A method, device and equipment for processing cell traffic
Through the analysis of the community coverage area and signal strength of the cell, the preset traffic prediction model is used to make the capacity expansion and reduction decisions of the 5G network, which solves the problem of difficulty in selecting capacity expansion and reduction solutions in the existing technology, and improves network resource utilization efficiency and reduces Operation and maintenance costs.
Patent Information
- Application Number
- CN202111407626.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-24
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2041-11-24
AI Technical Summary
The existing technology cannot accurately predict and select the capacity expansion and reduction scheme for high-load cells in 5G networks, resulting in a lack of theoretical support for capacity expansion and reduction, affecting network resource utilization efficiency and operation and maintenance costs.
By determining the cell-covers area, obtaining the signal strength and predicting traffic volume of the target cell, using the preset traffic prediction model to make capacity expansion or reduction decisions, and selecting the optimal capacity expansion and reduction plan.
It realizes the prediction of the service migration of the cell when expanding and reducing capacity, improves network resource utilization efficiency, reduces operation and maintenance costs, and avoids deterioration of performance indicators.
Smart Images

Figure CN116170815B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of communication technology, and in particular to a method, device and equipment for processing cell traffic. Background Art
[0002] With the rapid growth of 5G users and business volume, and the need to clear D-band for 5G construction, the thickness of 4G network has decreased. At the same time, 4G business volume is still showing a rapid growth trend, and high-load cells are increasing. Daily network expansion and reduction has become the norm. Network element expansion is the most direct and effective way to evenly improve network carrying capacity, solve network congestion, and improve user perception; while capacity reduction is an important means to improve equipment utilization, reduce network frequency interference, reduce electricity costs, and achieve cost reduction and efficiency improvement.
[0003] At present, the expansion and reduction of capacity is mainly carried out on the cells. The cells that need to be expanded or reduced are determined according to the set thresholds by evaluating the three dimensions of PRB (Physical Resource Block) utilization, number of effective RRC (Radio Resource Control) connections and cell traffic. However, this current evaluation method only solves the problem of "which cell needs to be expanded or reduced", but cannot determine "how to choose the cell to be expanded or reduced?". Object selection is based on experience, and the effect can only be evaluated by indicators afterwards. The overall expansion and reduction work lacks theoretical support. In order to improve the accuracy of expansion and reduction and improve the efficiency of network resource utilization, innovative research is conducted on the accurate prediction of business volume before network expansion and reduction.
[0004] In current wireless network optimization, business prediction is usually used in the network planning stage. The industry has not yet predicted the effects of capacity expansion and reduction before implementation, and there is no complete set of theoretical algorithms for capacity expansion and reduction plans. There is still a theoretical gap. Summary of the invention
[0005] In view of the above problems, embodiments of the present invention are proposed to provide a method, apparatus and device for processing cell traffic that overcome the above problems or at least partially solve the above problems.
[0006] According to one aspect of an embodiment of the present invention, a method for processing cell traffic is provided, the method comprising:
[0007] Determine a total coverage area of cells including the target cell;
[0008] Acquire the signal strength of the target cell according to the measurement reports of the reference cell and the target cell in the cell co-coverage area;
[0009] Predicting the service migration of the target cell by using a preset service volume prediction model to obtain the predicted service volume of the target cell;
[0010] The target cell is expanded or reduced in capacity according to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of a cell group in an area covered by the cell.
[0011] According to another aspect of an embodiment of the present invention, a device for processing cell traffic is provided, the device comprising:
[0012] An acquisition module is used to determine a cell co-coverage area including a target cell; obtain a signal strength of the target cell according to measurement reports of a reference cell and the target cell in the cell co-coverage area; and predict the service migration of the target cell by a preset service volume prediction model to obtain a predicted service volume of the target cell;
[0013] The processing module is used to expand or reduce the capacity of the target cell according to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of the cell group in the area covered by the cell.
[0014] According to another aspect of an embodiment of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;
[0015] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned method for processing cell traffic.
[0016] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a processor to execute operations corresponding to the above-mentioned method for processing cell traffic.
[0017] According to the scheme provided by the above-mentioned embodiment of the present invention, the method for processing cell traffic volume can be carried out by determining the common coverage area of cells including the target cell; obtaining the signal strength of the target cell according to the measurement reports of the reference cell and the target cell in the common coverage area of the cells; predicting the service migration of the target cell by a preset traffic volume prediction model to obtain the predicted traffic volume of the target cell; and expanding or reducing the capacity of the target cell according to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of the cell group in the common coverage area of the cells, thereby solving the problem of no simulation prediction for capacity expansion for high loads, realizing the prediction of service migration of the cell when reducing or expanding the capacity, realizing the prediction of the traffic volume of the cell after reduction or expansion and its common coverage cell group, and then selecting the optimal reduction or expansion scheme to realize the precise investment of resources, avoid the degradation of performance indicators, improve network production efficiency, reduce operation and maintenance costs, and have strong scalability and extensibility.
