CN113260070A

CN113260070A - Load scheduling method and device and electronic equipment

Info

Publication number: CN113260070A
Application number: CN202010089952.0A
Authority: CN
Inventors: 刘建强
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Guangdong Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Guangdong Co Ltd
Priority date: 2020-02-13
Filing date: 2020-02-13
Publication date: 2021-08-13
Anticipated expiration: 2040-02-13
Also published as: CN113260070B

Abstract

The embodiment of the invention discloses a load scheduling method, a load scheduling device and electronic equipment, wherein the method comprises the following steps: the method comprises the steps of obtaining capacity characteristic information of preset traffic attributes of a target cell to be detected in a wireless communication system, wherein the capacity characteristic information is information required for determining cell expansion priority, inputting the capacity characteristic information of the target cell into a pre-trained expansion priority evaluation model to obtain the expansion priority of the target cell, training historical capacity characteristic information of a plurality of cells in a preset time period based on a preset decision tree algorithm to obtain the expansion priority of the target cell, and determining an expansion strategy of the target cell based on the expansion priority of the target cell. By the method, the capacity expansion strategy of the target cell can be determined based on the capacity expansion priority of the target cell, so that the load scheduling efficiency is improved, and the accuracy of the load scheduling is ensured.

Description

Load scheduling method and device and electronic equipment

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a load scheduling method and apparatus, and an electronic device.

Background

Currently, a static configuration method is adopted for the admission (license) of wireless network carrier resources, but these carrier resources do not always work in a normal load state, so that reasonable load scheduling for cells becomes a concern for operators.

When load scheduling is carried out on a cell, the traffic capacity load condition of the cell can be monitored manually, and whether the cell needs to be expanded or not is determined according to the monitored traffic index data. For example, Key Performance Indicator (KPI) data of the cell 1 may be manually monitored, and if it is monitored that one or more pieces of traffic KPI Indicator data of the cell 1 exceed corresponding preset Indicator thresholds, capacity expansion may be performed on the cell 1.

However, the above-mentioned method of manually monitoring the traffic capacity load of the cell and scheduling the load of the cell has the following problems: in addition, if the telephone traffic KPI data of a plurality of cells exceed a preset index threshold value, but the telephone traffic capacity load condition of each cell is different, and if the same capacity expansion strategy is adopted to carry out load scheduling on the plurality of cells, the load scheduling accuracy is poor.

Disclosure of Invention

Embodiments of the present invention provide a load scheduling method, a load scheduling device, and an electronic device, so as to solve the problems of low load scheduling efficiency and poor accuracy when a cell is load scheduled by manually monitoring a cell traffic capacity load condition in the prior art

To solve the above technical problem, the embodiment of the present invention is implemented as follows:

in a first aspect, a load scheduling method provided in an embodiment of the present invention includes:

acquiring capacity characteristic information of a preset traffic attribute of a target cell to be detected in a wireless communication system, wherein the capacity characteristic information is required for determining the cell capacity expansion priority;

inputting the capacity characteristic information of the target cell into a pre-trained capacity expansion priority evaluation model to obtain the capacity expansion priority of the target cell, wherein the capacity expansion priority evaluation model is obtained by training the historical capacity characteristic information of a plurality of cells in a preset time period based on a preset decision tree algorithm;

and determining the capacity expansion strategy of the target cell based on the capacity expansion priority of the target cell.

Optionally, the determining the capacity expansion policy of the target cell based on the capacity expansion priority of the target cell includes:

acquiring a first cell which is at the same capacity expansion priority level as the target cell;

performing priority ranking on the target cell and the first cell based on a preset superposition ranking algorithm to obtain a target capacity expansion priority of the target cell;

and determining a capacity expansion strategy of the target cell based on the target capacity expansion priority of the target cell.

Optionally, the performing priority ranking on the target cell and the first cell based on a preset stacking ranking algorithm to obtain a target capacity expansion priority of the target cell includes:

and based on a preset telephone traffic sequencing index, carrying out priority sequencing on the target cell and the first cell to obtain the target capacity expansion priority of the target cell.

Optionally, before the inputting the capacity characteristic information of the target cell into the expansion priority evaluation model of the preselection training and obtaining the expansion priority of the target cell, the method further includes:

acquiring historical capacity characteristic information of preset traffic attributes of the plurality of cells within the preset time period;

constructing a corresponding decision tree based on the preset decision tree algorithm and the historical capacity characteristic information;

and obtaining the expansion priority evaluation model based on the decision tree.

Optionally, the constructing a corresponding decision tree based on the preset decision tree algorithm and the historical capacity feature information includes:

determining a plurality of first segmentation points corresponding to the preset traffic attributes;

acquiring first decision points corresponding to the plurality of first segmentation points;

acquiring a kini coefficient of each first decision point based on the historical capacity characteristic information;

determining a target decision point based on the kini coefficient of each first decision point;

determining capacity characteristic information which meets the segmentation condition corresponding to the target decision point in the historical capacity characteristic information as first capacity characteristic information, and determining capacity characteristic information which does not meet the segmentation condition corresponding to the target decision point in the historical capacity characteristic information as second capacity characteristic information;

constructing the decision tree based on the target decision point, the first capacity characteristic information and the second capacity characteristic information.

