High-load cell identification method, device, storage medium and electronic device

Abstract

The present disclosure provides a high-load cell identification method, device, storage medium and electronic device; it relates to the field of communication technology. The method includes: obtaining the original performance data of the target cell, the original performance data includes first performance data and original second performance data; fitting the first performance data and the original second performance data to obtain linear second performance data corresponding to the first performance data; when the load of the target cell is at the critical point of full load, determining the amount of resources when the target cell reaches the perception inflection point according to the linear second performance data; calculating the Treynor demand index corresponding to the original second performance data of the target period according to the linear second performance data and the amount of resources when the target cell reaches the perception inflection point, and identifying the network load of the target cell according to the Treynor demand index. The present disclosure can accurately quantify and identify high-load cells, and the output result is more accurate.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a high-load cell identification method, a high-load cell identification device, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the development of 4 / 5G networks and the increase in users, the demand for network optimization is getting higher and higher. For example, when resources are limited, it is necessary to conduct in-depth and detailed analysis of the network capacity of the cell to identify whether the cell meets the conditions for capacity expansion and the amount of resources required for capacity expansion in order to optimize the network capacity of the cell.

[0003] In the related technology, the cell to be expanded can be identified according to the specified expansion threshold. For example, if a cell meets the expansion threshold during busy hours for 4 consecutive weeks in a month and at least 4 days out of 7 days a week, the cell can be defined as a cell to be expanded. The expansion threshold can refer to meeting large traffic, such as the average downlink PRB utilization of the cell during busy hours is greater than 50% and the cell busy throughput is greater than 6GB; it can also refer to meeting multiple users, such as the average downlink PRB utilization of the cell during busy hours is greater than 50% and the average number of users establishing RRC connections is greater than 200 at the maximum.

[0004] However, when using the expansion threshold to identify the cell to be expanded, it is impossible to accurately expand the cell, which may result in a small amount of resources invested and fail to solve the actual problem. It may also result in too much resources invested, resulting in a waste of resources and low resource utilization.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The present disclosure provides a high-load cell identification method, a high-load cell identification device, a computer-readable storage medium and an electronic device, thereby overcoming the problem of being unable to accurately identify a cell to be expanded and unable to accurately expand the capacity due to the limitations of related technologies, at least to a certain extent.

[0007] The present disclosure provides a high-load cell identification method, comprising:

[0008] Acquire original performance data of the target cell, where the original performance data includes first performance data and original second performance data;

[0009] Fitting the first performance data and the original second performance data to obtain linear second performance data corresponding to the first performance data;

[0010] When the load of the target cell is at a full load critical point, determining, according to the linear second performance data, an amount of resources when the target cell reaches a perception inflection point;

[0011] The Treynor demand index corresponding to the original second performance data of the target time period is calculated based on the linear second performance data and the amount of resources when the target cell reaches the perception inflection point, and the network load of the target cell is identified based on the Treynor demand index.

[0012] In an exemplary embodiment of the present disclosure, the acquiring original performance data of the target cell includes:

[0013] Extracting original performance data of the target cell from background network management performance data;

[0014] The first performance data and the original second performance data are selected from the original performance data as sample data to fit the sample data.

[0015] In an exemplary embodiment of the present disclosure, fitting the first performance data and the original second performance data to obtain linear second performance data corresponding to the first performance data includes:

[0016] Performing linear fitting on the first performance data and the original second performance data, and obtaining a corresponding fitting curve when the fitting error is minimum;

[0017] The first performance data and fitting parameters in the fitting curve are calculated to obtain linear second performance data corresponding to the first performance data.

[0018] In an exemplary embodiment of the present disclosure, when the target cell load is at a full load critical point, determining, according to the linear second performance data, the amount of resources when the target cell reaches a perception inflection point includes:

[0019] Fitting the first performance data and the original second performance data within the target interval to determine a perception inflection point of the target cell;

[0020] When the target cell load is at a full load critical point, the resource amount of the target cell when reaching a perception inflection point is calculated based on the linear second performance data and the original second performance data in the target interval.

[0021] In an exemplary embodiment of the present disclosure, the step of calculating the Treynor demand index corresponding to the original second performance data of the target time period according to the linear second performance data and the amount of resources when the target cell reaches the perception inflection point includes:

[0022] according to

[0023] T=(RP -R f ) / β p

[0024] Obtaining the Treynor demand index of the target cell;

[0025] Where T is the Treynor demand index of the target cell, R P is the linear second performance data, R f is the original second performance data of the target period, β p It is the amount of resources when the target cell reaches the perception inflection point.

[0026] In an exemplary embodiment of the present disclosure, the method further includes:

[0027] When the target cell is a high-load cell, the resource demand of the target cell is determined according to the mapping relationship between the Treynor demand index and the resource demand, and the target cell is accurately expanded according to the resource demand.

[0028] In an exemplary embodiment of the present disclosure, the first performance data is the average number of users establishing an RRC connection, and the original second performance data is the average downlink PRB utilization and / or user plane PDCP downlink traffic.

