A 5G communication power supply monitoring method and system

Abstract

The present application relates to a 5G communication power supply monitoring method and system. The method includes: using artificial intelligence technology based on deep learning to perform time series analysis on the historical operation data of the power supply, respectively mining the time series dynamic change characteristics of the power supply voltage, power supply current and power supply temperature in each local time domain, and correspondingly fusing the three in the local time domain multimodal features to obtain the comprehensive feature representation of the power supply state in each local time domain, and then performing time series aggregation based on feature significance on the local time domain features of the power supply state to capture the core state information of the power supply in the global time domain, so as to intelligently identify whether preventive maintenance of the 5G communication power supply is required. In this way, potential failures of the 5G communication power supply can be discovered and prevented in advance, and the reliability and stability of the 5G communication power supply can be improved.

Description

Technical Field

[0001] The present application relates to the field of 5G communication technology, and specifically, to a 5G communication power supply monitoring method and system. Background Art

[0002] 5G communication technology is leading a revolution in communication technology with its high speed, low latency, and large capacity. However, the superior performance of 5G communication technology cannot be achieved without a stable and reliable power supply. Once the communication power supply in key facilities such as 5G base stations and data centers fails, it will cause signal interruption, service delays, and even system paralysis, seriously affecting user experience and the normal progress of social production activities. Therefore, ensuring the stable operation of 5G communication power supply is the basis for ensuring the quality of 5G communication networks and service continuity.

[0003] Traditional power supply monitoring methods mainly rely on threshold setting and periodic inspections. By setting thresholds for parameters such as voltage and current, alarms are triggered or emergency measures are taken when these parameters exceed the normal range. However, this method has several significant limitations: first, threshold settings are often based on experience or conservative estimates, which makes it difficult to accurately reflect the actual operating conditions of the power supply; second, the periodic inspection cycle is long and potential faults cannot be discovered in time; third, there is a lack of in-depth mining and analysis capabilities for power supply operation data, making it difficult to predict and prevent faults.

[0004] Therefore, a 5G communication power supply monitoring method and system are expected. Summary of the invention

[0005] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0006] In a first aspect, the present application provides a 5G communication power supply monitoring method, the method comprising:

[0007] Collecting historical operation data of the 5G communication power supply through a sensor network, wherein the historical operation data includes a time queue of power supply voltage, a time queue of power supply current, and a time queue of power supply temperature;

[0008] Transmitting the historical operation data of the 5G communication power supply to a power supply status remote monitoring center through a data transmission module;

[0009] In the power state remote monitoring center, extracting time series features based on local time scales for the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature, respectively, to obtain a sequence of local time series correlation feature vectors of the power supply voltage, a sequence of local time series correlation feature vectors of the power supply current, and a sequence of local time series correlation feature vectors of the power supply temperature;

[0010] Performing multimodal feature timing fusion on the sequence of the power supply voltage local timing associated feature vectors, the sequence of the power supply current local timing associated feature vectors, and the sequence of the power supply temperature local timing associated feature vectors to obtain a sequence of power state timing multimodal fusion representation vectors;

[0011] Performing information aggregation based on feature significance on the sequence of the power state time series multimodal fusion representation vectors to obtain a power state time series significant aggregation representation vector;

[0012] Based on the power state time series significant aggregation representation vector, determine whether to perform preventive maintenance on the 5G communication power supply.

[0013] Optionally, the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature are respectively subjected to timing feature extraction based on the local time scale to obtain a sequence of local timing association feature vectors of the power supply voltage, a sequence of local timing association feature vectors of the power supply current, and a sequence of local timing association feature vectors of the power supply temperature, including: dividing the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature respectively according to a predetermined time scale and then passing them through a sequence encoder based on a 1D-CNN model to obtain a sequence of local timing association feature vectors of the power supply voltage, a sequence of local timing association feature vectors of the power supply current, and a sequence of local timing association feature vectors of the power supply temperature.

[0014] Optionally, multimodal feature timing fusion is performed on the sequence of local timing association feature vectors of the power supply voltage, the sequence of local timing association feature vectors of the power supply current, and the sequence of local timing association feature vectors of the power supply temperature to obtain a sequence of power state timing multimodal fusion representation vectors, including: inputting each group of corresponding power supply voltage local timing association feature vectors, power supply current local timing association feature vectors, and power supply temperature local timing association feature vectors in the sequence of local timing association feature vectors of the power supply voltage, the sequence of local timing association feature vectors of the power supply current, and the sequence of local timing association feature vectors of the power supply temperature into a power state multimodal fusion representor based on a Bayesian probability network to obtain a sequence of power state timing multimodal fusion representation vectors.

