A method, device, electronic device and medium for optimizing network parameters

Abstract

An embodiment of the present invention provides a network parameter optimization method, apparatus, electronic device and medium, which relates to the field of computer technology. The method includes: obtaining performance indicators in a mobile network, determining the fitness of the mobile network based on the performance indicators of the mobile network; in the case where the fitness of the mobile network is less than a preset threshold, performing a genetic operator operation on the parameter sets of each base station to obtain the next-generation parameter sets of each base station, updating the parameters of each base station based on the next-generation parameter sets of each base station, and after a preset time period, returning to the step of obtaining the performance indicators of the mobile network. It can realize a method of simplifying the adjustment of network parameters on the premise of comprehensively evaluating the mobile network.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method, device, electronic device, and medium for optimizing network parameters. Background Art

[0002] At present, the mobile network networking and wireless propagation environment are complex, and it is necessary to optimize the wireless network parameters targeted. Currently, if the wireless network parameters of base station A are modified, other network metrics of base station A will change accordingly, and the network metrics of other adjacent base stations, such as base station B, may also change. Then it is necessary to manually adjust the wireless network parameters related to other network metrics of base station A, and adjust the wireless network parameters related to the affected network metrics of other adjacent base stations. It can be seen that the optimization of network parameters requires overall consideration. Currently, the method of manually adjusting network parameters lacks a comprehensive evaluation of the mobile network and is relatively complex to implement. Summary of the Invention

[0003] The purpose of the embodiments of the present invention is to provide a method, device, electronic device, and medium for optimizing network parameters to simplify the method of adjusting network parameters on the premise of a comprehensive evaluation of the mobile network. The specific technical solutions are as follows:

[0004] In a first aspect, an embodiment of the present application provides a method for optimizing network parameters, including:

[0005] Obtain the performance metrics of the mobile network;

[0006] Determine the fitness of the mobile network based on the performance metrics of the mobile network;

[0007] When the fitness of the mobile network is less than a preset threshold, perform genetic operator operations on the parameter sets of each base station to obtain the next-generation parameter sets of each base station, where the parameter set of a base station includes the parameter values that affect each performance metric of the base station;

[0008] Update the parameters of each base station based on the next-generation parameter sets of each base station. After a preset time period, return to the step of obtaining the performance metrics of the mobile network until the fitness of the mobile network is greater than or equal to the preset threshold.

[0009] In a possible implementation, the step of performing genetic operator operations on the parameter sets of each base station to obtain the next-generation parameter sets of each base station when the fitness of the mobile network is less than the preset threshold includes:

[0010] When the fitness of the mobile network is less than the preset threshold, determine the fitness of each base station;

[0011] Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and use the remaining base stations as the second type of base stations;

[0012] Use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations;

[0013] For each performance metric included in the second type of base stations, if the performance metric is less than the performance metric threshold corresponding to the performance metric, then use the performance metric as a low-performance metric;

[0014] Perform a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter set of each second type of base station.

[0015] In a possible implementation, the performing a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter set of each second type of base station includes:

[0016] For each second type of base station, perform the following operations on each parameter value corresponding to the low-performance metric of the second type of base station:

[0017] Encode the parameter value through a preset encoding method to obtain the gene value of the parameter value;

[0018] Perform a mutation operation on the gene value to obtain the gene mutation value corresponding to the gene value;

[0019] If the gene mutation value is within the gene range corresponding to the parameter value, update the parameter value to the parameter value obtained by decoding the gene mutation value, where the gene range is the range of gene values obtained by encoding the value range of the parameter value using the preset encoding method;

[0020] If the gene mutation value is not within the gene range corresponding to the parameter value, then search for the optimal performance metric of the same type of performance metric as the low-performance metric corresponding to the parameter value from the performance metrics corresponding to the historical generations of parameter sets;

[0021] Update the parameter value to the parameter value corresponding to the found optimal performance metric.

[0022] In a possible implementation, the determining the fitness of the mobile network based on the performance metrics of the mobile network includes:

[0023] Perform a weighted sum of the performance metrics of the mobile network to obtain the fitness of the mobile network.

[0024] In a possible implementation, the determining the fitness of each base station includes:

[0025] For each base station, perform a weighted sum of the performance indicators of the base station to obtain the fitness of the base station.

[0026] In a second aspect, an embodiment of the present application provides an electronic device, including a memory, a transceiver, and a processor:

[0027] The memory is used to store a computer program; the transceiver is used to transmit and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations:

[0028] Obtain the performance indicators of the mobile network;

[0029] Determine the fitness of the mobile network based on the performance indicators of the mobile network;

[0030] In the case where the fitness of the mobile network is less than a preset threshold, perform a genetic operator operation on the parameter sets of each base station to obtain the next-generation parameter sets of each base station, where the parameter set of a base station includes the parameter values that affect the performance indicators of the base station;

[0031] Update the parameters of each base station based on the next-generation parameter sets of each base station. After a preset time period, return to the step of obtaining the performance indicators of the mobile network until the fitness of the mobile network is greater than or equal to the preset threshold.

