A communication power supply status monitoring method and system based on 5G communication

Abstract

The present invention relates to the field of data processing technology, and specifically to a communication power supply status monitoring method and system based on 5G communication, the method comprising: obtaining electric power information input by a communication power supply at a network node in a communication network, the amount of data from a data source of the network node, and the total amount of data processed by the network node; determining the importance of fluctuations in data from the data source; fitting multiple data sequences under the total amount of data processing to obtain multiple data fitting sequences; determining a predicted power threshold of the network node according to the fitting validity of each data fitting sequence, the importance of fluctuations in each data source in each data fitting sequence, and the predicted amount of data from each data source; monitoring the status of the communication power supply based on the predicted power threshold and the actual electric power information provided by the communication power supply to the network node. The present invention improves the accuracy, reliability, and timeliness of status monitoring of the communication power supply.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a communication power supply status monitoring method and system based on 5G communication. Background Art

[0002] The communication power supply is a system that provides a stable power supply for communication equipment, which ensures the normal operation and reliability of the communication network. In order to ensure the normal operation and reliability of communication, it is necessary to monitor the status of the communication power supply. When monitoring the status of the communication power supply, the fifth generation mobile communication technology (Fifth Generation Mobile Networks, 5G) communication technology can be used to transmit data. 5G communication technology has high-speed data transmission capabilities and can quickly transmit the status information of the communication power supply from the monitoring point to the control center. The high-speed transmission of 5G communication technology reduces data delay, allowing the monitoring system to reflect the changes in the status of the communication power supply in real time, thereby improving the timeliness and accuracy of the monitoring of the communication power supply.

[0003] In some scenarios, the monitoring of the status of the communication power supply mainly relies on setting fixed thresholds, such as setting fixed thresholds for parameters such as voltage and current. When the voltage and current parameters of the communication power supply exceed the corresponding fixed thresholds, alarms and emergency measures will be triggered. However, the setting of the above fixed thresholds is often based on experience or conservative estimates. For example, when the amount of information processing of the communication equipment increases, the power usage of the corresponding communication power supply will also increase. The fixed threshold is difficult to accurately reflect the actual operating status of the communication power supply, and it is impossible to detect potential faults of the communication power supply in time, resulting in low accuracy, reliability and timeliness of the status monitoring of the communication power supply. Summary of the invention

[0004] In order to solve the technical problems of low accuracy, reliability and timeliness of communication power status monitoring, the purpose of the present invention is to provide a communication power status monitoring method and system based on 5G communication. The technical solutions adopted are as follows:

[0005] In the first aspect, an embodiment of the present invention provides a communication power supply status monitoring method based on 5G communication, including: obtaining electric power information of the communication power supply input at the network node in the communication network, the data volume of the data source of the network node, and the total data processing volume processed by the network node; determining the fluctuation importance of the data of the data source according to the data volume of the data source of the network node, the total data processing volume and electric power information; fitting multiple data sequences under the total data processing volume to obtain multiple data fitting sequences; determining the predicted power threshold of the network node according to the fitting validity of each data fitting sequence, the fluctuation importance of each data source in each data fitting sequence, and the predicted data volume of each data source; monitoring the status of the communication power supply based on the predicted power threshold and the actual electric power information provided by the communication power supply to the network node.

[0006] Optionally, determining the importance of data fluctuation of a data source based on the amount of data from the data source of the network node, the total amount of data processing, and the electric power information includes: determining a proportion parameter of the data source of the network node based on the amount of data from the data source and the total amount of data processing; determining the electric power fluctuation interval corresponding to a proportion combination composed of the proportion parameters of the data source in the total amount of data processing; determining the clustering of the distribution of data points in the proportion combination based on the first mean value and standard deviation of the electric power information in the electric power fluctuation interval; determining the difference in change of the proportion parameters of any two data sources based on the change of the proportion parameters of any two data sources; determining the importance of data fluctuation of the data source based on the difference in change of the proportion parameters of any two data sources, the difference in clustering in the electric power fluctuation interval of any two data sources, the difference in distance between the electric power fluctuation intervals of any two data sources, and the number of data in the current data source that are simultaneously in the electric power fluctuation intervals of any two data sources.

