Network capacity expansion method and device, electronic equipment and computer readable storage medium

Abstract

Embodiments of the present application provide a network capacity expansion method and device, electronic equipment and computer readable storage medium, the method comprising: inputting the current PRB utilization of each cell to the traffic prediction model corresponding to the type of each cell pre-trained, obtaining the theoretical traffic of each cell, and predicting the growth traffic of each cell according to the current actual traffic and the theoretical traffic of each cell; according to the growth traffic of each cell and the preset evaluation parameter, determine the target cell in each cell that exists capacity expansion demand; according to the value mark of the target cell preset, determine the network capacity standard of the target cell, and monitor whether the target cell satisfies the capacity expansion condition according to the network capacity standard; when it is monitored that the target cell satisfies the capacity expansion condition, determine the capacity expansion scheme corresponding to the target cell according to the growth traffic of the target cell, so that the network can be expanded in time, and the accuracy of network capacity expansion is improved.

Description

Technical Field

[0001] This application relates to the field of mobile communication technology, and in particular to a network expansion method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] With the development of mobile communication technology, the number of network users is constantly increasing, and with the promotion of various data plans, user data traffic is growing rapidly.

[0003] To ensure that users experience high-speed data services on wireless networks, operators need to optimize and expand network capacity to comprehensively improve the user's internet experience.

[0004] Currently, network expansion is typically assessed based on factors such as the number of effective Radio Resource Control (RRC) connections, uplink and downlink Physical Resource Block (PRB) utilization, and uplink and downlink traffic over a recent period to determine whether expansion thresholds have been reached. However, this approach lacks predictability for future traffic growth and cannot proactively and promptly expand the network, resulting in a degraded user experience. Furthermore, existing expansion schemes have low accuracy, leading to a waste of network resources as expansion may not improve network performance. Summary of the Invention

[0005] This application provides a network expansion method, apparatus, electronic device, and computer-readable storage medium, which can solve the technical problems of the inability to expand the network in a timely manner and the low accuracy of expansion in the prior art.

[0006] Firstly, this application provides a network expansion method, the method comprising:

[0007] The current PRB utilization rate of each cell is input into a pre-trained traffic prediction model corresponding to the type of each cell to obtain the theoretical traffic of each cell. Based on the current actual traffic of each cell and the theoretical traffic, the growth traffic of each cell is predicted. The traffic prediction model is used to predict the traffic of a cell based on the PRB utilization rate of the cell.

[0008] Based on the growth traffic of each cell and the preset evaluation parameters, the target cells with expansion needs are determined among the cells.

[0009] Based on the preset value identifier of the target cell, the network capacity standard of the target cell is determined, and based on the network capacity standard, the target cell is monitored to see if it meets the expansion conditions.

[0010] When it is monitored that the target cell meets the expansion condition, an expansion scheme corresponding to the target cell is determined according to the growth traffic of the target cell.

[0011] In an implementable embodiment, the method further comprises:

[0012] According to the cell features of the respective cells, the respective cells are classified based on a machine learning classification algorithm, and the types of the respective cells are determined.

[0013] The cell features include at least one of the following features: cell geographic location, cell average traffic, cell user number, cell frequency / bandwidth, cell busy / idle time, and cell service type.

[0014] In an implementable embodiment, the method further comprises:

[0015] For each type of cell, a benchmark cell is screened out according to preset optimization rules.

[0016] According to the PRB utilization rate and traffic of the benchmark cell, a traffic prediction model corresponding to each type of cell is obtained through model training.

[0017] In an implementable embodiment, the preset evaluation parameters include alarm, cell availability, load balancing parameter, and average Channel Quality Indication (CQI).

[0018] The target cell with expansion demand is determined from the respective cells according to the growth traffic and preset evaluation parameters of the respective cells, including:

[0019] A cell with growth traffic greater than a preset growth threshold is determined as a potential expansion cell.

[0020] The potential expansion cell without alarm, with cell availability less than a preset first threshold, meeting the load balancing condition, and with average CQI less than a preset second threshold is selected as the target cell with expansion demand.

[0021] In an implementable embodiment, the network capacity standard of the target cell is determined according to the preset value identifier of the target cell, including:

[0022] The network capacity standard of the target cell is determined according to the preset value identifier of the target cell and the corresponding relationship between the preset various value identifiers and network capacity standards.

