A network fault diagnosis system and method based on quantum computing and machine learning

Abstract

The application discloses a network fault diagnosis system and method based on quantum computing and machine learning, which comprises a data acquisition module, a preprocessing module, a quantum computing module, a machine learning module, an algorithm fusion module and a resource allocation module. The data acquisition module acquires the state data of network nodes and links in real time; the preprocessing module preprocesses the collected data; the quantum computing module quickly screens suspected fault data through a quantum screening algorithm and performs frequency domain analysis and time series analysis; the machine learning module trains a fault classification model according to historical data and classifies real-time data; the algorithm fusion module generates the final fault diagnosis result by combining frequency domain features, time series features, fault types and fault change trends through a multi-level weighted fusion strategy; and the resource allocation module dynamically adjusts network resource allocation according to the diagnosis result. The application significantly improves the efficiency and accuracy of fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a network fault diagnosis system and method based on quantum computing and machine learning. Background Technology

[0002] With the rapid development of information technology, network scale is constantly expanding, and network architecture is becoming increasingly complex. Especially in large-scale distributed systems, the state of network nodes and links is crucial to the performance and stability of the entire system. However, traditional network fault detection and diagnosis methods often suffer from poor real-time performance, low accuracy, and difficulty in fault location, making it difficult to cope with the various challenges in complex network environments.

[0003] Traditional network fault detection methods typically rely on rule-based detection systems, analyzing network state data through simple threshold judgments or static models. These methods usually only respond after a network fault has occurred and lack precision in identifying and locating the fault type. Therefore, when faced with a large number of complex network nodes and links, the efficiency and accuracy of these methods often fail to meet practical requirements.

[0004] In recent years, with the rapid development of technologies such as artificial intelligence, quantum computing, and machine learning, data-driven intelligent fault detection and diagnosis methods have gradually become a research hotspot. Quantum computing, due to its powerful computing capabilities in processing complex data, has become a potential tool for optimizing network fault detection and diagnosis. Furthermore, machine learning models, especially deep learning and recurrent neural networks, can provide accurate fault prediction and classification by learning from historical data, thereby improving the real-time performance and accuracy of fault diagnosis. Although some methods combining quantum computing and machine learning have emerged in existing technologies, they still face the following challenges:

[0005] Data processing complexity: Network fault data is large in volume and complex. How to efficiently process and analyze network status data is an urgent problem to be solved.

[0006] Limitations of quantum computing applications: While quantum computing has enormous theoretical potential, its practical applications still face technical challenges, especially in designing quantum algorithms suitable for network fault diagnosis.

[0007] Issues with the accuracy and real-time nature of fault diagnosis: Network faults usually occur suddenly and may manifest in many different ways. Traditional single models often cannot identify and diagnose the diverse types of faults in a timely and accurate manner.

[0008] Challenges of Algorithm Integration: Existing network fault detection systems often lack effective ways to integrate multiple algorithms such as quantum computing and machine learning, resulting in poor overall system diagnostic performance.

[0009] In conclusion, how to combine quantum computing and machine learning technologies to design an efficient, accurate, and real-time network fault diagnosis system based on quantum computing and machine learning has become a hot research topic. Summary of the Invention

[0010] To address the shortcomings of existing technologies, the present invention aims to provide a network fault diagnosis system and method based on quantum computing and machine learning, which integrates quantum computing and machine learning for network fault diagnosis, significantly improving the efficiency and accuracy of fault diagnosis.

[0011] To achieve the above objectives, the present invention provides the following technical solution: a network fault diagnosis system and method based on quantum computing and machine learning, comprising:

[0012] The data acquisition module is used to collect network status data at each network node and link in real time, as well as historical status data.

[0013] The preprocessing module, connected to the data acquisition module, is used to preprocess each of the network status data and each of the historical status data to obtain preprocessed status data and preprocessed historical data.

[0014] A quantum computing module, connected to the preprocessing module, is used to quickly filter the preprocessed state data according to a preset quantum screening algorithm to obtain suspected fault data, perform frequency domain analysis on the suspected fault data according to quantum Fourier transform to obtain frequency domain features, and perform time feature analysis on the suspected fault data according to a quantum phase estimation algorithm to obtain time series features.

[0015] A machine learning module, connected to the preprocessing module, is used to train a fault classification model based on each of the historical state data, and input the preprocessed state data into the fault classification model to obtain the corresponding fault type.

[0016] An algorithm fusion module, which connects the quantum computing module and the machine learning module respectively, includes:

[0017] The primary fusion unit is used to perform preliminary weighted fusion of the frequency domain features, the time series features, and the fault type to obtain a preliminary fusion result.

[0018] An intermediate fusion unit, connected to the primary fusion unit, is used to predict the fault change trend of the preliminary fusion result based on a preset recurrent neural network, and to form an intermediate fusion result based on the frequency domain features, the time series features, the fault type, and the fault change trend.

