: the generated transmitting signal is converted into an analog signal at a transmitting end through a DAC, amplified by a power amplifier, output with different powers, input into an LED, and converted into an optical signal by the LED for transmission. The transmitted signal is sent to a computer after photoelectric conversion and analog-to-digital conversion by a receiving end, the received signal is subjected to downsampling and filtering, and the bandwidth of the downsampled received signal is K times that of the initial signal. Then, synchronizing the down-sampled received signals, and finally storing the processed received signals and corresponding initial signals into a file;
step 3: changing the bias current of the LED, completing the operation of the step 2 again, and storing the received signal and the initial signal obtained after changing the bias current of the LED into corresponding files;
step 4: and (3) modeling a nonlinear channel of the visible light communication system by utilizing the transmission signals and the receiving signals obtained in the step (2) and the step (3) and utilizing a neural network:
the input of the network at the moment i is X i ＝[x(i-N),…,x(i),…,x(i+M),bias(i)] T Wherein bias (i) is X i The input-output relationship of each hidden layer of the network corresponding to the LED bias current is as follows:
where k refers to the kth hidden layer,omega as activation function of hidden layer k B k Is the parameter of hidden layer k. The number of input layer nodes is n+m+2. Since the bandwidth of the received signal is K times the bandwidth of the original signal, the number of nodes of the output layer is K. In order to optimize the network parameters, the following error indicator function is designed:
wherein y is network output, d is reference data;
step 5: the program reads the initial signal and the corresponding received signal from the file saved in step 3. The initial signal and the received signal are converted into a Toeplitz array, corresponding LED bias current is added to the initial signal after Toeplitz conversion and then is used as input data X, and corresponding received signal is used as reference data d. And (3) scrambling and rearranging the input data and the reference data, then putting the rearranged data and the rearranged data into a neural network for iteration, and circularly executing the step until the error function in the step (4) is not reduced.
The bias self-adaption visible light communication system nonlinear channel modeling method based on the neural network comprises the following specific steps of: after generating the BPSK modulated random signal, the signal is passed through a high pass filter so that the power of the signal can be uniformly distributed. And then up-sampling the signal, and enabling the sampling rate to meet the sampling rate requirement of DA.
According to the bias self-adaptive visible light communication system nonlinear channel modeling method based on the neural network, the sending signals in the step 2 are signals with different powers and identical LED bias currents. Neural networks trained using these signals may be suitable for channels at a single bias current, but may not be suitable for channels at other bias currents.
According to the bias self-adaptive visible light communication system nonlinear channel modeling method based on the neural network, step 3 is repeated after the LED bias current is changed for a plurality of times, the acquired signals are signals with different transmission powers and different bias currents, and the neural network trained by the signals can be suitable for channels under various bias currents.
The bias self-adaption visible light communication system nonlinear channel modeling method based on the neural network comprises the following steps of: input layer-multilayer hidden layer-output layer, wherein the activation function of the hidden layer is:
according to the bias self-adaptive visible light communication system nonlinear channel modeling method based on the neural network, the parameters of the adjustment neural network in the step 5 adopt an Adam learning rate self-adaptive optimization algorithm, the initial learning rate is set to be 0.01, and each 8 epochs are reduced by 0.5 times.
The bias self-adaption visible light communication system nonlinear channel modeling method based on the neural network comprises the steps that a test result of the neural network after training is completed, and a normalized mean square error NMSE between a predicted value and a true value is an error index function for measuring accuracy of waveform estimation:
where y (n) is the output of the real channel,is an estimate of y (n). Compared with the traditional LS estimation, the NMSE obtained by calculating the output of the neural network is obviously reduced, and the model is proved to perform more accurate estimation on the visible light channel.