[0029] In an exemplary embodiment of the present disclosure, the method further includes:

[0030] When the cell to be evaluated meets a preset condition, the cell to be evaluated is selected as a target cell; wherein the preset condition is that an average downlink PRB utilization rate is greater than a preset utilization rate threshold.

[0031] The present disclosure provides a high-load cell identification device, comprising:

[0032] A performance data acquisition module, used to acquire original performance data of the target cell, wherein the original performance data includes first performance data and original second performance data;

[0033] A first data determination module, used for fitting the first performance data and original second performance data to obtain linear second performance data corresponding to the first performance data;

[0034] A second data determination module, configured to determine, when the load of the target cell is at a critical point of full load, the amount of resources when the target cell reaches a perception inflection point according to the linear second performance data;

[0035] The network load identification module is used to calculate the Treynor demand index corresponding to the original second performance data of the target time period based on the linear second performance data and the resource amount when the target cell reaches the perception inflection point, and identify the network load of the target cell based on the Treynor demand index.

[0036] The present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, any one of the above-mentioned methods is implemented.

[0037] The present disclosure provides an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned methods by executing the executable instructions.

[0038] The exemplary embodiments of the present disclosure may have some or all of the following beneficial effects:

[0039] In the high-load cell identification method provided in the exemplary implementation of the present disclosure, the first performance data and the original second performance data of the target cell are obtained; the first performance data and the original second performance data are fitted to obtain the linear second performance data; when the target cell load is at the critical point of full load, the amount of resources when the target cell reaches the perceived inflection point is determined according to the linear second performance data; the Treynor demand index corresponding to the original second performance data of the target period is calculated according to the linear second performance data and the amount of resources when the target cell reaches the perceived inflection point, and the network load of the target cell is identified according to the Treynor demand index. On the one hand, the distribution relationship between the first performance data and the original second performance data obtained by fitting is used to build a model, and the Treynor demand index of the target cell is calculated according to the modeling result. This process does not require artificial definition of parameters, can avoid human interference, and the calculation result is more objective; on the other hand, by calculating the Treynor demand index of the target cell, the resource demand of the target cell can be accurately quantified and accurately expanded, thereby improving resource utilization.

[0040] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0042] Figure 1A schematic diagram showing an exemplary system architecture of a high-load cell identification method and device to which the embodiments of the present disclosure can be applied;

[0043] Figure 2 A flowchart of a high-load cell identification method according to an embodiment of the present disclosure is schematically shown;

[0044] Figure 3 Schematically shows a flow chart for calculating linear second performance data according to an embodiment of the present disclosure;

[0045] Figure 4 A schematic diagram schematically shows a resource demand change curve according to an embodiment of the present disclosure;

[0046] Figure 5 A flowchart of calculating the amount of resources when a cell reaches a perception inflection point according to an embodiment of the present disclosure is schematically shown;

[0047] Figure 6 A schematic diagram schematically illustrates a depression index curve according to an embodiment of the present disclosure;

[0048] Figure 7 A block diagram of a high-load cell identification device according to an embodiment of the present disclosure is schematically shown;

[0049] Figure 8 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0050] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0051] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0052] Figure 1 A schematic diagram of a system architecture of an exemplary application environment in which a high-load cell identification method and apparatus according to an embodiment of the present disclosure can be applied is shown.

[0053] like Figure 1 As shown, the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc. The terminal devices 101, 102, 103 may be various electronic devices, including but not limited to desktop computers, portable computers, smart phones, and tablet computers, etc. It should be understood that Figure 1 The number of terminal devices, networks and servers in is only schematic. According to the implementation needs, there can be any number of terminal devices, networks and servers. For example, server 105 can be a server cluster composed of multiple servers, etc. The server can obtain the original performance data of the target cell, and fit the first performance data and the original second performance data in the original performance data to obtain the linear second performance data when the resources are not suppressed. When the load of the target cell is the critical point of full load, the amount of resources when the target cell reaches the perception inflection point can be determined. When the server obtains the original second performance data of the target cell in the most recent period, the linear second performance data and the amount of resources when the target cell reaches the perception inflection point can be used to calculate the Treynor demand index of the target cell in the period, and then the network load state of the target cell can be identified according to the Treynor demand index of the period. When it is determined that the target cell is a high-load cell, the resource demand of the cell can be quantified to accurately optimize the wireless network of the cell.

[0054] The high-load cell identification method provided in the embodiment of the present disclosure is generally executed by the server 105, and accordingly, the high-load cell identification device is generally set in the server 105. After the server executes, the identification result can be sent to the terminal device, and the terminal device displays it to the user. However, it is easy for those skilled in the art to understand that the high-load cell identification method provided in the embodiment of the present disclosure can also be executed by one or more of the terminal devices 101, 102, and 103, and accordingly, the high-load cell identification device can also be set in the terminal devices 101, 102, and 103. For example, after being executed by the terminal device, the identification result can be directly displayed on the display screen of the terminal device, and this is not particularly limited in this exemplary embodiment.

