A method and apparatus for determining an expansion scheme

Abstract

The application discloses a capacity expansion scheme determination method and device, which is used for predicting a traffic suppression point of a cell in advance, determining a capacity expansion scheme according to the traffic suppression point, and thus expanding the capacity of the cell in advance to avoid traffic suppression and congestion of the cell. The method comprises the following steps: obtaining first traffic information of at least one first cell, wherein the first traffic information comprises the change of the number of users and the used traffic in the first cell; fitting a first correlation between the number of users and the used traffic according to the first traffic information, the first cell being a cell in which a traffic suppression point has occurred; obtaining the similarity between each first cell and each second cell; determining the traffic suppression point of each second cell according to the first correlation and the similarity, the traffic suppression point comprising a point at which the traffic growth rate decreases with the increase of the number of users in the second cell; and determining a capacity expansion scheme of at least one second cell according to the traffic suppression point.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular to a method and apparatus for determining a capacity expansion scheme. Background Technology

[0002] In wireless network cells, as the number of network users and the user traffic DOU increase, the traffic carried by the wireless cell gradually increases. However, the cell network equipment may be unable to meet the growing demand for user traffic. At this time, it is necessary to expand the cell in a timely manner to support more network cell users and network traffic, so as to avoid network congestion, reduced user experience and user churn due to the inability to support more network cell users and network traffic.

[0003] Some common wireless network expansion solutions rely on real-time monitoring of wireless network equipment. When a network cell indicator exceeds a predetermined threshold, the operator determines that the wireless network cell is congested and initiates expansion. Therefore, how to expand cell capacity in a timely manner has become an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method and apparatus for determining a capacity expansion plan, which is used to predict the traffic suppression point of a cell in advance, thereby predicting the time it takes for the cell to reach the traffic suppression point, and determining the capacity expansion plan based on the time. This allows for capacity expansion based on the traffic suppression point of the cell in advance, avoiding traffic suppression and congestion in the cell, and improving the user experience.

[0005] In a first aspect, this application provides a method for determining a capacity expansion scheme, comprising: firstly, acquiring first traffic information of at least one first cell, the first traffic information including information on the changes in the number of users and traffic usage in at least one first cell; then fitting a first correlation relationship between the number of users and traffic usage based on the first traffic information, the first cell being the cell where a traffic suppression point has occurred; then acquiring the similarity between each of the at least one first cell and each of the at least one second cell; then determining the traffic suppression point of each second cell based on the first correlation relationship and the similarity, the traffic suppression point including points in the second cell where the traffic growth rate decreases as the number of users increases; and determining a capacity expansion scheme for at least one second cell based on the traffic suppression point, the capacity expansion scheme including a scheme for expanding the bandwidth of the second cell.

[0006] Therefore, in this embodiment, the correlation between the number of users and the traffic generated in the first cell where traffic suppression has occurred, as well as the similarity between cells, can be used to fit the correlation between the number of users and the traffic in the second cell where traffic suppression has not occurred. Based on this correlation, the traffic suppression point of the second cell can be predicted, and based on the traffic suppression point, an expansion plan can be determined. This allows for a more accurate prediction of the traffic suppression point of the second cell in advance, enabling expansion before network traffic suppression occurs, covering the expansion period, and avoiding losses due to traffic suppression.

[0007] In one possible implementation, the aforementioned expansion scheme for determining at least one second cell based on the traffic suppression point may include: obtaining the duration from the current time to the traffic suppression point for each second cell; and determining the expansion scheme for at least one second cell based on the duration.

[0008] Therefore, in this embodiment, after predicting the time it takes for each second cell to reach the traffic suppression point from the current time, the expansion plan for each second cell can be determined based on the time, thereby expanding the capacity in advance for the traffic suppression points that may occur in each second cell and avoiding congestion in each second cell.

[0009] In one possible implementation, there can be multiple second cells. The aforementioned expansion scheme for determining at least one second cell based on duration may include: scoring multiple second cells based on duration to obtain a value score for each second cell, where the value score indicates the priority for expanding each second cell; and obtaining an expansion scheme based on the value score of each second cell.

[0010] In this embodiment of the application, when there are multiple second cells, the expansion priority of each second cell can be sorted according to the time it takes for each second cell to hit the predicted traffic suppression point. The expansion priority of each second cell is represented by a value score, so that the cells that need expansion more can be expanded in a timely manner to avoid congestion.

[0011] In one possible implementation, the aforementioned acquisition of the time it takes for each second cell to reach the traffic suppression point from the current position may include: acquiring the time it takes for each second cell to reach the traffic suppression point from the current position through a preset time series prediction model.

[0012] Therefore, in this embodiment, a time series prediction model can be used to accurately predict the time it takes for each second cell to reach the traffic suppression point from its current state, so that each cell can be expanded in a timely manner to avoid cell congestion.

[0013] In one possible implementation, the aforementioned acquisition of first traffic information of at least one first cell may include: acquiring initial traffic information of at least one first cell; and clustering the initial traffic information to obtain first traffic information.

