Base station abnormal power detection method and device and computer readable medium

Abstract

The application belongs to the technical field of communication, and particularly relates to a base station abnormal power detection method and device and a computer readable medium. The method comprises the following steps: obtaining original base station power data and preprocessing the original base station power data to obtain a to-be-audited sample; constructing a base station power calculation model based on an energy consumption factor in the to-be-audited sample, wherein the energy consumption factor is a power consumption factor affecting the base station power; obtaining a base station power calculation value through the base station power calculation model, and calculating a proportional value between the base station power calculation value and a base station power true value; and establishing a probability model according to the proportion of the base station power calculation value and the base station power true value to determine an abnormal power base station. Since the historical power of the base station is not required in the process, the influence of the inaccurate auditing result caused by the abnormal historical power of the base station is reduced, and the accuracy of the auditing result is improved.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and specifically relates to a method, device and computer-readable medium for detecting abnormal power levels in a base station. Background Technology

[0002] In the field of communication technology, in order to ensure the reliability of base stations, the power consumption of existing base stations is usually audited to understand the specific power consumption situation of the base stations.

[0003] Since the power consumption of base stations is affected by a variety of complex factors such as the equipment and environment of various base stations, the existing base station power consumption auditing methods generally rely on training models based on historical data and auditing base station power consumption through feature comparison. In this case, if there are anomalies in the training set, it will directly affect the accuracy of the audit results.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus and computer-readable medium for detecting abnormal power levels in base stations, which improves the accuracy of abnormal power level detection results to a certain extent.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0007] According to one aspect of the embodiments of this application, a method for detecting abnormal power levels in a base station is provided, the method comprising:

[0008] Obtain raw base station power data and preprocess it to obtain the sample to be audited;

[0009] Based on the energy consumption factors in the sample to be audited, a base station power consumption calculation model is constructed, wherein the energy consumption factors are power consumption factors that affect the power consumption of the base station.

[0010] The base station power consumption is calculated using the base station power consumption calculation model, and the ratio between the calculated base station power consumption and the actual base station power consumption is calculated.

[0011] A probability model is established based on the ratio of the base station's calculated power consumption to the actual power consumption of the base station to identify base stations with abnormal power consumption.

[0012] According to one aspect of the embodiments of this application, a base station abnormal power detection device is provided, the device comprising:

[0013] The acquisition module is used to acquire raw base station power data and preprocess it to obtain the sample to be audited;

[0014] A construction module is used to construct a base station power consumption calculation model based on the energy consumption factors in the sample to be audited, wherein the energy consumption factors are power consumption factors that affect the power consumption of the base station;

[0015] The calculation module is used to obtain the base station power measurement value through the base station power measurement model, and to calculate the ratio between the base station power measurement value and the actual base station power value.

[0016] The determination module is used to establish a probability model based on the ratio of the base station's measured power value to the actual power value of the base station, so as to identify base stations with abnormal power levels.

[0017] In some embodiments of this application, based on the above technical solutions, the acquisition module is further configured to acquire original base station power data, wherein the original base station power data includes at least the number of device types and base station power; and to delete or fill in data with missing or abnormal values ​​in the original base station power data to obtain the audit sample.

[0018] In some embodiments of this application, based on the above technical solutions, the acquisition module is further configured to: delete the row data containing the missing base station power values; fill the number of missing device types in the original base station power data with a preset value; delete the column data containing other missing data with two or more missing fields; delete the row data containing abnormal base station power values ​​in the original base station power data; set the number of abnormal device types in the original base station data to a preset value; and empty other abnormal data in the original base station power data to obtain the sample to be audited.

[0019] In some embodiments of this application, based on the above technical solutions, the construction module is further configured to: construct a mapping relationship between power consumption influencing factors and power consumption based on the energy consumption factors in the sample to be audited; determine a feature model according to the mapping relationship between power consumption influencing factors and power consumption; perform iterative optimization processing on the feature model; and determine the final feature model as the base station power consumption calculation model.