[0018] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation method of the embodiment of the present invention is specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the embodiments of the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0020] Figure 1 A flow chart showing a method for processing cell traffic provided by an embodiment of the present invention is shown;
[0021] Figure 2 An algorithm flow chart of a long-term memory artificial neural network provided by an embodiment of the present invention is shown;
[0022] Figure 3 A flowchart showing a training process of a preset traffic volume prediction model provided by an embodiment of the present invention is shown;
[0023] Figure 4 A schematic diagram of a curve showing loss of training data and loss of verification data in specific embodiment 4 provided by the present invention is shown;
[0024] Figure 5 A curve diagram showing the prediction of data for the next day based on data for the past seven days in a specific embodiment 5 provided by the present invention is shown;
[0025] Figure 6 A schematic diagram of a curve showing a long-term prediction result and an actual prediction result obtained by a prediction model in a specific embodiment 5 provided by the present invention is shown;
[0026] Figure 7 A schematic diagram showing the principle of the interoperability strategy during capacity reduction in specific embodiment 6 provided by the present invention;
[0027] Figure 8 A schematic diagram showing the priority during capacity expansion in specific embodiment 7 provided by the present invention is shown;
[0028] Fig. 9 A schematic diagram showing the principle of the interoperability strategy during capacity expansion in specific embodiment 6 provided by the present invention;
[0029] Fig.10 A schematic diagram of a pilot area in a specific embodiment 8 provided by the present invention is shown;
[0030] Fig.11 A schematic diagram showing the prediction of the main service indicators of a cell in a specific embodiment 8 provided by the present invention is shown;
[0031] Fig.12 A schematic diagram showing the structure of a device for processing cell traffic provided by an embodiment of the present invention;
[0032] Fig.13 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0033] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.
[0034] Figure 1 FIG. 2 is a flow chart showing a method for processing cell traffic provided by an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:
[0035] Step 11, determining a common coverage area of cells including the target cell;
[0036] Step 12: acquiring a signal strength of the target cell according to measurement reports of the reference cell and the target cell in the cell co-coverage area;
[0037] Step 13, predicting the service migration of the target cell by using a preset service volume prediction model to obtain the predicted service volume of the target cell;
[0038] Step 14: Expand or reduce the capacity of the target cell according to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of the cell group in the area covered by the cell.
[0039] In this embodiment, the common coverage area is identified based on the measurement report and the base station working parameters, and the common coverage area is used as the basic unit for predicting the business volume evaluation. The sampling points are reallocated according to the measurement report to simulate the cell to be reduced or expanded, and then the allocated sampling points are aggregated with the common coverage area as the basic unit, so as to obtain the predicted business volume of the target cell in each reduction or expansion scheme, so as to select the optimal reduction or expansion scheme to expand or reduce the target cell; the problem of no expansion simulation prediction for high load is solved, and the business migration prediction of the cell when reducing or expanding the capacity is realized, and the business volume prediction of the cell after reduction or expansion and its common coverage cell group is realized, so as to select the optimal reduction or expansion scheme to realize the precise investment of resources, avoid the degradation of performance indicators, improve network production efficiency, reduce operation and maintenance costs, and have strong scalability and extensibility.
[0040] In an optional embodiment of the present invention, step 11 includes:
[0041] Step 111, obtaining measurement report data of multiple cells according to a preset period;
[0042] Step 112, obtaining, according to the measurement report data, reference signal transmit powers RSRP of multiple sampling points in a primary cell and its neighboring cells in multiple cells;
[0043] Step 113: Determine a common coverage area of a plurality of cells according to the RSRPs of the plurality of sampling points and a preset threshold.
[0044] In this embodiment, the cell co-coverage area is acquired by using the MRO (Measurement Report Original, measurement report file) co-coverage sector algorithm, and the cell co-coverage area is output. Optionally, measurement report data of multiple cells are collected according to a preset period, and the measurement method of the measurement report data is preferably an inter-frequency measurement. Each cell in the measurement report data includes at least one sampling point, and each sampling point in the measurement report data includes a reference signal received power RSRP (Reference Signal Received Power) of the primary cell, a reference signal received power RSRP of the adjacent cell, and a terminal identifier UE_id of the sampling point. The terminal UE corresponding to the sampling point sends the measurement report MR to the base station according to a preset period; the measurement report data of each cell calculates the proportion of the adjacent cell and the primary cell according to the reference signal received power RSRP of the primary cell or the adjacent cell and the number of sampling points within a preset threshold statistical period, and selects a preset number of cells with the highest proportion of adjacent cells as cells in the cell co-coverage area;
[0045] Here, the proportion of neighboring cells and primary cells can be calculated by the formula:
[0046]
[0047] The proportion of sampling points of the neighboring cells with a power greater than the preset power in the sampling point group is calculated by the above formula, and the proportion is compared with the preset threshold. When the proportion is greater than the preset threshold, the neighboring cell is used as a cell to be added to the cell co-coverage area;
[0048] It should be noted that, further, all cells may be divided into a plurality of co-coverage areas according to the measurement report data, and the plurality of co-coverage areas may be constructed into a co-coverage area library, which may be regularly updated according to a preset period;
[0049] When the proportion of sampling points in the measurement report data of different frequencies is less than the preset proportion value, the collection of the measurement report data is invalid. Specifically, it can be based on the formula:
[0050]
[0051] After obtaining the common coverage area of the cell in step 11 and obtaining measurement report data according to a preset period, the valid measurement report data is added to the preset traffic prediction model in step 13 for calculation to ensure that the latest measurement data report of the common coverage area is used each time a capacity reduction or expansion plan is implemented.
[0052] In a specific embodiment 1, the measurement report data of multiple cells collected according to the preset period is shown in the following table:
[0053]
[0054]
[0055] Table 1
[0056] In an optional embodiment of the present invention, step 12 includes:
[0057] Step 121, selecting any cell in the cell co-coverage area in the same frequency band as the target cell as a reference cell, and obtaining a first measurement report of the reference cell;
[0058] Step 122, obtaining a second measurement report of the target cell;
[0059] Step 123: Obtain the signal strength of the target cell according to the first measurement report and the second measurement report.