The invention also provides a bias self-adaptive visible light communication system channel modeling device, which comprises:
a transmission signal generation module: the method comprises the steps of generating a random signal, performing BPSK modulation on the random signal, enabling the modulated BPSK signal to be called an initial signal, up-sampling the initial signal, and performing an over-shaping filter on the initial signal to generate a transmission signal;
signal transmitting and receiving module: the transmitting terminal is used for converting the generated transmitting signal into an analog signal through a DAC (digital-to-analog converter), amplifying the analog signal through a power amplifier, outputting the analog signal with different powers, inputting the analog signal into an LED, and converting the electric signal into an optical signal to be transmitted through the LED; the optical signal after sending is finished photoelectric conversion, analog-to-digital conversion by the receiving end and sent to the computer, the computer carries on the downsampling and filtering to the received signal, the bandwidth of the received signal after downsampling is K times of the original signal bandwidth; then, synchronizing the down-sampled received signals; changing the bias current of the LED at the transmitting module, repeating the transmitting and receiving steps to obtain different transmitting signal-receiving signal combinations;
the neural network training module: converting the initial signal and the received signal into a Toeplitz array, adding corresponding LED bias current into the initial signal after Toeplitz conversion, and taking the initial signal and the received signal as input data X and the corresponding received signal as reference data d; and (3) scrambling and rearranging the input data and the reference data, then putting the rearranged data and the rearranged data into a neural network for iteration, and circularly executing the step until the error function is not reduced.
The invention also provides a bias self-adaptive visible light communication system channel modeling device, which comprises:
a memory for storing a computer program;
and the processor is used for realizing the steps of the visible light communication system channel modeling method when executing the computer program.
The beneficial effects are that:
the method models the nonlinear channel of the visible light communication by utilizing the neural network, has higher accuracy than the traditional LS method, and has better fitting effect on the nonlinear channel. The LS method is a linear method, and accurate channel estimation cannot be completed for a nonlinear channel; the invention is applicable to nonlinear channels, and accurate channel estimation can be completed for nonlinear channels.
The modeling method is not only suitable for transmitting signals with different powers, but also suitable for nonlinear channels with different LED bias currents. The traditional modeling method, such as LS method and neural network modeling method without considering various bias currents, is only suitable for channels under single bias current, and when the bias current of the LED changes, the performance of the channel estimation matrix generated by the traditional method can be deteriorated, and the expansibility is not provided. In other words, the conventional method requires regeneration of the channel estimation matrix when the bias current of the LED is changed. The modeling method is suitable for nonlinear channels with different LED bias currents, and when the bias currents of the LEDs change, the channel model finished by the method can still ensure good performance without re-modeling.
Drawings
Fig. 1 is a schematic diagram of a neural network structure.
FIG. 2 is a graph of the relationship between waveform estimation error and signal-to-noise ratio when the bias current is 340mA, using a neural network that is trained for each bias current, to test the accuracy of the neural network channel modeling.
Fig. 3 is a graph of signal-to-noise ratio versus normalized mean square error for a network trained on various bias currents using transmitted signals of different bias currents.
Fig. 4 is a graph of normalized amplitude versus mean square error for a network trained for bias currents of 450mA using transmit signals of different bias currents.
Detailed Description
The invention is further described below with reference to examples and figures.
The embodiment provides a bias self-adaptive visible light communication system nonlinear channel modeling method based on a neural network, which comprises the following steps:
the first step: a uniformly distributed random signal is generated, BPSK modulation is performed on the random signal, and the modulated BPSK signal is referred to as an initial signal x. The initial signal is passed through a high pass filter to filter out the effects of the dc signal. And then up-sampling the signal, and changing the sampling rate of the signal from the initial rate to the sampling rate meeting the DA requirement as a transmitting signal.