[0020] In some embodiments of this application, based on the above technical solutions, the construction module is further configured to: construct a selection matrix based on the category of the energy consumption factor; construct a sample energy consumption matrix based on the base station power consumption in the energy consumption factor; construct a regression feature matrix based on the number of device types in the energy consumption factor; and construct a mapping relationship between power consumption influencing factors and power consumption based on the sample energy consumption matrix, the regression feature matrix, and the selection matrix.

[0021] In some embodiments of this application, based on the above technical solutions, the mapping relationship between the power consumption influencing factors and the power consumption satisfies the formula:

[0022] Y = TR(XBE)

[0023] Where TR represents taking the diagonal values ​​of the matrix, Y is the sample energy consumption matrix, X is the regression feature matrix, E is the selection matrix, and B is the feature model; the construction module is also used to calculate the feature model in reverse by using the mapping relationship between the power consumption influencing factors and power consumption.

[0024] In some embodiments of this application, based on the above technical solutions, the determining module is further configured to: calculate the ratio K between the measured base station power consumption value and the actual base station power consumption value; process the K value of each type of base station according to the category of energy consumption factor to obtain the K′ probability density distribution value, so as to establish a probability model, wherein the K′ probability density distribution value satisfies the formula:

[0025]

[0026] Where i represents the number of base stations in each category;

[0027] The probability density distribution values ​​of K′ in each category are statistically analyzed, and the base stations corresponding to the K′ probability density distribution values ​​that exceed the preset range are identified as abnormal power base stations.

[0028] According to one aspect of the embodiments of this application, a computer-readable medium is provided, on which a computer program is stored, which, when executed by a processor, implements the base station abnormal power detection method as described above.

[0029] According to one aspect of the embodiments of this application, an electronic device is provided, the electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the base station abnormal power detection method as described above by executing the executable instructions.

[0030] According to one aspect of the embodiments of this application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the base station abnormal power detection method as described in the above technical solutions.

[0031] In the technical solution provided in this application, the method constructs a base station power consumption calculation model based on the energy consumption factors in the sample to be audited. Then, it obtains the calculated power consumption value of the base station through the base station power consumption calculation model, and establishes a probability model by comparing the actual value with the calculated value to identify base stations with abnormal power consumption. Since the historical power consumption of the base station is not required in this process, the impact of abnormal historical power consumption of the base station on the inaccurate audit results is reduced, thereby improving the accuracy of the audit results.

[0032] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0034] Figure 1 The schematic diagram illustrates the steps of a base station abnormal power detection method provided in an embodiment of this application.

[0035] Figure 2 The illustration schematically shows the steps of obtaining raw base station power data and performing preprocessing to obtain the sample to be audited in one embodiment of this application.

[0036] Figure 3 The illustration schematically shows the steps in one embodiment of this application to remove or fill in data with missing or abnormal values ​​in the original base station power data to obtain the sample to be audited.

[0037] Figure 4 The illustration schematically shows the steps of constructing a base station power consumption calculation model based on the energy consumption factor in the sample to be audited in one embodiment of this application.

[0038] Figure 5 The illustration schematically shows the steps in one embodiment of this application for constructing a mapping relationship between power consumption influencing factors and power consumption based on the energy consumption factors in the sample to be audited.

[0039] Figure 6 The diagram illustrates a model based on the energy consumption factor selection regression algorithm of an embodiment of this application.

[0040] Figure 7The illustration schematically shows the steps in one embodiment of this application to establish a probability model based on the ratio of the base station's measured power value to the actual power value of the base station in order to determine the base station with abnormal power.

[0041] Figure 8 The sample to be audited in one embodiment of this application is illustrated schematically.

[0042] Figure 9 A schematic block diagram of the base station abnormal power detection device provided in an embodiment of this application is shown.