[0055] The technical solution of the embodiment of the present disclosure is described in detail below:

[0056] In the application process of LTE (Long Term Evolution) network, the designated capacity expansion threshold can be used to identify the cell to be expanded, which is an extensive threshold control valve. For example, if a cell meets the capacity expansion threshold during busy hours for 4 consecutive weeks in a month and at least 4 days out of 7 days a week, the cell can be defined as a cell to be expanded. The capacity expansion threshold can refer to meeting large traffic, such as the average downlink PRB utilization of the cell during busy hours is greater than 50% and the cell busy throughput is greater than 6GB; it can also refer to multiple users, such as the average downlink PRB utilization of the cell during busy hours is greater than 50% and the maximum number of valid RRC links is greater than 200.

[0057] When using the expansion threshold to identify the cell to be expanded, the longer it takes to meet the expansion threshold, it can only indicate that the cell has a continuous demand for resources during this period of time, and it cannot reflect the degree of demand for resources. When actually investing resources, limited resources need to be invested in the most demanding points to improve resource utilization. When too many resources are invested and secondary dismantling and application are carried out, it is not only difficult, but may also affect the overall network layout and networking structure, resulting in waste of resources and reduced resource utilization. In addition, this method cannot quantify the degree of depression in the cell to be expanded. For example, it is necessary to expand the capacity of several specific carriers to alleviate the over-busy cell, or the network depression can be alleviated through network balancing and other means, and no hardware investment is required. Therefore, the traditional solution is insufficient in quantitative reflection, resulting in the inability to accurately expand the capacity of the cell.

[0058] Based on one or more of the above problems, this exemplary embodiment provides a high-load cell identification method, which can be applied to the above server 105, and can also be applied to one or more of the above terminal devices 101, 102, 103, which is not particularly limited in this exemplary embodiment. Figure 2As shown, the high-load cell identification method may include the following steps S210 to S240:

[0059] Step S210. Acquire original performance data of the target cell, where the original performance data includes first performance data and original second performance data;

[0060] Step S220: Fit the first performance data and the original second performance data to obtain linear second performance data corresponding to the first performance data;

[0061] Step S230. When the load of the target cell is at the critical point of full load, determine the amount of resources of the target cell when it reaches the perception inflection point according to the linear second performance data;

[0062] Step S240. Calculate the Treynor demand index corresponding to the original second performance data of the target time period based on the linear second performance data and the amount of resources when the target cell reaches the perception inflection point, and identify the network load of the target cell based on the Treynor demand index.

[0063] In the high-load cell identification method provided in the exemplary implementation of the present disclosure, the first performance data and the original second performance data of the target cell are obtained; the first performance data and the original second performance data are fitted to obtain the linear second performance data; when the target cell load is at the critical point of full load, the amount of resources when the target cell reaches the perceived inflection point is determined according to the linear second performance data; the Treynor demand index corresponding to the original second performance data of the target period is calculated according to the linear second performance data and the amount of resources when the target cell reaches the perceived inflection point, and the network load of the target cell is identified according to the Treynor demand index. On the one hand, the distribution relationship between the first performance data and the original second performance data obtained by fitting is used to build a model, and the Treynor demand index of the target cell is calculated according to the modeling result. This process does not require artificial definition of parameters, can avoid human interference, and the calculation result is more objective; on the other hand, by calculating the Treynor demand index of the target cell, the resource demand of the target cell can be accurately quantified and accurately expanded, thereby improving resource utilization.

[0064] Next, the above steps of this exemplary embodiment are described in more detail.

[0065] In step S210, original performance data of the target cell is acquired, where the original performance data includes first performance data and original second performance data.

[0066] In this example implementation, the original performance data refers to a performance indicator that can be used to measure the quality of the network, such as a key performance indicator (KPI). In the process of KPI monitoring and optimization, several important indicators can usually be selected to reflect the overall performance of the network. Exemplarily, the first performance data and the original second performance data in the original performance data can be selected to analyze the network performance. Among them, the first performance data can be the average number of users for establishing an RRC (Radio Resource Control) connection. The average number of users for establishing an RRC connection can count the average number of RRC connections that exist at the same time. By sampling at a preset measurement time interval, the number of RRC connections that exist at the same time in the target cell can be obtained and the average value can be taken. The original second performance data can be a load indicator, such as the average utilization rate of the downlink PRB (Physical Resource Block). The average utilization rate of the downlink PRB refers to the average number of downlink PRB occupancy / the number of cell PRBs*100%, which can be used to reflect the usage of downlink physical resources. The original second performance data may also be a cell busy-time throughput indicator. The cell busy-time throughput may adopt air interface service traffic, which may be divided into uplink and downlink service bytes. This indicator reflects the uplink and downlink traffic of the air interface. For example, it may be user plane PDCP downlink traffic. Among them, user plane PDCP downlink traffic may be used to reflect the traffic situation of the system PDCP layer. It should be noted that the original second performance data in this example refers to the actual downlink PRB average utilization or actual user plane PDCP downlink traffic of the target cell when it is subject to resource constraints.

