KR102457331B1 - Method and apparatus for optimizing mobility-related parameter of network - Google Patents

Abstract

Determining an initial value of a parameter based on a fixed parameter determined by the environment of the network, a set of optimization parameters to be optimized, and a performance evaluation model built using machine learning, the initial value of the parameter A method of optimizing a parameter, comprising the steps of calculating a performance evaluation index by applying to a network environment and determining whether the initial value of the parameter is a final optimized mobility-related parameter value by comparing the performance evaluation index with a preset performance evaluation target index This is initiated. Here, the step of determining the initial value of the parameter includes calculating the performance evaluation index estimate based on a set of fixed parameters and optimization parameters through the performance evaluation model, and selecting the optimization parameter with the highest performance evaluation index estimate among the set of optimization parameters. It may include the step of extracting.

Description

METHOD AND APPARATUS FOR OPTIMIZING MOBILITY-RELATED PARAMETER OF NETWORK

The present invention relates to a method and apparatus for optimizing a mobility-related parameter of a network, and more particularly, to establish a performance evaluation model through machine learning to determine an initial value of a mobility-related parameter of a network, and to The present invention relates to a method and apparatus for optimizing mobility-related parameters of a network by performing an optimization cycle based on the optimization cycle.

In the existing 2G/3G wireless network, parameters related to many network elements were manually set. The design, setting, integration and management functions of network components and related parameters are very important for efficient and reliable network operation. However, manual operation of a professional engineer is required for network parameter adjustment, and due to this manual process, network parameter adjustment takes a lot of time, and there is a problem that an error may occur due to the manual operation.

In other words, the optimization of mobility-related network parameters was manually adjusted by the operator directly analyzing the problem situation based on mobility-related performance reports such as handover success rate, failure rate, and RLF occurrence type. However, a method of repeating the optimization cycle of analyzing the analysis situation and adjusting related parameters through the MRO (Mobility Robustness Optimization) function of SON (Self Organizing Network) was introduced to compensate for this manual problem.

The method of repeating the optimization cycle is a method of repeating the cycle of parameter application, performance evaluation, and parameter resetting with default parameter values that can be used without problems in various situations as initial values. However, this optimization cycle repetition method also has a problem that it may take an excessively long time depending on the number of repetitions of the cycle.

An object of the present invention for solving the above problems is to provide a method for optimizing a network mobility-related parameter.

Another object of the present invention to solve the above problems is to provide an apparatus for optimizing a network mobility-related parameter.

In a parameter optimization method according to an embodiment of the present invention for achieving the above object, a fixed parameter determined by a network environment, a set of optimization parameters to be optimized, and performance built using machine learning Determining the initial value of the parameter based on the evaluation model, calculating the performance evaluation index by applying the initial value of the parameter to the network environment, and comparing the performance evaluation index with the preset performance evaluation target index to determine the initial value of the parameter and determining whether it is a final optimized mobility-related parameter value.

Here, the determining of the initial values of the parameters may include generating a set of optimization parameters based on combinations of available individual optimization parameter values.

Here, the step of determining the initial value of the parameter may include calculating a performance evaluation index estimate based on a set of fixed parameters and optimization parameters through the performance evaluation model.

Here, the step of determining the initial value of the parameter includes extracting an optimization parameter having the highest performance evaluation index estimate among a set of optimization parameters, and determining individual optimization parameter values included in the extracted optimization parameter as the initial value of the parameter. may further include.

Here, the step of determining the initial value of the parameter may include constructing a performance evaluation model by performing machine learning based on a training data set stored in a database.

Here, the training data set may include a training parameter and a performance evaluation index according to the training parameter.

Here, the method may further include adding the initial value of the parameter and the performance evaluation index to the training data set.

Here, the step of determining whether the final optimized mobility-related parameter value is the step of performing a parameter optimization algorithm if the performance evaluation index is not greater than the performance evaluation target index, and applying the result value of the parameter optimization algorithm to the network to evaluate the performance The step of re-calculating the index, the step of repeatedly performing the parameter optimization algorithm until the recalculated performance evaluation index is greater than the performance evaluation target index, and the step of re-calculating the performance evaluation index, and the recalculated performance evaluation index When it is greater than the performance evaluation target index, the method may include determining a result value of the parameter optimization algorithm as a final optimized mobility-related parameter value.