Optionally, the decision tree includes a root node, a first branch and a second branch, and the constructing the decision tree based on the target decision point, the first capacity characteristic information and the second capacity characteristic information includes:

taking the target decision point as the root node of the decision tree;

constructing the first branch of the decision tree based on the first capacity characteristic information;

constructing the second branch of the decision tree based on the second capacity characteristic information.

Optionally, after constructing the first branch of the decision tree based on the first capacity characteristic information, the method further includes:

acquiring a first telephone traffic attribute corresponding to the target decision point;

acquiring second segmentation points corresponding to other telephone traffic attributes except the first telephone traffic attribute in the preset telephone traffic attribute;

acquiring a second decision point corresponding to the second division point;

acquiring a kini coefficient of each second decision point based on the first capacity characteristic information;

determining a target sub-decision point based on the kini coefficient of each second decision point;

determining capacity feature information which meets the segmentation condition corresponding to the target sub-decision point in the first capacity feature information as third capacity feature information, and determining capacity feature information which does not meet the segmentation condition corresponding to the target sub-decision point in the first capacity feature information as fourth capacity feature information;

constructing a first sub-branch of the first branch of the decision tree based on the third capacity characteristic information;

constructing a second sub-branch of the first branch of the decision tree based on the fourth capacity characteristic information.

In a second aspect, an embodiment of the present invention provides a load scheduling apparatus, where the apparatus includes:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring capacity characteristic information of a preset traffic attribute of a target cell to be detected in a wireless communication system, and the capacity characteristic information is information required for determining the capacity expansion priority of the cell;

a priority obtaining module, configured to input the capacity characteristic information of the target cell into a pre-trained expansion priority evaluation model to obtain an expansion priority of the target cell, where the expansion priority evaluation model is obtained by training historical capacity characteristic information of multiple cells within a preset time period based on a preset decision tree algorithm;

and the strategy determination module is used for determining the capacity expansion strategy of the target cell based on the capacity expansion priority of the target cell.

Optionally, the policy determining module is configured to:

Optionally, the apparatus further comprises:

a second obtaining module, configured to obtain historical capacity feature information of preset traffic attributes of the multiple cells within the preset time period;

the construction module is used for constructing a corresponding decision tree based on the preset decision tree algorithm and the historical capacity characteristic information;

and the model obtaining module is used for obtaining the expansion priority evaluation model based on the decision tree.

Optionally, the building module is configured to:

Optionally, the decision tree includes a root node, a first branch and a second branch, and the building module is configured to:

taking the target decision point as the root node of the decision tree;

Optionally, the apparatus further comprises:

the attribute acquisition module is used for acquiring a first telephone traffic attribute corresponding to the target decision point;

the data processing module is used for acquiring second segmentation points corresponding to other telephone traffic attributes except the first telephone traffic attribute in the preset telephone traffic attributes;

an obtaining module, configured to obtain a second decision point corresponding to the second segmentation point;

a coefficient determining module, configured to obtain a kini coefficient of each second decision point based on the first capacity feature information;

a decision point determining module, configured to determine a target sub-decision point based on the kini coefficient of each second decision point;

the data dividing module is used for determining capacity characteristic information which meets the dividing conditions corresponding to the target sub-decision point in the first capacity characteristic information as third capacity characteristic information, and determining capacity characteristic information which does not meet the dividing conditions corresponding to the target sub-decision point as fourth capacity characteristic information;

a first branch determination module for constructing a first sub-branch of a first branch of the decision tree based on the third capacity characteristic information;

a second score determination module for constructing a second sub-branch of the first branch of the decision tree based on the fourth capacity characteristic information.

In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, where the computer program, when executed by the processor, implements the steps of the load scheduling method provided in the foregoing embodiments.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps of the load scheduling method provided in the foregoing embodiment.

As can be seen from the above technical solutions provided by the embodiments of the present invention, in the embodiments of the present invention, capacity characteristic information of a target cell to be detected in a wireless communication system is obtained, where the capacity characteristic information includes cell traffic information and cell basic information, and the capacity characteristic information of the target cell is input into a pre-trained capacity expansion priority evaluation model to obtain a capacity expansion priority of the target cell, where the capacity expansion priority evaluation model is obtained by training historical capacity characteristic information of a plurality of cells within a preset time period based on a preset decision tree algorithm, and a capacity expansion strategy of the target cell is determined based on the capacity expansion priority of the target cell. Therefore, the capacity expansion priority of the target cell can be obtained through the capacity expansion priority evaluation model and the capacity characteristic information of the target cell, the corresponding capacity expansion strategy is determined, the traffic information of the target cell does not need to be detected manually, whether the target cell needs to be expanded or not is determined, the load scheduling efficiency is improved, and meanwhile the accuracy of load scheduling is guaranteed.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flowchart illustrating a load scheduling method according to the present invention;

FIG. 2 is a flow chart illustrating another load scheduling method according to the present invention;

FIG. 3 is a schematic diagram illustrating a training of a capacity-expansion priority evaluation model according to the present invention;

FIG. 4 is a schematic structural diagram of a load scheduling apparatus according to the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to the present invention.