[0067] When the cell to be evaluated meets the preset conditions, the cell to be evaluated can be selected as the target cell. The preset condition may be that the average downlink PRB utilization is greater than a preset utilization threshold. Exemplarily, when the average downlink PRB utilization of a cell to be evaluated is greater than 70%, the cell can be selected as the target cell to quantitatively identify the network load of the cell. In other examples, cells with an average downlink PRB utilization greater than 50% can also be used as target cells. It should be noted that the preset conditions for selecting the target cell can be set according to actual needs, and the present disclosure does not make specific limitations on this.

[0068] The wireless communication network allows each base station to actively report the performance monitoring data inside the base station to the network management. Therefore, when obtaining the original performance data of the target cell, the original performance data of the target cell can be extracted from the background network management performance data, and several important indicators can be selected from the original performance data as sample data. Exemplarily, the network bandwidth resources, average number of users for RRC connection establishment, average utilization of downlink PRB, user-plane PDCP downlink traffic, average user rate and other performance data of the target cell in the past 7 days can be extracted from the network management. KPIs of multiple target cells in the past 7 days can also be extracted from the network management at the same time to quantify and identify the network loads of multiple target cells. It is understandable that any number of sample data can be obtained according to implementation needs. The selected sample data can be statistically analyzed later, such as fitting and analyzing the sample data. Specifically, the performance data such as the average number of users for RRC connection establishment, the average utilization of downlink PRB, the user-plane PDCP downlink traffic and the average user rate can be used to fit and calculate the network suppression degree of the target cell and the corresponding Treynor demand index, and then the resource demand of the cell can be accurately quantified based on the Treynor demand index and network bandwidth resources of the target cell. In other examples, a drive test tool may also be used to perform static testing to obtain raw performance data, which is not specifically limited in the present disclosure.

[0069] In step S220, the first performance data and the original second performance data are fitted to obtain linear second performance data corresponding to the first performance data.

[0070] In a preferred embodiment, the degree of network suppression can be obtained based on the fitting algorithm of the Treynor demand index and the original performance data, and then the capacity can be expanded according to the suppressed resource amount. Among them, there is no need to define a specific threshold, only the Treynor demand index of the target cell needs to be calculated, and the resource demand degree of the target cell can be reflected by the size of the Treynor demand index. For example, the larger the Treynor demand index, the higher the network suppression degree of the target cell, and the greater the resource demand. Conversely, the smaller the resource demand. Finally, the amount of resources that need to be invested in the target cell can be quantified based on the corresponding relationship between the Treynor demand index and the resource demand.

[0071] Specifically, it can be based on:

[0072] T=(R P -R f ) / β p

[0073] Calculate the Treynor demand index of the target cell. Where: T is the Treynor demand index of the target cell, R PIt is the linear second performance data, which can represent the linear resource amount corresponding to the traffic edge of the target cell when resources are not limited, such as the average downlink PRB utilization and user plane PDCP downlink traffic when resources are not limited. f It is the original second performance data, which can indicate the amount of resources of the target cell when the target cell reaches the smoothed maximum value when the resources are limited, such as the actual downlink PRB average utilization rate and user plane PDCP downlink traffic of the target cell in a certain period of time. p It is the amount of resources when the target cell reaches the perception inflection point.

[0074] For example, for a target cell in a certain period of time, the actual average downlink PRB utilization rate of the target cell in the period of time can be obtained from the network management. For example, if the actual average downlink PRB utilization rate is 50% (i.e., R f ). In the case of unlimited resources, the average downlink PRB utilization rate of the target cell at this moment can reach 65% (i.e. R P ). P -R f It can indicate the network suppression degree of the target cell. P Greater than R f When R P Less than R f , it can indicate that the network of the target cell is not suppressed and is in idle state.

[0075] In the process of calculating the Treynor demand index of the target cell, the original second performance data R f For example, the average utilization of downlink PRBs and the downlink PDCP traffic of the user plane can be directly obtained from the network management. P , it is necessary to fit the first performance data and the original second performance data to obtain the linear second performance data R corresponding to the first performance data P For example, the average number of users establishing RRC connections and the average downlink PRB utilization rate may be fitted, or the average number of users establishing RRC connections and the user plane PDCP downlink traffic may be fitted. Figure 3 As shown, the linear second performance data R can be calculated according to step S310 and step S320. P .

[0076] Step S310: Perform linear fitting on the first performance data and the original second performance data, and obtain a corresponding fitting curve when the fitting error is minimum.

[0077] Preferably, the first performance data and the original second performance data can be linearly fitted, and the linear second performance data R can be calculated according to the fitting result. P For example, a linear fit may be performed on the average number of users establishing RRC connections and the actual average downlink PRB utilization in a large amount of sample data to obtain a distribution relationship between the average number of users establishing RRC connections and the average downlink PRB utilization, such as a one-dimensional linear relationship y=kx+b.