[0014] Therefore, in this embodiment, the initial traffic information of each first cell can be clustered, and outliers can be filtered out by clustering, so that the obtained first traffic information can better reflect the relationship between users and traffic usage in each first cell.

[0015] In one possible implementation, the aforementioned acquisition of the similarity between each of the at least one first cell and each of the at least one second cell includes: acquiring first cell information for each first cell, the first cell information including at least one of first cell feature information, first handover data, average number of users in the first cell RRC, or cell traffic; acquiring second cell information for each second cell, the second cell information including at least one of second cell feature information, second handover data, average number of users in the second cell RRC, or cell traffic; and calculating the similarity based on the first cell information of each first cell and the second cell information of each second cell.

[0016] Therefore, in this embodiment of the application, the similarity between each first cell and each second cell can be calculated based on the features of each first cell and the second cell in multiple dimensions, thereby obtaining an accurate similarity.

[0017] Secondly, this application provides a device for determining a capacity expansion scheme, comprising:

[0018] The acquisition module is used to acquire first traffic information of at least one first cell, the first traffic information including information on the number of users and changes in traffic usage in at least one first cell;

[0019] The fitting module is used to fit a first correlation between the number of users and the traffic used based on the first traffic information.

[0020] A similarity calculation module is used to obtain the similarity between each of the first cells in at least one first cell and each of the second cells in at least one second cell;

[0021] The prediction module is used to determine the traffic suppression point of each second cell based on the first correlation and similarity. The traffic suppression point includes the point in the second cell where the traffic growth rate decreases as the number of users increases.

[0022] The capacity expansion module is used to determine at least one capacity expansion scheme for a second cell based on the traffic suppression point. The capacity expansion scheme includes a scheme to expand the bandwidth of the second cell.

[0023] In one possible implementation, the capacity expansion module is specifically used to: obtain the duration from the current point of traffic suppression for each second cell; and determine a capacity expansion scheme for at least one second cell based on the duration.

[0024] In one possible implementation, there are multiple second cells, and the expansion module is specifically used to: score multiple second cells according to the duration to obtain a value score for each second cell, the value score being used to indicate the priority for expanding the capacity of each second cell; and to obtain an expansion plan based on the value score of each second cell.

[0025] In one possible implementation, the expansion module is specifically used to obtain the time it takes for each second cell to reach the traffic suppression point from the current state through a preset time series prediction model.

[0026] In one possible implementation, the acquisition module is specifically used to: acquire initial traffic information of at least one first cell; and cluster the initial traffic information to obtain first traffic information.

[0027] In one possible implementation, the similarity calculation module is specifically used to: obtain first cell information for each first cell, the first cell information including at least one of first cell feature information, first handover data, average number of users in the first cell RRC, or cell traffic; obtain second cell information for each second cell, the second cell information including at least one of second cell feature information, second handover data, average number of users in the second cell RRC, or cell traffic; and calculate similarity based on the first cell information of each first cell and the second cell information of each second cell.

[0028] Thirdly, embodiments of this application provide a capacity expansion scheme determination apparatus, including: a processor and a memory, wherein the processor and the memory are interconnected via a circuit, and the processor calls program code in the memory to execute processing-related functions in the capacity expansion scheme determination method shown in any of the first aspects above. Optionally, the capacity expansion scheme determination apparatus may be a chip.

[0029] Fourthly, embodiments of this application provide a capacity expansion scheme determination device, which may also be referred to as a digital processing chip or a chip. The chip includes a processing unit and a communication interface. The processing unit obtains program instructions through the communication interface, and the program instructions are executed by the processing unit. The processing unit is used to perform processing-related functions as described in the first aspect or any optional embodiment of the first aspect.

[0030] Fifthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the method described in the first aspect or any optional embodiment of the first aspect.

[0031] In a sixth aspect, embodiments of this application provide a computer program product containing instructions that, when run on a computer, cause the computer to perform the method described in the first aspect or any optional implementation thereof. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of a network framework used in this application;

[0033] Figure 2 A flowchart illustrating a method for determining a capacity expansion scheme provided in this application;

[0034] Figure 3 A flowchart illustrating another method for determining the capacity expansion scheme provided in this application;

[0035] Figure 4 A schematic diagram illustrating a traffic flow trend is provided for this application;

[0036] Figure 5 Another schematic diagram of traffic flow trends provided for this application;

[0037] Figure 6 This application provides a schematic diagram illustrating the relationship between user numbers and traffic.

[0038] Figure 7 Another diagram illustrating the relationship between user numbers and traffic provided for this application;

[0039] Figure 8 Another diagram illustrating the relationship between user numbers and traffic provided for this application;

[0040] Figure 9 A schematic diagram of a device for determining a capacity expansion scheme provided in this application;

[0041] Figure 10 A schematic diagram of the device for determining another capacity expansion scheme provided in this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0043] The capacity expansion scheme determination method provided in this application can be applied to various communication systems, such as wireless networks, wired networks, or combinations of wireless and wired networks. The wireless network includes, but is not limited to: 5th-Generation (5G) systems, Long Term Evolution (LTE) systems, Global System for Mobile Communication (GSM) or Code Division Multiple Access (CDMA) networks, Wideband Code Division Multiple Access (WCDMA) networks, the Internet of Things (IoT), Wireless Fidelity (WiFi), Bluetooth, Zigbee, Radio Frequency Identification (RFID), Long Range (Lora) wireless communication, and Near Field Communication (NFC), among other combinations. The wired network can include fiber optic communication networks or networks composed of coaxial cables.

