Multi-core optical cable fault on-line monitoring method based on optical fiber sensing technology

Abstract

The invention relates to the technical field of communication fault monitoring, in particular to a multi-core optical cable fault online monitoring method based on an optical fiber sensing technology. The method comprises the following steps: firstly, establishing a primary network topological graph according to a direct communication relationship of core nodes, selecting a key service optical cable according to a key service type of the primary network topological graph, and establishing a secondary network topological graph; the second-level link historical performance data of the second-level network topological graph is clustered, and the performance state of the second-level link is judged in real time; calculating a trunk index according to the bandwidth and the throughput and determining a trunk optical cable; performing fault monitoring on the trunk optical cable by using ROTDR equipment, completing super-resolution reconstruction and signal analysis through an SR-LSTM model, positioning a fault position and identifying a fault type; a state space and an action space are constructed through an Actor-Critic reinforcement learning framework in combination with a performance state, a fault position and a fault type, an intelligent agent learns an optimal operation and maintenance strategy, and online fault monitoring of a main optical cable is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of communication fault monitoring, and in particular to a multi-core optical cable fault online monitoring method based on optical fiber sensing technology. Background Art

[0002] As an important infrastructure for modern information transmission and industrial control, optical cables play a vital role in power systems. The optical cable network in power systems is usually composed of multi-core optical cables, which transmit different business data through each optical fiber core. This structure greatly improves the communication bandwidth and network reliability. Among these optical cables, the trunk optical cable connects the power dispatching center, substation, distribution network and control center, and carries key businesses such as dispatching control, protection communication and fault monitoring. Once the trunk optical cable fails, it will directly affect the stable operation of the power grid and may even cause serious power outages. Therefore, performance monitoring and fault detection of multi-core optical cables, especially trunk optical cables, are crucial for the efficient operation of power systems and rapid response to faults.

[0003] Raman optical time-domain reflectometry (ROTDR), as a distributed optical fiber sensing technology, has been widely used in multi-core optical cable fault monitoring. Based on the Raman scattering effect, ROTDR technology can accurately measure the temperature distribution along the optical cable by sending optical pulse signals and measuring the intensity ratio of Stokes light and anti-Stokes light in the echo. This technology is not only suitable for detecting temperature-related faults (such as overload heating or abnormal ambient temperature), but also can monitor the independent performance of each optical fiber core by utilizing the structural characteristics of multi-core optical cables. However, ROTDR technology has limitations in the direct detection of non-temperature-related faults such as mechanical damage and fiber breakage. In addition, due to the high signal complexity in multi-core optical cables, the accuracy of ROTDR technology in distinguishing single-core optical fiber faults from overall optical cable performance abnormalities in multi-core optical cables also needs to be further improved. Therefore, how to optimize the signal analysis capability of ROTDR technology in a multi-core optical cable environment and combine it with intelligent analysis methods to improve the accurate fault detection and operation and maintenance efficiency of trunk optical cables is a key issue that needs to be solved urgently.

[0004] Therefore, an online fault monitoring method for multi-core optical cables based on optical fiber sensing technology is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-core optical cable fault online monitoring method based on optical fiber sensing technology. The present invention performs cluster analysis according to historical performance data of key business optical cables, judges the performance status of optical cables, and calculates the trunk index according to the bandwidth and throughput of optical cables, so as to determine the trunk optical cables; the present invention performs signal super-resolution reconstruction and analysis on time domain reflection signals through an SR-LSTM model, and accurately obtains the fault location and fault type; the present invention establishes a state space based on performance status, fault location and type, constructs an action space in combination with expert experience and historical operation and maintenance records, optimizes the operation and maintenance strategy through an Actor-Critic reinforcement learning framework, and realizes efficient performance maintenance and intelligent fault repair of trunk optical cables.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The multi-core optical cable fault online monitoring method based on optical fiber sensing technology includes:

[0008] Establishing a first-level network topology diagram based on the direct communication relationship of core nodes; the core nodes include a power dispatching center, a substation, a distribution network and a control center;

[0009] Selecting a key service optical cable according to the service type between the first-level nodes of the first-level network topology diagram, and establishing a second-level network topology diagram according to the key service optical cable; the key service optical cable is an optical cable for processing key services, and the key services include dispatching control, protection communication and fault monitoring;

[0010] Collect and store historical performance data between the secondary links of the secondary network topology diagram, establish a performance database, cluster the historical performance data using a K-Means algorithm, and determine the current performance status of the secondary links based on the clustering results;

[0011] Calculate a backbone index according to the bandwidth and throughput of the secondary link, and establish a backbone optical cable of the secondary network topology diagram according to the backbone index;

[0012] Use a ROTDR device to perform fault monitoring on the trunk optical cable, obtain a time domain reflection signal, and use an SR-LSTM model to perform super-resolution reconstruction and signal analysis on the time domain reflection signal to obtain a fault location and a fault type;

[0013] A state space is established according to the performance status, the fault location and the fault type, and an action space is established according to expert experience and historical operation and maintenance records; the state space and the action space are combined through an Actor-Critic reinforcement learning framework, and reinforcement learning is performed using an intelligent agent to obtain an optimal operation and maintenance strategy.