And a second step of: after normalization of a floating point type emission signal, the emission signal is quantized to a fixed point number according to the bit number of a DAC, converted to an analog signal through the DAC, amplified by a power amplifier, output with specific power, added with bias current, and input into an LED, and the LED converts the electrical signal into an optical signal for emission. The optical signal is transmitted to a computer after photoelectric conversion and analog-to-digital conversion by a receiving end, and is stored as a file corresponding to the transmitting signal after downsampling and synchronization. The method comprises converting received signal with sampling rate of DA required rate into initial signal with bandwidthThe new received signal r is K times, and the downsampling is completed. When synchronizing, the received signal r is firstly downsampled by K times to generate a signal r consistent with the bandwidth of the initial signal 1 . Find the initial signal x and the signal r 1 Is a cross-correlation sequence V of (2) 1 Finding out the position with the maximum correlation value of the two positions to obtain a symbol synchronization position s 1 Let the related window length be n 1 The method comprises the following steps:
obtaining symbol synchronization position s 1 Then, let the synchronization window length be w, i.e. fetch sequence r 2 ＝[r 1 (s 1 -w)，r 1 (s 1 -w+1)，...，r 1 (s 1 )，...r 1 (s 1 +w)]. Then up-sampling the initial signal x by K times to obtain a signal x 1 At this time signal x 1 Sum signal r 2 Is the same. Find signal x 1 And signal r 2 Is a cross-correlation sequence V of (2) 2 Finding out the position with the maximum correlation value of the two to obtain the phase synchronization position s 2 Let the related window length be n 2 The method comprises the following steps:
s 2 i.e. the synchronization point, the synchronized received sequence y= [ r(s) 2 )，r(s 2 +1)，r(s 2 +2)，...]. Finally, the initial signal x and the received sequence Y are stored in a file. And then changing the transmission power of the transmission signal, repeating the second step to obtain initial signal-receiving sequence combinations with different transmission powers, and storing the initial signal-receiving sequence combinations in corresponding files for training the neural network.
And a third step of: changing the bias current of the LEDs, repeating the second step to obtain initial signal-receiving sequence combinations of different LED bias currents, and storing the initial signal-receiving sequence combinations in corresponding files for training the neural network.
Fourth step: building visible light using neural networkThe communication nonlinear channel model, as shown in fig. 1, the neural network has the structure: input layer-multilayer hidden layer-output layer. The input of the network at the moment i is X i ＝[x(i-N)，...，x(i)，...，x(i+M)，bias(i)] T Wherein bias (i) is X i Corresponding LED bias current. The input-output relationship of each hidden layer of the network is as follows:
where k refers to the kth hidden layer,omega as activation function of hidden layer k B k Is the parameter of hidden layer k. The number of the hidden layers is more than 1, the number of the hidden layers is adjustable, 2-3 layers are generally selected, and the activation function of the hidden layers is as follows:
the number of input layer nodes is n+m+2. Since the bandwidth of the received signal is K times the bandwidth of the original signal, the number of nodes of the output layer is K. In order to optimize the network parameters, the following error indicator function is designed:
where y is the network output and d is the reference data.
Adam learning rate self-adaptive optimization algorithm is adopted for adjusting parameters of the neural network, the initial learning rate is set to be 0.01, and each 8 epochs are reduced by 0.5 times.
The program reads the initial signal and the corresponding received signal from the saved data file. The initial signal and the received signal are converted into toeplitz arrays, corresponding LED bias current is added to the initial signal after toeplitz conversion and then is used as input data X, and corresponding received signal is used as reference data d. And (3) scrambling and rearranging the input data and the reference data, then putting the rearranged data and the rearranged data into a neural network for iteration, and circularly executing the step until the error function is not reduced.
Fig. 2 shows the result of the neural network test after the adjustment, the normalized mean square error NMSE between the predicted value and the real value is an error index function measuring the accuracy of the waveform estimation:
because LEDs require a certain on-current, visible light communication systems often provide a dc bias to the LEDs at the emission end. The non-linear characteristics of the channel are different when operating at different dc biases. The training data used by the training network not only has different transmitting power, but also has different magnitudes of LED bias current. The program reads signals of different bias currents and sends the signals as input data to the network in a disorder way, so that the trained network has worse error of channels under single bias than the network trained by the data of single bias, but has similar modeling error of the channels under each bias, and can be suitable for visible light channels working under different bias currents.
As can be seen from fig. 3 and 4, when the network trains for a single bias current, the test effect on the training bias current signal is excellent, but is not applicable to signals of other bias currents. The network used by the invention for training each bias current can be suitable for signals of different bias currents.
