A multi-frequency operator network parameter intelligent collaboration and adjustment system and method

Abstract

The present invention relates to the field of information technology, and particularly to a multi-frequency operator network parameter intelligent coordination and adjustment system and method, including: classifying different network scenarios into three types of scenarios: point, line, and surface, formulating corresponding parameter templates according to the characteristics of each type of scenario, and adding type stamps to each parameter template; obtaining network data under each type of scenario to form a historical data set; analyzing the historical data under each type of scenario through a machine learning model to predict whether a handover between operator networks will occur under the type of scenario; pre-allocating resources before the predicted handover occurs to reduce the front and rear time delays and reduce the handover failure rate; constructing a fitness function one; constructing a fitness function two; optimizing the parameters of the fitness function one and the fitness function two through a genetic algorithm to seek an optimal solution, and modifying the parameters of the parameter template of the corresponding type of scenario according to the optimal solution.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and particularly to an intelligent cooperation and adjustment system and method for multi-frequency operator network parameters. Background Art

[0002] The application of 4G technology is extremely extensive in the field of Internet consumption. By using the 4G network, it can help users conduct mobile payment and instant communication more conveniently. At the same time, in the process of transmitting content such as images and videos, the application effect of 4G is also relatively smooth. In contrast, 5G is mainly applied to special tasks such as industrial manufacturing, Internet, and intelligent driving. The two have a relationship of coordinated development and coexistence as a whole. With the gradual maturity and implementation of the 4G and 5G cross-system interoperability solutions, users will obtain a better continuous experience.

[0003] In actual use, 4G and 5G have the situation of multi-frequency covering the same area. To better use the spectrum resources and achieve a better coverage effect, this paper proposes an intelligent cooperation and adjustment system and method for multi-frequency operator network parameters. Summary of the Invention

[0004] In order to solve the problems in the background art, the present invention proposes a technical solution: an intelligent cooperation and adjustment method for multi-frequency operator network parameters, the method comprising:

[0005] Dividing different network scenarios into three types of scenarios: point, line, and surface, and formulating corresponding parameter templates according to the characteristics of each type of scenario, and adding a type stamp to each parameter template;

[0006] Obtaining network data under each type of scenario to form a historical data set; the network data includes average delay, signal strength, signal-to-noise ratio, total number of handover attempts between operator networks, and number of handover failures;

[0007] Analyzing the historical data under each type of scenario through a machine learning model to predict whether a handover between operator networks will occur under the type of scenario;

[0008] Pre-allocating resources before the predicted handover occurs to reduce the front and back delay and reduce the handover failure rate;

[0009] Constructing a fitness function one for evaluating the impact of reducing the handover failure rate on the network handover performance;

[0010] Constructing a fitness function two for evaluating the impact of network error amount and control input on the network handover quality to adjust the parameter templates under the three types of scenarios;

[0011] Optimize the parameters of fitness function one and fitness function two through genetic algorithms to seek the optimal solution, and modify the corresponding parameters of the corresponding type of scenario parameter template according to the optimal solution.

[0012] Preferably, the obtaining of network data under each type of scenario to form a historical data set includes the following steps:

[0013] Obtain the network data under the point type scenario according to the preset collection period and collection frequency to form the historical data set of the point type , and according to Construct the feature data set under the point type scenario ;

[0014] Obtain the network data under the surface type scenario according to the preset collection period and collection frequency to form the historical data set of the surface type , and according to Construct the feature data set under the line type scenario ;

[0015] Obtain the network data under the surface type scenario according to the preset collection period and collection frequency to form the historical data set of the surface type , and according to Construct the feature data set under the surface type scenario .

[0016] Preferably, the constructing of the feature data set under the point type scenario according to includes the following steps:

[0017] From Extract the network switching time points and switching failure time points within a preset time span ;

[0018] Obtain all the signal strength and signal-to-noise ratio data under the point type scenario within the seconds before the network switching time point to form a feature vector set , where represents the feature vector at the moment,

[0019] ;

[0019] All the signal strength and signal-to-noise ratio data within the seconds before the switching failure time point form a feature vector set , where represents the feature vector at the moment, respectively represent the signal-to-noise ratio and signal strength at a moment, ;

[0020] Then the historical data set in the point type scenario is ;

[0021] Said according to Construct the feature data set in the point type scenario , including the following steps:

[0022] From Extract the network switching time points within a preset time span , switching failure time points ;