[0044] This application exemplifies a wireless network. Typically, in a wireless network architecture, access devices can be deployed in multiple areas. Users can access the wireless network by connecting to these access devices, and the coverage area of ​​each access device can be referred to as a cell.

[0045] This access equipment can include base stations (eNodeB, eNB) in Long Term Evolution (LTE), base stations (gNodeB, gNB) in New Radio (NR), and so on. For example, from a product form perspective, a base station is a device with central control functions, such as macro base stations, micro base stations, pico, femeto, transmission points (TP), relays, and access points (AP).

[0046] The user referred to in this application can be a terminal or a device that carries a user account. For example, the user can include an account logged in on the device, or it can refer to the device that carries the account. The user device can be a terminal device, such as a mobile phone, computer, wristband, smartwatch, data card, sensor, station (STA), etc.

[0047] When multiple access devices exist, one of the access devices can be used as a management node, or a separate management node can be set up. The management node is used to manage the multiple access devices, such as allocating frequency bands and controlling their activation or deactivation. It can be understood that the method provided in this application can be executed by this management node, thereby achieving management of the cells covered by each access device.

[0048] For example, the network architecture applied in this application can be as follows: Figure 1 As shown, this includes multiple access devices. The area covered by one or more access devices can be considered a cell, or a cell can be defined as having one or more access devices. In a wireless network cell, as the number of network users and the data flow of usage (DOU) increase, the traffic carried by the wireless cell gradually increases. The cell network equipment may be unable to meet the growing demand for user traffic. At this time, it is necessary to expand the cell in a timely manner to support more network users and network traffic, and avoid network congestion, reduced user experience, and user churn due to the inability to support more network users and network traffic.

[0049] In some common expansion methods, when a cell is busy, if the carrier idle rate is greater than a threshold (e.g., 60%), the cell throughput is greater than a threshold (e.g., 3GB downlink or 0.7GB uplink), and the "average RRC connections" is greater than a threshold (e.g., 50), expansion is achieved by increasing the carrier frequency. Similarly, when the "maximum RRC connections" is greater than a threshold (e.g., 200), expansion is also achieved by increasing the carrier frequency. Expansion methods based on expansion thresholds are simple and easy to implement, facilitating network equipment expansion. However, due to the complexity of real-world network conditions, a single threshold-based method cannot account for differences in network equipment capacity caused by variations in cell users and services. Furthermore, expansion methods based on thresholds issue warnings when corresponding network indicators exceed the threshold, leading to longer expansion cycles. During these cycles, cell congestion may occur, resulting in a decreased user experience and customer churn.

[0050] In other expansion methods, network performance data of network devices can be acquired to train a machine learning model that determines the status of network devices. This model, combined with the real-time acquired performance data, determines the status of the network devices and thus whether expansion is necessary. However, while machine learning-based methods can analyze and judge network device status in real time, they cannot predict in advance whether expansion is needed, nor can they determine the time required to reach the required expansion state.

[0051] Therefore, this application provides a method for determining a capacity expansion scheme. By analyzing the traffic changes of cells that have experienced traffic suppression and the similarity between cells, the method predicts the traffic suppression point of a cell and determines the capacity expansion scheme based on the predicted suppression point. This allows for capacity expansion before network traffic suppression occurs, covering the expansion period and avoiding losses caused by traffic suppression.

[0052] See Figure 2 The following is a flowchart illustrating a method for determining a capacity expansion scheme provided in this application.

[0053] 201. Obtain the first traffic information of at least one first cell.

[0054] In this application, cells can be divided into several types, referred to as the first cell and the second cell for easy distinction. The first cell is the cell where traffic generation is suppressed, and the second cell is the cell where traffic suppression is not generated. Traffic suppression means that the rate of increase in traffic in a cell decreases as the number of users increases. This can be understood as the rate of increase in traffic generation decreasing as the number of users increases, meaning that network bandwidth may not be able to meet the users' traffic demands, potentially leading to congestion.

[0055] The number of first-level communities can be one or more, and the number of second-level communities can also be one or more.

[0056] The first traffic information includes information on the changes in the number of users and traffic usage in at least one first cell over a period of time. For example, the changes in the number of users and traffic usage in multiple first cells over a month can be collected on an hourly basis.

[0057] In one possible implementation, step 201 may specifically include: collecting initial traffic information of one or more first cells, i.e., the value of the number of users and the corresponding traffic generated within a certain period of time; filtering the collected initial traffic information; and deleting abnormal values ​​in the initial traffic information, such as values ​​that deviate far from the curve.

