Parameter updating method, system and electronic device

Through particle swarm algorithm and forgetting factor optimization technology, the problem of NR to LTE switching success rate optimization is solved, and the rapid response and efficient optimization of base station parameter configuration is achieved, and the 5G user experience is improved.

CN115529606BActive Publication Date: 2024-11-12CHINA MOBILE GROUP JILIN BRANCH +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110708855.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-25
Publication Date
2024-11-12
Estimated Expiration
2041-06-25

AI Technical Summary

Technical Problem

During the coexistence period of 5G NR and LTE networks, it is difficult to optimize the success rate of NR to LTE switching. The existing methods cannot quickly respond to changes in the network environment and user model, resulting in low parameter configuration efficiency and ineffective improvement of base station service quality.

Method used

Through the particle swarm algorithm, the forgetting factor is used to strengthen the weight influence of the current data, reduce the influence of historical data, calculate the optimal position of the particle, and use the optimal position to replace the extreme position of the particle, optimize the base station configuration parameters, and improve the system's overall Responsiveness of environmental changes and algorithm convergence speed.

Benefits of technology

It improves the service quality of the base station, enhances the ability to respond quickly to changes in the current environment and user model, and improves the success rate of NR to LTE switching and overall network performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115529606B_ABST
    Figure CN115529606B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses a parameter updating method, system and electronic device, the method comprising: obtaining configuration parameters of a base station, a particle group and a corresponding relationship, wherein the particle group includes a plurality of particles, and the corresponding relationship includes a corresponding relationship between the configuration parameters of the base station and the positions of the particles; initializing the position of each particle in the particle group based on the configuration parameters of the base station, and iteratively updating the position of each particle in the particle group to obtain the iteratively updated particle position; obtaining the extreme position of each particle based on the iteratively updated particle position; obtaining a forgetting factor, and obtaining an optimal position based on the forgetting factor and the extreme position of each particle, and replacing the extreme position of the particle with the optimal position; updating the configuration parameters of the base station based on the corresponding relationship and the optimal position of each particle.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to the field of wireless communication technology, and in particular to a parameter updating method, system and electronic equipment. [Background technology]

[0002] It is difficult to form continuous coverage in the early stage of 5G NR (New Radio) network construction. Therefore, mobility management between heterogeneous systems of 5G network is used to ensure the continuity of user service experience. When the coverage of 5G NR network is discontinuous, the LTE (Long Term Evolution) network with continuous coverage is used as the underlying coverage to perform timely NR to LTE switching, effectively reducing the impact of weak coverage areas and coverage holes of 5G NR network and improving user network quality. During the coexistence period of NR network and LTE network, mobility management between heterogeneous systems of 5G network, parameter configuration and optimization of switching process have become the key tasks of network optimization. Among them, the success rate of NR to LTE switching is the most intuitive manifestation of the continuity of user service experience. Therefore, how to optimize the heterogeneous system configuration parameters is one of the key factors to improve the success rate of NR to LTE switching and improve network service quality. [Summary of the invention]

[0003] In view of this, the embodiments of the present invention provide a parameter updating method, system and electronic device, which strengthen the weight influence of current data through a forgetting factor and reduce the influence of historical data to calculate the optimal position of the particle, and use the optimal position to replace the extreme position of the particle, which is beneficial to enhance the system's ability to respond quickly to changes in the current environment and user model, accelerate the convergence speed and optimization accuracy of the system algorithm, and solve the parameter configuration problems existing in base stations in various scenarios, and improve the service quality of base stations.

[0004] In a first aspect, an embodiment of the present invention provides a parameter updating method, the method comprising:

[0005] Acquire configuration parameters of a base station, a particle group, and a corresponding relationship, wherein the particle group includes a plurality of particles, and the corresponding relationship includes a corresponding relationship between the configuration parameters of the base station and the positions of the particles;

[0006] Initializing the position of each particle in the particle swarm based on the configuration parameters of the base station, and iteratively updating the position of each particle in the particle swarm to obtain an iteratively updated particle position;

[0007] Based on the iteratively updated particle positions, obtaining the extreme position of each particle;

[0008] Obtaining a forgetting factor, and obtaining an optimal position based on the forgetting factor and the extreme position of each particle, and replacing the extreme position of the particle with the optimal position;

[0009] Based on the corresponding relationship and the optimal position of each particle, the configuration parameters of the base station are updated.

[0010] In one possible implementation, the optimal position is given by the formula:

[0011] Calculated;

[0012] Among them, P() is the optimal position of the particle, g n is the number of iterations n, M is the number of particles in the particle swarm, e is a constant, β is the forgetting factor, P i is the extreme position of the particle.

[0013] In one possible implementation, initializing the position of each particle in the particle swarm includes:

[0014] Based on the configuration parameters of the multiple base stations, obtaining the proportion of the same configuration parameters in all the configuration parameters;

[0015] According to the proportion of the same configuration parameters, a first number of configuration parameters are selected from large to small;

[0016] According to a preset step size, within the parameter range of the configuration parameters, determine a second number of configuration parameters, and select a third number of configuration parameters from the second number of configuration parameters;

[0017] The first number of configuration parameters and the third number of configuration parameters are configured as the position of each particle in the particle group, and the number of particles in the particle group is equal to the sum of the first number and the third number.

[0018] In one possible implementation, the iteratively updating the position of each particle in the particle group to obtain an iteratively updated particle position includes:

[0019] After each iterative update, a fitness value of the particle is obtained based on the current position of the particle, where the fitness value of the particle is used to represent the service quality of the base station;

[0020] Based on the fitness value of the particle, determining whether a particle swarm initialization condition is met;

[0021] If the particle swarm initialization condition is met, the position of each particle in the particle swarm is initialized;

[0022] If the particle swarm initialization condition is not met, the next iterative update is performed.

