Intelligent remote operation and maintenance method and platform for machine room equipment

Abstract

The invention discloses an intelligent remote operation and maintenance method and platform for machine room equipment, and relates to the technical field of intelligent operation and maintenance, and the method comprises the steps: constructing a Bayesian probability model, and predicting the fault probability distribution of the machine room equipment in combination with optical signal features and current harmonic features; according to the fault probability distribution of the machine room equipment, converting the fault coordinate into an equipment logic identifier, detecting a quantum invisible state transmission link of the machine room equipment, and generating a machine room equipment switching instruction according to a detection result; and sending a Bell state measurement command to the fault equipment according to the machine room equipment switching instruction, and performing quantum state reconstruction and machine room equipment switching. According to the method, the multi-layer Bayesian probability model based on Gaussian distribution, Granger causal test and variational inference is constructed, nonlinear correlation analysis of optical signal wavelength shift and current harmonic characteristics is achieved, weak symptoms of potential faults of equipment can be accurately captured, and therefore the sensitivity and reliability of fault prediction are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent operation and maintenance technology, and in particular to an intelligent remote operation and maintenance method and platform for computer room equipment. Background Art

[0002] As data centers continue to expand, intelligent remote operation and maintenance (O&M) of equipment in computer rooms has become crucial for ensuring the reliability of IT infrastructure. Traditional O&M methods primarily rely on threshold alerts and manual inspections. In recent years, real-time monitoring and machine learning-based predictive technologies based on the Internet of Things (IoT) have been gradually introduced. However, these methods still have limitations in terms of real-time performance, multi-source data fusion, and proactive intervention capabilities. In particular, they lack the accuracy to capture physical layer anomalies such as optical signal wavelength deviation and current harmonics, resulting in a high rate of false alarms for fault warnings.

[0003] Existing technology often lacks intelligent management capabilities for quantum communication links in computer room equipment operations and maintenance systems. When equipment fails, traditional methods can only perform simple service switching, but cannot guarantee the continuity of quantum state transmission. Furthermore, existing solutions often use fixed thresholds to determine equipment risk levels, making them difficult to adapt to complex and changing operating environments and resulting in delayed responses to sudden failures. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent remote operation and maintenance method for computer room equipment to solve the technical problems that the existing computer room operation and maintenance system cannot guarantee the continuity of quantum state transmission and has a delayed response to sudden faults.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent remote operation and maintenance method for equipment in a computer room, comprising monitoring optical signal wavelength offset data and current harmonic data, and performing preprocessing;

[0008] Construct a Bayesian probability model and combine it with optical signal characteristics and current harmonic characteristics to predict the failure probability distribution of equipment in the computer room;

[0009] According to the fault probability distribution of the equipment in the computer room, the fault coordinates are converted into equipment logical identifiers, and the quantum teleportation links of the equipment in the computer room are detected. Based on the detection results, the equipment switching instructions in the computer room are generated;

[0010] According to the equipment switching instructions in the computer room, a Bell state measurement command is sent to the faulty equipment, and quantum state reconstruction and computer room equipment switching are performed.

[0011] As a preferred solution of the intelligent remote operation and maintenance method for computer room equipment of the present invention, wherein: the optical signal wavelength offset data includes the deviation between the center wavelength value and the reference wavelength, the offset duration and the change rate;

[0012] The current harmonic data includes the amplitude, total harmonic distortion, phase angle and spectrum energy distribution of the harmonic components;

[0013] The preprocessing includes data normalization, noise filtering, outlier extraction and time series alignment.

[0014] As a preferred solution of the intelligent remote operation and maintenance method for computer room equipment of the present invention, the steps of constructing the Bayesian probability model are as follows:

[0015] Gaussian distribution is used to fit the optical signal wavelength deviation data and current harmonic data into physical layer nodes;

[0016] Based on the conditional probability table and historical fault data, the latent variable nodes are constructed by defining the dependency relationship between optical signal anomalies and latent variable nodes.

[0017] Based on the latent variable nodes, the application layer nodes are constructed using the logistic regression algorithm;

[0018] Granger causality test is used to analyze the causal relationship between physical layer nodes and latent variable nodes, and a hierarchical directed acyclic graph is constructed using BayesPy.

[0019] Based on physical layer nodes, latent variable nodes, application layer nodes and hierarchical directed acyclic graph, a Bayesian probability model is constructed through the EM algorithm and variational inference.