[0023] In an implementable embodiment, whether the target cell meets the expansion condition is monitored according to the network capacity standard, including:

[0024] determining that the target cell satisfies the expansion condition when at least two of the following conditions are monitored to be satisfied:

[0025] a busy hour rate of the target cell is less than a busy hour rate threshold corresponding to a network capacity standard of the target cell;

[0026] a busy hour traffic of the target cell is greater than a busy hour traffic threshold corresponding to the network capacity standard of the target cell;

[0027] a number of radio resource control (RRC) connections in the target cell is greater than an RRC connection threshold corresponding to the network capacity standard of the target cell.

[0028] In an available implementation, the determining the expansion scheme corresponding to the target cell according to the growth traffic of the target cell comprises:

[0029] determining a carrier demand frequency of the target cell according to the growth traffic of the target cell;

[0030] determining the expansion scheme corresponding to the target cell according to the carrier demand frequency of the target cell, and a site distribution distance and a user distribution distance in the target cell.

[0031] In a second aspect, the present application provides a network expansion device, which comprises:

[0032] a prediction module configured to input a current PRB utilization rate of each cell into a pre-trained traffic prediction model corresponding to a type of each cell to obtain a theoretical traffic of each cell, and predict a growth traffic of each cell according to an actual traffic of each cell and the theoretical traffic;

[0033] a screening module configured to determine a target cell having an expansion demand from each cell according to the growth traffic of each cell and a preset evaluation parameter;

[0034] a monitoring module configured to determine a network capacity standard of the target cell according to a preset value identifier of the target cell, and monitor whether the target cell satisfies an expansion condition according to the network capacity standard;

[0035] a processing module configured to determine an expansion scheme corresponding to the target cell according to the growth traffic of the target cell when it is monitored that the target cell satisfies the expansion condition.

[0036] In a third aspect, the present application provides an electronic device, which comprises at least one processor and a memory;

[0037] The memory stores computer-executable instructions;

[0038] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the network expansion method provided in the first aspect.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer-executable instructions, and when a processor executes the computer-executable instructions, the network expansion method provided in the first aspect is implemented.

[0040] The network expansion method provided in the present application can accurately predict the growth traffic of each cell by classifying each cell and using the traffic prediction model between the PRB utilization rate and the traffic corresponding to each type of cell according to the type of each cell and the pre-trained traffic prediction model. Then, according to the growth traffic of each cell and the preset evaluation parameter, the target cell in each cell that has expansion demand is determined, the network capacity standard of the target cell is determined according to the preset value identifier of the target cell, and whether the target cell meets the expansion condition is monitored according to the network capacity standard. When it is monitored that the target cell meets the expansion condition, the expansion scheme corresponding to the target cell is determined according to the growth traffic of the target cell, so that the network can be expanded in time, and the accuracy of network expansion is improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A structure schematic diagram of an LTE network system provided in an embodiment of the present application;

[0042] Figure 2 A flowchart of a network expansion method provided in an embodiment of the present application;

[0043] Figure 3 A sub-flowchart of a network expansion method provided in an embodiment of the present application;

[0044] Figure 4 Another sub-flowchart of a network expansion method provided in an embodiment of the present application;

[0045] Figure 5 A program module schematic diagram of a network expansion device provided in an embodiment of the present application;

[0046] Figure 6 A hardware structure schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Furthermore, although the disclosure in this application is described with reference to one or several exemplary examples, it should be understood that each aspect of these disclosures can also constitute a complete implementation method on its own.

[0048] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0049] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms can be used interchangeably where appropriate, for example, to implement the embodiments in a sequence other than those given in the illustrations or descriptions of this application.

[0050] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclusively include, for example, a product or device that includes a series of components is not necessarily limited to those that are explicitly listed, but may include other components that are not explicitly listed or that are inherent to such product or device.

[0051] As used in this application, the term "module" means any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code capable of performing the functions associated with that element.

[0052] For example, refer to Figure 1 , Figure 1 This is a schematic diagram of the structure of an LTE network system provided in an embodiment of this application. Figure 1 As shown, the network system includes multiple base stations 11, multiple user terminals 12, and a server 13. A cell is an area that provides wireless communication services to users and is the basic unit of a wireless network. Base stations 11 are used to manage or support one or more cells. Typically, one base station corresponds to one cell, meaning a cell is a coverage area centered on a base station. The server 13 is used to analyze the causes of low data rates in a cell. When a user terminal 12 is within the wireless signal range provided by a cell, it establishes a connection with the base station managing that cell, and then establishes communication with the core network to realize wireless communication services.