[0023] In one possible implementation, the particle swarm initialization condition includes:

[0024] |E(g n -1)-E(g n -2)|≤R1 and |E(g n )-E(g n -1)|≥R2;

[0025] Among them, E() is the mean square error of the fitness value of the particle, g n is the number of iterations, R1 and R2 are set values.

[0026] In one possible implementation, obtaining the fitness value of the particle based on the current position of the particle includes:

[0027] Based on the corresponding relationship and the current position of the particle, obtaining target configuration parameters;

[0028] Setting the configuration parameters of the base station to the target configuration parameters, and obtaining the service quality of the base station within a preset time period;

[0029] Based on the service quality, a fitness value of the particle is obtained.

[0030] In one possible implementation, the fitness value is given by the formula:

[0031] Calculated;

[0032] Among them, J(Y) is the fitness value, Q1 and Q2 are set values, and Z1 is the network switching success rate, Z2 is the network redirection success rate, w1 is found in the preset first relationship table according to the network switching success rate, and w2 is found in the preset second relationship table according to the network redirection success rate.

[0033] In one possible implementation, the particle position after iterative update is given by the formula:

[0034] X i,d (g n +1) = X i,d (g n )+V i,d (g n +1),

[0035] V i,d (g n +1)=w*V i,d (gn )+c1*r1(g n )(P d (g n )-X i,d (g n ))+c2*r2(g n )(P g,d (g n )-X i,d (g n ))Calculated,

[0036] Among them, X i,d () is the position of the ith particle in the dth dimension, V i,d () is the update speed of the ith particle in the dth dimension, g n is the number of iterations n, P d () is the optimal position of the particle in the dth dimension, P g,d () is the group extreme value of the particle swarm in the dth dimension, w is the inertia weight, r1() and r2() are random numbers distributed between [0, 1], and c1 and c2 are acceleration factors.

[0037] In one possible implementation, the inertia weight is given by the formula:

[0038] Calculated,

[0039] Among them, w is the inertia weight, w max is the maximum inertia weight, w min is the minimum inertia weight, g n is the number of iterations, G n is the maximum number of iterations.

[0040] In one possible implementation, the corresponding relationship includes selecting a configuration parameter corresponding to the position of the particle from the second number of configuration parameters according to a difference between the position of the particle and a second number of configuration parameters, wherein the second number of configuration parameters are determined within a parameter range of the configuration parameters according to a preset step size.

[0041] In one possible implementation manner, updating the configuration parameters of the base station based on the optimal position of each particle includes:

[0042] Obtaining optimal configuration parameters according to the optimal position mean values ​​of the plurality of particles and the corresponding relationship;

[0043] The configuration parameters of the base station are set to the optimal configuration parameters.

[0044] In a second aspect, an embodiment of the present invention provides a parameter updating system, the system comprising:

[0045] An acquisition module, used to acquire configuration parameters of a base station, a particle group, and a corresponding relationship, wherein the particle group includes a plurality of particles, and the corresponding relationship includes a corresponding relationship between the configuration parameters of the base station and the positions of the particles;

[0046] A position updating module, used for initializing the position of each particle in the particle swarm based on the configuration parameters of the base station, and iteratively updating the position of each particle in the particle swarm to obtain an iteratively updated particle position;

[0047] An extreme position obtaining module, used for obtaining the extreme position of each particle based on the iteratively updated particle position;

[0048] A replacement module, used to obtain a forgetting factor, and based on the forgetting factor and the extreme position of each particle, obtain an optimal position, and use the optimal position to replace the extreme position of the particle;

[0049] A parameter updating module is used to update the configuration parameters of the base station based on the corresponding relationship and the optimal position of each particle.

[0050] In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor:

[0051] The memory is used to store computer programs;

[0052] The processor is used to execute the computer program stored in the memory so that the electronic device executes the method as described in the first aspect.

[0053] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, comprising a program or instructions. When the program or instructions are run on a computer, the method described in the first aspect is executed.

[0054] Compared with the prior art, this technical solution has at least the following beneficial effects:

[0055] The parameter updating method, system and electronic device disclosed in the embodiments of the present invention strengthen the weight influence of current data and reduce the influence of historical data through the forgetting factor to calculate the optimal position of the particle, and use the optimal position to replace the extreme position of the particle, which is beneficial to enhance the system's ability to respond quickly to changes in the current environment and user model, accelerate the convergence speed and optimization accuracy of the system algorithm, and solve the parameter configuration problems existing in the base station in various scenarios, and improve the service quality of the base station.

Brief Description of the Drawings

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 is a method schematic diagram of a parameter updating method provided by Embodiment 1 of the present invention;

[0058] Figure 2 is a flow chart of the steps of the parameter updating method provided in Embodiment 1 of the present invention;

[0059] Figure 3 It is a module diagram of the parameter updating system provided by Embodiment 2 of the present invention.

[0060] Reference numerals:

[0061] 10-acquisition module; 20-position update module; 30-extreme position acquisition module; 40-replacement module; 50-parameter update module. [Specific implementation method]

[0062] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0063] It should be clear that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] The existing NR to LTE handover success rate optimization methods mainly include the following methods:

[0065] Solution 1: By adjusting the azimuth and downtilt angles of the 5G NR and LTE networks and related coverage parameter configurations (such as antenna feed adjustment), the weak field areas of co-coverage can be eliminated or reduced, and the timeliness of mobility interaction can be enhanced to improve the quality of the wireless channel and increase the success rate of NR to LTE switching.

[0066] The disadvantage of Solution 1 is that antenna adjustment has great limitations. In areas with pure weak coverage, antenna adjustment cannot completely solve the problem of network coverage. Instead, due to the limitation of cell coverage, other areas with weak coverage are added. Secondly, antenna adjustment is labor-intensive and requires on-site testing and adjustment by optimization engineers, which takes up a lot of resources and is inefficient, making it unsuitable for large-scale implementation in the entire network. Then, relevant coverage parameters need to be jointly modified with the help of empirical values, and the network wireless environment is affected by factors such as weather, user behavior, and equipment, and has a large time-varying property. The parameters set based on empirical values ​​do not take into account the impact of the wireless environment in the current period compared to historical periods, and lack the ability to respond to changes in the wireless environment.

