Passive intermodulation interference avoidance method, device, equipment, medium and program product

Abstract

The application relates to the technical field of communication, and provides a passive intermodulation interference avoidance method, device, equipment, storage medium and program product, the method comprising the following steps: acquiring intermodulation interference feature data of a to-be-optimized cell in each time period of a preset time length and inputting the intermodulation interference feature data into a pre-trained interference identification model to identify a disturbed cell; determining an uplink resource scheduling range according to downlink physical resource block utilization of the disturbed cell, and using the uplink resource scheduling range to modify the configuration of a network device of the disturbed cell, so that the disturbed cell avoids the interference of passive intermodulation signals. The disturbed cell is identified through the intermodulation interference feature data of the to-be-optimized cell, the uplink resource scheduling range is determined according to the downlink physical resource block utilization, the configuration of the network device of the disturbed cell is used, the disturbed cell avoids the interference of passive intermodulation signals, the uplink user random access process is effectively guaranteed, the downlink resource utilization rate is maximized, and resource waste is reduced.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a passive intermodulation interference avoidance method, apparatus, device, storage medium and program product. Background Technology

[0002] Due to factors such as uneven or rough metal surfaces, substandard connectors, gold plating processes, and changes in ambient temperature, antenna feeder systems can exhibit nonlinear behavior. When broadband or multi-frequency carrier signals pass through the antenna feeder system, additional PIM (Passive Intermodulation) signals are generated. If the PIM signal falls within the uplink frequency domain of a cell, it will interfere with the channel of that cell, which is called PIM interference.

[0003] Currently, among the methods for suppressing or avoiding PIM interference, one approach involves obtaining a time-domain estimate based on the relationship between the PIM interference signal in the uplink received signal and M downlink signals. This estimate is then used to calculate a cancellation signal to counteract the PIM interference, thereby reducing the impact of the PIM component on the uplink carrier. However, this method is insufficient in suppressing the PIM component. Therefore, a method has emerged that involves joint scheduling of uplink and downlink resources to avoid passive intermodulation interference (PIM interference). Specifically, by identifying the overlapping frequencies between the uplink carrier frequency band and the passive intermodulation PIM interference, a first and second interference frequency band are determined. Then, a first available frequency band in the first downlink carrier f1 and a second available frequency band in the second downlink carrier f2 are determined. Network equipment can allocate downlink resources based on the interference frequency bands in the downlink carriers, ensuring that it does not affect the reception of uplink signals. This method only involves scheduling downlink resources and does not consider the impact of the uplink random access process on user perception. Furthermore, the existence of unschedulable frequency bands in the downlink channel can easily lead to resource waste. Summary of the Invention

[0004] This application provides a passive intermodulation interference avoidance method, apparatus, device, storage medium, and program product to solve the defect in the prior art where the avoidance of passive intermodulation interference results in an unschedulable range of the downlink channel, which easily leads to resource waste.

[0005] This application provides a passive intermodulation interference avoidance method, including: Acquire intermodulation interference characteristic data of the cell to be optimized in each time period of a preset duration; The intermodulation interference feature data is input into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The uplink resource scheduling range is determined based on the downlink physical resource block utilization rate of the affected cell; Based on the uplink resource scheduling range, the configuration of the network equipment of the interfered cell is modified so that the interfered cell can avoid interference from passive intermodulation signals.

[0006] In one embodiment, inputting the intermodulation interference feature data into a pre-trained interference identification model to identify the interfered cells in the cell to be optimized includes: The intermodulation interference feature data is input into a pre-trained interference recognition model, and the interference recognition model is used to match the intermodulation interference data with the interference feature sample data to obtain the matching degree between the intermodulation interference data and the interference feature sample data. The interfered cells in the cells to be optimized are identified based on the matching degree.

[0007] In one embodiment, the intermodulation interference characteristic data includes downlink physical resource block utilization and interference characteristic coefficients of passive intermodulation signals; obtaining the intermodulation interference characteristic data of the cell to be optimized in each time period of a preset duration includes: obtaining the performance data of the cell to be optimized in each time period of a preset duration, and determining the interference rise difference of the disturbed interval of the cell to be optimized and the downlink physical resource block utilization of the cell to be optimized based on the performance data. The interference characteristic coefficients of the passive intermodulation signal of the cell to be optimized are calculated based on the interference rise difference.

