Fault detection method and device for indoor distribution system

Abstract

The embodiment of the invention provides a fault detection method and device for an indoor distribution system, and the method comprises the steps: obtaining equipment network data of communication equipment of the indoor distribution system and terminal communication data of a network access terminal, carrying out the cleaning processing of the equipment network data and the terminal communication data, and obtaining detection basic data, and determining to-be-detected equipment according to the detection equipment type of the detection basic data, extracting fault detection data from the detection basic data based on a fault detection mechanism corresponding to the detection equipment type, and performing fault detection on the to-be-detected equipment according to the fault detection mechanism and the fault detection data.

Description

Technical Field

[0001] This document relates to the field of communication technology, and in particular to a fault detection method and device for an indoor distribution system. Background Technology

[0002] With the continuous development of Internet technology, the field of communication technology is iterating and upgrading towards high-density coverage and high-quality transmission. As the core support for indoor communication, the operation and maintenance of indoor distributed antenna systems (DAS) requires efficient technical means to detect faults in the communication equipment, which has become a key direction for ensuring stable communication operation. Among them, fault detection methods based on equipment data acquisition are widely used in the operation and maintenance of indoor DAS. However, as the architecture of indoor DAS becomes increasingly complex and the types of communication equipment continue to increase, and the fault characteristics of different equipment types are significantly different, how to accurately match equipment types with detection mechanisms to achieve rapid fault detection of communication equipment has become a focus of attention in the industry. Summary of the Invention

[0003] This disclosure provides a fault detection method and apparatus for an indoor distribution system to address the problem of how to improve the efficiency of detecting communication equipment faults.

[0004] In a first aspect, embodiments of this disclosure provide a fault detection method for an indoor distribution system, including: The system acquires device network data from communication equipment in the indoor distribution system and terminal communication data from network access terminals; it cleans and processes the device network data and terminal communication data to obtain basic detection data; it determines the device to be tested in the communication equipment based on the detection device type in the basic detection data, extracts fault detection data from the basic detection data based on the fault detection mechanism corresponding to the detection device type; and it performs fault detection on the device to be tested according to the fault detection mechanism and the fault detection data.

[0005] Secondly, embodiments of this disclosure provide a fault detection device for an indoor distribution system, comprising: The data acquisition unit is used to acquire the device network data of the communication equipment of the indoor distribution system and the terminal communication data of the network access terminal. A cleaning and processing unit is used to clean and process the device network data and the terminal communication data to obtain basic detection data. The data extraction unit is used to determine the device to be tested in the communication device according to the detection device type of the detection basic data, and extract fault detection data from the detection basic data based on the fault detection mechanism corresponding to the detection device type. The fault detection unit is used to perform fault detection on the device under test according to the fault detection mechanism and the fault detection data.

[0006] Thirdly, embodiments of this disclosure provide an electronic device, including: a memory, a processor, and computer-executable instructions stored in the memory and executable on the processor, wherein the computer-executable instructions, when executed by the processor, implement the method described in the first aspect above.

[0007] Fourthly, embodiments of this disclosure provide a computer-readable storage medium for storing computer-executable instructions that, when executed by a processor, implement the method described in the first aspect above.

[0008] Fifthly, embodiments of this disclosure provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the method described in the first aspect above.

[0009] In one or more embodiments of this disclosure, firstly, device network data of the communication equipment of the indoor distribution system and terminal communication data of the network access terminal are acquired; then, the device network data and terminal communication data are cleaned and processed to obtain basic detection data; next, the device to be tested in the communication equipment is determined according to the detection device type of the basic detection data, and fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the detection device type; finally, fault detection is performed on the device to be tested according to the fault detection mechanism and the fault detection data. As can be seen from this embodiment, in situations where indoor distributed antenna system (DAS) communication equipment is diverse, data sources are complex, and the fault characteristics of different types of communication equipment vary significantly, this embodiment obtains device network data and terminal communication data from network access terminals of the indoor DAS communication equipment. The device network data and terminal communication data are then cleaned and processed to obtain basic detection data. The device type corresponding to the basic detection data is used to determine the device to be tested and the matching fault detection mechanism, thereby achieving precise adaptation between the fault detection mechanism and the device type. Furthermore, fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the device type, and fault detection is performed on the device to be tested according to the fault detection mechanism and fault detection data. This allows the fault detection process to adapt to the fault detection logic of the indoor DAS, providing accurate basis for fault determination of different types of communication equipment and improving the accuracy and efficiency of fault detection in the indoor DAS. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in one or more embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating a fault detection method for an indoor distribution system provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of a fault detection device for an indoor distribution system provided in an embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present disclosure. Detailed Implementation

[0012] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this disclosure, the technical solutions in one or more embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of the embodiments. Based on one or more embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0013] This disclosure provides a fault detection method and apparatus for an indoor distributed antenna system (DAS), which can improve the accuracy and efficiency of fault detection in indoor DAS systems. The fault detection method can be applied to a server-side application and implemented by the server, which includes, but is not limited to, various types of computing service devices such as rack servers, blade servers, tower servers, cloud servers, virtual machine instances, containerized server nodes, edge computing servers, gateway servers, distributed server clusters, application servers, database servers, computing power servers, and private cloud servers.

[0014] Figure 1 This is a flowchart illustrating a fault detection method for an indoor distribution system according to an embodiment of this disclosure. Figure 1 As shown, the process includes: Step S102: Obtain the device network data of the communication equipment of the indoor distribution system and the terminal communication data of the network access terminal.