[0023] Obtain all the signal strength and signal-to-noise ratio data in the point type scenario within seconds before the network switching time point to form a feature vector set , where represents the feature vector at a moment, respectively represent the signal-to-noise ratio and signal strength at a moment, ;

[0024] Switching failure time point before seconds to form a feature vector set , where represents the feature vector at a moment, respectively represent the signal-to-noise ratio and signal strength at a moment, ;

[0025] Then the historical data set in the line type scenario is ;

[0026] Said according to Construct the feature data set in the surface type scenario , including the following steps:

[0027] From Extract the network switching time points within a preset time span , switching failure time points ;

[0028] Obtain all the signal strength and signal-to-noise ratio data in the point type scenario within seconds before the network switching time point to form a feature vector set , where representation The feature vector at a moment, respectively represent the signal-to-noise ratio and signal strength at a moment, ;

[0029] Handover failure time point the previous All signal strength and signal-to-noise ratio data within seconds form a feature vector set , where representation The feature vector at a moment, respectively represent the signal-to-noise ratio and signal strength at a moment, ;

[0030] Then the historical data set in the surface type scenario is .

[0031] Preferably, analyzing the historical data in each type of scenario through a machine learning model to predict whether there will be a handover between operator networks in the type of scenario includes the following steps:

[0032] Construct prediction models one, two, and three through a regression algorithm, which are respectively used to predict the handover between 4G and 5G networks in point type scenarios, line type scenarios, and surface type scenarios;

[0033] Train prediction models one, two, and three through the historical data sets in point type scenarios, line type scenarios, and surface type scenarios, specifically including the following steps:

[0034] After normalizing the data in the historical data set in the point type scenario, divide it into a training set and a validation set, train prediction model one through the training set, and verify the performance of prediction model one through the validation set;

[0035] After normalizing the data in the historical data set in the line type scenario, divide it into a training set and a validation set, train prediction model two through the training set, and verify the performance of prediction model two through the validation set;

[0036] After normalizing the data in the historical data set in the surface type scenario, divide it into a training set and a validation set, train prediction model three through the training set, and verify the performance of prediction model three through the validation set;

[0037] Collect network data information within a preset time span from networks of point, line, and surface types through a preset sliding window. After preprocessing and normalization of the newly collected network data information, input it into the trained prediction model one, prediction model two, and prediction model three respectively;

[0038] Predict whether a handover will occur between 4G and 5G networks at a future moment through the trained prediction model one, prediction model two, and prediction model three.

[0039] Preferably, the prediction model one includes a handover prediction model one and a handover failure prediction model one. The handover prediction model one is ; The handover failure model one is ;

[0040] Among them, 、 are the intercepts respectively, 、 are the error terms respectively, represents the number of feature vectors before successful handover, represents the number of feature vectors before handover failure;

[0041] The input variable of the prediction model one is a vector composed of signal-to-noise ratio and signal strength, , Therefore, the handover prediction model one is converted to:

[0042] ; Among them is the weight matrix one, used to represent the influence of signal-to-noise ratio and signal strength on the input variable, the ; Among them, ;

[0043] Similarly, the handover failure model one is converted to:

[0044] ;

[0045] Input the data seconds before the handover time point within the sliding window into the prediction model one to predict whether a network handover will occur at a future moment;

[0046] Set the handover threshold , If then it is judged that a network handover will occur at a future moment; otherwise, no network handover will occur;

[0047] If it is predicted that a network handover will occur at a future moment, then input the input variable of the handover prediction model one into the handover failure model one to predict the probability of successful handover;

[0048] Set a probability threshold If it is determined that the handover will fail.

[0049] Preferably, resources are pre-allocated before the predicted handover occurs to reduce the front and back time delays and reduce the handover failure rate, including the following steps:

[0050] If it is determined that the handover will fail, resources are allocated before the predicted handover time;

[0051] The allocation of resources includes the following steps:

[0052] Obtain the bandwidth resources and computing resources that can be pre-allocated through the network management system;

[0053] Obtain the real-time network loads of the 4G and 5G networks through the network management system; if the 4G network load is heavy, give priority to reserving bandwidth for the 5G network to relieve the pressure on the 4G network.

[0054] Preferably, if it is determined that the handover will fail, the handover threshold can also be dynamically adjusted. By increasing the handover threshold, the network handover is blocked, and the parameter data of the corresponding parameter template is corrected;

[0055] The correction of the parameter data of the corresponding parameter template includes the following steps:

[0056] Modify the power parameters of the devices in the parameter template to improve the network signal strength;

[0057] Modify the number of starting devices in the parameter template to start more network base stations to improve the network signal coverage and signal strength.