[0008] In one embodiment, determining the interference rise difference of the disturbed interval of the cell to be optimized based on the performance data includes: The interference values ​​of each resource block in the cell to be optimized are determined based on the performance data, and the number of target resource blocks is counted. The target resource block is a resource block whose interference value continuously increases and is greater than a preset interference threshold. The mean interference value of the cell to be optimized is calculated based on the number of target resource blocks and the interference value of each target resource block; the difference between the mean interference value and the interference threshold value is calculated to obtain the interference rise difference of the disturbed interval of the cell to be optimized; wherein, the interference characteristic coefficient is the product of the interference rise difference and the number of target resource blocks.

[0009] In one embodiment, determining the interference value of each resource block of the cell to be optimized based on the performance data includes: The first level value of the frequency domain noise floor power of each resource block in the cell to be optimized is determined based on the performance data. The first level value is converted into a power value, and the arithmetic mean of the power values ​​is calculated; The arithmetic average value is converted into a second level value to obtain the interference value of the resource block.

[0010] In one embodiment, before inputting the intermodulation interference feature data into a pre-trained interference identification model to identify the interfered cells in the cell to be optimized, the method further includes: Obtain historical performance data of known interfered cells, and calculate interference characteristic sample data of the known interfered cells in each time period of the preset duration based on the historical performance data; The interference identification model is constructed based on the interference feature sample data.

[0011] This application embodiment also provides a passive intermodulation interference avoidance device, including: The feature extraction module is used to obtain intermodulation interference feature data of the cell to be optimized in each time period of a preset duration; An interference identification module is used to input the intermodulation interference feature data into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The scheduling range determination module is used to determine the uplink resource scheduling range based on the downlink physical resource block utilization rate of the interfered cell; An interference avoidance module is used to modify the configuration of the network devices of the affected cell based on the uplink resource scheduling range, so that the affected cell can avoid interference from passive intermodulation signals.

[0012] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the passive intermodulation interference avoidance method described above.

[0013] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the passive intermodulation interference avoidance method described above.

[0014] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the passive intermodulation interference avoidance methods described above.

[0015] The passive intermodulation interference avoidance method, apparatus, device, storage medium, and program product provided in this application embodiment acquire intermodulation interference characteristic data of the cell to be optimized, identify the interfered cell using an interference identification model, determine the uplink resource scheduling range based on the downlink physical resource block utilization rate of the interfered cell, and modify the configuration of network devices within the uplink resource scheduling range. This enables the interfered cell to avoid interference from passive intermodulation signals. Furthermore, it achieves reasonable configuration of control channels and service channels, effectively ensuring the uplink user random access process while maximizing downlink resource utilization and reducing resource waste. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the passive intermodulation interference avoidance method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the passive intermodulation interference avoidance process provided in the embodiments of this application; Figure 3 This is a schematic diagram of the passive intermodulation interference avoidance device provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] According to the principle of PIM intermodulation interference, since the downlink channel subcarrier scheduling range is strongly correlated with the cell traffic volume, the larger the traffic volume, the more positively correlated the range and intensity of uplink channel interference. In other words, uplink channel PIM intermodulation interference exhibits time-varying characteristics that change with traffic volume. To avoid PIM intermodulation interference from a resource scheduling perspective, it is necessary to predict a reasonable resource scheduling range for the uplink channel based on traffic volume. However, given the time-varying characteristics of PIM intermodulation interference, frequent resource scheduling requires base stations to reconfigure cells, which may be counterproductive and further reduce user experience.

[0020] Based on this, this application provides a passive intermodulation interference avoidance method to avoid interference from uplink passive intermodulation (PIM) signals, which is particularly suitable for 5G narrow-bandwidth cells, such as 700M cells. Taking a 700M cell as an example, according to the PIM intermodulation interference principle, the third-order PIM components of the 700M downlink channel (758-798) carrier, calculated according to the maximum allocation, are 2f1-f2 = 718 and 2f2-f1 = 838. Among them, the third-order intermodulation component 2f1-f2 falls within the uplink channel (703-743), resulting in a maximum uplink interference range of 25M. At this time, the starting RB (Resource Block) of the uplink interference interval is PRB74 (PRB stands for Physical Resource Block), that is, the range of the interfered RB is PRB74-PRB159 (bandwidth 30M), or PRB74-PRB215 (bandwidth 40M). If the downlink channel scheduling range is narrowed to 771–798, the third-order intermodulation components 2f1–f2 fall at 744. The uplink channel will not be affected, but the downlink channel has a 12M unschedulable range, resulting in resource waste and impacting the downlink rate and user experience of the 700M interfered cell. The passive intermodulation interference avoidance method provided in this application can effectively protect user experience and maximize downlink traffic while avoiding uplink PIM intermodulation interference.

