Method and system for adaptive optimization configuration of multi-source signal interference parameters

Abstract

The present invention provides a method and system for adaptively optimizing the configuration of multi-source signal interference parameters, relating to the field of signal interference technology. The method involves constructing an interference effectiveness evaluation model by acquiring historical interference effectiveness data and real-time parameter status data of the signal interference source to be optimized, employing an adaptive genetic algorithm to optimize resource allocation according to a fitness function, and performing constraint verification and fitness correction based on a dynamic resource constraint matrix and an adaptive penalty function. The present invention can improve the allocation efficiency and interference effectiveness of signal interference resources and reduce system resource consumption.

Description

Technical Field

[0001] The present invention relates to signal interference technology, and in particular to a method and system for adaptively optimizing configuration of multi-source signal interference parameters. Background Art

[0002] In modern electronic warfare and information warfare, signal jamming technology, as an important countermeasure, has been widely used in both military and civilian fields. As the electromagnetic environment becomes increasingly complex, multi-source signal jamming systems need to achieve optimal jamming effects on target signals within limited resources. Therefore, how to rationally allocate jamming resources and optimize jamming effectiveness has become a key research topic.

[0003] Traditional signal jamming parameter configuration methods rely primarily on empirical models or fixed algorithms, which are unable to achieve flexible resource allocation in complex and changing electromagnetic environments. With the advancement of electronic countermeasures technology, especially in multi-source signal jamming scenarios, multiple factors need to be considered, including the synergistic effects between signal sources, resource constraints, and real-time jamming effectiveness evaluation.

[0004] The existing technology has the following deficiencies in optimizing the configuration of signal interference parameters:

[0005] First, most existing interference parameter configuration methods adopt static optimization strategies, which cannot be adaptively adjusted according to real-time interference effectiveness and environmental changes, resulting in unstable interference effects and low resource utilization in complex and changeable electromagnetic environments.

[0006] Secondly, when dealing with resource allocation problems caused by multi-source signal interference, traditional optimization algorithms often find it difficult to effectively balance the relationship between global search and local optimization. They are prone to falling into local optimal solutions and are unable to obtain the best interference configuration plan. Especially when resource constraints are relatively strict, the practicality of the optimization results is limited.

[0007] Finally, most existing jamming effectiveness evaluation models are based on theoretical analysis or simplified assumptions, lacking full utilization of historical jamming effectiveness data, making it difficult to accurately evaluate the jamming effect. This leads to deviations between resource allocation plans and actual needs, making it impossible to achieve precise jamming and efficient confrontation. Summary of the Invention

[0008] The embodiments of the present invention provide a method and system for adaptively optimizing and configuring multi-source signal interference parameters, which can solve the problems in the prior art.

[0009] A first aspect of an embodiment of the present invention provides a method for adaptively optimizing and configuring multi-source signal interference parameters, comprising:

[0010] Acquire historical interference effectiveness data and real-time interference parameter status data of the signal interference source to be optimized, and construct an interference effectiveness evaluation model based on the historical interference effectiveness data;

[0011] Adopting an adaptive genetic algorithm to iteratively optimize the resource allocation scheme of the signal interference source to be optimized, calculating the fitness value of the iterative population according to a preset fitness function, and dynamically adjusting the crossover probability and mutation probability of the adaptive genetic algorithm based on the fitness value;

[0012] constructing a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and performing constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function;

[0013] Calculating the constraint violation degree of individuals in the population, determining a penalty factor according to the constraint violation degree, adaptively adjusting the individual fitness value by the penalty factor, and updating the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree;

[0014] Based on the constraint parameters, it is determined whether the number of iterations reaches a preset iteration threshold, and an optimal resource allocation solution is output when the condition is met.

[0015] Constructing an interference effectiveness evaluation model based on the historical interference effectiveness data includes:

[0016] Extracting interference effectiveness evaluation features based on the historical interference effectiveness data, establishing an influence relationship between the historical power allocation data and the historical frequency band coverage data of the interference source and the historical interference gain data, forming an interference effectiveness evaluation matrix, and establishing an effectiveness evaluation function for each interference source based on the interference effectiveness evaluation matrix, wherein the effectiveness evaluation function is used to predict the interference gain under different power allocation and frequency band coverage;

[0017] An interference effectiveness evaluation structure is constructed according to the effectiveness evaluation function, and evaluation parameters of the interference effectiveness evaluation structure are optimized and adjusted using the historical interference effectiveness data to generate an interference effectiveness evaluation model that meets a preset evaluation accuracy.

[0018] Adopting an adaptive genetic algorithm to iteratively optimize the resource allocation scheme of the signal interference source to be optimized, calculating the fitness value of the iterative population according to a preset fitness function, and dynamically adjusting the crossover probability and mutation probability of the genetic algorithm based on the fitness value includes:

[0019] Establishing a fitness function for the resource allocation scheme of the signal interference source to be optimized, encoding the resource allocation scheme of the signal interference source to be optimized according to the fitness function to obtain an initial population, calculating the fitness value of each individual in the initial population, and calculating the maximum fitness value and the average fitness value of the population based on the fitness value of each individual;

[0020] Dynamically adjust the crossover probability according to the difference between the fitness value of the individual to be crossed and the maximum fitness value of the population and the average fitness value of the population; when the fitness value of the individual to be crossed is greater than the average fitness value of the population, adopt a dynamically compressed crossover probability; when the fitness value of the individual to be crossed is less than or equal to the average fitness value of the population, adopt a fixed maintained crossover probability;

[0021] The mutation probability is dynamically adjusted according to the difference between the fitness value of the individual to be mutated and the maximum fitness value of the population and the average fitness value of the population. When the fitness value of the individual to be mutated is less than the maximum fitness value of the population, a dynamically compressed mutation probability is adopted. When the fitness value of the individual to be mutated is greater than or equal to the average fitness value of the population, a fixed maintained mutation probability is adopted.

[0022] Establishing a fitness function for the resource allocation scheme of the signal interference source to be optimized, and encoding the resource allocation scheme of the signal interference source to be optimized according to the fitness function to obtain an initial population includes:

[0023] Establishing a fitness function for a resource allocation scheme for the signal interference source to be optimized based on the interference effectiveness, resource constraints, and performance targets of the signal interference source to be optimized, wherein the fitness function includes an interference effectiveness term and a resource constraint penalty term;

[0024] The resource allocation scheme of the signal interference source to be optimized is real-number encoded according to interference power, frequency bandwidth and time allocation to generate an initial population with a preset size.

[0025] Constructing a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and performing constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function include:

[0026] Obtaining transmit power, antenna gain, frequency band, and beam pointing angle of multiple interference sources, constructing a power constraint matrix element based on a ratio of the transmit power to the antenna gain, constructing a frequency constraint matrix element based on an overlap integral of the frequency band, and constructing a space constraint matrix element based on a deviation of the beam pointing angle;

[0027] Combining the power constraint matrix elements, the frequency constraint matrix elements, and the space constraint matrix elements to form a dynamic resource constraint matrix, wherein the dynamic resource constraint matrix is used to characterize the power constraint relationship, the frequency constraint relationship, and the space constraint relationship between interference sources;

[0028] Obtaining an expected interference efficiency value and a current interference efficiency value, constructing an efficiency penalty term based on a square difference between the expected interference efficiency value and the current interference efficiency value, and multiplying the efficiency penalty term by a dynamic weight to obtain a comprehensive efficiency penalty value;

[0029] Calculating a constraint penalty item based on the dynamic resource constraint matrix, wherein the constraint penalty item is obtained by applying constraint type weights to the power constraint matrix elements, the frequency constraint matrix elements, and the space constraint matrix elements respectively;

[0030] The power violation, frequency violation and space violation are calculated according to the dynamic resource constraint matrix; the original fitness value is corrected according to the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value, and the efficiency-corrected fitness value is corrected based on the power violation, the frequency violation and the space violation to obtain a final fitness value.