[0019] An advanced fusion unit, connected to the intermediate fusion unit, is used to dynamically adjust the frequency domain features according to the fault type and the fault change trend, and generate a final diagnostic result based on the adjusted intermediate fusion result.

[0020] The resource allocation module, connected to the algorithm fusion module, is used to adjust the network resource allocation at each network node and the link according to the final diagnostic result.

[0021] Furthermore, it also includes an external detection module connected to the algorithm fusion module, the external detection module comprising:

[0022] The first detection unit is used to detect multiple power parameters at each of the network nodes and the link in real time.

[0023] The second detection unit is used to detect the performance parameters of multiple devices at each of the network nodes and the link in real time.

[0024] The detection and calculation unit is connected to the first detection unit and the second detection unit respectively. It is used to input each of the power parameters into a preset power stability calculation formula to calculate the power network stability value, and to input each of the equipment performance parameters into a preset initial aging calculation formula to calculate the network equipment aging score.

[0025] The algorithm fusion module further includes a fusion optimization unit connected to the advanced fusion unit. The fusion optimization unit is used to obtain weight optimization coefficients based on the power network stability value and the network equipment aging score.

[0026] The advanced fusion unit optimizes and adjusts the final diagnostic result based on the weight optimization coefficient.

[0027] Furthermore, the external detection module also includes a third detection unit connected to the detection calculation unit, the third detection unit being used to detect device fault parameters at each network node and the link in real time;

[0028] The detection and calculation unit updates the initial aging calculation formula according to the fault parameters of each device to obtain an optimized aging calculation formula. The optimized aging calculation formula is used to calculate the aging score of the network device based on the performance parameters and fault parameters of each device.

[0029] Furthermore, the power parameters include voltage, current load, power frequency, battery health status, and power harmonics, and the power stability calculation formula is configured as follows:

[0030]

[0031] Where S(t) represents the power network stability value at time t, V(t) represents the voltage at time t, I(t) represents the current load at time t, P(t) represents the power consumption at time t, f(t) represents the power supply frequency at time t, H(t) represents the battery health state at time t, and λ represents the preset network stability attenuation coefficient. The power supply harmonics at time t are represented by α, β, and γ, which represent the preset first, second, and third constant coefficients, respectively. δ represents the preset stability attenuation constant. Ω k The stability parameter is used to represent the k-th network node, and N is used to represent the number of network nodes.

[0032] Furthermore, the device fault parameters include failure rate and number of failures, and the device performance parameters include CPU utilization, memory utilization, hard disk health index, network throughput, and network response time.

[0033] The optimized aging calculation formula is configured as follows:

[0034]

[0035] Where L(t) represents the aging score of the network device at time t, and N i (t) represents the number of failures at time t, P i (t) is used to represent the failure rate at time t, α i Used to represent the preset fault weighting factor, β i U(t) represents the preset failure count index, W(t) represents the CPU utilization at time t, Ξ(t) represents the memory utilization at time t, and Θ(t) represents the network throughput at time t. k (t) represents the hard disk health index at time t, φ represents the CPU and memory weighting factor, λ1 represents the preset device aging and decay rate, ξ represents the preset stability decay factor, ρ represents the preset dynamic weighting factor, σ′ represents the network response time, and t0 represents the preset start time.

[0036] Furthermore, the external detection module includes a fourth detection unit, which is used to detect multiple external environmental parameters at each network node and the link in real time. The external environmental parameters include ambient temperature, ambient humidity, ambient air pressure, and ambient magnetic field.

[0037] The fusion optimization unit inputs the power network stability value, the network equipment aging score, the ambient temperature, the ambient humidity, the ambient air pressure, and the ambient magnetic field into a preset weight optimization calculation formula to calculate the weight optimization coefficient.

[0038] Furthermore, the weight optimization calculation formula is configured as follows:

[0039]

[0040] Where W′(t) represents the weight optimization coefficient, and T i (t) represents the ambient temperature at time t, H i (t) represents the ambient humidity at time t, P i ′(t) is used to represent the ambient air pressure at time t, B i (t) represents the environmental magnetic field at time t, α i ′, β i ′, γ i δ i η i These are used to represent the preset first temperature weighting factor, second temperature weighting factor, humidity weighting factor, air pressure weighting factor, and magnetic field weighting factor, respectively; κ is used to represent the preset exponential decay factor; ζ is used to represent the preset circuit stability adjustment coefficient; θ is used to represent the preset equipment aging adjustment factor; σ is used to represent the preset network throughput weighting factor; and t1 is used to represent the preset end time.

[0041] Furthermore, the resource allocation module includes:

[0042] The resource allocation unit is used to identify the network topology to be repaired at each of the network nodes and links based on the final diagnostic results, and to readjust the network resource allocation at each of the network nodes and links based on a preset quantum optimization algorithm.

[0043] A topology adjustment unit, connected to the resource allocation unit, is used to adjust the network topology based on the adjusted network resources.

[0044] Furthermore, the quantum optimization algorithm is the quantum annealing algorithm.