[0007] Optionally, determining a proportion parameter of the data source of the network node based on the data volume of the data source and the total data processing volume includes: determining a first ratio between the data volume of the data source and the total data processing volume as the proportion parameter of the data source of the network node.

[0008] Optionally, determining the clustering of the data point distribution in the proportion combination based on the first mean value and standard deviation of the electric power information in the electric power fluctuation range includes: determining a second ratio between the first mean value and the standard deviation as the clustering of the data point distribution in the proportion combination.

[0009] Optionally, determining the fluctuation importance of data from a data source based on the difference in changes in proportion parameters of any two data sources, the difference in aggregation in the power fluctuation interval of any two data sources, the difference in distance between the power fluctuation intervals of any two data sources, and the number of data in the current data source that are simultaneously in the power fluctuation intervals of any two data sources includes: performing inverse proportional normalization processing on the numbers in the power fluctuation intervals of any two data sources to obtain a normalized value; calculating the first product between the difference in aggregation in the power fluctuation interval of any two data sources, the distance difference, and the normalized value; and determining the fifth ratio between the first product and the difference in changes in proportion parameters of any two data sources as the fluctuation importance of data from the data source.

[0010] Optionally, determining the predicted power threshold of the network node based on the fitting validity of each data fitting sequence, the fluctuation importance of each data source in each data fitting sequence, and the predicted data volume of each data source includes: determining the weight of each data source for subsequent electric power information under the total data processing volume based on the fitting validity of each data fitting sequence and the fluctuation importance of each data source in each data fitting sequence; determining the total predicted data processing volume in the network node by using the predicted data volume of each data source, the number of times each data source appears in the historical data, and the weight corresponding to each data source; screening target historical data with the same predicted data volume of each data source and the same predicted data processing volume from the historical data of the network node; determining the predicted power threshold of the network node based on the fitting validity of each data sequence, the electric power information of the target historical data, and the number of target historical data.

[0011] Optionally, based on the fitting validity of each data fitting sequence and the fluctuation importance of each data source in each data fitting sequence, determining the weight of each data source under the total data processing volume for subsequent electric power information includes: superimposing the fitting validity of each data fitting sequence to obtain a first superimposed value, and calculating the second product between the first superimposed value and the fluctuation importance of the first data source in the data fitting sequence; calculating the third product between the first superimposed value and the fluctuation importance of each data source in each data fitting sequence, and superimposing each third product to obtain a second superimposed value; determining a third ratio between the second product and the second superimposed value as the weight of the data source for the subsequent electric power information.

[0012] Optionally, the predicted data volume of each data source, the number of times each data source appears in historical data and the weight corresponding to each data source are used to determine the total predicted data processing volume in the network node, including: superimposing the weights corresponding to each data source to obtain the weight of the predicted value of each data source; calculating the fourth product between the predicted data volume of each data source and the weight, and superimposing each fourth product to obtain the total predicted data processing volume in the network node.

[0013] Optionally, determining the predicted power threshold of the network node based on the fitting validity of each data sequence, the electric power information of the target historical data and the number of target historical data includes: calculating the fifth product between the fitting validity of each data sequence and the electric power information of the target historical data; superimposing each fifth product to obtain a third superposition value; and determining a fourth ratio between the third superposition value and the number of target historical data as the predicted power threshold of the network node.

[0014] In the second aspect, an embodiment of the present invention further provides a communication power status monitoring system based on 5G communication, comprising: a processor and a memory; wherein the memory is used to store a computer program that can be run on the processor; and the processor is used to execute the program stored in the memory to implement the steps of the communication power status monitoring method based on 5G communication as mentioned in the first aspect.