[0015] The indoor distribution system described in this embodiment is a core system that provides communication signal coverage for indoor scenarios. It can be deployed in various indoor communication scenarios, such as shopping malls, office buildings, subways, and residential communities. The indoor distribution system consists of multiple communication devices. The communication devices are components in the indoor distribution system that realize functions such as signal transmission, combining and splitting, and signal amplification. The communication devices include: signal amplifiers, combiners, remote radio units (RRUs), baseband units (BBUs), low noise amplifiers (LNAs), and / or antenna feeders. The indoor distribution system can deploy multiple signal amplifiers, multiple combiners, multiple RRUs, or one combiner and multiple RRUs.

[0016] The network access terminal is a terminal device that establishes a communication connection with the indoor distribution system and obtains network services, such as a user's mobile phone, tablet computer, merchant's smart terminal, IoT device, etc. In this embodiment, the types of communication devices and network access terminals can be flexibly set according to the deployment scenario of the indoor distribution system.

[0017] The device network data is data generated during the operation of the communication equipment. It can reflect the operating status of the equipment and the network configuration. The device network data includes the signal strength of each network channel of the communication equipment, equipment status parameters and / or network configuration information of the indoor distribution system.

[0018] The terminal communication data refers to the data exchanged between the network access terminal and the indoor distribution system during the communication process. Specifically, the terminal communication data includes the location information of the network access terminal, the signal strength and / or the signal quality of the communication. The terminal communication data can be at the cell port (CP) level, that is, the data collected based on the cell port dimension of the indoor distribution system, or at the user equipment (UE) level, that is, the data collected based on the dimension of a single network access terminal.

[0019] In one embodiment, acquiring device network data of the communication equipment of the indoor distribution system and terminal communication data of the network access terminal includes: acquiring the signal strength and device status parameters of each network channel of the communication equipment according to a preset period, and reading the network configuration information of the indoor distribution system from the network management system; the device network data includes signal strength, device status parameters and network configuration information; and receiving terminal communication data uploaded by the network access terminal that has established a communication connection with the indoor distribution system.

[0020] Specifically, signal strength is the core parameter for measuring the signal transmission capability of communication equipment, and it can be quantified using Received Signal Strength Indication (RSSI). Equipment status parameters can be parameters that reflect the equipment's own operating status, such as the power supply status, operating temperature, working mode, and operating power of the communication equipment, or they can be engineering parameters of the communication equipment, such as antenna position, height, azimuth angle, feeder length, and loss.

[0021] Network configuration information is data used to record the deployment architecture of the indoor distribution system, the network relationships of the devices, and the communication parameter settings. Specifically, network configuration information can be the cell configuration parameters of the indoor distribution system, the device connection relationships, the device access logs, or the signal coverage range.

[0022] In one example, a preset period is first set, continuously acquiring the channel-level RSSI of the RRU at a 15-minute interval. Simultaneously, antenna operating status information is collected, which can be the antenna's equipment temperature or power value. Through the 5G communication link between the UE and the indoor distribution system, terminal communication data uploaded by the UE is obtained at the CP level. Following preset reporting rules, CP-level terminal communication data, including key indicators such as location information, signal strength, and signal quality, is collected in real time. Next, the cell configuration parameters and equipment connection relationships of the indoor distribution system are obtained through the network management system. Finally, engineering parameters are collected, including antenna position, height, azimuth angle, feeder length, and / or loss. This process enables the acquisition of equipment network data from the communication devices of the indoor distribution system and terminal communication data from network access terminals, providing a foundation for accurate fault location in the future.

[0023] The above examples are only for the purpose of understanding how the data is acquired. The granularity of the preset period can be the same or different, and the specific data content collected can be the same or different, and is not limited to the above examples.

[0024] Step S104: Clean and process the device network data and terminal communication data to obtain basic detection data.

[0025] The cleaning process refers to the process of identifying and deleting invalid, missing, or abnormal data in the device network data and terminal communication data collected in step S102 through a series of data verifications and screenings, thereby improving the reliability and accuracy of the data and providing reliable data for the subsequent identification of the device to be tested.

[0026] The basic detection data includes target device network data and target terminal communication data obtained after cleaning and processing device network data and terminal communication data. In other words, the basic detection data includes valid communication data of communication devices and network access terminals, providing data support for subsequent fault detection.

[0027] In one embodiment, cleaning the device network data and terminal communication data to obtain basic detection data includes: validating the device network data based on device status parameters, network configuration information, and terminal communication data; deleting invalid data from the device network data based on the verification results to obtain target device network data; performing integrity verification on the terminal communication data using a data verification algorithm; cleaning the terminal communication data that has an error in the verification; performing outlier detection on the cleaned terminal communication data and deleting outlier data to obtain target terminal communication data; the basic detection data includes target device network data and target terminal communication data.

[0028] In one example, the validity verification of device network data is implemented using the following steps: Step 1: Identify RRUs that have not established a communication connection with the network access terminal based on the device access logs in the network configuration information and delete their corresponding RSSIs. For example, by querying the network user access logs and the service traffic statistics system, obtain information such as user access time, duration, and service traffic volume to determine whether there are users under the RRU. If the user access record corresponding to the RRU is empty and the traffic is zero within a certain time period, determine that the RSSI within that time period belongs to the scenario data without users and delete the RSSI.

[0029] Step 2: Identify the faulty RRU based on the alarm information and working indicators in the device status parameters and delete the RSSI data corresponding to the faulty RRU. For example, if an RRU issues an alarm or the transmit power of an RRU drops significantly, it means that the RSSI data collected by that RRU cannot represent the normal network status and needs to be deleted.

