Communication signal monitoring method and system for repeater

Abstract

The present invention relates to the technical field of communication signal monitoring, and discloses a communication signal monitoring method and system for a repeater, comprising the following steps: Step 1: respectively obtain environmental parameters and communication quality parameters of historical data repeaters, and integrate the data into parameter data groups according to extreme weather types, and obtain parameter data groups corresponding to different extreme weather types; Step 2: based on the parameter data groups corresponding to different extreme weather types, respectively process the data in each parameter data group to obtain regularized parameter data groups for different extreme weather types; wherein the process of processing the data in each parameter data group includes removing abnormal values ​​therein. In the process of data cleaning, the present invention reasonably considers the rationality of parameter changes under extreme weather conditions, effectively solves the problem of removing the actually required valid data as abnormal values, thereby ensuring the effectiveness of the subsequent steps in performing correlation calculations.

Description

Technical Field

[0001] The present invention relates to the technical field of communication signal monitoring, and in particular to a communication signal monitoring method and system for a repeater. Background Art

[0002] A repeater (RP repeater) is a connection device working at the physical layer. It is suitable for interconnecting two completely identical networks. Its main function is to extend the distance of network transmission by retransmitting or forwarding data signals. A repeater is a network device that regenerates and restores signals: a physical layer device in the OSI model.

[0003] Under extreme weather conditions, such as high temperature, heavy rain, heavy snow, lightning or strong wind, the communication link between repeaters may be seriously affected. Due to signal attenuation, equipment damage or link interruption, the repeater may not be able to receive the upstream signal or transmit the signal normally to the downstream. However, the current repeater communication system often lacks an effective monitoring mechanism for detection and analysis, which leads to delayed fault discovery, affects the timeliness and efficiency of network maintenance, and makes it difficult to cope with the impact of extreme weather on repeater communication signals. Summary of the invention

[0004] The object of the present invention is to provide a communication signal monitoring method and system for a repeater to solve at least one of the above-mentioned prior art problems.

[0005] In a first aspect, the present invention provides a communication signal monitoring method of a repeater, comprising the following steps:

[0006] Step 1: Obtain the environmental parameters and communication quality parameters of the historical data repeater respectively, and integrate the data into parameter data groups according to the extreme weather types, and obtain parameter data groups corresponding to different extreme weather types;

[0007] Step 2: Based on the parameter data groups corresponding to different extreme weather types, the data in each parameter data group is processed respectively to obtain regularized parameter data groups of different extreme weather types;

[0008] The process of processing the data in each parameter data group includes removing abnormal values ​​therein, specifically:

[0009] Based on the data of any parameter data group, the data is analyzed, an outlier judgment value is calculated, and outliers of the parameter data group are removed based on the outlier judgment value to retain valid data;

[0010] Step 3: Based on the regularized parameter data groups of different extreme weather types, a method combining correlation coefficient analysis and decision tree algorithm is used to analyze the impact of different extreme weather types on the repeater communication signal and screen out key parameter combinations;

[0011] Step 4: Optimize and adjust the repeater communication signal quality based on the key parameter combinations of different extreme weather conditions.

[0012] In a second aspect, the present invention provides a communication signal monitoring method system for a repeater, the system comprising:

[0013] Data acquisition module: collects the environmental parameters and communication quality parameters of the repeater respectively, and integrates the data into parameter data groups according to the extreme weather types, and obtains parameter data groups corresponding to different extreme weather types;

[0014] Data processing module: based on the parameter data groups corresponding to different extreme weather types, the data in each parameter data group is processed respectively to obtain regularized parameter data groups of different extreme weather types;

[0015] The process of processing the data in each parameter data group includes removing abnormal values ​​therein, specifically:

[0016] Based on the data of any parameter data group, the data is analyzed, an outlier judgment value is calculated, and outliers of the parameter data group are removed based on the outlier judgment value to retain valid data;

[0017] Key parameter combination screening module: Based on the parameter data groups regularized by different extreme weather types, the module uses a combination of correlation coefficient analysis and decision tree algorithm to analyze the impact of different extreme weather types on the repeater communication signal and screen out key parameter combinations;

[0018] Optimization and adjustment module: optimizes and adjusts the repeater communication signal quality based on the key parameter combinations of different extreme weather conditions.