[0078] Specifically, refer to Figure 4 As shown, Figure 4 The scatter plot and linear fitting curve of the average number of users establishing RRC connections and the average downlink PRB utilization generated by a large amount of sample data are shown. Each discrete point in the scatter plot can represent the value of the actual average downlink PRB utilization corresponding to the average number of users establishing RRC connections. By formulating a large number of discrete points in the scatter plot, the analytical expression is continuously approached to the discrete points. When the fitting error is minimized, some discrete points with large deviations can be discarded, and the final linear fitting curve is y=3.6783x+93.424. Among them, the horizontal axis x is the average number of users establishing RRC connections, the vertical axis y is the average downlink PRB utilization, and R 2 It can express the fit in a one-dimensional linear relationship, given by Figure 4 From the linear fitting curve in R 2 =0.6049, which indicates that 60.49% of the sample data satisfy the analytical expression y=3.6783x+93.424. In addition, the fitting error can be the sum variance, which can calculate the sum of squares of the errors of the corresponding points of the fitting data and the original data. The smaller the sum variance, the better the model selection and fitting effect, and the more accurate the data prediction. The fitting error can also be the mean square error, the root mean square, etc., which is not specifically limited in the present disclosure.

[0079] Step S320: Calculate the first performance data and the fitting parameters in the fitting curve to obtain linear second performance data corresponding to the first performance data.

[0080] For example, when the distribution relationship between the average number of users establishing RRC connections and the average downlink PRB utilization is a one-dimensional linear relationship y=kx+b, a large number of sample data can be statistically analyzed to obtain the fitting parameters k and b. By inputting different first performance data, the corresponding linear second performance data can be calculated. Figure 4 The linear fitting curve y=3.6783x+93.424 obtained by fitting in the example is used for explanation. When x is the average number of users establishing different RRC connections, the corresponding y value can be calculated according to the linear fitting curve y=3.6783x+93.424, that is, the average downlink PRB utilization when resources are not limited can be obtained.

[0081] In this example, a one-dimensional linear relationship graph between the average number of users establishing RRC connections and the average downlink PRB utilization can be obtained through scattering and fitting of a large amount of data, that is, a trend graph of resources and users can be obtained. By discarding 10% of the abrupt data, a resource demand change curve containing 90% of the data volume can be obtained.

[0082] In this example, the data model of resources and users can be established through the distribution relationship between existing resources and users, so that the resource demand of PRB under the condition of large number of users, that is, the suppression index, can be predicted, so as to facilitate the subsequent determination of the resource demand of high-load cells according to the severity of the suppression index. This process does not require manual definition of parameters, avoids manual interference results, and the output results are more objective.

[0083] In step S230, when the load of the target cell is at a full load critical point, the amount of resources of the target cell when it reaches a perception inflection point is determined according to the linear second performance data.

[0084] In the process of calculating the Treynor demand index of the target cell, the present invention not only considers the relationship between resources and services, but also introduces the coefficient of the perception inflection point, combines the quantitative identification of high-load cells with user usage, and can fully consider the user's real perception when expanding resources.

[0085] Specifically, according to T=(R P -R f ) / β p When calculating the Treynor demand index T of the target cell, the linear second performance data R can be calculated according to step S220. P , the original second performance data R can be directly extracted from the network management f At present, it is also necessary to determine the resource amount β when the target cell reaches the perception inflection point p In one example, refer to Figure 5 As shown, the resource amount β when the target cell reaches the perception inflection point can be determined according to step S510 and step S520. p .

[0086] Step S510: Fitting the first performance data and the original second performance data within the target interval to determine the perception inflection point of the target cell;

[0087] When the average downlink PRB utilization rate of the target cell is between 70% and 90%, the network of the cell is at the critical point of being suppressed. Therefore, R can be selected accordingly. fThe average downlink PRB utilization is 70%-90%. By fitting the average downlink PRB utilization in the interval [70%, 90%] and the corresponding average number of users to establish RRC connections, the perceived inflection point of the target cell can be obtained by fitting. In other examples, the average user rate corresponding to the average downlink PRB utilization of 70%-90% can also be selected to fit and determine the perceived inflection point of the target cell. It should be noted that the average user rate can also be obtained directly from the network management.

[0088] Step S520. When the target cell load reaches the critical point of full load, the resource amount of the target cell when reaching the perception inflection point is calculated according to the linear second performance data and the original second performance data in the target interval.

[0089] When the target cell load is at the critical point of full load, that is, when the equipment resources of the target cell have just reached full load operation, the Treynor demand index T corresponding to the target cell is 100%, which is equivalent to the target cell network being just at the edge of depression under the existing network bandwidth resources. In order to further illustrate the corresponding relationship between the Treynor demand index and resources, for example, when the target cell Treynor demand index is calculated to be 150%, it means that the cell is currently in a depressed state, and 1.5 times the resources are actually needed to alleviate the network congestion of the target cell, that is, 0.5 times the bandwidth resources need to be invested on the basis of the existing network bandwidth resources.