[0015] Optionally, information aggregation based on feature significance is performed on the sequence of the power state timing multimodal fusion representation vectors to obtain the power state timing significant aggregation representation vector, including: inputting the sequence of the power state timing multimodal fusion representation vectors into a feature aggregation network guided by node feature significance attenuation to obtain the power state timing significant aggregation representation vector.

[0016] Optionally, the sequence of the power state time series multimodal fusion representation vectors is input into a feature aggregation network guided by node feature significance attenuation to obtain the power state time series significant aggregation representation vector, including: calculating the feature significance description factor of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors, wherein the feature significance description factor is related to the mean and variance of each power state time series multimodal fusion representation vector; taking the last power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors as the current power state time series multimodal fusion representation vector, and based on the power state time series multimodal fusion representation vectors of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors, The method comprises the following steps: constructing a characteristic significance attenuation factor of each power state time series multimodal fusion representation vector based on the distance span between the fusion representation vector and the current power state time series multimodal fusion representation vector; modulating the characteristic significance description factor of each power state time series multimodal fusion representation vector based on the characteristic significance attenuation factor of each power state time series multimodal fusion representation vector to obtain a sequence of characteristic significance attenuation description factors; inputting the sequence of characteristic significance attenuation description factors into a gated mask module to obtain a sequence of characteristic significance attenuation weight factors; taking the sequence of characteristic significance attenuation weight factors as a sequence of weights, calculating the weighted sum of the sequence of power state time series multimodal fusion representation vectors to obtain the power state time series significant aggregation representation vector.

[0017] Optionally, the feature significance description factor of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vector is calculated, including: calculating the expected value of the fourth power of the difference between each eigenvalue in the power state time series multimodal fusion representation vector and its eigenvalue mean, and dividing the expected value by the square of the feature variance of the power state time series multimodal fusion representation vector to obtain the feature significance description factor.

[0018] Optionally, based on the distance span between each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vector and the current power state time series multimodal fusion representation vector, a feature significance attenuation factor of each power state time series multimodal fusion representation vector is constructed, including: calculating the difference between the maximum eigenvalue of the current power state time series multimodal fusion representation vector and the maximum eigenvalue of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vector, and then dividing the difference by the number of eigenvectors separated therebetween to obtain the feature significance attenuation factor of each power state time series multimodal fusion representation vector.

[0019] Optionally, the feature significance description factors of each power state timing multimodal fusion representation vector are modulated based on the feature significance attenuation factors of each power state timing multimodal fusion representation vector to obtain a sequence of feature significance attenuation description factors, including: calculating the product between the feature significance attenuation factors of each power state timing multimodal fusion representation vector and their feature significance description factors to obtain the sequence of feature significance attenuation description factors.

[0020] Optionally, based on the power state time series significant aggregation representation vector, determining whether to perform preventive maintenance on the 5G communication power supply includes: inputting the power state time series significant aggregation representation vector into a classifier-based monitoring result generator to obtain a monitoring result, and the monitoring result is used to indicate whether to perform preventive maintenance on the 5G communication power supply.

[0021] In a second aspect, the present application provides a 5G communication power supply monitoring system, the system comprising:

[0022] A historical operation data collection module, used to collect historical operation data of the 5G communication power supply through a sensor network, wherein the historical operation data includes a time queue of the power supply voltage, a time queue of the power supply current, and a time queue of the power supply temperature;

[0023] A data transmission module, used to transmit the historical operation data of the 5G communication power supply to a power supply status remote monitoring center through the data transmission module;

[0024] A timing feature extraction module is used to extract timing features based on local time scales for the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature in the power supply status remote monitoring center to obtain a sequence of local timing correlation feature vectors of the power supply voltage, a sequence of local timing correlation feature vectors of the power supply current, and a sequence of local timing correlation feature vectors of the power supply temperature;

[0025] A multimodal feature timing fusion module, used for performing multimodal feature timing fusion on the sequence of the power supply voltage local timing associated feature vectors, the sequence of the power supply current local timing associated feature vectors and the sequence of the power supply temperature local timing associated feature vectors to obtain a sequence of power state timing multimodal fusion representation vectors;

[0026] A feature saliency information aggregation module, used for performing feature saliency-based information aggregation on the sequence of the power state time series multimodal fusion representation vector to obtain a power state time series saliency aggregation representation vector;

[0027] A preventive maintenance judgment module is used to determine whether to perform preventive maintenance on the 5G communication power supply based on the power supply state time series significant aggregation representation vector.