[0060] In this embodiment, a first measurement report of a reference cell and a second measurement report of a target cell are obtained to obtain a signal strength of the target cell;
[0061] Further, optionally, step 123 includes:
[0062] Step 1231: According to the first measurement report and the second measurement report, by formula:
[0063] RSRP2=RSRP1+L DIFF ; Calculate the signal strength of the target cell, where RSRP1 is the signal strength in the first measurement report of the reference cell, RSRP2 is the signal strength in the second measurement report of the target cell, L DIFF is the differential path loss between the target cell and the reference cell.
[0064] In this embodiment, the frequency point of the reference cell corresponds to the center frequency f1, the transmit power of the reference cell is W1dBm, the signal strength in the first measurement report of the reference cell is RSRP1, and the propagation loss of the reference cell is L1; the frequency point of the target cell corresponds to the center frequency f2, the transmit power of the target cell is W2dBm, the signal strength in the second measurement report of the target cell is RSRP2, the signal strength in the second measurement report of the target cell is RSRP2, and the propagation loss of the target cell is L2. Taking the reference cell as a reference, the formula RSRP2=RSRP1+L DIFF The signal strength of the target cell is calculated to be RSRP2. When in the same position, the signal strength of the reference cell can be expressed as RSRP1=W1-L1, and the signal strength of the target cell can be expressed as RSRP2=W2-L2. Further, RSRP2=RSRP1+W2-W1+L1-L2; where LDIFF is the differential path loss between the target cell and the reference cell;
[0065] It should be noted that the differential path loss L between the target cell and the reference cell is DIFF It can be calculated by taking the center frequency f1 corresponding to the frequency point of the reference cell and the center frequency f2 corresponding to the frequency point of the target cell;
[0066] In a specific embodiment 2, the Cost231-Hata propagation model is used for link budgeting:
[0067] L(dB)=46.3+33.9lgf c -13.82lgh b -a(h m )+(44.9-6.55lgh b )lg d +C m ;
[0068] Among them, f c is the operating frequency, in MHz; h b h is the effective height of the base station antenna; m is the effective height of the mobile station antenna; d (km) is the horizontal distance between the base station antenna and the mobile station antenna; a (h m ) is the effective antenna correction factor of the mobile station; C m Correction factor for large urban centers;
[0069] Specifically,
[0070]
[0071] Based on the same base station and terminal, the loss difference between different frequencies f1 and f2 is:
[0072]
[0073] The frequency points and center frequencies of this base station are shown in the following table:
[0074]
[0075]
[0076]
[0077] Table 2
[0078] As shown in Table 2, the equivalent isotropic radiated power EIRP of the transmitter = transmission power + gain + loss. When the terminal transmits at the same power, the target cell and the reference cell are under the same base station, the antenna feed gain and loss of the equipment related to the base station are the same, and the transmission power is approximately equal to the equivalent isotropic radiated power EIRP of the transmitter.
[0079] In an optional embodiment of the present invention, the preset traffic volume prediction model in step 13 is trained through the following process:
[0080] Step 131, preprocessing the data input into the prediction model to obtain preprocessed data;
[0081] Step 132, inputting at least one set of preprocessed data into the prediction model for N iterations to obtain a training result;
[0082] Step 133, verifying the training result according to at least one set of preprocessed data to obtain a verification result;
[0083] Step 134: If the verification result is within the preset result range, then when the verified training result is normal, the prediction model is determined as the preset business volume prediction model.
[0084] In this embodiment, when carrying out the capacity expansion or capacity reduction plan, it is related to the business volume of the cell, the trend of the business volume of the cell, and the time factor, etc. The time factor refers to the periodic time factors such as holidays, large-scale periodic activities, and winter and summer vacations; based on the LSTM (Long Short-Term Memory, long-term memory artificial neural network) neural algorithm, at least one set of historical data is analyzed to predict the changes in recent and periodic business volume; the LSTM neural algorithm here is an optimized recurrent neural network RNN, and the LSTM neural algorithm is used to solve the problem of gradient explosion or gradient disappearance of the recurrent neural network RNN as the training time increases and the number of network layers increases;
[0085] Figure 2 FIG. 4 shows an algorithm flow chart of a long-term memory artificial neural network provided by an embodiment of the present invention; Figure 2 As shown, Figure 2 The LSTM neural network in the algorithm is implemented through three gate control logics: forget gate, input gate, and output gate. It solves the gradient vanishing and gradient exploding problems in the long sequence training process. By using the autonomous learning function of the neural network and training at least one set of historical input data, it can achieve high-precision network capacity prediction with a long prediction cycle. At the same time, it uses the machine learning logistic regression algorithm to predict the burst type network capacity.