[0053] With the gradual expansion of the wireless network, the number of user terminals in the cell continues to increase, and the traffic of users using the cell presents an explosive growth. When the utilization rate of the cell wireless resources reaches a certain threshold, it will seriously affect the user experience. Therefore, it is necessary to predict the future traffic of the cell and timely expand the capacity of the cell that appears to be a bottleneck, so that the traffic of the expanded cell can meet the user development for a period of time.

[0054] Currently, for the expansion of the fourth generation mobile communication technology (4G) network, it is usually determined whether expansion is needed based on whether the load KPI (such as the number of users, traffic, PRB utilization rate, etc.) of the cell in the recent period of time exceeds the threshold. This method is not predictive enough for future traffic growth, resulting in passive expansion all the time, which is seriously insufficient in timeliness, and thus causing damage to traffic and user perception.

[0055] In actual expansion work, the existing determination criteria only consider cell coverage and cell quality, and are insufficient for load balancing and network operation. At the same time, the cell coverage and cell quality determination threshold is mainly based on empirical values, and the current business types, scene characteristics, and user behavior are not considered, which is relatively insufficient in accuracy, resulting in difficulty in implementing the optimization first and then construction, mainly simple expansion, and the network efficiency cannot be improved after expansion, resulting in waste of some resources. In addition, the existing expansion standard is mainly based on traditional KPI values, which cannot accurately reflect the influence of user business perception, resulting in relatively insufficient precision of expansion. In the expansion scheme, simply by stacking two or three carriers, the precision is not enough, which also leads to the fact that the actual network capacity and quality cannot meet the user perception and traffic growth demand.

[0056] To solve the above technical problems, the embodiment provides a network capacity expansion method. The network capacity expansion method can accurately predict the growth traffic of each cell by classifying each cell and using the traffic prediction model between the PRB utilization rate and the traffic of each type of cell and each cell. Then, the target cell with capacity expansion demand in each cell is determined according to the growth traffic of each cell and the preset evaluation parameter. The network capacity standard of the target cell is determined according to the preset value identifier of the target cell, and whether the target cell meets the capacity expansion condition is monitored according to the network capacity standard. When it is monitored that the target cell meets the capacity expansion condition, the capacity expansion scheme corresponding to the target cell is determined according to the growth traffic of the target cell, so that the network can be expanded in time, the accuracy of network capacity expansion is improved, the problems of low accuracy and insufficient value consideration in the traditional method are solved, and the capacity expansion is changed from passive to active. While improving the accuracy of capacity expansion, the user perception and network performance are effectively improved. The following detailed embodiments are described in detail.

[0057] Reference Figure 2 , Figure 2 A flowchart of a network capacity expansion method provided by the embodiment is shown in the figure. In a feasible implementation manner, the network capacity expansion method comprises the following steps.

[0058] S201, input the current PRB utilization rate of each cell into the traffic prediction model corresponding to the type of each cell which is trained in advance, obtain the theoretical traffic of each cell, and predict the growth traffic of each cell according to the current actual traffic and the theoretical traffic of each cell.

[0059] In the embodiment, the service type and service intensity used by the user will affect the traffic and PRB utilization rate of the cell, so the cells with different characteristics can be classified according to the service type and service intensity, and the type of each cell is determined.

[0060] Under normal circumstances, the traffic and PRB utilization rate of the cell show a synchronous growth relationship, so the traffic prediction model between the PRB utilization rate and the traffic can be established by using a machine learning algorithm. However, due to the differences in user behavior, wireless environment and cell characteristics, the relationship between PRB and traffic must also have differences. Therefore, the traffic prediction model between the PRB utilization rate and the traffic corresponding to each type of cell can be established by using a machine learning algorithm in advance for each type of cell.

[0061] Optionally, the traffic prediction model can adopt a generalized linear regression model.

[0062] In the embodiment, after determining the type of each cell and the traffic prediction model between the PRB utilization ratio corresponding to each type of cell and the traffic, the current PRB utilization ratio of each cell is input into the corresponding traffic prediction model, and the predicted theoretical traffic of each cell can be obtained according to the output of the traffic prediction model.

[0063] After obtaining the predicted theoretical traffic of each cell, the growth traffic of each cell can be predicted by combining the current traffic of each cell.

[0064] The growth traffic of each cell = the predicted theoretical traffic of each cell - the current traffic of each cell.

[0065] S202, according to the growth traffic of each cell and the preset evaluation parameter, determine the target cell with expansion demand in each cell.

[0066] In the embodiment, according to the growth traffic of each cell and the preset evaluation parameter, the cell that can meet the traffic growth demand through optimization or fault repair is determined as the cell without expansion, and the cell that cannot meet the traffic growth demand through optimization or fault repair is determined as the target cell with expansion demand.