Here, the step of determining whether it is the final optimized mobility-related parameter value may further include adding the result value of the parameter optimization algorithm and the recalculated performance evaluation index to the training data set.

Here, when the amount of change of the training dataset is larger than a preset value according to the addition of the training dataset, the method may further include the step of reconstructing the performance evaluation model through machine learning including the added training dataset.

A parameter optimization apparatus according to an embodiment of the present invention for achieving the above another object includes a processor and a memory in which at least one instruction executed through the processor is stored, and the at least one instruction comprises: It may be executed to determine an initial value of a parameter based on a fixed parameter determined by the network environment, a set of optimization parameters to be optimized, and a performance evaluation model built using machine learning, and It may be executed to calculate the performance evaluation index by applying the value to the network environment, and may be executed to determine whether the initial value of the parameter is the final optimized mobility-related parameter value by comparing the performance evaluation index and the preset performance evaluation target index.

Here, at least one instruction may be executed to generate a set of optimization parameters based on combinations of available individual optimization parameter values.

Here, the at least one instruction may be executed to calculate a performance evaluation index estimate based on a set of fixed parameters and optimization parameters through the performance evaluation model.

Here, the at least one command may be executed to extract an optimization parameter having the highest performance evaluation index estimate among a set of optimization parameters, and may be executed to determine an individual optimization parameter value included in the extracted optimization parameter as an initial value of the parameter. .

Here, at least one command may be executed to build a performance evaluation model by performing machine learning based on a training data set stored in a database.

Here, the training data set may include a training parameter and a performance evaluation index according to the training parameter.

Here, the at least one command may be executed to add the initial value of the parameter and the performance evaluation index to the training data set.

Here, the at least one command may be executed to perform a parameter optimization algorithm when the performance evaluation index is not greater than the performance evaluation target index, and to be executed to recalculate the performance evaluation index by applying the result value of the parameter optimization algorithm to the network. The performance of the parameter optimization algorithm and the recalculation of the performance evaluation index may be repeatedly performed until the recalculated performance evaluation index is larger than the performance evaluation target index, and the recalculated performance evaluation index is larger than the performance evaluation target index. In this case, it may be executed to determine the result of the parameter optimization algorithm as the final optimized mobility-related parameter value.

Here, at least one command may be executed to add the result value of the parameter optimization algorithm and the recalculated performance evaluation index to the training data set.

Here, at least one command may be executed to reconstruct the performance evaluation model through machine learning including the added training data set when the amount of change of the training data set is larger than a preset value according to the addition of the training data set. .

According to the present invention, since the optimization cycle is performed using an initial value close to the optimization parameter value, the number of cycle repetitions is reduced, so that parameter optimization can be performed relatively quickly.

According to the present invention, since the performance evaluation model can be reconstructed through machine learning according to the addition of the training data set, the performance of determining the initial value close to the optimal value can be continuously improved.

1 is a table showing mobility-related network parameters to be optimized according to the 3GPP standard.
2 is a diagram illustrating an optimization cycle of network parameters.
3 is a block diagram of an apparatus for optimizing parameters according to an embodiment of the present invention.
4 is a diagram illustrating the structure of a training data set according to an embodiment of the present invention.
5 is a diagram illustrating a process of generating a performance evaluation model according to an embodiment of the present invention.
6 is a diagram illustrating a set of optimization parameters according to an embodiment of the present invention.
7 is a diagram illustrating a process of calculating a performance evaluation index estimate using a performance evaluation model according to an embodiment of the present invention.
8 is a flowchart illustrating a parameter initial value setting method according to an embodiment of the present invention.
9 is a flowchart illustrating a parameter optimization method according to an embodiment of the present invention.
10 is a flowchart illustrating a method for reconstructing a performance evaluation model according to an embodiment of the present invention.

Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention. In describing each figure, like reference numerals have been used for like elements.

Terms such as first, second, A, B, etc. may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. The term "and/or" includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but it is understood that other components may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It is to be understood that this does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate the overall understanding, the same reference numerals are used for the same components in the drawings, and duplicate descriptions of the same components are omitted. Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

One of the advantages of a mobile communication terminal is mobility that allows a user to use a service while moving, as well as wireless communication that is free from the limitations of wired communication. The reason why a mobile communication terminal can use a communication service while moving is that handover is provided in a mobile communication network.

