Intelligent optical fiber distribution system based on fault alarm

Abstract

The invention relates to the technical field of optical fiber distribution management, provides an intelligent optical fiber distribution system based on fault alarm, and aims to improve the fault detection and management capability of an optical fiber network. The system combines a multi-scale convolution kernel, a spatial transformation network and a deep separable convolution U-Net model, and provides more accurate and efficient feature extraction. Besides, the control module introduces an epsilon-greedy strategy of noise injection on the basis of Dueling-DQN and DDPG algorithms so as to optimize an optical fiber connection path and flow distribution. The system not only enhances the recognition capability of complex fault modes, but also realizes intelligent decision support in a dynamic environment; the method has remarkable practical value in optical fiber distribution management, and more reliable network service is provided for users.

Description

Technical Field

[0001] The present invention relates to the technical field of optical fiber wiring management, and in particular to an intelligent optical fiber wiring system based on fault alarm. Background Art

[0002] The intelligent fiber optic wiring system is a modern communication infrastructure management support system that integrates fiber optic communication technology and intelligent network management system. It realizes dynamic management, real-time monitoring and efficient configuration of fiber optic networks through automation and intelligent technology. Traditional intelligent fiber optic wiring systems often rely on predefined rules when extracting features, and can only extract some significant features, failing to deeply explore the complex patterns in the data. The data of the fiber optic network often has temporal and spatial dependencies. However, the traditional intelligent fiber optic wiring system cannot fully capture the spatiotemporal characteristics of network data. In the control module, when facing a complex and dynamic fiber optic network environment, the traditional decision-making method of the traditional intelligent fiber optic wiring system often cannot quickly find the optimal solution, resulting in inefficient resource allocation and traffic distribution. When facing sudden failures or traffic changes in the network, it is often impossible to make real-time adjustments, resulting in reduced system performance or expanded network failures. Therefore, a more intelligent fiber optic wiring system is urgently needed to improve the real-time response capability, adaptability and fault recovery capability of the intelligent fiber optic wiring system. Summary of the invention

[0003] For an intelligent fiber optic wiring system based on fault alarm, a U-Net model combining multi-scale convolution kernels, spatial transformation networks and deep separable convolutions is proposed in feature engineering; this technology can more effectively extract multi-level features in fiber optic data, which not only enhances the ability to capture high-frequency features, but also improves the recognition rate of different fault modes, significantly improving the fault management efficiency of the fiber optic wiring system; in terms of the control module of the intelligent fiber optic wiring system, the present invention combines the ε-greedy strategy of noise injection, Dueling-DQN and DDPG, which can enhance the stability and flexibility of control decisions in complex environments, so that the intelligent fiber optic wiring system can still effectively adjust the fiber connection path and traffic distribution when facing dynamically changing network states, and will not fall into the local optimal solution; by comprehensively considering environmental noise and uncertainty, the present invention optimizes the adaptability of the control strategy, thereby improving the overall performance and reliability of the intelligent fiber optic wiring system, and providing users with a more intelligent and efficient solution.

[0004] The present invention provides an intelligent optical fiber wiring system based on fault alarm, which is characterized by comprising a data acquisition module, a feature engineering module, and a control module;

[0005] A data collection module collects connection status data, traffic load data, and fault alarm data of the optical fiber network as a data set;

[0006] Feature engineering module, build U-Net model, combine multi-scale convolution kernel, spatial transformation network and depth separable convolution on the basis of U-Net model, build MS-STS-DS-U-Net model, use MS-STS-DS-U-Net model to extract features of data set and generate enhanced data set; MS-STS-DS-U-Net model includes encoder and decoder;

[0007] The control module combines the ε-greedy strategy of noise injection, Dueling-DQN and DDPG to construct the NI-ε-G-D3S algorithm. The enhanced data set is analyzed by the NI-ε-G-D3S algorithm to generate the optimal control decision. According to the optimal control decision, instructions are issued to adjust the configuration of the optical fiber connection path and the traffic distribution.