[0014] Furthermore, establishing the first-level network topology diagram includes:

[0015] Determine all the core nodes in the area based on the existing power network database; analyze the communication traffic between each of the core nodes through a network detection tool to determine the communication optical cables directly connected between the core nodes; use a topology tool to model the core nodes and the communication optical cables into a first-level network topology diagram, wherein the core nodes are the first-level nodes of the first-level network topology diagram, and the communication optical cables are the first-level links of the first-level network topology diagram.

[0016] Furthermore, establishing the secondary network topology diagram includes:

[0017] Perform traffic analysis on each communication optical cable in the primary network topology diagram to obtain the service type of each communication optical cable; select key service optical cables according to the service type; use a topology tool to model the core nodes and the key service optical cables into a secondary network topology diagram, wherein the core nodes are the secondary nodes of the secondary network topology diagram, and the key service optical cables are the secondary links of the secondary network topology diagram.

[0018] Furthermore, the historical performance data includes bandwidth, delay, throughput, packet loss rate, bit error rate and optical power, and the performance status includes normal status, fiber aging, temperature drift, bandwidth overload, increased signal delay and abnormal fiber dispersion.

[0019] Further, determining the current performance status of the secondary link includes:

[0020] Collect the historical performance data of the secondary link, and perform data cleaning and data normalization on the historical performance data to obtain preprocessed data; use the elbow rule to determine the optimal K value, cluster the preprocessed data, and obtain performance status categories; cluster the performance data of the current secondary link, and output the performance status according to the clustering results.

[0021] Furthermore, the calculation formula of the backbone index is:

[0022]

[0023] Wherein, M represents the backbone index, B represents the bandwidth, T represents the throughput, α1 represents the bandwidth weight, α2 represents the throughput weight, and α3 represents the utilization weight.

[0024] Furthermore, the SR-LSTM model includes:

[0025] An input layer, used for receiving the time domain reflection signal;

[0026] A signal super-resolution layer is used to perform preliminary super-resolution processing on the time domain reflection signal using Fourier interpolation method to generate a low-order super-resolution signal; the preliminary super-resolution processing includes: performing fast Fourier transform on the time domain reflection signal to obtain a frequency domain signal; filling zero values ​​at the central symmetric position of the frequency domain signal to obtain an extended spectrum; performing inverse fast Fourier transform on the extended spectrum to generate a low-order super-resolution signal;

[0027] An LSTM layer is used to capture the temporal dependency of the preliminary super-resolution signal and generate a high-order super-resolution signal;

[0028] A feature decoding layer, used for extracting features related to the fault location and fault type according to the high-order super-resolution signal;

[0029] The output layer is used to output the prediction results of fault location and fault type.

[0030] Further, obtaining the fault location and the fault type includes:

[0031] Use the ROTDR device to send optical pulses to the trunk optical cable; record the time delay and intensity information of the reflected signal to obtain the time domain reflection signal; input the time domain reflection signal into the SR-LSTM model to obtain the fault location and the fault type.

[0032] Furthermore, the optimal operation and maintenance strategy is obtained:

[0033] S601: Establish the state space according to the performance state, the fault location and the fault type, and establish the action space according to the expert experience and the historical operation and maintenance records;

[0034] S602: Initialize the Actor network and the Critic network, and set the learning rate, discount factor, exploration strategy, and reward function;

[0035] S603: The agent generates a current action through the Actor network according to the current state, and obtains an immediate reward after the current action interacts with the system environment and returns to the next state;

[0036] S604: Calculate the update value of the Critic network using the TD error, and update the Actor network according to the TD error;

[0037] S605: Determine whether the iteration meets the convergence condition. If not, re-execute S603; the convergence condition is that the TD error is less than an error threshold.

[0038] S606: Obtain the optimal operation and maintenance strategy.