[0032] In a possible implementation manner, the processor is specifically used to read the computer program in the memory and perform the following operations:

[0033] In the case where the fitness of the mobile network is less than the preset threshold, determine the fitness of each base station;

[0034] Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and use the remaining base stations as the second type of base stations;

[0035] Use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations;

[0036] For each performance indicator included in the second type of base stations, if the performance indicator is less than the performance indicator threshold corresponding to the performance indicator, then regard the performance indicator as a low-performance indicator;

[0037] Perform a mutation operation on the parameter values corresponding to the low-performance indicators included in each second type of base station to obtain the next-generation parameter sets of each second type of base station.

[0038] In a possible implementation manner, the processor is specifically used to read the computer program in the memory and perform the following operations:

[0039] For each second - type base station, perform the following operations on each parameter value corresponding to the low - performance index of the second - type base station:

[0040] Encode the parameter value through a preset encoding method to obtain the gene value of the parameter value;

[0041] Perform a mutation operation on the gene value to obtain the gene mutation value corresponding to the gene value;

[0042] If the gene mutation value is within the gene range corresponding to the parameter value, update the parameter value to the parameter value obtained by decoding the gene mutation value, where the gene range is the range of gene values obtained by encoding the value range of the parameter value using the preset encoding method;

[0043] If the gene mutation value is not within the gene range corresponding to the parameter value, search for the optimal performance index among the performance indexes corresponding to the parameter sets of each historical generation that belongs to the same type of performance index as the low - performance index corresponding to the parameter value;

[0044] Update the parameter value to the parameter value corresponding to the found optimal performance index.

[0045] In a possible implementation manner, the processor is specifically configured to read the computer program in the memory and perform the following operations:

[0046] Perform a weighted sum of each performance index of the mobile network to obtain the fitness of the mobile network.

[0047] In a possible implementation manner, the processor is specifically configured to read the computer program in the memory and perform the following operations:

[0048] For each base station, perform a weighted sum of each performance index of the base station to obtain the fitness of the base station.

[0049] In a third aspect, an embodiment of the present application provides a network parameter optimization device, including:

[0050] An acquisition unit, configured to acquire the performance indexes of the mobile network;

[0051] A determination unit, configured to determine the fitness of the mobile network based on the performance indexes of the mobile network;

[0052] A genetic unit, configured to perform a genetic operator operation on the parameter sets of each base station to obtain the next - generation parameter sets of each base station when the fitness of the mobile network is less than a preset threshold, where the parameter set of the base station includes parameter values affecting each performance index of the base station;

[0053] An update unit, configured to update the parameters of each base station based on the next-generation parameter sets of each base station, and trigger the acquisition unit to acquire the performance metrics of the mobile network after a preset duration.

[0054] In a possible implementation, the genetic unit is specifically configured to:

[0055] When the fitness of the mobile network is less than the preset threshold, determine the fitness of each base station;

[0056] Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and regard the remaining base stations as the second type of base stations;

[0057] Use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations;

[0058] For each performance metric included in the second type of base stations, if the performance metric is less than the performance metric threshold corresponding to the performance metric, then regard the performance metric as a low-performance metric;

[0059] Perform a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter sets of each second type of base station.

[0060] In a possible implementation, the genetic unit is specifically configured to:

[0061] For each second type of base station, perform the following operations on each parameter value corresponding to the low-performance metric of the second type of base station:

[0062] Encode the parameter value through a preset encoding method to obtain the gene value of the parameter value;

[0063] Perform a mutation operation on the gene value to obtain the gene mutation value corresponding to the gene value;

[0064] If the gene mutation value is within the gene range corresponding to the parameter value, update the parameter value to the parameter value obtained by decoding the gene mutation value, where the gene range is the range of gene values obtained by encoding the value range of the parameter value using the preset encoding method;

[0065] If the gene mutation value is not within the gene range corresponding to the parameter value, search for the optimal performance metric of the same type of performance metric as the low-performance metric corresponding to the parameter value from the performance metrics corresponding to the historical generations of parameter sets;

[0066] Update the parameter value to the parameter value corresponding to the found optimal performance metric.

[0067] In a possible implementation, the determination unit is specifically configured to perform weighted summation on each performance index of the mobile network to obtain the fitness of the mobile network.

[0068] In a possible implementation, the genetic unit is specifically configured to, for each base station, perform weighted summation on each performance index of the base station to obtain the fitness of the base station.

[0069] Fourthly, an embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0070] Fifthly, an embodiment of the present application further provides a computer program product containing instructions, which when running on a computer, causes the computer to execute the method described in the above first aspect.

[0071] By adopting the above technical solution, the fitness of the mobile network can be determined based on the performance indexes of the mobile network. When the fitness of the mobile network is less than a preset threshold, a genetic operator operation is performed on the parameter sets of each base station to obtain the next-generation parameter sets of each base station. After applying the next-generation parameter sets to each base station, the above process can be executed again after a preset time period until the fitness of the mobile network is greater than or equal to the preset threshold, then the optimization of the network parameters is completed. It can be seen that by applying the genetic operator in the network parameter optimization process, the present application embodiment can realize the automatic adjustment of the parameter sets of each base station, and the implementation is simple. And the condition for completing the network parameter optimization is that the fitness of the mobile network is greater than or equal to the preset threshold, and the fitness of the mobile network is determined by the performance indexes of each base station, which is equivalent to optimizing the parameter sets of each base station on the condition of the performance indexes of the entire mobile network, realizing the network parameter optimization on the premise of a comprehensive evaluation of the mobile network.