[0045] A network fault diagnosis method based on quantum computing and machine learning, applied to the aforementioned network fault diagnosis system based on quantum computing and machine learning, includes:

[0046] Step S1: The data acquisition module collects network status data at each network node and link in real time, as well as historical status data.

[0047] Step S2: The preprocessing module preprocesses each of the network state data and each of the historical state data to obtain preprocessed state data and preprocessed historical data.

[0048] Step S3: The quantum computing module quickly filters the preprocessed state data according to the preset quantum screening algorithm to obtain suspected fault data, performs frequency domain analysis on the suspected fault data according to quantum Fourier transform to obtain frequency domain features, and performs time feature analysis on the suspected fault data according to the quantum phase estimation algorithm to obtain time series features.

[0049] Step S4: The machine learning module trains a fault classification model based on each of the historical state data, and inputs the preprocessed state data into the fault classification model to obtain the corresponding fault type.

[0050] Step S5: The primary fusion unit performs preliminary weighted fusion of the frequency domain features, the time series features, and the fault type to obtain a preliminary fusion result; the intermediate fusion unit predicts the fault change trend of the preliminary fusion result based on a preset recurrent neural network, and forms an intermediate fusion result based on the frequency domain features, the time series features, the fault type, and the fault change trend; the advanced fusion unit dynamically adjusts the frequency domain features according to the fault type and the fault change trend, and generates a final diagnostic result based on the adjusted intermediate fusion result.

[0051] Step S6: The resource allocation module adjusts the network resource allocation at each network node and link according to the final diagnostic result.

[0052] The beneficial effects of this invention are:

[0053] This invention achieves rapid screening and accurate analysis of network state data by combining quantum computing and machine learning modules. The quantum screening algorithm can quickly identify suspected fault data in large-scale datasets, significantly improving the real-time performance and processing efficiency of fault detection. By combining quantum Fourier transform for frequency domain analysis of suspected fault data and quantum phase estimation for temporal feature analysis, the invention can comprehensively and accurately capture fault characteristics in the network.

[0054] Meanwhile, this invention effectively combines frequency domain features, time series features, and fault types through a multi-level weighted fusion strategy in its algorithm fusion module. The primary fusion unit performs initial fusion of different features, the intermediate fusion unit predicts fault change trends based on a recurrent neural network, and the advanced fusion unit further dynamically adjusts the features and generates the final fault diagnosis result. Through this multi-level algorithm fusion, this invention achieves more accurate fault prediction and fault evolution trend identification, thereby improving the robustness and accuracy of the overall diagnostic system.

[0055] Furthermore, by integrating quantum computing and machine learning, this invention can not only diagnose faults but also predict the changing trends of network faults. Through recurrent neural networks predicting these trends, potential faults can be anticipated in advance, allowing relevant personnel to take preventative measures. Moreover, by incorporating a resource allocation module, this invention can dynamically adjust network resource allocation based on the final diagnostic results, effectively optimizing network performance and improving network stability and resource utilization. Attached Figure Description

[0056] Figure 1 This is a schematic diagram of the network fault diagnosis system based on quantum computing and machine learning in this invention;

[0057] Figure 2 This is a flowchart of the steps in the network fault diagnosis method based on quantum computing and machine learning in this invention.

[0058] Reference numerals: 1. Data acquisition module; 2. Preprocessing module; 3. Quantum computing module; 4. Machine learning module; 5. Algorithm fusion module; 51. Primary fusion unit; 52. Intermediate fusion unit; 53. Advanced fusion unit; 54. Fusion optimization unit; 6. Resource allocation module; 61. Resource allocation unit; 62. Topology adjustment unit; 7. External detection module; 71. First detection unit; 72. Second detection unit; 73. Detection calculation unit; 74. Third detection unit; 75. Fourth detection unit. Detailed Implementation

[0059] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Identical components are denoted by the same reference numerals. It should be noted that the terms "front," "rear," "left," "right," "upper," and "lower" used in the following description refer to directions in the accompanying drawings, and the terms "bottom surface," "top surface," "inner," and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.

[0060] Example 1, referring to Figure 1This is the first embodiment of the present invention, which provides a network fault diagnosis system based on quantum computing and machine learning. This system integrates quantum computing and machine learning for network fault diagnosis, significantly improving the efficiency and accuracy of fault diagnosis. The system includes:

[0061] Data acquisition module 1 is used to collect network status data at each network node and link in real time, as well as historical status data;

[0062] Preprocessing module 2, connected to data acquisition module 1, is used to preprocess each network status data and each historical status data to obtain preprocessed status data and preprocessed historical data.

[0063] Quantum computing module 3, connected to preprocessing module 2, is used to quickly filter the preprocessed state data according to a preset quantum screening algorithm to obtain suspected fault data, and to perform frequency domain analysis on the suspected fault data according to quantum Fourier transform to obtain frequency domain features, and to perform time feature analysis on the suspected fault data according to a quantum phase estimation algorithm to obtain time series features.