[0090] Specifically, when calculating the resource amount of the perception inflection point of the target cell, T = 100%, R f is the average utilization rate of downlink PRB at the perception inflection point, and the linear second performance data R P The average downlink PRB utilization rate when the resources corresponding to the perception inflection point are not limited is calculated according to step S220. P , R f When it is known, it can be calculated according to T=(R P -R f ) / β p Calculate the resource amount β when the target cell reaches the perception inflection point p .

[0091] Exemplary, reference Figure 6 As shown, Figure 6 A suppression index curve that can be used to represent the degree of network suppression of a target cell is shown. Figure 6 The horizontal axis is the average number of users establishing RRC connections, and the vertical axis is the average downlink PRB utilization (also known as downlink channel PRB resource utilization) and the user plane PDCP downlink traffic (also known as user plane PDCP SDU downlink data volume). Figure 6The figure also includes several scattered points 601, each of which represents the average downlink PRB utilization rate corresponding to the average number of users establishing RRC connections in the target cell within a certain period of time (such as one hour). The oblique line 602 is the resource demand change curve obtained by fitting the average number of users establishing RRC connections and the linear average downlink PRB utilization rate, corresponding to Figure 4 The vertical lines 603 and 606 are used to remove 10% of the abrupt data. The vertical line 604 is used to indicate the position where the network of the target cell begins to be in a suppressed state, and is also the starting point for calculating the perception inflection point. The vertical line 605 is used to indicate the resource demand line when the average number of users establishing RRC connections in the target cell in the recent period (such as the last hour) is 49. The intersection 607 of the resource demand line 605 and the resource demand change curve 602 is the average downlink PRB utilization rate R when the network is not suppressed. P , the actual downlink PRB average utilization rate R in this period f It can be obtained from the suppression index curve, which corresponds to the intersection 608 in the figure, or it can be directly extracted from the network management, R P and R f The difference between represents the network suppression degree of the target cell in the period. Similarly, the oblique line 609 is a resource demand change curve obtained by fitting the average number of users for establishing RRC connections and the user plane PDCP downlink traffic, and each of the scattered points 610 represents the user plane PDCP downlink traffic corresponding to the average number of users for establishing RRC connections in the target cell in a certain period.

[0092] In step S240, the Treynor demand index corresponding to the original second performance data of the target time period is calculated based on the linear second performance data and the amount of resources when the target cell reaches the perception inflection point, and the network load of the target cell is identified based on the Treynor demand index.

[0093] The second linear performance data R of the target cell can be calculated according to step S220 P , R P is the average downlink PRB utilization when resources are not limited, and the resource amount β when the target cell reaches the perception inflection point can be calculated according to step S230 p Then, the original second performance data R of the target period can be extracted from the network management f , and according to:

[0094] T=(R P -R f ) / β p

[0095] The Treynor demand index of the target cell in the target time period is calculated. For example, the actual downlink PRB average utilization rate of the target cell in the recent time period can be extracted to calculate the Treynor demand index of the target cell in the recent time period. Exemplarily, when the Treynor demand index of the target cell is greater than the Treynor demand index threshold, for example, the first threshold of the Treynor demand index can be set to 100%, and the second threshold of the Treynor demand index can be set to 150%. When the Treynor demand index of the target cell T<100%, it can be determined that the target cell is a cell with normal network load, that is, the network of the target cell is not suppressed under the existing network bandwidth resources. When the Treynor demand index of the target cell is 100%≤T<150%, it can be determined that the target cell is a high-load cell, that is, the network of the target cell is in a suppressed state under the existing network bandwidth resources, and the degree of suppression is low. When the Treynor demand index of the target cell T≥150%, it can be determined that the target cell is an ultra-high-load cell, that is, the degree of suppression of the network of the target cell is high under the existing network bandwidth resources. For example, when the Treynor demand index T of the target cell is 110%, it is equivalent to expanding the existing network capacity by 10%. Compared with the ultra-high load cell, it has a lower priority for expansion, and the network can be optimized by means of carrier balancing. When the Treynor demand index T is greater than 150%, the network depression cannot be alleviated by optimization means, and it can only be solved by expansion.

[0096] When there are multiple ultra-high-load cells that need to be expanded, the calculated Treynor demand index of each cell can be sorted, such as in descending order. The higher the ranking, the greater the degree of network depression in the cell, and the greater the corresponding resource demand. Therefore, the priority of each cell for expansion can be determined according to the sorted Treynor demand index, and then the efficiency of decision-making resource investment can be maximized according to the priority level and demand level when resources are limited.