[0072] Of course, it is not necessary for any product or method implementing the present invention to achieve all the above advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other embodiments according to these drawings without creative efforts.

[0074] Figure 1 It is a flowchart of a network parameter optimization method provided by an embodiment of the present application;

[0075] Figure 2Flowchart of another network parameter optimization method provided by an embodiment of this application;

[0076] Figure 3 Schematic structural diagram of an electronic device provided by an embodiment of this application;

[0077] Figure 4 Schematic structural diagram of a network parameter optimization device provided by an embodiment of this application. Detailed implementation manners

[0078] In the embodiments of this application, the term "a plurality of" means two or more, and other quantifiers are similar thereto.

[0079] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0080] The network parameter optimization method provided by the embodiments of the present application is used to optimize the parameters of base stations included in a network. Among them, this technical solution can be applied to systems of multiple networks, especially 5G systems or 4G and 5G collaborative systems. For example, applicable systems can be Global System of Mobile Communication (GSM) systems, Code Division Multiple Access (CDMA) systems, Wideband Code Division Multiple Access (WCDMA) General Packet Radio Service (GPRS) systems, Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Long Term Evolution Advanced (LTE-A) systems, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) systems, 5G New Radio (NR) systems, etc. Terminal devices and network devices are included in all these multiple systems. The system may also include a core network part, such as an Evolved Packet System (EPS), 5G System (5GS), etc.

[0081] The base station involved in the embodiments of the present application may include multiple cells that provide services to terminals. Depending on specific application scenarios, the base station may also be referred to as an access point, or may be a device in the access network that communicates with wireless terminal devices through one or more sectors over the air interface, or have other names. The base station can be used to mutually replace the received air frames and Internet Protocol (IP) packets, and act as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The base station can also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present application may be a network device (Base Transceiver Station, BTS) in a Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA), or may be a network device (NodeB) in a Wide-band Code Division Multiple Access (WCDMA), or may also be an evolved network device (evolutional Node B, eNB or e-NodeB) in a Long Term Evolution (LTE) system, a 5G base station (gNB) in a 5G network architecture (next generation system), or may be a Home evolved Node B (HeNB), a relay node, a femto, a pico, etc. The embodiments of the present application do not limit this. In some network architectures, the network device may include a centralized unit (centralized unit, CU) node and a distributed unit (distributed unit, DU) node, and the centralized unit and the distributed unit may also be arranged separately geographically.

[0082] As Figure 1 shown, the embodiments of the present application provide a network parameter optimization method, which can be executed by a network management device. The method includes:

[0083] S101. Obtain the performance metrics of the mobile network.

[0084] Among them, the required performance metrics to be obtained can be determined according to the network parameter optimization requirements.

[0085] In one implementation, the performance metrics of the mobile network can be classified, the performance metrics of the mobile network are divided into multiple parent categories, and each parent category is divided into multiple subcategories.

[0086] Exemplarily, the performance metrics of a mobile network can be divided into 5 major categories, namely: access metrics, retention metrics, mobility metrics, integrity metrics, and capacity metrics.

[0087] Among them, the access metrics can include sub - metrics for representing access performance, such as the success rate of intra - frequency handover, the success rate of inter - frequency handover, etc.

[0088] The retention metrics can include sub - metrics for representing retention performance, such as the radio link drop rate, the ratio of radio resource control (RRC) connection re - establishment, etc.

[0089] The access metrics can also include sub - metrics for representing access performance, such as the success rate of RRC connection establishment, the radio access success rate, etc.

[0090] The integrity metrics can include sub - metrics for representing integrity performance, such as the coding ratio of downlink 256 - Quadrature Amplitude Modulation (QAM), the downlink bit error rate, etc.

[0091] The capacity metrics can include sub - metrics for representing capacity, such as the average utilization rate of downlink physical resource blocks (PRBs), the average number of users, etc.

[0092] In the embodiments of the present application, the performance metrics of the mobile network can be obtained periodically within a cycle. Taking the success rate of intra - frequency handover of the mobile network as an example, the network management device can obtain the total number of intra - frequency handovers that occur in the entire mobile network within a cycle, and the number of successful intra - frequency handovers within this cycle. Furthermore, the ratio of the number of successful intra - frequency handovers to the total number of intra - frequency handovers within this cycle can be used as the success rate of intra - frequency handover.

[0093] S102. Determine the fitness of the mobile network based on the performance metrics of the mobile network.

[0094] Among them, fitness refers to the relative ability of an individual with a known genotype to pass its genes to the gene pool of its offspring under certain environmental conditions.

[0095] In the embodiments of the present application, all base stations included in the mobile network can be regarded as a cluster, and the relative ability of this cluster to pass its genes to the gene pool of its offspring can be determined. Among them, the genes can be the parameters of the base stations. That is to say, the fitness of the mobile network can be used to represent the quality of the parameters of all base stations in the mobile network, and also represents the possibility that the current parameter set of all base stations in the mobile network is inherited to the next generation.