[0064] Machine learning module 4, connected to preprocessing module 2, is used to train fault classification models based on historical state data, and input preprocessed state data into the fault classification models to obtain the corresponding fault types.

[0065] Algorithm fusion module 5, which connects to quantum computing module 3 and machine learning module 4 respectively, includes:

[0066] The primary fusion unit 51 is used to perform preliminary weighted fusion of frequency domain features, time series features and fault types to obtain preliminary fusion results.

[0067] The intermediate fusion unit 52 is connected to the primary fusion unit 51 and is used to predict the fault change trend of the preliminary fusion result based on a preset recurrent neural network, and to form an intermediate fusion result based on frequency domain features, time series features, fault type and fault change trend.

[0068] The advanced fusion unit 53 is connected to the intermediate fusion unit 52 and is used to dynamically adjust the frequency domain characteristics according to the fault type and fault change trend, and generate the final diagnostic result based on the adjusted intermediate fusion result.

[0069] Resource allocation module 6 and connection algorithm fusion module 5 are used to adjust the network resource allocation at each network node and link based on the final diagnostic results.

[0070] Working principle of Example 1:

[0071] Data acquisition module 1 collects relevant network status data in real time by deploying sensors at each network node and link. All data is collected through distributed acquisition units and transmitted to the data center in a unified manner. The real-time network status data includes the node's bandwidth utilization, latency, packet loss rate, throughput, etc., while the historical status data includes network status data at historical moments, fault records, maintenance records, etc.

[0072] Preprocessing module 2 is responsible for standardizing and cleaning the collected network status data and historical status data to remove noisy and outlier data, ensuring data quality. The data preprocessing process includes:

[0073] Data cleaning: removing irrelevant data, filling in missing data, and eliminating possible duplicate data.

[0074] Data standardization: Converting network status data from different sources into a unified format and normalizing the data so that data from different network nodes can be compared on the same scale.

[0075] Anomaly detection: Use rules or statistical methods to identify and remove outlier data points to ensure the accuracy and reliability of the data.

[0076] Quantum computing module 3 uses quantum screening algorithms, quantum Fourier transform, and quantum phase estimation algorithms to perform rapid screening and analysis based on preprocessed network state data.

[0077] Machine learning module 4 uses historical state data for training to obtain a fault classification model, and inputs the preprocessed network state data into the fault classification model to obtain the fault type.

[0078] The training process of the fault classification model includes: using historical network state data to train different machine learning models (such as support vector machines, decision trees, deep neural networks, etc.) for fault type classification. The machine learning models are trained using labeled historical data, continuously improving classification accuracy. Preprocessed network state data is input into the fault classification model, which outputs the fault type based on this data, such as node fault, link fault, bandwidth bottleneck, etc. Fault type identification is the foundation for subsequent fusion analysis.

[0079] The algorithm fusion module 5 is the core of this system. It combines the analysis results from the quantum computing module 3 and the machine learning module 4, integrates information from multiple sources, and outputs the final fault diagnosis result. It includes three sub-modules: a primary fusion unit 51, an intermediate fusion unit 52, and a high-level fusion unit 53. The primary fusion unit 51 weights and fuses the frequency domain features and time series features output by the quantum computing module 3 with the fault type output by the machine learning module 4 to obtain a preliminary fusion result. This stage of fusion mainly relies on weighted averaging or other simple weighting strategies. The intermediate fusion unit 52 predicts the fault change trend of the preliminary fusion result based on a pre-defined recurrent neural network (RNN). The RNN can capture the time dependence of the fault and predict its possible evolution trend. By combining frequency domain features, time series features, fault type, and its change trend, a more accurate intermediate fusion result is formed. The high-level fusion unit 53 dynamically adjusts the frequency domain features according to the fault type and fault change trend, and generates the final fault diagnosis result based on the adjusted intermediate fusion result. The intermediate fusion result is then adjusted. Based on the fault type and trend, the frequency domain characteristics of the output of quantum computing module 3 are dynamically adjusted to enhance the accuracy of fault diagnosis.

[0080] Based on the final diagnostic results, the resource allocation module 6 reallocates resources to network nodes and links to ensure network stability and efficiency.

[0081] This embodiment combines quantum computing module 3 and machine learning module 4 to achieve rapid screening and accurate analysis of network state data. The quantum screening algorithm can quickly identify suspected fault data in large-scale data, significantly improving the real-time performance and processing efficiency of fault detection. By combining quantum Fourier transform for frequency domain analysis of suspected fault data and quantum phase estimation algorithm for time feature analysis, fault characteristics in the network can be captured comprehensively and accurately.

[0082] Meanwhile, this embodiment effectively combines frequency domain features, time series features, and fault types through a multi-level weighted fusion strategy in algorithm fusion module 5. The primary fusion unit 51 performs initial fusion of different features, the intermediate fusion unit 52 predicts fault change trends based on a recurrent neural network, and the advanced fusion unit 53 further dynamically adjusts the features and generates the final fault diagnosis result. Through this multi-level algorithm fusion, this embodiment can achieve more accurate fault prediction and fault evolution trend identification, thereby improving the robustness and accuracy of the overall diagnostic system.