[0058] Preferably, the construction of the fitness function one is used to evaluate the impact of reducing the handover failure rate on the network handover performance, including:

[0059] Construct the fitness function one: ;

[0060] Among them, represents the handover failure rate; represents the average handover delay, represents the weight coefficient;

[0061] Among them, , ;

[0062] Obtain the total number of network handover attempts, the number of handover failures, and the delay of each handover through the network management system;

[0063] The constructed fitness function two is used to evaluate the influence of network error amount and control input on network handover quality, so as to adjust the parameter templates under three types of scenarios, including:

[0064] Construct the fitness function two: ;

[0065] Wherein, represents the network error, represents the control input, respectively represent the weight coefficients of the network error and the control input;

[0066] Optimizing the parameters of the fitness function one and the fitness function two through the genetic algorithm to seek the optimal solution includes the following steps:

[0067] Optimizing the parameters of the fitness function one through the genetic algorithm to seek the parameter combination one that makes obtain the minimum value;

[0068] Optimizing the parameters of the fitness function two through the genetic algorithm to seek the parameter combination two that makes obtain the minimum value, which is used to indicate that both the network error and the control input are controlled;

[0069] Optimizing the parameters of the fitness function one and the fitness function two through the genetic algorithm to seek the optimal solution, and modifying the corresponding parameters of the corresponding type of scenario parameter template according to the optimal solution, including:

[0070] Obtain the optimized parameter combination one ; Obtain the optimized parameter combination two ;

[0071] Since , modify the handover threshold in the parameter template to adjust the total number of handover attempts;

[0072] Since , by adjusting the cell reselection priority and the neighbor cell relationship configuration in the parameter template, the handover speed is improved and the handover delay is reduced.

[0073] The present invention also provides a multi-frequency operator network parameter intelligent coordination and adjustment system, and the system is used to execute the multi-frequency operator network parameter intelligent coordination and adjustment method described above.

[0074] The present invention also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the multi-frequency operator network parameter intelligent coordination and adjustment method described above.

[0075] The beneficial effects of the present invention:

[0076] 1. In the present invention, different network scenarios are classified into three types: point, line, and surface scenarios. Corresponding parameter templates are formulated according to the characteristics of each type of scenario, and a type stamp is added to each parameter template to distinguish different types of usage scenarios and facilitate the quick retrieval of the corresponding parameter templates during later parameter modification. By optimizing the handover process and the parameters of the parameter templates, network latency can be reduced, and the user experience can be improved, especially for latency-sensitive applications such as online games and video conferencing. After improving the handover speed, a more smooth and stable service can be provided through fast and accurate network handover, enhancing the user's satisfaction with the network service.

[0077] 2. In the present invention, by setting fitness function one and fitness function two, the influence of network handover failure rate and average handover latency on the handover network is evaluated through fitness function one to seek the optimal parameter combination; the influence of network error and control input on the network handover quality is evaluated through fitness function two to seek the optimal parameter combination. During the process of seeking the optimal solution, a genetic algorithm is applied to optimize the parameters, enabling the network parameters to be dynamically optimized according to different environmental factors (such as user distribution, time, location, etc.) to adapt to the complex and changeable network environment. After obtaining the optimal parameter combination, the parameters (signal strength, handover latency, base station power, handover control parameters, cell reselection priority, and relationship configuration for receiving, etc.) are adjusted by modifying the parameter template to ensure the network handover quality.

[0078] 3. In the present invention, when setting the input variables of prediction model one, prediction model two, and prediction model three, two key network parameters, signal-to-noise ratio and signal strength, are considered. The products obtained by multiplying them with weight matrix one, weight matrix two, and weight matrix three are respectively used as the input variables of the three models. The weight matrix reflects the degree of influence of the two variables on network handover. This method of integrating multiple parameters makes the prediction more comprehensive and improves the prediction accuracy.

[0079] 4. In the present invention, each prediction model includes a handover prediction model and a handover failure prediction model. By predicting the occurrence of handover, resources such as bandwidth are prepared in advance, thereby improving the success rate of handover; by predicting that the handover may fail, the handover threshold is adjusted to avoid this handover, thus avoiding the impact on user usage due to handover failure. By reducing the number of handover failures and optimizing network performance, the overall stability and reliability of the network can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 It is a flowchart of a method for intelligent coordination and adjustment of multi-frequency operator network parameters according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0081] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other implementation schemes, variant schemes, improvement schemes, equivalent schemes, and other technical schemes without departing from the spirit and scope of the present invention.