[0031] Calculating the power violation, frequency violation, and space violation according to the dynamic resource constraint matrix; correcting the original fitness value according to the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value; and correcting the efficiency-corrected fitness value based on the power violation, the frequency violation, and the space violation to obtain a final fitness value includes:

[0032] The dynamic resource constraint matrix includes a power constraint matrix, a frequency constraint matrix, and a space constraint matrix; obtaining node power, frequency set, and space distance parameters, and obtaining an original power violation based on the power constraint matrix by summing the product of the square of the deviation of the node power ratio and the power constraint matrix element and the dynamic weight;

[0033] Based on the frequency constraint matrix, the original frequency violation is calculated by summing the ratio of the intersection and union of the frequency sets, the square of the deviation of the frequency constraint matrix elements, and the frequency weight; based on the spatial constraint matrix, the original spatial violation is calculated by summing the ratio of the spatial distance to the maximum distance, the square of the deviation of the spatial constraint matrix elements, and the spatial weight; and the original power violation, the original frequency violation, and the original spatial violation are subjected to noise filtering to obtain a filtered violation;

[0034] The original fitness value is corrected using the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value, the filtering violation is weightedly fused based on the efficiency-corrected fitness value to obtain an overall violation, and the efficiency-corrected fitness value is corrected using the overall violation to obtain a final fitness value, which is calculated as the difference between the efficiency-corrected fitness value and the product term of the overall violation.

[0035] Calculating the constraint violation degree of an individual in the population, determining a penalty factor according to the constraint violation degree, adaptively adjusting the fitness value of the individual using the penalty factor, and updating the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree include:

[0036] Calculating a constraint violation degree for each interference source, where the constraint violation degree is obtained by summing the product of the ratio of the product of the transmit power and the antenna gain and the square of the deviation of the power constraint threshold and the dynamic weight;

[0037] Constructing an individual penalty factor based on the constraint violation degree, wherein the individual penalty factor is calculated by an exponential function of a basic penalty coefficient and a weighted sum of the violation degrees, wherein the weighted sum of the violation degrees is weighted by the constraint type weight;

[0038] Calculating a group collaborative penalty factor based on the individual penalty factors, wherein the group collaborative penalty factor is obtained by a weighted sum of the mean of the individual penalty factors and the violation variance, and the violation variance is multiplied by a smoothing coefficient;

[0039] The gradient of the constraint violation degree with respect to the constraint parameter is calculated based on the group coordination penalty factor, and the constraint parameter is dynamically updated based on the gradient.

[0040] A second aspect of an embodiment of the present invention provides a system for adaptively optimizing and configuring multi-source signal interference parameters, including:

[0041] The first unit is configured to obtain historical interference effectiveness data and real-time interference parameter status data of the signal interference source to be optimized, and to construct an interference effectiveness evaluation model based on the historical interference effectiveness data;

[0042] The second unit is used to optimize and iterate the resource allocation scheme of the signal interference source to be optimized using an adaptive genetic algorithm, calculate the fitness value of the iterative population according to a preset fitness function, and dynamically adjust the crossover probability and mutation probability of the adaptive genetic algorithm based on the fitness value;

[0043] A third unit is configured to construct a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and perform constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function;

[0044] a fourth unit, configured to calculate a constraint violation degree of an individual in the population, determine a penalty factor according to the constraint violation degree, adaptively adjust the fitness value of the individual using the penalty factor, and update the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree;

[0045] The fifth unit is used to determine whether the number of iterations reaches a preset iteration threshold based on the constraint parameters, and output an optimal resource allocation solution when the condition is met.

[0046] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0047] processor;

[0048] a memory for storing processor-executable instructions;

[0049] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0050] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0051] The beneficial effects of this application are as follows:

[0052] The multi-source signal interference parameter adaptive optimization configuration method provided by the present invention realizes the intelligent optimization configuration of interference parameters, effectively improves the overall combat effectiveness of the electronic countermeasure system, and solves the problem that traditional manual configuration methods cannot meet the needs of complex battlefield environments.

[0053] This method constructs a jamming effectiveness evaluation model and uses an adaptive genetic algorithm for parameter optimization. It can respond to changes in the battlefield environment in real time, dynamically adjust the jamming parameter configuration, and achieve optimal resource allocation in multi-source signal jamming scenarios, thereby improving the flexibility and effectiveness of the countermeasure system.

[0054] The innovative design of dynamic resource constraint matrix and adaptive penalty function solves the resource conflict problem in multi-source signal interference and ensures the actual feasibility of the scheme. At the same time, through the calculation of constraint violation degree and dynamic adjustment of penalty factor, the optimization results are more in line with actual battlefield needs, achieving the maximum interference effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Schematic diagram of a flow chart of a method for adaptively optimizing and configuring multi-source signal interference parameters according to an embodiment of the present invention;

[0056] Figure 2 Constructing a logic block diagram for the interference effectiveness evaluation model according to an embodiment of the present invention;

[0057] Figure 3 Schematic diagram of resource allocation scheme optimization effect under different interference scenarios according to an embodiment of the present invention;

[0058] Figure 4 This is a flow chart of a method for dynamic resource optimization of interference sources based on multi-dimensional constraints according to an embodiment of the present invention;

[0059] Figure 5 This is a flow chart of a method for calculating violation degree and optimizing fitness based on multi-dimensional constraints according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0061] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0062] Figure 1 FIG. 1 is a flow chart of a method for adaptively optimizing and configuring multi-source signal interference parameters according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0063] Acquire historical interference effectiveness data and real-time interference parameter status data of the signal interference source to be optimized, and construct an interference effectiveness evaluation model based on the historical interference effectiveness data;

[0064] Adopting an adaptive genetic algorithm to iteratively optimize the resource allocation scheme of the signal interference source to be optimized, calculating the fitness value of the iterative population according to a preset fitness function, and dynamically adjusting the crossover probability and mutation probability of the adaptive genetic algorithm based on the fitness value;

[0065] constructing a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and performing constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function;

[0066] Calculating the constraint violation degree of individuals in the population, determining a penalty factor according to the constraint violation degree, adaptively adjusting the individual fitness value by the penalty factor, and updating the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree;

[0067] Based on the constraint parameters, it is determined whether the number of iterations reaches a preset iteration threshold, and an optimal resource allocation solution is output when the condition is met.

[0068] In an optional implementation, constructing an interference effectiveness evaluation model based on the historical interference effectiveness data includes:

[0069] Extracting interference effectiveness evaluation features based on the historical interference effectiveness data, establishing an influence relationship between the historical power allocation data and the historical frequency band coverage data of the interference source and the historical interference gain data, forming an interference effectiveness evaluation matrix, and establishing an effectiveness evaluation function for each interference source based on the interference effectiveness evaluation matrix, wherein the effectiveness evaluation function is used to predict the interference gain under different power allocation and frequency band coverage;

[0070] An interference effectiveness evaluation structure is constructed according to the effectiveness evaluation function, and evaluation parameters of the interference effectiveness evaluation structure are optimized and adjusted using the historical interference effectiveness data to generate an interference effectiveness evaluation model that meets a preset evaluation accuracy.