[0086] Figure 3FIG. 4 is a flowchart showing a training process of a preset traffic volume prediction model provided by an embodiment of the present invention; Figure 3 As shown, the training process of the preset business volume prediction model may include: data preprocessing, model building, model training and network model prediction. The model here is preferably a Keras Sequential model;
[0087] Preprocess the data input into the prediction model to obtain preprocessed data. The preprocessing here is preferably normalization preprocessing of the data. Normalization preprocessing is used to limit the data to a certain data range after processing, reduce the impact of singular sample data on the prediction results, and improve the convergence speed of the algorithm. The MinMaxScaler function is usually used in the Keras Sequential model to shrink the data to between 0 and 1;
[0088] At least one set of preprocessed data is input into the prediction model for N iterative processing to obtain a training result; if the verification result is within the preset result range, then when the verified training result is normal, the prediction model is determined as the preset business volume prediction model; the prediction model here is preferably a Keras Sequential model. In a specific embodiment 3, the Keras Sequential model is:
[0089] model=keras.models.Sequential()
[0090] model.add(LSTM(input_shape=(168,1),
[0091] units=16,
[0092] dropout=0.2,
[0093] activation=None,
[0094] stateful=False, );
[0096] Among them, input_shape indicates that the first layer of the Keras Sequential model needs to specify the input_shape parameter, and the subsequent layers do not need it. Input_shape contains two elements. The first element represents the length of each input sample sequence, and the second element represents the number of input data in one element in each sequence. It is preferred to use an indicator for 7 days and 24 hours for prediction. At this time, the parameter is set to (168,1);
[0097] Units represents the dimension of the output of this layer. If the value is greater than a certain threshold, it will lead to overfitting and need debugging. Here it is preferably set to units = 16, and the output dimension is (168, 16);
[0098] Dropout means to disable the activation of a certain proportion of neuron outputs (i.e., unit outputs). The default value is 0 to prevent overfitting. Here, the preferred setting is 0.2.
[0099] Activation indicates the type of activation function, which determines the output range of each unit calculation each time. This value does not need to change the output value range, so the activation function is not set;
[0100] Stateful indicates whether to expand. Expanding the LSTM neural network will speed up the regression calculation process, but it will take up more memory, so it is preferred to expand it on a small sequence.
[0101] Input at least one set of preprocessed data into the above prediction model for N iterative processing to obtain training results; Figure 4 Schematic diagram of curves showing loss of training data and loss of verification data in specific embodiment 4 provided by the present invention; Figure 4 As shown, in a specific embodiment 4, 7 days of hourly data are used as the training sample number for training, 1 day of data is used for verification, and after each data is sent to the network, a forward calculation and back propagation process (i.e., epoch process) is completed, and the model indicators such as loss function training data and accuracy are tested. The model is trained 100 times in a cycle, and the loss of training data and loss of verification data are as follows Figure 4 As shown;
[0102] It can be seen from the training model that after about 20 trainings, the loss of training data and the loss of validation data have been greatly reduced and stabilized below 0.005. There is no overfitting or underfitting phenomenon, and the training network is normal.
[0103] In an optional embodiment of the present invention, step 13 includes:
[0104] Step 131, predicting the utilization rate of the physical resource block PRB of the target cell by using the preset traffic volume prediction model to obtain the predicted traffic volume of the target cell.
[0105] In this embodiment, the predicted PRB utilization rate of the short-period data busy-hour service in the common coverage area is PRB short , select historical data as the evaluation period, and the maximum value of the PRB utilization prediction value during the evaluation period is PRB long , through the formula:
[0106] After obtaining the PRB utilization rate of the traffic volume, prediction processing can be performed according to the PRB utilization rate and the prediction model to obtain the predicted traffic volume of the target cell.
[0107] Figure 5 A curve diagram showing the prediction of data for the next day based on data for the past seven days in a specific embodiment 5 provided by the present invention is shown; Figure 6 FIG. 5 shows a schematic diagram of a curve of a long-term prediction result and an actual prediction result obtained by a prediction model in a specific embodiment 5 provided by the present invention; Figures 5 to 6 As shown, in a specific embodiment 5, the prediction model obtained in the specific embodiment 4 is used to obtain the prediction data for the next day based on the real data of the past 7 days and the prediction model. The real data of the past 7 days is imported into the prediction model for calculation, and the prediction data for the next day is finally output as follows: Figure 5 As shown, it can be seen that the predicted data is consistent with the real data, and the prediction accuracy is high;
[0108] Furthermore, based on the real historical data and prediction model of the past year, the PRB (Physical Resource Block) utilization rate of the data traffic in the common coverage area during the second busiest hour is selected, and the LSTM algorithm is used to predict the long-term business volume change trend to solve the sudden business fluctuations caused by periodic time factors such as holidays, winter and summer vacations, and fixed large-scale activities; Figure 6 As shown in FIG. 1 , using the downlink PRB utilization, it can be seen that the data curves of the predicted value adjusted by the prediction model and the actual value are close to each other, and the prediction accuracy of the long-period service volume is relatively high.
[0109] In an optional embodiment of the present invention, step 14 includes:
[0110] Step 141, determining a service migration object according to the signal strength of the primary serving cell and the neighboring cell and the service migration priority;
[0111] Step 142: expand or reduce the capacity of the target cell according to the predicted traffic volume of the target cell, the migration object, the utilization rate of the physical resource blocks (PRBs) of each cell in the cell group in the common coverage area of the cell, and the migration ratio.
[0112] In this embodiment, the service migration object and the signal strength of the primary serving cell, the signal strength of the neighboring cell and the priority of the service migration are used to expand or reduce the capacity of the target cell according to the predicted service volume of the target cell, the migration object, the utilization rate of the physical resource block PRB of each cell in the cell group in the cell co-coverage area and the migration ratio. The predicted service volume is obtained by the prediction model in steps 11 to 13, the migration object is obtained by the service migration priority, and the migration ratio can be obtained by the formula
[0113] Calculated, here S is the total number of sampling points in a cell in a cycle, and its PRB utilization is PRB reduce There are n neighboring cells in the total coverage area, and each neighboring cell obtains s1, s2, ..., s n-1 、s n Sampling points
[0114] After capacity reduction or expansion, the service volume of the common coverage area is equal to the original service PRB utilization rate PRB initial Add or subtract the corresponding business volume.