[0020] As a preferred solution of the intelligent remote operation and maintenance method for computer room equipment of the present invention, the steps of combining optical signal characteristics and current harmonic characteristics to predict the failure probability distribution of computer room equipment are as follows:

[0021] Based on the pre-processed optical signal wavelength offset data, optical signal features are extracted through time-frequency analysis;

[0022] Based on the pre-processed current harmonic data, the current harmonic characteristics are extracted through fast Fourier transform and harmonic distortion analysis;

[0023] The optical signal characteristics and current harmonic characteristics are input into the Bayesian probability model, and the real-time failure probability P(D k );

[0024] The spatial interpolation kernel density estimation algorithm is used to map the failure probabilities of all equipment in the computer room according to their spatial locations to generate the failure probability distribution of the equipment in the computer room.

[0025] As a preferred solution of the intelligent remote operation and maintenance method for computer room equipment of the present invention, wherein: the fault coordinates are converted into a device logical identifier according to the fault probability distribution of the computer room equipment, the steps are as follows:

[0026] Based on the statistical analysis of historical fault data, define the risk warning threshold F1;

[0027] When P(D k )≥F1, the current equipment in the computer room is considered to be high-risk equipment;

[0028] Based on the failure probability distribution of equipment in the computer room, the location coordinates of high-risk equipment are identified, and the logical identifiers of high-risk equipment are identified from the BIM database.

[0029] As a preferred solution of the intelligent remote operation and maintenance method for computer room equipment of the present invention, wherein: the quantum teleportation link of the computer room equipment is detected, and the computer room equipment switching instruction is generated according to the detection result, the steps are as follows:

[0030] Based on the logical identifiers of high-risk devices, QKD is used to detect the survival status of entangled pairs between devices and identify surviving channels;

[0031] The entanglement degree and quantum bit error rate of the surviving channel are measured in real time, and the quantum channel quality score Q is obtained through compressed sensing quantum tomography method;

[0032] Based on the statistical analysis of historical quantum communication data, the channel quality threshold Q1 is defined;

[0033] When Q<Q1, the quantum channel quality is considered to be substandard, and a device switching instruction is generated through QNMP.

[0034] As a preferred solution of the intelligent remote operation and maintenance method for computer room equipment of the present invention, wherein: according to the computer room equipment switching instruction, a Bell state measurement command is sent to the faulty equipment, and quantum state reconstruction and computer room equipment switching are performed, the steps are as follows:

[0035] Based on the device switching instruction, a Bell state measurement command is sent to the high-risk device through the quantum control interface. A polarization beam splitter is used to perform Bell state analysis, and a Bell basis joint measurement of quantum bits is performed on the entangled particles in the quantum memory of the high-risk device to generate a 2-bit classical measurement result.

[0036] Based on the 2-bit classical measurement results, the quantum state is reconstructed, and the reconstructed state fidelity Y is verified by compressed sensing quantum tomography.

[0037] Based on the fidelity of the reconstructed state, the load balancer is used to migrate business traffic to the backup equipment in the backup computer room, release the quantum resources of high-risk equipment, and generate a computer room equipment switching report.

[0038] In a second aspect, the present invention provides an intelligent remote operation and maintenance platform for computer room equipment, comprising a data acquisition module, a fault probability prediction module, an instruction generation module, and an equipment switching module;

[0039] Data acquisition module, used to monitor optical signal wavelength offset data and current harmonic data, and perform pre-processing;

[0040] The fault probability prediction module is used to build a Bayesian probability model and combine the optical signal characteristics and current harmonic characteristics to predict the fault probability distribution of equipment in the computer room;

[0041] The instruction generation module is used to convert the fault coordinates into device logical identifiers based on the fault probability distribution of the equipment in the computer room, detect the quantum teleportation link of the equipment in the computer room, and generate the equipment switching instructions based on the detection results;

[0042] The equipment switching module is used to send Bell state measurement commands to the faulty equipment according to the equipment switching instructions in the computer room, and perform quantum state reconstruction and equipment switching in the computer room.

[0043] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent remote operation and maintenance method for computer room equipment as described in the first aspect of the present invention is implemented.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the intelligent remote operation and maintenance method for computer room equipment as described in the first aspect of the present invention is implemented.

[0045] The present invention has the following beneficial effects: By constructing a multi-layer Bayesian probability model based on Gaussian distribution, Granger causality test, and variational inference, it enables nonlinear correlation analysis of optical signal wavelength offset and current harmonic characteristics, accurately capturing subtle signs of potential equipment failure, thereby significantly improving the sensitivity and reliability of fault prediction. Through dynamic quality assessment of quantum teleportation links and verification using compressed sensing quantum tomography, it achieves intelligent switching and recycling of quantum resources while ensuring the fidelity of reconstructed states, thus ensuring the continuity of quantum state transmission and optimizing the utilization of quantum communication resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 This is a flow chart of the intelligent remote operation and maintenance method for computer room equipment in Example 1.