Detailed Description

The embodiment of the invention provides a load scheduling method and device and electronic equipment.

In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Example one

As shown in fig. 1, an execution main body of the method may be a server, and the server may be an independent server or a server cluster composed of a plurality of servers. The method may specifically comprise the steps of:

in S102, capacity characteristic information of a preset traffic attribute of a target cell to be detected in the wireless communication system is acquired.

The preset traffic attribute may include attributes corresponding to cell traffic information and cell basic information, and evaluation of a capacity expansion condition of a cell, where the cell traffic information may be information related to a cell traffic load condition, for example, the cell traffic information may include Resource utilization of the cell, a Radio Resource Control (RRC) number with data transmission, and the like, the cell basic information may include whether the cell covers a business center, traffic information of the cell, main service component information of the cell (for example, the cell is a large packet cell or a small packet cell), and the like, the capacity feature information may be information corresponding to the preset traffic attribute and required for determining a capacity expansion priority of the cell, and the target cell may be any one or more cells to be detected in a wireless communication system.

In implementation, currently, a static configuration method is adopted for the admission (license) of the carrier resources of the wireless network, but the carrier resources do not always work in a normal load state, so that reasonable load scheduling on cells becomes a concern of operators. When load scheduling is carried out on a cell, the traffic capacity load condition of the cell can be monitored manually, and whether the cell needs to be expanded or not is determined according to the monitored traffic index data. For example, Key Performance Indicator (KPI) data of the cell 1 may be manually monitored, and if it is monitored that one or more pieces of traffic KPI Indicator data of the cell 1 exceed corresponding preset Indicator thresholds, capacity expansion may be performed on the cell 1.

However, the above-mentioned method of manually monitoring the traffic capacity load of the cell and scheduling the load of the cell has the following problems: in addition, if the telephone traffic KPI data of a plurality of cells exceed a preset index threshold value, but the telephone traffic capacity load condition of each cell is different, and if the same capacity expansion strategy is adopted to carry out load scheduling on the plurality of cells, the load scheduling accuracy is poor. Therefore, another implementation scheme is provided in the embodiments of the present invention, which may specifically include the following:

the capacity characteristic information of the target cell with the preset traffic attribute to be detected may be obtained based on a preset time period, for example, the preset time period may be one day, and the resource utilization rate and the effective RRC number (i.e., cell traffic information) of the cell of the target cell on a certain day, the cell traffic information of the target cell, whether the cell covers a business center, the main service component information (i.e., cell basic information) of the cell, and the like may be obtained as the capacity characteristic information of the target cell. The resource utilization rate of the cell may be a maximum value of a Physical Downlink Shared Channel (PDSCH) utilization rate and a Physical Downlink Control Channel (PDCCH) utilization rate of the cell during self-busy time, and the cell traffic information may be a sum of RRC connection numbers of the active user and the inactive user.

In an actual application scenario, there may be multiple preset traffic attributes, and different preset traffic attributes may be selected according to different actual application scenarios, which is not specifically limited in the embodiment of the present invention.

In S104, the capacity characteristic information of the target cell is input into a pre-trained capacity expansion priority evaluation model to obtain a capacity expansion priority of the target cell.

Wherein, the capacity expansion priority evaluation model may be obtained by training historical capacity characteristic information of a plurality of cells within a preset time period based on a preset decision tree algorithm, the preset decision tree algorithm may be a classification regression tree (CART) algorithm, the preset time period may be the same as the preset time period for obtaining the capacity characteristic information of the target cell in the above S102, for example, the preset time period may be one day, the capacity characteristic information of the target cell in 11 months and 12 days may be obtained, and the historical capacity characteristic information of the plurality of cells in 10 months and 12 days may be obtained for training to obtain the pre-trained capacity expansion priority evaluation model, the plurality of cells may be expanded cells, the historical capacity characteristic information of the plurality of cells may include the capacity characteristic information before capacity expansion and the capacity expansion evaluation information after capacity expansion, for example, the cell 1 is expanded in 10 months and 13 days, then, the capacity characteristic information of the cell 1 in day 10, month and 12 may be obtained, and the capacity expansion evaluation information of the cell 1 may be determined based on the traffic information of the cell 1 in day 10, month and 13, for example, if the traffic increase rate of the cell 1 in day 10, month and 13 exceeds a preset threshold, it may be considered that the capacity bottleneck of the cell 1 may be removed by a corresponding capacity expansion policy, and the capacity expansion benefit is good, and it may be determined that the cell 1 is a cell that needs to be expanded, that is, the obtained historical capacity characteristic information of the cell 1 may include the capacity characteristic information of the cell 1 in day 10, month and 12 and the capacity expansion evaluation information of the cell 1 (that is, the cell 1 is a cell that needs to be expanded).

In implementation, since the pre-trained capacity expansion priority evaluation model may be determined based on a preset decision tree algorithm, before the capacity feature information of the target cell is input into the pre-trained capacity expansion priority evaluation model, the capacity feature information of the target cell may be pre-processed.