[0043] Figure 10 A schematic diagram of a computer system architecture suitable for implementing the embodiments of this application is shown. Detailed Implementation

[0044] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0045] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0046] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0047] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0048] Existing methods for detecting abnormal base station power consumption mainly include the following three approaches. The first approach is the expert experience method, which relies on expert experience to determine whether the base station's power consumption fluctuations are normal by tracking the power consumption over a long period. For example, for normal base station power consumption, the fluctuation range is generally less than 20%. If the fluctuation range is less than 20%, the base station's power consumption is considered normal; if the fluctuation range is greater than or equal to 20%, the base station's power consumption is considered abnormal. Although this auditing method is relatively simple and quick, the verification results obtained by this method are not accurate, and this auditing method is only effective for base stations with significant power consumption fluctuations.

[0049] The second approach is an auditing method based on KNN clustering. This method uses a simple KNN algorithm, where the value of K is manually determined. The algorithm then finds the set of Y values ​​corresponding to the K nearest neighbors of the feature vector to be audited, and takes the maximum value as the audit threshold. The result is then compared with this threshold to determine if the base station's power consumption is abnormal. This method is relatively simple and fast, but it suffers from significant auditing errors due to outliers, and the accuracy of the audit results is affected by anomalies in the training set.

[0050] The third approach is the auditing method based on prediction algorithms. This method uses historical power consumption data to predict future power consumption, thereby determining whether the power consumption of the audited base station is within a reasonable range. When predicting future power consumption, conventional methods such as linear regression and exponential prediction are generally used to determine if there are any anomalies in the base station's power consumption. Although this method is simple to implement and has a certain adaptability to linear trends, it still cannot effectively detect problems when there are anomalies in historical data.

[0051] To address the aforementioned technical issues, this application proposes a method for detecting abnormal power consumption in base stations. This method constructs a base station power consumption calculation model based on energy consumption factors in the sample to be audited. Then, it obtains the calculated power consumption value of the base station through this model. Finally, it establishes a probability model by comparing the actual value with the calculated value to identify base stations with abnormal power consumption. Since historical power consumption data of the base station is not required in this process, the impact of abnormal historical power consumption on the audit results is reduced, thereby improving the accuracy of the audit results. Furthermore, the technical solution of this application enables rapid detection of abnormal power consumption in base stations within the same billing period, improving the efficiency of abnormal power consumption detection.

[0052] The base station abnormal power detection method, device, and computer-readable medium provided in this application are described in detail below with reference to specific embodiments.

[0053] See Figure 1 , Figure 1The illustration schematically shows the steps of a base station abnormal power detection method according to an embodiment of this application. The method can be executed by a server, and it mainly includes the following steps S101 to S104.

[0054] Step S101: Obtain the original base station power data and perform preprocessing to obtain the sample to be audited.

[0055] First, raw base station power data is obtained. This raw base station power data includes: site address code, billing period, CDMA network equipment type, LDMA network equipment type, base station power consumption, and other data. After obtaining the raw base station power data, it is preprocessed to obtain the audit sample.

[0056] In one embodiment of this application, see Figure 2 , Figure 2 The illustration schematically shows the steps of obtaining raw base station power data and performing preprocessing to obtain an audit sample in one embodiment of this application. The steps of obtaining raw base station power data and performing preprocessing to obtain an audit sample mainly include the following steps S201 to S202.

[0057] Step S201: Obtain raw base station power data, wherein the raw base station power data includes at least the number of device types and the base station power.

[0058] Step S202: Delete or fill in the data with missing or abnormal values ​​in the original base station power data to obtain the sample to be audited.

[0059] After obtaining the original base station power data, the original base station power data is preprocessed, that is, outliers and missing data in the original base station power data are processed. Outliers may be deleted or replaced, and missing values ​​may be deleted or filled. Normalization processing is performed to obtain the sample to be audited.

[0060] In one embodiment of this application, see Figure 3 , Figure 3 The illustration schematically depicts the steps in an embodiment of this application for removing or filling in data with missing or abnormal values ​​in the original base station power data to obtain the audit sample. This process mainly includes the following steps S301 to S306.