[0058] Optionally, clustering can be used to cluster the initial traffic information, such as unsupervised clustering methods like DBSCAN and hierarchical clustering, and outliers after clustering can be removed; the data can be thinned to reduce the impact of uneven data distribution on the fitting results.

[0059] 202. Fit the first correlation between the number of users and the traffic usage based on the first traffic information.

[0060] In this process, after obtaining the first traffic information of at least one first cell, the correlation between the number of users and the traffic used is fitted based on the first traffic information. For ease of distinction, this is referred to as the first correlation.

[0061] This can be understood as obtaining information on the number of users and their data usage in communities that have experienced traffic suppression, and then fitting the correlation between the number of users and their data usage.

[0062] 203. Obtain the similarity between at least one first cell and the second cell.

[0063] This involves calculating the similarity between each first cell and each second cell, that is, the degree of similarity between each cell that has experienced traffic suppression and each cell that has not experienced traffic suppression.

[0064] Specifically, similarity can be calculated from at least one dimension, including but not limited to cell characteristics, handover data, average number of RRC users in the cell, or cell traffic. Cell characteristics may include information such as the number of devices in the cell, the model of the device's board, the device's standard, and the bandwidth supported by the device. Handover data may include data generated by users switching cells, such as handover time and cell information, which can be used to characterize the degree of correlation between cells. The average number of RRC users in the cell is the number of users who have established RRC connections in the cell. Cell traffic is the traffic generated by devices in the cell.

[0065] For example, first cell information for each first cell can be obtained, including at least one of first cell characteristic information, first handover data, average number of users in the first cell's RRC, or cell traffic. Second cell information for a second cell can also be obtained, including at least one of second cell characteristic information, second handover data, average number of users in the second cell's RRC, or cell traffic. Then, based on the first cell information for each first cell and the second cell information for each second cell, the similarity between each second cell and at least one first cell is calculated. Therefore, in this embodiment, the similarity between cells can be measured from various dimensions, thereby obtaining a more accurate similarity score.

[0066] Alternatively, similarity can be calculated using algorithms such as cosine similarity or Minkowski distance. For example, similarity can be expressed as:

[0067] similarity=cal_sim(SP,SH,SU,SQ)

[0068] Where S is the set of cells, including the first cell and the second cell, P is cell characteristic information, H is handover data, U is the average number of users in the cell RRC, and Q is cell traffic.

[0069] It should be noted that this application does not limit the execution order of steps 201 and 203. Step 201 can be executed first, or step 203 can be executed first, or steps 201 and 203 can be executed simultaneously. The specific order can be adjusted according to the actual application scenario, and this application does not limit it.

[0070] 204. Based on the first correlation and similarity, determine the traffic suppression point of each second cell.

[0071] This involves collecting data on changes in the number of users and traffic usage in the second cell over a past period. This data is referred to as "second traffic information" for easy differentiation. Then, based on the second traffic information, the first correlation, and similarity, a second correlation is fitted for each second cell, which is the relationship between the number of users and traffic usage in the second cell.

[0072] Specifically, this can be understood as adjusting the first association based on the similarity between the first and second cells, and combining it with the number of users and traffic usage in the second cell to obtain a second association, so that it matches the actual number of users and traffic usage in the second cell, and better reflects the relationship between the number of users and traffic usage in the second cell.

[0073] After obtaining the second correlation, the traffic suppression point of the second cell can be predicted based on the second correlation. This traffic suppression point is the point in the second correlation where the traffic growth rate decreases as the number of users increases.

[0074] This can be understood as follows: as the number of users increases, the expected increase in traffic growth may be reduced due to device bandwidth limitations, potentially failing to meet users' traffic demands.

[0075] This can be expressed as: Calculating the flow suppression point of an unsuppressed cell based on the known flow suppression point of the flow suppression cell:

[0076] A new = f(similarity, A)

[0077] The similarity and A are used as inputs to the correlation algorithm, and the output is the flow suppression point.

[0078] Therefore, based on the similarity between cells and the changing trends of cells that have already experienced traffic suppression points, the traffic suppression points of the second cell can be identified, thereby predicting the upcoming traffic suppression points in the cell.

[0079] 205. Determine at least one expansion plan for a second cell based on the traffic suppression point.

[0080] Once the traffic suppression point is identified, the expansion plan for the second cell can be determined based on the information of that traffic suppression point, that is, the plan to expand the bandwidth of the second cell.

[0081] Specific expansion plans can include information such as the timing of expansion of the second cell, expansion priority, expansion bandwidth, and the number of additional access devices. For example, if there is currently one second cell, the latest expansion time, expansion frequency band, or additional access devices can be determined. When multiple second cells exist, their priorities can be ranked to determine the expansion plans for each cell, such as the latest expansion time, expansion priority, and expansion method for each cell.

[0082] Therefore, in this embodiment, the correlation between the number of users and the traffic generated in the first cell where traffic suppression has occurred, as well as the similarity between cells, can be used to fit the correlation between the number of users and the traffic in the second cell where traffic suppression has not occurred. Based on this correlation, the traffic suppression point of the second cell can be predicted, and based on the traffic suppression point, an expansion plan can be determined. This allows for a more accurate prediction of the traffic suppression point of the second cell in advance, enabling expansion before network traffic suppression occurs, covering the expansion period, and avoiding losses due to traffic suppression.