For example, the capacity characteristic information of the target cell may include the traffic information of the cell, and the target cell may be determined to be a cell with a large traffic or a cell with a small traffic according to the traffic information of the cell. For example, the traffic information of the cell may be the sum of the RRC connection numbers of the active users and the inactive users, and if the sum of the RRC connection numbers of the active users and the inactive users of the target cell is greater than a preset traffic threshold (e.g., 300 people) within a preset statistical period (e.g., 2 consecutive hours), the target cell may be considered as a cell with a large traffic.

The capacity characteristic information of the target cell may further include main service component information of the cell, that is, the target cell is a large packet cell or a small packet cell, and whether an Evolved Radio Bearer (E-RAB) traffic of the target cell is greater than a preset traffic threshold may be determined according to whether the E-RAB traffic is greater than the preset traffic threshold. For example, if the E-RAB traffic of the target cell is not less than 1000kb, the target cell may be considered as a large packet cell, otherwise, the target cell is a small packet cell.

After the capacity characteristic information of the target cell is preprocessed, a pre-trained expansion priority evaluation model can be input, and the expansion priority of the target cell is obtained.

In addition, when there are multiple target cells, the capacity characteristic information of each target cell may be preprocessed and input into a pre-trained capacity expansion priority evaluation model, so as to obtain a capacity expansion priority of each target cell.

In S106, a capacity expansion policy of the target cell is determined based on the capacity expansion priority of the target cell.

In implementation, if the capacity expansion priority of the target cell is low, the load scheduling may not be performed on the target cell temporarily, that is, the capacity expansion of the target cell is not performed temporarily, and if the capacity expansion priority of the target cell is high, the capacity expansion of the target cell may be performed immediately, so as to avoid poor user perception due to the cell capacity problem.

The embodiment of the invention provides a load scheduling method, which comprises the steps of obtaining capacity characteristic information of a target cell to be detected in a wireless communication system, wherein the capacity characteristic information comprises cell traffic information and cell basic information, inputting the capacity characteristic information of the target cell into a pre-trained expansion priority evaluation model to obtain the expansion priority of the target cell, training historical capacity characteristic information of a plurality of cells in a preset time period based on a preset decision tree algorithm to obtain the expansion priority of the target cell, and determining an expansion strategy of the target cell based on the expansion priority of the target cell. Therefore, the capacity expansion priority of the target cell can be obtained through the capacity expansion priority evaluation model and the capacity characteristic information of the target cell, the corresponding capacity expansion strategy is determined, the traffic information of the target cell does not need to be detected manually, whether the target cell needs to be expanded or not is determined, the load scheduling efficiency is improved, and meanwhile the accuracy of load scheduling is guaranteed.

Example two

As shown in fig. 2, an execution main body of the method may be a server, and the server may be an independent server or a server cluster composed of a plurality of servers. The method may specifically comprise the steps of:

in S202, capacity characteristic information of a preset traffic attribute of a target cell to be detected in the wireless communication system is acquired.

For the specific processing procedure of S202, reference may be made to relevant contents in S102 in the first embodiment, which is not described herein again.

In S204, historical capacity characteristic information of preset traffic attributes of a plurality of cells within a preset time period is obtained.

In implementation, the historical capacity characteristic information (including the historical capacity characteristic information before capacity expansion and the capacity expansion evaluation information after capacity expansion) of a plurality of cells in a day may be obtained.

In S206, a corresponding decision tree is constructed based on a preset decision tree algorithm and the historical capacity feature information.

In implementation, the obtained partial historical capacity characteristic information may be as shown in table 1.

TABLE 1

The Cell Identifier may be a Global Cell Identifier (CGI) of each Cell.

In practical applications, the processing manner of S206 may be various, and an alternative implementation manner is provided below, which may specifically refer to the following processing from step one to step six.

Step one, a plurality of first segmentation points corresponding to preset traffic attributes are determined.

In implementation, a first segmentation point corresponding to each preset traffic attribute may be obtained. For example, the preset traffic attributes may include resource utilization of the cell, effective RRC number of the cell, whether the cell covers the business center, traffic volume of the cell, main service components of the cell, and capacity expansion evaluation of the cell. The four attributes, which are evaluated as the tag attributes, of whether the cell covers the business center, the traffic flow of the cell, the main service component of the cell, and the capacity expansion condition of the cell, may be determined according to the attribute values, for example, the first segmentation point corresponding to the four preset traffic attributes may include a first segmentation point 1 and a first segmentation point 2, where the first segmentation point 1 may be large for the traffic flow, and the first segmentation point 2 may be small for the traffic flow.

In addition, the two attributes of the resource utilization rate of the cell and the effective RRC number of the cell included in the preset traffic attribute are continuous value attributes, and a first segmentation point corresponding to each preset traffic attribute in the two preset traffic attributes may be determined based on a recursive algorithm.

For example, taking the preset traffic attribute of resource utilization as an example, assuming that the resource utilization corresponds to X continuous values in the acquired historical capacity characteristic information, there may be X-1 candidate values, each candidate value is an average value of every two adjacent continuous values, a kini coefficient corresponding to each candidate value is calculated based on the historical capacity characteristic information, and then the candidate value with the smallest kini coefficient may be determined as the first segmentation point.

For example, the obtained historical capacity characteristic information has 10 values of resource utilization rate, 9 candidate values can be generated based on the 10 values, and then the kini coefficients corresponding to the 9 candidate values are calculated based on the historical capacity characteristic information, and the calculation result can be shown in table 2.