[0067] In the embodiment, after determining the growth traffic of each cell, the reason why the cell with high growth traffic does not meet the expectation can be determined, and after excluding the cells that can be solved by optimization maintenance, the list of target cells with real expansion demand is formed.

[0068] S203, according to the preset value identifier of the target cell, determine the network capacity standard of the target cell, and monitor whether the target cell meets the expansion condition according to the network capacity standard.

[0069] In the embodiment, the corresponding relationship between various value identifiers and network capacity standards can be preset, and then the network capacity standard of the target cell can be determined according to the preset value identifier of the target cell.

[0070] For example, the above-mentioned value identifier can include three types, which are "strong aggregation and high commercial value", "focus area" and "non-focus area". The network capacity standard corresponding to "strong aggregation and high commercial value" is 1080P, the network capacity standard corresponding to "focus area" is 720P, and the network capacity standard corresponding to "non-focus area" is 480P. If it is determined that the preset value identifier of the target cell is "focus area", the network capacity standard of the target cell can be determined as 720P.

[0071] In the embodiment, after determining the network capacity standard of the target cell, whether the target cell meets the expansion condition can be monitored according to the network capacity standard.

[0072] S204, when it is monitored that the target cell satisfies the expansion condition, determining an expansion scheme corresponding to the target cell according to the growth traffic of the target cell.

[0073] In the embodiments of the present application, the capacity demand of the target cell is converted based on the growth traffic of the target cell, and then a differentiated expansion scheme is matched in combination with the user and site distribution.

[0074] The network expansion method provided in the present application can accurately predict the growth traffic of each cell by classifying each cell and according to the type of each cell and the traffic prediction model between the PRB utilization rate and the traffic of each type of cell pre-trained. Then, according to the growth traffic of each cell and the preset evaluation parameter, the target cell with expansion demand in each cell is determined, the network capacity standard of the target cell is determined according to the preset value identifier of the target cell, and whether the target cell satisfies the expansion condition is monitored according to the network capacity standard. When it is monitored that the target cell satisfies the expansion condition, the expansion scheme corresponding to the target cell is determined according to the growth traffic of the target cell, so that the network can be expanded in time, and the accuracy of network expansion is improved.

[0075] Based on the content described in the above embodiments, in a feasible implementation, each cell can be classified based on a machine learning classification algorithm according to the cell characteristics of each cell, and the type of each cell is determined.

[0076] Optionally, the above-mentioned cell characteristics include at least one of the following features: cell geographical location, cell average traffic, cell user number, cell frequency / bandwidth, cell busy / idle time, cell service type.

[0077] In some embodiments, for example, according to the user scenario, it can be divided into the following types: commercial center, urban center, residential area, school, highway, transportation hub, rural area, etc.; according to the frequency / bandwidth, it can be divided into the following types: 2.1G / 20M, 1800M / 20M, 1800M / 15M, 800M / 5M, etc.; according to the busy / idle identification, it can be divided into the following types: busy time adaptive, idle time adaptive, etc.; according to the service type, it can be divided into the following types: large packet adaptive, medium packet adaptive, small packet adaptive, etc.

[0078] In some embodiments, multiple cell characteristics can be integrated to classify each cell, such as integrating frequency / bandwidth and service type to be classified into 12 types: "2.1G / 20M, large packet adaptive", "2.1G / 20M, medium packet adaptive", "2.1G / 20M, small packet adaptive", "1800M / 20M, large packet adaptive", "1800M / 20M, medium packet adaptive", "1800M / 20M, small packet adaptive", "1800M / 15M, large packet adaptive", "1800M / 15M, medium packet adaptive", "1800M / 15M, small packet adaptive", "800M / 5M, large packet adaptive", "800M / 5M, medium packet adaptive", "800M / 5M, small packet adaptive", and the like.

[0079] In some embodiments, when the service packet is greater than or equal to a first preset value, the data packet is set as a large packet; when the service packet is less than the first preset value and greater than or equal to a second preset value, the data packet is set as a medium packet; and when the service packet is less than the second preset value, the data packet is set as a small packet. Optionally, the first preset value is 1MByte and the second preset value is 0.2MByte. The large packet service mainly refers to the highest proportion of large packet service, the medium packet service mainly refers to the highest proportion of medium packet service, and the small packet service mainly refers to the highest proportion of small packet service.

[0080] Further, for each type of cell, a benchmark cell is selected according to a preset optimization rule, and a traffic prediction model between the PRB utilization rate and the traffic of each type of cell is obtained through model training according to the PRB utilization rate and the traffic of the benchmark cell.