[0039] Furthermore, the calculation formula of the reward function is:

[0040]

[0041] Where R represents the reward function, P exp represents the expected performance, P act Indicates the actual performance after operation and maintenance, T rep Indicates the operation and maintenance time, C res represents the operation and maintenance cost, ω1 represents the performance weight, ω2 represents the time weight, and ω3 represents the cost weight.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention calculates the backbone index and establishes the backbone optical cable according to the bandwidth and throughput of the key business optical cable, which can accurately evaluate the importance and load level of the optical cable, and preferentially identify and build high-priority communication paths that carry key business. This method improves the scientificity and accuracy of network topology optimization by quantifying the distribution of network resources, ensures efficient allocation of resources and priority resolution of key issues, and indirectly improves the efficiency of online fault monitoring.

[0044] 2. The present invention proposes and uses the SR-LSTM model to perform super-resolution reconstruction and signal analysis on the time domain reflection signal, which significantly improves the accuracy and efficiency of fault detection. The signal resolution is improved by preliminary signal super-resolution processing, and the LSTM layer is combined to capture the timing dependency of the signal. The SR-LSTM model accurately extracts fault features while reconstructing high-resolution signals, achieving higher spatial resolution and more accurate fault location, and realizing the real-time and effectiveness of online monitoring of multi-core optical cable faults.

[0045] 3. The present invention uses the Actor-Critic reinforcement learning framework to intelligently optimize the online monitoring and maintenance process of multi-core optical cable faults. The framework combines state space and action space, and through the intelligent body's continuous interaction with the environment and iterative optimization of the optimal operation and maintenance strategy, it can achieve efficient maintenance of the performance status of the trunk optical cable, accurate fault location and repair. Through the precise reinforcement learning mechanism, the framework can dynamically learn the optimal decision path, significantly improve the real-time and accuracy of fault monitoring, and effectively ensure the stable operation of the trunk optical cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flow chart of a multi-core optical cable fault online monitoring method based on optical fiber sensing technology provided by the present invention;

[0047] Figure 2 A schematic diagram of the SR-LSTM model structure provided by the present invention;

[0048] Figure 3 A flow chart of learning the optimal operation and maintenance strategy provided by the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The first embodiment provided by the present invention is as follows:

[0051] Multi-core optical cable fault online monitoring method based on optical fiber sensing technology, such as Figure 1 As shown, including:

[0052] S100: Establishing a first-level network topology diagram according to the direct communication relationship of core nodes; the core nodes include a power dispatching center, a substation, a distribution network and a control center;

[0053] Furthermore, establishing the first-level network topology diagram includes:

[0054] Determine all the core nodes in the area based on the existing power network database; analyze the communication traffic between each of the core nodes through a network detection tool to determine the communication optical cables directly connected between the core nodes; use a topology tool to model the core nodes and the communication optical cables into a first-level network topology diagram, wherein the core nodes are the first-level nodes of the first-level network topology diagram, and the communication optical cables are the first-level links of the first-level network topology diagram.

[0055] Specifically, some data of a city's power network database is shown in Table 1. The core nodes of the city are selected according to the node name and node location. The communication IP addresses between nodes are detected by the NetFlow network detection tool to determine the communication optical cables directly connected between the core nodes. The core nodes and communication optical cables are modeled as a first-level network topology map using the topology map tool Gephi.

[0056] Table 1 Partial data of a city's power network database

[0057]

[0058] Establishing a first-level network topology diagram can intuitively display the connection relationship between core nodes and communication optical cables, providing a clear visualization basis for online monitoring of multi-core optical cables in the region.

[0059] S200: selecting a key service optical cable according to the service type between the first-level nodes of the first-level network topology map, and establishing a second-level network topology map according to the key service optical cable; the key service optical cable is an optical cable for processing key services, and the key services include dispatching control, protection communication and fault monitoring;

[0060] Furthermore, establishing the secondary network topology diagram includes:

[0061] Perform traffic analysis on each communication optical cable in the primary network topology diagram to obtain the service type of each communication optical cable; select key service optical cables according to the service type; use a topology tool to model the core nodes and the key service optical cables into a secondary network topology diagram, wherein the core nodes are the secondary nodes of the secondary network topology diagram, and the key service optical cables are the secondary links of the secondary network topology diagram.

[0062] Specifically, the protocol analysis tool Wireshark is used to extract the service type identification of the traffic data of the communication optical cable in the primary network topology map, and the communication optical cables with transmission service types such as scheduling control, protection communication and fault monitoring are set as key business optical cables. The topology map tool Gephi is used to model the key business optical cables into a secondary network topology map.

[0063] Establishing a secondary network topology map can focus on key business optical cables and their related core nodes, accurately depict the communication paths and dependencies of key businesses, and provide a reliable data basis for solving real-time online monitoring of key optical cable line performance indicators.