[0082] It can be understood that the term "a" should be understood as "at least one" or "one or more". That is, in one embodiment, the number of an element can be one, while in other embodiments, the number of the element can be multiple. The term "a" cannot be understood as a limitation on the quantity.

[0083] Referring to Figure 1 , the technical solution provided by the present invention is: a method for intelligent coordination and adjustment of multi-frequency operator network parameters, including the following steps:

[0084] Step 1: Classify different network scenarios into three types of scenarios: point, line, and surface, and formulate corresponding parameter templates according to the characteristics of each type of scenario, and add type stamps to each parameter template; so as to retrieve the parameter templates of the corresponding type of scenario.

[0085] The so-called point scenario refers to the network connection of a single device or node, the line scenario refers to the communication link between two devices, and the surface scenario may involve the entire network topology structure composed of multiple devices.

[0086] Set clear ranges and boundaries for each scenario type to ensure their operability and measurability in the actual network environment. The point scenario needs to focus on the bandwidth and latency of the device, the line scenario needs to focus on the reliability and bandwidth utilization rate of the link, and the surface scenario needs to focus on the stability and scalability of the entire network.

[0087] In this embodiment, appropriate bandwidth limits can be set for each scenario type according to the scenario type and actual requirements. For example, for the point scenario, the bandwidth can be set according to the processing capacity of the device; for the line scenario, the bandwidth can be set according to the capacity of the link; for the surface scenario, the bandwidth can be set according to the requirements of the entire network. For the point scenario, the latency threshold is set according to the processing speed of the device; for the line scenario, the latency threshold is set according to the transmission speed of the link; for the surface scenario, the latency threshold is set according to the transmission speed of the entire network.

[0088] Add a unique type stamp to each parameter template to identify the type of scenario to which the template applies. In this way, when specific scenario parameters need to be retrieved, the corresponding template can be quickly found based on the type stamp. Through the type stamp, it is convenient to manage and call parameter templates for different scenario types. For example, a database or other data storage system can be used to store the templates, and appropriate interfaces can be provided for other systems and services to call. Administrators or automated scripts dynamically update the parameter templates according to the monitoring results.

[0089] Step 2: Obtain network data for each type of scenario to form a historical data set; the network data includes average latency, signal strength, signal-to-noise ratio, total number of handover attempts between operator networks, and number of handover failures; specifically, it includes the following steps:

[0090] Step 2.1: Obtain network data for the point type scenario according to the preset collection period and collection frequency to form a historical data set of the point type , and according to Construct a feature data set for the point type scenario , specifically:

[0091] From Extract network handover time points within a preset time span , handover failure time points ;

[0092] Obtain the network handover time point Before Seconds, all signal strength and signal-to-noise ratio data for the point type scenario form a feature vector set , where Represents The feature vector at time , respectively represent The signal-to-noise ratio and signal strength at time ;

[0093] Handover failure time point Before Seconds, all signal strength and signal-to-noise ratio data form a feature vector set , where Represents The feature vector at time , respectively represent The signal-to-noise ratio and signal strength at time ;

[0094] Then the historical data set for the point type scenario is

[0095] Step 2.2. Obtain the network data in the surface type scenario according to the preset collection period and collection frequency to form a historical data set of the surface type , and based on construct a feature data set in the line type scenario , specifically:

[0096] From extract the network switching time points within a preset time span , switching failure time points ;

[0097] Obtain all the signal strength and signal-to-noise ratio data in the point type scenario within seconds before the network switching time point to form a feature vector set , where represents the feature vector at time respectively represents the signal-to-noise ratio and signal strength at time ;

[0098] All the signal strength and signal-to-noise ratio data within seconds before the switching failure time point form a feature vector set , where represents the feature vector at time respectively represents the signal-to-noise ratio and signal strength at time ;

[0099] Then the historical data set in the line type scenario is .