[0028] The above technical solution is adopted to analyze the historical operation data of the power supply by using artificial intelligence technology based on deep learning, and the time series dynamic change characteristics of the power supply voltage, power supply current and power supply temperature in each local time domain are respectively mined, and the three are correspondingly fused in the local time domain multimodal features to obtain the comprehensive feature representation of the power supply state in each local time domain, and then the local time domain features of the power supply state are aggregated based on feature significance to capture the core state information of the power supply in the global time domain, so as to intelligently identify whether preventive maintenance of the 5G communication power supply is required. In this way, potential failures of the 5G communication power supply can be discovered and prevented in advance, and the reliability and stability of the 5G communication power supply can be improved.

[0029] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0031] Figure 1 It is a flowchart of a 5G communication power supply monitoring method according to an exemplary embodiment.

[0032] Figure 2 It is a block diagram of a 5G communication power supply monitoring system according to an exemplary embodiment.

[0033] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0034] Figure 4It is an application scenario diagram of a 5G communication power supply monitoring method according to an exemplary embodiment. DETAILED DESCRIPTION

[0035] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0036] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0037] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0038] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0039] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0040] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0041] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0042] Figure 1 is a flow chart of a 5G communication power monitoring method according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0043] Step S101, collecting historical operation data of a 5G communication power supply through a sensor network, wherein the historical operation data includes a time queue of a power supply voltage, a time queue of a power supply current, and a time queue of a power supply temperature;

[0044] Step S102: transmitting the historical operation data of the 5G communication power supply to a power supply status remote monitoring center through a data transmission module;

[0045] Step S103: at the power state remote monitoring center, extracting time series features based on local time scales for the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature, respectively, to obtain a sequence of local time series correlation feature vectors of the power supply voltage, a sequence of local time series correlation feature vectors of the power supply current, and a sequence of local time series correlation feature vectors of the power supply temperature;

[0046] Step S104, performing multimodal feature timing fusion on the sequence of the power supply voltage local timing associated feature vectors, the sequence of the power supply current local timing associated feature vectors, and the sequence of the power supply temperature local timing associated feature vectors to obtain a sequence of power state timing multimodal fusion representation vectors;

[0047] Step S105, performing information aggregation based on feature significance on the sequence of the power state time series multimodal fusion representation vectors to obtain a power state time series significant aggregation representation vector;

[0048] Step S106: Determine whether to perform preventive maintenance on the 5G communication power supply based on the power supply status time series significant aggregation representation vector.

[0049] In response to the above technical problems, the technical concept of this application is to use artificial intelligence technology based on deep learning to perform time series analysis on the historical operation data of the power supply, respectively dig out the time series dynamic change characteristics of the power supply voltage, power supply current and power supply temperature in each local time domain, and fuse the three local time domain multimodal features to obtain the comprehensive feature representation of the power supply state in each local time domain, and then perform time series aggregation based on feature significance on the local time domain features of the power supply state to capture the core state information of the power supply in the global time domain, so as to intelligently identify whether preventive maintenance is needed for the 5G communication power supply. In this way, potential failures of the 5G communication power supply can be discovered and prevented in advance, and the reliability and stability of the 5G communication power supply can be improved.

[0050] Based on this, in the technical solution of this application, first, the historical operation data of the 5G communication power supply is collected through the sensor network, wherein the historical operation data includes the time queue of the power supply voltage, the time queue of the power supply current and the time queue of the power supply temperature. It should be understood that voltage, current and temperature are key indicators of the power supply operation status, which can effectively reflect the performance and stability of the power supply under different load conditions, and are important basic data for power supply monitoring.

[0051] Subsequently, the historical operation data of the 5G communication power supply is transmitted to the power supply status remote monitoring center through the data transmission module to realize remote monitoring and centralized data processing of the power supply status.

[0052] Next, considering that the historical operation data of the 5G communication power supply may have a huge amount of data and high-dimensional characteristics, direct data analysis not only has high computational complexity, but may also lead to the loss of local detail information. Therefore, in order to extract the historical operation status characteristics of the power supply more carefully, in the technical solution of the present application, the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature are first divided into a predetermined time scale to form a plurality of local time domain segments. Subsequently, the 1D-CNN (one-dimensional convolutional neural network) model is used as a sequence encoder to extract features of the voltage, current, and temperature data in each local time domain segment, and the dynamic change trend of each parameter in each local time domain is effectively mined through the sliding convolution operation, thereby generating a sequence of local timing-related feature vectors of the power supply voltage, a sequence of local timing-related feature vectors of the power supply current, and a sequence of local timing-related feature vectors of the power supply temperature.