[0067] Solution 2: By optimizing the interoperability parameters of different systems, mainly involving the B2 threshold and the 4G to 5G redirection threshold, adjusting the switching related parameters between 5G and 4G cells, effectively ensuring the continuity of network coverage and improving the success rate of NR to LTE switching. Among them, the B2 threshold includes B2 threshold 1 and B2 threshold 2, that is, when the level value of the main service 5G cell is lower than threshold 1 and the level value of the 4G neighboring cell of the different system is higher than threshold 2, NR to LTE switching is performed; 4G to 5G redirection threshold, that is, when the 5G cell level value is higher than this threshold, 4G redirection to 5G is performed.

[0068] The disadvantage of solution 2 is that, taking B2 threshold 1 as an example, if it is set too large, 5G users will switch to LTE network too early, affecting the user's high-speed experience of 5G data services; if it is set too small, the late switching from NR to LTE will lead to decreased data service perception, switching failure, disconnection and other problems. In addition, once the parameters are set, they cannot be automatically adjusted according to the real-time changes of the network wireless environment and user model; the settings of various parameters can only be tried and modified based on experience values, and the joint optimal setting value of each parameter cannot be determined; in the face of the trial modification and effect evaluation of various parameters, it is necessary to conduct continuous experiments on a certain number of cell sets and evaluate the effect over a certain amount of time, and the entire parameter test process has a long cycle and low efficiency. In addition, the network wireless environment has a large time-varying nature. The current optimal parameter setting ignores the problem that the closer the system's historical switching state and the wireless environment are to the current time, the greater the impact. Because the historical switching state of the system is not considered or only the "historical data" and "current data" are given the same influence weight, the system also lacks the ability to quickly perform automatic optimization and adjustment when facing complex wireless environments and real-time changes in user models.

[0069] To this end, the present application provides a parameter updating method, system and electronic device, which uses a forgetting factor to strengthen the weight influence of current data and reduce the influence of historical data to calculate the optimal position of the particle, and use the optimal position to replace the extreme position of the particle, which is beneficial to enhance the system's ability to respond quickly to changes in the current environment and user model, accelerate the convergence speed and optimization accuracy of the system algorithm, and solve the parameter configuration problems of base stations (such as cells) in various scenarios, and improve the service quality of base stations.

[0070] Example 1

[0071] Embodiment 1 of the present invention proposes a parameter updating method, such as Figure 1 As shown, the method may include:

[0072] S101. Acquire configuration parameters of a base station, a particle swarm, and a corresponding relationship, wherein the particle swarm includes a plurality of particles, and the corresponding relationship includes a corresponding relationship between the configuration parameters of the base station and the positions of the particles.

[0073] For example, this embodiment uses a particle swarm algorithm to track the optimal settings of the configuration parameters of the base station (such as the interoperability parameters between the 5G cell and its 4G neighbors). The optimal settings of the configuration parameters can improve the service quality of the base station (such as the NR to LTE switching success rate and / or the LTE to NR redirection success rate).

[0074] In step S101, the size of the particle swarm is M (e.g., the number of particles in the particle swarm is M), the position of the particles in the particle swarm is X, and the speed is V, then:

[0075]

[0076]

[0077] Among them, the position of the i-th particle is X i =(X i1 ,…,X id ,…,X iD ) T , speed is V i =(V i1 ,…,V id ,…,V iD ) T , d=1,2,…,D, D is the dimension of the target search space, that is, the number of interaction parameters that need to be determined, i=1,2,…,M, M is the size of the particle swarm.

[0078] Preferably, the number of configuration parameters of the base station is 3 (D=3), including a first parameter Y1, a second parameter Y2 and a third parameter Y3, wherein:

[0079] The first parameter Y1 may include: an RSRP absolute threshold 1 determined based on the covered NR to EUTRAN B2 event serving cell, with a parameter range of [-156, -31] and a step size of 1;

[0080] The second parameter Y2 may include: an RSRP absolute threshold for a covered NR to EUTRAN B1 event neighbor cell decision or an RSRP absolute threshold 2 for a B2 event neighbor cell decision, the parameter range is [-140, -43], and the step length is 1;

[0081] The third parameter Y3 may include: the RSRP threshold from EUTRAN to NR based on coverage redirection to NR, the parameter range is [-140, -43], and the step size is 1.

[0082] In one possible implementation, the correspondence between the configuration parameters of the base station and the particle position may include selecting the configuration parameters corresponding to the particle position from the second number of configuration parameters based on the difference between the particle position and the second number of configuration parameters, wherein the second number of configuration parameters are determined within the parameter range of the configuration parameters according to a preset step size.

[0083] For example, the position of the 5th particle is X5 = (-110.824, -85.431, -87.651) T , the position of the first spatial dimension of the particle is -110.824, corresponding to the RSRP absolute threshold 1 (first parameter Y1) based on the coverage NR to EUTRAN B2 event serving cell decision. Since the threshold parameter range is [-156, -31], the step size is 1. According to the minimum value of the difference between the particle position and the configuration parameter, the RSRP absolute threshold 1 (first parameter Y1) based on the coverage NR to EUTRAN B2 event serving cell decision is set to -111. The position of the second spatial dimension of the particle is -85.431, corresponding to the RSRP absolute threshold based on coverage from NR to EUTRANB1 event neighboring area or the RSRP absolute threshold 2 (second parameter Y2) of B2 event neighboring area. Since the threshold parameter range is [-140, -43], the step size is 1. According to the minimum value of the difference between the particle position and the configuration parameter, the RSRP absolute threshold based on coverage from NR to EUTRAN B1 event neighboring area or the RSRP absolute threshold 2 (second parameter Y2) of B2 event neighboring area is set to -85. The position of the third spatial dimension of the particle is -87.651, corresponding to the RSRP threshold (third parameter Y3) from EUTRAN to NR based on coverage redirection to NR. Since the threshold parameter range is [-140, -43], the step size is 1. According to the minimum value of the difference between the particle position and the configuration parameter, the RSRP threshold (third parameter Y3) from EUTRAN to NR based on coverage redirection to NR is set to -88.