[0100] Step 2.3. Obtain the network data in the surface type scenario according to the preset collection period and collection frequency to form a historical data set of the surface type , and based on construct a feature data set in the surface type scenario , specifically:

[0101] From extract the network switching time points within a preset time span , switching failure time points ;

[0102] Obtain all the signal strength and signal-to-noise ratio data in the point type scenario within seconds before the network switching time point to form a feature vector set , where represents The feature vector at a moment, respectively represent the signal-to-noise ratio and signal strength at a moment, ;

[0103] The handover failure time point before All the signal strength and signal-to-noise ratio data within seconds form a feature vector set , where represents the feature vector at a moment, respectively represent the signal-to-noise ratio and signal strength at a moment, ;

[0104] Then the historical data set in the face type scenario is .

[0105] Step 3: Analyze the historical data in each type of scenario through a machine learning model to predict whether there will be a handover between operator networks in the said type of scenario. Specifically:

[0106] Construct a prediction model one adapted to the point type scenario, including a handover prediction model one and a handover failure prediction model one. The handover prediction model one is ; The handover failure model one is ; Among them, , are the intercepts respectively, , are the error terms respectively, represents the number of feature vectors before a successful handover, represents the number of feature vectors before a handover failure;

[0107] Since the input variable of the prediction model one is a vector composed of the signal-to-noise ratio and signal strength, , therefore, the handover prediction model one is converted to:

[0108] ; Among them is the weight matrix, used to represent the influence of the signal-to-noise ratio and signal strength on the input variable. The ; Among them, ;

[0109] = = ;

[0110] ;

[0111] Similarly, the handover failure model one is converted to:

[0112] ;

[0113] Input the data within seconds before the switching time point in the sliding window into Prediction Model One to predict whether a network switch will occur at the next moment;

[0114] Set a switching threshold , if then it is determined that a network switch will occur at the next moment.

[0115] In this embodiment, the switching threshold is set to 0.5. If , then it is predicted that a network switch will occur; otherwise, it is predicted that no network switch will occur.

[0116] The so-called "next moment" is related to the time span from which the data is obtained. If one hour is used as the collection period and data is collected every 5 minutes, then the predicted next moment is the moment 5 minutes later.

[0117] If it is predicted that a network switch will occur at the next moment, then input the input variables of Switching Prediction Model One into Switching Failure Model One to predict the probability of successful switching, which helps to identify potential network switching problems in advance and take corresponding measures to optimize network performance or user experience. Specifically:

[0118] Set a probability threshold , if then it is determined that the switching will fail. In this embodiment, the probability threshold is set to 0.8. If , then it is determined that the switching will fail.

[0119] Similarly, construct Prediction Model Two adapted to the line type scenario: ; are the intercepts respectively, represents the regression coefficient, is the error term, represents the number of feature vectors before successful switching;

[0120] Construct Prediction Model Three adapted to the surface type scenario: ; are the intercepts respectively, represents the regression coefficient, is the error term.

[0121] Set a probability threshold , if then it is determined that the switching will occur; set a probability threshold , if then it is determined that the switching will occur.

[0122] The prediction of handover failure in online and surface type scenarios is also achieved by constructing a handover failure prediction model similar to that in point type scenarios. Since the principles of model construction and judgment are similar, they will not be elaborated here. By predicting the occurrence and success probability of network handover, network administrators can better plan network resources, improve network stability and reliability. At the same time, it also helps to reduce unnecessary network handover attempts, thus saving network resources and reducing potential risks.

[0123] Step 4: Pre-allocate resources before the predicted handover occurs to reduce the front and back latency and lower the handover failure rate, specifically as follows:

[0124] During the network handover process, the increase in latency and the increase in handover failure rate are two main problems. By predicting the time of handover occurrence, resource allocation can be carried out in advance, thus effectively reducing these problems.

[0125] If it is judged that the upcoming handover may fail, then pre-allocate resources (including the allocation of bandwidth resources and computing resources) before the predicted handover time to ensure the smooth progress of the handover process;

[0126] Obtain the real-time network load of 4G and 5G networks through the network management system; if the 4G network load is heavy, give priority to reserving bandwidth for the 5G network to relieve the pressure on the 4G network;

[0127] In addition, the handover threshold is an important parameter that determines whether to perform a network handover. By dynamically adjusting this threshold, the occurrence of network handover can be effectively controlled.

[0128] In this embodiment, if it is judged that the upcoming handover may fail, then the occurrence of this handover can be prevented by automatically increasing the size of the handover threshold. At the same time, modify the parameter data in the corresponding parameter template to ensure network stability. The way to increase the handover threshold includes increasing a certain percentage or value fixedly; after updating the handover threshold, check again whether the new threshold meets the requirements. When the handover threshold reaches the set upper limit (increase by more than 10%), stop increasing the threshold to prevent infinite loop or over-adjustment. At this time, other strategies can be selected to handle, such as sending an alarm to notify the administrator to take corresponding handling measures.