[0064] S300: Collect and store historical performance data between the secondary links of the secondary network topology diagram, establish a performance database, cluster the historical performance data using a K-Means algorithm, and determine the current performance status of the secondary link according to the clustering result;

[0065] Furthermore, the historical performance data includes bandwidth, delay, throughput, packet loss rate, bit error rate and optical power, and the performance status includes fiber aging, temperature drift, bandwidth overload, signal delay increase and fiber dispersion anomaly.

[0066] By collecting and analyzing historical performance data including bandwidth, latency, throughput, packet loss rate, bit error rate and optical power, the operating status of the optical cable can be fully monitored, and combined with the classification of multiple performance states, it helps to accurately identify the performance status of critical business optical cables.

[0067] Further, determining the current performance status of the secondary link includes:

[0068] Collect the historical performance data of the secondary link, and perform data cleaning and data normalization on the historical performance data to obtain preprocessed data; use the elbow rule to determine the optimal K value, cluster the preprocessed data, and obtain performance status categories; cluster the performance data of the current secondary link, and output the performance status according to the clustering results.

[0069] Specifically, the historical performance data of the secondary link is collected, including bandwidth, delay, throughput, packet loss rate, bit error rate, and optical power, and these indicators are integrated into a vector. The vector is expressed as follows:

[0070] D={x1,x2,x3,...,x n};

[0071] x i ={bandwidth, delay, throughput, packet loss rate, bit error rate, optical power};

[0072] Where D represents all historical performance data, n represents the amount of historical performance data, and x i Represents the indicators contained in the i-th historical performance data, then removes outliers and noise, fills in missing data, and normalizes the data to [0,1]. The best K value is obtained by comparing the mean square error and the mean square error under different K values. The calculation formula of the mean square error and the mean square error is:

[0073]

[0074] Among them, SSE represents the mean square error, K represents the number of clusters, j represents the cluster index, μ j represents the jth cluster center. In a feasible implementation, the optimal K value is 5, and the performance status categories are fiber aging, temperature drift, bandwidth overload, increased signal delay and abnormal fiber dispersion. The performance data of the current secondary link is clustered, and the performance status is output according to the clustering results.

[0075] Through real-time cluster analysis and performance status output of current optical cable performance data, accurate monitoring and abnormal monitoring of the optical cable network can be achieved, providing efficient support for maintenance decisions, performance optimization and fault warning, thereby greatly improving the stability and operation efficiency of the optical cable network.

[0076] S400: Calculating a backbone index according to the bandwidth and throughput of the secondary link, and establishing a backbone optical cable of the secondary network topology diagram according to the backbone index;

[0077] Furthermore, the calculation formula of the backbone index is:

[0078]

[0079] Wherein, M represents the backbone index, B represents the bandwidth, T represents the throughput, α1 represents the bandwidth weight, α2 represents the throughput weight, and α3 represents the utilization weight.

[0080] Specifically, the trunk index is calculated by the bandwidth and throughput of the key business optical cable, and N key business optical cables with the highest trunk index are selected to establish the trunk optical cable.

[0081] By calculating the backbone index through the bandwidth and throughput of key business optical cables, the optical cables with higher load criticality in the network can be accurately identified, which can effectively extract the backbone optical cables in the secondary network topology diagram. The establishment of backbone optical cables helps to optimize the allocation of network resources and provide technical support for the priority protection of key businesses.

[0082] S500: Use a ROTDR device to measure the trunk optical cable to obtain a time domain reflection signal, and use an SR-LSTM model to perform super-resolution reconstruction and signal analysis on the time domain reflection signal to obtain a fault location and a fault type;

[0083] Furthermore, the SR-LSTM model is as follows Figure 2 As shown, including:

[0084] An input layer, used for receiving the time domain reflection signal;

[0085] A signal super-resolution layer is used to perform preliminary super-resolution processing on the time domain reflection signal using Fourier interpolation method to generate a low-order super-resolution signal; the preliminary super-resolution processing includes: performing fast Fourier transform on the time domain reflection signal to obtain a frequency domain signal; filling zero values ​​at the central symmetric position of the frequency domain signal to obtain an extended spectrum; performing inverse fast Fourier transform on the extended spectrum to generate a low-order super-resolution signal;

[0086] An LSTM layer is used to capture the temporal dependency of the preliminary super-resolution signal and generate a high-order super-resolution signal;

[0087] A feature decoding layer, used for extracting features related to the fault location and fault type according to the high-order super-resolution signal;

[0088] The output layer is used to output the prediction results of fault location and fault type.

