Data center data management method and system based on TensorFlow ecosystem

Abstract

The present invention relates to the field of data management technology, and specifically to a data center data management method and system based on the TensorFlow ecosystem. The method and system collect historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and perform preprocessing to obtain first historical multi-source data and first real-time multi-source data; construct a data partitioning management model to analyze the first historical multi-source data, obtain data partitioning results, and generate a gradient baseline; calculate the real-time gradient baseline based on the first real-time multi-source data, calculate and obtain the reconstruction error of the gradient baseline, dynamically adjust the threshold in real time, and obtain an abnormal TensorFlow ecosystem gradient; construct an abnormality analysis management model to analyze the abnormal TensorFlow ecosystem gradient, obtain a TensorFlow ecosystem abnormality indicator vector, and obtain the specific abnormal factors that cause the abnormality; and evaluate and issue an alarm for the abnormal factors.

Description

Technical Field

[0001] The present invention relates to the field of data management technology, and specifically to a data center data management method and system based on the TensorFlow ecosystem. Background Art

[0002] With the rapid development of cloud computing and artificial intelligence technologies, the demand for massive data processing in data centers is growing exponentially. Traditional data management approaches face significant challenges in handling large-scale heterogeneous data processing, real-time analysis, and machine learning model integration. Existing data centers typically employ a layered architecture to handle data storage, computation, and analysis tasks, but this suffers from shortcomings such as fragmented data processing pipelines, inefficient resource scheduling, and insufficient support for machine learning workflows. Particularly in the context of the widespread adoption of the TensorFlow ecosystem, traditional systems struggle to effectively integrate the pipelined data processing of TensorFlow Extended (TFX), the dynamic data distribution of TensorFlow Data Service, and the heterogeneous computing resource scheduling capabilities of TensorFlow Runtime. This leads to significant I / O bottlenecks and idle computing resources in data processing and model training. Furthermore, existing solutions lack a unified management framework for data versioning, automated feature engineering, and distributed training collaborative optimization, making closed-loop management of data-model collaborative optimization difficult.

[0003] To this end, a data center data management method and system based on the TensorFlow ecosystem is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a data center data management method and system based on the TensorFlow ecosystem. By collecting historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and preprocessing them, first historical multi-source data and first real-time multi-source data are obtained; a data partitioning management model is constructed to analyze the first historical multi-source data, obtain data partitioning results, and generate a gradient baseline; the real-time gradient baseline is calculated based on the first real-time multi-source data, the reconstruction error of the gradient baseline is calculated, the threshold is dynamically adjusted in real time, and an abnormal TensorFlow ecological gradient is obtained; an abnormal analysis management model is constructed to analyze the abnormal TensorFlow ecological gradient, obtain a TensorFlow ecological abnormality indicator vector, and obtain the specific abnormal factors that cause the abnormality; and the abnormal factors are evaluated and alarmed.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] Data center data management methods based on the TensorFlow ecosystem include:

[0007] S1. Collect historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and preprocess them to obtain first historical multi-source data and first real-time multi-source data;

[0008] S2. Build a data partition management model to analyze the first historical multi-source data to obtain data partition results; generate a gradient baseline based on the data partition results;

[0009] S3. Calculate a real-time gradient baseline based on the first real-time multi-source data; obtain a reconstruction error of the gradient baseline by calculating the gradient baseline and the real-time gradient baseline; update the reconstruction error based on the real-time gradient baseline, dynamically adjust the threshold in real time, and obtain an abnormal TensorFlow ecological gradient;

[0010] S4. Construct an anomaly analysis and management model to analyze the abnormal TensorFlow ecological gradient and obtain a TensorFlow ecological anomaly indicator vector; based on the analysis of the TensorFlow ecological anomaly indicator vector, obtain the specific abnormal factors that cause the anomaly; evaluate and alert the abnormal factors.

[0011] Preferably, the historical multi-source heterogeneous data includes historical server performance indicators, historical network traffic data, historical application logs and historical device status data; the real-time multi-source heterogeneous data includes real-time server performance indicators, real-time network traffic data, real-time application logs and real-time device status data; the preprocessing includes cleaning, normalization and spatiotemporal alignment processing; wherein the preprocessing utilizes the data processing components in the TensorFlow ecosystem to construct a data flow graph to achieve efficient parallel processing and conversion of multi-source heterogeneous data.