[0115] Figure 7 A schematic diagram showing the principle of the interoperability strategy when reducing capacity in the specific embodiment 6 provided by the present invention; Figure 7 As shown, in a specific embodiment 6, when the target cell is reduced in capacity by a preset traffic prediction model, the terminal reports a measurement report data every 5 ms, and each report data includes a terminal identifier UE_id, a signal strength RSRP of a serving cell, a signal strength RSRP of a neighboring cell, a frequency point, and an ECI (E-UTRAN Cell Identifier, a cell unique identifier), etc. Each measurement report data selects the neighboring cell with the strongest signal strength RSRP, and summarizes the valid sampling points of the full amount of the main serving cell within the preset period; when the total coverage area [Cell1, Cell2, ..., Cell M ] includes M cells, and the number of measurement report data reported in the preset period T is N, of which Cell1 is the main serving cell and there are S. The level of the neighboring cell with the strongest signal strength in each measurement report data is RSRP nb_max , all cells in the common coverage area take turns as primary cells, and other cells are used as neighboring cells, and the measurement report coverage algorithm is used to calculate until all cells in the common coverage area are used as primary serving cells.
[0116] Let F be the coverage intensity, then F is
[0117]
[0118] The main service cell is reduced in capacity, and the neighboring cell with the strongest signal strength replaces the main service cell to obtain the proportion of coverage level greater than -110dBm; here, the preferred setting F Server =95%, when the coverage intensity F Server If it is smaller, there is a risk of local weak coverage in the co-covered area after capacity reduction;
[0119] When capacity reduction is carried out, the services will be taken over by other cells in the co-coverage area. The order of taking over is determined by the existing network's inter-frequency interoperability strategy. Specifically:
[0120] (1) A3 event switching is used between different frequency points in the same frequency band to ensure that users can switch to cells with good signals in a timely manner;
[0121] (2) Between different network layers, A5 events are used from high to low layers to ensure that users in the high-priority layer stay and switch to the low-priority band only when the signal of the high-priority band is poor;
[0122] (3) Between different network layers, the A4 event is used from the low layer to the high layer. When the high-priority frequency band priority signal is normal, it is preferred to switch to the high-priority frequency band;
[0123] In addition, when the relative priority between frequency bands within the capacity layer is D band>A band>FDD1800, the event configuration is consistent with the inter-layer configuration; due to the discontinuous coverage and service bearing of A band and FDD1800, in order to reserve an escape channel for users, A band and FDD1800 to F band adopt A3 event; data services adopt interval ranges and prevent ping-pong switching, A and D do not add neighboring cells to FDD900;
[0124] It should be noted that the existing network inter-frequency interoperability strategy here is set according to the actual situation, and this application is not limited to this;
[0125] According to the above existing network inter-frequency interoperability strategy, the network level of each frequency band is formulated as follows:
[0126] 1) The priority of coverage of private network communities such as high-speed rail and subway is set to 7;
[0127] 2) The room stratification priority is set to 6, including E band, FDD1800 room stratification, etc.;
[0128] 3) The capacity layer priority is set to 5, including D, A, and FDD1800 bands;
[0129] 4) The coverage layer priority is set to 4, including the F band;
[0130] 5) The emergency blind spot priority is set to 3, including FDD900.
[0131] Furthermore, the priority of each frequency band is shown in the following table:
[0132] sequence Frequency band Capacity calculation priority Migration Threshold (dBm) 1 E 1 -98 2 D 2 -96 3 A 3 -105 4 FDD1800 4 -96 5 F 5 -105 6 FDD900 6 /
[0133] Table 3
[0134] For all sampling points of the primary service cell within the preset period, the neighboring cell with the highest priority in the measurement report data and the largest signal strength RSRP of the primary service cell is selected as the migration object; if the cell with the highest priority cannot meet the minimum coverage signal strength RSRP threshold, the neighboring cell with the second highest priority in the measurement report data and meeting the minimum coverage signal strength RSRP threshold of the frequency is selected as the migration object, and the comparison is performed in sequence until all sampling points of the cell within the preset period are all attributed to the common coverage area; if all neighboring cells of the sampling point do not meet the conditions, the sampling point is abandoned; the cells in the common coverage area are shown in the following table, there are a total of 7 cells in the common coverage area, and one of the cells is prepared to be reduced in capacity. The sampling points of the cell as the primary service cell are shown in the following table:
[0135]
[0136]
[0137] Table 4
[0138] The sampling points of the full measurement report of the common coverage area are summarized and counted to predict the service migration ratio of each common coverage area. When there are S sampling points in the preset period of the reduced capacity cell, its PRB utilization rate is PRB reduce , there are n total coverage areas. After the above calculations, each total coverage area has obtained s1, s2, ..., s n-1 、s n Sampling points The service migration ratio of the total coverage area is After the capacity reduction, the service volume of the total coverage area is the original service PRB utilization rate PRB initial The business volume after capacity reduction absorption is:
[0139] PRB absorb =PRB initial +PRB reduce ×m;
[0140] After determining the objects that are easy to migrate, the cell PRB utilization rate is used to represent the traffic volume of each cell in the co-coverage area. Due to the differences in bandwidth and standard, the calculation during migration needs to be converted and calculated through bandwidth and equivalent carrier number. The currently common equivalent carrier number is shown in the following table:
[0141]
[0142] Table 5
[0143] The PRB utilization rate of the primary service cell is RPB Server , the PRB utilization of the migration object is RPB Neighbour , the service migration ratio is m%, then the PRB utilization rate RPB of the migration object after the cell capacity reduction 迁移后 , the prediction formula is as follows:
[0144] When migrating within the same network standard (TDD (Time Division Duplexing) to TDD or FDD (Frequency Division Duplexing) to FDD):
[0145]
[0146] When migrating between different network standards (TDD to FDD or FDD to TDD):