[0084] S102: Initialize the position of each particle in the particle swarm based on the configuration parameters of the base station, and iteratively update the position of each particle in the particle swarm to obtain an iteratively updated particle position.

[0085] In this embodiment, the position of each particle in the initialized particle swarm is used to initialize various configuration parameters of the base station.

[0086] In one possible implementation, in step S102, initializing the position of each particle in the particle group may include:

[0087] S201. Based on configuration parameters of the plurality of base stations, obtain a proportion of the same configuration parameters in all the configuration parameters;

[0088] S202, selecting a first number of configuration parameters in descending order according to the proportion of the same configuration parameters;

[0089] S203: determining a second number of configuration parameters within the parameter range of the configuration parameters according to a preset step size, and obtaining a third number of configuration parameters by selecting the second number of configuration parameters;

[0090] S204: configure the first number of configuration parameters and the third number of configuration parameters as the position of each particle in the particle swarm, the number of particles in the particle swarm being equal to the sum of the first number and the third number.

[0091] The particle swarm size can be set according to actual needs. For example, the particle swarm size is 100, such as M = 100. The first number N1 particle position selection weight is W1, the third number N2 particle position selection weight is W2, M = N1 + N2, N1 = W1 * M rounded up, N2 = W2 * M rounded down, and W1 + W2 = 1.

[0092] For example, D=2 (such as the first parameter Y1 and the second parameter Y2), M=100, N1=10, and N2=90. The proportion of the number of cells in the whole network based on the RSRP absolute threshold 1 (first parameter Y1) determined by the covered NR to EUTRAN B2 event serving cell in the whole network under statistical scenarios (such as indoors, subways, offices, etc.) is selected in descending order of proportion. If the top 10 RSRP absolute thresholds 1 (first parameter Y1) determined by the covered NR to EUTRAN B2 event serving cell are: -110, -112, -113, -116, -118, -120, -105, -107, -108, -100, then the particle initialization positions in the first spatial dimension of 10 particles in the particle swarm are -110, -112, -113, -116, -118, -120, -105, -107, -108, -100, respectively. The particle initialization positions in the first spatial dimension of the other 90 particles can be selected from the first parameter Y1 of the second quantity (such as randomly selected by the system, etc.). The first parameter Y1 of the second quantity is selected in sequence within the parameter range [-156, -31] of the first parameter Y1 according to the step size 1.

[0093] Correspondingly, the proportion of the number of cells of the RSRP absolute threshold based on the coverage of NR to EUTRAN B1 event neighbor area decision or the RSRP absolute threshold 2 (second parameter Y2) of the B2 event neighbor area decision of multiple base stations in the whole network in the statistical scenario is selected in descending order of proportion. If the top 10 RSRP absolute thresholds based on the coverage of NR to EUTRAN B1 event neighbor area decision or the RSRP absolute threshold 2 (second parameter Y2) of the B2 event neighbor area decision are: -85, -86, -89, -90, -72, -75, -78, -80, -81, -100, then the particle initialization positions in the second spatial dimension of 10 particles in the particle swarm are -85, -86, -89, -90, -72, -75, -78, -80, -81, and -100 respectively. The particle initialization positions in the second spatial dimension of the other 90 particles can be selected from the second parameter Y2 of the second quantity (such as randomly selected by the system, etc.). The second parameter Y2 of the second quantity is selected in sequence within the parameter range [-140, -43] of the second parameter Y2 according to the step size 1.

[0094] In one possible implementation, Figure 2 As shown, in step S102, iteratively updating the position of each particle in the particle group to obtain an iteratively updated particle position may include:

[0095] S301. After each iterative update, obtain a fitness value of the particle based on the current position of the particle, where the fitness value of the particle is used to represent the service quality of the base station;

[0096] S302, based on the fitness value of the particle, determining whether a particle swarm initialization condition is met;

[0097] S303, if the particle swarm initialization condition is met, initializing the position of each particle in the particle swarm;

[0098] S304: If the particle swarm initialization condition is not met, the next iterative update is performed.

[0099] In this embodiment, after the configuration parameters of the base station are set accordingly according to the current position of the particle, the service quality of the base station within a period of time is comprehensively evaluated, and the fitness value of the particle is calculated using the fitness function.

[0100] In one possible implementation, step S301 may include:

[0101] S401, obtaining target configuration parameters based on the corresponding relationship and the current position of the particle;

[0102] S402, setting the configuration parameters of the base station to the target configuration parameters, and obtaining the service quality of the base station within a preset time period;

[0103] S403: Based on the service quality, obtain the fitness value of the particle.

[0104] For example, the current position of the 5th particle is X5 = (-110.824, -85.431, -87.651) T According to the corresponding relationship, the target configuration parameters may include: RSRP absolute threshold 1 (first parameter Y1) based on coverage NR to EUTRAN B2 event serving cell decision, RSRP absolute threshold 2 (second parameter Y2) based on coverage NR to EUTRAN B1 event neighboring cell decision, and RSRP threshold (third parameter Y3) from EUTRAN to NR based on coverage redirection to NR, which are set to -111, -85, and -88, respectively, that is, Y = (-111, -85, -88). After the configuration parameters of the base station are set to the target configuration parameters, the overall performance of the cell (such as the service quality of the base station) within a period of time is comprehensively evaluated, such as obtaining the network switching success rate (such as NR to LTE switching success rate) and the network redirection success rate (such as LTE to NR redirection success rate) within a preset time period.