[0015] The present invention has the following beneficial effects: first, the electric power information of the communication power input at the network node in the communication network, the data volume of the data source of the network node and the total amount of data processed by the network node are obtained; then, the fluctuation importance of the data of the data source is determined according to the data volume of the data source of the network node, the total amount of data processed and the electric power information; secondly, multiple data sequences under the total amount of data processed are fitted to obtain multiple data fitting sequences; and the predicted power threshold of the network node is determined according to the fitting validity of each of the data fitting sequences, the fluctuation importance of each of the data sources in each of the data fitting sequences and the predicted amount of data of each of the data sources; finally, based on the predicted power threshold and the actual electric power information provided by the communication power supply to the network node, the state of the communication power supply is monitored.

[0016] In this way, the embodiment of the present invention can analyze data from different data sources, and predict the predicted power threshold of the network node based on the data from different data sources. The predicted power threshold is determined based on the actual operating status of the communication power supply and the actual data processing volume of the network node. It can timely discover potential faults of the communication power supply, and improve the accuracy, reliability and timeliness of status monitoring of the communication power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a communication power supply status monitoring method based on 5G communication provided by an embodiment of the present invention;

[0019] Figure 2 A scatter diagram of the total amount of data processing and electric power information of a network node provided by an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of the structure of a communication power supply status monitoring system based on 5G communication is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the communication power supply status monitoring method and system based on 5G communication proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0022] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0023] The following is a detailed description of a method and system for monitoring the status of a communication power supply based on 5G communication provided by the present invention in conjunction with the accompanying drawings.

[0024] Embodiment 1:

[0025] See also Figure 1 , which shows a flow chart of a communication power supply status monitoring method based on 5G communication provided by an embodiment of the present invention, including:

[0026] S101, obtaining power information of a communication power supply input at a network node in a communication network, the amount of data from a data source of the network node, and the total amount of data processed by the network node.

[0027] Specifically, the embodiment of the present invention obtains the current information and voltage information of the input power supply of each network node by installing the voltage detection device and the current detection device at the power input position of each network node in the network topology diagram, and simultaneously obtains the data volume and the total amount of data processing in the current network node.

[0028] The power information of the communication power input at the network node may be the product of voltage information and current information, and is specifically calculated using the formula P=I*V, where P represents the power information of the communication power input at the network node, I represents current information, and V represents voltage information.

[0029] S102, determining the importance of fluctuation of data at the data source according to the data volume, total data processing volume and electric power information of the data source of the network node.

[0030] Specifically, when monitoring the status of the communication power supply of each network node, a fixed threshold of electric power is directly set. When the acquired electric power exceeds the fixed threshold, the corresponding power supply status is abnormal. The power threshold can be set by setting a relatively high physical threshold. The equipment will not be damaged under the current fixed threshold. At the same time, it is necessary to set a soft threshold that can be related to the information processing of the network node under the physical threshold. The acquired soft threshold can be adjusted dynamically. When acquiring the threshold, it is necessary to analyze the information processing situation in the current network node. The sources of data that need to be processed in each network node are inconsistent. The types of data sources include but are not limited to data producers, data consumers, data relayers, etc. The energy consumption corresponding to different data sources is different. Each network node can have the above three data sources at the same time. When analyzing the corresponding data generation at different time points, the relationship between the composition ratios can be predicted, rather than simply predicting through the overall data. At the same time, the setting of the electric power threshold can be adjusted according to the data of different components.

[0031] Furthermore, according to the logic of the above-mentioned embodiment of the present invention, when performing network data processing, it is necessary to consider the transmission status of the data obtained from each network node. For example, when performing data processing, network node A needs to obtain certain data from network node C. When performing data transmission, network node A and network node C cannot directly transmit data, so network node B must be used as a relay for data transmission. The corresponding processing status of the obtained data is equivalent to one data going through multiple network nodes, and the corresponding data transmission needs to be considered in subsequent data prediction.