[0019] Beneficial effects of the present invention:

[0020] 1. In the process of data cleaning, the present invention reasonably considers the rationality of parameter changes under extreme weather conditions, effectively reducing the problem of removing the actually required valid data as outliers, thereby ensuring the effectiveness of the subsequent steps in performing correlation calculations;

[0021] 2. The present invention adopts a combination of statistical analysis and machine learning algorithms. First, the strongly correlated parameter combinations are screened out by calculating the correlation coefficient, and then the key parameter combinations are further screened based on the machine learning algorithm. It can deeply explore the intrinsic relationship between the parameters and more accurately obtain the parameter combination that has the greatest impact on the repeater communication signal compared to a single analysis method.

[0022] 3. According to the relationship between environmental parameters and communication quality parameters, the present invention predicts changes in communication quality in advance, discovers potential problems in a timely manner and makes targeted adjustments, effectively ensuring the stability and reliability of the repeater communication signal under different extreme weather conditions. By scientifically calculating the changing adjustment measures, the ability to cope with complex environmental changes is improved, the risk of communication interruption due to signal quality problems is reduced, and the operating efficiency and quality of the entire communication network are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a communication signal monitoring method of a repeater of the present invention;

[0025] Figure 2 It is a structural schematic diagram of a communication signal monitoring system of a repeater of the present invention;

[0026] Figure 3 It is a structural schematic diagram of a communication signal monitoring device of a repeater of the present invention.

[0027] In the figure: 3, computer device; 301, processor; 302, memory; 303, computer program; DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] Embodiment 1

[0030] Figure 1A flow chart of a method for monitoring the communication signal of a repeater provided in the first embodiment of the present invention. The embodiment of the present invention can be applied to monitoring the communication signal of a repeater under extreme weather conditions. The method for monitoring the communication signal of a repeater can be executed by a communication signal monitoring system of a repeater. The communication signal monitoring system of a repeater can be implemented by software and / or hardware. The communication signal monitoring system of a repeater can be configured in a communication signal monitoring device of a repeater. Optionally, a communication signal monitoring device of a repeater can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0031] like Figure 1 As shown, a communication signal monitoring method of a repeater provided by an embodiment of the present invention specifically includes the following steps:

[0032] Step 1: Obtain the environmental parameters and communication quality parameters of the historical data repeater respectively, and integrate the data into parameter data groups according to the extreme weather types;

[0033] Among them, environmental parameters include but are not limited to: temperature, humidity, and air pressure;

[0034] Communication quality parameters include but are not limited to: RSSI (received signal strength), SNR (signal to noise ratio), BER (bit error rate);

[0035] In some embodiments, each repeater to be monitored is numbered in order from 1 to N, and monitoring equipment is installed for each repeater, wherein the monitoring equipment includes but is not limited to: an environmental parameter sensor, a communication quality monitoring device;

[0036] The data collection frequency is set to monitor the environmental parameters and communication quality parameters of the repeater, wherein the data collection frequency is set by a person skilled in the art according to the application scenario requirements of the repeater. For example, in a scenario where weather conditions change rapidly, a higher sampling frequency needs to be set to capture instantaneous changes;

[0037] Integrate the environmental parameters and communication quality parameters of the same repeater into corresponding parameter data groups, such as a temperature parameter data group, a humidity parameter data group, an air pressure parameter data group, an RSSI parameter data group, an SNR parameter data group, and a BER parameter data group, in chronological order;

[0038] The occurrence time of the extreme weather event is marked in each parameter data group, wherein the occurrence time of the extreme weather event is obtained through weather forecast data or information from official weather stations;