In the handover, the mobile communication terminal decreases the strength of the received signal from the serving cell to which it is currently connected, and the neighboring cell ( When the strength of a received signal from a neighbor cell starts to increase, it may mean that the mobile communication terminal accesses another cell having a good received signal and establishes a new RRC (Radio Resource Control) connection.

In other words, the mobile communication terminal in communication can continuously communicate by connecting from the currently accessed base station (serving cell) to another base station (neighbor cell) without loss of transmit/receive data through handover. it will be available

LTE (Long Term Evolution) handover uses X2 interface (hereinafter referred to as X2 handover) and S1 interface depending on whether EPC (Evolved Packet Core) is involved in the preparation and execution of handover between the serving cell and the neighboring cell. It may be classified as a handover (hereinafter, S1 handover).

The X2 interface is an interface between LTE base stations, and X2 handover may be performed when there is an X2 connection between the serving base station to which the serving cell belongs and the target base station to which the target cell to be handover belongs. When the X2 handover is performed, the X2 interface may communicate for handover control between the serving base station and the target base station without MME (Mobility Management Entity) intervention.

The S1 interface is an interface between the base station and the EPC (the MME in the case of a control message or the serving gateway (S-GW) in the case of a user packet). S1 handover may be performed if it is not allowed to use, or handover preparation operation fails between the serving cell and the target cell through X2. In the S1 interface, when S1 handover is performed, the serving base station may communicate with the target base station through the MME for handover control.

When an RRC connection is established between a base station and a mobile communication terminal, for handover, the base station reports the received signal strength to the mobile communication terminal when there is any event such as a change in the strength of the received signal of the serving cell and the neighboring cell. Mobility Related parameter (mobility parameters) information may be delivered through an RRC Connection Reconfiguration message.

The mobile communication terminal measures the received signal strengths of the serving cell and neighboring cells, and when a corresponding event occurs, the mobile communication terminal may report these signal strengths to the serving base station through a Measurement Report message, and the serving base station receives the signal strength information reported by the terminal. The handover may be determined by referring to the overload state information of the and neighboring cells, and the handover may be performed to a cell determined as a handover target.

1 is a table showing mobility-related network parameters to be optimized according to the 3GPP standard.

2 is a diagram illustrating an optimization cycle of network parameters.

The mobility-related parameters of FIG. 1 that can be used in the process of performing the above-described handover are manually adjusted by the operator directly analyzing the problem situation based on the mobility-related performance report such as the handover success rate, the failure rate, and the RLF occurrence type for optimization. Alternatively, through the Mobility Robustness Optimization (MRO) function of the Self Organizing Network (SON), the optimization cycle of analyzing the analysis situation and adjusting related parameters as shown in FIG. 2 may be repeated. Here, FIGS. 1 and 2 show examples of mobility-related network parameters and examples of optimization cycles, but are not limited thereto.

The parameters in the direction of increasing the performance in relation to the parameters related to mobility are based on the engineer's experience, or the default parameter values that can be used without problems in various situations are set as initial values, and the cycle of parameter application, performance evaluation and parameter resetting can be repeated. However, this cycle repetition may have the following problems.

The first is that the time required to reach the optimized network may be large depending on the excessive number of iterations of the cycle because the default parameter value is the initial value until the optimal parameter is found. Even if SON technology is used, there is a time required for initial parameter application, performance data collection, performance data analysis, and setting of new parameter values according to the analysis results. because there is

The second point is that data of the optimum value found through the optimization cycle or data with an approximate value to the optimum are not used. Up to now, SON technology has gradually calculated and applied an optimal value or an approximation value to the optimal value through a mobility parameter optimization algorithm. Therefore, when the mobility parameter is optimized in a similar network environment but in a different network environment later, the cycle iteration fails to utilize the existing optimization result and starts again from the default parameter value, so there is a relatively inefficient problem. This is because the value calculated through the optimization algorithm is suitable only for the corresponding network environment, so it cannot be directly applied to other network environments, and it is difficult to determine how similar or different the existing environment is from the new environment.

Therefore, the present invention constructs a performance evaluation model through machine learning by configuring the performance evaluation index according to parameters and parameters as a training data set, and determines an initial value close to the optimal value of the network environment through this cycle. We propose a method for performing relatively efficient parameter optimization by reducing the number of iterations.