[0083] In one possible implementation, the duration from the current point when the second cell reaches its traffic suppression point can be determined, and then the expansion plan for the second cell can be determined based on this duration, including information such as the latest expansion time, the size of the expansion bandwidth, the number of additional devices, and the expansion priority. Therefore, in this embodiment, the expansion plan can be determined based on the duration when the second cell reaches its traffic suppression point, thus addressing the traffic suppression point of the second cell in advance.

[0084] Specifically, when multiple second cells exist, their value score can be determined based on the duration it takes for each second cell to reach its traffic suppression point. This value score can then be used to indicate the expansion priority of each second cell. For example, cells with more users, shorter durations, or faster user growth typically have higher value scores, meaning their priority can be set higher. Therefore, expansion can be performed on each of the multiple second cells based on their respective value scores. Thus, in this embodiment, when multiple second cells exist, their value score can be obtained by evaluating each cell based on the duration it takes for them to reach their traffic suppression point. This value score can then be used to indicate expansion priority, allowing expansion plans for each of the multiple second cells to be determined and implemented accordingly.

[0085] Optionally, when determining the duration for each second cell to reach the traffic suppression point, the duration for each second cell to reach the traffic suppression point can be calculated based on a preset time series prediction model, thereby accurately predicting the duration for the second cell to reach the traffic suppression point from the current point.

[0086] The foregoing has described the process of the method provided in this application. To facilitate understanding, the process of the method provided in this application will be further described below in conjunction with more specific application scenarios.

[0087] See Figure 3 This application provides a flowchart illustrating another method for determining capacity expansion schemes.

[0088] First, it should be noted that the first cell is the cell that has generated traffic suppression points, and the second cell is the cell that has not generated traffic suppression points. There can be one or more first cells, and there can also be one or more second cells.

[0089] The first traffic information and the first cell information can be collected from the relevant data of the first cell, and the second cell information can be collected from the relevant data of the second cell.

[0090] First traffic information: can include the number of users and traffic usage in the first cell during historical time periods. It can be collected in units of time, such as collecting the number of users and the traffic generated per hour within the past 30 days.

[0091] First cell information: This can include information related to the first cell, such as the number of devices in the first cell, the model of the device board, the network standard corresponding to the device, the geographical location of the cell, etc.

[0092] The information for the second cell is similar to that for the first cell, and may include information such as the number of devices in the second cell, the model of the device board, the network standard corresponding to the device, and the geographical location of the cell.

[0093] After collecting the above data, the following steps can be performed based on the collected data:

[0094] 301. Fit the relationship between the number of users and traffic in the first cell.

[0095] After obtaining the first traffic information, the relationship between the number of users and the traffic generated in the first cell can be fitted based on the first traffic information, that is, the first correlation relationship.

[0096] For example, user count and traffic data in the first cell can be collected hourly, and then the relationship between hourly user count and traffic can be fitted to determine the traffic suppression point in the first cell. Typically, the trend of no traffic suppression point can be as follows: Figure 4As shown, there is a linear relationship between the number of users and traffic. However, when there is a traffic bottleneck, that is, as the number of users increases, the growth rate of traffic decreases, as... Figure 5 As shown,

[0097] For example, it is possible to collect data on cell C and the average number of users U in cell C's RRC. t Cell downlink traffic Q t To minimize the impact of outlier data on the results, we first filter out outliers. Then, we use the U dataset after removing outliers. t And Q t Curve fitting is performed to obtain the flow suppression point A of the suppressed area. Unsupervised clustering methods such as density-based clustering of applications with noise (DBSCAN) or hierarchical clustering can be used to remove outliers after clustering; the data is thinned to reduce the impact of uneven data distribution on the fitting results.

[0098] The relationship between user numbers and traffic can then be fitted. For example, a piecewise fitting can be performed, represented as:

[0099] f1(x) = k1*x + y0 - k1*x0

[0100]

[0101] Where x represents the number of users, f represents the traffic generated, and f is a coefficient, which is usually a preset value or can be adjusted according to the actual algorithm.

[0102] After fitting the relationship between the number of users and traffic in the first cell, the traffic suppression point of each first cell can be identified based on this relationship. For example, some of the correlation relationships can be as follows: Figure 6 , Figure 7 as well as Figure 8 As shown, the point where the traffic growth rate begins to decrease as the number of users increases is taken as the traffic suppression point. This indicates that from the traffic suppression point onwards, network resources may not be able to meet the users' traffic needs, leading to network congestion, and some users may not be able to access the network or use network resources.

[0103] 302. Calculate the similarity between the first cell and the second cell.

[0104] One or more first cells and one or more second cells can be used as a cell set, and the similarity between cells in the cell set can be calculated.

[0105] Specifically, for a set of cells S, cell similarity is calculated by acquiring data including cell feature information P, handover data H, average number of users in cell RRC U, and cell traffic Q.