[0039] Set up an extreme weather window, which includes a period of time before an extreme weather event occurs (in order to observe precursor changes) and a period of time after the event (in order to assess recovery and long-term impacts). The window is set by implementers in this field based on actual conditions and experience;

[0040] Extract the parameter data corresponding to the extreme weather window period in each parameter data group, integrate the extracted parameter data according to the type of extreme weather, and obtain parameter data groups corresponding to different extreme weather types;

[0041] The above process can more comprehensively and accurately capture the relevant data changes of repeaters under extreme weather conditions by comprehensively acquiring multiple environmental parameters and communication quality parameters in historical data and integrating them according to extreme weather types. This process provides a high-quality data basis for subsequent analysis and can more completely reflect the actual situation compared to some processes that only collect single or partial parameters and do not consider changes before and after extreme weather conditions.

[0042] Step 2: Based on the parameter data groups corresponding to different extreme weather types, the data in each parameter data group is processed respectively to obtain regularized parameter data groups of different extreme weather types;

[0043] In some embodiments, the integrated parameter data groups corresponding to different extreme weather types are subjected to data cleaning and normalization processing;

[0044] The data cleaning operation includes but is not limited to: removing outliers and duplicate data; the normalization method includes but is not limited to: vector normalization and linear normalization;

[0045] In the process of removing outliers, the data actually needed may be treated as outliers and removed, thereby affecting the effectiveness of the subsequent correlation calculation, and further affecting the screening results of the strongly correlated parameter combination. For example, a sharp change in temperature that exceeds the normal physical law in a short period of time can be considered as abnormal data. However, in the extreme weather described in this embodiment, the change rate of parameters such as temperature is within a reasonably set fluctuation rate range, which should be regarded as valid data;

[0046] In this embodiment, the process of removing outliers is specifically as follows:

[0047] Based on any parameter data set, calculate the mean value CJ and standard deviation corresponding to the data in the data set;

[0048] For any data in a parameter data group, calculate the deviating judgment value QY. The specific formula is: ,in, and is the i-th data and i-1-th data in the parameter data, is the standard value of adjacent data change, a and b are preset proportional coefficients, a is 0.56, b is 0.44, and the standard value of adjacent data change is , obtained by taking the average value of the maximum and minimum values ​​of the variation range of adjacent data, the variation range of adjacent data is determined by those skilled in the art based on the characteristics and experience of the corresponding parameters;

[0049] A de-differentiation judgment threshold is set, and for each parameter data, data corresponding to a de-differentiation judgment value less than the de-differentiation judgment threshold is retained, and the retained data is marked as a regularized parameter data group;

[0050] The threshold for judging whether to remove anomalies is summarized and set by those skilled in the art based on the product of the standard deviation of the corresponding parameter and the coefficient, as well as the range of variation of adjacent data. The coefficient can be 4 or 1, and the specific value is not limited and is set by those skilled in the art according to specific circumstances.

[0051] In the data cleaning process, this embodiment particularly considers the rationality of parameter changes under extreme weather conditions, effectively reducing the problem of removing the actually required valid data as outliers, thereby ensuring the effectiveness of the subsequent steps in performing correlation calculations;

[0052] The technical solution of this embodiment is: first, by comprehensively collecting multiple environmental parameters and communication quality parameters of the repeater, and integrating them according to extreme weather types, parameter data groups under different extreme weather conditions are formed. Then, these parameter data groups are cleaned and normalized to remove outliers and duplicate data, and the data scale is unified. In the process of removing outliers, the rationality of parameter changes under extreme weather conditions is reasonably considered to ensure the retention of valid data.