[0089] Specifically, the input data of the input layer is a time domain reflection signal, which is expressed as:

[0090] x={x1,x2,...,x N};

[0091] Where N represents the sampling time point; the signal super-layer performs fast Fourier transform on the time domain reflection signal to obtain the frequency domain signal. The formula for obtaining the frequency domain signal is:

[0092]

[0093] Where F[k] represents the frequency component of the time domain reflection signal in the frequency domain, k represents the index of the frequency domain, and x n Represents the discrete points of the time domain reflection signal, n represents the index of the sampling point, e -j2πkn / N Represents the basis function of Fourier transform; fill zero values ​​at the central symmetric position of the frequency domain signal to obtain the extended spectrum. The calculation formula of the extended spectrum is:

[0094]

[0095] Among them, F padded [k] represents the extended spectrum, and M represents the length of the extended spectrum. The extended spectrum is subjected to inverse fast Fourier transform to generate a low-order super-resolution signal. The calculation formula of the low-order super-resolution signal is:

[0096]

[0097] Among them, f super [n] represents the low-order super-resolved signal; the LSTM layer uses LSTM units to capture the temporal dependencies of the low-order super-resolved signal. The process can be expressed as:

[0098] h t ,c t =LSTM(f super [n] t ,h t-1 ,c t-1 );

[0099] Among them, t represents the time variable, h t represents the hidden state at time t, c t represents the cell state at time t, LSTM() represents the LSTM module, and h t-1 represents the hidden state at time t-1, c t-1 Indicates the cell state at time t-1. The LSTM layer increases the expressiveness of the model by stacking multiple LSTM modules to obtain a high-order super-resolution signal, which is expressed as follows:

[0100] H={h1,h2,h3,...,h T};

[0101] Wherein, H represents a high-order super-resolution signal; the feature decoding layer extracts features related to the fault location and fault type according to the high-order super-resolution signal. The feature decoding layer is implemented by a fully connected or convolutional neural network. In this embodiment, a fully connected neural network is used to implement feature decoding. The process can be expressed as:

[0102] y location=Decoder1(H);

[0103] y type =Decoder2(H);

[0104] Among them, y location represents the fault location prediction, y type Decoder() represents the fault type prediction, and Decoder() represents the feature decoder. The output layer parses the output result of the feature decoding layer through the Softmax function to obtain the prediction result. The process can be expressed as:

[0105]

[0106] in, represents the fault location prediction result, It represents the fault type prediction result, and Softmax() represents the Softmax function.

[0107] The SR-LSTM model provides an efficient and accurate time domain reflection signal analysis method by combining signal processing and deep learning. The model integrates the advantages of traditional signal processing and deep learning, realizes efficient end-to-end analysis from original signals to prediction results, significantly improves the performance and reliability of optical cable fault monitoring, and provides technical support for the monitoring and maintenance of trunk optical cables.

[0108] Further obtaining the fault location and the fault type includes:

[0109] Use the ROTDR device to send optical pulses to the trunk optical cable; record the time delay and intensity information of the reflected signal to obtain the time domain reflection signal; input the time domain reflection signal into the SR-LSTM model to obtain the fault location and the fault type.

[0110] By using the ROTDR device to send optical pulses and record the time delay and intensity information of the time domain reflection signal, the performance data of the trunk optical cable can be efficiently collected. The collected signal is input into the SR-LSTM model, combined with signal super-resolution processing and timing analysis, to accurately extract the fault location and fault type. This process realizes online analysis from signal acquisition to fault diagnosis, improves the accuracy and speed of fault monitoring, and provides reliable technical support for optical cable maintenance and fault repair.

[0111] S600: Establish a state space according to the performance status, the fault location and the fault type, and establish an action space according to expert experience and historical operation and maintenance records; combine the state space and the action space through the Actor-Critic reinforcement learning framework, and use an intelligent agent to perform reinforcement learning to obtain the optimal operation and maintenance strategy.

[0112] Furthermore, the optimal operation and maintenance strategy is obtained as follows: Figure 3 As shown, including:

[0113] S601: Establish the state space according to the performance state, the fault location and the fault type, and establish the action space according to the expert experience and the historical operation and maintenance records;

[0114] S602: Initialize the Actor network and the Critic network, and set the learning rate, discount factor, exploration strategy, and reward function;

[0115] S603: The agent generates a current action through the Actor network according to the current state, and obtains an immediate reward after the current action interacts with the system environment and returns to the next state;

[0116] S604: Calculate the update value of the Critic network using the TD error, and update the Actor network according to the TD error;

[0117] S605: Determine whether the iteration meets the convergence condition. If not, re-execute S603; the convergence condition is that the TD error is less than an error threshold.