[0105] In one possible implementation, the quality of service includes a network switching success rate and a network redirection success rate, and the fitness value is given by the formula:

[0106] Calculated;

[0107] Among them, J(Y) is the fitness value, Q1 and Q2 are set values, and Z1 is the network switching success rate, Z2 is the network redirection success rate, w1 is found in the preset first relationship table according to the network switching success rate, and w2 is found in the preset second relationship table according to the network redirection success rate.

[0108] Optionally, Q j The weighted influencing factors are set according to the impact of the j-th cell performance (service quality) on the overall network and user service experience, as well as the need for the implementation of various special tasks.

[0109] That is to say, in order to ensure the service perception of users at the 4 / 5G switching boundary, a balance is sought between the NR to LTE switching success rate Z1 and the LTE to NR redirection success rate Z2 indicators as the standard for evaluating the service quality of base stations. For example, the cost function is used to comprehensively evaluate the cell performance (base station service quality) in multiple dimensions to provide a guarantee for accurate output.

[0110] Taking into account the correlation between the changes in various configuration parameter indicators of the cell and the user service perception in the cell, a hierarchical weight factor is specially set for each cell performance (service quality) indicator to be evaluated. For example, the weight factor w1 corresponds to the NR to LTE handover success rate Z1, and the weight factor w2 corresponds to the LTE to NR redirection success rate Z2. Taking the NR to LTE handover success rate Z1 as an example, the preset first relationship table is as follows:

[0111]

[0112]

[0113] For example, if the statistics show that the NR to LTE handover success rate in a cell is 93% and the LTE to NR redirection success rate is 87%, then w1 = 0.05. If the LTE to NR redirection success rate setting hierarchical weight factor w2 is the same as the NR to LTE handover success rate setting hierarchical weight factor w1, then w2 = 0.13. If Q1 = 0.6 and Q2 = 0.4, then the fitness value of the particle is Therefore, the smaller the fitness value J(Y) of the particle is, the better the overall performance of the cell is and the higher the service quality of the base station is.

[0114] Considering that the particle swarm algorithm in the prior art cannot adapt to the changes and continue to maintain the local optimal value when factors such as the wireless environment, user model and wireless device change suddenly, the particle swarm algorithm provided in this embodiment determines whether the current particle fitness value meets the particle swarm initialization condition after each iterative update. If so, the position of each particle is reinitialized to make it converge to a new optimal position value, so as to quickly adapt to the change and jump out of the local optimal value. If not, the next iterative update is performed.

[0115] In one possible implementation, the particle swarm initialization condition may include:

[0116] |E(g n -1)-E(g n -2)|≤R1 and |E(g n )-E(g n -1)|≥R2;

[0117] Among them, E() is the mean square error of the fitness value of the particle, g n is the number of iterations, R1 and R2 are set values.

[0118] That is to say, the difference between the mean square error of the fitness values ​​of the particles after two iterations is used as the trigger condition for reinitializing the particle swarm, where R1 and R2 are two sets of differences determined by repeated experiments (such as |E(g n -1)-E(g n -2)| and |E(g n )-E(g n -1)|). The principle for selecting R1 and R2 is to record the difference between the mean square errors of the two fitness values ​​before and after the wireless situation changes for many times. R1 needs to ensure that the difference between the mean square errors of the two fitness values ​​before the mutation is within the interval (0, R1), and R2 needs to ensure that the difference between the mean square errors of the two fitness values ​​after the mutation is within the interval (R2, +∞).

[0119] S103. Based on the iteratively updated particle positions, obtain the extreme value position of each particle.

[0120] In this embodiment, the local optimal individual extreme position of each particle and the global optimal group extreme position of the particle swarm are obtained according to the fitness value of each particle. Specifically, the position corresponding to the minimum fitness value of particle i is searched as the extreme position, that is, the extreme position of particle i is P i =(P i1 ,P i2 ,…P iD ) T , and at this time, the extreme value position searched by all particles in the entire particle swarm is the group extreme value, that is, the group extreme value is P g=(P g1 ,P g2 ,…P gD ) T .

[0121] S104, obtaining a forgetting factor, and based on the forgetting factor and the extreme position of each particle, obtaining an optimal position, and using the optimal position to replace the extreme position of the particle.

[0122] Preferably, the forgetting factor is used to determine the importance of current data and historical data. For example, by assigning different weights to current data and historical data, respectively, the forgetting factor can be determined based on the weight ratio of current data to historical data. For example, in order to strengthen the influence of current data and reduce the influence of historical data, the weight ratio of current data to historical data can be appropriately reduced (such as reducing the value of the forgetting factor).

[0123] Considering that the particle swarm algorithm in the prior art only uses the individual extreme value position and the group extreme value position of the particle when iterating and updating the particle, and does not make full use of other information except these two extreme value positions, resulting in a slow global convergence speed and low optimization accuracy, in view of the above shortcomings, in this embodiment, the individual extreme value position P of all particles is i The forgetting factor is used to calculate the optimal position of the individual P(g n ), to replace the individual extreme value position of a particle, so as to make full use of the extreme value information of the entire particle group, strengthen the influence of current data, reduce the influence of historical data, strengthen the ability to respond quickly to the current environment and user model, accelerate the global convergence speed and optimization accuracy, and enable the system to quickly achieve the expected goals.

[0124] In one possible implementation, the optimal position is given by the formula:

[0125] Calculated;

[0126] Among them, P() is the optimal position of the particle, g n is the number of iterations n, M is the number of particles in the particle swarm, e is a constant, β is the forgetting factor, P i is the extreme position of particle i.

[0127] In this embodiment, the maximum number of iterations is G n , the current number of iterations is g n , after each iterative update, the optimal position of the particle after the current iterative update can be obtained.