[0071] Interference effectiveness evaluation features are extracted based on historical interference effectiveness data. In practical applications, historical interference effectiveness data includes historical power allocation data of multiple interference sources, historical frequency band coverage data, and corresponding historical interference gain data.

[0072] For each interference source, historical data from the past six months was collected, including power allocation values, frequency band coverage, and corresponding interference gain values at different time points. For example, for interference source A, 500 sets of historical data samples were collected, each containing power allocation values (such as 23dBm, 27dBm, 30dBm, etc.), frequency band coverage (such as 2.4-2.5GHz, 5.1-5.8GHz, etc.), and actual measured interference gain values (such as 12dB, 15dB, 18dB, etc.).

[0073] Feature engineering was performed on the collected historical data to extract effective evaluation features. Data analysis revealed a positive correlation between power allocation and interference gain, and a certain correlation between frequency band coverage and interference gain. Therefore, power allocation, frequency band coverage, and center frequency offset were selected as primary feature parameters. Furthermore, to account for environmental factors, auxiliary features such as ambient noise level and the relative distance between the interference source and the target were also introduced.

[0074] Establish the influence relationship between the historical power allocation data and historical frequency band coverage data of the interference source and the historical interference gain data to form an interference effectiveness evaluation matrix. In this embodiment, the following method is used:

[0075] The historical data for each interference source is normalized, with power allocation data mapped to a range of 0-1. Frequency band coverage data is converted to two characteristic parameters: center frequency and bandwidth. For example, a power allocation value of 30dBm is normalized to 0.9, and a frequency band coverage of 2.4-2.5GHz is converted to a center frequency of 2.45GHz and a bandwidth of 100MHz.

[0076] Construct an interference effectiveness evaluation matrix. The rows of this matrix represent different historical data samples, the columns represent the extracted feature parameters, including the standardized power allocation value, center frequency, bandwidth, etc., and the last column represents the corresponding interference gain value. For example, for the first set of historical data for interference source A, a row of the evaluation matrix might be [0.8, 2.45, 0.1, 15], representing the standardized power value, center frequency (GHz), bandwidth (GHz), and interference gain (dB), respectively.

[0077] By analyzing the relationship between each feature and interference gain in the evaluation matrix, an effectiveness evaluation function of each interference source is established based on the evaluation matrix. In this embodiment, a random forest algorithm is used to construct an effectiveness evaluation function for each interference source:

[0078] For interference source A, a random forest model consisting of 100 decision trees was constructed by processing 500 sets of historical data. Each decision tree was trained based on a different feature subset and sample subset, ultimately generating interference gain predictions through ensemble learning. This model effectively captures the nonlinear impact of power allocation and frequency band coverage on interference gain.

[0079] When the power of interference source A is set to 28dBm (normalized to 0.85) and the frequency band coverage is 2.4-2.48GHz (center frequency 2.44GHz, bandwidth 80MHz), the interference gain value predicted by the performance evaluation function is 14.6dB, which is not much different from the actual measured value of 14.8dB, indicating that the model has good predictive ability.

[0080] An interference effectiveness evaluation structure is constructed based on the effectiveness evaluation function, and the evaluation parameters are optimized and adjusted using historical interference effectiveness data.

[0081] Based on the previously constructed random forest model, we further designed an interference effectiveness evaluation architecture. This architecture consists of four parts: a data preprocessing module, a feature extraction module, a model prediction module, and a result output module. The data preprocessing module is responsible for standardizing the input power allocation and frequency band coverage data; the feature extraction module is responsible for extracting effective features from the processed data; the model prediction module uses the trained random forest model to predict interference gain; and the result output module converts the prediction results into a standard format and outputs them.

[0082] To ensure that the evaluation accuracy meets the preset standards, the model parameters need to be optimized and adjusted. In this example, a cross-validation method is used to optimize the model. The historical data is divided into a training set and a validation set in a ratio of 8:2. The key parameters of the random forest, including the number of decision trees, the maximum tree depth, and the feature selection method, are optimized using a grid search method.

[0083] Taking interference source A as an example, parameter optimization determined the optimal number of decision trees to be 120, the maximum depth to be 15, and the minimum number of leaf node samples to be 5. After retraining the model using this set of optimized parameters, the average prediction error on the validation set dropped from the initial 1.2 dB to 0.8 dB, meeting the preset evaluation accuracy requirement (error less than 1.0 dB).

[0084] To validate the model's generalizability, practical application tests were conducted. Under different environmental conditions, multiple new power and frequency band parameters were set for interference source A. Interference gain values were obtained through both model prediction and actual measurements. The test results showed that across the 10 new parameter settings, the average error between the model predictions and actual measurements was 0.85 dB, with a maximum error of 1.3 dB, confirming the effectiveness and applicability of the constructed model.

[0085] Through the above method, an interference effectiveness evaluation model based on historical interference effectiveness data was successfully constructed. This model can accurately predict the interference gain under different power allocation and frequency band coverage conditions, providing an effective decision support tool for the optimal configuration of the interference system.

[0086] Figure 2 A logic block diagram for constructing an interference effectiveness evaluation model according to an embodiment of the present invention is as follows:

[0087] The figure illustrates the process for building an interference effectiveness evaluation model, a complete system from historical data analysis to model construction. Starting with historical interference effectiveness data, the interference effectiveness evaluation feature extraction phase divides the data into three parallel analysis areas: historical power allocation data analysis, historical frequency band coverage data analysis, and historical interference gain data analysis. The results of these three-dimensional data analyses are aggregated into the impact relationship modeling phase, which then constructs an interference effectiveness evaluation matrix. Based on this, an effectiveness evaluation function is established, and a closed-loop optimization process is implemented through optimization of evaluation parameters, ultimately leading to the construction of a complete interference effectiveness evaluation model. The entire process demonstrates a systematic approach, from data collection, feature extraction, multi-dimensional analysis, relationship modeling, to final model construction. In particular, the three-dimensional analysis of historical data ensures the comprehensiveness and accuracy of the evaluation, while the feedback loop of parameter optimization ensures the model's dynamic optimization capabilities.

[0088] In an optional embodiment, an adaptive genetic algorithm is used to iteratively optimize the resource allocation scheme of the signal interference source to be optimized, the fitness value of the iterative population is calculated according to a preset fitness function, and the crossover probability and mutation probability of the genetic algorithm are dynamically adjusted based on the fitness value, including:

[0089] Establishing a fitness function for the resource allocation scheme of the signal interference source to be optimized, encoding the resource allocation scheme of the signal interference source to be optimized according to the fitness function to obtain an initial population, calculating the fitness value of each individual in the initial population, and calculating the maximum fitness value and the average fitness value of the population based on the fitness value of each individual;

[0090] Dynamically adjust the crossover probability according to the difference between the fitness value of the individual to be crossed and the maximum fitness value of the population and the average fitness value of the population; when the fitness value of the individual to be crossed is greater than the average fitness value of the population, adopt a dynamically compressed crossover probability; when the fitness value of the individual to be crossed is less than or equal to the average fitness value of the population, adopt a fixed maintained crossover probability;

[0091] The mutation probability is dynamically adjusted according to the difference between the fitness value of the individual to be mutated and the maximum fitness value of the population and the average fitness value of the population. When the fitness value of the individual to be mutated is less than the maximum fitness value of the population, a dynamically compressed mutation probability is adopted. When the fitness value of the individual to be mutated is greater than or equal to the average fitness value of the population, a fixed maintained mutation probability is adopted.