[0106] For example, cosine similarity can be used to calculate the similarity score, expressed as:

[0107]

[0108] c1, c2, c3, ..., c n Let S be a feature vector composed of the feature information of n cells in the cell set S. Then, calculate the inter-cell similarity W between cells in the cell set S. ij Let be the similarity between neighborhoods i and j.

[0109] For example, the Minkowski distance can also be used to calculate similarity, as shown below:

[0110]

[0111] Where D ij Let D be the Minkowski distance between cells i and j. ij Normalization is performed, and the similarity between neighborhoods i and j is further obtained:

[0112]

[0113] 303. Predict the point of traffic suppression.

[0114] After obtaining the first correlation and the similarity between each cell, the traffic suppression point of the second cell can be predicted based on the first correlation.

[0115] For example, the flow suppression point (U) of the first cell obtained through the inter-cell similarity W. A Q A The current unsuppressed cell flow suppression point is obtained. Similarity-based calculation methods such as collaborative filtering can be used, as shown below:

[0116]

[0117]

[0118] in Let m be the number of users in the current unsuppressed cells who are acting as traffic suppressors. Let i be the number of users in the i-th currently unsuppressed cell whose traffic is suppressed. Let m be the traffic values ​​at the traffic suppression points of the currently unsuppressed cells. Let be the traffic suppression point value of the i-th currently unsuppressed cell.

[0119] For example, the similarity W between small cells, and the cell flow suppression point (U) obtained from the data, can be used to determine the cell flow suppression point. A Q A The current unsuppressed cell flow suppression point is obtained. Similarity-based calculation methods, including but not limited to tag propagation, are represented as follows:

[0120]

[0121]

[0122]

[0123] in The output is the predicted number of users at the traffic suppression point of the cell set, where μ is the absorption rate and 0 < μ < 1, and n is the total number of cells in the cell set.

[0124]

[0125]

[0126]

[0127] in The output is the predicted flow rate of the cell set flow suppression point, where μ is the absorption rate and 0 < μ < 1, and n is the total number of cells in the cell set.

[0128] 304. Calculate the time required to reach the flow suppression point.

[0129] Among them, the traffic suppression point A can be predicted, where A is the RRC average number of users minus the downlink traffic tuple (U A Q A Subsequently, time series forecasting can be used to predict the average number of users and downlink traffic in the cell's RRC (Remote Rate Control) for future times, yielding predicted values ​​U for the cell's average number of users and downlink traffic in the future. t Q t .

[0130] Based on time series forecasts, the predicted results for the average number of users and downlink traffic in the future cell RRC are as follows: U t Q t Calculate the flow suppression point reaching the cell. Time required:

[0131]

[0132] in This represents the average number of RRC users (i.e., the number of users with established RRC connections) and downlink traffic corresponding to the traffic suppression point of a single cell.

[0133] 305. Determine the expansion plan for the second community.

[0134] When there are multiple second cells, the expansion value of these multiple second cells can be scored, and they can be sorted according to the scoring results. This is equivalent to identifying the expansion priority of each cell through value scoring, thereby obtaining the final expansion plan.

[0135] Based on the time T when a cell reaches the suppressed state A, as well as information such as the number of users U, traffic Q, and other environmental characteristics K, the expansion priorities of cells are ranked, and a final cell expansion recommendation is given:

[0136]

[0137] Wherein: T now The current time is represented by ω1, ω2, ω3, and ω4, which are the weighting coefficients corresponding to the time dimension, user dimension, traffic dimension, and cell environment characteristics, respectively. These can be preset values ​​or values ​​adjusted according to the actual application scenario.

[0138] Generally, the shorter the time it takes for a community to reach its traffic suppression point, the higher its value score; the longer the time it takes to reach its traffic suppression point, the lower its value score. The more users a community has, the higher its value score; the fewer users a community has, the lower its value score. The more data a community uses, the higher its value score; the less data a community uses, the lower its value score, and so on.

[0139] For example, the calculated community score can be shown in Table 1:

[0140]

[0141] Table 1

[0142] Generally, the higher the score of a community, the higher its priority for capacity expansion. Therefore, when there are multiple communities, capacity expansion can be prioritized for communities with higher expansion needs based on their value scores. This ensures that the available traffic in a community meets user demand, avoids traffic bottlenecks, and improves user experience.

[0143] This application provides a network agile expansion method based on traffic suppression point prediction. It can be used not only for cell-level traffic suppression point prediction and agile expansion, but also for site-level, cell cluster-level, regional-level, and city-level agile network expansion at different levels. By predicting the timing of traffic suppression points, a recommended cell expansion schedule is provided, allowing expansion to be carried out before network traffic suppression occurs, covering the expansion cycle and avoiding losses due to traffic suppression. This helps operators control the expansion pace, smooth investment, and avoid the risks and losses caused by peak investment.