[0096] The parameter set of a base station includes parameter values that affect various performance indicators. For example, the parameters that affect the success rate of intra-frequency handover include: the offset of the (Reference Signal Receiving Power, RSRP) reported for A3 event, the hysteresis threshold reported for A3 event, the triggering time reported for A3 event, etc.

[0097] S103. When the fitness of the mobile network is less than a preset threshold, perform genetic operator operations on the parameter sets of each base station to obtain the next-generation parameter sets of each base station. Among them, the parameter set of a base station includes parameter values that affect various performance indicators of the base station.

[0098] In the embodiments of the present application, the parameter optimization problem can be converted into a problem of finding the optimal solution within the search space through a genetic algorithm. Each parameter included in the parameter set of a base station has a value range, and this value range can be used as the search space of the parameter. The parameter sets of each base station are candidate solutions.

[0099] If the fitness of the mobile network is less than the preset threshold, it indicates that the parameter sets of each base station still need to be optimized. At this time, genetic operator operations can be performed on the parameter sets of each base station, some candidate solutions of the base stations are retained, and the candidate solutions of another part of the base stations are updated to obtain the next-generation candidate solutions of each base station, that is, the next-generation parameter sets of each base station.

[0100] S104. Update the parameters of each base station based on the next-generation parameter sets of each base station. After a preset time period, return to S101 until the fitness of the mobile network is greater than or equal to the preset threshold.

[0101] After updating the parameters of each base station, the performance indicators of each base station will also change. The above S101 - S104 can be executed cyclically until the fitness of the mobile network is greater than or equal to the preset threshold to obtain the optimal parameter set of the base station.

[0102] In the embodiments of the present application, if the fitness of the mobile network is greater than or equal to the preset threshold, it indicates that the overall performance of the current mobile network is good, and the optimal solution within the search space has been obtained through the genetic algorithm. Therefore, the current parameter sets of each base station can be used as the optimized parameter sets to complete the network parameter optimization this time.

[0103] In one implementation, when the mobile network is initially started, an initial parameter set can be set for each base station, and then the method flow shown in Figure 1 can be executed once every preset period to achieve periodic network parameter optimization.

[0104] By adopting the above technical solution, the fitness of the mobile network can be determined based on the performance metrics of the mobile network. When the fitness of the mobile network is less than the preset threshold, genetic operator operations are performed on the parameter sets of each base station to obtain the next-generation parameter sets of each base station. After applying the next-generation parameter sets to each base station, the above process can be executed again after a preset duration until the fitness of the mobile network is greater than or equal to the preset threshold, thus completing the optimization of the network parameters. It can be seen that in the embodiment of the present application, by applying genetic operators in the network parameter optimization process, automatic adjustment of the parameter sets of each base station can be achieved, and the implementation is simple. Moreover, the condition for completing the network parameter optimization is that the fitness of the mobile network is greater than or equal to the preset threshold, and the fitness of the mobile network is determined by the performance metrics of each base station, which is equivalent to optimizing the parameter sets of each base station based on the performance metrics of the entire mobile network, realizing network parameter optimization on the premise of a comprehensive evaluation of the mobile network.

[0105] In an embodiment of the present application, the fitness of the mobile network can be determined based on a preset fitness function, that is, the above S102. Determining the fitness of the mobile network based on the performance metrics of the mobile network can be implemented as follows:

[0106] Perform weighted summation on the performance metrics of the mobile network to obtain the fitness of the mobile network.

[0107] Among them, the influence degree of each performance metric of the mobile network on the overall performance of the mobile network is different. The weight of each performance metric can be preset in advance, and then based on the weights of each performance metric, weighted summation is performed on the performance metrics of the mobile network to obtain the fitness of the mobile network, so that the fitness can reflect the overall performance of the mobile network.

[0108] In one implementation manner, the fitness of the mobile network can be determined through the following fitness function:

[0109] F (t) = A t * I t , where F (t) is the fitness of the mobile network obtained after applying the parameter set of the t-th generation of each base station in the mobile network, A t is a preset weight coefficient matrix used to represent the weights of each performance metric of the mobile network, and I t is the performance metric matrix of the mobile network obtained after applying the parameter set of the t-th generation of each base station in the mobile network.

[0110] Optionally, I t can be a two-dimensional matrix, which can be expressed as I ij , where i is the parent class index of the network metric, (i = 1, 2, 3,...); j is the subclass index of the network metric, (i = 1, 2, 3,...). For example, I11 Indicates the success rate of intra-frequency handover under the accessibility metric, I 12 Indicates the success rate of inter-frequency handover under the accessibility metric.

[0111] Correspondingly, A t is also a two-dimensional matrix and can be represented as A ij . For example, A 11 is the weight of I 11 , and A 12 is the weight of I 12 .

[0112] In the embodiments of the present application, J ijk (k = 1, 2, 3...) can also be used to represent the parameter set affecting the I ij metric. For example, J 111 represents the A3 reporting RSRP offset affecting the success rate of intra-frequency handover of the mobility metric, and J 112 represents the A3 reporting hysteresis threshold affecting the success rate of intra-frequency handover of the mobility metric.