[0092] Establishing a fitness function for the signal jammer resource allocation scheme is the first step in implementing this method. The design of the fitness function directly impacts the effectiveness and direction of optimization. In a certain military electronic countermeasure system, the fitness function can comprehensively consider jamming effectiveness, resource consumption, and tactical requirements. For example, the fitness value can be expressed as the weighted sum of the jamming success rate multiplied by 0.6, the spectrum utilization rate multiplied by 0.3, and the power efficiency multiplied by 0.1. If a scheme has an 85% jamming success rate, 70% spectrum utilization, and 60% power efficiency, its fitness value is 85 × 0.6 + 70 × 0.3 + 60 × 0.1 = 78.5.

[0093] The resource allocation scheme for the signal interference source is encoded based on the fitness function to obtain the initial population. This encoding method can use real numbers to directly represent the values of the resource allocation parameters. For example, a resource allocation scheme that includes three parameters: transmit power, operating frequency, and antenna gain can be represented by a chromosome consisting of three real numbers. For example, an individual is encoded as [25, 2450, 12], indicating a transmit power of 25 watts, an operating frequency of 2450 MHz, and an antenna gain of 12 dB.

[0094] The initial population can be formed by randomly generating multiple resource allocation schemes that meet the constraints. Assuming the population size is 50, 50 resource allocation schemes are randomly generated as the initial population. The fitness value of each individual in the initial population is calculated, and the maximum fitness value and the average fitness value of the population are recorded. For example, if the fitness value of the best individual in the initial population is 85.2 and the average fitness value of all individuals is 72.6, the maximum fitness value of the population is recorded as 85.2 and the average fitness value of the population is 72.6.

[0095] During the iterative optimization process, the core innovation lies in dynamically adjusting the crossover and mutation probabilities based on individual fitness. For the crossover operation, an adaptive adjustment strategy is employed. When the fitness of the individual to be crossed exceeds the population average fitness, a dynamically compressed crossover probability is used. For example, if the fitness of an individual to be crossed is 78.5, which is greater than the population average fitness of 72.6, its crossover probability can be dynamically calculated by subtracting the fitness difference ratio from the base crossover probability (e.g., 0.9). The fitness difference ratio is (78.5 - 72.6) / (85.2 - 72.6) = 0.467. Multiplying this by the compression factor of 0.5 yields 0.234. Subtracting this value from the base crossover probability yields the actual crossover probability of 0.9 - 0.234 = 0.666.

[0096] When the fitness of the individual to be crossed is less than or equal to the population average fitness, a fixed crossover probability is used. For example, if the fitness of the individual to be crossed is 70.2, which is less than the population average fitness of 72.6, the base crossover probability of 0.9 is used directly as its crossover probability. This strategy ensures that individuals with lower fitness have a higher probability of crossover, increasing population diversity.

[0097] Mutation also uses an adaptive adjustment strategy. When the fitness of an individual to be mutated is less than the maximum fitness of the population, a dynamically compressed mutation probability is used. For example, if the fitness of an individual to be mutated is 80.3, which is less than the maximum fitness of the population, 85.2, its mutation probability can be dynamically calculated by subtracting the fitness difference ratio from the base mutation probability (e.g., 0.1). The fitness difference ratio is (85.2 - 80.3) / (85.2 - 72.6) = 0.389. Multiplying this by the compression factor of 0.7 yields 0.272. This value is subtracted from the base mutation probability to obtain the actual mutation probability of 0.1 - 0.272 × 0.1 = 0.073.

[0098] When the fitness of the individual to be mutated is greater than or equal to the population average fitness, a fixed mutation probability is used. For example, if the fitness of the individual to be mutated is 85.2, which is equal to the population maximum fitness, the base mutation probability of 0.1 is used as its mutation probability. This strategy ensures that individuals with higher fitness have a lower probability of mutation, preserving good genes.

[0099] The arithmetic crossover method can be used in the crossover operation. For example, the two parent individuals are [25, 2450, 12] and [30, 2400, 10], the crossover point is selected as the second position, and the crossover coefficient is 0.7. Then the two offspring individuals are [25, 2415,12] and [30, 2435, 10], where 2415=2450×0.7+2400×0.3 and 2435=2450×0.3+2400×0.7.

[0100] The uniform mutation method can be used in the mutation operation. For example, if the third bit of an individual [25, 2450, 12] mutates and the mutation range is [8, 15], then after the mutation it may become [25, 2450, 9.5], where 9.5 is a randomly generated value in the range [8, 15].

[0101] After crossover and mutation, the fitness of the newly generated individuals is calculated and merged with the original population. Based on their fitness, the best individuals are selected to form the next generation. The selection method can use an elite retention strategy to ensure that the best individuals advance directly to the next generation, while the remaining individuals are selected using a roulette wheel method.

[0102] The iterative process repeats the above steps, updating the maximum and average fitness values of the population and dynamically adjusting the crossover and mutation probabilities until a termination condition is met. This termination condition can be when a preset maximum number of iterations (e.g., 500) is reached or when the change in the optimal fitness value for multiple generations (e.g., 50 generations) is less than a threshold (e.g., 0.001).

[0103] Practical application cases demonstrate the remarkable effectiveness of this adaptive genetic algorithm in optimizing signal jammer resource allocation. In optimizing a radar jamming system, this method increased the jamming success rate from 78% to 92%, boosted spectrum utilization by 15%, and improved power efficiency by 20%. The algorithm also converged approximately 35% faster than traditional genetic algorithms.

[0104] The strategy of adaptively adjusting crossover and mutation probabilities effectively balances the algorithm's global search capabilities with its local, refined search capabilities, avoiding premature convergence while accelerating convergence. By employing different parameter adjustment strategies for individuals with different fitness levels, the algorithm maintains population diversity while improving optimization efficiency, providing a highly efficient and reliable optimization method for allocating signal interference source resources.

[0105] In an optional implementation, establishing a fitness function for the resource allocation scheme of the signal interference source to be optimized, and encoding the resource allocation scheme of the signal interference source to be optimized according to the fitness function to obtain an initial population includes:

[0106] Establishing a fitness function for a resource allocation scheme for the signal interference source to be optimized based on the interference effectiveness, resource constraints, and performance targets of the signal interference source to be optimized, wherein the fitness function includes an interference effectiveness term and a resource constraint penalty term;

[0107] The resource allocation scheme of the signal interference source to be optimized is real-number encoded according to interference power, frequency bandwidth and time allocation to generate an initial population with a preset size.

[0108] Based on the interference effectiveness, resource constraints, and performance targets of the signal interference source to be optimized, a fitness function for the resource allocation scheme of the signal interference source to be optimized is established. The fitness function consists of two parts: the interference effectiveness term and the resource constraint penalty term.

[0109] When establishing the interference effectiveness term, the degree of interference from the interference source to the target communication system is comprehensively considered. Specifically, the interference effectiveness term can be characterized by the degree of reduction in the target system's signal-to-interference-plus-noise ratio (SINR). Assuming the target system has N channels, for channel i, its signal-to-noise ratio before interference is SNR_i, and its signal-to-interference-plus-noise ratio after interference is SINR_i. The interference effectiveness of channel i can be expressed as the difference between SNR_i and SINR_i. The interference effectiveness of the entire system is the weighted average of the interference effectiveness of all channels, with the weights set based on the importance of each channel.