[0147]
[0148] Figure 8 FIG. 4 is a schematic diagram showing the priority during capacity expansion in the specific embodiment 7 provided by the present invention; Figure 8 As shown, in a specific embodiment 7, when the target cell is expanded by using a preset traffic volume prediction model, its priority is as follows Figure 8 As shown, the priority of FDD900 in the emergency blind spot filling layer is 3, the priority of F band in the coverage layer is 4, the priority of D band, A band and FDD1800 in the capacity layer is 5, the priority of E band and FDD1800 (indoor) in the room layer is 6, and the priority of high-speed rail and subway in the private network layer is 7;
[0149] Fig. 9 A schematic diagram showing the principle of the interoperability strategy during capacity expansion in the specific embodiment 6 provided by the present invention is shown; it should be noted that the existing network heterogeneous frequency interoperability strategy here is set according to the actual situation, and this is not limited in the present application;
[0150] When there is a common coverage area that meets the conditions, there are a total of 5 cells in the common coverage area, F1 is the main service cell, and D1 frequency point is prepared for expansion, the D1 level strength can be calculated as RSRP F1 -1.57;
[0151]
[0152] Table 6
[0153] Table 6 shows the signal strength difference between frequency 1 and frequency 2. The process of service migration during capacity expansion is shown in the following table:
[0154]
[0155] Table 7
[0156] As shown in Table 7, through the above steps, the calculation and allocation of all sampling points can be completed, and then the total service load of all cells in the common coverage area after the sampling points are reconfigured can be calculated; and then the target cell can be expanded.
[0157] In an optional embodiment of the present invention, the method for processing cell traffic further includes:
[0158] All cells in the common coverage area are taken as target cells in turn, and the predicted traffic volume is calculated through the above steps 11 to 13, and then the capacity of the target cells is periodically expanded or reduced;
[0159] When the target cell needs to reduce capacity periodically:
[0160] According to the traffic volume and coverage of the common coverage area, if it is predicted that the common coverage area will have high traffic volume or weak coverage after capacity reduction, the cell is not suitable for capacity reduction;
[0161] All cells in the common coverage area are rotated as the main service cells, and the business volume and coverage of the common coverage area after capacity reduction are calculated. The cells that do not generate high business volume or weak coverage after capacity reduction and have the most balanced capacity are selected as the target cells for capacity reduction.
[0162] Furthermore, a traffic volume threshold is set for the co-coverage area. When the selected reduction target cell is calculated, if other co-coverage areas have not yet met the traffic volume threshold, secondary, tertiary, or multiple iterative cycle calculations can be performed based on the reduction target cell, that is, the traffic migration ratio needs to be accumulated with the previously migrated reduction cells until all cells have accumulated the predicted traffic volume calculation, or the neighboring cell traffic volume PRB utilization rate RPB 迁移后 If the predicted value exceeds the preset threshold, the migration prediction service volume is terminated and the final prediction result is output to form the final list of cells that can be reduced.
[0163] When the target cell needs to be expanded periodically:
[0164] Take cells in different frequency bands as the main service cells, calculate the traffic volume in the total coverage area after expansion, and select the cell with the most balanced capacity as the target cell for expansion.
[0165] Furthermore, a traffic volume threshold can be set for the co-covered area. When the selected expansion target cell is calculated, if other co-covered cells have not yet met the traffic volume threshold, secondary, tertiary, or multiple iterations can be performed on the basis of the expansion target cell. The proportion of services that can be migrated needs to be accumulated with the previously migrated expansion cells until the calculation of the accumulated predicted traffic volume of all cells is completed, or the PRB utilization rate RPB of the neighboring cell traffic volume is reached. 迁移后 If the predicted value exceeds the preset threshold, the migration prediction service volume is terminated and the final prediction result is output to form the final expansion cell list.
[0166] Fig.10 A schematic diagram of a pilot area in a specific embodiment 8 provided by the present invention is shown; Fig.11 FIG. 8 is a schematic diagram showing the prediction of the main service indicators of a cell in a specific embodiment 8 provided by the present invention; Fig.10 and 11 As shown, in a specific embodiment 8, in order to verify the effectiveness of the method for processing cell traffic, a certain area is used as a pilot. There are 366 physical sites in the pilot area, of which 1406 4 / 5G logical cells are located in the pilot area. Fig.10 As shown;
[0167] 1) First, enable inter-frequency measurement of measurement reports for all cells in the area, collect the measurement report file data MRO of the cells for three days, and extract the required MRO data information;
[0168] 2) According to the MRO data information of the extracted 1406 cells, the sampling point ratio of the main cell and the neighboring cells ranked in the top 10 priorities is calculated. When the sampling point ratio of the neighboring cell is greater than 10%, the main cell and the neighboring cell are classified as the same co-coverage unit, and the cluster units of all cells are calculated and divided in turn. A total of 368 co-coverage units are calculated in the pilot area. Some examples are shown in the following table:
[0169]
[0170]
[0171]
[0172] Table 8
[0173] 3) After obtaining the capacity reduction priority of each cell, the coverage of the cells is evaluated in order; 368 common coverage clusters are gathered from the 1406 cells in the pilot area, and 1134 cells suitable for capacity reduction and 372 coverage layer cells not suitable for capacity reduction are calculated by using the measurement report MR coverage prediction algorithm in the pilot area;
[0174] 4) After distinguishing the cells that can be reduced in capacity, the service load of the cells is predicted in order to make the next service migration prediction. Based on the LSTM long short-term memory neural network algorithm, the hourly KPI indicators of the cells 7 days before the prediction date are extracted for training, and the AI prediction model of the main indicators at the cell level is established. The capacity of all cells is predicted, and the hourly service model for November 27 is predicted.