[0021] Specifically, Figure 1 This is a flowchart illustrating the passive intermodulation interference avoidance method provided in the embodiments of this application, as follows: Figure 1 As shown, the method includes the following steps: Step 100: Obtain intermodulation interference characteristic data of the cell to be optimized in each time period of a preset duration; Step 200: Input the intermodulation interference feature data into the pre-trained interference identification model to identify the interfered cells in the cells to be optimized; Step 300: Determine the uplink resource scheduling range based on the downlink physical resource block utilization rate of the affected cell; Step 400: Modify the configuration of the network equipment of the interfered cell based on the uplink resource scheduling range, so that the interfered cell can avoid interference from passive intermodulation signals.

[0022] First, intermodulation interference characteristic data of the cell to be optimized is obtained in each time period of a preset duration. Optionally, the cell to be optimized includes one or more cells. For the same cell to be optimized, the intermodulation interference characteristic data is obtained in one or more time periods of a preset duration. The multiple time periods can be continuous or discontinuous.

[0023] In one embodiment, for multiple consecutive time periods of a preset duration, intermodulation interference (IMI) characteristic data of the cell to be optimized can be obtained by real-time monitoring of the cell. Then, the obtained IIM characteristic data can be divided according to the preset duration to obtain IIM characteristic data for multiple consecutive time periods. For example, taking a preset duration of 15 minutes as an example, IIM characteristic data of the cell to be optimized for the entire day is collected. Then, the IIM characteristic data of the cell to be optimized for the entire day is divided according to a 15-minute granularity to obtain IIM characteristic data of the cell to be optimized for each 15-minute period throughout the day.

[0024] In another embodiment, for multiple discontinuous time periods of a preset duration, intermodulation interference (IMI) characteristic data of the cell to be optimized within the same time period can be collected at the same time granularity. For example, at a daily granularity, IIM characteristic data of the cell to be optimized within the same time period can be collected daily. Alternatively, for multiple discontinuous time periods of a preset duration, IIM characteristic data of the cell to be optimized within the preset duration can be collected at every interval period, thus obtaining the IIM characteristic data of the cell to be optimized within multiple discontinuous time periods of the preset duration. The duration of the interval period corresponding to the multiple discontinuous time periods can be the same as or different from the preset duration; there is no limitation on this.

[0025] Furthermore, the acquired intermodulation interference feature data of the cells to be optimized are input into a pre-trained interference identification model to identify the interfered cells among the cells to be optimized. Optionally, the interfered cells include one or more, and the degree of interference of different interfered cells can be the same or different, depending on the intermodulation interference feature data of each interfered cell. The interference identification model is obtained by iteratively training a preset basic identification model based on a constructed sample dataset, and the sample dataset is constructed based on the historical intermodulation interference feature data of known interfered cells.

[0026] For affected cells, the uplink resource scheduling range is determined based on their downlink physical resource block (PRB) utilization. Within this range, the network device configuration of the affected cell is modified to help it avoid passive intermodulation (PIM) interference. After modifying the network device configuration, the network devices execute scheduling strategies to rationally schedule uplink resources. This involves appropriately configuring control and service channels to avoid uplink PIM intermodulation interference in the cell to be optimized, while effectively maximizing user experience and downlink traffic and reducing resource waste.

[0027] In this embodiment, by acquiring the intermodulation interference characteristic data of the cell to be optimized and using the interference identification model to identify the interfered cell, the uplink resource scheduling range is determined based on the downlink physical resource block utilization rate of the interfered cell. Modifying the configuration of network devices within the uplink resource scheduling range enables the interfered cell to avoid interference from passive intermodulation signals. Furthermore, it achieves reasonable configuration of control channels and service channels, effectively ensuring the uplink user random access process while maximizing downlink resource utilization and reducing resource waste.

[0028] In one embodiment, the interference identification model performs feature matching between the cell to be optimized and known interfered cells to identify the interfered cells. Specifically, in step 200, the intermodulation interference feature data of the acquired cell to be optimized is input into a pre-trained interference identification model to identify the interfered cells in the cell to be optimized. This may include: step 210, inputting the intermodulation interference feature data into the pre-trained interference identification model, and using the interference identification model to match the intermodulation interference data with interference feature sample data to obtain the matching degree between the intermodulation interference data and the interference feature sample data; Step 220: Identify the interfered cells in the cells to be optimized based on the matching degree.