[0008] Furthermore, the feature engineering module uses the MS-STS-DS-U-Net model to extract features from the dataset and generate an enhanced dataset, which specifically includes the following steps:

[0009] Step S1: Data preprocessing: performing spectrum subtraction and feature alignment on the data set to obtain a preprocessed data set;

[0010] Step S2: signal processing: the preprocessed data set is processed by the MS-STS-DS-U-Net model to separate the single event signal, the MS-STS-DS-U-Net model specifically includes extracting feature units, compressing information units and reconstructing signal units;

[0011] Step S3: Enhanced data set generation: Convert a single event signal into a time-frequency image through short-time Fourier transform, extract the frequency and time features in the single event signal, and obtain time-frequency feature data; establish an AlexNet model, introduce temperature parameters in the SoftMax layer of the AlexNet model, construct an improved AlexNet model, use the improved AlexNet model to analyze the time-frequency feature data, and generate an enhanced data set.

[0012] Furthermore, the steps of extracting the feature unit in step S2 specifically include:

[0013] Step M1: Input the preprocessed data set into the multi-scale convolution layer in the encoder, extract the fault signal features through three convolution kernels of 3x3, 5x5, and 7x7, capture the frequency and intensity changes of different scales in the fault signal features, and obtain the convolution feature data;

[0014] Step M2: Process the convolution feature data through a Sinc filter and a ReLU activation function to obtain nonlinear feature data;

[0015] Step M3: Pass the convolutional feature data to the decoder through the skip connection, retaining the high-resolution feature data.

[0016] Furthermore, the steps performed by the compression information unit in step S2 specifically include: using depthwise separable convolution to compress nonlinear feature data, reduce the dimension, extract fault information in the low-dimensional space, and obtain compressed feature data. The formula used is as follows:

[0017] Depth convolution operation formula:

[0018] ;

[0019] in, represents nonlinear characteristic data, Represents the output result of the deep convolution operation, i.e., "compressed nonlinear feature data"; Indicates the channel, Indicates The weight of each channel, represents the convolution operator, Represents nonlinear characteristic data part of a channel;

[0020] Point convolution operation formula:

[0021] ;

[0022] in, Represents compressed feature data, Represents a point convolution operation.

[0023] Furthermore, the steps performed by the reconstructed signal unit in step S2 specifically include: performing a deconvolution operation on the compressed feature data to obtain deconvolution feature data, decoding the deconvolution feature data through a Sinc filter and a ReLU activation function to obtain decoded nonlinear feature data, adding a spatial transformation network to the decoder, performing spatial transformation and correction on the decoded nonlinear feature data, and combining the high-resolution feature data to obtain a single event signal.

[0024] Furthermore, in step S3, the process of using the improved AlexNet model to analyze the time-frequency feature data and generate an enhanced data set specifically includes the following steps:

[0025] Step S31: establishing an improved AlexNet model, the improved AlexNet model includes a convolutional layer, a fully connected layer and a SoftMax layer, inputting the time-frequency feature data into the improved AlexNet model, using the convolutional layer to extract spatial features in the time-frequency feature data, identifying frequency patterns and time dependencies, and obtaining high-level image feature data;

[0026] Step S32: The high-level image feature data is further processed through a fully connected layer to integrate spatial features and temporal features to obtain comprehensive feature data;

[0027] Step S33: Introduce the temperature parameter in the SoftMax layer, input the comprehensive feature data into the SoftMax layer, obtain the feature probability distribution, and combine the feature probability distribution to form an enhanced data set. The formula used is as follows:

[0028] ;

[0029] in, An index that represents a specific event category. Indicates The unnormalized scores of the categories, represents the weight factor, represents the temperature parameter, represents the SoftMax output after temperature parameters and weight factors are adjusted, which is used to generate the probability distribution of each event category. represents the exponential function, Represents the index of all event categories, represents the normalization term.