[0083] Furthermore, by integrating quantum computing and machine learning, this embodiment can not only diagnose faults but also predict the changing trends of network faults. Through the prediction of fault trends using recurrent neural networks, potential faults can be anticipated in advance, allowing relevant personnel to take preventative measures. Additionally, by incorporating a resource allocation module 6, this embodiment can dynamically adjust network resource allocation based on the final diagnostic results, effectively optimizing network performance and improving network stability and resource utilization.

[0084] Example 2 is the second embodiment of the present invention. Unlike the previous embodiment, this embodiment provides an external detection module 7, which can further improve the accuracy of network fault diagnosis. It includes an external detection module 7 and a connection algorithm fusion module 5. The external detection module 7 includes:

[0085] The first detection unit 71 is used to detect multiple power parameters at each network node and link in real time.

[0086] The second detection unit 72 is used to detect the performance parameters of multiple devices at each network node and link in real time.

[0087] The detection and calculation unit 73 is connected to the first detection unit 71 and the second detection unit 72 respectively. It is used to input each power parameter into the preset power stability calculation formula to calculate the power network stability value, and to input each device performance parameter into the preset initial aging calculation formula to calculate the network device aging score.

[0088] The algorithm fusion module 5 also includes a fusion optimization unit 54, which is connected to the advanced fusion unit 53. The fusion optimization unit 54 is used to obtain the weight optimization coefficient based on the power network stability value and the network equipment aging score.

[0089] Advanced fusion unit 53 optimizes and adjusts the final diagnostic results based on the weight optimization coefficients.

[0090] Working principle of Example 2:

[0091] Power parameters reflect the stability of the power system and the power supply quality of network equipment, helping the system detect the impact of power anomalies on network equipment failures. Equipment performance parameters reflect the aging status of network equipment. The detection and calculation unit 73 calculates the power network stability value (reflecting the network stability of network nodes) based on each power parameter, and the network equipment aging score (reflecting the aging status of network nodes) based on each equipment performance parameter. The fusion optimization unit 54 processes the power network stability value and the network equipment aging score to obtain weight optimization coefficients. The advanced fusion unit 53 then multiplies these weight optimization coefficients with the final diagnostic result to optimize and adjust the final diagnostic result. This optimization avoids the influence of the power network stability and equipment aging status of network nodes, improves the calculation accuracy of the final diagnostic result, and further enhances the accuracy of network fault diagnosis.

[0092] Preferably, the power parameters include voltage, current load, power frequency, battery health status, and power harmonics, and the power stability calculation formula is configured as follows:

[0093]

[0094] Where S(t) represents the power network stability value at time t, V(t) represents the voltage at time t, I(t) represents the current load at time t, P(t) represents the power consumption at time t, f(t) represents the power supply frequency at time t, H(t) represents the battery health state at time t, and λ represents the preset network stability attenuation coefficient. The power supply harmonics at time t are represented by α, β, and γ, which represent the preset first, second, and third constant coefficients, respectively. δ represents the preset stability attenuation constant. Ω k The stability parameter is used to represent the k-th network node, and N represents the number of network nodes.

[0095] Specifically, in this embodiment, the range of the power network stability value is [0,1], where 0 represents extreme instability and 1 represents complete stability. The power network stability value is a dynamic quantity that changes over time, and can be calculated in real-time based on factors such as system voltage, current, power frequency, battery health, and harmonics. Power harmonics represent the harmonic components generated by nonlinear loads or imbalances in the power system. The network stability decay coefficient represents the rate at which the power network stability decays over time. The first, second, and third constant coefficients are used to adjust the weights of the contributions of voltage, current load, power frequency, battery health, and power harmonics to network stability. The stability decay constant is a constant that adjusts the system stability decay, affecting the weighting of the summation term. The stability parameter is used to measure the stability impact of a node. This formula integrates the influence of various important factors in the power network (voltage, current load, power frequency, battery health, and power harmonics) on power network stability, and combines multiple time-domain and spatial-domain variables through integration and summation functions, enabling accurate calculation of the power network stability value.

[0096] Preferably, the external detection module 7 further includes a third detection unit 74 connected to the detection calculation unit 73. The third detection unit 74 is used to detect the equipment fault parameters at each network node and link in real time.

[0097] The detection and calculation unit 73 updates the initial aging calculation formula based on the fault parameters of each device to obtain an optimized aging calculation formula. The optimized aging calculation formula is used to calculate the aging score of the network device based on the performance parameters and fault parameters of each device.

[0098] Specifically, in this embodiment, the fault parameters generated after a network node device failure will affect the aging score of the network device, thereby affecting the accuracy of fault diagnosis. By optimizing and updating the initial aging calculation formula using the detected device fault parameters, the influence of fault parameters on device aging calculation is introduced, thus improving the accuracy of network device aging score calculation.