[0118] S606: Obtain the optimal operation and maintenance strategy.

[0119] Table 2 State space and action space settings of the Actor-Critic reinforcement learning framework

[0120]

[0121] Specifically, the settings of the state space and action space are shown in Table 2, where the state space includes performance status, fault location and fault type, and the action space is the measures performed for different performance status and fault types. These measures are based on historical operation and maintenance records and expert experience, where expert experience is the solution proposed by technical personnel in this industry for the performance status and fault type to solve the above problems; initialize the Actor network and Critic network, and set the learning rate, discount factor, exploration strategy and reward function, where the Actor network and Critic network are both common multi-layer perceptrons, and the exploration strategy is the ε-greedy strategy; the Actor network converts the current state s t As input, the probability of generating each action in the current state is calculated through the Softmax function, and then the current action a is selected according to the probability t , the agent takes the current action a t Send to the system environment and execute the current action a t , return to the next state s t+1 and instant reward Rt ; Use the TD error to calculate the update value of the Critic network, and update the Actor network according to the TD error, where the calculation formula of the TD error is:

[0122] δ t =R t +γ×Q(s t+1 ,a t+1 )-Q(s t ,a t );

[0123] Among them, δ t represents the TD error, R t represents the immediate reward, γ represents the discount factor, Q() represents the expected value function of the state-action pair, Q(s t+1 ,a t+1 ) represents the expected value of the next state-action pair, Q(s t ,a t ) represents the expected value of the current state-action pair. The parameters in the Critic network are updated by the gradient descent method to more accurately estimate the value of the state-action pair. The update formula is:

[0124]

[0125] Among them, θ c Represents the parameters of the Critic network, α c represents the learning rate of the Critic network, Represents the gradient of the Critic network. The Actor network updates the parameters by maximizing the expected return of the action. The gradient update formula is:

[0126]

[0127] Among them, θ a Represents the parameters of the Actor network, α c represents the learning rate of the Actor network, logπ(a t |s t ) represents the action selection probability distribution generated by the Actor network; determine whether the TD error is less than the error threshold, if so, stop updating the Actor network and the Critic network, and give the optimal operation and maintenance strategy, otherwise re-execute step S603, in a feasible implementation, the error threshold is 0.5; when the iteration is completed, the optimal operation and maintenance strategy is finally obtained.

[0128] By combining performance status, fault location and fault type to establish a state space, and using expert experience and historical operation and maintenance records to build an action space, the Actor-Critic reinforcement learning framework can dynamically adapt to complex trunk optical cable maintenance needs. This process continuously learns and optimizes operation and maintenance strategies through intelligent agents to achieve accurate decision-making on trunk optical cable performance maintenance and fault repair.

[0129] Furthermore, the calculation formula of the reward function is:

[0130]

[0131] Among them, P exp represents the expected performance, P act Indicates the actual performance after operation and maintenance, T rep Indicates the operation and maintenance time, C res represents the operation and maintenance cost, ω1 represents the performance weight, ω2 represents the time weight, and ω3 represents the cost weight.

[0132] Specifically, the expected performance is the theoretical performance when the optical cable is in good condition, including theoretical bandwidth, theoretical delay, theoretical throughput, theoretical packet loss rate, theoretical bit error rate and theoretical optical power. The actual performance after operation and maintenance includes actual bandwidth, actual delay, actual throughput, actual packet loss rate, actual bit error rate and actual optical power. The physical meaning represented by the division operation of the expected performance and the actual performance after operation and maintenance can be expressed by the following formula:

[0133]

[0134] Operation and maintenance costs are the operation and maintenance expenses incurred during operation and maintenance.

[0135] The reward function takes into account performance recovery, operation and maintenance time, and operation and maintenance costs, and uses a weighted method to flexibly adjust the weight of each factor to achieve multi-objective optimization. By quantifying the difference between expected performance and actual performance, the performance improvement is explicitly incorporated into the reward calculation. At the same time, combined with operation and maintenance time and cost, the intelligent agent is guided to provide efficient and economical methods to help technicians complete fault repair and performance maintenance.