[0029] The intermodulation interference feature data of the cell to be optimized is input into the pre-trained interference identification model. The interference identification model is used to match the intermodulation interference feature data of the cell to be optimized with the interference feature sample data to obtain the matching degree between the intermodulation interference feature data and the interference feature sample data. Based on the matching degree, the interfered cells in the cell to be optimized are identified.

[0030] Optionally, the interference feature sample data is the intermodulation interference feature data of known interfered cells. The interference feature sample data includes the intermodulation interference feature data of multiple known interfered cells. The matching degree between the intermodulation interference feature data of the cell to be optimized and the interference feature sample data can be determined based on the matching degree with the intermodulation interference feature data of each known interfered cell.

[0031] Optionally, the intermodulation interference feature data of the cell to be optimized is matched with the intermodulation interference feature data of each known interfered cell in the interference feature sample data, and the known interfered cell with the highest matching degree with the intermodulation interference feature data of the cell to be optimized is selected. If the matching degree between the intermodulation interference feature data of the cell to be optimized and the known interfered cell exceeds a preset threshold, then the cell to be optimized is the interfered cell.

[0032] Optionally, the intermodulation interference feature data of the cell to be optimized is matched with the intermodulation interference feature data of each known interfered cell in the interference feature sample data. Known interfered cells with a matching degree greater than a preset threshold are selected. If the proportion of the selected known interfered cells is greater than the ratio, then the cell to be optimized is an interfered cell.

[0033] In one embodiment, the intermodulation interference characteristic data of the cell to be optimized includes downlink physical resource block utilization and interference characteristic coefficients, where downlink physical resource block utilization is the downlink PRB utilization rate. Based on this, step 100 involves acquiring the intermodulation interference characteristic data of the cell to be optimized within various time periods of a preset duration, including: Step 110: Obtain the performance data of the cell to be optimized in each time period of a preset duration, and determine the interference rise difference of the disturbed interval of the cell to be optimized and the downlink physical resource block utilization rate of the cell to be optimized based on the performance data; Step 120: Calculate the interference characteristic coefficient of the passive intermodulation signal of the cell to be optimized based on the interference rise difference.

[0034] The interference characteristic coefficients in the intermodulation interference characteristic data are calculated based on the performance data of the cell to be optimized. Specifically, when acquiring the intermodulation interference characteristic data of the cell to be optimized, the performance data of the cell to be optimized in each time period of a preset duration is first acquired. This performance data includes the CGI / nCGI (Cell Global Identifier / NR Cell Global Identifier), operating frequency band, channel number of the center carrier frequency, bandwidth, average uplink interference level PRB0 of the cell RB, average downlink interference level PRB1 of the cell RB, average uplink PRB utilization, and average downlink PRB utilization of the cell to be optimized.

[0035] Furthermore, based on the performance data of the cell to be optimized, the downlink PRB utilization rate of the cell to be optimized is determined, and the interference rise difference of the disturbed interval of the cell to be optimized is determined. Based on the interference rise difference, the interference characteristic coefficient of the passive intermodulation signal of the cell to be optimized is calculated, and the intermodulation interference characteristic data of the cell to be optimized is obtained.

[0036] In one embodiment, the interference rise difference of the disturbed interval of the cell to be optimized is calculated based on the interference value of the cell's redundancy block (RB). Specifically, in step 110, determining the interference rise difference of the disturbed interval of the cell to be optimized based on the performance data of the cell to be optimized includes: Step 111: Determine the interference value of each resource block in the cell to be optimized based on the performance data, and count the number of target resource blocks; the target resource block is a resource block whose interference value continuously increases and is greater than a preset interference threshold. Step 112: Calculate the average interference of the cell to be optimized based on the number of target resource blocks and the interference value of each target resource block; Step 113: Calculate the difference between the mean interference value and the interference threshold value to obtain the interference rise difference of the disturbed interval of the cell to be optimized; wherein, the interference characteristic coefficient is the product of the interference rise difference and the number of target resource blocks.

[0037] Based on the performance data of the cell to be optimized, the interference values ​​of each redundancy block (RB) in the cell are determined, and the number of target RBs is counted. Target RBs are those whose interference values ​​continuously increase and exceed a preset interference threshold. Based on the number of target RBs and the interference values ​​of each target RB, the mean interference of the cell to be optimized is calculated. This mean interference is the ratio of the sum of the interference values ​​of all target RBs to the number of target RBs.