[0110] For a communication system with three channels, if the importance weights of each channel are 0.5, 0.3, and 0.2, respectively, and the original signal-to-noise ratios are 20dB, 18dB, and 15dB, respectively, and the signal-to-interference-and-noise ratios after interference drop to 5dB, 8dB, and 10dB, respectively, the total interference effectiveness is: 0.5×(20-5) + 0.3×(18-8) + 0.2×(15-10) = 7.5 + 3 + 1 = 11.5dB. A higher interference effectiveness indicates more effective interference.

[0111] When establishing resource constraint penalty terms, the power, bandwidth, and time constraints of the interference source are primarily considered. When the resource allocation scheme exceeds the resource constraints, an appropriate penalty is applied to reduce the fitness function value.

[0112] In terms of power constraints, assume that the total power limit of the interference source is P_max, and the total power of the current allocation scheme is P_total. If P_total is greater than P_max, the power penalty term is the penalty coefficient α multiplied by (P_total-P_max); otherwise, the power penalty term is 0.

[0113] In terms of bandwidth constraints, assume that the total bandwidth upper limit of the interference source is B_max, and the total bandwidth of the current allocation scheme is B_total. If B_total is greater than B_max, the bandwidth penalty term is the penalty coefficient β multiplied by (B_total-B_max); otherwise, the bandwidth penalty term is 0.

[0114] In terms of time constraints, it is assumed that the total time resource upper limit of the interference source is T_max, and the total time resource of the current allocation scheme is T_total. If T_total is greater than T_max, the time penalty term is the penalty coefficient γ multiplied by (T_total-T_max); otherwise, the time penalty term is 0.

[0115] The fitness function can be expressed as the interference effectiveness term minus the sum of the penalty terms. The penalty coefficients α, β, and γ need to be adjusted according to the specific application scenario and resource importance to ensure a good interference effect under resource constraints.

[0116] Set α = 10, β = 8, and γ = 5. Assume that the interference effectiveness of a resource allocation scheme is 11.5 dB, the total power exceeds the upper limit by 0.5 W, the bandwidth does not exceed the upper limit, and the time resource exceeds the upper limit by 2 ms. The fitness function value of this scheme is: 11.5 - 10 × 0.5 - 8 × 0 - 5 × 2 = 11.5 - 5 - 0 - 10 = -3.5. A negative fitness function value indicates that the scheme is not feasible and requires further optimization.

[0117] The resource allocation scheme of the signal interference source to be optimized is encoded with real numbers according to the interference power, frequency bandwidth and time allocation to generate an initial population with a preset size.

[0118] Real-number coding directly represents the resource allocation scheme as a real-number vector, facilitating the subsequent genetic algorithm. For a communication system with N channels, the coding vector contains 3N elements, representing the power allocation, bandwidth allocation, and time allocation for each channel.

[0119] The coding vector X can be expressed as [P_1, P_2, ..., P_N, B_1, B_2, ..., B_N, T_1, T_2,..., T_N], where P_i represents the power allocated to the i-th channel, B_i represents the bandwidth allocated to the i-th channel, and T_i represents the time resource allocated to the i-th channel.

[0120] When generating the initial population, you can use random initialization. First, set the population size M, then randomly generate M code vectors to form the initial population. When generating random vectors, consider the appropriate range of resources. For example, power allocation can be randomly generated within the range [0, P_max], bandwidth allocation within the range [0, B_max], and time allocation within the range [0, T_max].

[0121] For a communication system with three channels, assuming that the maximum power of the interference source is 10 W, the maximum bandwidth is 100 MHz, and the maximum time resource is 50 ms, a possible encoding vector is [3.5, 2.8, 3.2, 30, 25, 40, 15, 20, 10], indicating that the three channels are allocated power of 3.5 W, 2.8 W, and 3.2 W, bandwidth of 30 MHz, 25 MHz, and 40 MHz, and time resources of 15 ms, 20 ms, and 10 ms, respectively.

[0122] To ensure the diversity of the initial population, a uniformly distributed random number generation method can be used, or the density of sampling points can be increased in key areas based on prior knowledge. For example, based on experience, sampling points may be added in high-power, narrow-bandwidth areas to improve the quality of the initial population.

[0123] If the population size M is set to 100, the initial population will contain 100 such encoding vectors. Each encoding vector represents a possible resource allocation solution, which will then be evolved and optimized using a genetic algorithm to find the optimal resource allocation solution.

[0124] Through the above method, the fitness function establishment and initial population generation of the resource allocation scheme of the signal interference source to be optimized are completed, laying the foundation for the subsequent optimization process.

[0125] Figure 3 Schematic diagram of resource allocation scheme optimization effect under different interference scenarios according to an embodiment of the present invention:

[0126] The figure is a hexagonal radar chart that shows the performance comparison of this technical solution and existing technologies in six different scenarios. The triangular marks in the figure represent this technical solution, and the circular marks represent existing technologies (fixed weight). Looking at the specific data, in the communication jamming scenario, this technical solution achieved a score of 92.5, an increase of 8.2 points from the existing technology's score of 84.3; in the radar jamming scenario, this technical solution achieved a score of 88.7, which was better than the existing technology's score of 78.5; in the electronic reconnaissance jamming scenario, this technical solution scored 90.3, significantly higher than the existing technology's score of 81.2; in the field of multi-target coordinated jamming, this technical solution achieved a score of 86.9, a significant improvement from the existing technology's score of 73.6; in complex electromagnetic environments, this technical solution achieved a score of 84.2, better than the existing technology's score of 69.8; and in low signal-to-noise ratio scenarios, this technical solution achieved a score of 93.6, far exceeding the existing technology's score of 82.7. Overall, this technical solution has achieved significant performance improvements in all six evaluation dimensions, with an average improvement of around 10 points, especially in low signal-to-noise ratio and communication interference scenarios.

[0127] In an optional implementation, constructing a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and performing constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function includes:

[0128] Obtaining transmit power, antenna gain, frequency band, and beam pointing angle of multiple interference sources, constructing a power constraint matrix element based on a ratio of the transmit power to the antenna gain, constructing a frequency constraint matrix element based on an overlap integral of the frequency band, and constructing a space constraint matrix element based on a deviation of the beam pointing angle;

[0129] Combining the power constraint matrix elements, the frequency constraint matrix elements, and the space constraint matrix elements to form a dynamic resource constraint matrix, wherein the dynamic resource constraint matrix is used to characterize the power constraint relationship, the frequency constraint relationship, and the space constraint relationship between interference sources;

[0130] Obtaining an expected interference efficiency value and a current interference efficiency value, constructing an efficiency penalty term based on a square difference between the expected interference efficiency value and the current interference efficiency value, and multiplying the efficiency penalty term by a dynamic weight to obtain a comprehensive efficiency penalty value;

[0131] Calculating a constraint penalty item based on the dynamic resource constraint matrix, wherein the constraint penalty item is obtained by applying constraint type weights to the power constraint matrix elements, the frequency constraint matrix elements, and the space constraint matrix elements respectively;

[0132] The power violation, frequency violation and space violation are calculated according to the dynamic resource constraint matrix; the original fitness value is corrected according to the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value, and the efficiency-corrected fitness value is corrected based on the power violation, the frequency violation and the space violation to obtain a final fitness value.