[0113] At t = t0, the network metric corresponding to the parameter set J t0 can be represented as I t0 . Correspondingly,

[0114] By calculating the fitness of the mobile network through the above method, the calculated fitness of the mobile network can reflect the quality of the overall performance of the mobile network, so that the parameter sets of each base station can be optimized in combination with the quality of the overall performance of the mobile network.

[0115] In an embodiment of the present application, the operation process of the genetic operator in the embodiments of the present application is described. As Figure 2 shown, in step S103 above, when the fitness of the mobile network is less than the preset threshold, perform genetic operator operations on the parameter sets of each base station to obtain the next-generation parameter sets of each base station, which can be implemented as:

[0116] S201. When the fitness of the mobile network is less than the preset threshold, determine the fitness of each base station.

[0117] In the embodiments of the present application, all base stations included in the mobile network can be regarded as a cluster, and each base station in the cluster is regarded as an individual in the cluster. The fitness of a base station is determined by the performance metrics of the base station and can reflect the quality of the parameter set of the base station.

[0118] The performance indicators of the base station are similar to those of the mobile network, and can also be classified in the same way as the performance indicators of the mobile network described above. The network management device can periodically obtain the performance indicators of the base station within a period. Taking the same-frequency handover success rate of the base station as an example, the network management device can obtain the total number of same-frequency handovers of the base station within a period, and the number of successful same-frequency handovers of the base station within this period. Furthermore, the ratio of the number of successful same-frequency handovers to the total number of same-frequency handovers can be used as the same-frequency handover success rate of the base station.

[0119] Among them, the impact of each performance indicator of the base station on the overall performance of the mobile network is different. Based on the impact degree of each performance indicator, the weight of each performance indicator can be preset in advance. Furthermore, after the network management device obtains each performance indicator of each base station, for each base station, the performance indicators of the base station can be weighted and summed to obtain the fitness of the base station.

[0120] The fitness function of the base station can be F (t) = A t * I t where F (t) is the fitness of the base station obtained after applying the parameter set of the t-th generation of the base station, A t is the preset weight coefficient matrix, used to represent the weight of each performance indicator of the base station, and I t is the performance indicator matrix of the base station obtained after applying the parameter set of the t-th generation of the base station.

[0121] S202. Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and regard the remaining base stations as the second type of base stations.

[0122] Among them, the preset proportion can be set according to the actual situation. For example, if the preset proportion is 50%, the fitness of each base station can be sorted. In descending order of fitness, the higher-half of the base stations with higher fitness are used as the first type of base stations, and the lower-half of the base stations with lower fitness are used as the second type of base stations.

[0123] S203. Take the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations.

[0124] Among them, because the fitness of the first type of base stations is higher, it indicates that the current parameter set of the first type of base stations is better. Therefore, the current parameter set of the first type of base stations can be inherited to the next generation.

[0125] S204. For each performance indicator included in the second type of base stations, if the performance indicator is less than the performance indicator threshold corresponding to the performance indicator, then regard the performance indicator as a low-performance indicator.

[0126] Since the fitness of the second type of base station is relatively low, it indicates that the current parameter set of the second type of base station is not good enough. Therefore, the parameter values with poor adaptability of the second type of base station can be eliminated, and the parameter values with good adaptability can be retained and inherited to the next generation. The adaptability of the parameter values can be reflected by the performance indicators corresponding to these parameter values.

[0127] In the embodiments of the present application, each performance indicator corresponds to a performance indicator threshold, such as the co-frequency handover success rate threshold, the inter-frequency handover success rate threshold, and the radio power-off rate threshold.

[0128] Each performance indicator of the second type of base station can be compared with the performance indicator threshold corresponding to this performance indicator. If this performance indicator is lower than the threshold corresponding to this performance indicator, then this performance indicator is determined as a low-performance indicator. For example, if the co-frequency handover success rate of the second type of base station is lower than the co-frequency handover success rate threshold, then the co-frequency handover success rate of the second type of base station is used as a low-performance indicator.

[0129] After the threshold comparison, if it is determined that 3 performance indicators of a second type of base station are low-performance indicators, and the remaining performance indicators are not low-performance indicators, then the parameter values corresponding to the remaining performance indicators are retained, and the parameter values corresponding to these 3 low-performance indicators are executed S204.

[0130] S205: Perform a mutation operation on the parameter values corresponding to the low-performance indicators included in each second type of base station to obtain the next-generation parameter set of each second type of base station.

[0131] Among them, S205 can be specifically implemented as follows: For each second type of base station, perform the following operations on each parameter value corresponding to the low-performance indicator of this second type of base station:

[0132] Step 1: Encode this parameter value through a preset encoding method to obtain the gene value of this parameter value.

[0133] Optionally, the preset encoding method can be Gray encoding. For example, assume that this parameter value is the RSRP offset value reported by event A3, and this RSRP offset value is -15. Then, through Gray encoding, the gene value 00000 corresponding to this RSRP offset value can be obtained. The preset encoding method can also be other binary encoding methods, and the embodiments of the present application do not limit this.

[0134] Step 2: Perform a mutation operation on this gene value to obtain the gene mutation value corresponding to this gene value.