[0144] The foregoing has described the method flow provided in this application; the apparatus for executing this method flow is described below. (See also...) Figure 9 The structural schematic diagram of a capacity expansion scheme determination device provided in this application may include:

[0145] The acquisition module 901 is used to acquire first traffic information of at least one first cell, the first traffic information including information on the number of users and changes in traffic usage in at least one first cell;

[0146] The fitting module 902 is used to fit a first correlation between the number of users and the traffic used based on the first traffic information;

[0147] The similarity calculation module 903 is used to obtain the similarity between each of the first cells in at least one first cell and each of the second cells in at least one second cell;

[0148] The prediction module 904 is used to determine the traffic suppression point of each second cell based on the first correlation and similarity. The traffic suppression point includes the point in the second cell where the traffic growth rate decreases as the number of users increases.

[0149] The capacity expansion module 905 is used to determine at least one capacity expansion scheme for a second cell based on the traffic suppression point. The capacity expansion scheme includes a scheme to expand the bandwidth of the second cell.

[0150] In one possible implementation, the capacity expansion module 905 is specifically used to: obtain the duration from the current point of traffic suppression for each second cell; and determine a capacity expansion scheme for at least one second cell based on the duration.

[0151] In one possible implementation, there are multiple second cells, and the expansion module 905 is specifically used to: score multiple second cells according to the duration to obtain a value score for each second cell, the value score being used to indicate the priority for expanding the capacity of each second cell; and to obtain an expansion plan based on the value score of each second cell.

[0152] In one possible implementation, the expansion module 905 is specifically used to obtain the duration from the current point to the traffic suppression point for each second cell through a preset time series prediction model.

[0153] In one possible implementation, the acquisition module 901 is specifically used to: acquire initial traffic information of at least one first cell; and cluster the initial traffic information to obtain first traffic information.

[0154] In one possible implementation, the similarity calculation module 903 is specifically used to: obtain first cell information for each first cell, the first cell information including at least one of first cell feature information, first handover data, average number of RRC users in the first cell, or cell traffic; obtain second cell information for each second cell, the second cell information including at least one of second cell feature information, second handover data, average number of RRC users in the second cell, or cell traffic; and calculate similarity based on the first cell information of each first cell and the second cell information of each second cell.

[0155] Please see Figure 10 The structural schematic diagram of another capacity expansion scheme determination device provided in this application is as follows.

[0156] The expansion scheme determination device may include a processor 1001, a memory 1002, and a transceiver 1003. The processor 1001 and the memory 1002 are interconnected via a line. The memory 1002 stores program instructions and data.

[0157] The aforementioned are stored in memory 1002 Figures 2-8 The steps in the code include the corresponding program instructions and data.

[0158] Processor 1001 is used to execute the aforementioned Figures 2-8 The method steps performed by the capacity expansion scheme determination device shown in any of the embodiments.

[0159] Transceiver 1003 is used to perform the aforementioned Figures 2-8 The expansion scheme shown in any embodiment determines the steps of receiving or transmitting data performed by the device. The transceiver 1003 is an optional module.

[0160] This application also provides a computer-readable storage medium storing a program for generating vehicle speed, which, when run on a computer, causes the computer to perform the aforementioned... Figures 2-8 The steps in the method described in the illustrated embodiment.

[0161] Alternatively, the aforementioned Figure 10 The device for determining the capacity expansion scheme shown is a chip.

[0162] This application embodiment also provides a capacity expansion scheme determination device, which can also be called a digital processing chip or a chip. The chip includes a processing unit and a communication interface. The processing unit obtains program instructions through the communication interface, and the program instructions are executed by the processing unit. The processing unit is used to perform the aforementioned... Figures 2-8 The method steps performed by the capacity expansion scheme determination device shown in any of the embodiments.

[0163] This application also provides a digital processing chip. This digital processing chip integrates circuitry for implementing the processor 1001 described above, or the functions of the processor 1001, and one or more interfaces. When the digital processing chip integrates a memory, it can complete the method steps of any one or more of the foregoing embodiments. When the digital processing chip does not integrate a memory, it can be connected to an external memory via a communication interface. The digital processing chip implements the actions performed by the expansion scheme determination device in the foregoing embodiments based on the program code stored in the external memory.

[0164] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned actions. Figures 2-8 The steps performed by the expansion scheme determination device in the method described in the illustrated embodiment.

[0165] The capacity expansion scheme determination device provided in this application embodiment can be a chip, which includes a processing unit and a communication unit. The processing unit can be, for example, a processor, and the communication unit can be, for example, an input / output interface, pins, or circuits. The processing unit can execute computer execution instructions stored in the storage unit to cause the chip within the server to perform the aforementioned operations. Figures 2-8 The device search method described in the illustrated embodiment. Optionally, the storage unit is a storage unit within the chip, such as a register, cache, etc. The storage unit can also be a storage unit located outside the chip within the wireless access device, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (RAM), etc.

[0166] Specifically, the aforementioned processing unit or processor can be a central processing unit (CPU), a neural-network processing unit (NPU), a graphics processing unit (GPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0167] The processor mentioned above can be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more processors used to control the above. Figures 2-8 The method of program execution of integrated circuits.

[0168] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0169] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, 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 is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., including 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 of this application.