[0030] Step 3: Based on the working status of the communication device in the device status parameters and the communication link status in the network configuration information, exclude abnormal data of the network channel. For example, if the network channel of a certain RRU is in a closed state or the communication link status is a link interruption, the RSSI data corresponding to that RRU needs to be deleted.

[0031] Step 4: Identify and delete abnormal data based on CP coverage data in network configuration information. Specifically, use Geographic Information System (GIS) and cell coverage planning data to identify and delete abnormal data caused by differences in coverage areas. For example, if the theoretical coverage area of ​​an RRU is a building, but the collected data comes from an area far away from the building, then the RSSI corresponding to that RRU is considered abnormal data and deleted.

[0032] In the above example, the integrity verification of terminal communication data is implemented using the following steps: Step 1: Check the integrity of the terminal communication data. Use a data verification algorithm to check each piece of the collected terminal communication data to ensure that no key indicators are missing. Key indicators include: the location information of the network access terminal, the signal strength and signal quality of the communication, etc. Specifically, for terminal communication data with missing location information, it can be supplemented by correlation analysis with surrounding data or by using other positioning methods. If key indicators such as signal strength are missing, estimate or remove the corresponding terminal communication data based on the time series characteristics and statistical patterns of the terminal communication data.

[0033] Step 2: Eliminate obvious erroneous data caused by signal interference or UE abnormalities. Signal interference may come from other wireless signal sources, while UE abnormalities may be caused by hardware failures or software errors leading to abnormal terminal communication data. Specifically, terminal communication data with signal strength exceeding a reasonable range, such as signal strength far exceeding or falling far below the normal signal strength range for that area, can be judged as abnormal data. Terminal communication data with severely deviated information locations should also be deleted. For example, if in an indoor scenario, the signal strength reported by the UE reaches the high intensity level of an open outdoor area, or the reported location does not match the actual location of the building, this terminal communication data is likely erroneous data caused by signal interference or UE abnormalities, and such terminal communication data should be deleted.

[0034] Step 3: Identify outliers in the terminal communication data that has passed the integrity check. Use statistical analysis to identify and remove outliers. The statistical analysis can be based on the interquartile range method or the standard deviation method. For example, when using the interquartile range method, if the signal strength of the terminal communication data is lower than -1.5 times the interquartile range of the lower quartile or higher than +1.5 times the interquartile range of the upper quartile, it is determined to be an outlier. When using the standard deviation method, if the signal strength of the terminal communication data deviates from the mean by more than 3 times the standard deviation, it is determined to be an outlier.

[0035] Step S106: Determine the device to be tested in the communication equipment based on the detection equipment type in the detection basic data, and extract fault detection data from the detection basic data based on the fault detection mechanism corresponding to the detection equipment type.

[0036] The type of testing equipment refers to the type of equipment determined based on the communication equipment corresponding to the basic testing data. Different types of communication equipment have significantly different fault characteristics due to their different functional positioning and operating logic. For example, combiners, RRUs, signal amplifiers, and antenna feeders are all different types of testing equipment and correspond to their respective fault detection requirements.

[0037] The device to be tested refers to the communication device corresponding to the basic detection data, that is, a communication device with a clear device type, valid operating data, and a need for targeted fault detection; the fault detection mechanism refers to the detection method preset for different types of detection devices and the detection logic adapted to different types of detection devices; the fault detection data refers to the key data extracted from the basic detection data based on the fault detection mechanism corresponding to the type of detection device.

[0038] In one example, if the detection device type is determined to be RRU based on the detection basic data, the fault detection mechanism of RRU is determined according to the preset mapping relationship, including signal imbalance detection and coupling fault detection mechanism. Then, the RSSI of each network channel of the RRU and the operating power and signal transmission delay parameters of the RRU are extracted from the detection basic data as fault detection data.

[0039] Step S108: Perform fault detection on the equipment to be tested according to the fault detection mechanism and fault detection data.

[0040] Due to differences in communication types, the aforementioned fault detection mechanism includes five different detection mechanisms, which are described below: (1) Detection method one: In one embodiment, fault detection of the device under test according to the fault detection mechanism and fault detection data includes: The fault detection data is input into the detection model that performs coupled fault detection to detect coupled faults in the device under test, and the detection results of coupled fault detection are output. Among them, the coupling fault detection includes: The fault detection data is input into the encoder for encoding processing to obtain fault code data; The fault coding data is input into a feature extraction network for extraction to obtain fault features; The fault features are coupled to detect faults through a detection network, and the coupled fault detection results are obtained.

[0041] In one example, if the fault detection of the device under test includes coupled fault detection, the fault detection data is input into an autoencoder for encoding to obtain fault code data. The fault code data can be obtained in the following ways: Set the input data as ,in This represents the i-th data sample, which is input data by the encoder. Mapped to low-dimensional encoding, the calculation formula is: = ; in, represent The corresponding low-order code, It is the encoder's transform function. These are the encoder's transformation parameters.

[0042] The low-order bits are encoded by the decoder corresponding to the encoder. Reconstructed into output data The calculation formula is: ; in the formula It is the transform function of the decoder. These are the transform parameters of the decoder.

[0043] The mean squared error (MSE) is defined by the following parameters: ; Where n is the number of data samples, and m is the number of features per sample. It is the j-th feature value of the i-th sample. It is the j-th feature value of the i-th sample after reconstruction, for each input data Calculate its reconstruction error by iterating through the data. .