[0048] Figure 2 This is a schematic diagram of the intelligent remote operation and maintenance platform for computer room equipment in Example 1.

[0049] Figure 3 This is a flowchart of the failure probability prediction in Example 1.

[0050] Figure 4 This is a flow chart of the Bayesian probability model constructed in Example 1. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0054] Example 1, with reference to Figures 1 to 4 This embodiment provides a method for intelligent remote operation and maintenance of equipment in a computer room, comprising the following steps:

[0055] S1. Monitor the optical signal wavelength offset data and current harmonic data and perform pre-processing;

[0056] The optical signal wavelength offset data includes the deviation between the central wavelength value and the reference wavelength, the offset duration and the change rate;

[0057] Current harmonic data includes the amplitude of harmonic components, total harmonic distortion, phase angle and spectrum energy distribution;

[0058] It should be noted that the signal wavelength offset data is obtained through real-time measurement using a tunable laser light source and a wavelength meter. The deviation between the center wavelength value and the reference wavelength is recorded using a high-precision optical spectrum analyzer at a fixed sampling interval (for example, every 10 ms). The offset duration is calculated using the timestamp difference, and the rate of change is obtained based on the difference in wavelength changes at consecutive sampling points. Current harmonic data is collected via a wide-band current sensor, and the amplitude, total harmonic distortion, and phase angle of the harmonic components are synchronously extracted using a phase-locked amplifier (for example, a sampling rate of 50 kHz). The spectrum energy distribution is calculated by performing a fast Fourier transform on the original waveform and then calculating the energy integral of each frequency band. All data are synchronously stored in a time series database after digital filtering to eliminate power frequency interference.

[0059] Preprocessing includes data normalization, noise filtering, outlier extraction, and time series alignment.

[0060] Furthermore, data normalization uses a maximum-minimum scaling method to linearly transform the original values ​​of the optical signal wavelength offset data and current harmonic data to the interval [0,1]. The maximum and minimum values ​​are dynamically calculated based on historical data within a sliding time window (for example, a window length of 60 seconds) to ensure the comparability of parameters of different dimensions.

[0061] Noise filtering is implemented using a digital Butterworth low-pass filter. A cutoff frequency (e.g., 5 Hz) is set for the optical signal wavelength offset data to suppress high-frequency jitter. Adaptive threshold wavelet denoising is used for the current harmonic data to retain the fundamental and main harmonic components while eliminating random interference.

[0062] Outlier extraction is based on a dynamic threshold outlier detection algorithm. The moving average and 3 times the standard deviation range of the optical signal wavelength offset data are calculated. The box plot method is used for the current harmonic data to identify data points that exceed 1.5 times the interquartile range. All outliers are marked and replaced by linear interpolation.

[0063] Time series alignment uses a dynamic time warping algorithm to compensate for the time difference between the acquisition of optical signal wavelength offset data and current harmonic data. By finding the minimum curvature path, the timestamps of the two types of data are forced to match (for example, the alignment accuracy reaches 1ms), forming a strictly synchronized feature sequence.

[0064] S2. Build a Bayesian probability model and combine it with optical signal characteristics and current harmonic characteristics to predict the failure probability distribution of equipment in the computer room.

[0065] Gaussian distribution is used to fit the optical signal wavelength deviation data and current harmonic data into physical layer nodes;

[0066] Furthermore, the optical signal wavelength deviation data is statistically analyzed, its distribution characteristics are calculated, and a Gaussian distribution describing the wavelength deviation characteristics is fitted to form an optical signal physical layer node. Simultaneously, the current harmonic data is statistically analyzed, its distribution characteristics are calculated, and a Gaussian distribution describing the harmonic characteristics is fitted to form a current harmonic physical layer node. These two physical layer nodes each output probability distribution information for the corresponding characteristics: the optical signal physical layer node outputs the wavelength deviation probability distribution, and the current harmonic physical layer node outputs the harmonic characteristic probability distribution. All distribution parameters are calculated using historical operating data and are continuously updated and maintained.

[0067] Based on the conditional probability table and historical fault data, the latent variable nodes are constructed by defining the dependency relationship between optical signal anomalies and latent variable nodes.

[0068] Based on the latent variable nodes, the application layer nodes are constructed using the logistic regression algorithm;

[0069] Furthermore, the co-occurrence frequency of optical signal wavelength deviation and equipment failures in historical data was analyzed to establish a conditional probability distribution P(fault state | optical signal anomaly). The dependency relationship between the latent variable node and the optical signal physical layer node was then defined. The posterior probability distribution of the latent variable node was calculated using Bayesian theorem, ultimately constructing a latent variable node that reflects the potential equipment failure risk. This node outputs a failure risk probability value that comprehensively considers the characteristics of the optical signal anomaly.