[0053] Embodiment 2

[0054] Based on the above embodiments, Figure 1 As shown, a communication signal monitoring method of a repeater provided by an embodiment of the present invention specifically includes the following steps:

[0055] Step 3: Based on the regularized parameter data groups of different extreme weather types, a method combining statistical analysis and machine learning algorithms is used to analyze the impact of different extreme weather types on the repeater communication signal and screen out key parameter combinations;

[0056] Based on any extreme weather, the correlation coefficient between each environmental parameter data and the communication quality parameter data is calculated respectively. The calculation formula of the correlation coefficient is: , where n is the number of data, and are the i-th observation values ​​of the two variables, and are the means of the two variables, and R is the Pearson correlation coefficient;

[0057] For example, take extreme weather such as heavy rain;

[0058] Extract the temperature data series from the parameter data group corresponding to the rainstorm extreme weather type and RSSI data sequence , where n is the number of data;

[0059] Extract humidity data series and SNR data sequence Other environmental parameters and communication quality parameter data sequences that need to be calculated for correlation;

[0060] Calculate the numerator of the correlation coefficient: Calculate the mean of the temperature data , calculate the mean of RSSI data , similarly calculate the mean of other parameter data;

[0061] Calculate the denominator of the correlation coefficient: Calculate the temperature , RSSI , and then multiply the two to get the denominator value of temperature and RSSI;

[0062] Among them, i represents the i-th data;

[0063] Similarly, calculate the denominator value of the combination of humidity and other parameters such as SNR;

[0064] Divide the numerator by the denominator to get the Pearson correlation coefficient between temperature and RSSI;

[0065] Similarly, the Pearson correlation coefficient between humidity and SNR and other Pearson correlation coefficients between other parameter pairs were obtained;

[0066] Set a correlation coefficient threshold, take the absolute value of the calculated correlation coefficient to obtain the absolute correlation coefficient, extract the parameter combination corresponding to the absolute correlation coefficient greater than the correlation coefficient threshold, and mark it as a strongly correlated parameter combination;

[0067] Obtain the corresponding strongly correlated parameter combination under each extreme weather condition;

[0068] Based on the combination of strongly correlated parameters, the key parameter combinations are screened in combination with machine learning algorithms, where the machine learning algorithms include but are not limited to: decision tree and random forest;

[0069] In a specific embodiment, based on any extreme weather, a decision tree is used to screen key parameter combinations in strongly correlated parameter combinations;

[0070] Among them, the key parameter combination is the environmental parameters and communication quality parameters that have a great impact on each other under the corresponding extreme weather conditions;

[0071] The specific process is as follows:

[0072] Obtain relevant data on strongly correlated parameter combinations that have been marked corresponding to extreme weather conditions;

[0073] For example, in extreme snowstorm weather, the determined strongly correlated parameter combinations may be temperature and RSSI, humidity and SNR. The historical monitoring data containing these parameters are extracted, and these data are the basis for the subsequent construction of the decision tree model.

[0074] Divide the extracted strongly correlated parameter combination data into a training set and a test set according to a certain ratio;

[0075] The ratio of the training set to the test set includes but is not limited to: 8:2, 7:3;

[0076] The decision tree algorithm selected, such as ID3, C4.5, CART (Classification and Regression Tree), etc., is selected by implementers in this field based on specific parameter characteristics;

[0077] For example, in the scenario of repeater communication signal monitoring, the communication quality parameter is a numerical variable (such as the specific value of RSSI), and the CART algorithm is used to build a decision tree model to meet the specific data characteristics and analysis requirements;

[0078] For the selected decision tree algorithm, determine the appropriate node division index;

[0079] For example, in the CART algorithm, the Gini Index is often used to measure the purity of nodes for classification problems, and the attribute that reduces the Gini Index the most (that is, a parameter in the strongly correlated parameter combination) is selected as the basis for node division; for regression problems, the mean square error (MSE) is often used to measure, and the attribute that can minimize the mean square error is selected for node division. By continuously selecting the optimal division attribute to construct the structure of the decision tree, the decision tree can well reflect the intrinsic relationship between the strongly correlated parameter combination and the communication quality parameter;

[0080] Using the training set data, based on the selected decision tree algorithm and node division indicators, starting from the root node, the nodes are continuously divided, the decision tree is gradually grown, and the decision tree model is constructed;