[0099] Preferably, the equipment fault parameters include the failure rate and the number of failures, and the equipment performance parameters include the CPU utilization rate, memory utilization rate, hard disk health index, network throughput, and network response time.

[0100] The optimized aging calculation formula is configured as follows:

[0101]

[0102] Where L(t) represents the network device aging score at time t, and N i (t) is used to represent the number of failures at time t, P i (t) is used to represent the failure rate at time t, αi Used to represent the preset fault weighting factor, β i U(t) represents the preset failure rate index, W(t) represents the CPU utilization rate at time t, Ξ(t) represents the memory utilization rate at time t, and Θ(t) represents the network throughput at time t. k (t) represents the hard disk health index at time t, φ represents the CPU and memory weighting factor, λ1 represents the preset device aging and decay rate, ξ represents the preset stability decay factor, ρ represents the preset dynamic weighting factor, σ′ represents the network response time, and t0 represents the preset start time.

[0103] Specifically, in this embodiment, the range of the equipment aging score is [0,1], where 0 indicates that the equipment is completely healthy and not aged; and 1 indicates that the equipment is completely aged and in an unusable state. This reflects the impact of the number of failures and the failure rate on equipment aging. By weighting with a failure weighting factor and a failure frequency index, the influence of the number of failures is ensured to change non-linearly, and the failure rate is also adjusted by weighting. This indicates the impact of device load (CPU and memory utilization) on aging, expressed through a time decay term. This simulates the accelerated aging of equipment over time. Health Index Section: This reflects the impact of the health status of all nodes on aging; the lower the node's health index, the higher its aging score. Throughput section: It describes the impact of network throughput changes over time on aging; the higher the throughput, the heavier the equipment load, and the faster the aging process.

[0104] Preferably, the external detection module 7 includes a fourth detection unit 75, which is used to detect multiple external environmental parameters at each network node and link in real time. The external environmental parameters include ambient temperature, ambient humidity, ambient air pressure and ambient magnetic field.

[0105] The fusion optimization unit 54 inputs the power network stability value, network equipment aging score, ambient temperature, ambient humidity, ambient air pressure and ambient magnetic field into the preset weight optimization calculation formula to calculate the weight optimization coefficient.

[0106] Specifically, in this embodiment, changes in the external environment can accelerate the aging of network node devices, thereby affecting the fault diagnosis of network node devices. By introducing external environment parameters to optimize and correct the weight optimization coefficients, the accuracy of network fault diagnosis can be further improved.

[0107] Preferably, the weight optimization calculation formula is configured as follows:

[0108]

[0109] Where W′(t) represents the weight optimization coefficient, and T i (t) represents the ambient temperature at time t, H i (t) is used to represent the ambient humidity at time t, P i B'(t) is used to represent the ambient air pressure at time t. i (t) is used to represent the environmental magnetic field at time t, α i ′, β i ′, γ i δ i η i These are used to represent the preset first temperature weighting factor, second temperature weighting factor, humidity weighting factor, air pressure weighting factor, and magnetic field weighting factor, respectively; κ is used to represent the preset exponential decay factor; ζ is used to represent the preset circuit stability adjustment coefficient; θ is used to represent the preset equipment aging adjustment factor; σ is used to represent the preset network throughput weighting factor; and t1 is used to represent the preset end time.

[0110] Specifically, in this embodiment, the weight optimization calculation formula integrates multiple factors (ambient temperature, humidity, air pressure, magnetic field, equipment aging, etc.) and employs mechanisms such as weighting, integration, and exponential decay to enable dynamic and intelligent network fault optimization. This not only improves computational efficiency and operational flexibility but also enhances the system's adaptability and robustness, helping network administrators make better fault prevention and optimization decisions, thereby ensuring the stable operation and efficient maintenance of the network system.

[0111] Preferably, resource allocation module 6 includes:

[0112] Resource allocation unit 61 is used to identify the network topology to be repaired at each network node and link based on the final diagnostic results, and to readjust the network resource allocation at each network node and link based on a preset quantum optimization algorithm.

[0113] The topology adjustment unit 62 and the resource allocation unit 61 are used to adjust the network topology according to the adjusted network resources.

[0114] Preferably, the quantum optimization algorithm is the quantum annealing algorithm.

[0115] Specifically, in this embodiment, the resource allocation unit 61 uses the quantum annealing algorithm to allocate network resources and adjust the network topology. Leveraging the advantages of quantum computing, it optimizes resource allocation for network nodes and links, ensuring rapid recovery and maintaining network performance after a network failure. The topology adjustment unit 62 receives the optimized resource allocation results from the resource allocation unit 61 and dynamically adjusts the network topology. The adjustment process includes optimizing routing paths, adjusting bandwidth allocation, and reallocating computing resources to ensure efficient network traffic transmission under the new resource allocation scheme.

[0116] A network fault diagnosis method based on quantum computing and machine learning is applied to the aforementioned network fault diagnosis system based on quantum computing and machine learning, such as... Figure 2 As shown, it includes:

[0117] Step S1: Data acquisition module 1 collects network status data at each network node and link in real time, as well as historical status data.