[0097] When accurately expanding the capacity of the target cell, the resource demand of the target cell can be determined based on the mapping relationship between the Treynor demand index and the resource demand, and the target cell can be accurately expanded based on the resource demand. Exemplarily, the Treynor demand index of the target cell is positively correlated with the resource demand. For example, the existing network bandwidth resource of the target cell is 5M bandwidth. When the Treynor demand index is 150%, the corresponding resource demand is 7.5M bandwidth, that is, it is necessary to invest another 2.5M bandwidth resources in the target cell to meet user needs, which can also be solved by optimization means such as carrier balancing. When the Treynor demand index is 250%, the corresponding resource demand can be 12.5M bandwidth, that is, it is necessary to invest another 7.5M bandwidth resources in the target cell to meet user needs.

[0098] In the high-load cell identification method provided in the exemplary implementation of the present disclosure, the first performance data and the original second performance data of the target cell are obtained; the first performance data and the original second performance data are fitted to obtain the linear second performance data; when the target cell load is at the critical point of full load, the amount of resources when the target cell reaches the perceived inflection point is determined according to the linear second performance data; the Treynor demand index corresponding to the original second performance data of the target period is calculated according to the linear second performance data and the amount of resources when the target cell reaches the perceived inflection point, and the network load of the target cell is identified according to the Treynor demand index. On the one hand, the distribution relationship between the first performance data and the original second performance data obtained by fitting is used to build a model, and the Treynor demand index of the target cell is calculated according to the modeling result. This process does not require artificial definition of parameters, can avoid human interference, and the calculation result is more objective; on the other hand, by calculating the Treynor demand index of the target cell, the resource demand of the target cell can be accurately quantified and accurately expanded, thereby improving resource utilization.

[0099] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0100] Furthermore, in this exemplary implementation, a high-load cell identification device is also provided. Figure 7 As shown, the high-load cell identification device 700 may include a performance data acquisition module 710, a first data determination module 720, a second data determination module 730 and a network load identification module 740, wherein:

[0101] The performance data acquisition module 710 is used to acquire original performance data of the target cell, where the original performance data includes first performance data and original second performance data;

[0102] A first data determination module 720, configured to fit the first performance data and original second performance data to obtain linear second performance data corresponding to the first performance data;

[0103] A second data determination module 730, configured to determine, when the load of the target cell is at a critical point of full load, the amount of resources when the target cell reaches a perception inflection point according to the linear second performance data;

[0104] The network load identification module 740 is used to calculate the Treynor demand index corresponding to the original second performance data of the target time period based on the linear second performance data and the resource amount when the target cell reaches the perception inflection point, and identify the network load of the target cell based on the Treynor demand index.

[0105] In an optional implementation, the performance data acquisition module 710 includes:

[0106] A performance data acquisition unit, used to extract the original performance data of the target cell from the background network management performance data;

[0107] The performance data selection unit is used to select the first performance data and the original second performance data from the original performance data as sample data to fit the sample data.

[0108] In an optional implementation, the first data determination module 720 includes:

[0109] A performance data fitting unit, used for performing linear fitting on the first performance data and the original second performance data, and obtaining a corresponding fitting curve when the fitting error is minimized;

[0110] The performance data determination unit is used to calculate the first performance data and the fitting parameters in the fitting curve to obtain linear second performance data corresponding to the first performance data.

[0111] In an optional implementation, the second data determination module 730 includes:

[0112] a perception inflection point determination unit, configured to fit the first performance data and the original second performance data within a target interval to determine a perception inflection point of the target cell;

[0113] The inflection point resource quantity determination unit is used to calculate the resource quantity when the target cell reaches the perceived inflection point based on the linear second performance data and the original second performance data in the target interval when the load of the target cell is at the full load critical point.

[0114] In an optional implementation, the network load identification module 740 is configured to:

[0115] according to

[0116] T=(R P -R f ) / β p

[0117] Obtaining the Treynor demand index of the target cell;

[0118] Where T is the Treynor demand index of the target cell, RP is the linear second performance data, R f is the original second performance data of the target period, β p It is the amount of resources when the target cell reaches the perception inflection point.

[0119] In an optional implementation manner, the high-load cell identification device 700 further includes:

[0120] The resource demand determination module is used to determine the resource demand of the target cell according to the mapping relationship between the Treynor demand index and the resource demand when the target cell is a high-load cell, and accurately expand the target cell according to the resource demand.

[0121] In an optional implementation, the first performance data is the average number of users establishing an RRC connection, and the original second performance data is the average downlink PRB utilization and / or user plane PDCP downlink traffic.

[0122] In an optional implementation manner, the high-load cell identification device 700 further includes:

[0123] The target cell selection module is used to select the cell to be evaluated as the target cell when the cell to be evaluated meets a preset condition; wherein the preset condition is that the average utilization rate of downlink PRBs is greater than a preset utilization rate threshold.

[0124] The specific details of each module in the above-mentioned high-load cell identification device have been described in detail in the corresponding high-load cell identification method, so they will not be repeated here.

[0125] Each module in the above device can be a general-purpose processor, including: a central processing unit, a network processor, etc.; it can also be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each module can also be implemented in the form of software, firmware, etc. Each processor in the above device can be an independent processor or integrated together.