[0061] Step S301: Delete the row of data containing the missing base station power value;

[0062] Step S302: Fill the number of missing device types in the original base station power data with a preset value;

[0063] Step S303: Delete the data in the columns containing other missing data that are missing two or more fields;

[0064] Step S304: Delete the row of data containing abnormal base station power values ​​from the original base station power data;

[0065] Step S305: Set the number of abnormal device types in the original base station data to a preset value;

[0066] Step S306: Empty other abnormal data in the original base station power data to obtain the sample to be audited.

[0067] The specific rules for handling missing values ​​are as follows: if the battery value is missing, the data in that row is directly removed; if the device quantity is missing, it is filled with 0; if two or more fields are missing, the data in that column is directly removed.

[0068] The specific rules for handling outliers are as follows: for power values ​​that are significantly too high or too low, or for abnormal power values ​​that cannot be identified, the data in that row will be removed directly; for abnormal device quantities, the values ​​will be set to 0; for other abnormal data, the values ​​will be set to null.

[0069] In this way, by processing outliers and missing values, we can obtain high-quality audit samples, which will help us build a reliable base station power measurement model in the future.

[0070] Step S102: Based on the energy consumption factors in the sample to be audited, construct a base station power consumption calculation model, where the energy consumption factors are the power consumption factors that affect the base station power consumption.

[0071] After obtaining the sample to be audited, since the data packets in the sample contain energy consumption factors, a base station power consumption calculation model is constructed using these factors to calculate the base station's power consumption, thereby obtaining the base station's power consumption value. Constructing this model helps in obtaining the calculated power consumption value, which in turn helps determine whether the current base station is experiencing abnormal power consumption.

[0072] Step S103: Obtain the base station power measurement value through the base station power measurement model, and calculate the ratio between the base station power measurement value and the actual base station power value.

[0073] Since the data packets in the sample to be audited contain the base station's power consumption, which is the actual value of the base station's power consumption, after obtaining the base station's power consumption calculation value through the base station power consumption calculation model, the ratio between the base station's power consumption calculation value and the actual value of the base station's power consumption is calculated, which is helpful for the subsequent identification of base stations with abnormal power consumption.

[0074] Step S104: Based on the ratio of the base station power measurement value to the actual base station power value, establish a probability model to identify base stations with abnormal power levels.

[0075] In the technical solution provided in this application, the method constructs a base station power consumption calculation model based on the energy consumption factors in the sample to be audited. Then, it obtains the calculated power consumption value of the base station through the model and establishes a probability model by comparing the actual value with the calculated value to identify base stations with abnormal power consumption. Since the historical power consumption of the base station is not required in this process, the impact of abnormal historical power consumption on the audit results is reduced, thereby improving the accuracy of the audit results. Furthermore, the technical solution of this application enables rapid detection of abnormal power consumption for base stations within the same billing period, improving the efficiency of abnormal power consumption detection.

[0076] In one embodiment of this application, see Figure 4 , Figure 4 The illustration schematically shows the steps of constructing a base station power consumption calculation model based on the energy consumption factors in the sample to be audited, according to an embodiment of this application. Constructing the base station power consumption calculation model based on the energy consumption factors in the sample to be audited mainly includes the following steps S401 to S403.

[0077] Step S401: Based on the energy consumption factors in the sample to be audited, construct the mapping relationship between the factors affecting power consumption and power consumption.

[0078] The audit sample includes energy consumption factors, which are power consumption factors that affect the base station's power consumption. By using the energy consumption factors in the audit sample, it is easy to construct the relationship between power consumption influencing factors and power consumption.

[0079] Step S402: Determine the feature model based on the mapping relationship between power consumption influencing factors and power consumption.

[0080] By identifying the factors influencing power consumption and their relationship with power consumption, it becomes easier to determine the characteristic model. Determining the characteristic model, in turn, facilitates the determination of the base station power consumption calculation model.

[0081] Step S403: Iteratively optimize the feature model and determine the final feature model as the base station power measurement model.

