CN116798210A - Optical divider control system based on 5G signal - Google Patents
Optical divider control system based on 5G signal Download PDFInfo
- Publication number
- CN116798210A CN116798210A CN202310825297.4A CN202310825297A CN116798210A CN 116798210 A CN116798210 A CN 116798210A CN 202310825297 A CN202310825297 A CN 202310825297A CN 116798210 A CN116798210 A CN 116798210A
- Authority
- CN
- China
- Prior art keywords
- signal
- optical splitter
- control
- module
- received
- 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
- 230000003287 optical effect Effects 0.000 title claims abstract description 115
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000011217 control strategy Methods 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 24
- 238000013528 artificial neural network Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 14
- 238000010801 machine learning Methods 0.000 claims description 10
- 239000010410 layer Substances 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 239000003623 enhancer Substances 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 239000002356 single layer Substances 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/06—Receivers
- H04B1/16—Circuits
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Signal Processing (AREA)
- Optical Communication System (AREA)
Abstract
The invention relates to the technical field of optical splitters, in particular to an optical splitter control system based on a 5G signal, which comprises an optical splitter, a control module and a 5G signal receiving device; the control module is connected to the 5G signal receiving device and is used for receiving a control signal sent by a 5G network; the control module controls the optical splitter to work based on the received control signal; the control module is provided with a processor, a memory and a control program embedded in the processor, wherein the control program comprises an instruction analysis module for analyzing control instructions in the received 5G signal and an instruction execution module for controlling the optical splitter according to analysis results. The invention realizes the real-time, remote and intelligent control of the optical splitter, improves the working efficiency and stability of the optical splitter, and has higher use flexibility and convenience.
Description
Technical Field
The invention relates to the technical field of optical splitters, in particular to an optical splitter control system based on 5G signals.
Background
Optical splitters (optical splitters) are a key device in optical networks for splitting incident light into two or more output lights, which have wide application in the fields of optical communications, optical fiber sensors, optical computing, etc., however, the control of optical splitters is mainly dependent on conventional methods, such as manual adjustment or automatic control based on limited rules, which are often difficult to cope with complex working environments and demands.
With the development of 5G communication technology, the characteristics of high speed, large bandwidth and low time delay provide possibility for remote and real-time control of the optical splitter, however, how to effectively use the 5G signal to control the optical splitter remains an unsolved problem.
In addition, with the development of artificial intelligence techniques, particularly deep learning and bayesian inference algorithms, intelligent device control is possible, these algorithms can learn from a large amount of historical data and then predict and decide the optimal control strategy, however, how to combine 5G signals to achieve intelligent control of the optical splitter is also an unsolved problem.
Therefore, in order to solve the above problems, we propose an optical splitter control system based on a 5G signal, which combines a 5G communication technology, deep learning and bayesian inference algorithm, and can realize remote, real-time and intelligent control of an optical splitter.
Disclosure of Invention
In view of the above, the present invention is directed to an optical splitter control system based on 5G signals, so as to solve the problem that the conventional manual adjustment or the automatic control based on the limited rule is difficult to cope with the complex working environment and the requirement.
Based on the above purpose, the invention provides an optical splitter control system based on a 5G signal.
An optical divider control system based on 5G signals comprises an optical divider, a control module and a 5G signal receiving device;
the control module is connected to the 5G signal receiving device and is used for receiving a control signal sent by a 5G network;
the control module controls the optical splitter to work based on the received control signal;
the control module is provided with a processor, a memory and a control program embedded in the processor, wherein the control program comprises an instruction analysis module for analyzing control instructions in the received 5G signal and an instruction execution module for controlling the optical splitter according to analysis results.
Further, the 5G signal receiving apparatus includes one or more antennas, a receiver, a demodulator, and an enhancer;
the antenna is used for receiving 5G signals;
the receiver is used for converting the received 5G signal into an electric signal;
the demodulator is used for demodulating the enhanced electric signal to obtain a control instruction;
the enhancer is used for enhancing the electric signal.
Further, the 5G signal receiving apparatus further includes a multi-antenna receiving module, which improves the signal receiving quality by combining the 5G signals received by the multiple antennas, and the multi-antenna receiving module adopts a maximum ratio combining (Maximal Ratio Combining, MRC) technique, and realizes optimal signal combining by balancing the signal quality received by each antenna.
Further, the control module further comprises an interface conversion module, which is used for converting the control instruction obtained by analysis into a control signal which can be identified by the optical splitter.