[0070] It should be noted that the conditional probability table is a lookup table created by analyzing the correspondence between optical signal anomalies and equipment fault states in historical operating data. The specific construction process involves counting the proportion of equipment failures occurring when the optical signal wavelength deviation exceeds a specific range, and simultaneously counting the proportion of failures occurring within the normal range. These proportions are then organized into a lookup table of failure probabilities corresponding to different degrees of optical signal anomaly. This table directly reflects the probabilistic association between optical signal anomaly characteristics and equipment fault states.

[0071] Granger causality test is used to analyze the causal relationship between physical layer nodes and latent variable nodes, and a hierarchical directed acyclic graph is constructed using BayesPy.

[0072] Furthermore, the Granger causality test method is used to verify the predictive power of physical-layer node time series data on latent variable node time series data. By comparing the prediction error variance of latent variable nodes with and without historical information about physical-layer nodes, it is determined whether the physical-layer nodes constitute the Granger cause of the latent variable nodes. For causal relationships that pass the test, the BayesPy tool is used to construct a hierarchical directed acyclic graph based on the verification results. In this graph, the physical-layer nodes serve as parent nodes pointing to the corresponding latent variable nodes, forming a probabilistic graph structure with clear causal directionality. During the test, the lag order is automatically determined according to the Bayesian Information Criterion, for example, the maximum lag order is set to 5.

[0073] Based on physical layer nodes, latent variable nodes, application layer nodes and hierarchical directed acyclic graph, a Bayesian probability model is constructed through the EM algorithm and variational inference.

[0074] Furthermore, the physical layer nodes, latent variable nodes, and application layer nodes are probabilistically modeled based on the structural relationship of the hierarchical directed acyclic graph. Parameter optimization is achieved through the EM algorithm: in the expectation step, the current conditional probability parameters are used to calculate the expectation of the posterior probability distribution of each node; in the maximization step, the conditional probability parameters are updated according to the expected statistics, and the value of the model log-likelihood function is gradually improved. At the same time, variational inference technology is used to approximate the complex posterior distribution as a tractable variational distribution, and efficient probabilistic reasoning is achieved by optimizing the variational lower bound. The causal relationship determined by the Granger causality test guides the connection method between nodes, ensuring that the physical layer nodes maintain an effective influence on the latent variable nodes. The final constructed Bayesian probability model completely retains the topological structure of the hierarchical directed acyclic graph, and the conditional dependency relationship between nodes is accurately expressed by the optimized parameter matrix.

[0075] Based on the pre-processed optical signal wavelength offset data, optical signal features are extracted through time-frequency analysis;

[0076] It should be noted that after preprocessing, the optical signal wavelength offset data is subjected to time-frequency analysis using short-time Fourier transform to calculate the energy distribution of the signal in the time-frequency domain, and extract parameters including the main frequency band energy proportion, frequency band energy entropy, and instantaneous frequency fluctuation rate, which together constitute the optical signal characteristics that characterize the abnormal state of the optical signal.

[0077] Based on the pre-processed current harmonic data, the current harmonic characteristics are extracted through fast Fourier transform and harmonic distortion analysis;

[0078] It should be noted that after the current harmonic data is preprocessed, a fast Fourier transform is first performed to obtain the spectrum distribution, and then the ratio of the amplitude of each harmonic component to the fundamental amplitude is calculated. At the same time, the total harmonic distortion rate and the phase relationship of each harmonic are analyzed. Finally, the energy proportion of the main frequency band is calculated by spectrum integration. These analysis results together constitute the current harmonic characteristics that reflect abnormal power quality.

[0079] The optical signal characteristics and current harmonic characteristics are input into the Bayesian probability model, and the real-time failure probability P(D k ), the expression is:

[0080]

[0081] Among them, P(D k ) represents the real-time failure probability of the k-th equipment in the computer room, The observed value of the mth feature at time t, w m is the weight coefficient of the mth feature, Indicates the fault status D of the kth equipment in the computer room k Fault characteristics x m The conditional probability, P'(D k ) represents the basic failure probability of equipment k in the computer room, γ is the credibility adjustment coefficient of the basic failure probability of equipment in the computer room, D k represents the fault status of the k-th equipment in the computer room, M is the total number of optical signal features and current harmonic features, m is the index variable of all features (including optical signal features and current harmonic features), λ is the exponential decay coefficient of the historical data on the current fault probability prediction, Δt is the time difference between time t and the time when the historical data was collected, and Z is the normalization factor;