[0038] Based on the calculated mean interference value of the cell to be optimized, the difference between the mean interference value and the interference threshold is calculated to obtain the interference rise difference of the disturbed interval of the cell to be optimized. The interference characteristic coefficient is the product of the interference rise difference and the number of target redundancies (RBs).

[0039] Furthermore, the interference value of the RB is obtained through level conversion. In step 111, the interference value of each RB in the cell to be optimized is determined based on the performance data of the cell to be optimized, including: Step 101: Determine the first level value of the frequency domain noise floor power of each resource block of the cell to be optimized based on the performance data; Step 102: Convert the first level value into a power value, and calculate the arithmetic average of the power values; Step 103: Convert the arithmetic average value into a second level value to obtain the interference value of the resource block.

[0040] Based on the performance data of the cell to be optimized, the first level value of the frequency domain noise floor power of each RB in the cell to be optimized is determined, and the first level value is converted into a power value. Then, the arithmetic mean of the power value is calculated, and the calculated arithmetic mean is converted into a second level value, which is the interference value of the RB of the cell to be optimized. This interference value is the average value of the second level value.

[0041] In one embodiment, taking 15 minutes as a preset duration as an example, the performance data of the cell to be optimized is obtained, and the intermodulation interference characteristic data of the cell to be optimized is calculated according to the 15-minute time granularity. Specifically, firstly, the level value of the frequency domain noise floor power is converted into a power value, then the arithmetic mean of the power values ​​is calculated, and then converted back into a level value to obtain the interference value of each RB of the cell to be optimized within this time period. Here, P represents the interference value of the cell to be optimized at the 15-minute time granularity, and N represents the total number of PRBs in the cell to be optimized. For example, a 700M cell with 30M bandwidth has 160 PRBs, and a 40M bandwidth has 216 PRBs. i This represents the average interference power of the i-th PRB. The interference value P is calculated as shown in Formula 1 below:

[0042] After calculating the interference value of the cell to be optimized at a time granularity of 15 minutes, the interference rise difference of the disturbed interval of the cell to be optimized is calculated. Specifically, the RB interference value P is statistically analyzed. i As i continuously increases, and the interference value P i Disturbed RB values ​​exceeding the preset interference threshold i and its quantity N j Disturbed RB i The target RB, for example, has a preset interference threshold of -105 dBm. The difference between the mean interference value of the affected area of ​​the cell to be optimized and the interference threshold of -105 dBm is calculated according to Formula 2 below, thus obtaining the interference rise difference Δ of the affected area of ​​the cell to be optimized. j :

[0043] Based on the calculated interference rise difference in the disturbed intervals of the cell to be optimized, the PIM interference characteristic coefficient of the cell to be optimized is calculated by comparing the interference rise difference in the disturbed intervals with the interference RB. i The number N j Multiplying these results in the interference characteristic coefficient X of the PIM of the cell to be optimized. j Therefore, it can be concluded that the disturbed RB i The number N j With PIM interference characteristic coefficient X j The PIM interference characteristic coefficient X is said to be positively correlated, and the stronger the perturbation of RB, the higher the value of the perturbation. j The larger.

[0044] Based on the pre-trained interference identification model, the downlink PRB utilization and interference characteristic coefficient X of the cell to be optimized are calculated. jAnalysis is performed to identify the interfered cells among the cells to be optimized. Specifically, for any cell to be optimized, after acquiring its performance data, the intermodulation interference characteristic data of the cell to be optimized, including the interfered RBs, are calculated according to a preset time granularity. i Quantity N j PIM interference characteristic coefficient X j And downstream PRB utilization rate.

[0045] Optionally, the intermodulation interference feature data corresponding to each time period are combined into a target data group. The intermodulation interference feature data of one cell to be optimized corresponds to multiple target data groups. Based on the pre-trained interference identification model, a binary method is used to identify the intermodulation interference feature coefficient X. j For both the downlink PRB utilization rate and the intermodulation interference characteristic data of the affected cells, sample data groups are selected that are closest to the values ​​in the target data group. These sample data groups are constructed based on known intermodulation interference characteristic data of the affected cells; that is, the data groups corresponding to the interference characteristic sample data. If the matching and selection results based on the characteristic values ​​of the interference characteristic coefficients and the downlink PRB utilization rate are the same sample data group M, then sample data group M is used as the matching data group for the interference identification model.