[0081] For example, if temperature, a strongly correlated parameter, is initially selected to divide the root node, the data set is divided into different subsets according to different temperature value ranges, and then other strongly correlated parameters are further selected on each subset for further division until certain stopping conditions are met, such as the tree depth reaches a preset maximum value, the number of samples in the node is too small (such as less than a certain set minimum number of samples), or the improvement of the index brought by continuing to divide the node is not obvious (such as the change in the Gini coefficient or mean square error is less than the set threshold), and finally a complete decision tree model is constructed;

[0082] Based on the constructed decision tree model, evaluate the importance of each strongly correlated parameter in the model;

[0083] In this embodiment, the importance of each strongly correlated parameter in the model is evaluated based on the reduction in the impurity of the node:

[0084] That is, the more a parameter reduces the impurity of a node during multiple node divisions, the higher its feature importance is.

[0085] Calculate the impurity reduction based on the Gini coefficient: For a data set with K categories, its Gini coefficient The calculation formula ,in, and k is the proportion of samples in the kth class;

[0086] Divide the dataset D into two subsets D1 and D2 according to the corresponding environmental parameter thresholds. The Gini coefficient of the divided dataset D is , the Gini coefficients of the subsets D1 and D2 after division are and ;

[0087] The node impurity reduction based on the environmental parameter division is for: , set the impurity reduction threshold. If the impurity reduction is greater than the impurity reduction threshold, it means that the pressure parameter has a significant effect on reducing impurity when dividing the node, and its feature importance is high. Otherwise, its feature importance is low.

[0088] Select the strongly correlated parameters with higher feature importance, and the parameter combination composed of these selected parameters is the selected key parameter combination;

[0089] Input the strongly correlated parameter combination data in the test set into the constructed decision tree model to obtain the prediction results of the communication quality parameters;

[0090] According to the communication quality parameters, select the corresponding evaluation indicators to measure the performance of the model;

[0091] Evaluation indicators include but are not limited to: mean square error (MSE), mean absolute error (MAE) indicators;

[0092] If the evaluation indicators of the model perform well, it means that the model is reliable, and the selected key parameter combination will be more credible, and can more accurately reflect the environmental parameters and communication quality parameters that have the greatest impact on each other under the corresponding extreme weather conditions;

[0093] On the contrary, if the model performance is poor, the key parameter combination is adjusted and re-screened to ensure that the final key parameter combination is effective;

[0094] The above process uses a combination of statistical analysis and machine learning algorithms. First, the strongly correlated parameter combinations are screened out by calculating the correlation coefficient, and then the key parameter combinations are further screened based on the machine learning algorithm. This can deeply explore the intrinsic relationship between the parameters and more accurately obtain the parameter combination that has the greatest impact on the repeater communication signal compared to a single analysis method.

[0095] The technical solution of this embodiment is as follows: first, the environmental parameters and communication quality parameters of the repeater are collected, integrated and preprocessed according to the extreme weather type, an extreme weather window is set and the corresponding parameter data is extracted, and then the strongly correlated parameter combinations are determined by calculating the correlation coefficients. Then, based on these combinations, a decision tree model is constructed. During the construction process, the mean square error is used as the node division indicator, and the decision tree is grown according to the training set data. The importance of the strongly correlated parameters is evaluated by the reduction in node impurity, and the key parameter combinations are screened out. Finally, the model performance is evaluated using test set data and indicators such as the mean square error, and the key parameter combinations are adjusted according to the results.

[0096] Embodiment 3

[0097] Based on the above embodiments, Figure 1 As shown, a communication signal monitoring method of a repeater provided by an embodiment of the present invention specifically includes the following steps:

[0098] Step 4: Optimize and adjust the repeater communication signal quality based on the key parameter combinations of different extreme weather conditions;

[0099] In some embodiments, based on any combination of key parameters under extreme weather conditions, a corresponding regularized environmental parameter data group and a communication quality parameter data group are obtained;

[0100] It should be noted that the environmental parameter data corresponds to the communication quality parameters. For example, if the key parameter combination is temperature and RSSI, then one temperature value corresponds to one RSSI value.