[0136] The second embodiment provided by the present invention is as follows:

[0137] In response to the call for the development of digital and intelligent power, a power company has upgraded the fault monitoring system A of the trunk optical cable of the power communication network to realize the online monitoring of multi-core optical cable faults of the trunk optical cable of the power communication network. For this purpose, a new fault monitoring system B is adopted. The system is equipped with the multi-core optical cable fault online monitoring method based on optical fiber sensing technology proposed in the present invention, including:

[0138] The multi-core optical cable fault online monitoring method based on optical fiber sensing technology includes:

[0139] Establishing a primary network topology diagram based on direct communication relationships of core nodes, wherein the core nodes include a power dispatching center, a substation, a distribution network, and a control center;

[0140] Selecting a key service optical cable according to the service type between the first-level nodes of the first-level network topology diagram, and establishing a second-level network topology diagram according to the key service optical cable, wherein the key service optical cable is an optical cable for processing key services, and the key services include dispatching control, protection communication and fault monitoring;

[0141] Collect and store historical performance data between the secondary links of the secondary network topology diagram, establish a performance database, cluster the historical performance data using a K-Means algorithm, and determine the current performance status of the secondary links based on the clustering results;

[0142] Calculate a backbone index according to the bandwidth and throughput of the secondary link, and establish a backbone optical cable of the secondary network topology diagram according to the backbone index;

[0143] Use a ROTDR device to perform fault monitoring on the trunk optical cable, obtain a time domain reflection signal, and use an SR-LSTM model to perform super-resolution reconstruction and signal analysis on the time domain reflection signal to obtain a fault location and a fault type;

[0144] A state space is established according to the performance status, the fault location and the fault type, and an action space is established according to expert experience and historical operation and maintenance records; the state space and the action space are combined through an Actor-Critic reinforcement learning framework, and reinforcement learning is performed using an intelligent agent to obtain an optimal operation and maintenance strategy.

[0145] After implementing the fault monitoring system B based on the present invention, its performance is compared with the original fault monitoring system A as shown in Table 3. It can be seen from the comparison in the table that the fault monitoring system B based on the present invention is significantly better than the original fault monitoring system A in multiple key performance indicators. First, in terms of fault recognition rate, system B reached 93%, which is 8 percentage points higher than 85% of system A, showing higher accuracy. Secondly, the fault spatial resolution of system B reached 0.4 meters, which is much better than 1.5 meters of system A, which shows that system B can locate the fault point more accurately and improve the refinement of fault detection. In addition, the fault response time of system B is only 1 minute, which is 2 minutes shorter than system A, significantly improving the fault response efficiency. In addition, system B also has functions that system A does not have, including providing line performance detection and online operation and maintenance solutions. These extended functions not only improve the comprehensive performance of the system, but also provide a scientific basis for subsequent operation and maintenance, making operation and maintenance more efficient and intelligent. On the whole, the fault monitoring system B has achieved a comprehensive upgrade in accuracy, precision, efficiency and comprehensiveness of functions, and has important value for the monitoring and operation and maintenance of power communication networks.

[0146] Table 3 Performance comparison of different fault monitoring systems

[0147] performance Fault Monitoring System A Fault Monitoring System B Fault recognition rate 85％ 93％ Fault spatial resolution (meters) 1.5 0.4 Fault response time (minutes) 3 1 Whether to provide line performance detection no yes Whether to provide online operation and maintenance solutions no yes

[0148] The present invention establishes a primary network topology diagram according to the direct communication relationship between the core nodes of the power network, selects key business optical cables according to the business type, and constructs a secondary network topology diagram; by collecting the historical performance data of the secondary link, a performance database is established, and the K-Means algorithm is used for cluster analysis to determine the performance status of the secondary link; at the same time, the trunk index is calculated according to the bandwidth and throughput of the secondary link, so as to determine the trunk optical cable; the ROTDR device is used to monitor the fault of the trunk optical cable, and the signal is super-resolved and reconstructed and analyzed through the SR-LSTM model to accurately obtain the fault location and fault type; based on the performance status, fault location and type, a state space is established, and an action space is constructed in combination with expert experience and historical operation and maintenance records, and the operation and maintenance strategy is optimized through the Actor-Critic reinforcement learning framework to achieve efficient performance maintenance and intelligent fault repair of the trunk optical cable. This method significantly improves the operation and maintenance efficiency of the optical cable and the network reliability, and provides comprehensive monitoring and protection for key business optical cables.