[0053] In one embodiment of the present application, the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature are respectively subjected to timing feature extraction based on the local time scale to obtain a sequence of local timing association feature vectors of the power supply voltage, a sequence of local timing association feature vectors of the power supply current, and a sequence of local timing association feature vectors of the power supply temperature, including: dividing the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature respectively according to a predetermined time scale and then passing them through a sequence encoder based on a 1D-CNN model to obtain a sequence of local timing association feature vectors of the power supply voltage, a sequence of local timing association feature vectors of the power supply current, and a sequence of local timing association feature vectors of the power supply temperature.

[0054] Secondly, in order to integrate multi-dimensional information and more comprehensively evaluate the power supply operation status, the present application further adopts a power supply state multimodal fusion representation based on a quasi-Bayesian probability network to fuse the local timing correlation feature vectors of the power supply voltage, the local timing correlation feature vectors of the power supply current, and the local timing correlation feature vectors of the power supply temperature in each local time domain. Specifically, the quasi-Bayesian probability network is a multi-source information fusion technology based on a probabilistic graph model, which can effectively handle the uncertainty and correlation in the data and realize the effective integration of multi-source data. In the technical solution of the present application, the topological structure of the quasi-Bayesian probability network is constructed based on the mutual dependence between the power supply voltage, the power supply current, and the power supply temperature, and the network is used to perform probabilistic reasoning and information integration on the local timing correlation feature vectors of the power supply voltage, the local timing correlation feature vectors of the power supply current, and the local timing correlation feature vectors of the power supply temperature to generate a sequence of power supply state timing multimodal fusion representation vectors. In this way, the mutual influence and correlation between different power supply parameters are fully considered, so that the actual operation state of the power supply can be described more accurately and comprehensively.

[0055] In one embodiment of the present application, multimodal feature timing fusion is performed on the sequence of local timing association feature vectors of the power supply voltage, the sequence of local timing association feature vectors of the power supply current, and the sequence of local timing association feature vectors of the power supply temperature to obtain a sequence of power state timing multimodal fusion representation vectors, including: each group of corresponding power supply voltage local timing association feature vectors, power supply current local timing association feature vectors, and power supply temperature local timing association feature vectors in the sequence of local timing association feature vectors of the power supply voltage, the sequence of local timing association feature vectors of the power supply current, and the sequence of local timing association feature vectors of the power supply temperature are respectively input into a power state multimodal fusion representor based on a Bayesian probability network to obtain a sequence of power state timing multimodal fusion representation vectors.

[0056] Furthermore, in order to further explore the core features and evolution trends of the power state from a global perspective, this application introduces a feature aggregation network guided by the attenuation of node feature significance to fuse the sequence of the power state time series multimodal fusion representation vector, and performs feature screening and aggregation according to feature significance, thereby improving the feature discrimination.

[0057] In one embodiment of the present application, information aggregation based on feature significance is performed on the sequence of the power state timing multimodal fusion representation vectors to obtain the power state timing significant aggregation representation vector, including: inputting the sequence of the power state timing multimodal fusion representation vectors into a feature aggregation network guided by node feature significance attenuation to obtain the power state timing significant aggregation representation vector.

[0058] Specifically, the feature aggregation network first calculates the feature significance description factor based on the mean and variance of each power state time series multimodal fusion representation vector, providing an important priority indicator for subsequent feature selection and aggregation. Here, the mean reflects the central position of the feature value, while the variance represents the degree of dispersion of the feature value, and the two together determine the significance of the feature. Then, based on the distance span between each power state time series multimodal fusion representation vector and the current power state time series multimodal fusion representation vector (the end of the time series), a feature significance attenuation factor is constructed, so that the feature vector that is closer to the current power state in the feature space obtains a higher weight, thereby strengthening the correlation of the local time domain power features. Furthermore, the feature significance attenuation factor of each power state time series multimodal fusion representation vector is used to modulate its feature significance description factor, so that it more accurately reflects the relative importance of each local time domain feature in the global time domain. Then, the modulated descriptive factors are further screened using activation functions and gating mechanisms, and the screened descriptive factors are used as weights to perform weighted aggregation on the sequence of the power state time series multimodal fusion representation vectors, so as to integrate the power state information of each local time domain and generate a global power state time series significant aggregation representation vector, thereby more accurately characterizing the overall operating status of the power supply.