Further, the optical splitter comprises an input port, an output port and an optical path switching device, the input port receives an input optical signal, the output port outputs the optical signal processed by the optical path switching device, and the optical path switching device switches the input optical signal according to a control signal sent by the control module.
Further, the control module further comprises a feedback module for feeding back the working state of the optical splitter to the 5G network, and the feedback module comprises a state acquisition module for acquiring the working state information of the optical splitter; and the state transmission module is used for transmitting the collected working state information through a 5G network, the state collection module comprises a sensor and is used for monitoring the physical states of the optical splitter, such as temperature, pressure, vibration and the like in real time and feeding back the information to the control module, and the state transmission module uses an uplink of the 5G network so as to support real-time and high-speed state information transmission.
Further, the control module further comprises a machine learning unit which learns and predicts a possible future working state and an optimal control strategy according to the historical working state of the optical splitter and the received control instruction by using a machine learning algorithm, and the machine learning unit comprises a training sub-module and a prediction sub-module;
the training submodule trains according to the historical working state of the optical splitter and the received control instruction to generate a model, and the training submodule is based on a deep learning algorithm;
the prediction submodule predicts the future possible working state of the optical splitter and an optimal control strategy by using the generated model, and the prediction submodule provides probabilistic trust degree for a prediction result by using a Bayesian inference algorithm in the prediction process so as to more accurately guide the working of the optical splitter.
Further, the 5G signal receiving apparatus further includes a filter, configured to filter out non-5G signals, where the filter is a band-pass filter, and configured to filter out 5G signals in a specified frequency band, and a passband frequency range of the band-pass filter may be dynamically adjusted to adapt to a frequency allocation change of the 5G network.
Further, in the training submodule, the training is specifically performed by using a Deep Neural Network (DNN), and considering a single-layer fully connected neural network, we can calculate by using the following formula:
y = σ(Wx + b)
where x is the state and control command input, W and b are the weights and biases of the neural network, respectively, σ is a nonlinear activation function, e.g., a ReLU function, y is the output of the network, representing the predicted operating state and control strategy;
the deep neural network is formed by stacking a plurality of layers, and the output of each layer becomes the input of the next layer;
during training we use a back-propagation algorithm to update the weights W and the bias b to minimize the prediction error, which can be measured by the following loss function L:
L = 1/N ∑ (y_true - y_pred)^2
wherein y_true is the actual working state and control strategy, y_pred is the prediction result of the neural network, and N is the number of training samples;
in the prediction sub-module, a trained neural network model is used for inputting the current state and control instructions, so that the predicted working state and control strategy can be obtained.
Further, the bayesian inference algorithm is specifically configured to estimate and predict the unknown parameters: let us assume that we need to infer the parameter θ, and that the observed data is D, calculated using the following formula:
P(θ | D) = P(D | θ)P(θ) / P(D)
where P (θ|d) is a posterior probability representing a probability distribution of the parameter θ given the observed data D; p (d|θ) is a likelihood function representing the probability that data D is observed given the parameter θ; p (θ) is a priori probability representing the probability distribution of the parameter θ before there is no observation; p (D) is evidence, representing the probability that data D is observed at all possible parameter values;
in particular, in the present invention, we can consider the observed data D as a 5G signal received by the 5G signal receiving means, and the real-time working state of the optical splitter, such as temperature, pressure, vibration, etc.; the parameter θ can be regarded as a control strategy of the optical splitter;
according to historical data, the prior probability P (theta) is calculated, then the likelihood function P (D|theta) is calculated according to the newly received 5G signal and the real-time working state of the optical splitter, then the posterior probability P (theta|D) is calculated according to a Bayesian formula, and the control strategy with the maximum posterior probability is selected as the current control strategy.
The invention has the beneficial effects that:
the invention has real-time performance and remote control: the optical splitter control system based on the 5G signals utilizes the characteristics of high speed, large bandwidth and low time delay of the 5G network, realizes real-time and remote control of the optical splitter, and greatly improves the use flexibility and convenience of the optical splitter.
The invention has intelligent control: by combining deep learning and Bayesian inference algorithm, the system can learn from historical data and dynamically determine the optimal control strategy according to the real-time 5G signal and the working state of the optical splitter. The intelligent control mode can effectively cope with complex working environments and demands, and improves the working efficiency and stability of the optical splitter.
The invention has strong adaptability: the optical splitter control system comprises the signal intensity detection module, can be adjusted according to the real-time signal intensity, and enhances the adaptability of the system to the signal intensity change.