[0044] Set a dynamic threshold T, when When the value is greater than T, the data is marked as an outlier. The dynamic threshold T can be calculated by averaging the reconstruction errors of all input data. and standard deviation To determine, among which, +3 The advantage of setting T as a dynamic threshold and relating it to the mean μ and standard deviation σ of the reconstruction error is that it can be dynamically readjusted after each traversal loop based on the reconstruction error of all samples, according to changes in the samples, thus avoiding error deviation and inaccuracy caused by a fixed threshold.

[0045] In practical applications, the input data dimension is input_dim, and the encoding dimension is set to encoding_dim (e.g., encoding_dim=10°). The autoencoder is trained using the Adam optimizer with 50 training epochs and a batch size of 32.

[0046] In this example, after acquiring the fault coding data, to ensure consistency of feature values ​​across different ranges, the Min-Max normalization method is used to normalize the obtained normal data. For each feature x, the normalized result is... The calculation formula is: ; in, and These are the minimum and maximum values ​​of the feature across all samples, respectively.

[0047] After data normalization, a convolutional neural network is used to extract fault features, adjusting the normalized data into a three-dimensional tensor form suitable for input to the convolutional neural network. The first dimension represents the number of samples, the second dimension represents the number of features per sample, and the third dimension represents the number of channels. The number of channels can be determined based on the device to be tested corresponding to the fault detection data.

[0048] Construct a fault feature extraction convolutional neural network model, including convolutional layer 1, max pooling layer 1, convolutional layer 2, max pooling layer 2, flattening layer, fully connected layer 1, and fully connected layer 2: Convolutional layer 1 uses two convolutional kernels of size 3, with ReLU activation function. The formula for calculating the convolution operation is: ,in It is the i-th element output by the convolution. It is the i-th weight of the convolution kernel. is the i-th element of the input data, b is the bias term, and k is the size of the convolution kernel.

[0049] The pooling size of max pooling layer 1 is 2. It reduces the data dimensionality by taking the maximum value of a local region for downsampling.

[0050] Convolutional layer 2 uses 64 convolutional kernels of size 3 and the activation function is ReLU().

[0051] The pooling size of max pooling layer 2 is 2.

[0052] The multidimensional data after convolution and pooling is converted into a one-dimensional vector by a flattening layer.

[0053] Fully connected layer 1 contains 64 neurons and the activation function is ReLU().

[0054] The output dimension of the fully connected layer 2 is 10, the activation function is ReLU(), and the output is a fault feature vector.

[0055] The training and test datasets are input into a convolutional neural network to obtain the corresponding fault feature vectors. and .

[0056] After extracting the fault feature vectors, a detection network is used to classify the extracted fault feature vectors to determine whether the combiner has a fault. For a given fault feature vector... and its corresponding tags ,in This represents the category of the nth sample.

[0057] When using the radial basis function (RBF), the decision function of the support vector machine is defined as follows: ; in, It is a Lagrange multiplier. Here, b is the radial basis function kernel, and b is the bias term. Its calculation formula is defined as follows: ; in, These are the parameters of the kernel function. Is sample x and Euclidean distance.

[0058] In this example, the kernel function is chosen as the radial basis function, and the penalty parameter C = 1.0°. Automatic calculation is performed using the 'scale' method. Fault feature vectors from the training set are used. and corresponding tags Train the detection network.

[0059] In the detection network, the scaling method is set to a value of gamma, which is a parameter in the radial basis function (RBF). (In the formula...) In this context, gamma determines the scope and shape of the kernel function, while in the scale mode, the calculation of gamma is related to the characteristics of the data. Setting the scale mode can automatically calculate the value of gamma based on the number of features and variance of the input data. The specific calculation formula is as follows: , in, It is the number of features in the data. It is the variance of all features.

[0060] This calculation method is crucial for adapting to the characteristics of the data in this scenario. It can automatically adjust the gamma value based on the data's inherent features without requiring manual setting. Different datasets have varying numbers of features and feature variances, making it difficult to determine the optimal gamma value through manual parameter tuning. Using the scaling method allows the model to better adapt to the characteristics of different datasets, avoiding poor model performance due to inappropriate gamma settings. For example, for datasets with a large number of features and high variance, the scaling method calculates a relatively small gamma value, broadening the kernel function's scope and enabling it to map the data over a larger space. Conversely, for datasets with fewer features or lower variance, the gamma value is relatively larger, allowing the kernel function to map the data more finely within a local range.

[0061] It should be noted that this calculation method also simplifies the parameter tuning process and increases the fault identification rate. In practical applications, parameter tuning is a complex and time-consuming task. The scale method reduces the workload of manually adjusting gamma, lowers the complexity of model training, and improves efficiency. Especially when dealing with large-scale data or multiple different datasets, this automatic gamma calculation method has a more obvious advantage, quickly finding a relatively suitable gamma value for different data, thus improving the model's adaptability and stability.

[0062] (2) Detection method two: In one embodiment, fault detection of the device under test according to the fault detection mechanism and fault detection data includes: The signal strength of each network channel is extracted according to the preset data format, and target communication devices with signal strength lower than the strength threshold are selected from the devices to be tested. Verify whether the target communication device meets the configuration requirements. If the target communication device reports an alarm and its network channel is blocked, it is determined that the uplink network channel of the target communication device is faulty.