[0012] Preferably, the data partition management model includes a data partition layer, a data feature extraction layer and a gradient baseline generation layer;

[0013] The data partitioning layer generates preliminary data partitions by performing cluster analysis on the historical server performance indicators and historical application logs in the first historical multi-source data; performs feature correlation analysis on the historical application logs, historical network traffic data, historical application logs and historical device status data to obtain the first TensorFlow ecological variable features; modifies the preliminary data partitions based on the first TensorFlow ecological variable features to obtain data partitioning results; the data feature extraction layer obtains the TensorFlow ecological feature vector by performing feature extraction on the first TensorFlow ecological variable features and the data partitioning results; the gradient baseline generation layer obtains a preliminary theoretical TensorFlow ecological baseline by performing multidimensional regression analysis on the TensorFlow ecological feature vector and the first real-time multi-source data; performs nonlinear mapping on the TensorFlow ecological feature vector through the autoencoder model to extract potential features in the TensorFlow ecosystem, reconstructs the original TensorFlow ecological gradient data based on the learned potential features, and generates a gradient baseline.

[0014] Preferably, the abnormal TensorFlow ecological gradient generation step includes:

[0015] Real-time gradient baseline measurement: based on the first real-time multi-source data, combined with the data partitioning results and the TensorFlow ecological feature vector, the real-time collected TensorFlow ecological data is subjected to feature learning and reconstruction using multidimensional regression analysis and the autoencoder model to generate a real-time gradient baseline; reconstruction error measurement: the real-time gradient baseline is subjected to nonlinear mapping and reconstruction using the autoencoder to obtain a reconstructed gradient baseline, and the reconstruction error is measured; abnormal TensorFlow ecological gradient identification: the reconstruction error is updated based on the real-time gradient baseline, and the preset threshold is dynamically adjusted in real time. When the reconstruction error is greater than the preset threshold, the abnormal TensorFlow ecological gradient is judged to be abnormal.

[0016] Preferably, the anomaly analysis and management model includes a TensorFlow ecological anomaly indicator vector acquisition layer and an anomaly factor acquisition layer;

[0017] The TensorFlow ecological anomaly indicator vector acquisition layer compares the abnormal TensorFlow ecological gradient with the gradient baseline generated based on historical multi-source data, calculates the deviation of each variable, and combines the feature weights to calculate the TensorFlow ecological anomaly indicator vector;

[0018] The abnormal factor acquisition layer attributes the ecological factors to the input TensorFlow ecological abnormality index vector using principal component regression analysis to obtain abnormal factors.

[0019] Preferably, the specific formula for evaluating the abnormal factors is:

[0020] ;

[0021] in, For each intervention program, For the plan the cost, For the plan An estimate of the reduction in abnormal risk, is the cost-estimated trade-off coefficient, When the minimum value of the objective function is obtained The variable value of .

[0022] A data center data management system based on the TensorFlow ecosystem, including:

[0023] A data acquisition module is used to collect historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and perform pre-processing to obtain first historical multi-source data and first real-time multi-source data;

[0024] A gradient baseline acquisition module is used to build a data partition management model to analyze the first historical multi-source data to obtain data partition results; and generate a gradient baseline based on the data partition results;

[0025] An abnormal TensorFlow ecological gradient acquisition module is used to calculate the real-time gradient baseline based on the first real-time multi-source data; obtain the reconstruction error of the gradient baseline by measuring the gradient baseline and the real-time gradient baseline; update the reconstruction error based on the real-time gradient baseline, dynamically adjust the threshold in real time, and obtain the abnormal TensorFlow ecological gradient;

[0026] The abnormal factor acquisition module is used to build an abnormal analysis and management model to analyze the abnormal TensorFlow ecological gradient and obtain the TensorFlow ecological abnormality indicator vector; based on the analysis of the TensorFlow ecological abnormality indicator vector, the specific abnormal factors that cause the abnormality are obtained; and the abnormal factors are evaluated and alarmed.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention builds a digital management platform based on the TensorFlow ecosystem and uses data processing components in the TensorFlow ecosystem to construct a data flow graph, thereby achieving efficient parallel processing of multi-source heterogeneous data such as historical server performance indicators, network traffic data, application logs, and device status data. The autoencoder model is used to perform nonlinear mapping on feature vectors, which can automatically extract potential correlation features that are difficult to capture with traditional methods. The multi-dimensional feature fusion capability improves the accuracy of data partitioning, laying a high-quality data foundation for subsequent anomaly detection.

[0029] 2. This invention builds a dynamically adaptive anomaly detection system, improving detection sensitivity through a dynamic gradient baseline reconstruction mechanism. By employing multidimensional regression analysis and autoencoder dual-mode drive technology, the generation of real-time gradient baselines is adaptive to time series changes, effectively adapting to dynamic changes in data center operating conditions. Using an online reconstruction error update algorithm, the threshold adjustment response time is reduced to milliseconds.