[0081] In the embodiment, in order to ensure the accuracy of the obtained traffic prediction model, the cells for training are selected, and high-quality cells are selected as benchmark cells. The traffic prediction model corresponding to each type of cell is obtained through training according to the traffic and the PRB utilization rate of the benchmark cells of different types.

[0082] In some embodiments, in order to ensure the accuracy of the trained model, the benchmark cell in each type of cell is selected through the set optimization rule, and different optimization rules can be set for different cell types. Exemplarily, the evaluation parameters in the optimization rule can include but are not limited to the average speed of users, the number of streaming media stalls, the congestion index of the cell, the complaint situation, and the PRB utilization rate, and the like.

[0083] In some embodiments, the cells with the average speed of users greater than a threshold value, the number of streaming media stalls lower than a threshold value, the PRB utilization rate of the cell lower than a certain threshold value, the number of complaints lower than a certain threshold value, and the congestion index lower than a threshold value can be set as the benchmark cells.

[0084] The network capacity expansion method provided in the embodiment trains according to the traffic and PRB utilization of different types of cells, obtains the traffic prediction model corresponding to different types of cells, and makes the determined growth traffic of each cell more in line with the actual situation of the cell, thereby improving the accuracy of cell growth traffic prediction.

[0085] Based on the content described in the above embodiments, in a feasible implementation manner, referring to Figure 3 , Figure 3 A sub-process schematic diagram of the network capacity expansion method provided in the embodiment.

[0086] In the embodiment, after the growth traffic of each cell is determined, potential capacity expansion cells in which the growth traffic is greater than a preset growth threshold are determined, and then target cells in which capacity expansion demand exists in each potential capacity expansion cell are determined according to preset evaluation parameters.

[0087] Optionally, the preset evaluation parameters include an alarm, a cell availability rate, a load balancing parameter, and an average CQI.

[0088] In some embodiments, the target cell in which capacity expansion demand exists in the potential capacity expansion cell can be determined by the following steps.

[0089] S301, it is judged whether the potential capacity expansion cell has a fault. If yes, S302 is performed; if no, S303 is performed.

[0090] In some embodiments, it can be determined whether an alarm exists in the potential capacity expansion cell. If the alarm exists, it is considered that the potential capacity expansion cell has a fault. If the alarm does not exist, it is considered that the potential capacity expansion cell does not have a fault.

[0091] In some embodiments, it can be judged whether the availability rate of the potential capacity expansion cell is less than a preset first threshold. If no, it is considered that the potential capacity expansion cell does not have a fault. If yes, it is considered that the potential capacity expansion cell has a fault.

[0092] Optionally, the preset first threshold can be 80%.

[0093] S302, fault repair is performed.

[0094] S303, it is judged whether the potential capacity expansion cell meets a load balancing condition. If yes, S304 is performed. If no, S305 is performed.

[0095] Optionally, when the difference between the PRB utilization of the busy hour and the PRB utilization of the coverage carrier is greater than 20%, it is determined that the load balancing condition is not met. Otherwise, it is determined that the load balancing condition is met.

[0096] S304, load balancing optimization is performed.

[0097] S305, judging whether the average channel quality indication of the potential capacity expansion cell is less than a preset second threshold value. If yes, S306 is executed; if no, the potential capacity expansion cell is determined as the target cell with capacity expansion demand.

[0098] Optionally, the preset second threshold value can be 10%.

[0099] S306, performing coverage / interference optimization.

[0100] The network capacity expansion method provided by the embodiments of the present application can more accurately determine the target cell with capacity expansion demand in each cell according to the growth traffic of each cell and the preset evaluation parameter, and prevent unnecessary resource waste.

[0101] Based on the content described in the above embodiments, in a feasible implementation, after the network capacity standard of the target cell is determined, whether the target cell meets the capacity expansion condition can be monitored according to the network capacity standard.

[0102] In some embodiments, the capacity expansion condition of each network capacity standard can be preset, and the capacity expansion condition includes at least two of the following conditions:

[0103] The busy hour rate of the target cell is less than the busy hour rate threshold value corresponding to the network capacity standard of the target cell;

[0104] The busy hour traffic of the target cell is greater than the busy hour traffic threshold value corresponding to the network capacity standard of the target cell;

[0105] The RRC connection number in the target cell is greater than the RRC connection number threshold value corresponding to the network capacity standard of the target cell.

[0106] In order to better understand the embodiments of the present application, refer to Table 1, which is a capacity expansion condition table of each network capacity standard.