TABLE 2

Based on table 2, it can be determined that 42% of the candidate values have the smallest corresponding kini coefficient, and the first split point corresponding to the resource utilization rate can be 42%, and based on the above method, the first split point (for example, 24) corresponding to the preset traffic attribute of the valid RRC number can also be obtained.

And step two, acquiring first decision points corresponding to the plurality of first segmentation points.

In an implementation, taking the above table 2 as an example, assuming that the first segmentation point corresponding to the preset traffic attribute of resource utilization rate is 42%, the corresponding first decision point may include a first decision point 3 and a first decision point 4, where the first decision point 3 may be that the resource utilization rate is less than or equal to 42%, and the first decision point 4 may be that the resource utilization rate is greater than 42%.

Similarly, the first dividing point corresponding to the preset traffic attribute of the effective RRC number may include a first dividing point 5 and a first dividing point 6, where the effective RRC number of the first dividing point 5 may be less than or equal to 24, and the effective RRC number of the first dividing point 6 may be greater than 24.

For a preset traffic attribute of the tag attribute, a first splitting point of the tag attribute may be directly used as a first decision point, for example, a preset traffic attribute of a traffic volume of a cell, and the corresponding first splitting point may include a first splitting point 1 and a first splitting point 2, where the first splitting point 1 may be large for the traffic volume, and the first splitting point 2 may be small for the traffic volume, and then the first decision point 1 corresponding to the preset traffic attribute may be the same as the first splitting point 1, and the first decision point 2 may be the same as the first splitting point.

And step three, acquiring the kini coefficient of each first decision point based on the historical capacity characteristic information.

As with the calculation of the kini coefficient of each candidate value in table 2 above, the kini coefficient of each first decision point may be obtained based on the historical capacity feature information.

The obtained kini coefficient for each first decision point may be as follows: gini (D1, resource utilization > 42%) -0.27; gini (D1, yes for business centers or not) 0.321; gini (D1, no for business center coverage) 0.323; gini (D1, resource utilization rate is less than or equal to 42%) -0.364; gini (D1, traffic) 0.439199; gini (D1, major service component ═ big bag) ═ 0.414; gini (D1, less pedestrian flow) 0.427; gini (D1, main service component: small packet) ═ 0.417999; gini (D1, RRC number > 24 for data transmission) ═ 0.4472; gini (D1, RRC number is less than or equal to 24) is 0.404205;

where D1 is historical capacity feature information.

And step four, determining a target decision point based on the kini coefficient of each first decision point.

In an implementation, the first decision point with the smallest kini coefficient may be used as the target decision point, for example, if Gini (D1, resource utilization rate > 42%) is 0.27 min, the first decision point with resource utilization rate > 42% may be used as the target decision point.

And step five, determining the capacity characteristic information which meets the segmentation condition corresponding to the target decision point in the historical capacity characteristic information as first capacity characteristic information, and determining the capacity characteristic information which does not meet the segmentation condition corresponding to the target decision point in the historical capacity characteristic information as second capacity characteristic information.

And step six, constructing a decision tree based on the target decision point, the first capacity characteristic information and the second capacity characteristic information.

In implementation, when constructing the decision tree, the target decision point may be used as a root node of the decision tree, a first branch of the decision tree is constructed based on the first capacity characteristic information, and a second branch of the decision tree is constructed based on the second capacity characteristic information.

In addition, after the second branch of the decision tree is constructed, the first traffic attribute corresponding to the target decision point can be obtained, and then the second division point corresponding to other traffic attributes except the first traffic attribute in the preset traffic attribute is obtained.

For example, the first traffic attribute corresponding to the target decision point is a resource utilization rate, and in the preset traffic attribute, other traffic attributes except the traffic attribute may be an effective RRC number, whether to cover a business center, a traffic volume, and the like, and then the second split points corresponding to the traffic attributes may be obtained.

And then acquiring a second decision point corresponding to the second segmentation point. A kini coefficient for each second decision point may be obtained based on the first capacity characteristic information.

Then, the method for obtaining the kini coefficient of each first decision point based on the historical capacity characteristic information can be adopted, and the kini coefficient of each second decision point is obtained based on the first capacity characteristic information.

And determining the target sub-decision point based on the kini coefficient of each second decision point. The second decision point with the smallest kini coefficient may be determined as the target sub-decision point.

And determining the capacity characteristic information which meets the segmentation condition corresponding to the target sub-decision point in the first capacity characteristic information as third capacity characteristic information, and determining the capacity characteristic information which does not meet the segmentation condition corresponding to the target sub-decision point in the first capacity characteristic information as fourth capacity characteristic information.

Finally, a first sub-branch of the first branch of the decision tree is constructed based on the third capacity characteristic information. Based on the fourth capacity characteristic information, a second sub-branch of the first branch of the decision tree is constructed.

A third and a fourth sub-branch of the second branch of the decision tree may then be constructed based on the above-described method of constructing the first and second sub-branches. Similarly, the first sub-branch may be continuously classified until it is impossible to perform classification.