[0030] 3. Through anomaly analysis and intervention planning, this invention deeply analyzes the causes of abnormal TensorFlow ecological gradients and accurately attributes them through principal component regression, achieving precise identification of abnormal factors. It comprehensively evaluates each intervention plan based on cost, effectiveness, and trade-off coefficients, automatically generates the optimal intervention strategy, and provides real-time warnings about abnormal risks, enabling data-driven ecological risk management and scientific decision-making, improving overall management effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A flow chart of the data center data management method based on the TensorFlow ecosystem provided by the present invention;

[0032] Figure 2 This is a schematic diagram of the data center data management system structure based on the TensorFlow ecosystem provided by the present invention;

[0033] Figure 3 A schematic diagram of ecological data anomaly assessment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0035] Example 1

[0036] See also Figures 1 to 2The present invention provides a data center data management method based on the TensorFlow ecosystem and is applied to a data center data management system based on the TensorFlow ecosystem. The technical solution is as follows:

[0037] As an embodiment of the present invention, refer to Figure 1 S1 in the figure is applied to the data acquisition module of the data center data management system of the TensorFlow ecosystem. The data acquisition module is used to collect historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and perform preprocessing to obtain first historical multi-source data and first real-time multi-source data.

[0038] S1. Collect historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and preprocess them to obtain first historical multi-source data and first real-time multi-source data;

[0039] The historical multi-source heterogeneous data includes historical server performance indicators, historical network traffic data, historical application logs and historical device status data; the real-time multi-source heterogeneous data includes real-time server performance indicators, real-time network traffic data, real-time application logs and real-time device status data; the preprocessing includes cleaning, normalization and spatiotemporal alignment processing; wherein the preprocessing uses the data processing components in the TensorFlow ecosystem to construct a data flow graph to achieve efficient parallel processing and conversion of multi-source heterogeneous data.

[0040] This implementation introduces historical and real-time multi-source heterogeneous data and utilizes TensorFlow data flow graphs to build an efficient parallel processing platform. This platform enables data cleaning, normalization, and spatiotemporal alignment, ensuring data standardization, spatiotemporal consistency, and integrity. This provides high-quality data support for subsequent ecological gradient baseline generation, anomaly detection, and intelligent analysis.

[0041] As an embodiment of the present invention, refer to Figure 1 S2 in the figure is applied to the gradient baseline acquisition module of the data center data management system of the TensorFlow ecosystem. The gradient baseline acquisition module is used to build a data partition management model to analyze the first historical multi-source data and obtain data partition results; and generate a gradient baseline based on the data partition results.

[0042] S2. Build a data partition management model to analyze the first historical multi-source data to obtain data partition results; generate a gradient baseline based on the data partition results;

[0043] The data partition management model includes a data partition layer, a data feature extraction layer and a gradient baseline generation layer;

[0044] The data partitioning layer generates preliminary data partitions by performing cluster analysis on the historical server performance indicators and historical application logs in the first historical multi-source data; performs feature correlation analysis on the historical application logs, historical network traffic data, historical application logs and historical device status data to obtain the first TensorFlow ecological variable features; modifies the preliminary data partitions based on the first TensorFlow ecological variable features to obtain data partitioning results; the data feature extraction layer obtains the TensorFlow ecological feature vector by performing feature extraction on the first TensorFlow ecological variable features and the data partitioning results; the gradient baseline generation layer obtains a preliminary theoretical TensorFlow ecological baseline by performing multidimensional regression analysis on the TensorFlow ecological feature vector and the first real-time multi-source data; performs nonlinear mapping on the TensorFlow ecological feature vector through the autoencoder model to extract potential features in the TensorFlow ecosystem, reconstructs the original TensorFlow ecological gradient data based on the learned potential features, and generates a gradient baseline.

[0045] The present invention constructs a data partition management model, uses clustering and feature correlation analysis to perform preliminary partition correction on historical data, and realizes accurate data partitioning; obtains TensorFlow ecological feature vectors through data feature extraction and combines them with real-time data for multidimensional regression, generates a theoretical TensorFlow ecological baseline, and uses autoencoder nonlinear mapping to extract potential features and reconstruct ecological gradient data; this method greatly improves data partitioning accuracy and baseline modeling reliability, laying a solid foundation for ecological environment monitoring.