[0059] In one embodiment of the present application, the sequence of the power state time series multimodal fusion representation vectors is input into a feature aggregation network guided by node feature significance attenuation to obtain the power state time series significant aggregation representation vector, including: calculating the feature significance description factor of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors, wherein the feature significance description factor is related to the mean and variance of each power state time series multimodal fusion representation vector; taking the last power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors as the current power state time series multimodal fusion representation vector, and based on the power state time series multimodal fusion representation vectors in the sequence of the power state time series multimodal fusion representation vectors, calculating the feature significance description factor of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors; ... The method comprises the following steps: according to the distance span between the time series multimodal fusion representation vector of the current power state and the time series multimodal fusion representation vector of the current power state, constructing the feature significance attenuation factors of the time series multimodal fusion representation vectors of each power state; modulating the feature significance description factors of the time series multimodal fusion representation vectors of each power state based on the feature significance attenuation factors of the time series multimodal fusion representation vectors of each power state to obtain a sequence of feature significance attenuation description factors; inputting the sequence of feature significance attenuation description factors into a gated mask module to obtain a sequence of feature significance attenuation weight factors; taking the sequence of feature significance attenuation weight factors as a sequence of weights, calculating the weighted sum of the sequence of the power state time series multimodal fusion representation vectors to obtain the power state time series significant aggregation representation vector.

[0060] Furthermore, in one embodiment of the present application, the feature significance description factor of each power state timing multimodal fusion representation vector in the sequence of the power state timing multimodal fusion representation vector is calculated, including: calculating the expected value of the fourth power of the difference between each eigenvalue in the power state timing multimodal fusion representation vector and its eigenvalue mean, and dividing the expected value by the square of the feature variance of the power state timing multimodal fusion representation vector to obtain the feature significance description factor.

[0061] Furthermore, in one embodiment of the present application, based on the distance span between each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vector and the current power state time series multimodal fusion representation vector, a feature significance attenuation factor of each power state time series multimodal fusion representation vector is constructed, including: calculating the difference between the maximum eigenvalue of the current power state time series multimodal fusion representation vector and the maximum eigenvalue of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vector, and then dividing the difference by the number of eigenvectors separated therebetween to obtain the feature significance attenuation factor of each power state time series multimodal fusion representation vector.

[0062] Furthermore, in one embodiment of the present application, the feature significance description factor of each power state timing multimodal fusion representation vector is modulated based on the feature significance attenuation factor of each power state timing multimodal fusion representation vector to obtain a sequence of feature significance attenuation description factors, including: calculating the product between the feature significance attenuation factor of each power state timing multimodal fusion representation vector and its feature significance description factor to obtain the sequence of feature significance attenuation description factors.

[0063] Specifically, the sequence of the power state time series multimodal fusion representation vector is processed by the following feature significance attenuation guided fusion formula to obtain the power state time series significant aggregation representation vector, wherein the feature significance attenuation guided fusion formula is:

[0064]

[0065] in, A sequence of multimodal fusion representation vectors representing the power state timing, The value of is the number of feature vectors in the sequence of the power state time series multimodal fusion representation vector, , , , and Respectively represent the first, second, and third in the sequence of the multimodal fusion representation vector of the power state time series , and the current power state time series multimodal fusion representation vector, represents the maximum eigenvalue of the eigenvector, Indicates the The first power state time series multimodal fusion representation vector eigenvalues, and Respectively represent the The feature mean and square of the feature variance of the multimodal fusion representation vector of the power state time series are: Indicates the The fourth-order central moment of the multimodal fusion representation vector of the power state time series, that is, The expected value of the fourth power of the difference between each eigenvalue and its eigenmean in the multimodal fusion representation vector of the power state time series, Indicates the The characteristic significance attenuation factor of the multimodal fusion representation vector of the power state time series, Indicates The feature significance decay factor is described by Indicates Normalized feature significance decay description factor, Indicates feature significance decay weight factor, is the preset threshold, Indicates mask processing, A vector representing a significant aggregation of the power state timings is shown.

[0066] Next, the power state time series significant aggregation representation vector is input into a classifier-based monitoring result generator to obtain a monitoring result, and the monitoring result is used to indicate whether preventive maintenance is performed on the 5G communication power supply.

[0067] In one embodiment of the present application, based on the power state time series significant aggregation representation vector, determining whether to perform preventive maintenance on the 5G communication power supply includes: inputting the power state time series significant aggregation representation vector into a classifier-based monitoring result generator to obtain a monitoring result, and the monitoring result is used to indicate whether to perform preventive maintenance on the 5G communication power supply.

[0068] Here, each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vector represents the local time series features of the power supply voltage, power supply current and power supply temperature respectively, and the local time series multimodal fusion features of the power state are determined by a posteriori reasoning based on a quasi-Bayesian probability network. Considering that the local time series feature distribution difference caused by the source time series distribution difference of the power supply voltage, power supply current and power supply temperature will cause the local time domain fine-grained time series interaction aggregation offset in the full time domain when the feature aggregation guided by the node feature significance attenuation is based on the node feature significance attenuation, it is expected to further improve the full time domain fine-grained time series aggregation regression comprehensibility of the power state time series significant aggregation representation vector, thereby improving the accuracy of the monitoring result obtained by the monitoring result generator based on the classifier input.