[0129] The modification of the parameter data in the corresponding parameter template includes the following steps:

[0130] Modify the power parameter of the device in the parameter template to improve the network signal strength;

[0131] Modify the number of starting devices in the parameter template to start more network base stations to improve the network signal coverage and signal strength.

[0132] Step 5: Construct Fitness Function 1 for evaluating the impact of reducing handover failure rate on network handover performance, including:

[0133] Construct Fitness Function 1: ;

[0134] wherein, represents the handover failure rate; represents the average handover delay, represents the weight coefficient;

[0135] wherein, , ;

[0136] Obtain the total number of network handover attempts, the number of handover failures, and the handover delay each time through the network management system;

[0137] Step 6: Construct Fitness Function 2 for evaluating the impact of network error amount and control input on network handover quality to adjust the parameter templates in three types of scenarios; including:

[0138] Construct Fitness Function 2: ;

[0139] wherein, represents the network error, represents the control input, respectively represent the weight coefficients of the network error and the control input;

[0140] Optimizing the parameters of Fitness Function 1 and Fitness Function 2 through the genetic algorithm to seek the optimal solution, including the following steps:

[0141] Optimizing the parameters of Fitness Function 1 through the genetic algorithm to seek the parameter combination 1 that minimizes ;

[0142] Optimizing the parameters of Fitness Function 2 through the genetic algorithm to seek the parameter combination 2 that minimizes , which is used to indicate that both the network error and the control input are controlled;

[0143] Step 7: Optimizing the parameters of Fitness Function 1 and Fitness Function 2 through the genetic algorithm to seek the optimal solution, and modifying the corresponding parameters of the corresponding type of scenario parameter template according to the optimal solution, including:

[0144] Obtain the optimized parameter combination 1 ; Obtain the optimized parameter combination 2 ;

[0145] Since , modifying the handover threshold within the parameter template can be used to adjust the total number of handover attempts;

[0146] Combined with the above method of reserving bandwidth and computing resources, the number of failed handovers can also be reduced to a certain extent, while further improving the handover speed.

[0147] Since , by adjusting the cell reselection priority and neighbor cell relationship configuration within the parameter template, the handover speed can be increased and the handover delay can be reduced. For example, increasing the priority of the cell with 5G network deployed and preferentially handing over to the 5G network. Or, updating the neighbor cell list to ensure that the user equipment can promptly identify and hand over to a neighbor cell with better signal quality.

[0148] The process of optimizing parameters through the genetic algorithm in Steps Six and Seven includes conventional steps such as initializing the population, evaluating fitness, selection, crossover, mutation, replacement, and termination condition check, and can be specifically implemented through Python.

[0149] In this embodiment, in the optimization of the fitness function one, the main parameters can be set as: population_size = 100, gene_length = 2, max_iterations = 1000, mutation_rate = 0.1, crossover_rate = 0.8.

[0150] In the crossover operation, the single-point crossover method is adopted to return the offspring after crossover; in the mutation operation, the uniform mutation method is used to return the offspring after mutation.

[0151] The present invention also provides a multi-frequency operator network parameter intelligent coordination and adjustment system, and the system is used to execute the multi-frequency operator network parameter intelligent coordination and adjustment method described above.

[0152] The present invention also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the multi-frequency operator network parameter intelligent coordination and adjustment method described above.

[0153] Embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. Embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the methods of the present application are executed. It should be noted that the above-mentioned computer-readable medium in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program codes. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or combined with an instruction execution system, apparatus, or device. The program codes contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless segments, wire segments, optical cables, RF, etc., or any suitable combination of the above.

[0154] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0155] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and illustrated in the embodiments. Without departing from the said principles, the embodiments of the present invention may have any variations or modifications.