[0063] In one example, if the fault detection of the device under test includes the fault detection of the uplink LNA, the RSSI index of each network channel of the RRU is extracted according to the NR standard. The obtained RSSI index is then filtered, and RRUs with an average RSSI value below -100dBm are listed as target RRUs. Under normal working conditions, the average RSSI value of the RRU will be maintained within a certain range. When the average RSSI value is too low, it may indicate that there is a fault in the uplink LNA of the RRU, resulting in an abnormal weakening of the signal reception strength.

[0064] Simultaneously verify whether the configuration condition of the RRU is 100M bandwidth. Specifically, compare it in detail with the configuration information in the network planning database to rule out misjudgments caused by incorrect bandwidth configuration. Different bandwidth configurations will affect the RSSI measurement value. Further test the RRUs that meet the configuration conditions.

[0065] Check whether the RRU has uploaded alarm information, and check whether the network channel of the RRU is blocked according to the network management system.

[0066] If the average RSSI of the RRU is below -100dBm, and the RRU has alarm information or the network channel is blocked, the uplink LNA of the RRU is determined to be faulty.

[0067] (3) Detection method three: In one embodiment, fault detection of the device under test according to the fault detection mechanism and fault detection data includes: If the device under test has multiple network channels, calculate the difference in signal strength between the multiple network channels according to a preset time period. If the difference is greater than the fault threshold, it is determined that there is a signal imbalance in the indoor distribution system.

[0068] In one example, the following operation is performed on an RRU with dual channels and ≥10 CP / cell users: The RSSI values ​​of the two network channels of the RRU are extracted during busy hours using time series analysis, and the average difference between the two network channels is calculated. The busy hours can be 9:00-12:00 on weekdays or 14:00-18:00 on weekdays.

[0069] When the average difference is greater than the fault threshold, it is determined that there may be a fault or connection error in one of the dual-path systems. The fault threshold can be 8dB, and the average difference can switch between 5-15dB.

[0070] Furthermore, during fault diagnosis, a comprehensive analysis can be conducted by combining the antenna's radiation pattern and coverage area prediction model. The antenna's radiation pattern describes its radiation characteristics in different directions, while the coverage area prediction model predicts the antenna's signal coverage range in a specific environment. By combining the average difference between two channels with the antenna's radiation pattern and coverage area prediction model, the possible location and cause of the fault can be further analyzed. For example, if the RSSI value of one channel is significantly lower than that of another channel, and the radiation pattern and coverage area prediction model reveal abnormal signal attenuation in the antenna's radiation area corresponding to that channel, then it can be determined that the fault lies with that antenna or its connecting lines.

[0071] (4) Detection method four: In one embodiment, fault detection of the device under test according to the fault detection mechanism and fault detection data includes: Calculate the signal strength difference of the network channels corresponding to multiple devices under test, generate the corresponding difference distribution features based on the signal strength difference, and determine whether the similarity of the difference distribution features is higher than the similarity threshold.

[0072] In one example, when a dual-path system consists of two RRUs, the following method is used to detect whether the fault is a mismatched wiring problem: First, for the two RRUs, calculate the RSSI difference of each network channel. The RSSI difference can characterize the difference in signal strength between different network channels of the two RRUs. If the difference is large, it indicates that the signal strength of the network channels of the RRUs is significantly different, that is, there is no mismatched cable connection problem.

[0073] Construct a time series model, which includes: Record the signal strength data of each network channel of the two RRUs according to the preset time granularity. For example, collect the RSSI of the two RRUs every minute, and calculate the RSSI difference of each RRU at each time node, denoted as ΔS1(t) and ΔS2(t).

[0074] The time series model is used to align and smooth the above differences, generating the channel difference time series and corresponding change curves for each of the two RRUs, which intuitively presents the fluctuation patterns of the two over time.

[0075] To achieve quantitative judgment, time series models introduce a similarity threshold λ, which is determined in the following way: Historical channel difference time series data of RRUs of the same type in cells without cross-connection were collected. The similarity distribution of multiple normal RRUs was calculated, and the 95th percentile of the distribution was taken as the similarity threshold λ. The similarity calculation adopted the dynamic time warping algorithm that adapts to the time series morphology comparison. Combined with the Pearson correlation coefficient, the morphological overlap and trend consistency of the two change curves were comprehensively measured, and the final similarity score Sim was output.

[0076] The similarity score Sim calculated by the model is compared with the similarity threshold λ. If Sim≥λ, it indicates that the channel difference changes of the two RRUs are highly synchronized. However, in a normal scenario without cross-connection, the channel difference changes of the two RRUs are affected by independent factors such as their respective loads, signal attenuation, and environmental interference, and should exhibit random and asynchronous fluctuation characteristics. The similarity score will be significantly lower than λ. Therefore, when Sim≥λ, it can be determined that the above RRUs have a cross-connection problem, that is, the cross-pairing of the wiring harnesses causes the signal changes to be synchronized.

[0077] Furthermore, to further verify the above judgment, a comprehensive analysis was conducted combining the network topology and cell handover records. The network topology shows the connection relationships and layout between various devices in the entire indoor distribution system, while the cell handover records document the user's handover activities between different cells. By analyzing the network topology, it can be determined whether the physical connections between RRUs conform to normal cabling rules; by examining the cell handover records, it is possible to identify any abnormal handover behavior, such as frequent handovers or unreasonable handover paths. If abnormal connections are found in the network topology, and the cell handover records also show abnormalities, then it can be further confirmed that there is a mismatched cabling connection problem.

[0078] (5) Detection method five: In one embodiment, fault detection of the device under test according to the fault detection mechanism and fault detection data includes: The dynamic parameters of the signal strength of each network channel are extracted according to a preset time period, and the network channels whose dynamic parameters are not greater than the parameter threshold are marked as channel abnormalities.