[0030] Furthermore, in the control module, the enhanced data set is analyzed by the NI-ε-G-D3S algorithm to obtain the optimal control decision process, which specifically includes the following steps:

[0031] Step B1: Initialize and establish a replay pool: Initialize the network weights of Dueling-DQN and DDPG, and establish an experience replay pool;

[0032] Step B2: Action selection: Based on the enhanced dataset, Dueling-DQN uses the noise-injected ε-greedy strategy to select discrete actions from the current state. The formula used is as follows:

[0033] ;

[0034] in, Indicates the current state. represents discrete actions, Represents the adjustment after adding noise value, Original value, represents the variance of the noise, represents the Gaussian noise term;

[0035] Step B3: Action parameterization: Parameterize discrete actions and use DDPG to generate continuous actions to form comprehensive control decisions;

[0036] Step B4: Data sampling and updating: Randomly sample data from the experience replay pool, calculate the gradients of Dueling-DQN and DDPG, and update the network weights of Dueling-DQN and DDPG;

[0037] Step B5: Optimize control decision: Set the maximum number of cycles, repeat the above steps until the maximum number of cycles is reached, and finally output the optimal control decision.

[0038] By adopting the above scheme, the beneficial effects achieved by the present invention are as follows:

[0039] The present invention provides an intelligent optical fiber distribution system based on fault alarm. In the feature engineering stage, by combining a multi-scale convolution kernel, a spatial transformation network and a U-Net model of deep separable convolution, it is possible to provide more accurate and efficient feature extraction when processing high-dimensional and complex optical fiber network data; the multi-scale convolution kernel can simultaneously process optical fiber data features at different scales, and effectively capture the diversity and complexity of various fault signals; through the spatial transformation network, the intelligent optical fiber distribution system can more accurately analyze and predict signals in the optical fiber network, and improve the accuracy of fault detection and flow optimization under conditions of different network configurations and changes in optical fiber connections; deep separable convolution greatly reduces the amount of calculation and complexity of the intelligent optical fiber distribution system, helps to extract more fine-grained features, and improves the accuracy of network faults and flow problems, thereby improving the accuracy and efficiency of fault diagnosis;

[0040] In the control module, the present invention combines the ε-greedy strategy, Dueling-DQN and DDPG strategies of noise injection to achieve intelligent optimization of optical fiber connection paths and traffic distribution; this strategy enhances the decision-making ability of the intelligent optical fiber wiring system in a dynamic environment, enabling it to maintain efficient control decisions in the face of uncertainty; by introducing the influence of environmental noise, this method effectively improves the system's adaptability to real-time data, thereby optimizing the overall network performance and reducing the risk of failures;

[0041] In summary, through the combination of the above-mentioned technologies, the present invention not only improves the fault detection and control capabilities of the intelligent fiber optic distribution system, but also provides a more intelligent solution for network management; it enables the system to operate efficiently and stably in the face of complex and changeable network environments, providing users with more reliable services. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a module of an intelligent optical fiber wiring system based on fault alarm proposed by the present invention;

[0043] Figure 2This is a flow chart of the feature engineering module proposed in Example 2;

[0044] Figure 3 This is a flow chart of the NI-ε-G-D3S algorithm proposed in Example 10. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0046] Embodiment 1, according to Figure 1 ,The present invention provides an intelligent optical fiber wiring system based on fault alarm, the system includes a data acquisition module, a feature engineering module, and a control module;

[0047] A data collection module collects connection status data, traffic load data, and fault alarm data of the optical fiber network as a data set;

[0048] Feature engineering module, build U-Net model, combine multi-scale convolution kernel, spatial transformation network and depth separable convolution on the basis of U-Net model, build MS-STS-DS-U-Net model, use MS-STS-DS-U-Net model to extract features of data set and generate enhanced data set; MS-STS-DS-U-Net model includes encoder and decoder;

[0049] The control module combines the ε-greedy strategy of noise injection, Dueling-DQN and DDPG to construct the NI-ε-G-D3S algorithm. The enhanced data set is analyzed by the NI-ε-G-D3S algorithm to generate the optimal control decision. According to the optimal control decision, instructions are issued to adjust the configuration of the optical fiber connection path and the traffic distribution.