[0082] Furthermore, after the optical signal characteristics and current harmonic characteristics are input into the Bayesian probability model, the conditional probability table is first used to query each characteristic. In the current device state D k The conditional probability of For example, the probability of the main lobe energy concentration of the optical signal in the fault state is 0.85. Then calculate the weighted sum of the logarithmic probabilities of each feature, and the weight coefficient w m According to the dynamic adjustment of feature importance, in this example, the optical signal feature weight is set to 0.6 and the current harmonic feature weight is set to 0.4. At the same time, the basic failure probability of the equipment P'(D k) logarithmic term, the credibility adjustment coefficient γ is set to 0.3 to balance the prior influence. The time decay term λΔt exponentially decays the contribution of historical data, and the decay coefficient λ is set to 0.01 / minute. Finally, all terms are summed and the exponential is taken, and the normalization factor Z is used to ensure that the probability value is between 0 and 1. During the calculation process, the feature index variable m traverses all M optical signal features and current harmonic features, and the device status D k The value of 0 or 1 indicates normal and faulty status respectively. The entire calculation process achieves real-time update of fault probability through dynamic feature fusion and time decay mechanism.

[0083] The spatial interpolation kernel density estimation algorithm is used to map the failure probabilities of all equipment in the computer room according to their spatial locations to generate the failure probability distribution of the equipment in the computer room.

[0084] It should be noted that the spatial interpolation kernel density estimation algorithm first obtains the three-dimensional coordinate positions of all equipment in the computer room and the corresponding real-time failure probability P(D k ), the Gaussian kernel function is used as the spatial weight function, and the kernel function bandwidth is automatically determined by the Silverman rule. For any position point in the space, the algorithm calculates the weighted average of the failure probabilities of all computer room equipment within a radius around the point. The weight is determined by the distance from the computer room equipment to the target point. The closer the distance, the greater the weight. For example, when calculating a certain position point, 12 computer room equipment within a radius of 5 meters are considered, and the contribution weight of each device decays with distance according to the Gaussian kernel function. By traversing the computer room space grid points, a three-dimensional fault probability distribution map covering the entire computer room area is finally generated. The value of each grid point in the map represents the failure risk probability density of the location. During the calculation process, the basic failure probability P'(D k ) remains unchanged, and the continuous expression of probability density is achieved only through spatial interpolation.

[0085] Dynamic feature fusion specifically refers to the ability to identify equipment faults by dynamically quantifying optical signal features and current harmonic features through KL divergence;

[0086] It is based on historical data (such as abnormal records of optical signal wavelength offset and current harmonic distortion events, which are classified and counted by equipment failure status to generate conditional probability distribution) and is fitted using the kernel density estimation method.

[0087] D k ∈{0,1}, 0 indicates normal and 1 indicates fault.

[0088] S3. According to the fault probability distribution of the equipment in the computer room, the fault coordinates are converted into equipment logical identifiers, and the quantum teleportation link of the equipment in the computer room is detected. Based on the detection results, a switching instruction for the equipment in the computer room is generated;

[0089] Based on the statistical analysis of historical fault data, define the risk warning threshold F1;

[0090] Furthermore, the definition of the risk warning threshold F1 is based on the probability characteristics of the equipment before the failure in the historical failure data. The specific definition process is: first, collect a large amount of historical monitoring data of the equipment during normal operation and before the failure occurs, and analyze the real-time failure probability P(D k )’s typical change pattern; then, a statistical distribution analysis method is used to determine the probability critical value that can cover the vast majority of real failure cases; finally, this critical value is used as the risk warning threshold F1 to identify high-risk equipment in real-time monitoring.

[0091] When P(D k )≥F1, the current equipment in the computer room is considered to be high-risk equipment;

[0092] Based on the failure probability distribution of equipment in the computer room, the location coordinates of high-risk equipment are identified, and the logical identifiers of high-risk equipment are identified from the BIM database.

[0093] Furthermore, the failure probability distribution data of the computer room equipment is spatially matched with the BIM database. First, the high-risk equipment position with a failure probability exceeding the threshold F1 is located in the three-dimensional coordinate system, and the X / Y / Z coordinate values ​​of the corresponding position are extracted. Then, through the spatial indexing function of the BIM database, the coordinate values ​​are used as query conditions to retrieve the matching equipment objects, and the unique logical identifier of the equipment in the BIM model is obtained, including metadata information such as the equipment code, type number, and the system to which it belongs.

[0094] Based on the logical identifiers of high-risk devices, QKD is used to detect the survival status of entangled pairs between devices and identify surviving channels;

[0095] Furthermore, after the logical identifier of a high-risk device is entered into the QKD detection process, the quantum key distribution protocol is first used to query the states of all entangled pairs that have established a quantum connection with the device. The survival of each entangled pair is verified using Bell basis measurements. For surviving entangled pairs, the corresponding quantum channel number is recorded and the channel parameters, including entanglement fidelity, quantum bit error rate, and transmission delay, are measured. For example, of the three quantum channels corresponding to the logical identifier MEP-AC-025, channel QCH-1024 was measured to have an entanglement fidelity of 0.95, a quantum bit error rate of 2%, and a delay of 120μs, and was marked as a surviving channel. All surviving channel information is stored in the quantum channel state table for subsequent quality assessment.