[0149] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-core optical cable fault online monitoring method based on optical fiber sensing technology, characterized in that: include: Establish a first-level network topology diagram based on the direct communication relationship of core nodes; The core nodes include power dispatching center, substation, distribution network and control center; Selecting a key service optical cable according to the service type between the primary nodes of the primary network topology diagram, and establishing a secondary network topology diagram according to the key service optical cable; The critical business optical cable is an optical cable for processing critical business, and the critical business includes dispatching control, protection communication and fault monitoring; Collect and store historical performance data between the secondary links of the secondary network topology diagram, establish a performance database, cluster the historical performance data using a K-Means algorithm, and determine the current performance status of the secondary links based on the clustering results; Calculate a backbone index according to the bandwidth and throughput of the secondary link, and establish a backbone optical cable of the secondary network topology diagram according to the backbone index; Use a ROTDR device to perform fault monitoring on the trunk optical cable, obtain a time domain reflection signal, and use an SR-LSTM model to perform super-resolution reconstruction and signal analysis on the time domain reflection signal to obtain a fault location and a fault type; A state space is established according to the performance status, the fault location and the fault type, and an action space is established according to expert experience and historical operation and maintenance records; the state space and the action space are combined through an Actor-Critic reinforcement learning framework, and reinforcement learning is performed using an intelligent agent to obtain an optimal operation and maintenance strategy.

2. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: Establishing the first-level network topology diagram includes: Determine all the core nodes in the area based on the existing power network database; analyze the communication traffic between each of the core nodes through a network detection tool to determine the communication optical cables directly connected between the core nodes; use a topology tool to model the core nodes and the communication optical cables into a first-level network topology diagram, wherein the core nodes are the first-level nodes of the first-level network topology diagram, and the communication optical cables are the first-level links of the first-level network topology diagram.

3. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: Establishing the secondary network topology diagram includes: Perform traffic analysis on each communication optical cable in the primary network topology diagram to obtain the service type of each communication optical cable; select key service optical cables according to the service type; use a topology tool to model the core nodes and the key service optical cables into a secondary network topology diagram, wherein the core nodes are the secondary nodes of the secondary network topology diagram, and the key service optical cables are the secondary links of the secondary network topology diagram.

4. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: The historical performance data includes bandwidth, delay, throughput, packet loss rate, bit error rate and optical power, and the performance status includes normal status, fiber aging, temperature drift, bandwidth overload, increased signal delay and abnormal fiber dispersion.

5. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: Determining the current performance status of the secondary link includes: Collect the historical performance data of the secondary link, and perform data cleaning and data normalization on the historical performance data to obtain preprocessed data; use the elbow rule to determine the optimal K value, cluster the preprocessed data, and obtain performance status categories; cluster the performance data of the current secondary link, and output the performance status according to the clustering results.

6. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: The calculation formula of the backbone index is: Wherein, M represents the backbone index, B represents the bandwidth, T represents the throughput, α1 represents the bandwidth weight, α2 represents the throughput weight, and α3 represents the utilization weight.

7. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: The SR-LSTM model includes: An input layer, used for receiving the time domain reflection signal; A signal super-resolution layer is used to perform preliminary super-resolution processing on the time domain reflection signal using Fourier interpolation method to generate a low-order super-resolution signal; the preliminary super-resolution processing includes: performing fast Fourier transform on the time domain reflection signal to obtain a frequency domain signal; filling zero values ​​at the central symmetric position of the frequency domain signal to obtain an extended spectrum; performing inverse fast Fourier transform on the extended spectrum to generate a low-order super-resolution signal; An LSTM layer is used to capture the temporal dependency of the preliminary super-resolution signal and generate a high-order super-resolution signal; A feature decoding layer, used for extracting features related to the fault location and fault type according to the high-order super-resolution signal; The output layer is used to output the prediction results of fault location and fault type.

8. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: Obtaining the fault location and the fault type includes: Use the ROTDR device to send optical pulses to the trunk optical cable; record the time delay and intensity information of the reflected signal to obtain the time domain reflection signal; input the time domain reflection signal into the SR-LSTM model to obtain the fault location and the fault type.

9. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 1 is characterized in that: The optimal operation and maintenance strategy is obtained: S601: Establish the state space according to the performance state, the fault location and the fault type, and establish the action space according to the expert experience and the historical operation and maintenance records; S602: Initialize the Actor network and the Critic network, and set the learning rate, discount factor, exploration strategy, and reward function; S603: The agent generates a current action through the Actor network according to the current state, and obtains an immediate reward after the current action interacts with the system environment and returns to the next state; S604: Calculate the update value of the Critic network using the TD error, and update the Actor network according to the TD error; S605: Determine whether the iteration meets the convergence condition. If not, re-execute S603; the convergence condition is that the TD error is less than an error threshold. S606: Obtain the optimal operation and maintenance strategy.

10. The multi-core optical cable fault online monitoring method based on optical fiber sensing technology according to claim 9 is characterized in that: The calculation formula of the reward function is: Where R represents the reward function, P exp represents the expected performance, P act Indicates the actual performance after operation and maintenance, T rep Indicates the operation and maintenance time, C res represents the operation and maintenance cost, ω1 represents the performance weight, ω2 represents the time weight, and ω3 represents the cost weight.

Images