[0135] Among them, in the genetic algorithm, the mutation operation refers to replacing the gene values at some gene loci in the individual chromosome coding string with other alleles at the same gene loci, that is, replacing 0 at some bits in the gene value with 1, or replacing 1 with 0. For example, the mutation operation on the gene value 00000 can be to replace 0 at a random bit included in 00000 with 1. For instance, the obtained gene mutation value can be 00001, or it can be 10000, 11000, etc. Here, no more examples will be listed one by one.

[0136] Step 3: If the gene mutation value is within the gene range corresponding to this parameter value, update this parameter value to the parameter value decoded from the gene mutation value. Among them, the gene range is the range of gene values obtained by encoding the value range of this parameter value using the above-mentioned preset encoding method.

[0137] Suppose this parameter value is the RSRP offset value reported for the A3 event. The value range of the RSRP offset value is (-15, -14.5, -14, …, 14.5, 15). Then, the gene range obtained after Gray encoding this value range is (00000, 00001, 00011, 00010, …, 11110).

[0138] If the gene mutation value obtained after the mutation operation on the gene value 00000 in Step 2 above is 00001, and the parameter value decoded from 0001 is -14.5, then the RSRP offset value reported for the A3 event of this second type of base station can be updated from -15 to -14.5.

[0139] Step 4: If the gene mutation value is not within the gene range corresponding to this parameter value, search for the optimal performance index of the same type of performance index as the low performance index corresponding to this parameter value from the performance indexes corresponding to the parameter sets of each previous generation.

[0140] Step 5: Update this parameter value to the parameter value corresponding to the found optimal performance index.

[0141] For example, if the gene mutation value obtained after the mutation operation on the gene value 00000 in Step 2 above is 11111, and assume the current is the 5th generation, then the highest same-frequency handover success rate that occurred in the previous 4 generations can be searched. Suppose the RSRP offset value reported for the A3 event of the base station with the highest same-frequency handover success rate is 13. Then, the RSRP offset value reported for the A3 event of the second type of base station is updated from -15 to 13.

[0142] By adopting this method, through performing genetic operator operations on the parameter sets of each base station, mutation operations can be performed on the parameter sets of the second type of base stations with lower fitness. Specifically, mutation operations are performed on the parameter values corresponding to the low-performance indicators of the second type of base stations, which is equivalent to adjusting the parameter values that cause the low-performance indicators of the second type of base stations, thereby achieving the optimization of the parameter values corresponding to the low-performance indicators, and it is highly probable that the next-generation parameter sets of the second type of base stations will become better to improve the fitness of the second type of base stations.

[0143] Corresponding to the above method embodiment, an embodiment of the present application further provides an electronic device, as Figure 3 shown, including a transceiver 300, a processor 310, and a memory 320.

[0144] The memory 320 is used to store computer programs; the transceiver 300 is used to transmit and receive data under the control of the processor 310; the processor 310 is used to read the computer programs in the memory 320 and perform the following operations:

[0145] Obtain the performance indicators of the mobile network;

[0146] Determine the fitness of the mobile network based on the performance indicators of the mobile network;

[0147] When the fitness of the mobile network is less than a preset threshold, perform genetic operator operations on the parameter sets of each base station to obtain the next-generation parameter sets of each base station, where the parameter set of a base station includes the parameter values that affect each performance indicator of the base station;

[0148] Update the parameters of each base station based on the next-generation parameter sets of each base station. After a preset time period, return to the step of obtaining the performance indicators of the mobile network until the fitness of the mobile network is greater than or equal to the preset threshold.

[0149] In another embodiment of the present application, the processor 310 is specifically used to read the computer programs in the memory 320 and perform the following operations:

[0150] When the fitness of the mobile network is less than a preset threshold, determine the fitness of each base station;

[0151] Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in the order of fitness from large to small, and regard the remaining base stations as the second type of base stations;

[0152] Use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations;

[0153] For each performance indicator included in the second type of base stations, if the performance indicator is less than the performance indicator threshold corresponding to the performance indicator, then regard the performance indicator as a low-performance indicator;

[0154] Perform a mutation operation on the parameter values corresponding to the low performance metrics included in each second type of base station to obtain the next-generation parameter set for each second type of base station.

[0155] In another embodiment of the present application, the processor 310 is specifically configured to read the computer program in the memory 320 and perform the following operations:

[0156] For each second type of base station, perform the following operations on each parameter value corresponding to the low performance metric of the second type of base station:

[0157] Encode the parameter value through a preset encoding method to obtain the gene value of the parameter value;

[0158] Perform a mutation operation on the gene value to obtain the gene mutation value corresponding to the gene value;

[0159] If the gene mutation value is within the gene range corresponding to the parameter value, update the parameter value to the parameter value obtained by decoding the gene mutation value, where the gene range is the range of gene values obtained by encoding the value range of the parameter value using the preset encoding method;

[0160] If the gene mutation value is not within the gene range corresponding to the parameter value, search for the optimal performance metric among the performance metrics corresponding to the historical generations of parameter sets that belongs to the same type of performance metric as the low performance metric corresponding to the parameter value;

[0161] Update the parameter value to the parameter value corresponding to the found optimal performance metric.