[0101] Randomly select two environmental parameters with different data to perform difference calculation to obtain the change value of the environmental parameters;

[0102] Based on any environmental parameter change value, the environmental parameter change value is calculated by the communication quality parameter value corresponding to the environmental parameter, and the corresponding communication quality parameter change value is calculated;

[0103] Calculate the ratio of the environmental parameter change value to the communication quality parameter change value to obtain the change ratio;

[0104] It should be noted that if the communication quality parameter change value is zero, no calculation is performed;

[0105] Calculate the standard deviation of all change ratios to evaluate the degree of dispersion of these change values ​​and set a standard deviation threshold, which is set by a person skilled in the art based on data summary;

[0106] If the standard deviation is less than or equal to the standard deviation threshold, it means that the change is relatively stable. The change ratios are summed and averaged to obtain the change mean, which is marked as the change coefficient.

[0107] Based on the coefficient of variation, obtain the actual value of the current environmental parameter and the actual value of the current signal quality parameter in real time;

[0108] Obtain the predicted value of the environmental parameter, perform difference calculation between the predicted value of the environmental parameter and the actual value of the current environmental parameter, and obtain the predicted change value of the environmental parameter;

[0109] The predicted values ​​of environmental parameters are obtained by technicians in this field from weather forecasts or meteorological stations;

[0110] The predicted change value of the environmental change parameter is processed by ratio with the change coefficient to obtain the predicted change value of the communication quality parameter, and the predicted change value of the communication quality parameter is calculated by summing the actual value of the current communication quality parameter to obtain the predicted value of the communication quality parameter;

[0111] Compare the predicted value of the communication quality parameter with the corresponding standard range of the communication quality parameter, if the predicted value of the communication quality parameter is within the corresponding standard range of the communication quality parameter, generate a normal signal, if the predicted value of the communication quality parameter is not within the corresponding standard range of the communication quality parameter, generate an abnormal signal;

[0112] Based on abnormal signals, communication quality parameters are adjusted in advance. The adjustment method is as follows:

[0113] If the predicted value of the communication quality parameter is lower than the minimum value of the standard range, the communication quality parameter value needs to be increased. The improvement measures include but are not limited to: increasing the transmission power of the repeater, optimizing the frequency of signal transmission, or adjusting the angle of the antenna to improve the communication quality;

[0114] If the predicted value of the communication quality parameter is higher than the maximum value of the standard range, the communication quality parameter value is reduced, and the reduction measures include but are not limited to: reducing the transmission power of the repeater, adjusting the signal transmission strategy, monitoring and optimizing the network topology;

[0115] If the standard deviation is greater than the standard deviation threshold, other methods are used to calculate the coefficient of variation, including but not limited to: machine learning algorithms, weighted average method;

[0116] The technical solution of this embodiment is: based on the key parameter combination of different extreme weather conditions, environmental parameters and communication quality parameter data are obtained and processed, the change ratio is calculated and its stability is evaluated, so as to determine the change coefficient, and the real-time environmental parameter prediction value and the change coefficient are used to predict the future communication quality parameters, and compare them with the standard range to generate corresponding signals. If the predicted value is abnormal, the communication quality parameters are adjusted in advance;

[0117] Therefore, based on the relationship between environmental parameters and communication quality parameters, changes in communication quality can be predicted in advance, potential problems can be discovered in a timely manner and targeted adjustments can be made, effectively ensuring the stability and reliability of the repeater communication signal under different extreme weather conditions. By scientifically calculating the adjustment measures of the coefficient of variation, the ability to cope with complex environmental changes is improved, the risk of communication interruption due to signal quality problems is reduced, and the operating efficiency and quality of the entire communication network are improved.