[0170] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0171] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0172] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0173] Finally, it should be noted that the above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining a capacity expansion scheme, characterized in that, include: Obtain first traffic information of at least one first cell, wherein the first traffic information includes information on the number of users and changes in traffic usage in the at least one first cell; Based on the first traffic information, a first correlation relationship is fitted between the number of users and the traffic used; Obtain the similarity between each of the at least one first cell and each of the at least one second cell; Based on the first association relationship and the similarity, the traffic suppression point of each second cell is determined. The traffic suppression point includes the point in the second cell where the traffic growth rate decreases as the number of users increases. The expansion scheme for the at least one second cell is determined based on the traffic suppression point, and the expansion scheme includes a scheme to expand the bandwidth of the second cell.

2. The method according to claim 1, characterized in that, The step of determining the expansion scheme for the at least one second cell based on the traffic suppression point includes: Obtain the time taken for each of the second cells to reach the traffic suppression point from the current position; The expansion scheme for the at least one second cell is determined based on the duration.

3. The method according to claim 2, characterized in that, There are multiple second cells, and determining the expansion plan for at least one second cell based on the duration includes: The multiple second cells are scored according to the duration to obtain a value score for each second cell. The value score is used to indicate the priority for expanding the capacity of each second cell. The expansion plan is obtained based on the value score of each second cell.

4. The method according to claim 2 or 3, characterized in that, The step of obtaining the time from the current point to the traffic suppression point for each second cell includes: The time taken for each second cell to reach the traffic suppression point from the current position is obtained through a preset time series prediction model.

5. The method according to any one of claims 1-4, characterized in that, The step of obtaining the first traffic information of at least one first cell includes: Obtain the initial traffic information of the at least one first cell; The initial traffic information is clustered to obtain the first traffic information.

6. The method according to any one of claims 1-5, characterized in that, The step of obtaining the similarity between each of at least one first cell and each of at least one second cell includes: Obtain first cell information for each first cell, wherein the first cell information includes at least one of first cell characteristic information, first handover data, average number of users in the first cell RRC, or cell traffic. Obtain the second cell information for each second cell, the second cell information including at least one of the second cell characteristic information, second handover data, average number of users in the second cell RRC, or cell traffic; The similarity is calculated based on the first cell information of each first cell and the second cell information of each second cell.

7. A device for determining a capacity expansion scheme, characterized in that, include: The acquisition module is used to acquire first traffic information of at least one first cell, wherein the first traffic information includes information on the number of users and changes in traffic usage in the at least one first cell; The fitting module is used to fit a first correlation relationship between the number of users and the traffic used based on the first traffic information. The similarity calculation module is used to obtain the similarity between each of the at least one first cell and each of the at least one second cell; The prediction module is used to determine the traffic suppression point of each second cell based on the first correlation and the similarity, wherein the traffic suppression point includes the point in the second cell where the traffic growth rate decreases as the number of users increases; The capacity expansion module is used to determine the capacity expansion scheme of the at least one second cell based on the traffic suppression point, wherein the capacity expansion scheme includes a scheme to expand the bandwidth of the second cell.

8. The apparatus according to claim 7, characterized in that, The expansion module is specifically used for: Obtain the time taken for each of the second cells to reach the traffic suppression point from the current position; The expansion scheme for the at least one second cell is determined based on the duration.

9. The apparatus according to claim 8, characterized in that, There are multiple second-cell areas, and the expansion module is specifically used for: The multiple second cells are scored according to the duration to obtain a value score for each second cell. The value score is used to indicate the priority for expanding the capacity of each second cell. The expansion plan is obtained based on the value score of each second cell.

10. The apparatus according to claim 8 or 9, characterized in that, The expansion module is specifically used to obtain the time it takes for each second cell to reach the traffic suppression point from the current state through a preset time series prediction model.

11. The apparatus according to any one of claims 7-10, characterized in that, The acquisition module is specifically used for: Obtain the initial traffic information of the at least one first cell; The initial traffic information is clustered to obtain the first traffic information.

12. The apparatus according to any one of claims 7-11, characterized in that, The similarity calculation module is specifically used for: Obtain first cell information for each first cell, wherein the first cell information includes at least one of first cell characteristic information, first handover data, average number of users in the first cell RRC, or cell traffic. Obtain the second cell information for each second cell, the second cell information including at least one of the second cell characteristic information, second handover data, average number of users in the second cell RRC, or cell traffic; The similarity is calculated based on the first cell information of each first cell and the second cell information of each second cell.

13. A device for determining a capacity expansion scheme, characterized in that, The method includes a processor coupled to a memory storing a program, wherein the program instructions stored in the memory are executed by the processor to implement the method of any one of claims 1 to 6.

14. A computer-readable storage medium comprising a program, which, when executed by a processing unit, performs the method as described in any one of claims 1 to 6.

15. A device for determining a capacity expansion scheme, characterized in that, The system includes a processing unit and a communication interface. The processing unit obtains program instructions through the communication interface, and when the program instructions are executed by the processing unit, the system implements the method of any one of claims 1 to 6.

16. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1 to 6.

Images