[0162] In another embodiment of the present application, the processor 310 is specifically configured to read the computer program in the memory 320 and perform the following operations:

[0163] Perform a weighted sum of the performance metrics of the mobile network to obtain the fitness of the mobile network.

[0164] In another embodiment of the present application, the processor 310 is specifically configured to read the computer program in the memory 320 and perform the following operations:

[0165] For each base station, perform a weighted sum of the performance metrics of the base station to obtain the fitness of the base station.

[0166] Wherein, in Figure 3Among them, the bus architecture may include any number of interconnected buses and bridges, specifically, various circuits of one or more processors represented by the processor 310 and the memory represented by the memory 320 are linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and thus will not be further described herein. The bus interface provides an interface. The transceiver 300 may be multiple components, that is, including a transmitter and a receiver, and provides a unit for communicating with various other devices on the transmission medium, and these transmission media include wireless channels, wired channels, optical fiber cables, and other transmission media. The processor 310 is responsible for managing the bus architecture and general processing, and the memory 320 may store the data used by the processor 310 when executing operations.

[0167] The processor 310 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0168] It should be noted here that the above-mentioned electronic device provided by the embodiment of the present invention can implement all the method steps implemented by the above-mentioned method embodiment, and can achieve the same technical effect. The same parts and beneficial effects as those in the method embodiment will not be specifically described in this embodiment.

[0169] Corresponding to the above method embodiment, the embodiment of the present application also provides a network parameter optimization device, as Figure 4 shown, the device includes:

[0170] An obtaining unit 401, configured to obtain performance indicators of a mobile network;

[0171] A determining unit 402, configured to determine the fitness of the mobile network based on the performance indicators of the mobile network;

[0172] A genetic unit 403, configured to perform a genetic operator operation on the parameter sets of each base station when the fitness of the mobile network is less than a preset threshold, to obtain the next-generation parameter sets of each base station, where the parameter set of a base station includes parameter values affecting each performance indicator of the base station;

[0173] An updating unit 404, configured to update the parameters of each base station based on the next-generation parameter sets of each base station, and after a preset time period, trigger the obtaining unit 401 to obtain the performance indicators of the mobile network.

[0174] In another embodiment of the present application, the genetic unit 403 is specifically configured to:

[0175] When the fitness of the mobile network is less than a preset threshold, determine the fitness of each base station;

[0176] Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and use the remaining base stations as the second type of base stations;

[0177] Use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations;

[0178] For each performance metric included in the second type of base stations, if the performance metric is less than the performance metric threshold corresponding to the performance metric, then regard the performance metric as a low-performance metric;

[0179] Perform a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter set of each second type of base station.

[0180] In another embodiment of the present application, the genetic unit 403 is specifically configured to:

[0181] For each second type of base station, perform the following operations on each parameter value corresponding to the low-performance metric of the second type of base station:

[0182] Encode the parameter value through a preset encoding method to obtain the gene value of the parameter value;

[0183] Perform a mutation operation on the gene value to obtain the gene mutation value corresponding to the gene value;

[0184] If the gene mutation value is within the gene range corresponding to the parameter value, then update the parameter value to the parameter value obtained by decoding the gene mutation value, and the gene range is the range of gene values obtained by encoding the value range of the parameter value using the preset encoding method;

[0185] If the gene mutation value is not within the gene range corresponding to the parameter value, then search for the optimal performance metric of the same type of performance metric as the low-performance metric corresponding to the parameter value from the performance metrics corresponding to the historical generations of parameter sets;

[0186] Update the parameter value to the parameter value corresponding to the found optimal performance metric.

[0187] In another embodiment of the present application, the determination unit 402 is specifically configured to perform a weighted sum of the performance metrics of the mobile network to obtain the fitness of the mobile network.

[0188] In another embodiment of the present application, the genetic unit 403 is specifically configured to perform weighted summation on the performance indicators of each base station to obtain the fitness of the base station for each base station.

[0189] It should be noted that the division of units in the embodiments of the present application is illustrative, merely a logical function division. In actual implementation, there may be other division methods. Additionally, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0190] If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0191] It should be noted here that the above device provided in the embodiments of the present invention can implement all the method steps implemented in the above method embodiments and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described in this embodiment.

[0192] In yet another embodiment provided by the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of any of the above network parameter optimization methods.

[0193] In yet another embodiment provided by the present invention, a computer program product containing instructions is further provided. When it runs on a computer, it causes the computer to execute any of the network parameter optimization methods in the above embodiments.

[0194] 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 program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0195] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements but also other elements that are not explicitly listed, or elements that are inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or device that includes the element.

[0196] Each embodiment in this specification is described in a related manner. The same or similar parts between the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0197] The above are only the preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are all included in the protection scope of the present invention.

Claims

1. A method for optimizing network parameters, characterized in that, Including: Obtain performance metrics of a mobile network, where the mobile network includes multiple base stations; Determine the fitness of the mobile network based on the performance metrics of the mobile network, where the fitness represents the quality of the parameters of all base stations in the mobile network and represents the possibility that the current parameter set of all base stations in the mobile network is inherited to the next generation; When the fitness of the mobile network is less than a preset threshold, determine the fitness of each base station; Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and regard the remaining base stations as the second type of base stations; Use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations; For each performance metric included in the second type of base stations, if the performance metric is less than the performance metric threshold corresponding to the performance metric, then regard the performance metric as a low-performance metric; Perform a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter set of each second type of base station, where the parameter set of a base station includes the parameter values affecting the performance metrics of the base station; Update the parameters of each base station based on the next-generation parameter sets of the base stations. After a preset duration, return to the step of obtaining the performance metrics of the mobile network until the fitness of the mobile network is greater than or equal to the preset threshold.