The invention also provides a bias self-adaptive visible light communication system channel modeling device, which comprises:
a transmission signal generation module: the method comprises the steps of generating a random signal, performing BPSK modulation on the random signal, enabling the modulated BPSK signal to be called an initial signal, up-sampling the initial signal, and performing an over-shaping filter on the initial signal to generate a transmission signal;
signal transmitting and receiving module: the transmitting terminal is used for converting the generated transmitting signal into an analog signal through a DAC (digital-to-analog converter), amplifying the analog signal through a power amplifier, outputting the analog signal with different powers, inputting the analog signal into an LED, and converting the electric signal into an optical signal to be transmitted through the LED; the optical signal after sending is finished photoelectric conversion, analog-to-digital conversion by the receiving end and sent to the computer, the computer carries on the downsampling and filtering to the received signal, the bandwidth of the received signal after downsampling is K times of the original signal bandwidth; then, synchronizing the down-sampled received signals; changing the bias current of the LED at the transmitting module, repeating the transmitting and receiving steps to obtain different transmitting signal-receiving signal combinations;
the neural network training module: converting the initial signal and the received signal into a Toeplitz array, adding corresponding LED bias current into the initial signal after Toeplitz conversion, and taking the initial signal and the received signal as input data X and the corresponding received signal as reference data d; and (3) scrambling and rearranging the input data and the reference data, then putting the rearranged data and the rearranged data into a neural network for iteration, and circularly executing the step until the error function is not reduced.
The invention also provides a bias self-adaptive visible light communication system channel modeling device, which comprises:
a memory for storing a computer program;
and the processor is used for realizing the steps of the visible light communication system channel modeling method when executing the computer program.
The present invention is capable of other and further embodiments and its several details are capable of modification and variation in light of the present invention, as will be apparent to those skilled in the art, without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. A bias self-adaptive visible light communication system channel modeling method is characterized in that a neural network is utilized to model a nonlinear channel of visible light communication, training data used by the neural network are visible light system transmitting signals with different transmitting powers and different bias currents, and reference data are corresponding receiving signals.
2. The bias adaptive channel modeling method of a visible light communication system as claimed in claim 1, wherein said generating step of said transmission signal comprises: generating a random signal, performing BPSK modulation on the random signal, enabling the modulated BPSK signal to be called an initial signal, up-sampling the initial signal, and performing an over-shaping filter on the initial signal to generate a transmission signal.
3. The bias adaptive channel modeling method of a visible light communication system as claimed in claim 1, wherein said received signal generating step comprises:
converting the generated transmitting signal into an analog signal at a transmitting end through a DAC, amplifying the analog signal through a power amplifier, outputting the analog signal with different powers, inputting the analog signal into an LED, and converting an electric signal into an optical signal by the LED for transmitting; the optical signal after sending is finished photoelectric conversion, analog-to-digital conversion by the receiving end and sent to the computer, the computer carries on the downsampling and filtering to the received signal, the bandwidth of the received signal after downsampling is K times of the original signal bandwidth; then, synchronizing the down-sampled received signals;
and changing the bias current of the LED, and repeating the steps to obtain a corresponding receiving signal.
4. The method for modeling a channel of a bias-adaptive visible light communication system according to claim 2, wherein the initial signal at the time i is converted into a toeplitz matrix, and the toeplitz initial signal is added with a corresponding LED bias current to be used as training data X of a neural network at the time i i The method comprises the steps of carrying out a first treatment on the surface of the The corresponding reception signal of the toeplitz i is used as the reference data of the neural network at the time i.
5. The bias-adaptive channel modeling method of a visible light communication system according to claim 1, wherein the neural network has a structure as follows: input layer-multilayer hidden layer-output layer, wherein the activation function of the hidden layer is:
6. the bias adaptive channel modeling method of a visible light communication system according to claim 1, wherein in the process of training the neural network, an Adam learning rate adaptive optimization algorithm is adopted for adjusting parameters of the neural network, and an initial learning rate is set to be 0.01, and each 8 epochs are reduced by 0.5 times.