[0082] The feature matrix is ​​iteratively optimized using the gradient descent algorithm to determine the final feature model as the base station power consumption calculation model. This model facilitates the subsequent calculation of base station power consumption values.

[0083] In this way, by using the energy consumption factors in the sample to be audited, the relationship between the factors affecting power consumption and power consumption can be constructed, which is conducive to determining the power consumption calculation model of the base station and obtaining the calculated value of the power consumption of the base station.

[0084] In one embodiment of this application, see Figure 5 , Figure 5 The illustration schematically depicts the steps of constructing a mapping relationship between power consumption influencing factors and power consumption based on energy consumption factors in the sample to be audited, according to an embodiment of this application. Constructing the mapping relationship between power consumption influencing factors and power consumption based on energy consumption factors in the sample to be audited mainly includes the following steps S501 to S504.

[0085] Step S501: Construct a selection matrix based on the category of energy consumption factors.

[0086] Select matrix E for sample classification. Select matrix E represents sample classification based on energy consumption factors such as data center type, CDMA network equipment type, LDMA network equipment type, and 5G equipment type.

[0087] Step S502: Construct a sample energy consumption matrix based on the base station power consumption in the energy consumption factor.

[0088] We will use electricity consumption as the actual value to construct a sample energy consumption matrix.

[0089] Step S503: Construct a regression feature matrix based on the number of equipment types in the energy consumption factor.

[0090] Step S504: Based on the sample energy consumption matrix, regression feature matrix, and selection matrix, construct the mapping relationship between the factors affecting power consumption and power consumption.

[0091] In this way, by using the sample energy consumption matrix, regression feature matrix, and selection matrix to obtain the relationship between the factors affecting power consumption and power consumption, it is beneficial to determine the base station power consumption calculation model and obtain the calculated value of base station power consumption.

[0092] In one embodiment of this application, the mapping relationship between power consumption influencing factors and power consumption satisfies the formula:

[0093] Y = TR(XBE)

[0094] Where TR represents taking the diagonal values ​​of the matrix, Y is the sample energy consumption matrix, X is the regression feature matrix, E is the selection matrix, and B is the feature model;

[0095] Based on the mapping relationship between factors affecting power consumption and power consumption, a characteristic model is determined, including:

[0096] By mapping the factors affecting power consumption to power consumption, the feature model is obtained through reverse calculation.

[0097] In this way, by calculating the characteristic model, it is easier to determine the base station power measurement model, so as to obtain the measured value of the base station power.

[0098] In one embodiment of this application, see Figure 6 , Figure 6 The diagram illustrates a model based on the energy consumption factor selection regression algorithm of an embodiment of this application.

[0099] The process of applying the energy consumption factor-based regression algorithm for modeling is as follows: First, construct the selection matrix, which is based on energy consumption factors such as data center type, C-network equipment type, L-network equipment type, and 5G equipment type.

[0100]

[0101] In the E matrix, the values ​​are either 1 or 0, and each column has exactly one value of 1 and all others are 0. 1 represents the category to which the sample belongs.

[0102] Next, a model of power consumption influencing factors and power consumption is generated based on a regression algorithm, including: introducing a selection matrix E for sample classification, and constructing a selection regression algorithm based on energy consumption factors, with the algorithm formula: Y = TR(XBE). Here, TR represents taking the diagonal values ​​of the matrix, matrix Y is composed of sample energy consumption values, matrix X is composed of regression feature values, feature matrix B is composed of feature parameters, and selection matrix E represents sample classification based on energy consumption factors such as data center type, CDMA network equipment type, LDMA network equipment type, and 5G equipment type.

[0103] Assuming that the m samples are divided into α classes based on the power consumption factor selection matrix E, the matrix expressions for Y = TR(XBE) are as follows:

[0104]

[0105]

[0106]

[0107]

[0108] Based on the classified samples to be audited, given matrices Y, X, and E, the feature matrix B is calculated in reverse. The feature matrix B is iteratively optimized using the gradient descent algorithm to output the final model, thus obtaining the base station power measurement model.