[0118] Step S2: Preprocessing module 2 preprocesses each network status data and each historical status data to obtain preprocessed status data and preprocessed historical data.

[0119] Step S3: The quantum computing module 3 quickly filters the preprocessed state data according to the preset quantum screening algorithm to obtain suspected fault data, and performs frequency domain analysis on the suspected fault data according to the quantum Fourier transform to obtain frequency domain features, and performs time feature analysis on the suspected fault data according to the quantum phase estimation algorithm to obtain time series features.

[0120] Step S4: Machine learning module 4 trains fault classification models based on each historical state data, and inputs the preprocessed state data into the fault classification models to obtain the corresponding fault types.

[0121] In step S5, the primary fusion unit 51 performs preliminary weighted fusion of frequency domain features, time series features, and fault type to obtain a preliminary fusion result; the intermediate fusion unit 52 predicts the fault change trend of the preliminary fusion result based on a preset recurrent neural network, and forms an intermediate fusion result based on frequency domain features, time series features, fault type, and fault change trend; the advanced fusion unit 53 dynamically adjusts the frequency domain features according to the fault type and fault change trend, and generates the final diagnostic result based on the adjusted intermediate fusion result.

[0122] Step S6: The resource allocation module 6 adjusts the network resource allocation at each network node and link based on the final diagnostic results.

[0123] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principle of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A network fault diagnosis system based on quantum computing and machine learning, characterized in that, include: The data acquisition module (1) is used to collect network status data at each network node and link in real time, as well as historical status data. The preprocessing module (2) is connected to the data acquisition module (1) and is used to preprocess each of the network status data and each of the historical status data to obtain preprocessed status data and preprocessed historical data. The quantum computing module (3) is connected to the preprocessing module (2) and is used to quickly filter the preprocessed state data according to the preset quantum screening algorithm to obtain suspected fault data, and to perform frequency domain analysis on the suspected fault data according to the quantum Fourier transform to obtain frequency domain features, and to perform time feature analysis on the suspected fault data according to the quantum phase estimation algorithm to obtain time series features. The machine learning module (4) is connected to the preprocessing module (2) and is used to train a fault classification model based on each of the historical state data, and input the preprocessed state data into the fault classification model to obtain the corresponding fault type. The algorithm fusion module (5) is connected to the quantum computing module (3) and the machine learning module (4) respectively, and includes: The primary fusion unit (51) is used to perform preliminary weighted fusion of the frequency domain features, the time series features and the fault type to obtain a preliminary fusion result; Intermediate fusion unit (52), connected to the primary fusion unit (51), is used to predict the fault change trend of the preliminary fusion result based on a preset recurrent neural network, and to form an intermediate fusion result based on the frequency domain features, the time series features, the fault type and the fault change trend; Advanced fusion unit (53), connected to intermediate fusion unit (52), is used to dynamically adjust the frequency domain features according to the fault type and the fault change trend, and generate the final diagnostic result based on the adjusted intermediate fusion result; The resource allocation module (6) is connected to the algorithm fusion module (5) and is used to adjust the network resource allocation of each network node and the link according to the final diagnostic result.

2. The network fault diagnosis system based on quantum computing and machine learning according to claim 1, characterized in that: It also includes an external detection module (7), connected to the algorithm fusion module (5), the external detection module (7) comprising: The first detection unit (71) is used to detect multiple power parameters at each of the network nodes and the link in real time; The second detection unit (72) is used to detect the performance parameters of each network node and multiple devices at the link in real time; The detection and calculation unit (73) is connected to the first detection unit (71) and the second detection unit (72) respectively. It is used to input each of the power parameters into the preset power stability calculation formula to calculate the power network stability value, and to input each of the equipment performance parameters into the preset initial aging calculation formula to calculate the network equipment aging score. The algorithm fusion module (5) further includes a fusion optimization unit (54) connected to the advanced fusion unit (53). The fusion optimization unit (54) is used to obtain weight optimization coefficients based on the power network stability value and the network equipment aging score. The advanced fusion unit (53) optimizes and adjusts the final diagnostic result according to the weight optimization coefficient.

3. The network fault diagnosis system based on quantum computing and machine learning according to claim 2, characterized in that: The external detection module (7) further includes a third detection unit (74) connected to the detection calculation unit (73). The third detection unit (74) is used to detect the equipment fault parameters of each network node and the link in real time. The detection calculation unit (73) updates the initial aging calculation formula according to the fault parameters of each device to obtain an optimized aging calculation formula. The optimized aging calculation formula is used to calculate the aging score of the network device according to the performance parameters and fault parameters of each device.