[0107] Table 1: Capacity expansion condition table of each network capacity standard

[0108]

[0109] In some embodiments, the busy hour rate threshold value, the busy hour traffic threshold value and the RRC connection number threshold value corresponding to each network capacity standard can be accurately found from the user service (video) perception.

[0110] The network capacity expansion method provided by the embodiments of the present application can timely monitor the cell that needs to be expanded according to the network capacity standard of the target cell and the preset capacity expansion condition, so that the network can be expanded in time, and the accuracy of network capacity expansion can be improved.

[0111] Based on the content described in the above embodiments, in a feasible implementation, when it is monitored that the target cell satisfies the expansion condition, an expansion scheme corresponding to the target cell can be determined according to the growth traffic of the target cell.

[0112] In some embodiments, the carrier demand frequency of the target cell can be determined according to the growth traffic of the target cell, to avoid multiple expansions; and then an expansion scheme corresponding to the target cell can be determined according to the carrier demand frequency of the target cell, and the site distribution distance and the user distribution distance in the target cell.

[0113] In a feasible implementation, the carrier demand = 1 + sum (traffic growth prediction under the same sector) / 4GB.

[0114] In the above formula, in the case of CQI ≥ 10 and PRB utilization rate not less than 30%, the average busy time traffic of a video-aware high-quality cell is about 4GB.

[0115] Referring to Table 2, Table 2 is an expansion scheme table.

[0116] Table 2: Expansion scheme table

[0117]

[0118] In some embodiments, the expansion scheme can be accurately matched by combining the carrier demand, the user and site distribution, and new technologies and new devices.

[0119] In order to better understand the embodiments of the present application, refer to Figure 4 , Figure 4 Another sub-process diagram of a network expansion method provided by the embodiments of the present application.

[0120] The network expansion method provided by the embodiments of the present application can effectively improve the accuracy of the expansion scheme by using the above-mentioned refined and accurate expansion scheme.

[0121] Based on the content described in the above embodiments, the embodiments of the present application further provide a network expansion device, refer to Figure 5 , Figure 5 A program module diagram of a network expansion device provided in the embodiments of the present application, the network expansion device comprises:

[0122] The prediction module 501 inputs the current PRB utilization rate of each cell into a pre-trained traffic prediction model corresponding to the type of each cell to obtain the theoretical traffic of each cell, and predicts the growth traffic of each cell according to the actual traffic of each cell at present and the theoretical traffic. In the above formula, the traffic prediction model is used to predict the traffic of the cell according to the PRB utilization rate of the cell;

[0123] The screening module 502 is configured to determine a target cell having an expansion demand from the cells according to the growth traffic of the cells and a preset evaluation parameter;

[0124] The monitoring module 503 is configured to determine a network capacity standard of the target cell according to a preset value identifier of the target cell, and monitor whether the target cell meets an expansion condition according to the network capacity standard.

[0125] The processing module 504 is configured to determine an expansion scheme corresponding to the target cell according to the growth traffic of the target cell when it is monitored that the target cell meets the expansion condition.

[0126] The network expansion device provided in the application can accurately predict the growth traffic of each cell by classifying each cell and using the traffic prediction model between the PRB utilization rate and the traffic of each type of cell according to the type of each cell and the pre-trained traffic prediction model of each type of cell. Then, the target cell having an expansion demand is determined from the cells according to the growth traffic of each cell and a preset evaluation parameter, the network capacity standard of the target cell is determined according to a preset value identifier of the target cell, and whether the target cell meets an expansion condition is monitored according to the network capacity standard. When it is monitored that the target cell meets the expansion condition, the expansion scheme corresponding to the target cell is determined according to the growth traffic of the target cell, so that the network can be expanded in time and the accuracy of network expansion is improved.

[0127] In an available implementation, the device further comprises:

[0128] The classification module is configured to classify the cells based on a machine learning classification algorithm according to cell features of the cells, and determine the type of each cell, wherein the cell features include at least one of the following features: cell geographical position, cell average traffic, cell user number, cell frequency / bandwidth, cell busy / idle time, and cell service type.

[0129] In an available implementation, the device further comprises:

[0130] The model training module is configured to, for each type of cell, screen a benchmark cell according to a preset optimization rule, and train a model according to the PRB utilization rate and the traffic of the benchmark cell to obtain a traffic prediction model corresponding to each type of cell.