3 is a block diagram of an apparatus for optimizing parameters according to an embodiment of the present invention.

Referring to FIG. 3 , the parameter optimization apparatus 300 according to an embodiment of the present invention may include at least one processor 310 , a memory 320 , and a storage device 330 .

The processor 310 may execute a program command stored in the memory 320 and/or the storage device 330 . The processor 310 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to the present invention are performed. The memory 320 and the storage device 330 may be configured of a volatile storage medium and/or a non-volatile storage medium. For example, the memory 320 may be configured as a read only memory (ROM) and/or a random access memory (RAM).

The memory 320 may store at least one instruction executed through the processor 310 . At least one command is a command for determining an initial value of a parameter based on a fixed parameter determined by the network environment, a set of optimization parameters to be optimized, and a performance evaluation model built using machine learning; Includes a command to calculate the performance evaluation index by applying the initial value of the parameter to the network environment, and a command to determine whether the initial value of the parameter is the final optimized mobility-related parameter value by comparing the performance evaluation index and the preset performance evaluation target index can do.

Here, the at least one command for determining the initial value of the parameter is a command for generating a set of optimization parameters based on a combination of available individual optimization parameter values, a set of fixed parameters and optimization parameters through a performance evaluation model. A command for calculating the performance evaluation index estimate, a command for extracting the optimization parameter with the highest performance evaluation index estimate among a set of optimization parameters, a command for determining the individual optimization parameter values included in the extracted optimization parameter as the initial value of the parameters, and the database It may further include at least one of the instructions for constructing a performance evaluation model by performing machine learning based on the stored training data set (set).

Here, at least one command for determining the final optimized mobility-related parameter value is a command to perform a parameter optimization algorithm, when the performance evaluation index is not greater than the performance evaluation target index, and the result value of the parameter optimization algorithm is applied to the network. The command to recalculate the performance evaluation index, the command to execute the parameter optimization algorithm and the command to recalculate the performance evaluation index until the recalculated performance evaluation index is larger than the performance evaluation target index, and the command to repeatedly perform the command to recalculate the performance evaluation index When the index is larger than the performance evaluation target index, at least among the command to determine the result value of the parameter optimization algorithm as the final optimized mobility-related parameter value, and the command to add the result value of the parameter optimization algorithm and the recalculated performance evaluation index to the training data set It may include one more.

Here, at least one command is a command for adding the initial value and performance evaluation index of a parameter to the training data set and when the amount of change in the training data set according to the addition of the training data set is greater than a preset value, the added training data set Including, it may further include at least one of the instructions for rebuilding the performance evaluation model through machine learning.

Here, the training data set may include a training parameter and a performance evaluation index according to the training parameter.

The operation of the parameter optimizing apparatus 300 according to an embodiment of the present invention may be largely represented by first to fourth steps. Here, the first step may be a step of building a performance evaluation model through machine learning, and the second step may be a step of determining initial values of parameters based on the performance evaluation model. In addition, the third step may be a step of adding a training data set while performing an optimization cycle based on the initial value, and the fourth step is using machine learning when the amount of change of the added training data set is greater than a preset value. It may be a step to rebuild the performance evaluation model.

Here, each step is divided for convenience in explaining the operation of the parameter optimization apparatus 300 according to an embodiment of the present invention, and the order and division of each step are not limited thereto.

First, the structure of a training data set used in the apparatus for optimizing parameters according to an embodiment of the present invention will be described later with reference to FIG. 4 . Hereinafter, a more detailed description of the first step will be described later with FIG. 5 , and a more detailed description of the second step will be described later with FIGS. 6 , 7 and 8 . In addition, a more detailed description of the third step will be described later with FIG. 9, and a more detailed description of the fourth step will be described later with FIG. 10 . Before a more detailed description of the first step

4 is a diagram illustrating the structure of a training data set according to an embodiment of the present invention.

Referring to FIG. 4 , the training data set according to an embodiment of the present invention is a parameter whose value is fixed according to a change in the environment (Fixed Parameter, FP), and an optimization parameter that needs to optimize the value according to the change of the environment (Optimization Parameter) , OP) and parameters may be included in the network environment, including the Key Performance Index (KPI) of the mobile communication terminal. Here, each parameter and performance evaluation index may include at least one individual parameter and individual performance evaluation index, and the fixed parameter (FP) and optimization parameter OP) are independent variables at the point where the performance evaluation index is determined by the parameter. It can be expressed as X, and the performance evaluation index (KPI) can be expressed as a dependent variable Y.