[0069] In a preferred example, inputting the power state time series significant aggregation representation vector into a classifier-based monitoring result generator to obtain a monitoring result includes:

[0070] Calculate the sum of the absolute values ​​of each eigenvalue of the power state time series significant aggregation representation vector to obtain a first power state time series significant aggregation and modulation value, and calculate the square root of the sum of the squares of each eigenvalue of the power state time series significant aggregation representation vector to obtain a second power state time series significant aggregation and modulation value;

[0071] After performing dot-wise subtraction on the power state time series significant aggregation representation vector and the second power state time series significant aggregation and modulation value, perform dot-wise multiplication on the number of eigenvalues ​​of the power state time series significant aggregation representation vector and the reciprocal of the first power state time series significant aggregation and modulation value, and take the reciprocal of each eigenvalue to obtain the first power state time series significant aggregation phase transition vector;

[0072] After performing dot-wise subtraction on the power state time series significant aggregation representation vector and the first power state time series significant aggregation and modulation value, perform dot-wise multiplication on the square root of the number of eigenvalues ​​of the power state time series significant aggregation representation vector and the reciprocal of the second power state time series significant aggregation and modulation value, and take the reciprocal of each eigenvalue to obtain the second power state time series significant aggregation phase transition vector;

[0073] Subtract the dot product vector of the second power state timing significant aggregation phase transition vector and the weighted hyperparameter from the first power state timing significant aggregation phase transition vector to obtain an optimized power state timing significant aggregation representation vector;

[0074] The optimized power state timing significant aggregation representation vector is input into a classifier-based monitoring result generator to obtain a monitoring result.

[0075] Here, the power state time series significant aggregation representation vector is denoted as The optimization expression is:

[0076]

[0077] in, A significant aggregation representation vector for the power state timing, represents the set of real numbers, The first vector representing the power state timing significant aggregation representation vector The eigenvalues ​​at the positions, The number of eigenvalues ​​representing the significant aggregation of the power state time series representation vector, Indicates the first power state timing significant aggregation and modulation values, Indicates the second power state timing significant aggregation and modulation values, It means point multiplication by position. It means subtracting by position. It means to calculate the inverse of each eigenvalue of the eigenvector. Indicates the first power state timing significantly aggregated phase transition vector, Indicates that the second power state timing significantly aggregates the phase transition vector, represents the weighted hyperparameter, The optimized power state timings are significantly aggregated into representation vectors.

[0078] Therefore, in the preferred example, the difference of the difference and modulation representation of the eigenvalue of the power state time series significant aggregation representation vector relative to the feature set of the vector as a whole of the power state time series significant aggregation representation vector is used as the semantic change intensity information, and a phase-like transformation corresponding to the position-based intensity modulation is performed through different and modulation representation forms, so that the aggregation enhancement of the semantic change phase perception can enhance the axial aggregation receptive field along the feature aggregation direction by performing a spatial translation operation based on alternating stacking under the scale balance of the vector set of the power state time series significant aggregation representation vector, thereby improving the perception effect of the aggregation semantics of the power state time series significant aggregation representation vector on the detailed semantic changes, so as to improve the full-time domain fine-grained time series aggregation regression comprehensibility of the power state time series significant aggregation representation vector, and improve the accuracy of the monitoring results obtained by the monitoring result generator based on the classifier of the power state time series significant aggregation representation vector.

[0079] In summary, the above scheme uses artificial intelligence technology based on deep learning to perform time series analysis on the historical operation data of the power supply, and respectively mines out the time series dynamic change characteristics of the power supply voltage, power supply current and power supply temperature in each local time domain, and fuses the local time domain multimodal features of the three to obtain the comprehensive feature representation of the power supply state in each local time domain, and then through the time series aggregation of the local time domain features of the power supply state based on feature significance, to capture the core state information of the power supply in the global time domain, so as to intelligently identify whether preventive maintenance of the 5G communication power supply is required. In this way, potential failures of the 5G communication power supply can be discovered and prevented in advance, and the reliability and stability of the 5G communication power supply can be improved.