[0046] Furthermore, based on the interference identification model, all matching data groups that meet the conditions are selected and matched. The number of matching data groups corresponding to the PIM intermodulation interference feature data of the cell to be optimized is recorded. The model matching degree of the PIM intermodulation interference feature data is calculated. The model matching degree is the proportion of the number of model matching data groups in the target data group (X%). If the model matching degree of the PIM intermodulation interference feature data of the cell to be optimized reaches a preset threshold, such as 90%, it is determined that the cell to be optimized is affected by the interference of PIM intermodulation signal, and the cell to be optimized is the interfered cell.

[0047] Based on the interference identification model and the identification results of the cell to be optimized, the optimal uplink resource scheduling range for the interfered cell is determined according to the range of the affected resource blocks (RBs) when the downlink PRB utilization of the interfered cell is maximized. That is, based on the matched data groups that meet the criteria, the affected RBs corresponding to the maximum downlink PRB utilization are obtained. i Quantity N j At this point, the uplink channel is most severely disrupted. Therefore, the maximum scheduling range for the uplink channel can be obtained, i.e., the recommended scheduling range is from RB0 to N. j RB at its maximum i To date, control channels and service channels can be configured reasonably within the maximum scheduling range.

[0048] To ensure efficient uplink resource allocation in affected cells, network devices in these cells modify their configurations to implement scheduling policies, specifically by appropriately configuring control and service channels. This approach avoids uplink PIM intermodulation interference in affected cells while maximizing user experience and downlink traffic, thus minimizing resource waste.

[0049] In one embodiment, based on the time-varying characteristics of PIM intermodulation interference with traffic volume, i.e., the downlink channel subcarrier scheduling range is strongly correlated with cell traffic volume, and the larger the traffic volume, the more positively correlated the uplink channel interference range and interference intensity change. By screening the performance data of the disturbed cell at a preset time granularity, the PIM intermodulation interference characteristic coefficients are calculated and then correlated with cell traffic volume to construct a PIM intermodulation interference identification model, which serves as the interference identification model for the disturbed cell.

[0050] Specifically, refer to Figure 2 The passive intermodulation interference avoidance process shown includes the following steps before inputting the intermodulation interference feature data of the cell to be optimized into the pre-trained interference identification model: Step 201: Obtain historical performance data of known interfered cells, and calculate interference feature sample data of known interfered cells in each time period of the preset duration based on the historical performance data; Step 202: Construct the interference identification model based on the interference feature sample data.

[0051] Obtain historical performance data of known interfered cells, and calculate interference feature sample data of known interfered cells in each time period of a preset duration based on the obtained historical performance data. Construct an interference identification model for interfered cells based on the interference feature sample data.

[0052] Optionally, the method of obtaining interference characteristic sample data of known interfered cells within a preset time period based on historical performance data is the same as the method of obtaining intermodulation interference characteristic data of the cell to be optimized, and will not be described again here.

[0053] Optionally, an interference identification model can be constructed based on known interference feature sample data of the affected cells. This includes, but is not limited to, using known interference feature sample data of the affected cells as a sample dataset to iteratively train a preset basic identification model to obtain an identification model for the affected cells, which can be used to identify PIM intermodulation interference cells.

[0054] like Figure 2As shown, firstly, performance data of known disturbed cells is acquired. Then, based on a preset time granularity, intermodulation interference characteristic data of the disturbed cells is calculated as interference characteristic sample data. Based on the analysis of the interference characteristic sample data of known PIM disturbed cells, an interference identification model is constructed. After acquiring the intermodulation interference characteristic data of the cells to be optimized, it is input into the interference identification model, thereby identifying the disturbed cells in the cells to be optimized. For the disturbed cells, the optimal uplink resource scheduling range for the disturbed cells is determined based on the range of disturbed RBs when the downlink PRB utilization is maximized. Control channels and service channels are configured within this optimal resource scheduling range. Network devices execute scheduling policies by modifying configurations, rationally scheduling uplink resources within the optimal resource scheduling range.