[0096] The entanglement degree and quantum bit error rate of the surviving channel are measured in real time, and the quantum channel quality score Q is obtained through the compressed sensing quantum tomography method. The expression is:

[0097]

[0098] Where S is the entanglement fidelity, R is the entanglement generation rate, QBER is the quantum bit error rate, τ is the channel delay, and τ0 is the reference delay;

[0099] It should be noted that the calculation process of the quantum channel quality score Q of the surviving channel is as follows: first, the entanglement fidelity S of the surviving channel is measured in real time using quantum state tomography technology, and the entanglement generation rate R is calculated by the coincidence counting rate. At the same time, the quantum bit error rate QBER is collected using a single-photon detector array, and the channel transmission delay τ is recorded. The reference delay τ0 is taken as 100μs as a reference. In the calculation process, the product of the entanglement fidelity S and the entanglement generation rate R is used as the numerator to characterize the channel transmission quality; the quantum bit error rate QBER is combined with the delay influence factor The product of is used as the denominator to reflect the impact of channel noise and delay. Finally, the quantum channel quality score Q is obtained by dividing the numerator by the denominator.

[0100] Based on the statistical analysis of historical quantum communication data, the channel quality threshold Q1 is defined;

[0101] It should be noted that the definition of the channel quality threshold Q1 is based on the corresponding relationship between the channel quality score Q and communication reliability in historical quantum communication data. The specific definition process is: collecting the quality score Q values ​​of the quantum channel from a large amount of historical operation data, analyzing the relationship between these Q values ​​and actual communication quality, and calculating the minimum Q value level that can ensure reliable quantum state transmission; then, through probability distribution analysis, determining a critical value that ensures that the Q values ​​of the vast majority of reliable communication cases are above this critical value; finally, this critical value is determined as the channel quality threshold Q1, which is used to determine whether the current quantum channel meets the communication quality requirements.

[0102] When Q<Q1, the quantum channel quality is considered to be substandard, and a device switching instruction is generated through QNMP.

[0103] S4. According to the equipment switching instruction in the computer room, a Bell state measurement command is sent to the faulty equipment, and quantum state reconstruction and equipment switching in the computer room are performed.

[0104] Based on the device switching instruction, a Bell state measurement command is sent to the high-risk device through the quantum control interface. A polarization beam splitter is used to perform Bell state analysis, and a Bell basis joint measurement of quantum bits is performed on the entangled particles in the quantum memory of the high-risk device to generate a 2-bit classical measurement result.

[0105] Furthermore, once a device switching command is issued, the quantum control interface immediately issues a Bell state measurement command to the target high-risk device. The entangled particle pairs stored in the high-risk device's quantum memory are processed by precision optical components: a polarization beam splitter separates the entangled photon pairs according to their polarization states, with the separated photons then entering two independent measurement channels. Each measurement channel is equipped with tunable optical elements, enabling projection measurements of different Bell bases. After polarization analysis, the photons are detected by highly sensitive single-photon detectors. The detectors in both channels work together, and when a photon is detected simultaneously, a coincidence count event is generated, which is encoded as a 2-bit classical measurement result. For example, under a specific Bell basis measurement, simultaneous detection of a photon in both channels may correspond to a result of 00, indicating successful projection to a specific Bell state.

[0106] It should be noted that a 2-bit classical measurement result represents two bits of binary data obtained when performing a Bell-based measurement on a quantum entangled state. This result is composed of the independent measurement outputs of two entangled particles, with the first bit corresponding to the measurement value of the first particle and the second bit to the measurement value of the second particle. The four possible combinations reflect different quantum state correlation characteristics: the combination 00 indicates a perfect correlation between the two particle measurement results, the combination 11 indicates a perfect anti-correlation between the two particle measurement results, and the combinations 01 and 10 indicate a specific correlation pattern between the particles. These measurement results, obtained using a polarization beam splitter and a single-photon detector, directly reflect the non-classical correlation characteristics of quantum entanglement, providing key information for verifying quantum state quality and executing quantum communication protocols. Each binary combination corresponds to a specific quantum state projection measurement result, fully recording the statistical properties of quantum entanglement.