The invention has accurate signal selection: by introducing a band pass filter, the system can accurately select and process 5G signals, and the passband frequency range of the filter can be dynamically adjusted to accommodate frequency allocation variations of the 5G network.
The invention has the advantages of system optimization: the machine learning module of the system can learn and optimize according to actual feedback information, and control efficiency and accuracy of the system are continuously improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a system logic block diagram of an embodiment of the present invention;
fig. 2 is a schematic diagram of a signal receiving apparatus according to an embodiment of the invention;
fig. 3 is a schematic diagram of a control module according to an embodiment of the invention.
Description of the embodiments
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
Referring to fig. 1-3, an optical splitter control system based on a 5G signal includes an optical splitter, a control module, and a 5G signal receiving device;
the control module is connected to the 5G signal receiving device and is used for receiving a control signal sent by a 5G network;
the control module controls the optical splitter to work based on the received control signal;
the control module is provided with a processor, a memory and a control program embedded in the processor, wherein the control program comprises an instruction analysis module for analyzing control instructions in the received 5G signal and an instruction execution module for controlling the optical splitter according to analysis results.
Further, the 5G signal receiving apparatus includes one or more antennas, a receiver, a demodulator, and an enhancer;
the antenna is used for receiving 5G signals;
the receiver is used for converting the received 5G signal into an electric signal;
the demodulator is used for demodulating the enhanced electric signal to obtain a control instruction;
the enhancer is used for enhancing the electric signal, and the enhancer adopts a self-adaptive gain control technology, so that the gain can be dynamically adjusted according to the strength of the received electric signal, and the quality and stability of the signal are improved.
Further, the 5G signal receiving apparatus further includes a multi-antenna receiving module, which improves the signal receiving quality by combining the 5G signals received by the multiple antennas, and the multi-antenna receiving module adopts a maximum ratio combining (Maximal Ratio Combining, MRC) technique, and realizes optimal signal combining by balancing the signal quality received by each antenna.
Further, the control module further comprises an interface conversion module, which is used for converting the control instruction obtained by analysis into a control signal which can be identified by the optical splitter.
Further, the optical splitter comprises an input port, an output port and an optical path switching device, the input port receives an input optical signal, the output port outputs the optical signal processed by the optical path switching device, and the optical path switching device switches the input optical signal according to a control signal sent by the control module.
Further, the control module further comprises a feedback module for feeding back the working state of the optical splitter to the 5G network, and the feedback module comprises a state acquisition module for acquiring the working state information of the optical splitter; the state transmission module is used for transmitting the collected working state information through a 5G network, the state collection module comprises a sensor and is used for monitoring the physical states of the optical splitter, such as temperature, pressure, vibration and the like in real time and feeding the information back to the control module, the state transmission module uses an uplink of the 5G network to support real-time and high-speed state information transmission, the control module further comprises a threshold judgment module, when the collected working state information exceeds a preset threshold, the threshold judgment module starts an early warning or protecting program to ensure the safe operation of the optical splitter, and the threshold adopted by the threshold judgment module is dynamic and is dynamically adjusted according to the prediction result of the self-learning module and the actually collected working state information.
Further, the control module further comprises a machine learning unit which learns and predicts a possible future working state and an optimal control strategy according to the historical working state of the optical splitter and the received control instruction by using a machine learning algorithm, and the machine learning unit comprises a training sub-module and a prediction sub-module;
the training submodule trains according to the historical working state of the optical divider and the received control instruction to generate a model, and the training submodule can effectively learn and abstract the working state of the optical divider and the complex mode of the received control instruction based on a deep learning algorithm;
the prediction sub-module predicts the future possible working state of the optical splitter and an optimal control strategy by using the generated model, and provides probabilistic trust degree for a prediction result by using a Bayesian inference algorithm in the prediction process so as to more accurately guide the working of the optical splitter.
Further, the 5G signal receiving apparatus further includes a filter, configured to filter out non-5G signals, where the filter is a band-pass filter, and configured to filter out 5G signals in a specified frequency band, and a passband frequency range of the band-pass filter may be dynamically adjusted to adapt to a frequency allocation change of the 5G network, and the 5G signal receiving apparatus further includes a signal strength detection module, configured to detect a strength of a received 5G signal and feed back signal strength information to the control module, and the control module includes a signal processing module, configured to adjust an operating state of the optical splitter according to the fed back signal strength information, so as to adapt to a change of the signal strength.