2. The method according to claim 1, characterized in that, The performing a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter set of each second type of base station includes: For each second type of base station, perform the following operations on each parameter value corresponding to the low-performance metric of the second type of base station: Encode the parameter value through a preset encoding method to obtain the gene value of the parameter value; Perform a mutation operation on the gene value to obtain the gene mutation value corresponding to the gene value; If the gene mutation value is within the gene range corresponding to the parameter value, update the parameter value to the parameter value obtained by decoding the gene mutation value, where the gene range is the range of gene values obtained by encoding the value range of the parameter value using the preset encoding method; If the gene mutation value is not within the gene range corresponding to the parameter value, search for the optimal performance metric among the performance metrics corresponding to the historical generations of parameter sets that belongs to the same type of performance metric as the low-performance metric corresponding to the parameter value; Update the parameter value to the parameter value corresponding to the found optimal performance metric.

3. The method according to claim 1, characterized in that, The determining the fitness of the mobile network based on the performance metrics of the mobile network includes: Perform a weighted sum of the performance metrics of the mobile network to obtain the fitness of the mobile network.

4. The method according to claim 1, characterized in that, The determining the fitness of each base station includes: For each base station, perform a weighted sum of the performance metrics of the base station to obtain the fitness of the base station.

5. An electronic device, characterized in that, Including a memory, a transceiver, and a processor: The memory is used to store computer programs; the transceiver is used to transmit and receive data under the control of the processor; the processor is used to read the computer programs in the memory and perform the following operations: Obtain performance metrics of a mobile network, where the mobile network includes multiple base stations; Determine the fitness of the mobile network based on the performance metrics of the mobile network, where the fitness represents the quality of the parameters of all base stations in the mobile network and represents the possibility that the current parameter set of all base stations in the mobile network is inherited to the next generation; When the fitness of the mobile network is less than a preset threshold, determine the fitness of each base station; Select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and use the remaining base stations as the second type of base stations; Use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations; For each performance metric included in the second type of base stations, if the performance metric is less than the performance metric threshold corresponding to the performance metric, then regard the performance metric as a low-performance metric; Perform a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter set of each second type of base station, where the parameter set of a base station includes the parameter values affecting the performance metrics of the base station; Update the parameters of each base station based on the next-generation parameter set of each base station. After a preset time period, return to the step of obtaining the performance metrics of the mobile network until the fitness of the mobile network is greater than or equal to the preset threshold.

6. The electronic device according to claim 5, characterized in that, The processor is specifically configured to read the computer program in the memory and perform the following operations: For each second type of base station, perform the following operations on each parameter value corresponding to the low-performance metric of the second type of base station: Encode the parameter value through a preset encoding method to obtain the gene value of the parameter value; Perform a mutation operation on the gene value to obtain the gene mutation value corresponding to the gene value; If the gene mutation value is within the gene range corresponding to the parameter value, update the parameter value to the parameter value obtained by decoding the gene mutation value, where the gene range is the range of gene values obtained by encoding the value range of the parameter value using the preset encoding method; If the gene mutation value is not within the gene range corresponding to the parameter value, search for the optimal performance metric among the performance metrics corresponding to the historical generations of parameter sets that belongs to the same type of performance metric as the low-performance metric corresponding to the parameter value; Update the parameter value to the parameter value corresponding to the found optimal performance metric.

7. A network parameter optimization device, characterized in that, Include: An acquisition unit, configured to acquire the performance metrics of a mobile network, where the mobile network includes multiple base stations; A determination unit, configured to determine the fitness of the mobile network based on the performance metrics of the mobile network, where the fitness represents the quality of the parameters of all base stations in the mobile network and represents the possibility that the current parameter set of all base stations in the mobile network is inherited to the next generation; A genetic unit, configured to determine the fitness of each base station when the fitness of the mobile network is less than a preset threshold; select a preset proportion of base stations from the base stations of the mobile network as the first type of base stations in descending order of fitness, and use the remaining base stations as the second type of base stations; use the current parameter set of the first type of base stations as the next-generation parameter set of the first type of base stations; for each performance metric included in the second type of base stations, if the performance metric is less than the performance metric threshold corresponding to the performance metric, then use the performance metric as a low-performance metric; perform a mutation operation on the parameter values corresponding to the low-performance metrics included in each second type of base station to obtain the next-generation parameter set of each second type of base station, where the parameter set of a base station includes the parameter values affecting the performance metrics of the base station. An update unit, configured to update the parameters of each base station based on the next-generation parameter set of each base station, and trigger the acquisition unit to acquire the performance metrics of the mobile network after a preset duration.

8. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program, and the computer program is used to cause the processor to execute the method according to any one of claims 1 to 4.

Images