[0046] As an embodiment of the present invention, refer to Figure 1 S3 in the example is used in the abnormal TensorFlow ecological gradient acquisition module of the data center data management system of the TensorFlow ecology. The abnormal TensorFlow ecological gradient acquisition module is used to calculate the real-time gradient baseline based on the first real-time multi-source data; obtain the reconstruction error of the gradient baseline by measuring the gradient baseline and the real-time gradient baseline; update the reconstruction error based on the real-time gradient baseline, dynamically adjust the threshold in real time, and obtain the abnormal TensorFlow ecological gradient.

[0047] S3. Calculate a real-time gradient baseline based on the first real-time multi-source data; obtain a reconstruction error of the gradient baseline by calculating the gradient baseline and the real-time gradient baseline; update the reconstruction error based on the real-time gradient baseline, dynamically adjust the threshold in real time, and obtain an abnormal TensorFlow ecological gradient;

[0048] The abnormal TensorFlow ecological gradient generation steps include:

[0049] Real-time gradient baseline measurement: based on the first real-time multi-source data, combined with the data partitioning results and the TensorFlow ecological feature vector, the real-time collected TensorFlow ecological data is subjected to feature learning and reconstruction using multidimensional regression analysis and the autoencoder model to generate a real-time gradient baseline; reconstruction error measurement: the real-time gradient baseline is subjected to nonlinear mapping and reconstruction using the autoencoder to obtain a reconstructed gradient baseline, and the reconstruction error is measured; abnormal TensorFlow ecological gradient identification: the reconstruction error is updated based on the real-time gradient baseline, and the preset threshold is dynamically adjusted in real time. When the reconstruction error is greater than the preset threshold, the abnormal TensorFlow ecological gradient is judged to be abnormal.

[0050] This implementation plan uses multidimensional regression and autoencoders to perform feature learning and reconstruction on real-time collected ecological data to generate a real-time gradient baseline, calculate the reconstruction error through nonlinear mapping, and dynamically update the preset threshold to achieve accurate identification of abnormal TensorFlow ecological gradients. This method effectively overcomes the limitations of traditional static thresholds, improves real-time monitoring and abnormal warning capabilities, and provides timely and accurate response guarantees for ecological risk prevention and control, thereby realizing the efficient operation of real-time data monitoring and risk warning systems.

[0051] As an embodiment of the present invention, refer to Figure 1 S4 in the code is used in the abnormal factor acquisition module of the data center data management system of the TensorFlow ecosystem. The abnormal factor acquisition module is used to build an abnormal analysis management model to analyze the abnormal TensorFlow ecosystem gradient and obtain the TensorFlow ecosystem abnormal indicator vector; based on the analysis of the TensorFlow ecosystem abnormal indicator vector, the specific abnormal factors that cause the abnormality are obtained; and the abnormal factors are evaluated and alarmed.

[0052] S4. Construct an anomaly analysis management model to analyze the abnormal TensorFlow ecological gradient and obtain a TensorFlow ecological anomaly indicator vector; based on the analysis of the TensorFlow ecological anomaly indicator vector, obtain the specific abnormal factors that cause the anomaly; evaluate and alert the abnormal factors;

[0053] The anomaly analysis and management model includes a TensorFlow ecological anomaly indicator vector acquisition layer and an anomaly factor acquisition layer;

[0054] The TensorFlow ecological anomaly indicator vector acquisition layer compares the abnormal TensorFlow ecological gradient with the gradient baseline generated based on historical multi-source data, calculates the deviation of each variable, and combines the feature weights to calculate the TensorFlow ecological anomaly indicator vector;

[0055] The abnormal factor acquisition layer attributes the ecological factors to the input TensorFlow ecological abnormality index vector using principal component regression analysis to obtain abnormal factors;

[0056] This implementation plan builds an anomaly analysis and management model, comparing abnormal TensorFlow ecological gradients with historical baselines to calculate variable deviations and generating anomaly indicator vectors based on feature weights. Principal component regression analysis is used to attribute ecological factors and accurately identify anomaly factors. This method effectively improves the accuracy of anomaly diagnosis, clarifies the causes of anomalies, and provides a scientific basis for subsequent precise intervention and risk mitigation. It also optimizes the efficiency of ecological monitoring data utilization and the accuracy of anomaly warnings.

[0057] The specific formula for evaluating the abnormal factors is:

[0058] ;

[0059] in, For each intervention program, For the plan the cost, For the plan An estimate of the reduction in abnormal risk, is the cost-estimated trade-off coefficient, When the minimum value of the objective function is obtained The variable value of .