4. The network fault diagnosis system based on quantum computing and machine learning according to claim 3, characterized in that: The power parameters include voltage, current load, power frequency, battery health status, and power harmonics. The power stability calculation formula is configured as follows: Where S(t) represents the power network stability value at time t, V(t) represents the voltage at time t, I(t) represents the current load at time t, P(t) represents the power consumption at time t, f(t) represents the power supply frequency at time t, H(t) represents the battery health state at time t, and λ represents the preset network stability attenuation coefficient. The power supply harmonics at time t are represented by α, β, and γ, which represent the preset first, second, and third constant coefficients, respectively. δ represents the preset stability attenuation constant. Ω k The stability parameter is used to represent the k-th network node, and N is used to represent the number of network nodes.

5. The network fault diagnosis system based on quantum computing and machine learning according to claim 4, characterized in that: The device fault parameters include failure rate and number of failures, and the device performance parameters include CPU utilization, memory utilization, hard disk health index, network throughput, and network response time. The optimized aging calculation formula is configured as follows: Where L(t) represents the aging score of the network device at time t, and N i (t) represents the number of failures at time t, P i (t) is used to represent the failure rate at time t, α i Used to represent the preset fault weighting factor, β i U(t) represents the preset failure count index, W(t) represents the CPU utilization at time t, Ξ(t) represents the memory utilization at time t, and Θ(t) represents the network throughput at time t. k (t) represents the hard disk health index at time t, φ represents the CPU and memory weighting factor, λ1 represents the preset device aging and decay rate, ξ represents the preset stability decay factor, ρ represents the preset dynamic weighting factor, σ′ represents the network response time, and t0 represents the preset start time.

6. The network fault diagnosis system based on quantum computing and machine learning according to claim 5, characterized in that: The external detection module (7) includes a fourth detection unit (75), which is used to detect multiple external environmental parameters of each network node and the link in real time. The external environmental parameters include ambient temperature, ambient humidity, ambient air pressure and ambient magnetic field. The fusion optimization unit (54) inputs the power network stability value, the network equipment aging score, the ambient temperature, the ambient humidity, the ambient air pressure and the ambient magnetic field into a preset weight optimization calculation formula to calculate the weight optimization coefficient.

7. The network fault diagnosis system based on quantum computing and machine learning according to claim 6, characterized in that: The weight optimization calculation formula is configured as follows: Where W′(t) represents the weight optimization coefficient, and T i (t) represents the ambient temperature at time t, H i (t) represents the ambient humidity at time t, P i ′(t) is used to represent the ambient air pressure at time t, B i (t) represents the environmental magnetic field at time t, α i ′, β i ′, γ i δ i η i These are used to represent the preset first temperature weighting factor, second temperature weighting factor, humidity weighting factor, air pressure weighting factor, and magnetic field weighting factor, respectively; κ is used to represent the preset exponential decay factor; ζ is used to represent the preset circuit stability adjustment coefficient; θ is used to represent the preset equipment aging adjustment factor; σ is used to represent the preset network throughput weighting factor; and t1 is used to represent the preset end time.

8. The network fault diagnosis system based on quantum computing and machine learning according to claim 1, characterized in that: The resource allocation module (6) includes: The resource allocation unit (61) is used to identify the network topology to be repaired at each of the network nodes and links based on the final diagnostic results, and to readjust the network resource allocation at each of the network nodes and links based on a preset quantum optimization algorithm. The topology adjustment unit (62) is connected to the resource allocation unit (61) and is used to adjust the network topology according to the adjusted network resources.

9. The network fault diagnosis system based on quantum computing and machine learning according to claim 8, characterized in that: The quantum optimization algorithm is the quantum annealing algorithm.

10. A network fault diagnosis method based on quantum computing and machine learning, applied to the network fault diagnosis system based on quantum computing and machine learning as described in any one of claims 1-9, characterized in that, include: Step S1, the data acquisition module (1) collects network status data at each network node and link in real time, as well as historical status data; Step S2, the preprocessing module (2) preprocesses each of the network state data and each of the historical state data to obtain preprocessed state data and preprocessed historical data; Step S3, the quantum computing module (3) quickly filters the preprocessed state data according to the preset quantum screening algorithm to obtain suspected fault data, and performs frequency domain analysis on the suspected fault data according to the quantum Fourier transform to obtain frequency domain features, and performs time feature analysis on the suspected fault data according to the quantum phase estimation algorithm to obtain time series features; Step S4, the machine learning module (4) trains a fault classification model based on each of the historical state data, and inputs the preprocessed state data into the fault classification model to obtain the corresponding fault type; Step S5: The primary fusion unit (51) performs preliminary weighted fusion of the frequency domain features, the time series features, and the fault type to obtain a preliminary fusion result; the intermediate fusion unit (52) predicts the fault change trend of the preliminary fusion result based on a preset recurrent neural network, and forms an intermediate fusion result based on the frequency domain features, the time series features, the fault type, and the fault change trend. The advanced fusion unit (53) dynamically adjusts the frequency domain features according to the fault type and the fault change trend, and generates the final diagnostic result based on the adjusted intermediate fusion result; Step S6, the resource allocation module (6) adjusts the network resource allocation at each network node and the link according to the final diagnosis result.

Images