[0118] Embodiment 4

[0119] Based on the above embodiments, Figure 2 As shown, a communication signal monitoring system for a repeater provided by an embodiment of the present invention specifically includes:

[0120] Data acquisition module: collects the environmental parameters and communication quality parameters of the repeater respectively, and integrates the data into parameter data groups according to the extreme weather types, and obtains parameter data groups corresponding to different extreme weather types;

[0121] Data processing module: based on the parameter data groups corresponding to different extreme weather types, the data in each parameter data group is processed respectively to obtain regularized parameter data groups of different extreme weather types;

[0122] Key parameter combination screening module: Based on the parameter data groups regularized by different extreme weather types, the module uses a combination of correlation coefficient analysis and decision tree algorithm to analyze the impact of different extreme weather types on the repeater communication signal and screen out key parameter combinations;

[0123] Optimization and adjustment module: optimizes and adjusts the repeater communication signal quality based on the key parameter combinations of different extreme weather conditions.

[0124] Embodiment 5

[0125] like Figure 3 As shown, an embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a communication signal monitoring method for a repeater as described in any one of the above methods is implemented.

[0126] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that

[0127] Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0128] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0129] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit and an external storage device of the computer device 3. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0130] Embodiment 6

[0131] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the communication signal monitoring method of a repeater as described in any one of the above methods is implemented.

[0132] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0133] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0135] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal equipment and method can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0136] One point, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0139] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for monitoring communication signals of a repeater, characterized in that: The following steps are involved: Step 1: Obtain the environmental parameters and communication quality parameters of the historical data repeater respectively, and integrate the data into parameter data groups according to the extreme weather types, and obtain parameter data groups corresponding to different extreme weather types; The process of obtaining parameter data sets corresponding to different extreme weather types is as follows: installing monitoring equipment for each repeater; Set the data collection frequency to monitor the repeater's environmental parameters and communication quality parameters; In accordance with the time sequence, the environmental parameters and communication quality parameters of the same repeater are respectively integrated into corresponding parameter data groups; Mark the time of occurrence of extreme weather events in each parameter data set; Setting extreme weather windows; Extract the parameter data corresponding to the extreme weather window period in each parameter data group, integrate the extracted parameter data according to the type of extreme weather, and obtain parameter data groups corresponding to different extreme weather types; Step 2: Based on the parameter data groups corresponding to different extreme weather types, the data in each parameter data group is processed respectively to obtain regularized parameter data groups of different extreme weather types; The process of processing the data in each parameter data group includes: Based on the data of any parameter data group, the data is analyzed, an outlier judgment value is calculated, and outliers of the parameter data group are removed based on the outlier judgment value to retain valid data; Step 3: Based on the regularized parameter data groups of different extreme weather types, a method combining correlation coefficient analysis and decision tree algorithm is used to analyze the impact of different extreme weather types on the repeater communication signal and screen out key parameter combinations; The process of obtaining the key parameter combination is as follows: obtaining the strongly correlated parameter combination corresponding to each extreme weather condition; Based on the combination of strongly correlated parameters; obtain the relevant data of the strongly correlated parameter combination that has been marked corresponding to extreme weather conditions; Divide the extracted strongly correlated parameter combination data into a training set and a test set according to the proportion; Select a decision tree algorithm and determine the node division index; use the training set data to build a decision tree model based on the decision tree algorithm and node division index; based on the built decision tree model, evaluate the importance of each strongly correlated parameter in the model; select the strongly correlated parameters with high feature importance and mark them as key parameter combinations; Step 4: Optimize and adjust the repeater communication signal quality based on the key parameter combinations of different extreme weather conditions; Based on any combination of key parameters under extreme weather conditions, obtain the corresponding regularized environmental parameter data group and communication quality parameter data group; Calculate the coefficient of variation; Obtain the actual value of the current environmental parameter and the actual value of the current communication quality parameter in real time; obtain the predicted value of the environmental parameter, calculate the difference between the predicted value of the environmental parameter and the actual value of the current environmental parameter, and obtain the predicted change value of the environmental parameter; The predicted change value of the environmental change parameter is processed by ratio with the change coefficient to obtain the predicted change value of the communication quality parameter, and the predicted change value of the communication quality parameter is calculated by summing it with the actual value of the current communication quality parameter to obtain the predicted value of the communication quality parameter; If the predicted value of the communication quality parameter is not within the corresponding communication quality parameter standard range, an abnormal signal is generated; Based on abnormal signals, communication quality parameters are adjusted in advance.