[0032] Further, as an optional embodiment of the present invention, determining the fluctuation importance of data from a data source according to the data volume, total data processing volume and electric power information of the data source of a network node includes: determining a proportion parameter of the data source of the network node according to the data volume and total data processing volume of the data source; determining the electric power fluctuation interval corresponding to a proportion combination composed of the proportion parameters of the data source in the total data processing volume; determining the clustering of the distribution of data points in the proportion combination according to the first mean value and standard deviation of the electric power information in the electric power fluctuation interval; determining the difference in the change of the proportion parameters of any two data sources according to the change of the proportion parameters of any two data sources; determining the fluctuation importance of data from the data source according to the difference in the change of the proportion parameters of any two data sources, the difference in the clustering in the electric power fluctuation interval of any two data sources, the distance difference between the electric power fluctuation intervals of any two data sources and the number of data in the current data source that are simultaneously in the electric power fluctuation intervals of any two data sources.

[0033] Specifically, for each network node in the obtained network topology diagram, the corresponding network data is obtained, and the original data can be divided into three types of data sources according to the data source, and the data proportion of different data sources of each network node is calculated. Among them, as an optional embodiment of the present invention, determining the proportion parameter of the data source of the network node according to the data volume and the total amount of data processing of the data source includes: determining a first ratio between the data volume of the data source and the total amount of data processing as the proportion parameter of the data source of the network node.

[0034] The embodiment of the present invention specifically uses the following formula to calculate the proportion parameter of the data source of the network node:

[0035] ,

[0036] In the above formula, Indicates the first The network node The proportion parameter of each data source. Indicates the first The amount of data from the first data source in a network node. Indicates the first The total amount of data processed by each network node.

[0037] Furthermore, the same operation is performed on data from different sources according to the above-mentioned acquisition operation to obtain the proportion of different data sources in a network node, which is equivalent to dividing the data obtained at each time point into a multi-dimensional sequence: .in, Indicates the first The network node The proportion parameter of each data source. Indicates the first The network node The proportion parameter of each data source. Indicates the first The network node The proportion parameter of each data source. V and I represent the voltage information and current information obtained at the current time point. The power information obtained can be calculated through the voltage information and current information. That is, the power information P = I*V.

[0038] Furthermore, according to the operation of the above embodiment of the present invention, the proportion parameters of data from different data sources of network nodes can be obtained, the historical data of all network nodes obtained can be analyzed, and the data in the network nodes can be filtered to obtain the proportion parameters of different data sources with the same data. The filtered data is constructed into a two-dimensional space through the total amount of data processing of each network node and the power information of the network node. Among them, the horizontal axis is the total amount of data processing obtained, and the vertical axis is the power information of the network node. For example, Figure 2 As shown, Figure 2 A scatter diagram of the total amount of data processed and the electric power information of a network node provided for an embodiment of the present invention. According to the data points in the coordinate system constructed above in the embodiment of the present invention, curve fitting is performed. Since there is one horizontal coordinate corresponding to multiple vertical coordinates, the fitting data is obtained by the least squares method, and the mean square error MSE of the fitting curve is obtained at the same time. The sum of squares of the residuals is calculated and divided by the number of data points. The smaller the value, the better the fitting effect. Further, the historical data obtained from other data sources is analyzed, and the curve is constructed in the manner of the above embodiment of the present invention.

[0039] Furthermore, the influence of different proportion parameters on the total amount of data processing obtained, and the power fluctuation range of the proportion combination of the proportion parameters of each data source obtained.

[0040] Further, as an optional embodiment of the present invention, determining the clustering of the distribution of data points in the proportion combination based on the first mean value and standard deviation of the electric power information in the power fluctuation range includes: determining the second ratio between the first mean value and the standard deviation as the clustering of the distribution of data points in the proportion combination.

[0041] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the aggregation of data point distribution in the proportion combination:

[0042] ,

[0043] In the above formula, Indicates the first The clustering of the distribution of data points in the proportion combination. Indicates the first The first average value of the electric power information in the current electric power fluctuation range in the proportion combination. Indicates the standard deviation of the acquired electric power information in the electric power fluctuation interval.