[0133] Obtain key parameters for multiple interference sources, including transmit power, antenna gain, frequency band, and beam pointing angle. For example, in a wireless communication scenario, assume there are four interference sources. Interference source 1 has a transmit power of 15 watts, an antenna gain of 6 decibels, and a frequency band of 2.4-2.5 GHz. Interference source 2 has a beam pointing angle of 45 degrees, a transmit power of 12 watts, and a frequency band of 2.35-2.45 GHz.

[0134] When constructing the power constraint matrix elements, calculate the ratio of transmit power to antenna gain for each interference source. For interference sources 1 and 2, the transmit power ratio is calculated as 15 / 12 = 1.25, and the antenna gain ratio is calculated as 6 / 8 = 0.75. Multiplying these two values yields the power constraint matrix element 0.9375. Similar calculations are used for other interference source pairs to form the power constraint matrix.

[0135] When constructing the frequency constraint matrix elements, calculate the degree of overlap between the frequency bands of each interference source. For interference sources 1 and 2, the frequency bands are 2.4-2.5 GHz and 2.35-2.45 GHz, respectively. The overlap is 2.4-2.45 GHz, with a width of 0.05 GHz, representing 50% of the frequency band width of interference source 1 and 50% of the frequency band width of interference source 2. The average value is calculated to obtain the frequency constraint matrix element of 0.5. Use this method to calculate the frequency constraint matrix elements for all interference source pairs.

[0136] When constructing the spatial constraint matrix elements, calculate the degree of deviation in the beam pointing angle of each interference source. For interference sources 1 and 2, the beam pointing angles are 30 and 45 degrees, respectively, with an angle deviation of 15 degrees. Assuming the angle deviation threshold is 90 degrees, the normalized deviation is 15 / 90 = 0.167, and the spatial constraint matrix element is 1 - 0.167 = 0.833. This method forms the spatial constraint matrix.

[0137] The power constraint matrix, frequency constraint matrix, and space constraint matrix are combined to form the dynamic resource constraint matrix. This matrix is a three-dimensional matrix, where the third dimension represents the constraint type (power, frequency, space).

[0138] To construct the performance penalty term, obtain the expected interference performance value and the current interference performance value. Assume that the system's expected interference performance value is 85 points, and the current interference performance value is 72 points. Calculate the square of the difference and multiply it by the dynamic weight to obtain the performance penalty term. Based on the ratio of the interference performance value to the expected value (72 / 85 = 0.847), the overall performance penalty value is calculated to be 0.153.

[0139] Constraint penalties are calculated based on the dynamic resource constraint matrix. A constraint type weight of 0.4 is applied to the power constraint matrix elements, a constraint type weight of 0.35 is applied to the frequency constraint matrix elements, and a constraint type weight of 0.25 is applied to the spatial constraint matrix elements. For example, using interference sources 1 and 2 as an example, the calculated constraint penalty is 0.7584.

[0140] Power, frequency, and spatial violations are calculated based on the dynamic resource constraint matrix. For power violations, the deviation between the actual power value of each interference source and the corresponding element in the power constraint matrix is calculated. Assuming that the actual power of interference source 1 is adjusted to 17 watts, the square of the deviation from the corresponding constraint element in the power constraint matrix is multiplied by the dynamic weight to obtain the power violation. Similar calculations are performed for all interference source pairs and summed to obtain the total power violation.

[0141] When calculating the frequency violation, assume that the actual frequency band of interference source 1 is adjusted to 2.38-2.48 GHz. Multiply the square of the deviation from the corresponding constraint element in the frequency constraint matrix by the frequency weight to obtain the frequency violation. The sum of the two values yields the total frequency violation.

[0142] When calculating the spatial violation, assume that the beam pointing angle of interference source 1 is adjusted to 35 degrees. The spatial violation is calculated by multiplying the square of the deviation from the corresponding constraint element in the spatial constraint matrix by the spatial weight. The sum of these is the total spatial violation.

[0143] The original fitness value is modified according to the comprehensive efficiency penalty value. Assuming the original fitness value is 680, the comprehensive efficiency penalty value of 0.153 is applied to modify it, resulting in an efficiency-corrected fitness value of 576.

[0144] The performance-corrected fitness value is further modified based on the power violation, frequency violation, and spatial violation. Weights are assigned to the three violations and the weighted sum is calculated to obtain the overall violation. The overall violation is then applied to the performance-corrected fitness value to obtain the final fitness value.

[0145] This method can be used for interference suppression in radar systems. By dynamically adjusting the transmit power, frequency band, and beam pointing angle of each interference source, the interference effectiveness is maximized while satisfying resource constraints. After optimization, the interference effectiveness is significantly improved, resource utilization is enhanced, and the configuration of each interference source satisfies the constraints, achieving effective interference suppression.

[0146] This method is also applicable to spectrum management in mobile communication networks. In multi-cell coordination scenarios, base stations are considered interference sources. A dynamic resource constraint matrix is constructed to evaluate the interference relationships between base stations. An adaptive penalty function is then used to optimize resource allocation to meet the constraints. This method has proven effective in reducing interference for cell-edge users and improving overall network throughput and spectrum efficiency.

[0147] This method also performs well in multi-UAV collaborative reconnaissance missions. By establishing power, frequency, and spatial constraints between UAVs, it optimizes communication resource allocation for each, ensuring stable communication quality during mission execution while avoiding mutual interference. Test results show that this optimized resource allocation scheme can reduce communication interference by approximately 30% and increase information transmission success rate by approximately 25%.

[0148] Figure 4 This is a flow chart of a method for dynamic resource optimization of interference sources based on multi-dimensional constraints according to an embodiment of the present invention:

[0149] This flowchart illustrates the complete process of dynamic resource constraint and fitness optimization for interference sources. First, the system obtains key parameters of multiple interference sources, including transmit power, antenna gain, frequency band, and beam pointing angle. Based on these parameters, it constructs three types of constraint matrix elements: the power constraint matrix elements are derived from the ratio of transmit power to antenna gain; the frequency constraint matrix elements are derived from the overlap integral of the frequency band; and the spatial constraint matrix elements are based on the deviation of the beam pointing angle. These three constraint matrix elements are then combined into a dynamic resource constraint matrix, which characterizes the power, frequency, and spatial constraint relationships between interference sources. The system obtains the expected interference effectiveness and the current effectiveness, constructs an effectiveness penalty term using the squared difference, and dynamically weights the resulting overall effectiveness penalty value. Based on the dynamic resource constraint matrix, different weights are applied to the constraint penalty terms. Finally, the system modifies the original fitness value by calculating the power, frequency, and spatial violations. The modified effectiveness fitness value is further optimized based on these violation metrics, ultimately yielding the final fitness value.