2. The method for monitoring communication signals of a repeater according to claim 1, characterized in that: The process of obtaining the regularized parameter data set of different extreme weather types is as follows: Remove outliers from the integrated parameter data sets corresponding to different extreme weather types; Based on any parameter data group, obtain the de-differentiation judgment value; A de-differentiation judgment threshold is set. For each parameter data, the data whose de-differentiation judgment value is less than the de-differentiation judgment threshold is retained, and the retained data is marked as a regularized parameter data group.

3. The method for monitoring communication signals of a repeater according to claim 2, characterized in that: The process of obtaining the deviating judgment value is as follows: Based on any parameter data set, calculate the mean value CJ and standard deviation corresponding to the data in the data set; For any data in a parameter data group, calculate the deviating judgment value QY. The specific formula is: ,in, and is the i-th data and i-1-th data in the parameter data, is the standard value of the change of adjacent data, and a and b are the preset proportional coefficients.

4. The method for monitoring communication signals of a repeater according to claim 1, characterized in that: The process of evaluating the importance of each strongly correlated parameter in the model is: Measured based on the reduction in node impurity; Based on the Gini coefficient of the nodes divided by the environmental parameters, the impurity reduction is calculated, and the impurity reduction threshold is set. If the impurity reduction is greater than the impurity reduction threshold, the feature importance is high.

5. The communication signal monitoring method of a repeater according to claim 1, characterized in that: The process of obtaining the corresponding strongly correlated parameter combination under the extreme weather is as follows: Based on any extreme weather, the correlation coefficient between each environmental parameter data and the communication quality parameter data is calculated by the Pearson correlation coefficient; Set a correlation coefficient threshold, take the absolute value of the calculated correlation coefficient to obtain the absolute correlation coefficient, extract the parameter combination corresponding to the absolute correlation coefficient greater than the correlation coefficient threshold, and mark it as a strongly correlated parameter combination; Obtain the strongly correlated parameter combination corresponding to each extreme weather condition.

6. The method for monitoring communication signals of a repeater according to claim 1, characterized in that: The calculation process of the coefficient of variation is: Randomly select two environmental parameters with different data to perform difference calculation to obtain the change value of the environmental parameters; Obtaining a communication quality parameter value corresponding to the environmental parameter, and calculating a communication quality parameter change value corresponding to the environmental parameter change value; Calculate the ratio of the environmental parameter change value to the communication quality parameter change value to obtain the change ratio; Calculate the standard deviation of all change ratios and set the standard deviation threshold; If the standard deviation is less than or equal to the standard deviation threshold, the change ratios are summed and averaged to obtain the change mean, which is marked as the change coefficient.

7. A method and system for monitoring communication signals of a repeater, characterized in that: The system is used to execute the method described in any one of claims 1 to 6, and the system comprises: Data acquisition module: obtains environmental parameters and communication quality parameters of historical data repeaters respectively, and integrates the data into parameter data groups according to extreme weather types, and obtains parameter data groups corresponding to different extreme weather types; Data processing module: based on the parameter data groups corresponding to different extreme weather types, the data in each parameter data group is processed respectively to obtain regularized parameter data groups of different extreme weather types; The process of processing the data in each parameter data group includes removing abnormal values ​​therein, specifically: Based on the data of any parameter data group, the data is analyzed, an outlier judgment value is calculated, and outliers of the parameter data group are removed based on the outlier judgment value to retain valid data; Key parameter combination screening module: Based on the parameter data groups regularized by different extreme weather types, the module uses a combination of correlation coefficient analysis and decision tree algorithm to analyze the impact of different extreme weather types on the repeater communication signal and screen out key parameter combinations; Optimization and adjustment module: optimizes and adjusts the repeater communication signal quality based on the key parameter combinations of different extreme weather conditions.

Images