[0131] In an available implementation, the preset evaluation parameter includes an alarm, a cell availability rate, a load balancing parameter, and an average CQI, and the screening module 502 is configured to:

[0132] The cell with the growth traffic greater than a preset growth threshold is determined as a potential capacity expansion cell; and the potential capacity expansion cell without an alarm, with a cell availability less than a preset first threshold, meeting a load balancing condition, and with an average CQI less than a preset second threshold is selected as the target cell with the capacity expansion demand.

[0133] In an implementation, the monitoring module 503 is configured to determine the network capacity standard of the target cell according to a preset value identifier of the target cell and a preset correspondence between various value identifiers and network capacity standards.

[0134] In an implementation, the monitoring module 503 is configured to:

[0135] The target cell meets the capacity expansion condition when at least two of the following conditions are met:

[0136] The busy hour rate of the target cell is less than a busy hour rate threshold corresponding to the network capacity standard of the target cell; the busy hour traffic of the target cell is greater than a busy hour traffic threshold corresponding to the network capacity standard of the target cell; and the number of RRC connections in the target cell is greater than an RRC connection number threshold corresponding to the network capacity standard of the target cell.

[0137] In an implementation, the processing module 504 is configured to:

[0138] The carrier demand frequency of the target cell is determined according to the growth traffic of the target cell; and the capacity expansion scheme corresponding to the target cell is determined according to the carrier demand frequency of the target cell, and the site distribution distance and the user distribution distance in the target cell.

[0139] It should be noted that the specific implementation of the prediction module 501, the screening module 502, the monitoring module 503, and the processing module 504 in the embodiments of the present application can refer to the related content in the embodiments shown in Figures 2 to 4 , which will not be described here in detail.

[0140] Further, based on the content described in the above embodiments, the embodiments of the present application also provide an electronic device, which includes at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory to implement each step of the network capacity expansion method described in the above embodiments, which will not be described here in detail.

[0141] For better understanding of the embodiments of the present application, reference is made to Figure 6 , Figure 6 A hardware structure schematic diagram of an electronic device provided in the embodiments of the present application.

[0142] As Figure 6 shown in the figure, the electronic device 60 of the embodiment comprises a processor 601 and a memory 602; wherein:

[0143] The memory 602 is configured to store computer-executable instructions.

[0144] The processor 601 is configured to execute the computer-executable instructions stored in the memory, so as to implement each step of the network expansion method described in the above embodiment, which will not be repeated here.

[0145] Optionally, the memory 602 can be independent or integrated with the processor 601.

[0146] When the memory 602 is independently arranged, the device further comprises a bus 603 configured to connect the memory 602 and the processor 601.

[0147] Further, based on the above description, the embodiment of the present application further provides a computer readable storage medium, which stores computer-executable instructions, when the processor executes the computer-executable instructions, each step of the network expansion method described in the above embodiment is implemented, which will not be repeated here.

[0148] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0149] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the embodiment.

[0150] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each module can be physically present alone, or two or more modules can be integrated in one unit. The above module integrated unit can be realized in the form of hardware or hardware plus software function unit.

[0151] The integrated module realized in the form of the software function module can be stored in a computer readable storage medium. The software function module is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of steps of the method according to various embodiments of the present application.

[0152] It should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0153] The memory can include a high-speed RAM memory, and can also include a non-volatile storage NVM, for example, at least one disk memory, and can also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0154] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit only one bus or one type of bus.

[0155] The storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0156] An example storage medium is coupled to the processor such that the processor can read information from, and can write information to, the storage medium. Of course, the storage medium can be a part of the processor. Consistent with the teachings provided herein, the processor (acting in response to a plurality of instructions executed by the processor) can be capable of implementing any of the features, steps, or functions disclosed herein, including the methods and techniques described above. The storage medium can be realized as a collection of programming instructions that, when executed by the processor, implement the features, steps, or functions disclosed herein. The storage medium can be realized as a volatile memory, a non-volatile memory, or a combination of volatile and non-volatile memory. The storage medium can include, but is not limited to, RAM, ROM, EEPROM, flash memory, or a combination of different memory storage mediums. For example, a non-transitory computer readable storage medium can be realized as a volatile memory, a non-volatile memory, or a combination of volatile and non-volatile memory. Of course, the storage medium can be a part of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Alternatively, the processor and the storage medium can be located in a circuit.

[0157] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a computer readable storage medium. The program executes to perform the steps of the above-mentioned method embodiments; and the foregoing storage medium includes ROM, RAM, magnetic disk or optical disk and various storage medium capable of storing program codes.