[0126] The exemplary embodiments of the present disclosure also provide a computer-readable storage medium on which a program product capable of implementing the above-mentioned method of this specification is stored. In some possible embodiments, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on an electronic device, the program code is used to cause the electronic device to perform the steps according to various exemplary embodiments of the present disclosure described in the above-mentioned "exemplary method" section of this specification. The program product may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on an electronic device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, an apparatus or a device or used in combination with it.

[0127] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0128] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0129] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0130] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0131] The exemplary embodiment of the present disclosure also provides an electronic device capable of implementing the above method. Figure 8 800 according to this exemplary embodiment of the present disclosure will be described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0132] like Figure 8 As shown, the electronic device 800 may be in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0133] The storage unit 820 stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can execute Figures 2 to 5 Any one or more method steps.

[0134] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 821 and / or a cache memory unit 822 , and may further include a read-only memory unit (ROM) 823 .

[0135] The storage unit 820 may also include a program / utility 824 having a set (at least one) of program modules 825, such program modules 825 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0136] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0137] The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0138] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the exemplary implementation of the present disclosure.

[0139] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiment of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0140] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0141] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for identifying a high-load cell in a network, characterized in that: include: Acquire original performance data of the target cell, the original performance data including first performance data and original second performance data; wherein the first performance data is an average number of users establishing a radio resource control RRC connection, and the original second performance data is a resource amount indicating that the target cell reaches a smoothed maximum value when resource restriction is reached; Fitting the first performance data and the original second performance data to obtain linear second performance data corresponding to the first performance data; When the load of the target cell is at a full load critical point, determining, according to the linear second performance data, an amount of resources when the target cell reaches a perception inflection point; Calculating a Treynor demand index corresponding to the original second performance data of the target period according to the linear second performance data and the amount of resources when the target cell reaches a perception inflection point, and identifying a network load of the target cell according to the Treynor demand index; The Treynor demand index of the target cell is determined and calculated according to the following formula: T==(RP-Rf) / βp T is the Treynor demand index of the target cell, R P is the linear second performance data, R f is the original second performance data of the target period, β p It is the amount of resources when the target cell reaches the perception inflection point.

2. The method for identifying a network high-load cell according to claim 1, characterized in that: The obtaining of original performance data of the target cell includes: Extracting original performance data of the target cell from background network management performance data; The first performance data and the original second performance data are selected from the original performance data as sample data to fit the sample data.

3. The method for identifying a network high-load cell according to claim 1, characterized in that: The fitting of the first performance data and the original second performance data to obtain linear second performance data corresponding to the first performance data includes: Performing linear fitting on the first performance data and the original second performance data, and obtaining a corresponding fitting curve when the fitting error is minimum; The first performance data and fitting parameters in the fitting curve are calculated to obtain linear second performance data corresponding to the first performance data.

4. The method for identifying a network high-load cell according to claim 3, characterized in that: When the target cell load is at a full load critical point, determining, according to the linear second performance data, the amount of resources when the target cell reaches a perception inflection point, includes: Fitting the first performance data and the original second performance data within the target interval to determine a perception inflection point of the target cell; When the target cell load is at a full load critical point, the resource amount of the target cell when reaching a perception inflection point is calculated based on the linear second performance data and the original second performance data in the target interval.

5. The method for identifying a network high-load cell according to claim 1, characterized in that: The method further comprises: When the target cell is a high-load cell, the resource demand of the target cell is determined according to the mapping relationship between the Treynor demand index and the resource demand, and the target cell is accurately expanded according to the resource demand.

6. The method for identifying a network high-load cell according to claim 1, characterized in that: The original second performance data is the downlink PRB average utilization and / or the user plane PDCP downlink traffic.

7. The method for identifying a network high-load cell according to claim 6, characterized in that: The method further comprises: When the cell to be evaluated meets a preset condition, the cell to be evaluated is selected as a target cell; wherein the preset condition is that an average downlink PRB utilization rate is greater than a preset utilization rate threshold.

8. A network high-load cell identification device, characterized in that: include: A performance data acquisition module, used to acquire original performance data of the target cell, the original performance data including first performance data and original second performance data; wherein the first performance data is an average number of users establishing a radio resource control RRC connection, and the original second performance data is a resource amount indicating that the target cell reaches a smoothed maximum value when the resource is limited; A first data determination module, used for fitting the first performance data and original second performance data to obtain linear second performance data corresponding to the first performance data; A second data determination module, configured to determine, when the load of the target cell is at a critical point of full load, the amount of resources when the target cell reaches a perception inflection point according to the linear second performance data; A network load identification module, configured to calculate a Treynor demand index corresponding to the original second performance data of the target period according to the linear second performance data and the amount of resources when the target cell reaches a perception inflection point, and identify the network load of the target cell according to the Treynor demand index; The Treynor demand index of the target cell is determined and calculated according to the following formula: T=(RP-Rf) / βp T is the Treynor demand index of the target cell, R P is the linear second performance data, R f is the original second performance data of the target period, β p It is the amount of resources when the target cell reaches the perception inflection point.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

Images