Further, in the training submodule, the training is specifically performed by using a Deep Neural Network (DNN), and considering a single-layer fully connected neural network, we can calculate by using the following formula:
y = σ(Wx + b)
where x is the state and control command input, W and b are the weights and biases of the neural network, respectively, σ is a nonlinear activation function, e.g., a ReLU function, y is the output of the network, representing the predicted operating state and control strategy;
the deep neural network is formed by stacking a plurality of layers, and the output of each layer becomes the input of the next layer;
during training we use a back-propagation algorithm to update the weights W and the bias b to minimize the prediction error, which can be measured by the following loss function L:
L = 1/N ∑ (y_true - y_pred)^2
where y_true is the actual working state and control strategy, y_pred is the predicted result of the neural network, and N is the number of training samples.
The specific implementation mode is as follows:
input: our input data x is the 5G signal received by the 5G signal receiving device and the real-time operating state of the optical splitter, which may include information about the temperature, pressure, vibration, etc. of the optical splitter.
Neural network calculation: we use a deep neural network for the calculation, with a specific formula y=σ (wx+b). Wherein σ is a nonlinear activation function, such as a ReLU function. W and b are the weights and biases, respectively, of the neural network, which are continually updated during the training process to minimize prediction errors.
And (3) outputting: the output y of the neural network is the predicted operating state of the optical splitter and the optimal control strategy. The output is sent to a control module, which generates control instructions for the optical splitter based on the prediction.
In the training process we use historical data including the past 5G signal, the operating state of the optical splitter and the current control strategy. We train the neural network with these data so that the neural network can learn from the historical data how to predict the operating state of the optical splitter and the optimal control strategy.
During the training process, we want the predicted outcome y_pred of the neural network to be as close as possible to the actual outcome y_true, we achieve this goal by minimizing the following loss function L:
L = 1/N ∑ (y_true - y_pred)^2
where N is the number of training samples.
In the prediction sub-module, a trained neural network model is used for inputting the current state and control instructions, so that the predicted working state and control strategy can be obtained.
Further, the bayesian inference algorithm is specifically configured to estimate and predict the unknown parameters: let us assume that we need to infer the parameter θ, and that the observed data is D, calculated using the following formula:
P(θ | D) = P(D | θ)P(θ) / P(D)
where P (θ|d) is a posterior probability representing a probability distribution of the parameter θ given the observed data D; p (d|θ) is a likelihood function representing the probability that data D is observed given the parameter θ; p (θ) is a priori probability representing the probability distribution of the parameter θ before there is no observation; p (D) is evidence, representing the probability that data D is observed at all possible parameter values;
in particular, in the present invention, we can consider the observed data D as a 5G signal received by the 5G signal receiving means, and the real-time working state of the optical splitter, such as temperature, pressure, vibration, etc.; the parameter θ can be regarded as a control strategy of the optical splitter;
according to historical data, calculating prior probability P (theta), then calculating likelihood function P (D|theta) according to the newly received 5G signal and the real-time working state of the optical splitter, and then calculating posterior probability P (theta|D) according to a Bayesian formula, and selecting a control strategy with the maximum posterior probability as a current control strategy;
the method has the advantages that the control strategy can be dynamically updated each time new 5G signals and the working state information of the optical splitter are received, so that the control strategy can always reflect the latest information. Furthermore, since bayesian inference is a probabilistic method, uncertainty and noise of signals and operating state information can be handled well.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (10)
1. The optical splitter control system based on the 5G signal is characterized by comprising an optical splitter, a control module and a 5G signal receiving device;
the control module is connected to the 5G signal receiving device and is used for receiving a control signal sent by a 5G network;
the control module controls the optical splitter to work based on the received control signal;
the control module is provided with a processor, a memory and a control program embedded in the processor, wherein the control program comprises an instruction analysis module for analyzing control instructions in the received 5G signal and an instruction execution module for controlling the optical splitter according to analysis results.
2. The 5G signal based optical splitter control system of claim 1, wherein the 5G signal receiving means comprises one or more antennas, a receiver, a demodulator, and an enhancer;
the antenna is used for receiving 5G signals;
the receiver is used for converting the received 5G signal into an electric signal;
the demodulator is used for demodulating the enhanced electric signal to obtain a control instruction;
the enhancer is used for enhancing the electric signal.