In addition, before the decision tree is constructed, classification parameters may be preset, for example, the depth of the decision tree, the number of samples of leaf nodes of the decision tree, and the determination method of the leaf nodes at different depths, etc. may be preset.

In S208, based on the decision tree, an expansion priority evaluation model is obtained.

In an implementation, the capacity expansion priority evaluation model may be formed according to a decision tree, for example, as shown in fig. 3, each leaf node may correspond to one capacity expansion priority. Based on the historical capacity characteristic information, a plurality of cells can be divided into 16 corresponding expansion priorities, and each expansion priority at least comprises 1 cell.

In S210, the capacity characteristic information of the target cell is input into a pre-trained capacity expansion priority evaluation model to obtain a capacity expansion priority of the target cell.

The specific processing procedure of S210 may refer to relevant contents in S104 in the first embodiment, and is not described herein again.

Because the number of cells is large and the number of expansion priority levels is limited, a situation that a plurality of cells are in the same expansion priority level may exist, and in this situation, if the same expansion strategy is adopted for the cells of the same expansion priority level, the problem of poor load scheduling accuracy may also be caused, so that after S210 is executed, S212 to S214 may be continuously executed.

In S212, a first cell in the same capacity expansion priority as the target cell is acquired.

The first cell may be one or more than one cell, where the first cell and the target cell are all cells with the same capacity expansion priority.

In an implementation, for example, if the capacity expansion priority of the target cell is priority 2, the first cell with priority 2 may be acquired.

In S214, based on the preset stacking and sorting algorithm, priority sorting is performed on the target cell and the first cell to obtain a target capacity expansion priority of the target cell.

In practical applications, the processing manner of S214 may be various, and an alternative implementation manner is provided below, which may specifically refer to the following steps:

and based on a preset telephone traffic sequencing index, performing priority sequencing on the target cell and the first cell to obtain the target capacity expansion priority of the target cell.

In implementation, the preset traffic ordering index may include a PDSCH utilization rate or a PDCCH utilization rate, and may obtain a maximum value of the PDSCH utilization rate and the PDCCH utilization rate of the target cell and a maximum value of the PDSCH utilization rate and the PDCCH utilization rate of the first cell, and then perform priority ordering on the target cell and the first cell, and obtain a target capacity expansion priority of the target cell.

For example, the capacity expansion priorities of the target cell and the first cell are both priority 2, the target cell may be ranked as 5 in all cells in priority 2 (i.e., including the target cell and the first cell), and the target capacity expansion priority of the target cell includes the capacity expansion priority of the target cell in all cells and its sub-priority in the capacity expansion priority, that is, priority 2+ 5.

In S216, a capacity expansion policy of the target cell is determined based on the target capacity expansion priority of the target cell.

EXAMPLE III

Based on the same idea, the load scheduling method provided in the embodiment of the present invention further provides a load scheduling apparatus, as shown in fig. 4.

The load scheduling device includes: a first obtaining module 401, a priority obtaining module 402 and a policy determining module 403, wherein:

a first obtaining module 401, configured to obtain capacity characteristic information of a preset traffic attribute of a target cell to be detected in a wireless communication system, where the capacity characteristic information is information required to determine a cell capacity expansion priority;

a priority obtaining module 402, configured to input the capacity characteristic information of the target cell into a pre-trained capacity expansion priority evaluation model to obtain a capacity expansion priority of the target cell, where the capacity expansion priority evaluation model is obtained by training historical capacity characteristic information of multiple cells within a preset time period based on a preset decision tree algorithm;

a policy determining module 403, configured to determine an expansion policy of the target cell based on the expansion priority of the target cell.

In this embodiment of the present invention, the policy determining module 403 is configured to:

In an embodiment of the present invention, the apparatus further includes:

In an embodiment of the present invention, the building module is configured to:

In an embodiment of the present invention, the decision tree includes a root node, a first branch and a second branch, and the building module is configured to:

taking the target decision point as the root node of the decision tree;

In an embodiment of the present invention, the apparatus further includes:

The embodiment of the invention provides a load scheduling device, which is used for inputting capacity characteristic information of a target cell to be detected in a wireless communication system into a pre-trained capacity expansion priority evaluation model to obtain the capacity expansion priority of the target cell by acquiring the capacity characteristic information of the target cell to be detected, wherein the capacity characteristic information comprises cell traffic information and cell basic information, the capacity expansion priority evaluation model is obtained by training historical capacity characteristic information of a plurality of cells in a preset time period based on a preset decision tree algorithm, and a capacity expansion strategy of the target cell is determined based on the capacity expansion priority of the target cell. Therefore, the capacity expansion priority of the target cell can be obtained through the capacity expansion priority evaluation model and the capacity characteristic information of the target cell, the corresponding capacity expansion strategy is determined, the traffic information of the target cell does not need to be detected manually, whether the target cell needs to be expanded or not is determined, the load scheduling efficiency is improved, and meanwhile the accuracy of load scheduling is guaranteed.

Example four

Figure 5 is a schematic diagram of a hardware configuration of an electronic device implementing various embodiments of the invention,

the electronic device 500 includes, but is not limited to: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, a processor 510, and a power supply 511. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 5 does not constitute a limitation of the electronic device, and that the electronic device may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.