[0107] Based on the 2-bit classical measurement results, the quantum state is reconstructed, and the reconstructed state fidelity is verified by the compressed sensing quantum tomography method. The expression is:

[0108]

[0109] Where Y is the fidelity of the reconstructed state, d is the dimension of the Hilbert space, ρ is the density matrix of the reconstructed state, ψ i is the i-th measurement basis vector selected in the compressed sensing quantum tomography method, N is the number of measurement basis vectors actually used in the compressed sensing quantum tomography method, and i is the index variable of the measurement basis vector;

[0110] Furthermore, the quantum state reconstruction process first uses the 2-bit classical measurement results to establish the measurement statistical distribution, and reconstructs the quantum state density matrix from the limited measurement data through compressed sensing quantum tomography technology. During the reconstruction process, N specific measurement basis vectors are selected in the Hilbert space for projection measurement, and the measurement expectation value under each basis vector is recorded. When calculating the fidelity, the influence of the Hilbert space dimension d is taken into account, and the projection results under each measurement basis vector are weighted and summed to finally obtain a normalized fidelity value between 0 and 1. For example, in a two-qubit system, when 9 measurement basis vectors are used and the measurement data show good consistency, a reconstructed state fidelity of more than 0.9 can be obtained. This method effectively reduces the measurement resources required for traditional quantum tomography while ensuring reconstruction accuracy.

[0111] Based on the fidelity of the reconstructed state, the load balancer is used to migrate business traffic to the backup equipment in the backup computer room, release the quantum resources of high-risk equipment, and generate a computer room equipment switching report.

[0112] The quantum resources of high-risk devices include entangled particle pairs stored in the device's quantum memory, established quantum channel connections, and available quantum key distribution resources.

[0113] The equipment switching report in the computer room includes the identification information of the equipment to be switched, the comparison data of the quantum channel status before and after the switch, the quantum measurement results during the switch, and the resource reallocation plan after the switch is completed.

[0114] This embodiment also provides an intelligent remote operation and maintenance platform for equipment in a computer room, comprising: a data acquisition module, a fault probability prediction module, a command generation module, and an equipment switching module;

[0115] Data acquisition module, used to monitor optical signal wavelength offset data and current harmonic data, and perform pre-processing;

[0116] The fault probability prediction module is used to build a Bayesian probability model and combine the optical signal characteristics and current harmonic characteristics to predict the fault probability distribution of equipment in the computer room;

[0117] The instruction generation module is used to convert the fault coordinates into device logical identifiers based on the fault probability distribution of the equipment in the computer room, detect the quantum teleportation link of the equipment in the computer room, and generate the equipment switching instructions based on the detection results;

[0118] The equipment switching module is used to send Bell state measurement commands to the faulty equipment according to the equipment switching instructions in the computer room, and perform quantum state reconstruction and equipment switching in the computer room.

[0119] This embodiment also provides a computer device suitable for the intelligent remote operation and maintenance method of computer room equipment, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent remote operation and maintenance method of computer room equipment proposed in the above embodiment.

[0120] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0121] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for realizing intelligent remote operation and maintenance of computer room equipment as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0122] In summary, the present invention constructs a multi-layer Bayesian probability model based on Gaussian distribution, Granger causality test, and variational inference, enabling nonlinear correlation analysis of optical signal wavelength offset and current harmonic characteristics. This allows accurate capture of subtle signs of potential equipment failure, significantly improving the sensitivity and reliability of fault prediction. Through dynamic quality assessment of quantum teleportation links and verification through compressed sensing quantum tomography, intelligent switching and recycling of quantum resources is achieved while ensuring the fidelity of reconstructed states, safeguarding the continuity of quantum state transmission and optimizing the utilization of quantum communication resources.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligent remote operation and maintenance of equipment in a computer room, characterized by: include, Monitor optical signal wavelength offset data and current harmonic data and perform pre-processing; Construct a Bayesian probability model and combine it with optical signal characteristics and current harmonic characteristics to predict the failure probability distribution of equipment in the computer room; According to the fault probability distribution of the equipment in the computer room, the fault coordinates are converted into equipment logical identifiers, and the quantum teleportation links of the equipment in the computer room are detected. Based on the detection results, the equipment switching instructions in the computer room are generated; According to the equipment switching instructions in the computer room, a Bell state measurement command is sent to the faulty equipment, and quantum state reconstruction and computer room equipment switching are performed.

2. The intelligent remote operation and maintenance method for computer room equipment according to claim 1, characterized in that: The optical signal wavelength offset data includes the deviation between the central wavelength value and the reference wavelength, the offset duration and the change rate; The current harmonic data includes the amplitude, total harmonic distortion, phase angle and spectrum energy distribution of the harmonic components; The preprocessing includes data normalization, noise filtering, outlier extraction and time series alignment.