Claims

1. A method for intelligent coordination and adjustment of multi - frequency operator network parameters, characterized in that, The method includes: Dividing different network scenarios into three types of scenarios: point, line, and surface, and formulating corresponding parameter templates according to the characteristics of each type of scenario, and adding type stamps to each parameter template; the point scenario is the scenario of the network connection of a single device or node, the line scenario is the scenario of the communication link between two devices, and the surface scenario is the scenario of the entire network topology structure composed of multiple devices; Obtaining network data under each type of scenario to form a historical data set; the network data includes average delay, signal strength, signal-to-noise ratio, total number of handover attempts between operator networks, and number of handover failures; Analyzing the historical data under each type of scenario through a machine learning model to predict whether a handover between operator networks will occur under the type of scenario; Pre-allocating resources before the predicted handover occurs to reduce the front and back delays and reduce the handover failure rate; Constructing a fitness function one for evaluating the impact of reducing the handover failure rate on the network handover performance; Constructing a fitness function two for evaluating the impact of network error amount and control input on the network handover quality to adjust the parameter templates under the three types of scenarios; Optimizing the parameters of the fitness function one and the fitness function two through a genetic algorithm to seek the optimal solution, and modifying the corresponding parameters of the corresponding type of scenario parameter template according to the optimal solution; The constructing of the fitness function one for evaluating the impact of reducing the handover failure rate on the network handover performance includes: Construct fitness function 1: ; Among them, represents the handover failure rate; represents the average handover delay, represents the weight coefficient; Among them, , ; Obtaining the total number of network handover attempts, number of handover failures, and delay of each handover through a network management system; The constructing of the fitness function two for evaluating the impact of network error amount and control input on the network handover quality to adjust the parameter templates under the three types of scenarios includes: Construct fitness function two: ; Among them, represents the network error, represents the control input, respectively represent the weight coefficients of the network error and the control input.

2. The intelligent collaboration and adjustment method for multi-frequency operator network parameters according to claim 1, characterized in that The obtaining of the network data under each type of scenario to form a historical data set includes the following steps: Obtain the network data in the point type scenario according to the preset collection period and collection frequency to form the historical data set of the point type , and according to construct the feature data set in the point type scenario Obtain network data in the line type scenario according to the preset collection period and collection frequency to form a historical data set of the surface type , and based on construct a feature data set in the line type scenario ; Obtain network data in the scenario of the surface type according to the preset collection period and collection frequency to form a historical data set of the surface type , and based on construct a feature data set in the scenario of the surface type .

3. The intelligent coordination and adjustment method for multi-frequency operator network parameters according to claim 2, characterized in that, The said according to Construct a feature data set in the point type scenario , including the following steps: From Extract the network switching time points within a preset time span , the switching failure time points ; Obtain the network switching time point Previous The signal strength and signal-to-noise ratio data under all point type scenarios within the previous seconds form a feature vector set where represents the feature vector at time respectively represent the signal-to-noise ratio and signal strength at time ; Handover failure time point Previous All signal strength and signal-to-noise ratio data within the previous seconds form a feature vector set where represents the feature vector at time which respectively represent the signal-to-noise ratio and signal strength at time ; Then the historical data set in the point type scenario is ; The said according to Construct a feature dataset in the line type scenario , including the following steps: From Extract the network switching time points within a preset time span , the switching failure time points ; Obtain the network switching time point Previous The signal strength and signal-to-noise ratio data under all point type scenarios within the previous [[0000086]] seconds constitute a feature vector set , where Denote The feature vector at time [[0000090]], Respectively denote The signal-to-noise ratio and signal strength at time [[0000092]], ; Time point of handover failure Previous All signal strength and signal-to-noise ratio data within the previous seconds form a feature vector set where represents the feature vector at time and represent the signal-to-noise ratio and signal strength at time respectively; The historical data set in the line type scenario is ; The said according to Construct a feature data set under the surface type scenario , including the following steps: From Extract the network switching time points within a preset time span , the switching failure time points ; Obtain the network switching time point Previous The signal strength and signal-to-noise ratio data under all point type scenarios within the previous seconds form a feature vector set where represents the feature vector at time respectively represent the signal-to-noise ratio and signal strength at time ; Time point of handover failure Previous All signal strength and signal-to-noise ratio data within the previous seconds form a feature vector set where represents the feature vector at time and represent the signal-to-noise ratio and signal strength at time respectively; The historical dataset in the side type scenario is .