The processor 510 is configured to obtain capacity characteristic information of a preset traffic attribute of a target cell to be detected in a wireless communication system, where the capacity characteristic information is information required for determining a cell capacity expansion priority;

a processor 510, configured to input the capacity characteristic information of the target cell into a pre-trained expansion priority evaluation model to obtain an expansion priority of the target cell, where the expansion priority evaluation model is obtained by training historical capacity characteristic information of multiple cells within a preset time period based on a preset decision tree algorithm;

the processor 510 is further configured to determine a capacity expansion policy of the target cell based on the capacity expansion priority of the target cell.

The processor 510 is further configured to acquire a first cell with the same capacity expansion priority as the target cell;

in addition, the processor 510 is further configured to perform priority ranking on the target cell and the first cell based on a preset stacking ranking algorithm, so as to obtain a target capacity expansion priority of the target cell;

in addition, the processor 510 is further configured to determine a capacity expansion policy of the target cell based on the target capacity expansion priority of the target cell.

In addition, the processor 510 is further configured to perform priority ranking on the target cell and the first cell based on a preset traffic ranking index, so as to obtain a target capacity expansion priority of the target cell.

In addition, the processor 510 is further configured to obtain historical capacity characteristic information of preset traffic attributes of the multiple cells in the preset time period;

in addition, the processor 510 is further configured to construct a corresponding decision tree based on the preset decision tree algorithm and the historical capacity feature information;

in addition, the processor 510 is further configured to obtain the capacity expansion priority evaluation model based on the decision tree.

The processor 510 is further configured to determine a plurality of first segmentation points corresponding to the preset traffic attribute;

in addition, the processor 510 is further configured to obtain a first decision point corresponding to the plurality of first segmentation points;

the processor 510 is further configured to obtain a kini coefficient of each first decision point based on the historical capacity characteristic information;

additionally, the processor 510 is further configured to determine a target decision point based on the kini coefficient of each of the first decision points;

the processor 510 is further configured to determine, as first capacity feature information, capacity feature information that satisfies the segmentation condition corresponding to the target decision point in the historical capacity feature information, and determine, as second capacity feature information, capacity feature information that does not satisfy the segmentation condition corresponding to the target decision point;

in addition, the processor 510 is further configured to construct the decision tree based on the target decision point, the first capacity characteristic information, and the second capacity characteristic information.

The processor 510 is further configured to use the target decision point as the root node of the decision tree;

additionally, the processor 510 is further configured to construct the first branch of the decision tree based on the first capacity characterization information;

furthermore, the processor 510 is further configured to construct the second branch of the decision tree based on the second capacity characterization information.

In addition, the processor 510 is further configured to obtain a first traffic attribute corresponding to the target decision point;

in addition, the processor 510 is further configured to obtain a second partition point corresponding to other traffic attributes, except the first traffic attribute, in the preset traffic attribute;

in addition, the processor 510 is further configured to obtain a second decision point corresponding to the second segmentation point;

further, the processor 510 is further configured to obtain a kini coefficient of each of the second decision points based on the first capacity characteristic information;

additionally, the processor 510 is further configured to determine a target sub-decision point based on the kini coefficient of each of the second decision points;

the processor 510 is further configured to determine, as third capacity feature information, capacity feature information that satisfies the segmentation condition corresponding to the target sub-decision point in the first capacity feature information, and determine, as fourth capacity feature information, capacity feature information that does not satisfy the segmentation condition corresponding to the target sub-decision point;

additionally, the processor 510 is further configured to construct a first sub-branch of the first branch of the decision tree based on the third capacity characteristic information;

furthermore, the processor 510 is further configured to construct a second sub-branch of the first branch of the decision tree based on the fourth capacity characterization information.

The embodiment of the invention provides electronic equipment, which is characterized in that capacity characteristic information of a target cell to be detected in a wireless communication system is acquired, the capacity characteristic information comprises cell traffic information and cell basic information, the capacity characteristic information of the target cell is input into a pre-trained capacity expansion priority evaluation model to acquire capacity expansion priority of the target cell, the capacity expansion priority evaluation model is acquired by training historical capacity characteristic information of a plurality of cells in a preset time period based on a preset decision tree algorithm, and a capacity expansion strategy of the target cell is determined based on the capacity expansion priority of the target cell. Therefore, the capacity expansion priority of the target cell can be obtained through the capacity expansion priority evaluation model and the capacity characteristic information of the target cell, the corresponding capacity expansion strategy is determined, the traffic information of the target cell does not need to be detected manually, whether the target cell needs to be expanded or not is determined, the load scheduling efficiency is improved, and meanwhile the accuracy of load scheduling is guaranteed.

It should be understood that, in the embodiment of the present invention, the radio frequency unit 501 may be used for receiving and sending signals during a message sending and receiving process or a call process, and specifically, receives downlink data from a base station and then processes the received downlink data to the processor 510; in addition, the uplink data is transmitted to the base station. In general, radio frequency unit 501 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 501 can also communicate with a network and other electronic devices through a wireless communication system.

The electronic device provides wireless broadband internet access to the user via the network module 502, such as assisting the user in sending and receiving e-mails, browsing web pages, and accessing streaming media.