7. An offset-adaptive visible light communication system channel modeling apparatus, comprising:
a transmission signal generation module: the method comprises the steps of generating a random signal, performing BPSK modulation on the random signal, enabling the modulated BPSK signal to be called an initial signal, up-sampling the initial signal, and performing an over-shaping filter on the initial signal to generate a transmission signal;
signal transmitting and receiving module: the transmitting terminal is used for converting the generated transmitting signal into an analog signal through a DAC (digital-to-analog converter), amplifying the analog signal through a power amplifier, outputting the analog signal with different powers, inputting the analog signal into an LED, and converting the electric signal into an optical signal to be transmitted through the LED; the optical signal after sending is finished photoelectric conversion, analog-to-digital conversion by the receiving end and sent to the computer, the computer carries on the downsampling and filtering to the received signal, the bandwidth of the received signal after downsampling is K times of the original signal bandwidth; then, synchronizing the down-sampled received signals; changing the bias current of the LED at the transmitting module, repeating the transmitting and receiving steps to obtain different transmitting signal-receiving signal combinations;
the neural network training module: converting the initial signal and the received signal into a Toeplitz array, adding corresponding LED bias current into the initial signal after Toeplitz conversion, and taking the initial signal and the received signal as input data X and the corresponding received signal as reference data d; and (3) scrambling and rearranging the input data and the reference data, then putting the rearranged data and the rearranged data into a neural network for iteration, and circularly executing the step until the error function is not reduced.
8. An offset-adaptive visible light communication system channel modeling apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for modeling a channel of a visible light communication system according to any one of claims 1 to 6 when executing said computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310768508.5A CN116707688A (en) | 2023-06-28 | 2023-06-28 | Bias self-adaptive visible light communication system channel modeling method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310768508.5A CN116707688A (en) | 2023-06-28 | 2023-06-28 | Bias self-adaptive visible light communication system channel modeling method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116707688A true CN116707688A (en) | 2023-09-05 |
Family
ID=87839034
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310768508.5A Pending CN116707688A (en) | 2023-06-28 | 2023-06-28 | Bias self-adaptive visible light communication system channel modeling method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116707688A (en) |
-
2023
- 2023-06-28 CN CN202310768508.5A patent/CN116707688A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111245512B (en) | Nonlinear channel modeling method of visible light communication system based on neural network | |
| CN107359935B (en) | A kind of ultraviolet scatter communication system of non line of sight based on step-by-step counting and its method | |
| CN111525955B (en) | Visible light communication balancing method and system based on sparse Bayesian learning | |
| Uhlemann et al. | Deep-learning autoencoder for coherent and nonlinear optical communication | |
| CN107210814A (en) | The electronic equipment related to photovoltaic module for optimizing VLC type transmitted in both directions flows | |
| CN105099553A (en) | Visible light communication receiving method and system based on neural network | |
| CN112242969A (en) | Novel single-bit OFDM receiver based on model-driven deep learning | |
| CN106941463A (en) | A kind of single-bit quantification mimo system channel estimation methods and system | |
| CN102035602B (en) | Optimal channel coding modulation-based adaptive optical transmission system and method | |
| CN115102616A (en) | Underwater wireless green light communication transmission system based on plastic optical fiber extension communication link | |
| Kafizov et al. | Probabilistic shaping-based spatial modulation for spectral-efficient VLC | |
| CN110365414A (en) | A kind of enhanced smooth modulating method being suitable for lognormal Turbulence Channels | |
| CN116707688A (en) | Bias self-adaptive visible light communication system channel modeling method and system | |
| CN116827444A (en) | FTN-MIMO wireless optical communication method based on ladder code | |
| MXPA02008400A (en) | Application of digital processing scheme for enhanced cable television network performance. | |
| CN115987397A (en) | Flexible rate adjustment access network system based on bidirectional constellation probability shaping | |
| CN204948075U (en) | A kind of visible light communication receiving system based on neuroid | |
| CN112187318B (en) | Pulse noise reduction method based on deep learning | |
| CN113285763A (en) | Diversity receiving method in blue-green LED communication | |
| Nabavi et al. | Conformal VLC receivers with photodetector arrays: Design, analysis and prototype | |
| CN113612540A (en) | Amplitude-phase OFDM modulation method for wireless optical communication system | |
| CN112019295A (en) | Orthogonal mode multiplexing transmission method based on three-dimensional pulse amplitude position modulation | |
| CN114650100B (en) | 16-CAP mapping transmission method with adjustable constellation point probability | |
| Nayak et al. | A review on PAPR reduction techniques in OFDM system | |
| Guerra-Yánez et al. | Experimental evaluation of a hermite function-based multicarrier scheme for VLC |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |