Method and system for optimally configuring frequency resources of LTE (Long Term Evolution) network

Abstract

The invention discloses an LTE network frequency resource optimal configuration method and system, and relates to the technical field of communication, and the method comprises the steps: collecting network state data based on a network demand and a performance target, and carrying out the preprocessing; evaluating a current frequency resource allocation condition based on the processed network state data; determining an objective function of a dynamic multi-objective optimization algorithm based on the evaluated frequency resource allocation condition; calculating a new frequency resource configuration based on a dynamic multi-objective optimization algorithm of the determined objective function; new frequency resource configuration is implemented in an actual network environment, and network performance is continuously monitored. Through real-time acquisition and intelligent preprocessing of network state data, dynamic adjustment of a multi-target optimization algorithm and refined calculation and implementation of resource configuration, efficient optimal configuration of LTE network frequency resources is realized.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and system for optimizing the configuration of LTE network frequency resources. Background Art

[0002] With the rapid development of mobile Internet, LTE networks are facing unprecedented challenges of data traffic surge, especially in high-density user areas such as busy urban centers and large public venues. The limitations of traditional frequency resource allocation strategies are becoming increasingly prominent, manifested in uneven frequency resource allocation, fluctuations in user experience quality, delayed optimization strategy response, and lack of intelligent decision-making capabilities. These problems directly lead to low resource utilization efficiency and declining user satisfaction.

[0003] Traditional methods of frequency resource allocation have problems such as uneven resource allocation, fluctuating user experience, lagging optimization strategies, lack of intelligent decision-making, and resource waste. These problems not only affect network performance and service quality, but also hinder network operators from providing efficient and reliable services. Therefore, seeking smarter and more flexible resource allocation strategies has become the key to improving network efficiency and user experience. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for optimizing the configuration of LTE network frequency resources to solve the problem of uneven frequency allocation in the LTE network.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: (Detailed description of rights 1-8 in the first aspect)

[0007] In a first aspect, an embodiment of the present invention provides a method for optimizing the configuration of frequency resources in an LTE network, which includes collecting network status data and performing preprocessing based on network requirements and performance targets;

[0008] Based on the processed network status data, evaluate the current frequency resource allocation;

[0009] Determine the objective function of the dynamic multi-objective optimization algorithm based on the evaluated frequency resource allocation;

[0010] Calculate new frequency resource configuration based on a dynamic multi-objective optimization algorithm with a determined objective function;

[0011] Implement new frequency resource configurations in actual network environments and continuously monitor network performance.

[0012] As a preferred solution of the method for optimizing the configuration of LTE network frequency resources described in the present invention, the network status data includes the number of user terminal devices, channel quality indicators, reference signal reception power, reference signal reception quality, carrier-to-interference ratio and cell load information; and the preprocessing includes data cleaning, data conversion and feature engineering.

[0013] As a preferred solution of the method for optimizing the configuration of LTE network frequency resources of the present invention, the frequency resource allocation of each cell in the current LTE network is comprehensively evaluated based on the processed network status data. The specific steps are as follows:

[0014] Define the weight coefficient, where k = 1, 2, 3, 4, and its dynamic adjustment is expressed as,

[0015]

[0016] In the formula, w kj is the dynamically adjusted weight coefficient, x kj It is a user terminal device j The normalized value on index k, u k and σ k are the mean and standard deviation of index k on all user terminal devices;

[0017] Define a function to process cell load information, expressed as,

[0018]

[0019] Where, L i is the cell load information, L avg is the average load of cell i, L peak is the peak load, α and β are parameters that are dynamically adjusted according to network planning and objectives;

[0020] Based on the processed network status data, a comprehensive performance index model is established, which is expressed as:

[0021]

[0022] Where P i represents the comprehensive performance index of the ith cell, N i is the number of user terminal devices in cell i, CQI ij 、RSRP ij 、RSRQ ij and SINR ij are the channel quality index, reference signal received power, reference signal received quality and carrier-to-interference ratio of the jth user terminal in cell i, and w 1j 、w 2j 、w 3jand w 4j They are the weight coefficients of channel quality index, reference signal received power, reference signal received quality and carrier-to-interference ratio, L i is the load information of cell i, ε is a positive infinitesimal;

[0023] For each cell i in the network, calculate the corresponding P i value;

[0024] Create a vector whose length is equal to the total number of cells in the network;

[0025] The P of each cell i The values ​​are placed in the corresponding positions in the vector to generate an evaluation data set.

[0026] As a preferred solution of the method for optimizing the configuration of LTE network frequency resources of the present invention, the objective function of the dynamic multi-objective optimization algorithm is determined based on the evaluated frequency resource allocation, and the specific steps are as follows:

[0027] One of the goals of the dynamic multi-objective optimization algorithm is to improve the comprehensive performance index P of all cells. i The average value of , while minimizing the impact of cells with poor performance, the optimization objective function is expressed as,

[0028]

[0029] In the formula, G represents the optimization target value, N C Represents the total number of cells in the network, P i represents the comprehensive performance index of the ith cell;

[0030] Balance the overall performance of the network while minimizing P i The variance of , the second optimization function is expressed as,

[0031]

[0032] In the formula, G2 represents the second optimization target value, Represents the average value of comprehensive performance indicators of all cells, P i represents the comprehensive performance index of the ith cell;

[0033] Define a P-based i The soft constraint for P i For cells whose performance is below the threshold θ of the comprehensive performance index, a penalty function H is imposed i , H i represents the penalty coefficient of the ith cell. When P i When H is greater than or equal to the threshold value θ, i is 0, when P i When H is lower than the threshold value θ,i =(θ-P i ) 2 ;

[0034] When Pi ≥ θ, that is, the comprehensive performance index of the cell is higher than or equal to the set threshold, the penalty coefficient Hi = 0. This means that the performance of the cell has reached the expected level and no additional penalty is required.

[0035] When Pi<θ, that is, the comprehensive performance index of the cell is lower than the threshold, the penalty coefficient Hi=(θ-Pi). The penalty function here is to ensure that those cells below the threshold can be focused on and improved. The penalty coefficient increases as the gap with the threshold increases, which helps the optimization algorithm give priority to these poorly performing cells.

[0036] The total penalty function is the sum of all cell penalty functions, expressed as,

[0037]

[0038] Where H represents the sum of all cell penalty functions, N C Represents the total number of cells in the network, and Hi represents the penalty coefficient of the ith cell

[0039] Based on the multi-objective optimization algorithm NSGA-II, G, G2, H i and H form a dynamic multi-objective optimization algorithm with a determined objective function.

[0040] As a preferred solution of the method for optimizing the configuration of LTE network frequency resources of the present invention, wherein: based on the dynamic multi-objective optimization algorithm of the determined objective function, the new frequency resource configuration is calculated, and the specific steps are as follows:

[0041] Applying a dynamic multi-objective optimization algorithm with a determined objective function to the evaluation data set, launching an iterative search process;

[0042] Analyze the intermediate results, including monitoring the changing trend of fitness values, evaluating the convergence of dynamic multi-objective optimization algorithms, analyzing the distribution of non-dominated solution sets, and identifying potential Pareto frontier solutions;

[0043] Decode the output of the dynamic multi-objective optimization algorithm with the determined objective function and convert it into an actual executable frequency resource allocation plan;

[0044] According to the resource allocation scheme output by the dynamic multi-objective optimization algorithm, the new frequency resource configuration is accurately calculated, and the frequency resources are efficiently allocated according to the guidance of the optimization algorithm, which is expressed as,

[0045]

[0046] In the formula, Fi represents the new frequency resource configuration of the ith cell, N i represents the number of user terminal devices in cell i, A ij Indicates user terminal equipment j Frequency resource allocation ratio in cell i, R ij Indicates user terminal equipment j The number of frequency resource blocks in cell i.

[0047] As a preferred solution of the method for optimizing the configuration of LTE network frequency resources of the present invention, the specific steps of implementing the new frequency resource configuration in the actual network environment are as follows:

[0048] The frequency resource allocation scheme is first encoded into an algorithm-readable digital format, where each frequency resource block R ij With the distribution ratio A ij Corresponds to a specific value. This step ensures that the optimization algorithm can correctly parse and operate these configuration data;

[0049] Generate an XML configuration file containing the optimized frequency resource configuration, which lists in detail the user terminal equipment in each cell i j Frequency resource allocation ratio A ij and the number of resource blocks R ij ;

[0050] Deploy the configuration files to the network management platform, which is responsible for distributing updates to base stations BTS and related network elements;

[0051] The update process follows the software upgrade process provided by the network equipment manufacturer to ensure that the new configuration is installed correctly without interrupting existing services;

[0052] After receiving the update, BTS and related network elements immediately adjust the frequency resource allocation according to the new configuration file to ensure that all user terminal devices obtain the corresponding frequency resources according to the optimization plan.

[0053] As a preferred solution of the method for optimizing the configuration of LTE network frequency resources of the present invention, a continuous monitoring mechanism is established to collect network status data and analyze network performance changes. The specific steps are as follows:

[0054] After implementing the new frequency resource configuration, continuously monitor network performance, paying special attention to the comprehensive performance indicator P i changes;

[0055] If we find that the performance does not meet expectations, or that overload and resource waste occur, we will return to the optimization algorithm stage, adjust the parameters, and recalculate the new frequency resource configuration in order to achieve better network performance.

[0056] In a second aspect, the present invention provides a system based on LTE network frequency resource optimization configuration,

[0057] It includes data collection and preprocessing module, frequency resource evaluation module, dynamic multi-objective optimization algorithm construction module, frequency resource configuration calculation module and network implementation and performance monitoring module;

[0058] The data collection and preprocessing module is used to collect network status data and perform preprocessing based on network requirements and performance targets;

[0059] The frequency resource evaluation module is used to evaluate the current frequency resource allocation based on the processed network status data;

[0060] The dynamic multi-objective optimization algorithm construction module determines the objective function of the dynamic multi-objective optimization algorithm based on the evaluated frequency resource allocation situation;

[0061] The frequency resource configuration calculation module is used to calculate a new frequency resource configuration based on a dynamic multi-objective optimization algorithm with a determined objective function;

[0062] The network implementation and performance monitoring module is used to implement new frequency resource configuration in an actual network environment and continuously monitor network performance.

[0063] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for optimizing and configuring frequency resources of an LTE network as described in the first aspect of the present invention is implemented.

[0064] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for optimizing and configuring frequency resources of an LTE network as described in the first aspect of the present invention is implemented.

[0065] The beneficial effects of the present invention are: enhancing algorithm robustness through data preprocessing, evaluating the current resource allocation status to identify bottlenecks, using a dynamic multi-objective optimization algorithm to intelligently allocate network resources, calculating and implementing optimal configuration to significantly improve performance and user experience, while continuously monitoring the network to ensure service quality, and realizing efficient adaptive resource management of LTE networks in high-density user environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0067] Figure 1 This is a flowchart of the method for optimizing the configuration of LTE network frequency resources in Example 1.

[0068] Figure 2 This is the penalty selection decision diagram in Example 1. DETAILED DESCRIPTION

[0069] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0070] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0071] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0072] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for optimizing the configuration of LTE network frequency resources, comprising the following steps:

[0073] S1. Based on network requirements and performance goals, collect network status data and perform preprocessing, including the following steps:

[0074] Network status data includes the number of user terminal devices, channel quality indicators, reference signal reception power, reference signal reception quality, carrier-to-interference ratio and cell load information; preprocessing includes data cleaning (removing outliers, filling missing values, and correcting erroneous data), data conversion (standardizing indicator values ​​to ensure that data of different dimensions are compared on the same scale) and feature engineering (creating new features to enhance model performance).

[0075] Network status data is key information for the operation of wireless communication systems. It covers various performance indicators of the network and is used to evaluate and optimize network quality. The following is a supplementary explanation of network status data:

[0076] Channel Quality Indicator (CQI): reflects the channel condition of the wireless environment in which the user terminal equipment is located. It is used to determine the downlink transmission mode and modulation and coding scheme (MCS), thereby affecting the data rate and bit error rate.

[0077] Reference Signal Received Power (RSRP): measures the linear average power received from the reference signal of a cell. It is used by user terminal equipment for cell selection / reselection and handover decisions. It is also an important parameter for evaluating network coverage.

[0078] Reference Signal Received Quality (RSRQ): is the ratio of RSRP to the total received power. It is used to evaluate signal quality and is an important indicator for determining the quality of the link between a user terminal device and a base station.

[0079] Signal-to-Interference-plus-Noise Ratio (SINR): indicates the ratio of signal strength to interference and noise. The higher the SINR, the better the signal quality and the higher the data transmission rate.

[0080] Cell load information L (Cell Load Information): includes the number of users in the cell, data traffic, number of occupied resource blocks, etc., which is used to evaluate the load status of the cell and help with resource scheduling and load balancing.

[0081] Preprocessing refers to a series of cleaning and transformation operations on raw data before data analysis and modeling, with the aim of improving data quality and the effectiveness of analysis. The following is a supplementary explanation of preprocessing:

[0082] Remove outliers: Detect and exclude measurements that significantly deviate from the normal range, which may be caused by equipment failure, signal interference or other abnormal events. The presence of outliers may seriously affect the results of data analysis.

[0083] Handling missing data: Data records may contain missing measurements, which may be due to equipment failure or data transmission problems. Methods for handling missing data include deleting records with missing values, using statistical methods to fill missing values ​​(such as mean, median, interpolation), or using machine learning methods to predict missing values.

[0084] Correcting erroneous data: Correcting inaccurate data due to measurement errors, improper equipment calibration, or data entry errors. This may involve applying correction factors or reprocessing the original signal to obtain the correct measurement value.

[0085] Preprocessing is an integral part of the data analysis process, which ensures the accuracy and reliability of subsequent analysis and decision-making processes.

[0086] S2. Based on the processed network status data, evaluating the current frequency resource allocation, including the following steps:

[0087] Based on the processed data, comprehensively evaluate the frequency resource allocation of each cell in the current LTE network. The specific steps are as follows:

[0088] Weight coefficient w kj The dynamic adjustment of (k=1,2,3,4) is expressed as,

[0089]

[0090] In the formula, w kj is the weight coefficient used to quantify the user terminal equipment j The relative importance of indicator k, x kj It is a user terminal device j The standardized value on the indicator k. Standardization is to eliminate the impact of different dimensions between indicators and make them comparable on the same scale. k and σ k They are the average value and standard deviation of indicator k on all user terminal devices. The average value is used to centralize the data and reflect the average level of the indicator. The standard deviation measures the discreteness of the data and is used to determine the decay rate of the weight coefficient.

[0091] Cell load information L i Processed by the following function, it is expressed as,

[0092]

[0093] Where, L avg is the average load of cell i, reflecting the resource occupancy of the cell under normal working conditions. peak is the peak load, which reflects the resource occupancy of the cell during high load periods. α and β are parameters that are dynamically adjusted according to network planning and objectives. They are used to balance the importance of average load and peak load and can be obtained through historical data analysis.

[0094] Based on the processed network status data, a comprehensive performance indicator model is designed, which is expressed as:

[0095]

[0096] Where P i represents the comprehensive performance index of the ith cell, taking into account the resource allocation efficiency and load of the cell. i is the number of user terminals in cell i, indicating the user density of the cell, CQI ij 、RSRP ij 、RSRQ ij and SINR ij They are the channel quality index, reference signal received power, reference signal received quality and carrier-to-interference ratio of the jth user terminal in cell i, which are key indicators of network performance. 1j 、w 2j 、w 3j and w 4j They are the weight coefficients of channel quality index, reference signal received power, reference signal received quality and carrier-to-interference ratio, which are used to highlight the contribution of user terminal equipment in different performance indicators. i is the load information of cell i, and ε is a positive infinitesimal quantity used to avoid the situation where the denominator is zero and ensure the numerical stability of the formula.

[0097] For each cell i in the network, calculate the corresponding Pi value;

[0098] Create a vector whose length is equal to the total number of cells in the network;

[0099] Put the Pi value of each cell into the corresponding position in the vector to generate an evaluation data set.

[0100] S3. Based on the evaluated frequency resource allocation, determining the objective function of the dynamic multi-objective optimization algorithm includes the following steps:

[0101] Dynamic Multi-Objective Optimization Algorithms (DMOAs) are a class of algorithms designed to handle multi-objective optimization problems that change over time. In traditional multi-objective optimization, the objective function and constraints are considered static and unchanging, but in many real-world applications, such as economic systems, ecological environment, and traffic management, the objectives and constraints may change dynamically over time due to external factors. Dynamic multi-objective optimization algorithms aim to find solutions that can continuously optimize multiple objectives in a changing environment.

[0102] One of the goals of the dynamic multi-objective optimization algorithm is to improve the comprehensive performance index P of all cells. i The average value of , while minimizing the impact of cells with poor performance, the optimization objective function is expressed as,

[0103]

[0104] In the formula, G represents the optimization objective function, which aims to maximize the average value of the comprehensive performance indicators of all cells, and N C Represents the total number of cells in the network, used for calculating the standardized average value, P i It represents the comprehensive performance index of the ith cell, reflecting the performance of the cell.

[0105] Balance the overall performance of the network while minimizing P i The variance of , the second optimization function is expressed as,

[0106]

[0107] Where G2 represents the second optimization objective function, which aims to minimize the comprehensive performance index P of all cells. i The variance of It represents the average value of the comprehensive performance indicators of all cells and is used to calculate the deviation of each cell performance indicator from the average value. i Represents the comprehensive performance index of the ith cell.

[0108] Define a P-based i The soft constraint for P i For cells whose performance is below the threshold θ of the comprehensive performance index, a penalty function H is imposed i , H i represents the penalty coefficient of the ith cell, and the threshold θ of the penalty function is set to the comprehensive performance index P of all cells. i The mean plus 20% standard deviation, when P i When H is greater than or equal to the threshold value θ, i is 0, when P i When H is lower than the threshold value θ, i =(θ-P i ) 2 ;

[0109] The total penalty function is the sum of all cell penalty functions, expressed as,

[0110]

[0111] Where H is the sum of all cell penalty functions, reflecting the negative impact of cells below the performance standard on the overall network performance. C It represents the total number of cells in the network and is used to traverse all cells to calculate the total penalty. Hi represents the penalty coefficient of the ith cell and is used to calculate the total penalty function.

[0112] G and G2 are independent goals. These two goals are related but not exactly the same. Minimizing the impact of cells with poor performance is achieved by maximizing the average value of the comprehensive performance indicators of all cells, that is, improving the performance of cells with poor performance to achieve overall performance improvement. Balancing the overall performance of the network while minimizing the variance of Pi ensures that the performance of the entire network is more uniform and reduces performance fluctuations. The former focuses on improving the cells with the worst performance, while the latter focuses on reducing the performance differences between cells.

[0113] The role of H is to make the algorithm tend to find solutions that can reduce or eliminate cells with poor performance during the optimization process, thereby improving the overall service quality and user experience of the network.

[0114] They are directly used as independent objectives in the optimization algorithm. In NSGA-II, each individual (i.e., a frequency resource allocation scheme) is evaluated based on all objectives, rather than a single objective. The algorithm generates a new population in each iteration, and the individuals in this population are selected based on non-dominated sorting and crowding distance.

[0115] S4. Calculate a new frequency resource configuration based on a dynamic multi-objective optimization algorithm of a determined objective function, including the following steps:

[0116] A dynamic multi-objective optimization algorithm with a determined objective function is applied to the evaluation data set, and the iterative search process is started. The algorithm parameters such as population size (defines the number of solutions in each generation of the algorithm. A larger population helps to improve the diversity of solutions and the global search ability of the algorithm), number of iterations (determines the total number of rounds of the algorithm run. More iterations usually mean more sophisticated exploration of the solution space), crossover probability (controls the possibility of two individuals exchanging gene fragments. A high crossover probability promotes the mixing of genetic information and helps to generate new solutions), and mutation probability (determines the probability of random changes in individual genes. Mutation helps maintain population diversity and avoid local optimality) are set.

[0117] Initialize the population and generate a set of random frequency resource configuration schemes as the starting point of the algorithm.

[0118] Based on the advanced multi-objective optimization solver NSGA-II (a well-known multi-objective optimization solver that can effectively handle multiple conflicting objectives), the iterative search process is started. In each iteration, crossover and mutation operations are performed to generate the next generation of populations. The fitness value of each individual (frequency resource allocation scheme) in the new generation of populations is calculated. Here, the fitness value is based on P i and penalty function H i . Apply non-dominated sorting and crowding distance strategies to screen out non-dominated solution sets.

[0119] During the iteration process, according to the convergence speed of the algorithm and the quality of the intermediate results, the algorithm parameters: population size, crossover probability and mutation probability are adjusted in a timely manner to accelerate the convergence of the algorithm or improve the diversity of solutions.

[0120] Analyze the intermediate results, including monitoring the changing trend of fitness values, evaluating the convergence of the algorithm, analyzing the distribution of non-dominated solution sets, and identifying potential Pareto frontier solutions.

[0121] The output of the decoding optimization algorithm is converted into an actual executable frequency resource allocation plan.

[0122] According to the resource allocation scheme output by the optimization algorithm, the new frequency resource configuration is accurately calculated, and the frequency resources are efficiently allocated according to the guidance of the optimization algorithm, which is expressed as,

[0123]

[0124] In the formula, F i Represents the new frequency resource configuration of the i-th cell, representing the total frequency resources allocated to cell i after optimization, N i A represents the number of user terminals in cell i, indicating how many user terminals in the cell need to be served, and directly affects the fair allocation of resources. ij Indicates user terminal equipment j The frequency resource allocation ratio in cell i reflects the needs and priorities of user terminal equipment. ij Indicates user terminal equipment j The number of frequency resource blocks in cell i, where a resource block can be part of the spectrum.

[0125] Based on the dynamic multi-objective optimization algorithm, calculate the new frequency resource configuration. The specific steps are as follows:

[0126] The frequency resource allocation scheme is first encoded into an algorithm-readable digital format, where each frequency resource block R ij With the distribution ratio A ij This step ensures that the optimization algorithm can correctly parse and operate these configuration data.

[0127] Generates XML or YAML configuration files containing optimized frequency resource configurations, which list in detail the user terminal devices in each cell i j Frequency resource allocation ratio A ij and the number of resource blocks R ij .

[0128] S5. Implement new frequency resource configuration in the actual network environment and continuously monitor network performance, including the following steps:

[0129] The configuration files are deployed to the network management platform, which is responsible for distributing updates to each base station BTS (Base Transceiver Station) and related network elements.

[0130] The update process follows the software upgrade process provided by the network equipment manufacturer to ensure that the new configuration is installed correctly without interrupting existing services.

[0131] After receiving the update, BTS and related network elements immediately adjust the frequency resource allocation according to the new configuration file to ensure that all user terminal devices obtain the corresponding frequency resources according to the optimization plan.

[0132] Establish a continuous monitoring mechanism to collect network status data and analyze network performance changes. The specific steps are as follows:

[0133] Based on the latest network status data, the comprehensive performance index P of each cell is calculated in real time i .

[0134] Compare with historical data and analyze P i to identify performance improvement or decline.

[0135] Record and analyze cell load to check for signs of overload or underutilization of resources.

[0136] Set performance alarm thresholds. i When the performance falls below the preset lower limit or exceeds the expected fluctuation range, an alarm is automatically triggered.

[0137] Implement resource waste and overload detection mechanisms to monitor whether there is uneven allocation or overuse of resources.

[0138] Establish a performance degradation early warning system to promptly notify the network operation and maintenance team of abnormal changes in network performance.

[0139] When the alarm system detects P i When the drop exceeds the preset threshold, the optimization algorithm re-run process is automatically started.

[0140] According to the performance analysis results, adjust the parameters of the optimization algorithm, such as population size, number of iterations, crossover probability, and mutation probability.

[0141] If it is found that resources are not allocated properly or the network performance does not meet expectations, a new frequency resource configuration plan is recalculated.

[0142] Based on the adjusted parameters and optimization objectives, the multi-objective optimization algorithm is re-executed to find an improved frequency resource configuration.

[0143] Evaluate the effect of new configuration on P ito ensure that the new solution can improve or at least maintain the current network performance level.

[0144] Verify the optimization results to confirm that the new configuration can solve problems such as overload and resource waste. Implement new configuration and verify the effect:

[0145] The optimized frequency resource configuration scheme is converted into an executable configuration file, such as an XML or YAML format.

[0146] Deploy updates through the network management platform to ensure that all base stations and related network elements are synchronized with the new configuration.

[0147] After implementation, continue to monitor network performance to verify whether the optimization measures have effectively improved P i and other key performance indicators.

[0148] This embodiment also provides a system based on LTE network frequency resource optimization configuration, including a data collection and preprocessing module, a frequency resource evaluation module, a dynamic multi-objective optimization algorithm construction module, a frequency resource configuration calculation module and a network implementation and performance monitoring module;

[0149] The data collection and preprocessing module is used to collect network status data and perform preprocessing based on network requirements and performance targets;

[0150] The frequency resource evaluation module is used to evaluate the current frequency resource allocation based on the processed network status data;

[0151] The dynamic multi-objective optimization algorithm building module determines the objective function of the dynamic multi-objective optimization algorithm based on the evaluated frequency resource allocation;

[0152] The frequency resource configuration calculation module is used to calculate a new frequency resource configuration based on a dynamic multi-objective optimization algorithm with a determined objective function;

[0153] The network implementation and performance monitoring module is used to implement new frequency resource configurations in the actual network environment and continuously monitor network performance.

[0154] This embodiment also provides a computer device, which is applicable to the method for optimizing the configuration of LTE network frequency resources, and includes: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method for optimizing the configuration of LTE network frequency resources as proposed in the above embodiment.

[0155] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0156] The present embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing the optimal configuration of LTE network frequency resources as proposed in the above embodiment is realized. The storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EEPROM), etc.

[0157] Programmable Read Only Memory, referred to as EPROM), Programmable Read-Only Memory (Programmable Red-Only Memory, referred to as PROM), Read-Only Memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0158] In summary, the present invention collects network status data and performs preprocessing to remove erroneous information, ensure the accuracy of subsequent analysis, and improve the quality of frequency resource allocation decisions; by defining weight coefficients and cell load processing functions, a comprehensive performance indicator model is established to make resource allocation more fair and reasonable, and avoid excessive congestion in some areas while idle resources in other areas; by setting optimization objective functions and soft constraints, the dynamic multi-objective optimization algorithm not only improves the overall network performance, but also reduces performance fluctuations, ensuring network stability and user perceived quality; using the NSGA-II algorithm for iterative search, the frequency resource configuration scheme obtained can more accurately meet network requirements while enhancing network adaptability and flexibility; deploying the optimized configuration in the actual network ensures efficient resource utilization, while the continuous monitoring mechanism can promptly discover and solve the problem of network performance degradation, forming a closed-loop feedback, and continuously improving network performance.

[0159] Example 2

[0160] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of the method for optimizing the configuration of LTE network frequency resources are provided.

[0161] In order to verify the innovation and advantages of the invention, we designed an experiment that simulated an LTE network environment with six different cells. Network status data such as the number of user terminal devices, CQI, RSRP, RSRQ, SINR and cell load information L in each cell were carefully set to reflect different network conditions and user behaviors. The experiment was divided into two stages: the first stage adopted traditional static resource configuration, and the second stage implemented the dynamic frequency resource configuration optimization method of the present invention.

[0162] In the first phase, the network operates under the default static frequency resource configuration, that is, frequency resources are evenly allocated to all cells. In the second phase, we collect and preprocess network status data according to the method of the present invention, then evaluate the frequency resource allocation based on the processed data, design a comprehensive performance indicator model, and construct a dynamic multi-objective optimization algorithm. Finally, we calculate the new frequency resource configuration and implement it in the actual network environment.

[0163] The details are shown in Table 1:

[0164] Table 1 Experimental record of implementing dynamic frequency resource configuration optimization method

[0165]

[0166] Before the optimization, the comprehensive performance index (Pi) of the cell was generally low, reflecting that the frequency resource allocation failed to fully consider the network status and user terminal equipment requirements. After the optimization, the comprehensive performance index of the cell was significantly improved, especially in areas with dense user terminal equipment, such as cell 4, where the comprehensive performance index increased from 0.7 before the optimization to 0.8, reflecting the efficient use of frequency resources and better satisfaction of user terminal equipment requirements.

[0167] By comparing the frequency resource allocation before and after optimization, we can observe that resources are reallocated to better match the actual needs of each cell. For example, since cell 4 has the largest number of user terminal devices, its frequency resource allocation increased from 20 before optimization to 30, which directly led to the improvement of the comprehensive performance indicators of cell 4. On the contrary, in cell 3, which has a small number of user terminal devices, the frequency resource allocation decreased from 15 to 10, because the reduced resources were reallocated to cells with greater needs, such as cell 4.

[0168] In addition, the overall performance of the network has been significantly improved after optimization. Before optimization, the average value of the comprehensive performance index of all cells was 0.7, while after optimization, this average value rose to 0.75. This shows that the dynamic frequency resource configuration method of the present invention not only improves the performance of a single cell, but also improves the efficiency and user experience of the entire network.

[0169] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing the configuration of LTE network frequency resources, characterized in that: include, Collect network status data and perform preprocessing based on network requirements and performance goals; Based on the processed network status data, evaluate the current frequency resource allocation; Determine the objective function of the dynamic multi-objective optimization algorithm based on the evaluated frequency resource allocation; Calculate new frequency resource configuration based on a dynamic multi-objective optimization algorithm with a determined objective function; Implement new frequency resource configurations in actual network environments and continuously monitor network performance.

2. The method for optimizing the configuration of LTE network frequency resources according to claim 1, characterized in that: The network status data includes the number of user terminal devices, channel quality indicators, reference signal reception power, reference signal reception quality, carrier-to-interference ratio and cell load information; The preprocessing includes data cleaning, data conversion and feature engineering.

3. The method for optimizing the configuration of LTE network frequency resources as claimed in claim 2, characterized in that: Based on the processed network status data, comprehensively evaluate the frequency resource allocation of each cell in the current LTE network. The specific steps are as follows: Define the weight coefficient, where k = 1, 2, 3, 4, and its dynamic adjustment is expressed as, In the formula, w kj is the dynamically adjusted weight coefficient, x kj It is a user terminal device j The normalized value on index k, u k and σ k are the mean and standard deviation of index k on all user terminal devices; Define a function to process cell load information, expressed as, Where, L i is the cell load information, L avg is the average load of cell i, L peak is the peak load, α and β are parameters that are dynamically adjusted according to network planning and objectives; Based on the processed network status data, a comprehensive performance index model is established, which is expressed as: Where P i represents the comprehensive performance index of the ith cell, N i is the number of user terminal devices in cell i, CQI ij 、RSRP ij 、RSRQ ij and SINR ij are the channel quality index, reference signal received power, reference signal received quality and carrier-to-interference ratio of the jth user terminal in cell i, and w 1j 、w 2j 、w 3j and w 4j They are the weight coefficients of channel quality index, reference signal received power, reference signal received quality and carrier-to-interference ratio, L i is the load information of cell i, ε is a positive infinitesimal; For each cell i in the network, calculate the corresponding P i value; Create a vector whose length is equal to the total number of cells in the network; The P of each cell i The values ​​are placed in the corresponding positions in the vector to generate an evaluation data set.

4. The method for optimizing the configuration of LTE network frequency resources as claimed in claim 3, characterized in that: Based on the evaluated frequency resource allocation, determine the objective function of the dynamic multi-objective optimization algorithm. The specific steps are as follows: One of the goals of the dynamic multi-objective optimization algorithm is to improve the comprehensive performance index P of all cells. i The average value of , while minimizing the impact of cells with poor performance, the optimization objective function is expressed as, In the formula, G represents the optimization target value, N C Represents the total number of cells in the network, P i represents the comprehensive performance index of the ith cell; Balance the overall performance of the network while minimizing P i The variance of , the second optimization function is expressed as, In the formula, G2 represents the second optimization target value, Represents the average value of comprehensive performance indicators of all cells, P i represents the comprehensive performance index of the ith cell; Define a P-based i The soft constraint for P i For cells whose performance is below the threshold θ of the comprehensive performance index, a penalty function H is imposed i , H i represents the penalty coefficient of the ith cell. When P i When H is greater than or equal to the threshold value θ, i is 0, when P i When H is lower than the threshold value θ, i =(θ-P i ) 2 ; The total penalty function is the sum of all cell penalty functions, expressed as, Where H represents the sum of all cell penalty functions, N C represents the total number of cells in the network, Hi represents the penalty coefficient of the ith cell; Based on the multi-objective optimization algorithm NSGA-II, G and G2 are used as the objectives of the multi-objective optimization algorithm, H i and H are integrated as soft constraints to form a dynamic multi-objective optimization algorithm with a determined objective function.

5. The method for optimizing the configuration of LTE network frequency resources as claimed in claim 4, characterized in that: Based on the dynamic multi-objective optimization algorithm with the determined objective function, the new frequency resource configuration is calculated. The specific steps are as follows: Applying a dynamic multi-objective optimization algorithm with a determined objective function to the evaluation data set, launching an iterative search process; Analyze the intermediate results, including monitoring the changing trend of fitness values, evaluating the convergence of dynamic multi-objective optimization algorithms, analyzing the distribution of non-dominated solution sets, and identifying potential Pareto frontier solutions; Decode the output of the dynamic multi-objective optimization algorithm with the determined objective function and convert it into an actual executable frequency resource allocation plan; According to the resource allocation scheme output by the dynamic multi-objective optimization algorithm, the new frequency resource configuration is accurately calculated, and the frequency resources are efficiently allocated according to the guidance of the optimization algorithm, which is expressed as, In the formula, F i represents the new frequency resource configuration of the ith cell, N i represents the number of user terminal devices in cell i, A ij Indicates user terminal equipment j Frequency resource allocation ratio in cell i, R ij Indicates user terminal equipment j The number of frequency resource blocks in cell i.

6. The method for optimizing the configuration of LTE network frequency resources as claimed in claim 5, characterized in that: The specific steps of implementing the new frequency resource configuration in the actual network environment are as follows: The frequency resource allocation scheme is first encoded into an algorithm-readable digital format, where each frequency resource block R ij With the distribution ratio A ij corresponds to a specific value; Generate an XML configuration file containing the optimized frequency resource configuration, which lists in detail the user terminal equipment in each cell i j Frequency resource allocation ratio and number of resource blocks; Deploy the configuration files to the network management platform, which is responsible for distributing updates to base stations BTS and related network elements; The update process follows the software upgrade process provided by the network equipment manufacturer; After receiving the update, the BTS and related network elements immediately adjust the frequency resource allocation to the user terminal equipment according to the new configuration file.

7. The method for optimizing the configuration of LTE network frequency resources as claimed in claim 6, characterized in that: Establish a continuous monitoring mechanism to collect network status data and analyze network performance changes. The specific steps are as follows: After implementing new frequency resource allocation, continuously monitor changes in comprehensive performance indicators; If we find that the performance does not meet expectations, or that overload and resource waste occur, we will return to the optimization algorithm stage, adjust the parameters, and recalculate the new frequency resource configuration in order to achieve better network performance.

8. A mobile network control system, based on the system for optimizing the configuration of LTE network frequency resources according to any one of claims 1 to 7, characterized in that: It includes data collection and preprocessing module, frequency resource evaluation module, dynamic multi-objective optimization algorithm construction module, frequency resource configuration calculation module and network implementation and performance monitoring module; The data collection and preprocessing module is used to collect network status data and perform preprocessing based on network requirements and performance targets; The frequency resource evaluation module is used to evaluate the current frequency resource allocation based on the processed network status data; The dynamic multi-objective optimization algorithm construction module determines the objective function of the dynamic multi-objective optimization algorithm based on the evaluated frequency resource allocation situation; The frequency resource configuration calculation module is used to calculate a new frequency resource configuration based on a dynamic multi-objective optimization algorithm with a determined objective function; The network implementation and performance monitoring module is used to implement new frequency resource configuration in an actual network environment and continuously monitor network performance.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for optimizing the configuration of LTE network frequency resources are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing the configuration of LTE network frequency resources are implemented as described in any one of claims 1 to 7.

Images