[0079] In one example, if the fault detection of the device under test includes channel anomaly detection: From the cleaned fault detection data, select RRUs with ≥10 CP users to ensure that there is enough user service data to reflect the true working status of the channel. Use a sliding window algorithm to calculate the RSSI change amplitude for each RRU. For example, set a 2-hour time window and continuously detect RSSI fluctuations within the time window to calculate the RSSI change amplitude during that time period.

[0080] The judgment is based on the calculated RSSI change range. If the RSSI change range of a certain RRU network channel is lower than the parameter threshold, the network channel is marked as channel abnormal, that is, a load channel.

[0081] It should be noted that the above embodiments can be combined during the fault detection process to achieve more comprehensive fault detection. In one embodiment, fault detection of the device under test according to the fault detection mechanism and fault detection data includes: In one embodiment, fault detection of the device under test according to the fault detection mechanism and fault detection data includes: The dynamic parameters of the signal strength of each network channel are extracted according to a preset time period, and it is determined whether the dynamic parameters of the signal strength are greater than the parameter threshold. If not, mark the network channel corresponding to the dynamic parameter as a channel abnormality; If so, calculate the difference in signal strength of each network channel according to the preset time period. If the difference is greater than the fault threshold, it is determined that there is a signal imbalance in the indoor distribution system. If the difference is not greater than the fault threshold, the fault detection data is input into the detection model to perform coupled fault detection on the device under test, and the detection result of coupled fault detection is output.

[0082] In one example, if the device under test is an RRU, its fault detection mechanism includes channel anomaly detection, signal imbalance detection, and coupling fault detection. The specific detection process is as follows: The preset time period is 1 minute. The sliding window algorithm is used to calculate the RSSI dynamic parameters of each network channel of each RRU. If the dynamic parameter is lower than the parameter threshold, the network channel is marked as a channel abnormal, that is, a channel under load.

[0083] If the RSSI dynamic parameters of each network channel are all greater than the parameter threshold, the difference between the average RSSI values ​​of the two channels is calculated at a time period of 1 minute. For example, if the average RSSI value of channel 1 is -75dBm and the average RSSI value of channel 2 is -71dBm, the difference between the two is 4dBm. If this difference is greater than the fault threshold, it indicates that the signal fluctuations of the two network channels are not synchronized, and it is determined that there is a signal imbalance in the indoor distribution system.

[0084] If the difference is not greater than the fault threshold, the fault detection data of the RRU is input into the coupled fault detection model.

[0085] The model performs low-dimensional transformation on the fault detection data through an encoder, extracts coupled fault features through a feature extraction network, and finally outputs the results through a detection network. If the result indicates the presence of a coupled fault, the RRU is determined to have a hardware coupling anomaly; if the result indicates the absence of a coupled fault, the RRU is determined to be operating normally.

[0086] In summary, firstly, the device network data of the communication equipment and the terminal communication data of the network access terminals of the indoor distribution system are acquired; then, the device network data and terminal communication data are cleaned and processed to obtain basic detection data; next, the device to be tested in the communication equipment is determined according to the detection device type in the basic detection data, and fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the detection device type; finally, fault detection is performed on the device to be tested according to the fault detection mechanism and the fault detection data. As can be seen from this embodiment, in situations where indoor distributed antenna system (DAS) communication equipment is diverse, data sources are complex, and the fault characteristics of different types of communication equipment vary significantly, this embodiment obtains device network data and terminal communication data from network access terminals of the indoor DAS communication equipment. The device network data and terminal communication data are then cleaned and processed to obtain basic detection data. The device type corresponding to the basic detection data is used to determine the device to be tested and the matching fault detection mechanism, thereby achieving precise adaptation between the fault detection mechanism and the device type. Furthermore, fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the device type, and fault detection is performed on the device to be tested according to the fault detection mechanism and fault detection data. This allows the fault detection process to adapt to the fault detection logic of the indoor DAS, providing accurate basis for fault determination of different types of communication equipment and improving the accuracy and efficiency of fault detection in the indoor DAS.

[0087] Figure 2 This is a schematic diagram of the structure of a fault detection device for an indoor distribution system provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, the device includes: The data acquisition unit 202 is used to acquire the device network data of the communication equipment of the indoor distribution system and the terminal communication data of the network access terminal; The cleaning unit 204 is used to clean and process the equipment network data and terminal communication data and obtain basic detection data. Data extraction unit 206 is used to determine the device to be tested in the communication equipment based on the detection equipment type of the detection basic data, and extract fault detection data from the detection basic data based on the fault detection mechanism corresponding to the detection equipment type. The fault detection unit 208 is used to perform fault detection on the equipment to be tested according to the fault detection mechanism and fault detection data.

[0088] An embodiment of this disclosure provides a fault detection device for an indoor distribution system that can implement the various processes in the aforementioned method embodiments and achieve the same functions and effects, which will not be repeated here.

[0089] Furthermore, one embodiment of this disclosure also provides an electronic device, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, such as... Figure 3 As shown, the device includes: a memory 301, a processor 302, a bus 303, and a communication interface 304. The memory 301, the processor 302, and the communication interface 304 communicate via the bus 303. The communication interface 304 may include input / output interfaces, including but not limited to a keyboard, mouse, monitor, microphone, and loudspeaker.