[0060] This implementation plan constructs an abnormal factor evaluation formula to quantitatively measure the cost and estimated effect of each intervention plan, and introduces a cost-effectiveness trade-off coefficient to achieve a scientific balance between economic benefits and risk reduction. This formula provides a quantitative basis for the selection of abnormal risk intervention measures, effectively avoiding subjective evaluation errors, improving the feasibility and execution efficiency of intervention plans, and thus providing a scientific basis for intervention decisions to achieve optimal risk.

[0061] The present invention is based on the data center data management method of the TensorFlow ecosystem, which achieves high efficiency and intelligence in data management by integrating advanced data processing and analysis technologies. First, by utilizing the data processing components in the TensorFlow ecosystem, a data flow graph is constructed to perform efficient parallel processing and conversion of multi-source heterogeneous data, greatly improving data processing efficiency. Secondly, by constructing an anomaly analysis management model, various indicators of the data center can be monitored in real time, abnormal factors can be accurately identified and analyzed, potential problems can be warned in a timely manner, and system stability can be ensured. At the same time, based on multidimensional regression analysis and autoencoder models, thresholds can be dynamically adjusted and data gradient baselines can be optimized, thereby improving the accuracy of anomaly detection. In addition, machine learning technology is used to predict and optimize the energy consumption of the data center in real time, realizing intelligent energy allocation and energy saving and consumption reduction. Overall, the present invention provides a flexible, efficient and accurate solution, which effectively improves the operating efficiency, resource utilization and security of the data center, and provides strong support for the intelligent management of the data center.

[0062] Example 2

[0063] In this embodiment, the mountain ecological data is managed by the data center based on the TensorFlow ecology.

[0064] With the rapid development of information technology and the Internet of Things (IoT), mountain ecological and environmental monitoring is gradually moving towards data multi-source and real-time. Traditional mountain ecological data management systems often rely on a single data source or employ simple statistical analysis methods, making it difficult to fully integrate diverse data, including historical geography, climate, soil, vegetation, topography, and spatial remote sensing data. This leads to significant limitations in spatiotemporal alignment, data cleaning, and normalization. Furthermore, mountainous regions exhibit complex topography and variable climates, and their ecosystems exhibit highly dynamic and nonlinear characteristics. Traditional methods are unable to meet practical needs for identifying ecological anomalies and predicting ecological changes. Meanwhile, the emergence of deep learning platforms such as TensorFlow has provided new opportunities for large-scale data fusion and high-precision modeling. However, research on their application in mountain ecological data center construction, real-time data processing, and anomaly detection remains insufficient. Therefore, a data center data management method and system based on the TensorFlow ecosystem is urgently needed. By integrating multi-source heterogeneous data, achieving precise preprocessing, and efficient data fusion, an intelligent platform capable of dynamically monitoring and predicting abnormal changes in mountain ecology is needed.

[0065] As an embodiment of the present invention, refer to Figure 1 S1 in the above process collects historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the mountain ecological area and performs pre-processing to obtain first historical multi-source data and first real-time multi-source data;

[0066] The historical multi-source heterogeneous data includes historical geographic data, historical climate data, historical soil data, historical vegetation data, historical terrain data and historical spatial remote sensing data; the real-time multi-source heterogeneous data includes real-time geographic data, real-time climate data, real-time soil data, real-time vegetation data, real-time terrain data and real-time spatial remote sensing data; the preprocessing includes cleaning, normalization and spatiotemporal alignment processing; wherein the preprocessing utilizes the data processing components in the TensorFlow ecosystem to construct a data flow graph to achieve efficient parallel processing and conversion of multi-source heterogeneous data.

[0067] Multi-source heterogeneous data includes multiple levels of space, time, and ecological environment. The main characteristic dimensions are as follows:

[0068] Climate data: temperature, humidity, precipitation, wind speed;

[0069] Soil data: soil moisture, soil nutrients (such as nitrogen, phosphorus, and potassium content), and soil type;

[0070] Vegetation data: vegetation index (NDVI), species diversity and vegetation coverage;

[0071] Topographic data: elevation, slope, and aspect (the angle of the slope toward the sun);

[0072] Spatial remote sensing data: high-resolution remote sensing image features, LiDAR point cloud data features, and drone video data features (obtained through deep learning feature extraction);

[0073] As an embodiment of the present invention, refer to Figure 1 S2 in which a mountain zoning management model is constructed to analyze the first historical multi-source data based on the altitude vertical zoning to obtain a mountain vertical zoning result; and a gradient baseline is generated based on the mountain vertical zoning result.