[0044] Further, the embodiment of the present invention performs a quantitative analysis on one of the data, and calculates the influence of the change of the data proportion between the other two data sources on the electric power information. Wherein, as an optional embodiment of the present invention, according to the change difference of the proportion parameters of any two data sources, the difference of the aggregation in the power fluctuation interval of any two data sources, the distance difference between the power fluctuation interval of any two data sources, and the number of data in the current data source that are simultaneously in the power fluctuation interval of any two data sources, determining the fluctuation importance of the data of the data source includes: performing inverse proportional normalization processing on the number in the power fluctuation interval of any two data sources to obtain a normalized value; calculating the difference of the aggregation in the power fluctuation interval of any two data sources, the distance difference and the first product between the normalized value; determining the fifth ratio between the first product and the change difference of the proportion parameters of any two data sources as the fluctuation importance of the data of the data source.

[0045] Specifically, the embodiment of the present invention is When the proportion of the first data source remains unchanged, the importance of fluctuation of the data from the first data source is calculated. In this embodiment of the present invention, the importance of fluctuation of the data from the first data source is calculated using the following formula:

[0046] ,

[0047] ,

[0048] In the above formula, Indicates the first The importance of fluctuations in data from a data source. Indicates the difference in the proportion parameters of any two data sources obtained. Indicates the obtained first The changes in the proportion parameters of the data sources. Indicates the obtained first The changes in the proportion parameters of the data sources. It indicates the difference in the aggregation of power fluctuation ranges obtained from any two data sources. It represents the distance difference between the power fluctuation ranges of any two data sources. Its minimum value is 1, which indicates a complete inclusion relationship. It indicates the number of acquired data in two intervals at the same time. The number of data in the current data source is simultaneously in the power fluctuation interval of any two data sources. The more the number, the smaller the change in power usage, and the less important the fluctuation is to the calculation. (-) indicates the inverse normalization function, which is used to Perform normalization.

[0049] Among them, by calculating the changes in the corresponding electric power information when the data proportion parameters of different data sources change, the greater the changes in the two situations, the more important the data from the current data source is.

[0050] S103, fitting multiple data sequences under the total amount of data processing to obtain multiple data fitting sequences.

[0051] Specifically, the embodiment of the present invention performs quantitative analysis on all the data of the acquired network nodes, and performs the calculations in the above embodiment of the present invention on each data. , for different data sequences Perform data fitting to obtain multiple data fitting sequences.

[0052] S104, determining a predicted power threshold of a network node according to the fitting validity of each data fitting sequence, the importance of fluctuation of each data source in each data fitting sequence, and the predicted data volume of each data source.

[0053] Specifically, as an optional embodiment of the present invention, determining the predicted power threshold of a network node based on the fitting validity of each data fitting sequence, the fluctuation importance of each data source in each data fitting sequence, and the predicted data volume of each data source includes: determining the weight of each data source under the total data processing volume for subsequent electric power information based on the fitting validity of each data fitting sequence and the fluctuation importance of each data source in each data fitting sequence; determining the total predicted data processing volume in the network node by using the predicted data volume of each data source, the number of times each data source appears in the historical data, and the weight corresponding to each data source; screening target historical data with the same predicted data volume of each data source and the same predicted data processing volume from the historical data of the network node; determining the predicted power threshold of the network node based on the fitting validity of each data sequence, the electric power information of the target historical data, and the number of target historical data.

[0054] Specifically, as an optional embodiment of the present invention, according to the fitting validity of each data fitting sequence and the fluctuation importance of each data source in each data fitting sequence, determining the weight of each data source under the total data processing amount to the subsequent electric power information includes: superimposing the fitting validity of each data fitting sequence to obtain a first superimposed value, and calculating the second product between the first superimposed value and the fluctuation importance of the first data source in the data fitting sequence; calculating the third product between the first superimposed value and the fluctuation importance of each data source in each data fitting sequence, and superimposing each third product to obtain a second superimposed value; determining the third ratio between the second product and the second superimposed value as the weight of the data source to the subsequent electric power information.

[0055] The embodiment of the present invention specifically uses the following formula to calculate the weight of the data source to the subsequent electric power information:

[0056] ,

[0057] In the above formula, Indicates the total amount of data processed The next The weight of each data source on subsequent electricity usage. Indicates the number of data fitting sequences obtained under the total amount of data processing F. represents the mean squared error of the series fitted to the data. (-) indicates the inverse normalization function, which is used to Perform inverse proportional normalization. Indicates the first The fitting effectiveness of the data fitting series. Indicates obtaining the The first The importance of fluctuations in the data sources. S represents the number of data sources obtained. Indicates obtaining the The first The importance of fluctuations in each data source. Accumulate the fluctuations of data from all different sources.