[0050] Embodiment 2, according to Figure 2 This embodiment is based on the first embodiment. In this embodiment, the feature engineering module uses the MS-STS-DS-U-Net model to extract features from the data set and generate an enhanced data set. The process specifically includes the following steps:

[0051] Step S1: Data preprocessing: performing spectrum subtraction and feature alignment on the data set to obtain a preprocessed data set;

[0052] Step S2: signal processing: the preprocessed data set is processed by the MS-STS-DS-U-Net model to separate the single event signal, the MS-STS-DS-U-Net model specifically includes extracting feature units, compressing information units and reconstructing signal units;

[0053] Step S3: Enhanced data set generation: Convert a single event signal into a time-frequency image through short-time Fourier transform, extract the frequency and time features in the single event signal, and obtain time-frequency feature data; establish an AlexNet model, introduce temperature parameters in the SoftMax layer of the AlexNet model, construct an improved AlexNet model, use the improved AlexNet model to analyze the time-frequency feature data, and generate an enhanced data set.

[0054] Embodiment 3: This embodiment is based on embodiment 1. In this embodiment, the feature engineering module generates an enhanced data set, which specifically includes the following steps:

[0055] Step E1: Data preprocessing: Spectral subtraction and feature alignment are performed on the data set to obtain a preprocessed data set;

[0056] Step E2: Signal processing: The preprocessed data set is processed by the U-Net model to separate the single event signal;

[0057] Step E3: Enhanced data set generation: Convert the single event signal into a time-frequency image through short-time Fourier transform, extract the frequency and time features in the single event signal, and obtain the time-frequency feature data; establish an AlexNet model, introduce the temperature parameter in the SoftMax layer of the AlexNet model, construct an improved AlexNet model, use the improved AlexNet model to analyze the time-frequency feature data, and generate an enhanced data set.

[0058] Embodiment 4: This embodiment is based on embodiment 2. In this embodiment, the steps performed by the feature extraction unit in step S2 specifically include:

[0059] Step M1: Input the preprocessed data set into the multi-scale convolution layer in the encoder, extract the fault signal features through three convolution kernels of 3x3, 5x5, and 7x7, capture the frequency and intensity changes of different scales in the fault signal features, and obtain the convolution feature data;

[0060] Step M2: Process the convolution feature data through a Sinc filter and a ReLU activation function to obtain nonlinear feature data;

[0061] Step M3: Pass the convolutional feature data to the decoder through the skip connection, retaining the high-resolution feature data.

[0062] Embodiment 5, this embodiment is based on embodiment 4. In this embodiment, the steps performed by the compressed information unit in step S2 specifically include: using depthwise separable convolution to compress nonlinear feature data, reduce the dimension, extract fault information in the low-dimensional space, and obtain compressed feature data. The formula used is as follows:

[0063] Depth convolution operation formula:

[0064] ;

[0065] in, represents nonlinear characteristic data, Represents the output result of the deep convolution operation, i.e., "compressed nonlinear feature data"; Indicates the channel, Indicates The weight of each channel, represents the convolution operator, Represents nonlinear characteristic data part of a channel;

[0066] Point convolution operation formula:

[0067] ;

[0068] in, Represents compressed feature data, Represents a point convolution operation.

[0069] Embodiment 6. This embodiment is based on embodiment 5. In this embodiment, the steps performed by the reconstructed signal unit in step S2 specifically include: performing a deconvolution operation on the compressed feature data to obtain deconvolution feature data, decoding the deconvolution feature data through a Sinc filter and a ReLU activation function to obtain decoded nonlinear feature data, adding a spatial transformation network to the decoder, performing spatial transformation and correction on the decoded nonlinear feature data, and combining the high-resolution feature data to obtain a single event signal.

[0070] Embodiment 7. This embodiment is based on embodiment 5. In this embodiment, the steps performed by the reconstructed signal unit in step S2 specifically include: performing a deconvolution operation on the compressed feature data to obtain deconvolution feature data, and then decoding the deconvolution feature data through a Sinc filter and a ReLU activation function to obtain decoded nonlinear feature data, and combining the high-resolution feature data to obtain a single event signal.