[0055] In this embodiment, based on the time-varying characteristics of PIM intermodulation interference with traffic volume, a PIM intermodulation interference feature identification model is constructed. Correlation analysis is performed on the PIM interference feature coefficients and downlink PRB utilization of the cell to be optimized, enabling the identification of interfered cells based on PIM intermodulation interference feature data. Furthermore, based on the location of the interfered RB corresponding to the maximum downlink PRB utilization, the optimal uplink resource scheduling range is determined. Control channels and service channels are then rationally configured within this optimal resource scheduling range. This achieves uplink PIM intermodulation interference avoidance while effectively ensuring user experience and maximizing downlink traffic volume, effectively reducing resource waste.

[0056] The passive intermodulation interference avoidance device provided in the embodiments of this application is described below. The passive intermodulation interference avoidance device described below can be referred to in correspondence with the passive intermodulation interference avoidance method described above.

[0057] Reference Figure 3 The passive intermodulation interference avoidance device provided in this application embodiment includes: Feature extraction module 10 is used to obtain intermodulation interference feature data of the cell to be optimized in each time period of a preset duration; Interference identification module 20 is used to input the intermodulation interference feature data into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The scheduling range determination module 30 is used to determine the uplink resource scheduling range based on the downlink physical resource block utilization rate of the interfered cell; The interference avoidance module 40 is used to modify the configuration of the network equipment of the interfered cell based on the uplink resource scheduling range, so that the interfered cell avoids interference from passive intermodulation signals.

[0058] In one embodiment, the interference identification module 20 is further configured to: The intermodulation interference feature data is input into a pre-trained interference recognition model, and the interference recognition model is used to match the intermodulation interference data with the interference feature sample data to obtain the matching degree between the intermodulation interference data and the interference feature sample data. The interfered cells in the cells to be optimized are identified based on the matching degree.

[0059] In one embodiment, the intermodulation interference feature data includes downlink physical resource block utilization and interference feature coefficients of passive intermodulation signals; the feature extraction module 10 is further configured to: The performance data of the cell to be optimized is obtained in each time period of a preset duration, and the interference rise difference of the disturbed interval of the cell to be optimized and the downlink physical resource block utilization rate of the cell to be optimized are determined based on the performance data. The interference characteristic coefficients of the passive intermodulation signal of the cell to be optimized are calculated based on the interference rise difference.

[0060] In one embodiment, the feature extraction module 10 is further configured to: The interference values ​​of each resource block in the cell to be optimized are determined based on the performance data, and the number of target resource blocks is counted. The target resource block is a resource block whose interference value continuously increases and is greater than a preset interference threshold. The mean interference value of the cell to be optimized is calculated based on the number of target resource blocks and the interference value of each target resource block; the difference between the mean interference value and the interference threshold value is calculated to obtain the interference rise difference of the disturbed interval of the cell to be optimized; wherein, the interference characteristic coefficient is the product of the interference rise difference and the number of target resource blocks.

[0061] In one embodiment, the feature extraction module 10 is further configured to: The first level value of the frequency domain noise floor power of each resource block in the cell to be optimized is determined based on the performance data. The first level value is converted into a power value, and the arithmetic mean of the power values ​​is calculated; The arithmetic average value is converted into a second level value to obtain the interference value of the resource block.

[0062] In one embodiment, the passive intermodulation interference avoidance device further includes a model building module, used for: Obtain historical performance data of known interfered cells, and calculate interference characteristic sample data of the known interfered cells in each time period of the preset duration based on the historical performance data; The interference identification model is constructed based on the interference feature sample data.

[0063] Figure 4An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute the steps of a passive intermodulation interference avoidance method, which includes: Acquire intermodulation interference characteristic data of the cell to be optimized in each time period of a preset duration; The intermodulation interference feature data is input into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The uplink resource scheduling range is determined based on the downlink physical resource block utilization rate of the affected cell; Based on the uplink resource scheduling range, the configuration of the network equipment of the interfered cell is modified so that the interfered cell can avoid interference from passive intermodulation signals.

[0064] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0065] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to perform the steps of the passive intermodulation interference avoidance method provided in the above embodiments, the method including: Acquire intermodulation interference characteristic data of the cell to be optimized in each time period of a preset duration; The intermodulation interference feature data is input into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The uplink resource scheduling range is determined based on the downlink physical resource block utilization rate of the affected cell; Based on the uplink resource scheduling range, the configuration of the network equipment of the interfered cell is modified so that the interfered cell can avoid interference from passive intermodulation signals.

[0066] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the passive intermodulation interference avoidance method provided in the above embodiments, the method comprising: Acquire intermodulation interference characteristic data of the cell to be optimized in each time period of a preset duration; The intermodulation interference feature data is input into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The uplink resource scheduling range is determined based on the downlink physical resource block utilization rate of the affected cell; Based on the uplink resource scheduling range, the configuration of the network equipment of the interfered cell is modified so that the interfered cell can avoid interference from passive intermodulation signals.