[0175] 5) If Fig.11 As shown, the service migration is predicted; the service load balancing target value of the common coverage area is set (downlink PRB utilization rate of 40%), and it is calculated that after the cell is delisted, the predicted values of the service PRB utilization rates of the neighboring cells in the common coverage area do not exceed the load target value of 40%. The cell can be used as a capacity reduction cell, and other cells in the common coverage area are predicted at the same time until the service load target value is reached; finally, among the 368 common coverage areas, it is calculated that 136 cells can be reduced in capacity, and the capacity reduction ratio is 136 / 1406*100%=9.67%.
[0176] The embodiments of the present invention determine a common coverage area of cells including a target cell; obtain the signal strength of the target cell according to measurement reports of a reference cell and the target cell in the common coverage area of the cells; predict the service migration of the target cell by a preset service volume prediction model to obtain the predicted service volume of the target cell; expand or reduce the capacity of the target cell according to the signal strength of the target cell, the predicted service volume of the target cell and the service volume of the cell group in the common coverage area of the cells; solve the problem of no capacity expansion simulation prediction for high loads, realize the service migration prediction of the cell when reducing or expanding the capacity, realize the service volume prediction of the cell after reduction or expansion and its common coverage cell group, and then select the optimal capacity reduction or expansion plan to realize accurate resource investment, avoid performance indicator degradation, improve network production efficiency, reduce operation and maintenance costs, and have strong generalizability and scalability.
[0177] Fig.12 FIG. 2 is a schematic diagram showing the structure of a cell traffic processing device provided by an embodiment of the present invention. Fig.12 As shown, the device 120 includes:
[0178] The acquisition module 121 is used to determine a cell co-coverage area including a target cell; obtain the signal strength of the target cell according to the measurement reports of the reference cell and the target cell in the cell co-coverage area; predict the service migration of the target cell by a preset service volume prediction model to obtain the predicted service volume of the target cell;
[0179] The processing module 122 is used to expand or reduce the capacity of the target cell according to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of the cell group in the area covered by the cell.
[0180] Optionally, the acquisition module 121 determines the common coverage area of cells including the target cell, including:
[0181] Obtain measurement report data of multiple cells according to a preset period;
[0182] According to the measurement report data, a reference signal transmit power RSRP of multiple sampling points in a primary cell and its neighboring cells in multiple cells is obtained;
[0183] A common coverage area of the multiple cells is determined according to the RSRPs of the multiple sampling points and a preset threshold.
[0184] Optionally, the acquiring module 121 acquires the signal strength of the target cell according to the measurement reports of the reference cell and the target cell in the cell co-coverage area, including:
[0185] Selecting any cell in the cell co-coverage area in the same frequency band as the target cell as a reference cell, and obtaining a first measurement report of the reference cell;
[0186] Obtaining a second measurement report of the target cell;
[0187] The signal strength of the target cell is obtained according to the first measurement report and the second measurement report.
[0188] Optionally, obtaining the signal strength of the target cell according to the first measurement report and the second measurement report includes:
[0189] According to the first measurement report and the second measurement report, by formula:
[0190] RSRP2=RSRP1+L DIFF ; Calculate the signal strength of the target cell, where RSRP1 is the signal strength in the first measurement report of the reference cell, RSRP2 is the signal strength in the second measurement report of the target cell, L DIFF is the differential path loss between the target cell and the reference cell.
[0191] Optionally, the preset business volume prediction model is trained through the following process:
[0192] Preprocessing the data input into the prediction model to obtain preprocessed data;
[0193] Inputting at least one set of preprocessed data into the prediction model for N iterative processing to obtain a training result;
[0194] Verifying the training result according to at least one set of preprocessed data to obtain a verification result;
[0195] If the verification result is within the preset result range, then when the verified training result is normal, the prediction model is determined as the preset business volume prediction model.
[0196] Optionally, predicting the service migration of the target cell by using a preset service volume prediction model to obtain the predicted service volume of the target cell includes:
[0197] The preset traffic volume prediction model is used to predict the utilization rate of the physical resource block (PRB) of the target cell to obtain the predicted traffic volume of the target cell.
[0198] Optionally, the processing module 122 includes:
[0199] The first processing submodule is used to obtain the signal strength of the primary serving cell and the neighboring cell in the cell co-coverage area;
[0200] A second processing submodule is used to determine a service migration object according to the signal strength of the primary serving cell and the neighboring cell and the service migration priority;
[0201] The third processing submodule is used to expand or reduce the capacity of the target cell according to the predicted traffic volume of the target cell, the migration object, the utilization rate of the physical resource blocks (PRBs) of each cell in the cell group in the common coverage area of the cell, and the migration ratio.