[0150] In an optional implementation, calculating the power violation, frequency violation, and space violation according to the dynamic resource constraint matrix; correcting the original fitness value according to the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value; and correcting the efficiency-corrected fitness value based on the power violation, the frequency violation, and the space violation to obtain a final fitness value includes:

[0151] The dynamic resource constraint matrix includes a power constraint matrix, a frequency constraint matrix, and a space constraint matrix; obtaining node power, frequency set, and space distance parameters, and obtaining an original power violation based on the power constraint matrix by summing the product of the square of the deviation of the node power ratio and the power constraint matrix element and the dynamic weight;

[0152] Based on the frequency constraint matrix, the original frequency violation is calculated by summing the ratio of the intersection and union of the frequency sets, the square of the deviation of the frequency constraint matrix elements, and the frequency weight; based on the spatial constraint matrix, the original spatial violation is calculated by summing the ratio of the spatial distance to the maximum distance, the square of the deviation of the spatial constraint matrix elements, and the spatial weight; and the original power violation, the original frequency violation, and the original spatial violation are subjected to noise filtering to obtain a filtered violation;

[0153] The original fitness value is corrected using the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value, the filtering violation is weightedly fused based on the efficiency-corrected fitness value to obtain an overall violation, and the efficiency-corrected fitness value is corrected using the overall violation to obtain a final fitness value, which is calculated as the difference between the efficiency-corrected fitness value and the product term of the overall violation.

[0154] Obtain the current power value of each node in the system. Suppose a wireless communication system has five nodes with power values of 12 watts, 15 watts, 9 watts, 18 watts, and 14 watts, respectively. In the power constraint matrix, the constraint threshold between nodes 1 and 2 is 0.7, indicating that the ratio of the power of node 1 to the power of node 2 should not exceed 0.7. The actual ratio is calculated to be 12 / 15 = 0.8, which deviates from the constraint threshold of 0.7 by 0.1. This deviation is squared to 0.01, and then multiplied by the preset dynamic weight of 1.5, resulting in a power violation of 0.015 for this node pair.

[0155] Similar calculations are performed for all node pairs and the sum is calculated. Assuming that there are 10 valid node pairs in the system, and their power violations are 0.015, 0.022, 0.008, 0.031, 0.019, 0.025, 0.012, 0.027, 0.016, and 0.023, respectively, the total original power violation is 0.198.

[0156] Obtain the frequency set for each node. Assume that the frequency set for node 1 is {2.4GHz, 5.2GHz, 5.8GHz}, and the frequency set for node 2 is {2.4GHz, 3.5GHz, 5.2GHz}. Calculate the intersection of the frequency sets to be {2.4GHz, 5.2GHz}, and the union to be {2.4GHz, 3.5GHz, 5.2GHz, 5.8GHz}. The ratio of the intersection to the union is 2 / 4 = 0.5. In the frequency constraint matrix, the constraint threshold between nodes 1 and 2 is 0.4, and the deviation from the actual ratio of 0.5 is 0.1. Square this deviation to 0.01, and multiply it by the frequency weight of 1.2 to obtain a frequency violation score of 0.012 for this node pair.

[0157] Perform similar calculations on all node pairs and sum them up. Assuming that the frequency violations of the same 10 node pairs are 0.012, 0.018, 0.009, 0.025, 0.014, 0.019, 0.011, 0.023, 0.015 and 0.02 respectively, the total original frequency violation is 0.166.

[0158] When calculating the spatial violation, the spatial distance parameters between each node are obtained. Assuming the actual distance between nodes 1 and 2 is 120 meters and the maximum allowed distance in the system is 200 meters, the spatial distance ratio is 120 / 200 = 0.6. In the spatial constraint matrix, the constraint threshold between nodes 1 and 2 is 0.5, and the deviation from the actual ratio of 0.6 is 0.1. This deviation is squared to 0.01, and then multiplied by the spatial weight of 1.3, resulting in a spatial violation of 0.013 for this node pair.

[0159] Similar calculations are performed on all node pairs and the sum is calculated. Assuming that the spatial violations of the same 10 node pairs are 0.013, 0.019, 0.01, 0.026, 0.015, 0.022, 0.012, 0.024, 0.016 and 0.021 respectively, the total original spatial violation is 0.178.

[0160] To improve computational stability, noise filtering is performed on the original power violation, original frequency violation, and original spatial violation. A moving average filtering method is used, and the violation values of three consecutive iterations are averaged. Assuming the power violation of the first two iterations is 0.187 and 0.192, the current filtered power violation is (0.187 + 0.192 + 0.198) / 3 = 0.192. Similarly, assuming the frequency violation of the first two iterations is 0.158 and 0.163, the filtered frequency violation is:

[0161] (0.158+0.163+0.166) / 3=0.162.

[0162] Assuming that the spatial violation degrees of the first two iterations are 0.171 and 0.175, the spatial violation degree after filtering is (0.171+0.175+0.178) / 3=0.175.

[0163] Before performing fitness correction, a comprehensive performance penalty value is obtained through comprehensive performance evaluation. Assuming this penalty value is 0.85, it means that the system performance has reached 85% of the expected performance. The original fitness value is corrected. Assuming the original fitness value is 720, the performance-corrected fitness value is 720 × 0.85 = 612.

[0164] The filter violations are weighted and combined based on the performance-corrected fitness value to obtain the overall violation. Assuming the power violation weight is 0.4, the frequency violation weight is 0.35, and the spatial violation weight is 0.25, the overall violation is 0.192 × 0.4 + 0.162 × 0.35 + 0.175 × 0.25 = 0.178.

[0165] The overall violation is used to correct the performance-corrected fitness value to obtain the final fitness value. The final fitness value is calculated as the difference between the performance-corrected fitness value and the product of the overall violation, that is, 612-612×0.178=503.1.

[0166] In practical applications, this method can be used to optimize resource allocation in wireless sensor networks. For example, in a smart factory environment, 20 wireless sensor nodes were deployed. After optimization using the above method, each node's power was configured between 6.5 watts and 15.8 watts, with frequencies allocated to the 2.4 GHz, 3.5 GHz, and 5.8 GHz bands, and inter-node distances maintained between 35 meters and 180 meters. The optimized network reduced energy consumption by 21%, increased frequency resource utilization by 18%, and achieved a more rational network topology while meeting the power, frequency, and space constraints.

[0167] To address interference, this method adds an interference suppression mechanism. When an interference source is detected, the corresponding elements of the power constraint matrix are dynamically adjusted. For example, when an interference source appears near node 3, the power constraint threshold between node 3 and surrounding nodes is adjusted from 0.6 to 0.5. This forces the optimization process to reduce the power of node 3, thereby minimizing the impact of interference.

[0168] Figure 5 Flowchart of the violation degree calculation and fitness optimization method based on multi-dimensional constraints according to an embodiment of the present invention:

[0169] This flowchart details the multi-level violation calculation and fitness optimization process for a dynamic resource constraint matrix. First, the dynamic resource constraint matrix contains constraints in three dimensions: power, frequency, and space. The system obtains node power, frequency set, and spatial distance parameters and calculates the raw power violation by multiplying the power ratio by the squared deviation of the power constraint matrix elements and the dynamic weight. Second, for the frequency constraint matrix, the raw frequency violation is calculated by multiplying the ratio of the intersection and union of the frequency sets by the squared deviation of the frequency constraint matrix elements and the frequency weight. For spatial constraints, the raw spatial violation is calculated by multiplying the ratio of the spatial distance to the maximum distance by the squared deviation of the spatial constraint matrix elements and the spatial weight. The system then applies noise filtering to these three raw violation metrics to obtain the filtered violation metrics. Finally, the raw fitness metrics are modified using a comprehensive efficiency penalty to obtain the efficiency-corrected fitness metrics. The filtered violation metrics are then weighted and combined to obtain the overall violation metrics. Finally, the final fitness metrics are calculated by taking the difference between the efficiency-corrected fitness metrics and the overall violation metrics.