[0128] In the iterative update process, all particles continuously approach the optimal position of the current particle swarm, and the particle position is iteratively updated according to the particle swarm algorithm. The particle position after iterative update is given by the formula:

[0129] X i,d (g n +1) = X i,d (g n )+V i,d (g n +1),

[0130] V i,d (g n +1)=w*V i,d (g n )+c1*r1(g n )(P d (g n )-X i,d (g n ))+c2*r2(g n )(P g,d (g n )-X i,d (g n ))Calculated,

[0131] Among them, X i,d () is the position of the ith particle in the dth dimension, V i,d () is the update speed of the ith particle in the dth dimension, g n is the number of iterations, P d () is the optimal position of the particle in the dth dimension, P g,d () is the group extreme value of the particle swarm in the dth dimension, w is the inertia weight, r1() and r2() are random numbers distributed between [0, 1], and c1 and c2 are acceleration factors.

[0132] In one possible implementation, the inertia weight is given by the formula:

[0133] Calculated,

[0134] Among them, w is the inertia weight, w max is the maximum inertia weight, w min is the minimum inertia weight, g n is the number of iterations, G n is the maximum number of iterations.

[0135] Since the inertia weight of the particle swarm algorithm in the prior art is a fixed value, it is easy to fall into the local minimum solution in the early stage of optimization, and it is easy to continuously fly over the global optimal solution and produce oscillation in the later stage of optimization. In view of the shortcomings of the prior art, the particle swarm algorithm in this embodiment adopts a dynamically changing inertia weight, so that the inertia weight w increases from the maximum value w to the maximum value w as the number of iterations increases. max Reduce to the minimum value w min, in order to jump out of the local optimum and avoid oscillation in the global optimum.

[0136] Furthermore, the method may further include: after each iteration update, determining the current iteration number g n Whether the maximum number of iterations G has been reached n , if the current iteration number g n Reach the maximum number of iterations G n , the iterative update is terminated, and the optimal position of each particle after each iterative update is output. If the current number of iterations g n The maximum number of iterations G has not been reached n , then execute the next iterative update.

[0137] S105: Based on the corresponding relationship and the optimal position of each particle, update the configuration parameters of the base station.

[0138] That is to say, after the iterative update is completed, the optimal settings of the base station configuration parameters are tracked according to the optimal position of each particle and the correspondence between the particle position and the configuration parameters of the base station, which effectively solves the parameter configuration problems of the base station, improves the service quality of the base station, and enhances 5G user perception.

[0139] In one possible implementation, step S105 may include:

[0140] S501, obtaining optimal configuration parameters according to the optimal position mean values ​​of the plurality of particles and the corresponding relationship;

[0141] S502: Set the configuration parameters of the base station to the optimal configuration parameters.

[0142] Specifically, the optimal position mean can be expressed as:

[0143] Calculated,

[0144] in, is the optimal position mean, P i is the optimal position of the ith particle, and M is the number of particles.

[0145] Therefore, according to the correspondence between the particle position and the configuration parameters of the base station, the optimal position mean is obtained. The corresponding optimal configuration parameters are set, and the configuration parameters of the base station are set to the optimal configuration parameters, that is, the optimal setting of the cell interoperability parameters is met, which effectively improves the overall performance of the cell.

[0146] It is worth mentioning that according to the above parameter update method provided in this embodiment, by traversing all cells (base stations) in the entire network, the optimal settings of the interoperability parameters between 4 / 5G cells can be tracked, the parameter configuration problems between cells can be effectively solved, the success rate of NR to LTE switching can be optimized, the overall performance of each cell can be improved, and the 5G user perception can be enhanced.

[0147] For example, there are multiple cells in the whole network, such as the first cell, the second cell, the third cell, etc. In this embodiment, the above parameter updating method can be used to update the parameters of each cell respectively, so that each cell reaches the optimal configuration parameter setting. For example, when updating the parameters of the first cell, according to the above parameter updating method, all particle positions in the first particle group are initialized according to the configuration parameters of the first cell, and after multiple iterations of updating the first particle group, the optimal configuration parameters of the first cell are output, and the configuration parameters of the first cell are set to the optimal configuration parameters. Correspondingly, when updating the parameters of the second cell, according to the above parameter updating method, all particle positions in the second particle group are initialized according to the configuration parameters of the second cell, and after multiple iterations of updating the second particle group, the optimal configuration parameters of the second cell are output, and the configuration parameters of the second cell are set to the optimal configuration parameters. By analogy, all cells in the whole network are traversed to meet the optimal configuration parameter settings of each cell and improve the overall performance of each cell.

[0148] In other possible embodiments, the above parameter updating method can be used to update parameters of multiple cells in the entire network so that multiple cells in the entire network reach the global optimal configuration parameter setting. For example, multiple cells in the entire network correspond to multiple particles in a particle swarm, such as the configuration parameters of the first cell correspond to the first particle position in the particle swarm, the configuration parameters of the second cell correspond to the second particle position in the particle swarm, ..., according to the above parameter updating method, all particle positions in the particle swarm are initialized according to the configuration parameters of each cell, after multiple iterations of updating the particle swarm, the optimal configuration parameters of each cell are output, and the configuration parameters of each cell in the entire network are respectively set to the optimal configuration parameters, so that each cell in the entire network reaches the global optimal configuration parameter setting, so as to improve the overall performance of the entire network.

[0149] It is to be understood that some or all of the steps or operations in the above embodiments are merely examples, and the present application embodiments may also perform other operations or variations of various operations. In addition, the various steps may be performed in different orders presented in the above embodiments, and it is possible that not all of the operations in the above embodiments need to be performed.