4 , since each parameter and performance index may include at least one individual parameter and individual performance index, the fixed parameter FP may include 1 individual fixed parameter, and the optimization parameter OP ) may include m individual optimization parameters, and KPI may include n individual performance evaluation parameters. Here, l, m, and n may each mean a positive integer of 1 or more.

The values of the individual parameters FP ₁ to FP ₁ of the fixed parameter FP may have a value in a real range according to changes in the environment, but the values of the individual parameters OP ₁ to OP _m of the optimization parameter OP are It can have a value within a set of finite discrete values according to the specification for the components of the network. In other words, the target parameter to be optimized by the apparatus for optimizing parameters according to an embodiment of the present invention has a value within a specific set of discrete values, and thus may have a finite number of combinations. A detailed description thereof will be described later along with FIG. 6 .

The performance evaluation index (KPI) may be an index that can determine whether a parameter is optimized. In other words, if the individual performance evaluation index (KPI ₁ to KPI _n ) of the performance evaluation index (KPI) is high, the corresponding parameter can be determined as a parameter suitable for the environment. can be judged as Accordingly, the corresponding parameter when the individual performance evaluation index (KPI ₁ to KPI _n ) of the performance evaluation index (KPI) is the highest may be determined as a parameter optimized for the environment.

Here, when the size of each individual performance evaluation index (KPI ₁ to KPI _n ) is different, a specific performance evaluation index among individual performance evaluation indices is considered first, and if they are equal, the next specific performance evaluation index is considered, all individual performance evaluations The best performance evaluation index may be selected using either a method of using the average value of the index or a method of allocating a weight for each performance evaluation index, but the above-described method is provided as an example and is not limited thereto.

The training data set having the structure of FIG. 4 may be used as a training set for performing machine learning in the first step, and data input to the performance evaluation model to determine the initial value of the parameter in the second step It can also be used in the structure of In this regard, it will be further described later along with the description of each step.

5 is a diagram illustrating a process of generating a performance evaluation model according to an embodiment of the present invention.

The first step may be a step of building a performance evaluation model through machine learning.

The apparatus for optimizing a parameter according to an embodiment of the present invention may construct a performance evaluation model by performing machine learning based on a training data set. Here, the training data set may have the structure of FIG. 4 , and the values of parameters and performance evaluation index included in the training data set may be determined based on data accumulated in the existing network operation process, and through methods such as simulation You can also create and use data.

The apparatus for optimizing parameters according to an embodiment of the present invention may store accumulated data or data generated through a method such as simulation in a database, and may be obtained from the outside through wired/wireless communication, but in order to perform machine learning A method of acquiring data for this purpose is not limited thereto. In addition, as the machine learning method used by the parameter optimization apparatus according to an embodiment of the present invention, any general machine learning method may be used.

The performance evaluation model construction in the first stage may be initially performed only once, and thereafter, the performance evaluation model rebuilding for improving the performance of the model may be performed in the fourth stage to be described later.

6 is a diagram illustrating a set of optimization parameters according to an embodiment of the present invention.

The second step may be a step of determining initial values of parameters based on the performance evaluation model.

The apparatus for optimizing a parameter according to an embodiment of the present invention inputs a fixed parameter (FP) and an optimization parameter (OP) into a performance evaluation model, and calculates a performance evaluation index (KPI) estimate for the corresponding parameter as an output of the performance evaluation model and the parameter for which the performance evaluation index (KPI) estimate is the highest may be determined as the initial value.

More specifically, in the parameter optimization apparatus according to an embodiment of the present invention, the parameters input to the performance evaluation model are fixed parameters (FP) and changeable parameters depending on the network environment and optimization parameters for which a specific value must be determined for optimization. (OP) may be included. Here, the optimization parameter (OP) may be determined as one of finite discrete values according to the specification for network components as described above,

Accordingly, the apparatus for optimizing a parameter according to an embodiment of the present invention generates a set of optimization parameters by combining all possible individual optimization parameter values, and adds a fixed parameter (FP) to each optimization parameter included in the optimization parameter set to at least One input parameter set can be created.