[0074] The mountain zoning management model includes a vertical zone zoning layer, a vertical zone feature extraction layer and an ecological gradient baseline generation layer;

[0075] The vertical zone partition layer generates preliminary mountain partitions by performing cluster analysis on the historical terrain data and historical geographic data in the first historical multi-source data; performs feature correlation analysis on the historical geographic data, historical climate data, historical soil data, historical vegetation data, historical terrain data, and historical spatial remote sensing data to obtain first ecological variable characteristics; wherein the first ecological variable characteristics include a first feature, a second feature, a third feature, and a fourth feature;

[0076] The first characteristic is strongly correlated with temperature, humidity, and precipitation, reflecting the climate gradient;

[0077] The second characteristic is strongly correlated with altitude, slope, and aspect, reflecting the topographic gradient;

[0078] The third characteristic is strongly correlated with NDVI and vegetation coverage, reflecting the ecological characteristics of vegetation;

[0079] The fourth characteristic is strongly correlated with soil moisture and nutrient content, reflecting the soil environment.

[0080] The data after dimensionality reduction can better highlight the significant ecological differences between different regions, reduce noise and redundant feature interference, and thus provide a clearer feature space for hierarchical partitioning.

[0081] Based on the characteristics of the first ecological variable, the preliminary mountain zoning was revised to obtain the mountain vertical zone zoning results. The mountain vertical zone zoning results include each zone's specific ecological characteristics (for example, temperature and humidity distribution patterns) and spatial boundaries. A convolutional neural network was used to extract spatial features from high-resolution remote sensing imagery and drone video data. Time series analysis was used to analyze the dynamic trends of temperature, humidity, and other factors over time. A feature selection algorithm was used to identify the features that most significantly influence ecological gradient changes.

[0082] The vertical zone feature extraction layer extracts features from the first ecological variable features and the mountain vertical zone partitioning results to obtain an ecological feature vector;

[0083] The ecological gradient baseline generation layer obtains a preliminary theoretical ecological baseline by performing multidimensional regression analysis on the ecological feature vector and the first real-time multi-source data; nonlinearly maps the ecological feature vector using an autoencoder model to extract potential features in the ecosystem, and reconstructs the original ecological gradient data based on the learned potential features to generate a gradient baseline. The effectiveness and complementary relationship between the multidimensional regression analysis and the autoencoder are shown in Table 1.

[0084] As an embodiment of the present invention, refer to Figure 1 S3 in which a real-time ecological gradient baseline is calculated based on the first real-time multi-source data; a reconstruction error of the ecological gradient baseline is calculated by analyzing the ecological gradient baseline and the real-time ecological gradient baseline; the reconstruction error is updated based on the real-time ecological gradient baseline, and a threshold is dynamically adjusted in real time to obtain an abnormal ecological gradient;

[0085]

[0086] The abnormal ecological gradient generation step includes:

[0087] Real-time ecological gradient baseline calculation, based on the first real-time multi-source data, combined with the mountain vertical zone zoning results and ecological feature vectors, uses multidimensional regression analysis and autoencoder models to learn and reconstruct features of the real-time collected ecological data to generate a real-time ecological gradient baseline;

[0088] The real-time ecological gradient baseline calculation process is as follows:

[0089] Based on the first real-time multi-source heterogeneous data Multidimensional ecological gradient baseline generated from historical data , using multidimensional regression analysis to establish a prediction model and calculate the real-time ecological gradient baseline , the calculation formula is as follows:

[0090] ;

[0091] in, is the real-time ecological gradient baseline, is an activation function to enhance the nonlinear mapping capability. is the bias term, is the regression coefficient, For the feature, is the number of features; in this embodiment is 4;

[0092] Reconstruction error calculation: using an autoencoder to perform nonlinear mapping and reconstruction on the real-time ecological gradient baseline to obtain a reconstructed ecological gradient baseline, and calculate the reconstruction error;

[0093] The specific process of reconstruction error is:

[0094] Use autoencoder to learn the potential features of ecological feature vectors and reconstruct the reconstructed ecological baseline ; The reconstruction process is:

[0095] ;

[0096] in, For the encoder, For the decoder;

[0097] By reconstructing the ecological baseline and real-time ecological gradient baseline Calculating reconstruction error , the specific calculation formula is:

[0098] ;

[0099] Abnormal ecological gradient identification: updating the reconstruction error based on the real-time ecological gradient baseline, dynamically adjusting the preset threshold in real time, and determining that the abnormal ecological gradient is abnormal when the reconstruction error is greater than the preset threshold;

[0100] The abnormal ecological gradient identification process is as follows:

[0101] The reconstruction error With dynamic threshold Compare and adjust thresholds in real time based on the latest data updates:

[0102] ;

[0103] in, is the mean of the historical reconstruction error, is the preset sensitivity factor, is the standard deviation of the historical reconstruction error;

[0104] An abnormal ecological gradient is determined when the following conditions are met:

[0105] ;

[0106] At this point, the data is marked as an abnormal ecological gradient and input into the anomaly analysis management model to analyze the specific abnormal factors.