3. The optical splitter control system according to claim 2, wherein the 5G signal receiving device further comprises a multi-antenna receiving module, the multi-antenna receiving module improves the signal receiving quality by combining the 5G signals received by the plurality of antennas, and the multi-antenna receiving module adopts a maximum ratio combining technology to achieve optimal signal combining by balancing the signal quality received by each antenna.
4. The optical splitter control system based on the 5G signal according to claim 1, wherein the control module further includes an interface conversion module, configured to convert the control instruction obtained by parsing into a control signal that can be identified by the optical splitter.
5. The 5G signal-based optical splitter control system of claim 1, wherein the optical splitter includes an input port, an output port, and an optical path switching device, the input port receives an input optical signal, the output port outputs an optical signal processed by the optical path switching device, and the optical path switching device switches the input optical signal according to a control signal sent by the control module.
6. The optical splitter control system based on the 5G signal according to claim 1, wherein the control module further comprises a feedback module for feeding back the working state of the optical splitter to the 5G network, and the feedback module comprises a state acquisition module for acquiring the working state information of the optical splitter; and a state transmission module for transmitting the collected working state information through the 5G network.
7. The 5G signal-based optical splitter control system of claim 1, wherein the control module further comprises a machine learning unit that learns and predicts a future possible operating state and an optimal control strategy based on a historical operating state of the optical splitter and the received control instructions using a machine learning algorithm, the machine learning unit comprising a training sub-module and a prediction sub-module;
the training submodule trains according to the historical working state of the optical splitter and the received control instruction to generate a model, and the training submodule is based on a deep learning algorithm;
the prediction submodule predicts the future possible working state of the optical splitter and an optimal control strategy by using the generated model, and the prediction submodule provides probabilistic trust degree for a prediction result by using a Bayesian inference algorithm in the prediction process so as to more accurately guide the working of the optical splitter.
8. A 5G signal based optical splitter control system according to claim 3, wherein the 5G signal receiving device further comprises a filter for filtering out non-5G signals, the filter is a band-pass filter, 5G signals with specified frequency bands can be filtered out, and a passband frequency range of the band-pass filter can be dynamically adjusted to adapt to a frequency allocation change of the 5G network.
9. The 5G signal-based optical splitter control system of claim 7, wherein the training sub-module is specifically configured to train with a Deep Neural Network (DNN), and wherein considering a single-layer fully-connected neural network, we can calculate using the following formula:
y = σ(Wx + b)
where x is the state and control command input, W and b are the weights and biases of the neural network, respectively, σ is a nonlinear activation function, e.g., a ReLU function, y is the output of the network, representing the predicted operating state and control strategy;
the deep neural network is formed by stacking a plurality of layers, and the output of each layer becomes the input of the next layer;
during training we use a back-propagation algorithm to update the weights W and the bias b to minimize the prediction error, which can be measured by the following loss function L:
L = 1/N ∑ (y_true - y_pred)^2
where y_true is the actual working state and control strategy, y_pred is the predicted result of the neural network, and N is the number of training samples.
10. The optical splitter control system according to claim 7, wherein the bayesian inference algorithm is configured to estimate and predict the unknown parameters specifically by: let us assume that we need to infer the parameter θ, and that the observed data is D, calculated using the following formula:
P(θ | D) = P(D | θ)P(θ) / P(D)
where P (θ|d) is a posterior probability representing a probability distribution of the parameter θ given the observed data D; p (d|θ) is a likelihood function representing the probability that data D is observed given the parameter θ; p (θ) is a priori probability representing the probability distribution of the parameter θ before there is no observation; p (D) is evidence, representing the probability that data D is observed at all possible parameter values;
in particular, in the present invention, we can consider the observed data D as a 5G signal received by the 5G signal receiving means, and the real-time working state of the optical splitter, such as temperature, pressure, vibration, etc.; the parameter θ can be regarded as a control strategy of the optical splitter;