The input unit 504 is used to receive an audio or video signal. The input Unit 504 may include a Graphics Processing Unit (GPU) 5041 and a microphone 5042. The processed image frames may be displayed on the display unit 506. The image frames processed by the graphic processor 5041 may be stored in the memory 509 (or other storage medium) or transmitted via the radio frequency unit 501 or the network module 502. The microphone 5042 may receive sounds and may be capable of processing such sounds into audio data. The processed audio data may be converted into a format output transmittable to a mobile communication base station via the radio frequency unit 501 in case of the phone call mode.

The display unit 506 is used to display information input by the user or information provided to the user. The Display unit 506 may include a Display panel 5061, and the Display panel 5061 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

The user input unit 507 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device. Specifically, the user input unit 507 includes a touch panel 5071 and other input devices 5072. The touch panel 5071 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 510, and receives and executes commands sent by the processor 510. Further, the touch panel 5071 may be overlaid on the display panel 5061, and when the touch panel 5071 detects a touch operation thereon or nearby, the touch operation is transmitted to the processor 510 to determine the type of the touch event, and then the processor 510 provides a corresponding visual output on the display panel 5061 according to the type of the touch event. Although in fig. 5, the touch panel 5071 and the display panel 5061 are two independent components to implement the input and output functions of the electronic device, in some embodiments, the touch panel 5071 and the display panel 5061 may be integrated to implement the input and output functions of the electronic device, and is not limited herein.

The interface unit 508 is an interface for connecting an external device to the electronic apparatus 500. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification module, an audio input/output (I/O) port, a video I/O port, an earphone port, and the like. The interface unit 508 may be used to receive input (e.g., data information, power, etc.) from external devices and transmit the received input to one or more elements within the electronic apparatus 500 or may be used to transmit data between the electronic apparatus 500 and external devices.

The memory 509 may be used to store software programs as well as various data. The memory 509 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 509 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The processor 510 is a control center of the electronic device, connects various parts of the whole electronic device by using various interfaces and lines, performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 509 and calling data stored in the memory 509, thereby performing overall monitoring of the electronic device. Processor 510 may include one or more processing units; preferably, the processor 510 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 510.

The electronic device 500 may further include a power supply 511 (e.g., a battery) for supplying power to various components, and preferably, the power supply 511 may be logically connected to the processor 510 via a power management system, so as to implement functions of managing charging, discharging, and power consumption via the power management system.

Preferably, an embodiment of the present invention further provides an electronic device, which includes a processor 510, a memory 509, and a computer program that is stored in the memory 509 and can be run on the processor 510, and when the computer program is executed by the processor 510, the processes of the load scheduling method embodiment are implemented, and the same technical effect can be achieved, and in order to avoid repetition, details are not described here again.

EXAMPLE five

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the load scheduling method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

The embodiment of the invention provides a computer-readable storage medium, which is used for inputting capacity characteristic information of a target cell to be detected in a wireless communication system into a pre-trained capacity expansion priority evaluation model to obtain capacity expansion priority of the target cell by acquiring the capacity characteristic information of the target cell to be detected, wherein the capacity characteristic information comprises cell traffic information and cell basic information, the capacity expansion priority evaluation model is obtained by training historical capacity characteristic information of a plurality of cells in a preset time period based on a preset decision tree algorithm, and a capacity expansion strategy of the target cell is determined based on the capacity expansion priority of the target cell. Therefore, the capacity expansion priority of the target cell can be obtained through the capacity expansion priority evaluation model and the capacity characteristic information of the target cell, the corresponding capacity expansion strategy is determined, the traffic information of the target cell does not need to be detected manually, whether the target cell needs to be expanded or not is determined, the load scheduling efficiency is improved, and meanwhile the accuracy of load scheduling is guaranteed.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above description is only an example of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for load scheduling, the method comprising:

2. The method of claim 1, wherein the determining the capacity expansion strategy of the target cell based on the capacity expansion priority of the target cell comprises:

3. The method according to claim 2, wherein the prioritizing the target cell and the first cell based on a preset overlap-add-order algorithm to obtain a target capacity expansion priority of the target cell comprises:

4. The method of claim 3, wherein before entering the capacity characteristic information of the target cell into a pre-selection trained capacity-expansion priority evaluation model to obtain the capacity-expansion priority of the target cell, the method further comprises:

5. The method according to claim 4, wherein the constructing a corresponding decision tree based on the preset decision tree algorithm and the historical capacity feature information comprises:

6. The method of claim 5, wherein the decision tree comprises a root node, a first branch, and a second branch, and wherein constructing the decision tree based on the target decision point, the first capacity characteristic information, and the second capacity characteristic information comprises:

taking the target decision point as the root node of the decision tree;

7. The method of claim 6, wherein after constructing the first branch of the decision tree based on the first capacity characterization information, further comprising:

acquiring a second decision point corresponding to the second division point;

8. A load scheduling apparatus, the apparatus comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring capacity characteristic information of a target cell to be detected in a wireless communication system, and the capacity characteristic information comprises cell telephone traffic information and cell basic information;

9. An electronic device, comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the load scheduling method according to any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the load scheduling method according to any one of claims 1 to 7.