[0107] As an embodiment of the present invention, refer to Figure 1 S4 in which an abnormality analysis and management model is constructed to analyze the abnormal ecological gradient to obtain a mountain ecological abnormality index vector; based on the analysis of the mountain ecological abnormality index vector, a specific abnormal factor causing the abnormality is obtained; and the abnormal factor is evaluated and an alarm is issued;

[0108] The anomaly analysis and management model includes a mountain ecological anomaly indicator vector acquisition layer and an anomaly factor acquisition layer;

[0109] The mountain ecological anomaly index vector acquisition layer compares the abnormal ecological gradient with the ecological gradient baseline generated based on historical multi-source data, calculates the deviation of each ecological variable, and calculates the mountain ecological anomaly index vector by combining the feature weights;

[0110] The abnormal factor acquisition layer attributes the input mountain ecological abnormality index vector to ecological factors using principal component regression analysis to obtain abnormal factors.

[0111] The specific formula for evaluating the abnormal factors is:

[0112] ;

[0113] ;

[0114] in, For each intervention program, For the plan the cost, For the plan An estimate of the reduction in abnormal risk, is the cost-estimated trade-off coefficient, is the average reconstruction error between the theoretical ecological gradient baseline generated based on historical multi-source data and the real-time ecological gradient baseline without intervention, reflecting the initial ecological anomaly risk. To apply the intervention plan After that, the reconstruction error reduction value measured by reconstructing the ecological characteristics through the autoencoder is When the minimum value of the objective function is obtained The variable value of .

[0115] This formula quantitatively reflects the solution The relative improvement effect in reducing the risk of ecological abnormalities, the larger the value, the more significant the intervention effect.

[0116] This invention proposes a data center data management method based on the TensorFlow ecosystem, aiming to improve the accuracy and efficiency of mountain ecological environment monitoring. By collecting and preprocessing historical and real-time multi-source heterogeneous data, a mountain zoning management model is constructed to achieve accurate characterization of ecological gradients. Using multidimensional regression analysis and autoencoder models, real-time ecological gradient baselines are dynamically generated to detect abnormal ecological gradients in a timely manner. Furthermore, an abnormal analysis management model is used to deeply analyze abnormal indicators, determine specific abnormal factors, and provide effective intervention plans through evaluation and alarm mechanisms. This method makes full use of the powerful computing power and flexibility of TensorFlow to achieve all-round, real-time monitoring and management of mountain ecosystems, providing a scientific basis for ecological protection and resource management. For the overall process, please refer to Figure 3 , please refer to Table 2 for specific data.

[0117]

[0118] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A data center data management method based on the TensorFlow ecosystem, characterized by: Construct a digital management platform, which includes: S1. Collect historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and preprocess them to obtain first historical multi-source data and first real-time multi-source data; the multi-source heterogeneous data includes spatial, temporal, and ecological environment data; S2. Build a data partition management model to analyze the first historical multi-source data to obtain data partition results; generate a gradient baseline based on the data partition results; The data partition management model includes a gradient baseline generation layer, which obtains a preliminary theoretical TensorFlow ecological baseline by performing multidimensional regression analysis on the TensorFlow ecological feature vector and the first real-time multi-source data. The autoencoder model performs nonlinear mapping on the TensorFlow ecological feature vector to extract the potential features in the TensorFlow ecosystem. The original TensorFlow ecological gradient data is reconstructed based on the learned potential features to generate a gradient baseline. S3. Calculate a real-time gradient baseline based on the first real-time multi-source data; obtain a reconstruction error of the gradient baseline by calculating the gradient baseline and the real-time gradient baseline; update the reconstruction error based on the real-time gradient baseline, dynamically adjust the threshold in real time, and obtain an abnormal TensorFlow ecological gradient; S4. Construct an anomaly analysis and management model to analyze the abnormal TensorFlow ecological gradient and obtain a TensorFlow ecological anomaly indicator vector; based on the analysis of the TensorFlow ecological anomaly indicator vector, obtain the specific abnormal factors that cause the anomaly; evaluate and alert the abnormal factors.