[0109] In one embodiment of this application, see Figure 7 , Figure 7The illustration schematically depicts the steps in one embodiment of this application to establish a probabilistic model based on the ratio of the calculated base station power consumption to the actual base station power consumption, thereby identifying base stations with abnormal power consumption. Establishing a probabilistic model based on the ratio of the calculated base station power consumption to the actual base station power consumption to identify base stations with abnormal power consumption mainly includes the following steps S701 to S703.

[0110] Step S701: Calculate the ratio K between the measured base station power consumption and the actual base station power consumption.

[0111] Step S702: Process the K value of each type of base station according to the category of energy consumption factor to obtain the K′ probability density distribution value, so as to establish a probability model, wherein the K′ probability density distribution value satisfies the formula:

[0112]

[0113] Where i represents the number of base stations in each category;

[0114] Step S703: Calculate the probability density distribution value of K′ in each category, and determine the base station corresponding to the K′ probability density distribution value that exceeds the preset range as an abnormal power base station.

[0115] Statistically calculate the probability of K' within the range of N sigma, and output the list of base station power consumption outside the range of N sigma to identify base stations with abnormal power consumption.

[0116] In this way, the reasonable deviation range of base station power is calculated by statistical methods, and a probability model is established by calculating the ratio K of the actual power value and the measured power value of the base station. The base station with a low probability K value is the base station with abnormal power.

[0117] To facilitate understanding of the technical solution of this application, examples are provided below. (See attached image) Figure 8 , Figure 8 The illustration schematically depicts a sample to be audited in one embodiment of this application. The sample includes site address code, power consumption, CDMA network equipment type, LDMA network equipment type, 5G equipment type, number of CDMA network sectors, number of LDMA RRUs, and number of 5G AAUs. Based on the energy consumption factors in the sample, the base station power consumption calculation model is constructed as follows:

[0118] Based on power consumption factors, the 6 samples can be divided into 2 categories. The matrix Y = TR(XBE) represents the power consumption, and X represents the number of C-network sectors, L-network BBUs, L-network RRUs, 5G BBUs, and 5G AAUs corresponding to the regression feature matrix. The matrices represented by Y, X, B, and E are as follows:

[0119]

[0120]

[0121]

[0122]

[0123]

[0124]

[0125]

[0126] The modeling yielded the following:

[0127] The calculated values ​​are obtained based on the model:

[0128] Based on the ratio between the calculated base station power consumption and the actual base station power consumption, and combined with the following formula, K' is obtained:

[0129]

[0130]

[0131] Finally, base stations with power levels exceeding this range are identified as abnormal power base stations.

[0132] It should be noted that although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0133] The following describes an apparatus embodiment of this application, which can be used to execute the base station abnormal power detection method in the above embodiments of this application. Figure 9 A schematic block diagram of a base station abnormal power detection device provided in an embodiment of this application is shown. Figure 9 As shown, the base station abnormal power detection device 900 includes:

[0134] The acquisition module 901 is used to acquire raw base station power data and preprocess it to obtain the sample to be audited;

[0135] Module 902 is used to construct a base station power consumption calculation model based on the energy consumption factors in the sample to be audited, wherein the energy consumption factors are the power consumption factors that affect the power consumption of the base station.

[0136] The calculation module 903 is used to obtain the base station power measurement value through the base station power measurement model, and to calculate the ratio between the base station power measurement value and the actual base station power value.

[0137] The determination module 904 is used to establish a probability model based on the ratio of the base station power measurement value to the actual base station power value in order to identify base stations with abnormal power levels.

[0138] In some embodiments of this application, based on the above technical solutions, the acquisition module 901 is further configured to acquire original base station power data, wherein the original base station power data includes at least the number of device types and base station power; and to delete or fill in data with missing or abnormal values ​​in the original base station power data to obtain the audit sample.