Here, the process of generating a set of optimization parameters will be described in more detail as follows.

The parameter FP having a fixed value according to a change in the network environment may include the individual fixed parameters FP ₁ to FP ₁ , and the value of the fixed parameter FP may be expressed as Equation (1).

In Equation 1, VFP may mean values of fixed parameters FP, and VFP ₁ to VFP ₁ may mean values of individual fixed parameters FP ₁ to FP ₁ . Here, l may mean the number of individually fixed parameters, and may be a positive integer of 1 or more.

The optimization parameter OP that needs to be optimized according to a change in the network environment may include individual optimization parameters OP ₁ to OP _m , and the value of the optimization parameter OP may be expressed as Equation (2).

In Equation 2, VOP may mean values of optimization parameters OP, and VOP1 to VOPm may mean values of individual optimization parameters OP ₁ to OP _m . Here, m may mean the number of individual optimization parameters, and may be a positive integer of 1 or more.

Here, since the value VOP of the optimization parameter may have values of a plurality of optimization parameters according to a combination of available individual optimization parameters, a set of optimization parameters may be generated accordingly.

The set of optimization parameters according to an embodiment of the present invention may include each optimization parameter according to a combination of individual optimization parameter values. Here, the possible values of individual optimization parameter values may be expressed as in Equation (3).

In Equation 3, SVOP _j may mean a set of all values that the j-th VOP may have, and v _j1 to v _jl may mean l values that the j-th VOP may have, respectively. Here, l may be a positive integer of 1 or more.

For example, when the i-th individual optimization parameter (OP _i ) may have values of a, b, and c, SVOP _i may be expressed as {a, b, c}.

The sum of the optimization parameters including each optimization parameter according to the combination of each individual optimization parameter value can be expressed as Equation (4).

In Equation 4, VOP may mean an optimization parameter, m may mean the number of individual optimization parameters, and may be a positive integer of 1 or more. In addition, CVOP may mean a set of optimization parameters, and may mean all combinations of possible individual optimization parameters.

6 is an example for explaining a set of optimization parameters, in one example, three individual optimization parameters included in the optimization parameter, the first individual optimization parameter may have values of 1 and 2, and the second individual optimization parameter Assume that the parameter may have values of 3 and 4, and the third individual optimization parameter may have values of 5 and 6.

Each individual optimization parameter SVOP ₁ to SVOP ₃ and a set of optimization parameters CVOP according to the assumptions described above with reference to FIG. 6 may be expressed as follows.

SVOP ₁ = {1, 2}

SVOP ₂ = {3, 4}

SVOP ₃ = {5, 6}

CVOP= {(1, 3, 5), (1, 3, 6), (1, 4, 5), (1, 4, 6), (2, 3, 5), (2, 3, 6) , (2, 4, 5), (2, 4, 6)}

In other words, the set of optimization parameters (CVOP) according to the example of FIG. 6 may include eight optimization parameters.

7 is a diagram illustrating a process of calculating a performance evaluation index estimate using a performance evaluation model according to an embodiment of the present invention.

Referring to FIG. 7 , the apparatus for optimizing a parameter according to an embodiment of the present invention inputs all input parameters obtained by adding a fixed parameter value (VFP) to individual elements of a set of optimization parameters (CVOP) into a performance evaluation model. can do.

Accordingly, the parameter optimization device can calculate the KPI estimate for the corresponding parameter by the performance evaluation model, respectively, and determine the corresponding parameter with the highest KPI as the initial value of the parameter optimization cycle. can

In other words, the optimization parameter value (VOP) and the fixed parameter value (VFP) of the input parameter having the highest performance evaluation index (KPI) may be determined as the initial values of the parameters.

8 is a flowchart illustrating a parameter initial value setting method according to an embodiment of the present invention.

The second step of the present invention will be described with reference to FIG. 8 as follows.

First, the apparatus for optimizing parameters according to an embodiment of the present invention may generate a set of quantitative parameters based on a combination of available individual optimization parameter values (S810).

The parameter optimization apparatus may calculate a performance evaluation index estimate based on a set of parameters fixed according to an environment and a set of optimization parameters through a performance evaluation model built using machine learning in the first step ( S820 ). Here, the parameter optimization apparatus may add fixed parameters to individual elements included in the set of optimization parameters, respectively, and input them into the performance evaluation model, and thus may calculate the performance evaluation index estimates for the corresponding parameters, respectively.