[0067] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0068] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A passive intermodulation interference avoidance method, characterized in that, include: Acquire intermodulation interference characteristic data of the cell to be optimized in each time period of a preset duration; The intermodulation interference feature data is input into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The uplink resource scheduling range is determined based on the downlink physical resource block utilization rate of the affected cell; Based on the uplink resource scheduling range, modify the configuration of the network equipment of the interfered cell so that the interfered cell can avoid interference from passive intermodulation signals; The intermodulation interference characteristic data includes downlink physical resource block utilization and interference characteristic coefficients of passive intermodulation signals; The acquisition of intermodulation interference characteristic data of the cell to be optimized within each time period of a preset duration includes: The performance data of the cell to be optimized is obtained in each time period of a preset duration, and the interference rise difference of the disturbed interval of the cell to be optimized and the downlink physical resource block utilization rate of the cell to be optimized are determined based on the performance data. The interference characteristic coefficients of the passive intermodulation signal of the cell to be optimized are calculated based on the interference rise difference.

2. The passive intermodulation interference avoidance method according to claim 1, characterized in that, The step of inputting the intermodulation interference feature data into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized includes: The intermodulation interference feature data is input into a pre-trained interference recognition model, and the interference recognition model is used to match the intermodulation interference data with the interference feature sample data to obtain the matching degree between the intermodulation interference data and the interference feature sample data. The interfered cells in the cells to be optimized are identified based on the matching degree.

3. The passive intermodulation interference avoidance method according to claim 1, characterized in that, The step of determining the interference rise difference of the disturbed interval of the cell to be optimized based on the performance data includes: The interference values ​​of each resource block in the cell to be optimized are determined based on the performance data, and the number of target resource blocks is counted. The target resource block is a resource block whose interference value continuously increases and is greater than a preset interference threshold. The average interference value of the cell to be optimized is calculated based on the number of target resource blocks and the interference value of each target resource block. The difference between the mean interference value and the interference threshold value is calculated to obtain the interference rise difference of the disturbed interval of the cell to be optimized; wherein, the interference characteristic coefficient is the product of the interference rise difference and the number of target resource blocks.

4. The passive intermodulation interference avoidance method according to claim 3, characterized in that, The step of determining the interference value of each resource block in the cell to be optimized based on the performance data includes: The first level value of the frequency domain noise floor power of each resource block in the cell to be optimized is determined based on the performance data. The first level value is converted into a power value, and the arithmetic mean of the power values ​​is calculated; The arithmetic average value is converted into a second level value to obtain the interference value of the resource block.

5. The passive intermodulation interference avoidance method according to claim 1, characterized in that, Before inputting the intermodulation interference feature data into the pre-trained interference identification model to identify the interfered cells in the cell to be optimized, the method further includes: Obtain historical performance data of known interfered cells, and calculate interference characteristic sample data of the known interfered cells in each time period of the preset duration based on the historical performance data; The interference identification model is constructed based on the interference feature sample data.

6. A passive intermodulation interference avoidance device, characterized in that, include: The feature extraction module is used to obtain intermodulation interference feature data of the cell to be optimized in each time period of a preset duration; An interference identification module is used to input the intermodulation interference feature data into a pre-trained interference identification model to identify the interfered cells in the cells to be optimized. The scheduling range determination module is used to determine the uplink resource scheduling range based on the downlink physical resource block utilization rate of the interfered cell; An interference avoidance module is used to modify the configuration of the network devices of the affected cell based on the uplink resource scheduling range, so that the affected cell can avoid interference from passive intermodulation signals. The intermodulation interference characteristic data includes downlink physical resource block utilization and interference characteristic coefficients of passive intermodulation signals; The feature extraction module is further configured to: acquire performance data of the cell to be optimized in each time period of a preset duration, and determine the interference rise difference of the disturbed interval of the cell to be optimized and the downlink physical resource block utilization rate of the cell to be optimized based on the performance data. The interference characteristic coefficients of the passive intermodulation signal of the cell to be optimized are calculated based on the interference rise difference.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the passive intermodulation interference avoidance method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the passive intermodulation interference avoidance method as described in any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the passive intermodulation interference avoidance method as described in any one of claims 1 to 5.

Images