[0071] Embodiment 8, this embodiment is based on embodiment 6. In this embodiment, in step S3, the process of using the improved AlexNet model to analyze the time-frequency feature data and generate an enhanced data set specifically includes the following steps:

[0072] Step S31: establishing an improved AlexNet model, the improved AlexNet model includes a convolutional layer, a fully connected layer and a SoftMax layer, inputting the time-frequency feature data into the improved AlexNet model, using the convolutional layer to extract spatial features in the time-frequency feature data, identifying frequency patterns and time dependencies, and obtaining high-level image feature data;

[0073] Step S32: The high-level image feature data is further processed through a fully connected layer to integrate spatial features and temporal features to obtain comprehensive feature data;

[0074] Step S33: Introduce the temperature parameter in the SoftMax layer, input the comprehensive feature data into the SoftMax layer, obtain the feature probability distribution, and combine the feature probability distribution to form an enhanced data set. The formula used is as follows:

[0075] ;

[0076] in, An index that represents a specific event category. Indicates The unnormalized scores of the categories, represents the weight factor, represents the temperature parameter, represents the SoftMax output after temperature parameters and weight factors are adjusted, which is used to generate the probability distribution of each event category. represents the exponential function, Represents the index of all event categories, represents the normalization term.

[0077] Embodiment 9, this embodiment is based on embodiment 6. In this embodiment, in step S3, the process of using the improved AlexNet model to analyze the time-frequency feature data and generate an enhanced data set specifically includes the following steps:

[0078] Step N1: Establish an improved AlexNet model, which includes a convolutional layer, a fully connected layer, and a SoftMax layer. Input the time-frequency feature data into the improved AlexNet model, use the convolutional layer to extract the spatial features in the time-frequency feature data, identify the frequency pattern and time dependency, and obtain high-level image feature data.

[0079] Step N2: The high-level image feature data is further processed through the fully connected layer to integrate the spatial features and temporal features to obtain comprehensive feature data;

[0080] Step N3: Input the comprehensive feature data into the SoftMax layer to obtain the feature probability distribution, and combine the feature probability distribution to form an enhanced data set.

[0081] Embodiment 10, according to Figure 3 This embodiment is based on the eighth embodiment. In this embodiment, in the control module, the process of analyzing the enhanced data set by the NI-ε-G-D3S algorithm to obtain the optimal control decision specifically includes the following steps:

[0082] Step B1: Initialize and establish a replay pool: Initialize the network weights of Dueling-DQN and DDPG, and establish an experience replay pool;

[0083] Step B2: Action selection: Based on the enhanced dataset, Dueling-DQN uses the noise-injected ε-greedy strategy to select discrete actions from the current state. The formula used is as follows:

[0084] ;

[0085] in, Indicates the current state. represents discrete actions, Represents the adjustment after adding noise value, Original value, represents the variance of the noise, represents the Gaussian noise term;

[0086] Step B3: Action parameterization: Parameterize discrete actions and use DDPG to generate continuous actions to form comprehensive control decisions;

[0087] Step B4: Data sampling and updating: Randomly sample data from the experience replay pool, calculate the gradients of Dueling-DQN and DDPG, and update the network weights of Dueling-DQN and DDPG;

[0088] Step B5: Optimize control decision: set the maximum number of cycles, repeat the above steps until the maximum number of cycles is reached, and finally output the optimal control decision;

[0089] The maximum number of cycles is 500.

[0090] The present invention and its embodiments are described above, which is not restrictive. What is shown in the accompanying drawings is only one of the embodiments of the present invention, and the actual structure is not limited to this. In short, if ordinary technicians in this field are inspired by it and do not deviate from the purpose of the invention, they can creatively design structural methods and embodiments similar to the technical solution, which should all fall within the scope of protection of the present invention.

Claims

1. An intelligent optical fiber wiring system based on fault alarm, comprising a data acquisition module, wherein the data acquisition module collects connection status data, flow load data and fault alarm data of the optical fiber network as a data set; characterized in that: The system also includes a feature engineering module and a control module; The feature engineering module establishes a U-Net model, combines multi-scale convolution kernels, spatial transformation networks and depth-separable convolutions on the basis of the U-Net model, constructs an MS-STS-DS-U-Net model, uses the MS-STS-DS-U-Net model to extract features from the data set, and generates an enhanced data set; The MS-STS-DS-U-Net model includes an encoder and a decoder; The control module combines the ε-greedy strategy of noise injection, Dueling-DQN and DDPG to construct the NI-ε-G-D3S algorithm, analyzes the enhanced data set through the NI-ε-G-D3S algorithm, generates the optimal control decision, issues instructions according to the optimal control decision, and adjusts the configuration and traffic distribution of the optical fiber connection path.