according to historical data, calculating prior probability P (theta), then calculating likelihood function P (D|theta) according to the newly received 5G signal and the real-time working state of the optical splitter, and then calculating posterior probability P (theta|D) according to a Bayesian formula, and selecting a control strategy with the maximum posterior probability as a current control strategy;
the method has the advantages that the control strategy can be dynamically updated when new 5G signals and the working state information of the optical splitter are received each time, so that the control strategy can always reflect the latest information; furthermore, since bayesian inference is a probabilistic method, uncertainty and noise of signals and operating state information can be handled well.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310825297.4A CN116798210A (en) | 2023-07-06 | 2023-07-06 | Optical divider control system based on 5G signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310825297.4A CN116798210A (en) | 2023-07-06 | 2023-07-06 | Optical divider control system based on 5G signal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116798210A true CN116798210A (en) | 2023-09-22 |
Family
ID=88041916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310825297.4A Pending CN116798210A (en) | 2023-07-06 | 2023-07-06 | Optical divider control system based on 5G signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116798210A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN214228264U (en) * | 2021-02-09 | 2021-09-17 | 中山早稻田科技有限公司 | Real-time remote network converter for robot |
| CN115486132A (en) * | 2020-05-07 | 2022-12-16 | 索尼集团公司 | Communication device, infrastructure equipment and method |
| CN115567679A (en) * | 2022-07-01 | 2023-01-03 | 江苏中科未来科学研究院有限公司 | Image acquisition processing system based on 5G transmission technology |
| CN115767860A (en) * | 2022-11-06 | 2023-03-07 | 深圳市赛欧菲照明科技有限公司 | Control method, device and equipment of roadway lamp and storage medium |
| CN116347723A (en) * | 2023-03-31 | 2023-06-27 | 温州市迈卡威电器有限公司 | Control system of sound control type wall switch with adjustable lamplight sample color |
-
2023
- 2023-07-06 CN CN202310825297.4A patent/CN116798210A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115486132A (en) * | 2020-05-07 | 2022-12-16 | 索尼集团公司 | Communication device, infrastructure equipment and method |
| CN214228264U (en) * | 2021-02-09 | 2021-09-17 | 中山早稻田科技有限公司 | Real-time remote network converter for robot |
| CN115567679A (en) * | 2022-07-01 | 2023-01-03 | 江苏中科未来科学研究院有限公司 | Image acquisition processing system based on 5G transmission technology |
| CN115767860A (en) * | 2022-11-06 | 2023-03-07 | 深圳市赛欧菲照明科技有限公司 | Control method, device and equipment of roadway lamp and storage medium |
| CN116347723A (en) * | 2023-03-31 | 2023-06-27 | 温州市迈卡威电器有限公司 | Control system of sound control type wall switch with adjustable lamplight sample color |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111954228B (en) | Beam management method, beam management device, electronic equipment and computer readable storage medium | |
| CN109525299B (en) | Satellite communication system and communication method for adaptive coding modulation optimization | |
| Haykin | Cognitive dynamic systems | |
| CN110933638B (en) | Heterogeneous network access selection strategy method applied to vehicle following queue | |
| WO2020246918A1 (en) | Neural network circuit remote electrical tilt antenna infrastructure management based on probability of actions | |
| Yan et al. | Reinforcement learning-based mobile edge computing and transmission scheduling for video surveillance | |
| CN116599602B (en) | Low-energy-consumption long-distance sonar communication system for ocean monitoring | |
| CN116798210A (en) | Optical divider control system based on 5G signal | |
| CN117674422A (en) | Automatic power dispatching monitoring system with alarm function | |
| CN111417124A (en) | Method for sensing frequency spectrum in cognitive wireless network environment | |
| CN117945226A (en) | Intelligent yarn winding system and method based on intelligent control | |
| CA3103025A1 (en) | Disturbance detection for transport links | |
| CN116166444B (en) | Collaborative reasoning method oriented to deep learning hierarchical model | |
| CN110082757B (en) | Cognitive radar information processing platform architecture based on big data feature matching technology | |
| US12088358B2 (en) | Predictive quality of service via channel aggregation | |
| Alhassan et al. | Towards Congestion Control Approach Based on Weighted Random Early Detection and Type-2 Fuzzy Logic System | |
| CN112512062B (en) | Intelligent anti-interference method for communication system | |
| CN115987406A (en) | Underwater acoustic communication link self-adaption method based on deep reinforcement learning | |
| CN115987446A (en) | IRS communication anti-interference strategy analysis system and method with uncertain double information | |
| CN115021399A (en) | Topology identification method and device adaptive to park multi-energy power supply network | |
| Chakraborty et al. | ANFIS based opportunistic power control for cognitive radio in spectrum sharing | |
| Haykin | Cognitive dynamic systems | |
| CN116528280A (en) | Method for predicting and avoiding wireless communication interference based on interception of wireless device communication | |
| CN117741590B (en) | Distance interference confusion system and method | |
| CN117580124B (en) | Routing protocol system and method for wireless ad hoc network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230922 |