[0139] In some embodiments of this application, based on the above technical solutions, the acquisition module 901 is further configured to: delete the row data containing the missing base station power values; fill the number of missing device types in the original base station power data with a preset value; delete the column data containing other missing data with two or more missing fields; delete the row data containing abnormal base station power values ​​in the original base station power data; set the number of abnormal device types in the original base station data to a preset value; and empty other abnormal data in the original base station power data to obtain the sample to be audited.

[0140] In some embodiments of this application, based on the above technical solutions, the construction module 902 is further configured to: construct a mapping relationship between power consumption influencing factors and power consumption based on the energy consumption factors in the sample to be audited; determine a feature model based on the mapping relationship between power consumption influencing factors and power consumption; perform iterative optimization on the feature model; and determine the final feature model as the base station power consumption calculation model.

[0141] In some embodiments of this application, based on the above technical solutions, the construction module 902 is further configured to: construct a selection matrix based on the category of energy consumption factors; construct a sample energy consumption matrix based on the base station power consumption in the energy consumption factors; construct a regression feature matrix based on the number of device types in the energy consumption factors; and construct a mapping relationship between power consumption influencing factors and power consumption based on the sample energy consumption matrix, the regression feature matrix, and the selection matrix.

[0142] In some embodiments of this application, based on the above technical solutions, the mapping relationship between power consumption influencing factors and power consumption satisfies the formula:

[0143] Y = TR(XBE)

[0144] Where TR represents taking the diagonal values ​​of the matrix, Y is the sample energy consumption matrix, X is the regression feature matrix, E is the selection matrix, and B is the feature model; the construction module is also used to calculate the feature model in reverse by using the mapping relationship between the factors affecting power consumption and power consumption.

[0145] In some embodiments of this application, based on the above technical solutions, the determining module 904 is further configured to calculate the ratio between the measured base station power consumption value and the actual base station power consumption value as a K value; process the K value of each type of base station according to the category of energy consumption factor to obtain the K′ probability density distribution value, so as to establish a probability model, wherein the K′ probability density distribution value satisfies the formula:

[0146]

[0147] Where i represents the number of base stations in each category;

[0148] The probability density distribution values ​​of K′ in each category are statistically analyzed, and the base stations corresponding to the K′ probability density distribution values ​​that exceed the preset range are identified as abnormal power base stations.

[0149] The specific details of the base station abnormal power detection device provided in the various embodiments of this application have been described in detail in the corresponding method embodiments, and will not be repeated here.

[0150] Figure 10 A schematic block diagram of a computer system architecture for implementing an electronic device according to embodiments of the present application is shown.

[0151] It should be noted that, Figure 10 The computer system 1000 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application. The electronic device may be, for example, a washing machine.

[0152] like Figure 10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage section 1008 into random access memory (RAM). The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output interface 1005 (I / O interface) is also connected to the bus 1004.

[0153] The following components are connected to the input / output interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a local area network card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output interface 1005 as needed. A removable medium 1010, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0154] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1010. When the computer program is executed by central processing unit 1001, it performs various functions defined in the system of this application.

[0155] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0157] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0158] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0159] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0160] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for detecting abnormal power levels in a base station, characterized in that, The method includes: Obtain raw base station power data and preprocess it to obtain the sample to be audited; Based on the energy consumption factors in the sample to be audited, a base station power consumption calculation model is constructed, wherein the energy consumption factors are power consumption factors that affect the power consumption of the base station. The base station power consumption is calculated using the base station power consumption calculation model, and the ratio between the calculated base station power consumption and the actual base station power consumption is calculated. Based on the ratio of the base station's calculated power consumption to the actual power consumption of the base station, a probability model is established to identify base stations with abnormal power consumption. The step of constructing a base station power consumption calculation model based on the energy consumption factors in the sample to be audited includes: constructing a selection matrix based on the categories of the energy consumption factors; constructing a sample energy consumption matrix based on the base station power consumption in the energy consumption factors; constructing a regression feature matrix based on the number of device types in the energy consumption factors; constructing a mapping relationship between power consumption influencing factors and power consumption based on the sample energy consumption matrix, the regression feature matrix, and the selection matrix; calculating a feature model in reverse through the mapping relationship between power consumption influencing factors and power consumption; iteratively optimizing the feature model; and determining the final feature model as the base station power consumption calculation model. The mapping relationship between the factors affecting power consumption and power consumption satisfies the formula: Y = TR(XBE); where TR represents taking the diagonal value of the matrix, Y is the sample energy consumption matrix, X is the regression feature matrix, E is the selection matrix, and B is the feature model.