[0090] Figure 3 In the memory 301, computer-executable instructions that can run on the processor 302 are stored. When the processor 302 executes the computer-executable instructions, the following process is implemented: Acquire device network data of the communication equipment in the indoor distribution system and terminal communication data of the network access terminal; Clean and process the equipment network data and terminal communication data to obtain basic detection data; Based on the detection equipment type in the detection basic data, the device to be tested in the communication equipment is determined, and fault detection data is extracted from the detection basic data based on the fault detection mechanism corresponding to the detection equipment type. Fault detection is performed on the equipment to be tested according to the fault detection mechanism and fault detection data.

[0091] In this embodiment, firstly, the device network data of the communication equipment of the indoor distribution system and the terminal communication data of the network access terminal are acquired; then, the device network data and terminal communication data are cleaned and processed to obtain basic detection data; next, the device to be tested in the communication equipment is determined according to the detection device type in the basic detection data, and fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the detection device type; finally, fault detection is performed on the device to be tested according to the fault detection mechanism and the fault detection data. As can be seen from this embodiment, in situations where indoor distributed antenna system (DAS) communication equipment is diverse, data sources are complex, and the fault characteristics of different types of communication equipment vary significantly, this embodiment obtains device network data and terminal communication data from network access terminals of the indoor DAS communication equipment. The device network data and terminal communication data are then cleaned and processed to obtain basic detection data. The device type corresponding to the basic detection data is used to determine the device to be tested and the matching fault detection mechanism, thereby achieving precise adaptation between the fault detection mechanism and the device type. Furthermore, fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the device type, and fault detection is performed on the device to be tested according to the fault detection mechanism and fault detection data. This allows the fault detection process to adapt to the fault detection logic of the indoor DAS, providing accurate basis for fault determination of different types of communication equipment and improving the accuracy and efficiency of fault detection in the indoor DAS.

[0092] An electronic device provided in one embodiment of this disclosure can implement the various processes in the foregoing method embodiments and achieve the same functions and effects, which will not be repeated here.

[0093] Another embodiment of this disclosure also provides a computer-readable storage medium for storing computer-executable instructions that, when executed by a processor, implement the following process: Acquire device network data of the communication equipment in the indoor distribution system and terminal communication data of the network access terminal; Clean and process the equipment network data and terminal communication data to obtain basic detection data; Based on the detection equipment type in the detection basic data, the device to be tested in the communication equipment is determined, and fault detection data is extracted from the detection basic data based on the fault detection mechanism corresponding to the detection equipment type. Fault detection is performed on the equipment to be tested according to the fault detection mechanism and fault detection data.

[0094] In this embodiment, firstly, the device network data of the communication equipment of the indoor distribution system and the terminal communication data of the network access terminal are acquired; then, the device network data and terminal communication data are cleaned and processed to obtain basic detection data; next, the device to be tested in the communication equipment is determined according to the detection device type in the basic detection data, and fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the detection device type; finally, fault detection is performed on the device to be tested according to the fault detection mechanism and the fault detection data. As can be seen from this embodiment, in situations where indoor distributed antenna system (DAS) communication equipment is diverse, data sources are complex, and the fault characteristics of different types of communication equipment vary significantly, this embodiment obtains device network data and terminal communication data from network access terminals of the indoor DAS communication equipment. The device network data and terminal communication data are then cleaned and processed to obtain basic detection data. The device type corresponding to the basic detection data is used to determine the device to be tested and the matching fault detection mechanism, thereby achieving precise adaptation between the fault detection mechanism and the device type. Furthermore, fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the device type, and fault detection is performed on the device to be tested according to the fault detection mechanism and fault detection data. This allows the fault detection process to adapt to the fault detection logic of the indoor DAS, providing accurate basis for fault determination of different types of communication equipment and improving the accuracy and efficiency of fault detection in the indoor DAS.

[0095] The computer-readable storage medium includes read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc.

[0096] The computer-readable storage medium provided in one embodiment of this disclosure can implement the various processes in the foregoing method embodiments and achieve the same functions and effects, which will not be repeated here.

[0097] Another embodiment of this disclosure also provides a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the following process: Acquire device network data of the communication equipment in the indoor distribution system and terminal communication data of the network access terminal; Clean and process the equipment network data and terminal communication data to obtain basic detection data; Based on the detection equipment type in the detection basic data, the device to be tested in the communication equipment is determined, and fault detection data is extracted from the detection basic data based on the fault detection mechanism corresponding to the detection equipment type. Fault detection is performed on the equipment to be tested according to the fault detection mechanism and fault detection data.

[0098] In this embodiment, firstly, the device network data of the communication equipment of the indoor distribution system and the terminal communication data of the network access terminal are acquired; then, the device network data and terminal communication data are cleaned and processed to obtain basic detection data; next, the device to be tested in the communication equipment is determined according to the detection device type in the basic detection data, and fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the detection device type; finally, fault detection is performed on the device to be tested according to the fault detection mechanism and the fault detection data. As can be seen from this embodiment, in situations where indoor distributed antenna system (DAS) communication equipment is diverse, data sources are complex, and the fault characteristics of different types of communication equipment vary significantly, this embodiment obtains device network data and terminal communication data from network access terminals of the indoor DAS communication equipment. The device network data and terminal communication data are then cleaned and processed to obtain basic detection data. The device type corresponding to the basic detection data is used to determine the device to be tested and the matching fault detection mechanism, thereby achieving precise adaptation between the fault detection mechanism and the device type. Furthermore, fault detection data is extracted from the basic detection data based on the fault detection mechanism corresponding to the device type, and fault detection is performed on the device to be tested according to the fault detection mechanism and fault detection data. This allows the fault detection process to adapt to the fault detection logic of the indoor DAS, providing accurate basis for fault determination of different types of communication equipment and improving the accuracy and efficiency of fault detection in the indoor DAS.