2. The intelligent optical fiber wiring system based on fault alarm according to claim 1, characterized in that: The feature engineering module generates an enhanced data set, which specifically includes the following steps: Step S1: Data preprocessing: performing spectrum subtraction and feature alignment on the data set to obtain a preprocessed data set; Step S2: signal processing: the preprocessing data set is processed by the MS-STS-DS-U-Net model to separate and obtain a single event signal, wherein the MS-STS-DS-U-Net model specifically includes a feature extraction unit, an information compression unit, and a signal reconstruction unit; Step S3: Enhanced data set generation: Convert a single event signal into a time-frequency image through short-time Fourier transform, extract the frequency and time features in the single event signal, and obtain time-frequency feature data; establish an AlexNet model, introduce temperature parameters in the SoftMax layer of the AlexNet model, construct an improved AlexNet model, use the improved AlexNet model to analyze the time-frequency feature data, and generate an enhanced data set.

3. The intelligent optical fiber wiring system based on fault alarm according to claim 2, characterized in that: The steps of extracting feature units specifically include: Step M1: Input the preprocessed data set into the multi-scale convolution layer in the encoder, extract the fault signal features through three convolution kernels of 3x3, 5x5, and 7x7, capture the frequency and intensity changes of different scales in the fault signal features, and obtain the convolution feature data; Step M2: Process the convolution feature data through a Sinc filter and a ReLU activation function to obtain nonlinear feature data; Step M3: Pass the convolutional feature data to the decoder through the skip connection, retaining the high-resolution feature data.

4. The intelligent optical fiber wiring system based on fault alarm according to claim 3, characterized in that: The steps performed by the compression information unit specifically include: using depth-separable convolution to compress nonlinear feature data, reduce the dimension, extract fault information in the low-dimensional space, and obtain compressed feature data.

5. The intelligent optical fiber wiring system based on fault alarm according to claim 4, characterized in that: The steps of reconstructing the signal unit specifically include: performing a deconvolution operation on the compressed feature data to obtain deconvolution feature data, decoding the deconvolution feature data through a Sinc filter and a ReLU activation function to obtain decoded nonlinear feature data, adding a spatial transformation network to the decoder, performing spatial transformation and correction on the decoded nonlinear feature data, and combining the high-resolution feature data to obtain a single event signal.

6. The intelligent optical fiber wiring system based on fault alarm according to claim 5, characterized in that: In step S3, the process of using the improved AlexNet model to analyze the time-frequency feature data and generate an enhanced data set specifically includes the following steps: Step S31: establishing an improved AlexNet model, the improved AlexNet model includes a convolutional layer, a fully connected layer and a SoftMax layer, inputting the time-frequency feature data into the improved AlexNet model, using the convolutional layer to extract spatial features in the time-frequency feature data, identifying frequency patterns and time dependencies, and obtaining high-level image feature data; Step S32: The high-level image feature data is further processed through a fully connected layer to integrate spatial features and temporal features to obtain comprehensive feature data; Step S33: Introduce the temperature parameter in the SoftMax layer, input the comprehensive feature data into the SoftMax layer, obtain the feature probability distribution, and combine the feature probability distribution to form an enhanced data set.

7. The intelligent optical fiber wiring system based on fault alarm according to claim 1, characterized in that: The process of obtaining the optimal control decision by the control module specifically includes the following steps: Step B1: Initialize and establish a replay pool: Initialize the network weights of Dueling-DQN and DDPG, and establish an experience replay pool; Step B2: Action selection: Based on the augmented dataset, Dueling-DQN uses the noise-injected ε-greedy strategy to select discrete actions from the current state; Step B3: Action parameterization: Parameterize discrete actions and use DDPG to generate continuous actions to form comprehensive control decisions; Step B4: Data sampling and updating: Randomly sample data from the experience replay pool, calculate the gradients of Dueling-DQN and DDPG, and update the network weights of Dueling-DQN and DDPG; Step B5: Optimize control decision: Set the maximum number of cycles, repeat the above steps until the maximum number of cycles is reached, and finally output the optimal control decision.

Images