2. The base station abnormal power detection method according to claim 1, characterized in that, The process of acquiring and preprocessing raw base station power data to obtain the audit sample includes: Obtain raw base station power data, wherein the raw base station power data includes at least the number of device types and the base station power; The data with missing or abnormal values ​​in the original base station power data are deleted or filled in to obtain the sample to be audited.

3. The base station abnormal power detection method according to claim 2, characterized in that, The process of removing or filling in missing and abnormal data in the original base station power data to obtain the audit sample includes: Delete the row containing the missing base station power value from the original base station power data; Fill the number of missing device types in the original base station power data with a preset value; Delete the data in columns containing other missing data that are missing two or more fields; Delete the row containing the abnormal base station power values ​​from the original base station power data; Set the number of abnormal device types in the original base station power data to a preset value; Other abnormal data in the original base station power data are cleared to obtain the sample to be audited.

4. The base station abnormal power detection method according to claim 1, characterized in that, The step of establishing a probability model based on the ratio of the base station's measured power consumption to the actual power consumption of the base station to identify base stations with abnormal power consumption includes: The ratio K is calculated as the ratio between the calculated base station power consumption and the actual base station power consumption. The K value of each type of base station is processed according to the category of energy consumption factor to obtain the K′ probability density distribution value, so as to establish a probability model, wherein the K′ probability density distribution value satisfies the formula: Where i represents the number of base stations in each category; The probability density distribution values ​​of K′ in each category are statistically analyzed, and the base stations corresponding to the K′ probability density distribution values ​​that exceed the preset range are identified as abnormal power base stations.

5. A base station abnormal power detection device, characterized in that, The device includes: The acquisition module is used to acquire raw base station power data and preprocess it to obtain the sample to be audited; A construction module is used to construct a base station power consumption calculation model based on the energy consumption factors in the sample to be audited, wherein the energy consumption factors are power consumption factors that affect the power consumption of the base station; The calculation module is used to obtain the base station power measurement value through the base station power measurement model, and to calculate the ratio between the base station power measurement value and the actual base station power value. The determination module is used to establish a probability model based on the ratio of the base station's measured power value to the actual power value of the base station, so as to identify base stations with abnormal power levels. The step of constructing a base station power consumption calculation model based on the energy consumption factors in the sample to be audited includes: constructing a selection matrix based on the categories of the energy consumption factors; constructing a sample energy consumption matrix based on the base station power consumption in the energy consumption factors; constructing a regression feature matrix based on the number of device types in the energy consumption factors; constructing a mapping relationship between power consumption influencing factors and power consumption based on the sample energy consumption matrix, the regression feature matrix, and the selection matrix; calculating a feature model in reverse through the mapping relationship between power consumption influencing factors and power consumption; iteratively optimizing the feature model; and determining the final feature model as the base station power consumption calculation model. The mapping relationship between the factors affecting power consumption and power consumption satisfies the formula: Y = TR(XBE); where TR represents taking the diagonal value of the matrix, Y is the sample energy consumption matrix, X is the regression feature matrix, E is the selection matrix, and B is the feature model.

6. A computer-readable medium, characterized in that, The computer-readable medium stores a computer program that, when executed by a processor, implements the base station abnormal power detection method according to any one of claims 1 to 4.

7. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the base station abnormal power detection method according to any one of claims 1 to 4 by executing the executable instructions.

Images