The parameter optimization apparatus may extract the optimization parameter having the highest performance evaluation index estimate among the set of optimization parameters (S830), and determine individual optimization parameter values included in the extracted parameters as the initial values of the optimization parameters (S840).

The parameter optimization apparatus may perform an optimization cycle based on the determined initial value of the optimization parameter and the fixed parameter, which will be described later with reference to FIG. 9 .

9 is a flowchart illustrating a parameter optimization method according to an embodiment of the present invention.

The third step may be a step of performing an optimization cycle based on the initial value and adding a training data set.

Referring to FIG. 9 , the apparatus for optimizing a parameter according to an embodiment of the present invention may first set an initial value of a parameter based on the value of the optimization parameter determined through the above-described steps and the value of the fixed parameter ( S910 ).

The parameter optimization device can calculate the performance evaluation index according to the environment by applying it to the network based on the value of the set parameter (S920), and at this time, the parameter value and the performance evaluation index are added to the training dataset as a pair. It can be added (S930). In other words, the parameter optimization device stores parameter values and performance evaluation indexes in a database and can be used for machine learning when reconstructing a performance evaluation model later. A detailed description thereof will be described later with reference to FIG. 10 .

The parameter optimization apparatus may compare the calculated performance evaluation index with the performance evaluation target index preset by the user (S940), and if the performance evaluation index is not greater than the performance evaluation target index, perform a network parameter optimization algorithm (S950) ), by modifying the parameter value to the result value of the algorithm (S960), a parameter optimization cycle may be performed.

Therefore, the parameter optimization apparatus may calculate the performance evaluation index after applying the modified parameter value to the network again (S920), and may be repeatedly performed until the performance evaluation index is greater than the performance evaluation target index. In addition, the parameter optimization apparatus may store the parameter value and the performance evaluation index in a database every time the performance evaluation index is calculated and add it to the training data set. Here, as the parameter optimization algorithm, an algorithm used in a normal parameter optimization cycle may be used.

When the performance evaluation index is greater than the performance evaluation target index, the parameter optimization apparatus may determine the corresponding parameter as the final optimization parameter (S970).

10 is a flowchart illustrating a method for reconstructing a performance evaluation model according to an embodiment of the present invention.

The fourth step may be a step of reconstructing a performance evaluation model using machine learning when the amount of change of the added training data set is greater than a preset value.

Referring to FIG. 9 , the apparatus for optimizing parameters according to an embodiment of the present invention may check the amount of change of the training data set added in the third step, and compare the change amount of the training data set with a value preset by the user. can be (S1010).

When the amount of change in the training data set is larger than the value preset by the user, the parameter optimization device considers that the number of iterations of the optimization cycle is excessive, and performs machine learning based on the existing training data set and the added training data set to evaluate performance. The model may be reconstructed (S1020).

However, when the amount of change in the training data set is not greater than a value preset by the user, the parameter optimization apparatus can maintain the current performance evaluation model as it is determined that the current performance evaluation model and the number of repetitions of the optimization cycle are appropriate.

The apparatus for optimizing a parameter according to an embodiment of the present invention can provide a short optimization time by reducing the number of repetitions of a parameter optimization cycle according to a change in a network environment by the above-described operations, and it is possible to reconstruct a performance evaluation model under a specific condition. Through this, parameter optimization performance can be continuously improved.

The operation according to the embodiment of the present invention can be implemented as a computer-readable program or code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. In addition, the computer-readable recording medium may be distributed in a network-connected computer system to store and execute computer-readable programs or codes in a distributed manner.

In addition, the computer-readable recording medium may include a hardware device specially configured to store and execute program instructions, such as ROM, RAM, and flash memory. The program instructions may include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

Although some aspects of the invention have been described in the context of an apparatus, it may also represent a description according to a corresponding method, wherein a block or apparatus corresponds to a method step or feature of a method step. Similarly, aspects described in the context of a method may also represent a corresponding block or item or a corresponding device feature. Some or all of the method steps may be performed by (or using) a hardware device such as, for example, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, one or more of the most important method steps may be performed by such an apparatus.