[0202] It should be noted that the device is a device corresponding to the above-mentioned method for processing cell traffic, and all implementations of the above-mentioned method are applicable to the embodiments of the device and can achieve the same technical effects.
[0203] An embodiment of the present invention provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the method for processing cell traffic in any of the above method embodiments.
[0204] Fig.13 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention is shown, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
[0205] like Fig.13As shown, the computing device may include: a processor, a communications interface, a memory, and a communication bus.
[0206] The processor, the communication interface, and the memory communicate with each other via a communication bus. The communication interface is used to communicate with other devices such as a client or other server network elements. The processor is used to execute a program, specifically, to execute the relevant steps in the above-mentioned processing method for calculating the cell traffic volume of the device.
[0207] Specifically, the program may include program codes including computer operation instructions.
[0208] The processor may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
[0209] The memory is used to store programs. The memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.
[0210] The program can be specifically used to enable the processor to execute the cell traffic processing method in any of the above method embodiments. The specific implementation of each step in the program can refer to the corresponding descriptions in the corresponding steps and units in the above cell traffic processing method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above method embodiment, which will not be repeated here.
[0211] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language either. It should be understood that various programming languages can be utilized to realize the content of the embodiment of the present invention described herein, and the description of the above specific language is to disclose the best mode of the embodiment of the present invention.
[0212] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0213] Similarly, it should be understood that in order to streamline the embodiments of the present invention and to aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: that the claimed embodiments of the present invention require more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.
[0214] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.
[0215] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.
[0216] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The embodiments of the present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing an embodiment of the present invention may be stored on a computer-readable medium, or may have the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.
[0217] It should be noted that the above embodiments illustrate rather than limit the present invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim listing a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.
Claims
1. A method for processing cell traffic, characterized in that: The method comprises: Determine a total coverage area of cells including the target cell; Acquire the signal strength of the target cell according to the measurement reports of the reference cell and the target cell in the cell co-coverage area; Predicting the service migration of the target cell by using a preset service volume prediction model to obtain the predicted service volume of the target cell; The target cell is expanded or reduced in capacity according to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of a cell group in an area covered by the cell.
2. The method for processing cell traffic according to claim 1, characterized in that: Determine the total coverage area of the cells including the target cell, including: Obtain measurement report data of multiple cells according to a preset period; According to the measurement report data, a reference signal transmit power RSRP of multiple sampling points in a primary cell and its neighboring cells in multiple cells is obtained; A common coverage area of the multiple cells is determined according to the RSRPs of the multiple sampling points and a preset threshold.
3. The method for processing cell traffic according to claim 1, characterized in that: Acquiring the signal strength of the target cell according to the measurement reports of the reference cell and the target cell in the cell co-coverage area, including: Selecting any cell in the cell co-coverage area in the same frequency band as the target cell as a reference cell, and obtaining a first measurement report of the reference cell; Obtaining a second measurement report of the target cell; The signal strength of the target cell is obtained according to the first measurement report and the second measurement report.
4. The method for processing cell traffic according to claim 3, characterized in that: Obtaining, according to the first measurement report and the second measurement report, a signal strength of the target cell, including: According to the first measurement report and the second measurement report, by formula: RSRP2=RSRP1+L DIFF ; Calculate the signal strength of the target cell, where RSRP1 is the signal strength in the first measurement report of the reference cell, RSRP2 is the signal strength in the second measurement report of the target cell, L DIFF is the differential path loss between the target cell and the reference cell.
5. The method for processing cell traffic according to claim 1, characterized in that: The preset business volume prediction model is trained through the following process: Preprocessing the data input into the prediction model to obtain preprocessed data; Inputting at least one set of preprocessed data into the prediction model for N iterative processing to obtain a training result; Verifying the training result according to at least one set of preprocessed data to obtain a verification result; If the verification result is within the preset result range, then when the verified training result is normal, the prediction model is determined as the preset business volume prediction model.
6. The method for processing cell traffic according to claim 1, characterized in that: Predicting the service migration of the target cell by using a preset service volume prediction model to obtain the predicted service volume of the target cell includes: The preset traffic volume prediction model is used to predict the utilization rate of the physical resource block (PRB) of the target cell to obtain the predicted traffic volume of the target cell.
7. The method for processing cell traffic according to claim 1, characterized in that: According to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of the cell group in the cell co-coverage area, the target cell is expanded or reduced in capacity, including: obtaining the signal strength of the primary serving cell and the neighboring cell in the cell co-coverage area; Determine a service migration object according to the signal strength of the primary serving cell and the neighboring cell and the service migration priority; The target cell is expanded or reduced in capacity according to the predicted traffic volume of the target cell, the migration object, the utilization rate of the physical resource blocks (PRBs) of each cell in the cell group in the common coverage area of the cell, and the migration ratio.
8. A cell traffic processing device, characterized in that: The device comprises: An acquisition module is used to determine a cell co-coverage area including a target cell; obtain a signal strength of the target cell according to measurement reports of a reference cell and the target cell in the cell co-coverage area; and predict the service migration of the target cell by a preset service volume prediction model to obtain a predicted service volume of the target cell; The processing module is used to expand or reduce the capacity of the target cell according to the signal strength of the target cell, the predicted traffic volume of the target cell and the traffic volume of the cell group in the area covered by the cell.
9. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the method for processing cell traffic according to any one of claims 1-7.
10. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute an operation corresponding to the method for processing cell traffic according to any one of claims 1 to 7.