3. The intelligent remote operation and maintenance method for computer room equipment according to claim 1, characterized in that: The steps of constructing the Bayesian probability model are as follows: Gaussian distribution is used to fit the optical signal wavelength deviation data and current harmonic data into physical layer nodes; Based on the conditional probability table and historical fault data, the latent variable nodes are constructed by defining the dependency relationship between optical signal anomalies and latent variable nodes. Based on the latent variable nodes, the application layer nodes are constructed using the logistic regression algorithm; Granger causality test is used to analyze the causal relationship between physical layer nodes and latent variable nodes, and a hierarchical directed acyclic graph is constructed using BayesPy. Based on physical layer nodes, latent variable nodes, application layer nodes and hierarchical directed acyclic graph, a Bayesian probability model is constructed through the EM algorithm and variational inference.

4. The intelligent remote operation and maintenance method for computer room equipment according to claim 3, characterized in that: The steps for predicting the failure probability distribution of equipment in the computer room by combining the optical signal characteristics and the current harmonic characteristics are as follows: Based on the pre-processed optical signal wavelength offset data, optical signal features are extracted through time-frequency analysis; Based on the pre-processed current harmonic data, the current harmonic characteristics are extracted through fast Fourier transform and harmonic distortion analysis; The optical signal characteristics and current harmonic characteristics are input into the Bayesian probability model, and the real-time failure probability P(D k ); The spatial interpolation kernel density estimation algorithm is used to map the failure probabilities of all equipment in the computer room according to their spatial locations to generate the failure probability distribution of the equipment in the computer room.

5. The intelligent remote operation and maintenance method for computer room equipment according to claim 4, characterized in that: According to the failure probability distribution of the equipment in the computer room, the fault coordinates are converted into equipment logical identifiers in the following steps: Based on the statistical analysis of historical fault data, define the risk warning threshold F1; When P(D k )≥F1, the current equipment in the computer room is considered to be high-risk equipment; Based on the failure probability distribution of equipment in the computer room, the location coordinates of high-risk equipment are identified, and the logical identifiers of high-risk equipment are identified from the BIM database.

6. The intelligent remote operation and maintenance method for computer room equipment according to claim 5, characterized in that: The steps of detecting the quantum teleportation link of the computer room equipment and generating the computer room equipment switching instruction according to the detection result are as follows: Based on the logical identifiers of high-risk devices, QKD is used to detect the survival status of entangled pairs between devices and identify surviving channels; The entanglement degree and quantum bit error rate of the surviving channel are measured in real time, and the quantum channel quality score Q is obtained through compressed sensing quantum tomography method; Based on the statistical analysis of historical quantum communication data, the channel quality threshold Q1 is defined; When Q<Q1, the quantum channel quality is considered to be substandard, and a device switching instruction is generated through QNMP.

7. The intelligent remote operation and maintenance method for computer room equipment according to claim 6, characterized in that: According to the equipment switching instruction in the computer room, a Bell state measurement command is sent to the faulty equipment, and quantum state reconstruction and equipment switching in the computer room are performed. The steps are as follows: Based on the device switching instruction, a Bell state measurement command is sent to the high-risk device through the quantum control interface. A polarization beam splitter is used to perform Bell state analysis, and a Bell basis joint measurement of quantum bits is performed on the entangled particles in the quantum memory of the high-risk device to generate a 2-bit classical measurement result. Based on the 2-bit classical measurement results, the quantum state is reconstructed, and the reconstructed state fidelity Y is verified by compressed sensing quantum tomography. Based on the fidelity of the reconstructed state, the load balancer is used to migrate business traffic to the backup equipment in the backup computer room, release the quantum resources of high-risk equipment, and generate a computer room equipment switching report.

8. An intelligent remote operation and maintenance platform for computer room equipment, based on the intelligent remote operation and maintenance method for computer room equipment according to any one of claims 1 to 7, characterized in that: Including data acquisition module, fault probability prediction module, instruction generation module and equipment switching module; Data acquisition module, used to monitor optical signal wavelength offset data and current harmonic data, and perform pre-processing; The fault probability prediction module is used to build a Bayesian probability model and combine the optical signal characteristics and current harmonic characteristics to predict the fault probability distribution of equipment in the computer room; The instruction generation module is used to convert the fault coordinates into device logical identifiers based on the fault probability distribution of the equipment in the computer room, detect the quantum teleportation link of the equipment in the computer room, and generate the equipment switching instructions based on the detection results; The equipment switching module is used to send Bell state measurement commands to the faulty equipment according to the equipment switching instructions in the computer room, and perform quantum state reconstruction and equipment switching in the computer room.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent remote operation and maintenance method for computer room equipment according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent remote operation and maintenance method for computer room equipment according to any one of claims 1 to 7 are implemented.

Images