In embodiments, a programmable logic device (eg, a field programmable gate array) may be used to perform some or all of the functionality of the methods described herein. In embodiments, the field programmable gate array may operate in conjunction with a microprocessor to perform one of the methods described herein. In general, the methods are preferably performed by some hardware device.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

300: parameter optimizer 310: processor
320: memory 330: storage device

Claims (20)

A method of optimizing mobility-related parameters to be suitable for a mobile communication network, the method comprising:
constructing a parameter optimization model trained by machine learning using a training data set;
determining an initial value of the parameter to be applied to the network using the parameter optimization model;
operating the network by applying the initial value of the parameter to the network, and optimizing the parameter by changing the parameter value and calculating a performance evaluation index accordingly; and
Reinforcing by adding the changed parameter value and the corresponding combination of the performance evaluation index to the training data set, and reconstructing the parameter optimization model using the reinforced training data set
Including, parameter optimization method. The method according to claim 1,
wherein the parameter comprises a plurality of individual parameters. 3. The method according to claim 2,
Determining the initial value of the parameter comprises:
calculating a performance evaluation index estimate based on a combination of usable parameter values for the plurality of individual parameters; and
and determining initial values of parameter values for the plurality of individual parameters based on the performance score estimate. The method according to claim 1,
and optimizing the parameter by changing the parameter value and calculating the performance evaluation index accordingly, using the parameter optimization model. The method according to claim 1,
The training data set used to build the parameter optimization model is
A parameter optimization method comprising at least one of data accumulated in an existing operation process of the network and data generated by simulation. delete delete 6. The method of claim 5,
The step of optimizing the parameter through the change of the parameter value and the calculation of the performance evaluation index accordingly
if the performance evaluation index does not satisfy a predetermined condition, changing the parameter value and calculating the performance evaluation index according to the changed parameter value; and
and repeatedly performing the steps of changing the parameter value and calculating the performance evaluation index until the performance evaluation index satisfies the condition. The method according to claim 8, wherein the predetermined condition is
The parameter optimization method, wherein the performance evaluation index is greater than a predetermined performance evaluation target index. The method according to claim 1, Reconstructing the parameter optimization model comprises:
The parameter optimization method, which is performed only when the amount of change of the training data set is greater than a preset value. An apparatus for optimizing mobility-related parameters to be suitable for a mobile communication network, comprising:
processor; and
At least one instruction executed through the processor comprises a memory (memory) stored,
When the at least one instruction is executed by the processor:
build a parameter optimization model trained by machine learning using the training data set;
determine an initial value of the parameter to be applied to the network using the parameter optimization model;
operating the network by applying the initial value of the parameter to the network, and optimizing the parameter by changing the parameter value and calculating a performance evaluation index accordingly;
A parameter optimization apparatus for reconstructing the parameter optimization model by adding the changed parameter value and the corresponding combination of the performance evaluation index to the training data set, and reconstructing the parameter optimization model using the reinforced training data set. 12. The method of claim 11,
wherein the parameter comprises a plurality of individual parameters. 13. The method of claim 12, wherein the instruction to determine the initial value of the parameter when executed by the processor comprises:
calculating a performance evaluation index estimate in units of combinations of usable parameter values for the plurality of individual parameters;
and determining initial values of parameter values for the plurality of individual parameters based on the performance evaluation index estimate. 12. The method of claim 11,
The command for optimizing the parameter through the change of the parameter value and the calculation of the performance evaluation index accordingly
A parameter optimizing device for optimizing the parameter by using the parameter optimization model. 12. The method of claim 11,
The training data set used to build the parameter optimization model is
and at least one of data accumulated in an existing operation process of the network and data generated by simulation. delete delete 16. The method of claim 15,
The command for optimizing the parameter through the change of the parameter value and the calculation of the performance evaluation index accordingly
when the performance evaluation index does not satisfy a predetermined condition, changing the parameter value and calculating the performance evaluation index according to the changed parameter value;
until the performance evaluation index satisfies the condition, repeatedly changing the parameter value and calculating the performance evaluation index. The method according to claim 18, wherein the predetermined condition is
wherein the performance evaluation index is greater than a predetermined performance evaluation target index. The method according to claim 11, wherein the command to rebuild the parameter optimization model is
The apparatus for optimizing parameters, which is executed only when the amount of change of the training data set is greater than a preset value.

Images