[0099] The computer program product in this embodiment can implement the various processes of the above-described indoor distribution system fault detection and processing method embodiment, and achieve the same effect and function, which will not be repeated here.

[0100] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] Memory may include non-persistent storage in computer-readable storage media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable storage media.

[0106] Computer-readable storage media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0108] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A fault detection method for an indoor distribution system, characterized in that, include: Acquire device network data of the communication equipment in the indoor distribution system and terminal communication data of the network access terminal; The device network data and the terminal communication data are cleaned and processed to obtain basic detection data; Based on the detection device type of the detection basic data, determine the device to be tested in the communication equipment, and extract fault detection data from the detection basic data based on the fault detection mechanism corresponding to the detection device type. The fault detection is performed on the device under test according to the fault detection mechanism and the fault detection data.

2. The method according to claim 1, characterized in that, The acquisition of device network data of the communication equipment and terminal communication data of the network access terminal of the indoor distribution system includes: The signal strength and device status parameters of each network channel of the communication device are obtained according to a preset period, and the network configuration information of the indoor distribution system is read from the network management system; the device network data includes the signal strength, the device status parameters and the network configuration information; Receive terminal communication data uploaded by the network access terminal that has established a communication connection with the indoor distribution system.

3. The method according to claim 2, characterized in that, The step of cleaning and processing the device network data and the terminal communication data to obtain basic detection data includes: Based on the device status parameters, the network configuration information, and the terminal communication data, the validity of the device network data is verified. Based on the verification result, invalid data in the device network data is deleted and the target device network data is obtained. The integrity of the terminal communication data is verified by a data verification algorithm, the terminal communication data with abnormal verification is cleaned, outlier detection is performed on the cleaned terminal communication data and outlier data is deleted, and the target terminal communication data is obtained. The basic detection data includes the target device network data and the target terminal communication data.

4. The method according to claim 1, characterized in that, The step of performing fault detection on the device under test according to the fault detection mechanism and the fault detection data includes: The fault detection data is input into the detection model that performs coupled fault detection to detect coupled faults in the device under test, and the detection result of the coupled fault detection is output. The coupling fault detection includes: The fault detection data is input into the encoder for encoding processing to obtain fault code data; The fault coding data is input into a feature extraction network for extraction to obtain fault features; The fault features are coupled to detect faults using a detection network, and the coupled fault detection results are obtained.

5. The method according to claim 2, characterized in that, The step of performing fault detection on the device under test according to the fault detection mechanism and the fault detection data further includes: The signal strength of each network channel is extracted according to a preset data format, and target communication devices with signal strength lower than the strength threshold are selected from the devices to be detected. Verify whether the target communication device meets the configuration conditions. If the target communication device reports an alarm and its network channel is blocked, it is determined that the uplink network channel of the target communication device is faulty.

6. The method according to claim 1, characterized in that, The step of performing fault detection on the device under test according to the fault detection mechanism and the fault detection data includes: If the device under test has multiple network channels, the difference in signal strength of the multiple network channels is calculated according to a preset time period. If the difference is greater than the fault threshold, it is determined that there is a signal imbalance in the indoor distribution system.

7. The method according to claim 6, characterized in that, The step of performing fault detection on the device under test according to the fault detection mechanism and the fault detection data further includes: Calculate the signal strength difference of the network channels corresponding to multiple devices to be detected, generate corresponding difference distribution features based on the signal strength difference, and determine whether the similarity of the difference distribution features is higher than the similarity threshold. When the similarity threshold is higher than the threshold, query the network configuration information of the device to be detected to see if there is an abnormal state. If so, determine that the wiring harness pairing of the indoor distribution system is abnormal.

8. The method according to claim 2, characterized in that, The step of performing fault detection on the device under test according to the fault detection mechanism and the fault detection data includes: Dynamic parameters of the signal strength of each network channel are extracted according to a preset time period, and network channels whose dynamic parameters are not greater than a parameter threshold are marked as channel abnormalities.

9. The method according to claim 2, characterized in that, The step of performing fault detection on the device under test according to the fault detection mechanism and the fault detection data includes: The dynamic parameters of the signal strength of each network channel are extracted according to a preset time period, and it is determined whether the dynamic parameters of the signal strength are greater than the parameter threshold. If not, mark the network channel corresponding to the dynamic parameter as a channel abnormality; If so, calculate the difference in signal strength of each network channel according to the preset time period. If the difference is greater than the fault threshold, it is determined that there is a signal imbalance in the indoor distribution system. If the difference is not greater than the fault threshold, the fault detection data is input into the detection model for coupled fault detection to perform coupled fault detection on the device under test, and the detection result of the coupled fault detection is output.

10. A fault detection device for an indoor distribution system, characterized in that, include: The data acquisition unit is used to acquire the device network data of the communication equipment of the indoor distribution system and the terminal communication data of the network access terminal. A cleaning and processing unit is used to clean and process the device network data and the terminal communication data to obtain basic detection data. The data extraction unit is used to determine the device to be tested in the communication device according to the detection device type of the detection basic data, and extract fault detection data from the detection basic data based on the fault detection mechanism corresponding to the detection device type. The fault detection unit is used to perform fault detection on the device under test according to the fault detection mechanism and the fault detection data.

11. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory stores computer-executable instructions that, when executed on the processor, implement the method described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed by a processor, implement the method described in any one of claims 1-9.

13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-9.

Images