[0080] Figure 2 FIG. 1 is a block diagram of a 5G communication power supply monitoring system according to an exemplary embodiment. Figure 2 As shown, the system 200 includes:

[0081] A historical operation data collection module 201 is used to collect historical operation data of the 5G communication power supply through a sensor network, wherein the historical operation data includes a time queue of the power supply voltage, a time queue of the power supply current, and a time queue of the power supply temperature;

[0082] A data transmission module 202, used to transmit the historical operation data of the 5G communication power supply to a power supply status remote monitoring center through the data transmission module;

[0083] A timing feature extraction module 203 is used to extract timing features based on local time scales for the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature in the power supply status remote monitoring center to obtain a sequence of local timing correlation feature vectors of the power supply voltage, a sequence of local timing correlation feature vectors of the power supply current, and a sequence of local timing correlation feature vectors of the power supply temperature;

[0084] The multimodal feature timing fusion module 204 is used to perform multimodal feature timing fusion on the sequence of the power supply voltage local timing associated feature vectors, the sequence of the power supply current local timing associated feature vectors and the sequence of the power supply temperature local timing associated feature vectors to obtain a sequence of power state timing multimodal fusion representation vectors;

[0085] The feature saliency information aggregation module 205 is used to perform feature saliency-based information aggregation on the sequence of the power state time series multimodal fusion representation vectors to obtain a power state time series saliency aggregation representation vector;

[0086] The preventive maintenance judgment module 206 is used to determine whether to perform preventive maintenance on the 5G communication power supply based on the power supply state time series significant aggregation representation vector.

[0087] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0088] like Figure 3As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0089] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0090] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0091] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0092] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0093] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0094] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0095] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0096] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".

[0097] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0098] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] Figure 4 FIG. 1 is an application scenario diagram of a 5G communication power supply monitoring method according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, the historical operation data of the 5G communication power supply is collected through the sensor network, wherein the historical operation data includes a time queue of the power supply voltage (for example, Figure 4 C1 as shown in the figure), the time queue of the power supply current (for example, Figure 4 C2) and the time sequence of the power supply temperature (e.g., as Figure 4 Then, the obtained time queue of power supply voltage, time queue of power supply current and time queue of power supply temperature are input to a server (for example, Figure 4 In S) shown in , the server is capable of processing the time queue of the power supply voltage, the time queue of the power supply current and the time queue of the power supply temperature based on the 5G communication power supply monitoring algorithm to determine whether to perform preventive maintenance on the 5G communication power supply.

[0100] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0101] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0102] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementation. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

Claims

1. A 5G communication power supply monitoring method, characterized in that: include: Collecting historical operating data of the 5G communication power supply through a sensor network, wherein the historical operating data includes a time queue of power supply voltage, a time queue of power supply current, and a time queue of power supply temperature; Transmitting the historical operating data of the 5G communication power supply to a power supply status remote monitoring center through a data transmission module; At the power status remote monitoring center, performing time series feature extraction based on local time scale on the time queue of the power voltage, the time queue of the power current, and the time queue of the power temperature, respectively, to obtain a sequence of local time series correlation feature vectors of the power voltage, a sequence of local time series correlation feature vectors of the power current, and a sequence of local time series correlation feature vectors of the power temperature; Performing multimodal feature time series fusion on the sequence of the power supply voltage local time series associated feature vectors, the sequence of the power supply current local time series associated feature vectors, and the sequence of the power supply temperature local time series associated feature vectors to obtain a sequence of power supply state time series multimodal fusion representation vectors; Performing feature-significance-based information aggregation on the sequence of the power state time series multimodal fusion representation vectors to obtain a power state time series significant aggregation representation vector; Determining whether to perform preventive maintenance on the 5G communication power supply based on the power supply state time series significant aggregation representation vector; The time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature are respectively subjected to time series feature extraction based on a local time scale to obtain a sequence of local time series correlation feature vectors of the power supply voltage, a sequence of local time series correlation feature vectors of the power supply current, and a sequence of local time series correlation feature vectors of the power supply temperature, including: The time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature are respectively divided into predetermined time scales and passed through a sequence encoder based on a 1D-CNN model to obtain a sequence of local timing correlation feature vectors of the power supply voltage, a sequence of local timing correlation feature vectors of the power supply current, and a sequence of local timing correlation feature vectors of the power supply temperature; Performing multimodal feature time series fusion on the sequence of the power supply voltage local time series associated feature vectors, the sequence of the power supply current local time series associated feature vectors, and the sequence of the power supply temperature local time series associated feature vectors to obtain a sequence of power supply state time series multimodal fusion representation vectors, including: Inputting each corresponding group of the power supply voltage local timing association feature vectors, the power supply current local timing association feature vectors, and the power supply temperature local timing association feature vectors in the sequence of the power supply voltage local timing association feature vectors, the power supply current local timing association feature vectors, and the power supply temperature local timing association feature vectors into a power state multimodal fusion representor based on a Bayesian-like probability network to obtain a sequence of the power state timing multimodal fusion representation vectors; Performing feature-significance-based information aggregation on the sequence of the power state time series multimodal fusion representation vectors to obtain a power state time series significant aggregation representation vector, including: Inputting the sequence of the power state time series multimodal fusion representation vectors into a feature aggregation network guided by node feature significance attenuation to obtain the power state time series significant aggregation representation vector; Inputting the sequence of the power state time series multimodal fusion representation vectors into a feature aggregation network guided by node feature significance attenuation to obtain the power state time series significant aggregation representation vector, including: Calculating a feature significance description factor of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors, wherein the feature significance description factor is related to the mean and variance of each power state time series multimodal fusion representation vector; Taking the last power state time series multimodal fusion representation vector in the sequence of power state time series multimodal fusion representation vectors as the current power state time series multimodal fusion representation vector, and constructing feature significance attenuation factors of each power state time series multimodal fusion representation vector based on the distance span between each power state time series multimodal fusion representation vector in the sequence of power state time series multimodal fusion representation vectors and the current power state time series multimodal fusion representation vector; Modulating the feature significance description factors of each power state time series multimodal fusion representation vector based on the feature significance attenuation factors of each power state time series multimodal fusion representation vector to obtain a sequence of feature significance attenuation description factors; Inputting the sequence of feature significance attenuation description factors into a gated mask module to obtain a sequence of feature significance attenuation weighting factors; Using the sequence of the feature significance attenuation weight factors as a sequence of weights, calculating a weighted sum of the sequence of the power state time series multimodal fusion representation vectors to obtain the power state time series significant aggregation representation vector; Constructing a feature significance attenuation factor of each power state time series multimodal fusion representation vector based on a distance span between each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vector and the current power state time series multimodal fusion representation vector, including: Calculating the difference between the maximum eigenvalue of the current power state time series multimodal fusion representation vector and the maximum eigenvalue of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors, and then dividing the difference by the number of eigenvectors between the two to obtain a feature significance attenuation factor of each power state time series multimodal fusion representation vector; Determining whether to perform preventive maintenance on the 5G communication power supply based on the power supply state time series significant aggregation representation vector includes: The power state time series significant aggregation representation vector is input into a classifier-based monitoring result generator to obtain a monitoring result, and the monitoring result is used to indicate whether preventive maintenance is performed on the 5G communication power supply.