4. A method for intelligent coordination and adjustment of multi-frequency operator network parameters according to claim 1, characterized in that The analyzing of the historical data under each type of scenario through a machine learning model to predict whether a handover between operator networks will occur under the type of scenario includes the following steps: Constructing prediction models one, two, and three through a regression algorithm, which are respectively used to predict the handovers of 4G and 5G networks in the point type scenario, line type scenario, and surface type scenario; Training the prediction models one, two, and three through the historical data sets under the point type scenario, line type scenario, and surface type scenario, specifically including the following steps: Normalizing the data in the historical data set under the point type scenario, dividing it into a training set and a validation set, training the prediction model one through the training set, and validating the performance of the prediction model one through the validation set; Normalizing the data in the historical data set under the line type scenario, dividing it into a training set and a validation set, training the prediction model two through the training set, and validating the performance of the prediction model two through the validation set; Normalizing the data in the historical data set under the surface type scenario, dividing it into a training set and a validation set, training the prediction model three through the training set, and validating the performance of the prediction model three through the validation set; Collect network data information within a preset time span from networks of point, line, and surface types respectively through a preset sliding window. After preprocessing and normalizing the newly collected network data information, input it into the trained prediction model one, prediction model two, and prediction model three respectively; Predict whether a handover will occur between the 4G and 5G networks at the next moment through the trained prediction model one, prediction model two, and prediction model three.

5. The intelligent coordination and adjustment method for multi-frequency operator network parameters according to claim 4, characterized in that The first prediction model includes a first handover prediction model and a first handover failure prediction model. The first handover prediction model is ; The first handover failure model is ; Among them, and are the intercepts respectively, and are the error terms respectively, represents the number of feature vectors before successful switching, represents the number of feature vectors before failed switching; The input variable of the prediction model 1 is a vector composed of signal-to-noise ratio and signal strength. , therefore, the conversion of switching to the prediction model 1 is: ; among which is the first weight matrix, used to represent the influence of signal-to-noise ratio and signal strength on the input variables, the ; where ; Similarly, the handover failure model one is converted to: ； The data within the sliding window before the handover time point seconds is input into Prediction Model One to predict whether a network handover will occur at the next moment; Set a handover threshold If it is determined that network handover will occur at the next moment; otherwise, network handover will not occur; If it is predicted that a network handover will occur at the next moment, then input the input variables of the handover prediction model one into the handover failure model one to predict the probability of successful handover; Set a probability threshold If it is determined that the handover will fail.

6. A method for intelligent coordination and adjustment of multi - frequency operator network parameters according to claim 4, characterized in that Pre-allocating resources before the predicted handover occurs to reduce the front-to-back time delay and reduce the handover failure rate includes the following steps: If it is determined that the handover will fail, then allocate resources before predicting the time of the handover; The resource allocation includes the following steps: Obtain the bandwidth resources and computing resources that can be pre-allocated through the network management system; Obtain the real-time network loads of the 4G and 5G networks through the network management system; if the 4G network load is heavy, give priority to reserving bandwidth for the 5G network to relieve the pressure on the 4G network.

7. A method for intelligent coordination and adjustment of multi-frequency operator network parameters according to claim 1, characterized in that If it is determined that the handover will fail, the handover threshold can also be dynamically adjusted. By increasing the handover threshold, the network handover is blocked, and the parameter data of the corresponding parameter template is corrected; The correction of the parameter data of the corresponding parameter template includes the following steps: Modify the power parameters of the devices in the parameter template to improve the network signal strength; Modify the number of starting devices in the parameter template to start more network base stations to improve the network signal coverage and signal strength.

8. A method for intelligent coordination and adjustment of multi-frequency operator network parameters according to claim 1, characterized in that Optimizing the parameters of the fitness function one and the fitness function two through the genetic algorithm to seek the optimal solution includes the following steps: Optimize the parameters of fitness function 1 through a genetic algorithm to find parameter combination 1 that minimizes ; Optimize the parameters of the fitness function two through the genetic algorithm to seek the parameter combination two that makes achieve the minimum, which is used to indicate that both the network error and the control input are controlled; Optimizing the parameters of the fitness function one and the fitness function two through the genetic algorithm to seek the optimal solution, and modifying the corresponding parameters of the corresponding type of scenario parameter template according to the optimal solution, including: Obtain the optimized parameter combination one ; Obtain the optimized parameter combination two ; Since , modify the switching threshold in the parameter template to adjust the total number of switching attempts; Due to , by adjusting the cell reselection priority and neighbor cell relationship configuration in the parameter template, the handover speed is improved and the handover delay is reduced.

9. An intelligent coordination and adjustment system for multi-frequency operator network parameters, characterized in that, The system is used to execute a multi-frequency operator network parameter intelligent collaboration and adjustment method described in any one of claims 1-8 above.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a multi-frequency operator network parameter intelligent collaboration and adjustment method described in any one of claims 1-8 above.

Images