[0058] Furthermore, the weight calculation is determined by the current data source for the final power information, because the essence of power information is the load of the equipment, that is, the processing of the overall data. The greater the impact of the data source on its final power information during processing, the greater the corresponding weight obtained during subsequent prediction calculations.

[0059] Specifically, the embodiment of the present invention obtains the above-mentioned data proportions obtained under different network nodes and the influence of the power information usage between the proportion parameters of different data sources. When performing subsequent power monitoring, it is necessary to predict the total amount of data processing obtained based on the previous data from different sources. According to the predicted total amount of data processing, the fluctuation range of the status of the communication power supply can be obtained, and according to the obtained fluctuation range of the status of the communication power supply, the status of the communication power supply can be monitored.

[0060] Furthermore, the embodiment of the present invention predicts the data volume of each data source in the network node by using the historical data of different data sources obtained for each network node through the ARIMA algorithm. The embodiment of the present invention performs the same calculation on each network node to predict the data volume of each data source in the network node. When obtaining the total amount of data processing in each network node, the embodiment of the present invention needs to consider the amount of data generated by itself that may need to be processed and the amount of external data transmission.

[0061] Further, as an optional embodiment of the present invention, the predicted data volume of each data source, the number of times each data source appears in historical data and the weight corresponding to each data source are used to determine the predicted total data processing amount in the network node, including: superimposing the weights corresponding to each data source to obtain the weights of the predicted values ​​of each data source; calculating the fourth product between the predicted data volume of each data source and the weight, and superimposing each fourth product to obtain the predicted total data processing amount in the network node.

[0062] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the weight of the predicted value of each data source:

[0063] ,

[0064] In the above formula, Indicates the first The weight of the predicted value of each data source. Indicates the first The weight of the data volume of the xth data source corresponding to the total amount of data. Indicates the first prediction obtained The number of times the data from a data source exists in historical data.

[0065] Furthermore, the embodiment of the present invention specifically uses the following formula to calculate the total amount of predicted data processing in the network node:

[0066] ,

[0067] In the above formula, Indicates the first The total amount of predicted data processing in the network nodes. Indicates the first The weight of the predicted value of each data source. Indicates the first prediction obtained The amount of data from each data source. Indicates the number of data sources obtained.

[0068] Furthermore, an embodiment of the present invention screens and matches historical data based on the acquired total predicted data processing volume and the data volume of the predicted data source, and obtains the data volume of each data source with the same prediction and the same total predicted data processing volume from the historical data as a reference for subsequent threshold calculation, or similar historical data. In an embodiment of the present invention, the normalized result of calculating the difference between each value is set to be similar if it is less than 0.3.

[0069] Further, as an optional embodiment of the present invention, determining the predicted power threshold of the network node based on the fitting validity of each data sequence, the electric power information of the target historical data and the number of target historical data includes: calculating the fifth product between the fitting validity of each data sequence and the electric power information of the target historical data; superimposing each fifth product to obtain a third superimposed value; and determining a fourth ratio between the third superimposed value and the number of target historical data as the predicted power threshold of the network node.

[0070] Specifically, the embodiment of the present invention uses the following formula to calculate the predicted power threshold of the network node:

[0071] ,

[0072] In the above formula, Indicates the first The predicted power threshold of each network node. The number of target historical data obtained after filtering by the above conditions, Indicates the first The fitting effectiveness of the data fitting series. Indicates the first The first position The electric power information of each target's historical data. represents the mean squared error of the series fitted to the data. (-) indicates the inverse normalization function, which is used to Perform inverse proportional normalization.

[0073] S105: Monitor the status of the communication power supply based on the predicted power threshold and the actual power information provided by the communication power supply to the network node.