[0150] Example 2

[0151] like Figure 3 As shown, in Embodiment 2 of the present invention, a parameter updating system 100 is disclosed. The system 100 may include

[0152] An acquisition module 10 is used to acquire configuration parameters of a base station, a particle swarm, and a corresponding relationship, wherein the particle swarm includes a plurality of particles, and the corresponding relationship includes a corresponding relationship between the configuration parameters of the base station and the positions of the particles;

[0153] A position updating module 20, configured to initialize the position of each particle in the particle swarm based on the configuration parameters of the base station, and iteratively update the position of each particle in the particle swarm to obtain an iteratively updated particle position;

[0154] An extreme position obtaining module 30, used for obtaining the extreme position of each particle based on the iteratively updated particle position;

[0155] A replacement module 40 is used to obtain a forgetting factor, and based on the forgetting factor and the extreme position of each particle, obtain an optimal position, and use the optimal position to replace the extreme position of the particle;

[0156] The parameter updating module 50 is used to update the configuration parameters of the base station based on the corresponding relationship and the optimal position of each particle.

[0157] In one possible implementation, the optimal position is given by the formula:

[0158] Calculated;

[0159] Among them, P() is the optimal position of the particle, g n is the number of iterations n, M is the number of particles in the particle swarm, e is a constant, β is the forgetting factor, P i is the extreme position of the particle.

[0160] In one possible implementation, the location updating module 20 is further configured to:

[0161] Based on the configuration parameters of the multiple base stations, obtaining the proportion of the same configuration parameters in all the configuration parameters;

[0162] According to the proportion of the same configuration parameters, a first number of configuration parameters are selected from large to small;

[0163] According to a preset step size, within the parameter range of the configuration parameters, determine a second number of configuration parameters, and select a third number of configuration parameters from the second number of configuration parameters;

[0164] The first number of configuration parameters and the third number of configuration parameters are configured as the position of each particle in the particle group, and the number of particles in the particle group is equal to the sum of the first number and the third number.

[0165] In one possible implementation, the location updating module 20 is further configured to:

[0166] After each iterative update, a fitness value of the particle is obtained based on the current position of the particle, where the fitness value of the particle is used to represent the service quality of the base station;

[0167] Based on the fitness value of the particle, determining whether a particle swarm initialization condition is met;

[0168] If the particle swarm initialization condition is met, the position of each particle in the particle swarm is initialized;

[0169] If the particle swarm initialization condition is not met, the next iterative update is performed.

[0170] In one possible implementation, the particle swarm initialization condition includes:

[0171] |E(g n -1)-E(g n -2)|≤R1 and |E(g n )-E(g n -1)|≥R2;

[0172] Among them, E() is the mean square error of the fitness value of the particle, g n is the number of iterations, R1 and R2 are set values.

[0173] In one possible implementation, the location updating module 20 is further configured to:

[0174] Based on the corresponding relationship and the current position of the particle, obtaining target configuration parameters;

[0175] Setting the configuration parameters of the base station as the target configuration parameters, and obtaining a network switching success rate and a network redirection success rate of the base station within a preset time period;

[0176] Based on the network switching success rate and the network redirection success rate, the fitness value of the particle is obtained.

[0177] In one possible implementation, the fitness value is given by the formula:

[0178] Calculated;

[0179] Among them, J(Y) is the fitness value, Q1 and Q2 are set values, and Z1 is the network switching success rate, Z2 is the network redirection success rate, w1 is found in the preset first relationship table according to the network switching success rate, and w2 is found in the preset second relationship table according to the network redirection success rate.

[0180] In one possible implementation, the particle position after iterative update is given by the formula:

[0181] X i,d (g n +1) = X i,d (g n )+V i,d (g n +1),

[0182] V i,d (g n +1)=w*V i,d (g n )+c1*r1(g n )(P d (g n )-X i,d (g n ))+c2*r2(g n )(P g,d (g n )-X i,d (g n ))Calculated,

[0183] Among them, X i,d () is the position of the ith particle in the dth dimension, V i,d () is the update speed of the ith particle in the dth dimension, g n is the number of iterations, P d () is the optimal position of the particle in the dth dimension, P g,d () is the group extreme value of the particle swarm in the dth dimension, w is the inertia weight, r1() and r2() are random numbers distributed between [0, 1], and c1 and c2 are acceleration factors.

[0184] In one possible implementation, the inertia weight is given by the formula:

[0185] Calculated,

[0186] Among them, w is the inertia weight, w max is the maximum inertia weight, w min is the minimum inertia weight, g n is the number of iterations, G n is the maximum number of iterations.

[0187] In one possible implementation, the corresponding relationship includes selecting a configuration parameter corresponding to the position of the particle from the second number of configuration parameters according to a difference between the position of the particle and a second number of configuration parameters, wherein the second number of configuration parameters are determined within a parameter range of the configuration parameters according to a preset step size.

[0188] In one possible implementation, the parameter updating module 50 includes:

[0189] Obtaining optimal configuration parameters according to the optimal position mean values ​​of the plurality of particles and the corresponding relationship;

[0190] The configuration parameters of the base station are set to the optimal configuration parameters.

[0191] Understandably, Figure 3 The parameter updating system provided in the embodiment shown can be used to implement the present application Figure 1 The technical solution of the method embodiment shown, its implementation principle and technical effects can be further referred to the relevant description in the method embodiment.

[0192] It should be understood that the above Figure 3 The division of the various modules of the parameter update system shown is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the parameter update module can be a separately established processing element, or it can be integrated in a chip of an electronic device. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. In the implementation process, each step of the above method or each of the above modules can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0193] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital singnal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0194] Example 3

[0195] Embodiment 3 of the present invention provides an electronic device, including: a memory and a processor:

[0196] Memory for storing computer programs;

[0197] The processor is used to execute the computer program stored in the memory so that the electronic device executes the method of embodiment 1.

[0198] The processor and the memory can communicate with each other through an internal connection path to transmit control and / or data signals. The memory is used to store a computer program, and the processor is used to call and execute the computer program from the memory.

[0199] The above-mentioned memory can be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or it can be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or it can also be any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0200] Example 4

[0201] Embodiment 4 of the present invention provides a computer-readable storage medium, including a program or an instruction. When the program or the instruction runs on a computer, the method of embodiment 1 is executed.