2. The 5G communication power supply monitoring method according to claim 1, characterized in that: Calculating a feature significance description factor of each power state time series multimodal fusion representation vector in the sequence of the power state time series multimodal fusion representation vectors includes: Calculate the expected value of the fourth power of the difference between each eigenvalue in the power state time series multimodal fusion representation vector and its eigenvalue mean, and divide the expected value by the square of the eigenvariance of the power state time series multimodal fusion representation vector to obtain the feature significance description factor.

3. The 5G communication power supply monitoring method according to claim 2, characterized in that: Modulating the feature significance description factors of the respective power state time series multimodal fusion representation vectors based on the feature significance attenuation factors of the respective power state time series multimodal fusion representation vectors to obtain a sequence of feature significance attenuation description factors includes: The product of the feature significance attenuation factor of each power state time series multimodal fusion representation vector and its feature significance description factor is calculated to obtain a sequence of the feature significance attenuation description factors.

4. A 5G communication power supply monitoring system for executing the 5G communication power supply monitoring method according to claim 1, characterized in that: include: A historical operation data acquisition module is used to collect historical operation data of the 5G communication power supply through a sensor network, wherein the historical operation data includes a time queue of the power supply voltage, a time queue of the power supply current, and a time queue of the power supply temperature; A data transmission module, used to transmit the historical operating data of the 5G communication power supply to a power supply status remote monitoring center through the data transmission module; a timing feature extraction module, configured to perform timing feature extraction based on a local time scale on the time queue of the power supply voltage, the time queue of the power supply current, and the time queue of the power supply temperature in the power supply status remote monitoring center, so as to obtain a sequence of local timing correlation feature vectors of the power supply voltage, a sequence of local timing correlation feature vectors of the power supply current, and a sequence of local timing correlation feature vectors of the power supply temperature; a multimodal feature timing fusion module, configured to perform multimodal feature timing fusion on the sequence of the power supply voltage local timing correlation feature vectors, the sequence of the power supply current local timing correlation feature vectors, and the sequence of the power supply temperature local timing correlation feature vectors to obtain a sequence of power supply state timing multimodal fusion representation vectors; A feature saliency information aggregation module, configured to perform feature saliency-based information aggregation on the sequence of the power state time series multimodal fusion representation vectors to obtain a power state time series saliency aggregation representation vector; A preventive maintenance judgment module is used to determine whether to perform preventive maintenance on the 5G communication power supply based on the power supply status time series significant aggregation representation vector.

Images