[0074] Specifically, the embodiment of the present invention calculates the difference between the actual power information and the predicted power threshold based on the predicted power threshold of each network node, and normalizes the difference to obtain a normalized difference. When the normalized difference is in (0, 0.3), it is considered to be in a normal fluctuation range. When the normalized difference exceeds 0.7, it is considered an abnormal situation that needs to be handled.

[0075] The embodiment of the present invention can analyze data from different data sources, and predict the predicted power threshold of the network node based on the data from different data sources. The predicted power threshold is determined based on the actual operating status of the communication power supply and the actual data processing volume of the network node. It can timely discover potential faults of the communication power supply, and improve the accuracy, reliability and timeliness of status monitoring of the communication power supply.

[0076] Embodiment 2:

[0077] Corresponding to the communication power supply status monitoring method based on 5G communication provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a communication power supply status monitoring system based on 5G communication, and the communication power supply status monitoring system based on 5G communication is used to execute the above communication power supply status monitoring method based on 5G communication, Figure 3 A schematic diagram of the structure of a communication power supply status monitoring system based on 5G communication is provided as another embodiment of the present invention, such as Figure 3 The communication power supply status monitoring system based on 5G communication may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and memory 302, the memory 302 is used to store computer programs that can be run on the processor 301, and the processor 301 is used to execute the program stored in the memory 302 to achieve the above Figure 1 The various steps in the method embodiment. Among them, the memory 302 can be a temporary storage or a persistent storage. The application stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the communication power supply status monitoring system based on 5G communication.

[0078] Furthermore, the processor 301 may be configured to communicate with the memory 302, and execute a series of computer executable instructions in the memory 302 on the communication power supply status monitoring system based on 5G communication. The communication power supply status monitoring system based on 5G communication may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input and output interfaces 305, and one or more keyboards 306.

[0079] Specifically in this embodiment, the communication power supply status monitoring system based on 5G communication includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to achieve the above Figure 1 The various steps in the method embodiment are similar to those in the method embodiment, and have the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described in detail here.

[0080] It should be noted that the communication power supply status monitoring system based on 5G communication provided in an embodiment of the present invention and the communication power supply status monitoring method based on 5G communication provided in an embodiment of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned communication power supply status monitoring method based on 5G communication, and has the same or similar beneficial effects, and the repetitions will not be repeated.

[0081] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A communication power supply status monitoring method based on 5G communication, characterized in that: The communication power supply status monitoring method based on 5G communication includes: Acquire power information of a communication power supply input at a network node in the communication network, the amount of data from a data source of the network node, and the total amount of data processed by the network node; Determine the importance of fluctuation of the data of the data source according to the amount of data of the data source of the network node, the total amount of data processing and the electric power information; Fitting multiple data sequences under the total amount of data processing to obtain multiple data fitting sequences; Determining a predicted power threshold of the network node according to the fitting validity of each of the data fitting sequences, the importance of fluctuations of each of the data sources in each of the data fitting sequences, and the predicted data volume of each of the data sources; Based on the predicted power threshold and actual electric power information provided by the communication power supply to the network node, monitoring the state of the communication power supply; Determining the predicted power threshold of the network node according to the fitting validity of each of the data fitting sequences, the fluctuation importance of each of the data sources in each of the data fitting sequences, and the predicted data volume of each of the data sources includes: Determining the weight of each of the data sources under the total amount of data processing for subsequent electric power information according to the fitting validity of each of the data fitting sequences and the importance of fluctuations of each of the data sources in each of the data fitting sequences; Determine the total amount of predicted data processing in the network node by using the predicted data volume of each of the data sources, the number of times each of the data sources appears in the historical data, and the weight corresponding to each of the data sources; Filtering target historical data having the same predicted data volume of each data source and the same predicted data processing total volume from the historical data of the network node; Determining the predicted power threshold of the network node according to the fitting validity of each of the data sequences, the electric power information of the target historical data and the amount of the target historical data includes: Calculating a fifth product between the fitting effectiveness of each of the data sequences and the electric power information of the target historical data; The fifth products are superimposed to obtain a third superposition value; and a fourth ratio between the third superposition value and the amount of the target historical data is determined as a predicted power threshold of the network node.