[0158] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the above embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A network expansion method, characterized in that, The method includes: The current physical resource block (PRB) utilization rate of each cell is input into a pre-trained traffic prediction model corresponding to the type of each cell to obtain the theoretical traffic of each cell. Based on the current actual traffic of each cell and the theoretical traffic, the growth traffic of each cell is predicted. The traffic prediction model is used to predict the traffic of a cell based on the PRB utilization rate of the cell. Based on the increased traffic of each cell and preset evaluation parameters, target cells with expansion needs are determined. The preset evaluation parameters include alarms, cell availability, load balancing parameters, and average channel quality indicator (CQI). Cells with increased traffic exceeding a preset growth threshold are identified as potential expansion cells. Potential expansion cells that have no alarms, cell availability less than a preset first threshold, meet load balancing conditions, and have an average CQI less than a preset second threshold are selected as target cells with expansion needs. Based on the preset value identifier of the target cell, the network capacity standard of the target cell is determined, and based on the network capacity standard, the target cell is monitored to see if it meets the expansion conditions. When the target cell is detected to meet the expansion conditions, the expansion plan corresponding to the target cell is determined based on the increased traffic of the target cell. The step of monitoring whether the target cell meets the expansion conditions according to the network capacity standard includes: The target cell is determined to meet the expansion conditions when at least two of the following conditions are met: The busy-hour rate of the target cell is less than the busy-hour rate threshold corresponding to the network capacity standard of the target cell; The busy-hour traffic of the target cell is greater than the busy-hour traffic threshold corresponding to the network capacity standard of the target cell; The number of Radio Resource Control (RRC) connections in the target cell is greater than the RRC connection threshold corresponding to the network capacity standard of the target cell.

2. The method according to claim 1, characterized in that, Also includes: Based on the characteristics of each cell, the cells are classified using a machine learning classification algorithm to determine the type of each cell. The cell features include the following features: At least one of the following: cell location, average cell traffic, number of cell users, cell frequency / bandwidth, cell busy / idle time, and cell service type.

3. The method according to claim 2, characterized in that, Also includes: For each type of community, benchmark communities are selected based on preset optimization rules; Based on the PRB utilization rate and traffic of the benchmark cell, model training is performed to obtain traffic prediction models corresponding to various types of cells.

4. The method according to claim 1, characterized in that, The step of determining the network capacity standard of the target cell based on the preset value identifier of the target cell includes: Based on the preset value identifier of the target cell and the correspondence between various preset value identifiers and network capacity standards, the network capacity standard of the target cell is determined.

5. The method according to claim 1, characterized in that, The step of determining the expansion plan corresponding to the target cell based on the increased traffic of the target cell includes: Based on the increased traffic of the target cell, determine the carrier demand frequency of the target cell; Based on the carrier demand frequency of the target cell, as well as the site distribution distance and user distribution distance within the target cell, the corresponding expansion scheme for the target cell is determined.

6. A network expansion device, characterized in that, The device includes: The prediction module inputs the current physical resource block (PRB) utilization rate of each cell into a pre-trained traffic prediction model corresponding to the type of each cell to obtain the theoretical traffic of each cell, and predicts the growth traffic of each cell based on the current actual traffic of each cell and the theoretical traffic. The traffic prediction model is used to predict the traffic of a cell based on the PRB utilization rate of the cell. The filtering module is used to determine the target cells with expansion needs among the cells based on the increased traffic of each cell and preset evaluation parameters. The preset evaluation parameters include alarms, cell availability, load balancing parameters, and average channel quality indicator (CQI). Cells with increased traffic exceeding a preset increase threshold are identified as potential expansion cells. Potential expansion cells that have no alarms, cell availability less than a preset first threshold, meet load balancing conditions, and have an average CQI less than a preset second threshold are selected as the target cells with expansion needs. The monitoring module is used to determine the network capacity standard of the target cell based on the preset value identifier of the target cell, and to monitor whether the target cell meets the expansion conditions based on the network capacity standard. The processing module is used to determine the expansion scheme corresponding to the target cell based on the increased traffic of the target cell when the target cell is detected to meet the expansion conditions. The monitoring module is specifically configured to determine that the target cell meets the expansion conditions when at least two of the following conditions are met: The busy-hour rate of the target cell is less than the busy-hour rate threshold corresponding to the network capacity standard of the target cell; The busy-hour traffic of the target cell is greater than the busy-hour traffic threshold corresponding to the network capacity standard of the target cell; The number of Radio Resource Control (RRC) connections in the target cell is greater than the RRC connection threshold corresponding to the network capacity standard of the target cell.

7. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the network expansion method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by the processor, implement the network expansion method as described in any one of claims 1 to 5.

Images