2. The data center data management method based on the TensorFlow ecosystem according to claim 1, characterized in that: The historical multi-source heterogeneous data includes historical server performance indicators, historical network traffic data, historical application logs, and historical device status data; the real-time multi-source heterogeneous data includes real-time server performance indicators, real-time network traffic data, real-time application logs, and real-time device status data; the preprocessing includes cleaning, normalization, and spatiotemporal alignment processing; The preprocessing uses the data processing components in the TensorFlow ecosystem to build a data flow graph to achieve efficient parallel processing and conversion of multi-source heterogeneous data.

3. The data center data management method based on the TensorFlow ecosystem according to claim 1, characterized in that: The data partition management model includes a data partition layer and a data feature extraction layer; The data partitioning layer generates preliminary data partitions by performing cluster analysis on the historical server performance indicators and historical application logs in the first historical multi-source data; performs feature correlation analysis on the historical application logs, historical network traffic data, historical application logs and historical device status data to obtain the first TensorFlow ecological variable features; modifies the preliminary data partitions based on the first TensorFlow ecological variable features to obtain data partition results; the data feature extraction layer obtains the TensorFlow ecological feature vector by performing feature extraction on the first TensorFlow ecological variable features and the data partition results.

4. The data center data management method based on the TensorFlow ecosystem according to claim 1, characterized in that: The abnormal TensorFlow ecological gradient generation steps include: Real-time gradient baseline measurement: based on the first real-time multi-source data, combined with the data partitioning results and the TensorFlow ecological feature vector, the real-time collected TensorFlow ecological data is subjected to feature learning and reconstruction using multidimensional regression analysis and the autoencoder model to generate a real-time gradient baseline; reconstruction error measurement: the real-time gradient baseline is subjected to nonlinear mapping and reconstruction using the autoencoder to obtain a reconstructed gradient baseline, and the reconstruction error is measured; abnormal TensorFlow ecological gradient identification: the reconstruction error is updated based on the real-time gradient baseline, and the preset threshold is dynamically adjusted in real time. When the reconstruction error is greater than the preset threshold, the abnormal TensorFlow ecological gradient is judged to be abnormal.

5. The data center data management method based on the TensorFlow ecosystem according to claim 1, characterized in that: The anomaly analysis and management model includes a TensorFlow ecological anomaly indicator vector acquisition layer and an anomaly factor acquisition layer; The TensorFlow ecological anomaly indicator vector acquisition layer compares the abnormal TensorFlow ecological gradient with the gradient baseline generated based on historical multi-source data, calculates the deviation of each variable, and combines the feature weights to calculate the TensorFlow ecological anomaly indicator vector; The abnormal factor acquisition layer attributes the ecological factors to the input TensorFlow ecological abnormality index vector using principal component regression analysis to obtain abnormal factors.

6. The data center data management method based on the TensorFlow ecosystem according to claim 1, characterized in that: The specific formula for evaluating the abnormal factors is: ； ； in, For each intervention program, For the plan the cost, For the plan An estimate of the reduction in abnormal risk, is the cost-estimated trade-off coefficient, is the average reconstruction error between the theoretical ecological gradient baseline generated based on historical multi-source data and the real-time ecological gradient baseline without intervention, reflecting the initial ecological anomaly risk. To apply the intervention plan After that, the reconstruction error reduction value measured by reconstructing the ecological characteristics through the autoencoder is When the minimum value of the objective function is obtained The variable value of .

7. Data center data management system based on TensorFlow ecosystem, characterized by: Executing the data center data management method based on the TensorFlow ecosystem as claimed in claim 1, comprising: A data acquisition module is used to collect historical multi-source heterogeneous data and real-time multi-source heterogeneous data in the data center and perform pre-processing to obtain first historical multi-source data and first real-time multi-source data; A gradient baseline acquisition module is used to build a data partition management model to analyze the first historical multi-source data to obtain data partition results; and generate a gradient baseline based on the data partition results; An abnormal TensorFlow ecological gradient acquisition module is used to calculate the real-time gradient baseline based on the first real-time multi-source data; obtain the reconstruction error of the gradient baseline by measuring the gradient baseline and the real-time gradient baseline; update the reconstruction error based on the real-time gradient baseline, dynamically adjust the threshold in real time, and obtain the abnormal TensorFlow ecological gradient; The abnormal factor acquisition module is used to build an abnormal analysis and management model to analyze the abnormal TensorFlow ecological gradient and obtain the TensorFlow ecological abnormality indicator vector; based on the analysis of the TensorFlow ecological abnormality indicator vector, the specific abnormal factors that cause the abnormality are obtained; and the abnormal factors are evaluated and alarmed.

Images