[0202] The parameter updating method, system and electronic device disclosed in the embodiments of the present invention strengthen the weight influence of current data and reduce the influence of historical data through the forgetting factor to calculate the optimal position of the particle, and use the optimal position to replace the extreme position of the particle, which is beneficial to enhance the system's ability to respond quickly to changes in the current environment and user model, accelerate the convergence speed and optimization accuracy of the system algorithm, and solve the parameter configuration problems existing in the base station in various scenarios, and improve the service quality of the base station.

[0203] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, data center, etc. that contains one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0204] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A parameter updating method, characterized in that: The method comprises: Acquire configuration parameters of a base station, a particle group, and a corresponding relationship, wherein the particle group includes a plurality of particles, and the corresponding relationship includes a corresponding relationship between the configuration parameters of the base station and the positions of the particles; Initializing the position of each particle in the particle swarm based on the configuration parameters of the base station, and iteratively updating the position of each particle in the particle swarm to obtain an iteratively updated particle position; Based on the iteratively updated particle positions, obtaining the extreme position of each particle; Obtaining a forgetting factor, and obtaining an optimal position based on the forgetting factor and the extreme position of each particle, and replacing the extreme position of the particle with the optimal position; Based on the corresponding relationship and the optimal position of each particle, updating the configuration parameters of the base station; The iterative updating of the position of each particle in the particle group to obtain an iteratively updated particle position includes: After each iterative update, a fitness value of the particle is obtained based on the current position of the particle, where the fitness value of the particle is used to represent the service quality of the base station; Based on the fitness value of the particle, determining whether a particle swarm initialization condition is met; If the particle swarm initialization condition is met, the position of each particle in the particle swarm is initialized; If the particle swarm initialization condition is not met, the next iterative update is performed; The optimal position is given by the formula: Calculated; Among them, P() is the optimal position of the particle, g n is the number of iterations n, M is the number of particles in the particle swarm, e is a constant, β is the forgetting factor, P i is the extreme position of the particle.

2. The parameter updating method according to claim 1, characterized in that: Initializing the position of each particle in the particle group includes: Based on the configuration parameters of the multiple base stations, obtaining the proportion of the same configuration parameters in all the configuration parameters; According to the proportion of the same configuration parameters, a first number of configuration parameters are selected from large to small; According to a preset step size, within the parameter range of the configuration parameters, determine a second number of configuration parameters, and select a third number of configuration parameters from the second number of configuration parameters; The first number of configuration parameters and the third number of configuration parameters are configured as the position of each particle in the particle group, and the number of particles in the particle group is equal to the sum of the first number and the third number.

3. The parameter updating method according to any one of claims 1 to 2, characterized in that: The obtaining the fitness value of the particle based on the current position of the particle comprises: Based on the corresponding relationship and the current position of the particle, obtaining target configuration parameters; Setting the configuration parameters of the base station as the target configuration parameters, and obtaining a network switching success rate and a network redirection success rate of the base station within a preset time period; Based on the network switching success rate and the network redirection success rate, a fitness value of the particle is obtained.

4. The parameter updating method according to claim 1, characterized in that: The particle position after iterative update is given by the formula: X i,d (g n +1)=X i,d (g n )+V i,d (g n +1), V i,d (g n +1)=w*V i,d (g n )+c1*r1(g n )(P d (g n )-X i,d (g n ))+c2*r2(g n )(P g,d (g n )-X i,d (g n )), Calculated, Among them, X i,d () is the position of the ith particle in the dth dimension, V i,d () is the update speed of the ith particle in the dth dimension, P d () is the optimal position of the particle in the dth dimension, P g,d () is the extreme value of the particle swarm in the dth dimension, r1() and r2() are random numbers distributed between [0,1], c1 and c2 are acceleration factors, w is the inertia weight, w max is the maximum inertia weight, w min is the minimum inertia weight, g n is the number of iterations, G n is the maximum number of iterations.

5. The parameter updating method according to claim 1, characterized in that: The corresponding relationship includes selecting configuration parameters corresponding to the position of the particle from the second number of configuration parameters according to the difference between the position of the particle and the second number of configuration parameters, wherein the second number of configuration parameters are determined within the parameter range of the configuration parameters according to a preset step size.

6. A parameter updating system, characterized in that: The system comprises: An acquisition module, used to acquire configuration parameters of a base station, a particle group, and a corresponding relationship, wherein the particle group includes a plurality of particles, and the corresponding relationship includes a corresponding relationship between the configuration parameters of the base station and the positions of the particles; A position updating module, configured to initialize the position of each particle in the particle swarm based on the configuration parameters of the base station, and iteratively update the position of each particle in the particle swarm to obtain an iteratively updated particle position; An extreme position obtaining module, used for obtaining the extreme position of each particle based on the iteratively updated particle position; A replacement module, used to obtain a forgetting factor, and based on the forgetting factor and the extreme position of each particle, obtain an optimal position, and use the optimal position to replace the extreme position of the particle; A parameter updating module, used for updating the configuration parameters of the base station based on the corresponding relationship and the optimal position of each particle; The iterative updating of the position of each particle in the particle group to obtain an iteratively updated particle position includes: After each iterative update, a fitness value of the particle is obtained based on the current position of the particle, where the fitness value of the particle is used to represent the service quality of the base station; Based on the fitness value of the particle, determining whether a particle swarm initialization condition is met; If the particle swarm initialization condition is met, the position of each particle in the particle swarm is initialized; If the particle swarm initialization condition is not met, the next iterative update is performed; The optimal position is given by the formula: Calculated; Among them, P() is the optimal position of the particle, g n is the number of iterations n, M is the number of particles in the particle swarm, e is a constant, β is the forgetting factor, P i is the extreme position of the particle.

7. An electronic device, characterized in that: include: Memory and processor: The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory so that the electronic device executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The method comprises a program or an instruction. When the program or the instruction is run on a computer, the method according to any one of claims 1 to 5 is executed.