2. The method for monitoring the communication power supply status based on 5G communication according to claim 1, characterized in that: The determining the importance of fluctuation of the data of the data source according to the data volume of the data source of the network node, the total amount of data processing and the electric power information comprises: Determine a proportion parameter of the data source of the network node according to the data volume of the data source and the total amount of data processing; Determine the power fluctuation range corresponding to the proportion combination composed of the proportion parameters of the data sources in the total data processing amount; Determining the aggregation of data point distribution in the proportion combination according to a first average value and a standard deviation of the electric power information in the electric power fluctuation interval; Determine the difference in the change of the proportion parameters of any two data sources according to the change of the proportion parameters of any two data sources; The fluctuation importance of the data from the data sources is determined based on the difference in changes in the proportion parameters of any two data sources, the difference in aggregation in the power fluctuation range of any two data sources, the difference in distance between the power fluctuation ranges of any two data sources, and the number of data in the current data source that are simultaneously in the power fluctuation range of any two data sources.

3. The communication power supply status monitoring method based on 5G communication according to claim 2 is characterized in that: The determining of the proportion parameter of the data source of the network node according to the data volume of the data source and the total amount of data processing includes: A first ratio between the amount of data from the data source and the total amount of data processing is determined as a proportion parameter of the data source of the network node.

4. The method for monitoring the communication power supply status based on 5G communication according to claim 2, characterized in that: Determining the aggregation of data point distribution in the proportion combination according to the first mean value and standard deviation of the electric power information in the electric power fluctuation interval includes: Determine a second ratio between the first mean and the standard deviation as a clustering condition of the distribution of the data points in the proportion combination.

5. The method for monitoring the communication power supply status based on 5G communication according to claim 2, characterized in that: Determining the importance of fluctuation of data from the data source according to the difference in the change of the proportion parameters of the two data sources, the difference in the aggregation in the power fluctuation interval of the two data sources, the distance difference between the power fluctuation intervals of the two data sources, and the number of data in the current data source that are simultaneously in the power fluctuation intervals of the two data sources includes: Performing inverse proportional normalization processing on the quantities in the power fluctuation range of the arbitrary two data sources to obtain a normalized value; Calculating a first product between the difference in aggregation conditions in the power fluctuation interval of the arbitrary two data sources, the distance difference, and the normalized value; A fifth ratio between the first product and the difference in changes in the proportion parameters of the arbitrary two data sources is determined as the importance of fluctuations in the data of the data sources.

6. The method for monitoring the communication power supply status based on 5G communication according to claim 1, characterized in that: Determining the weight of each data source under the total amount of data processing for subsequent electric power information according to the fitting validity of each data fitting sequence and the fluctuation importance of each data source in each data fitting sequence includes: Superimposing the fitting validity of each of the data fitting sequences to obtain a first superimposed value, and calculating a second product between the first superimposed value and the fluctuation importance of the first data source in the data fitting sequence; Calculating a third product between the first superposition value and the fluctuation importance of each of the data sources in each of the data fitting sequences, and superimposing each of the third products to obtain a second superposition value; A third ratio between the second product and the second superposition value is determined as a weight of the data source for subsequent electric power information.

7. The method for monitoring the communication power supply status based on 5G communication according to claim 1, characterized in that: Determining the total amount of predicted data processing in the network node by using the predicted data amount of each data source, the number of times each data source appears in the historical data, and the weight corresponding to each data source includes: The weights corresponding to the data sources are superimposed to obtain the weights of the predicted values ​​of the data sources; The fourth product between the predicted data volume of each of the data sources and the weight is calculated, and each of the fourth products is superimposed to obtain the total predicted data processing volume in the network node.

8. A communication power supply status monitoring system based on 5G communication, characterized in that: The communication power status monitoring system based on 5G communication includes: a processor and a memory; wherein the memory is used to store computer programs that can be run on the processor; the processor is used to execute the program stored in the memory to implement the steps of the communication power status monitoring method based on 5G communication as described in any one of claims 1-7.

Images