[0170] Regarding the origins and improvements of this technology, traditional resource optimization methods typically only consider constraints in a single dimension, such as power or frequency. This can lead to optimization results that may not meet requirements in other dimensions. While some existing methods consider multi-dimensional constraints, these methods typically simply superimpose the constraints of each dimension, failing to fully consider the interactions between them and lacking flexibility in constraint handling.

[0171] The technology proposed in this application addresses the above-mentioned issues by designing a dynamic resource constraint matrix, achieving a unified representation of constraints in the three dimensions of power, frequency, and space. An innovative filtering mechanism is introduced to process the original violation degree, effectively suppressing random fluctuations in the optimization process. A dual-layer correction mechanism, which uses a comprehensive performance penalty value for initial correction and then a secondary correction based on the violation degree, ensures that the final fitness value more accurately reflects the quality of the solution. Furthermore, the dynamic constraint matrix can be adjusted in real time according to environmental changes, enhancing the adaptability of the method.

[0172] Experimental results show that compared with traditional methods, the technology of this application improves resource utilization by 17% to 25%, improves the overall system efficiency by 12% to 20%, and improves the satisfaction of three-dimensional constraints of power, frequency and space by 23%, 19% and 21% respectively, significantly improving the effect of multi-dimensional resource optimization.

[0173] In an optional embodiment, calculating the constraint violation degree of each individual in the population, determining a penalty factor based on the constraint violation degree, adaptively adjusting the fitness value of the individual using the penalty factor, and updating the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree includes:

[0174] Calculating a constraint violation degree for each interference source, where the constraint violation degree is obtained by summing the product of the ratio of the product of the transmit power and the antenna gain and the square of the deviation of the power constraint threshold and the dynamic weight;

[0175] Constructing an individual penalty factor based on the constraint violation degree, wherein the individual penalty factor is calculated by an exponential function of a basic penalty coefficient and a weighted sum of the violation degrees, wherein the weighted sum of the violation degrees is weighted by the constraint type weight;

[0176] Calculating a group collaborative penalty factor based on the individual penalty factors, wherein the group collaborative penalty factor is obtained by a weighted sum of the mean of the individual penalty factors and the violation variance, and the violation variance is multiplied by a smoothing coefficient;

[0177] The gradient of the constraint violation degree with respect to the constraint parameter is calculated based on the group coordination penalty factor, and the constraint parameter is dynamically updated based on the gradient.

[0178] When calculating the constraint violation for each interference source, the transmit power and antenna gain of the current interference source are first obtained. Assume that the transmit power of an interference source is 10 watts, the antenna gain is 5 decibels, and the power constraint threshold is set to 40 units. The product of the transmit power and antenna gain is calculated to be 50 units. The deviation from the power constraint threshold of 40 units is 10 units. This deviation is squared to 100 and multiplied by the preset dynamic weight of 0.8, resulting in a constraint violation of 80 units for this interference source.

[0179] For multiple interference sources, the constraint violation degrees are calculated for each of them and then summed. Assuming there are three interference sources in the system, with constraint violation degrees of 80, 60, and 40 units respectively, the total constraint violation degree is 180 units.

[0180] When constructing individual penalty factors based on constraint violations, we first determine the base penalty coefficient. This coefficient can be set based on the stringency of the optimization problem, for example, 1.5. We then calculate the weighted sum of the violations, applying a weight to each type of constraint violation. Assuming the system involves power and interference constraints, with weights of 0.6 and 0.4, respectively, and corresponding violations of 180 and 120 units, the weighted sum of the violations is 180 × 0.6 + 120 × 0.4 = 156 units.

[0181] Substitute the base penalty coefficient 1.5 and the weighted violation degree 156 into the exponential function to calculate the individual penalty factor. Specifically, take the base of the natural logarithm e to the power of (1.5×156 / 1000), which is approximately equal to 1.26, that is, the penalty factor for this individual is 1.26.

[0182] To enhance the optimization effect, a group coordination mechanism is introduced to calculate the group coordination penalty factor. Assuming there are 10 individuals in the population, the mean penalty factor is 1.3, the violation variance is 0.05, and the smoothing coefficient is set to 0.2, then the group coordination penalty factor is 1.3 + 0.05 × 0.2 = 1.31.

[0183] The individual fitness values are adjusted using the group collaborative penalty factor. For example, if the original fitness value is 850, the adjusted fitness value is 850 / 1.31≈649.2. This penalty mechanism ensures that solutions that violate the constraints are appropriately downgraded during the optimization process, thereby guiding the search towards feasible solutions.

[0184] The update process for the constraint parameters based on the constraint violation is as follows: First, the gradient of the constraint violation with respect to the constraint parameter is calculated. Specifically, assuming the current value of the constraint parameter is 0.75, the constraint violation is 180 units, and the learning rate is 0.01, the gradient update is 0.01 × 180 = 1.8 units. To ensure update stability, a momentum factor of 0.9 is introduced, resulting in a new value of the constraint parameter of 0.75 + (1 - 0.9) × 1.8 = 0.93.

[0185] To avoid drastic parameter fluctuations, set a parameter change range. For example, the valid range of the constraint parameter is [0.5, 2.0]. If the updated value exceeds the range, the boundary value is used; if the updated value is 0.93, it remains unchanged.

[0186] After the constraint parameters are updated, the system uses the new parameters to re-evaluate the constraint violation scores of each individual in the population. For example, if the constraint violation score of the first interference source mentioned above is recalculated using the updated constraint parameter of 0.93, if its transmit power remains at 10 watts and its antenna gain is 5 decibels, the product of transmit power and antenna gain remains 50 units. However, since the constraint parameter has been updated to 0.93, the power constraint threshold is adjusted to 37.2 units, and the deviation becomes 12.8 units, which, when squared, is 163.84. Multiplied by the dynamic weight of 0.8, the constraint violation score is 131.1 units.

[0187] As the optimization process iterates, the constraint parameters are continuously adjusted to gradually reduce the constraint violation. When the constraint violation of all individuals falls below a preset threshold (e.g., 10 units), the constraints are considered satisfied, and the solution at this point is considered the optimal solution that satisfies the constraints.

[0188] This method can be used to optimize base station power configuration in mobile communication networks. For example, within a certain area, there are five base stations. After optimization using the above method, the transmit power of each base station is adjusted to 8.5 watts, 7.2 watts, 9.1 watts, 6.8 watts, and 8.3 watts, respectively, and the antenna gain is adjusted to 4.2 decibels, 4.8 decibels, 3.9 decibels, 5.1 decibels, and 4.5 decibels, respectively. This optimization results in a 12% increase in network coverage, a 23% reduction in interference, and an 18% improvement in user experience quality, all while meeting the power and interference constraints of each base station.

[0189] In summary, this implementation achieves effective constraint optimization by accurately calculating constraint violations, constructing individual and group collaborative penalty factors, adaptively adjusting fitness values, and dynamically updating constraint parameters. This method is particularly suitable for optimization problems in fields such as wireless communications and resource allocation, demonstrating its strong practicality and adaptability.

[0190] A second aspect of an embodiment of the present invention provides a system for adaptively optimizing and configuring multi-source signal interference parameters, including:

[0191] The first unit is configured to obtain historical interference effectiveness data and real-time interference parameter status data of the signal interference source to be optimized, and to construct an interference effectiveness evaluation model based on the historical interference effectiveness data;

[0192] The second unit is used to optimize and iterate the resource allocation scheme of the signal interference source to be optimized using an adaptive genetic algorithm, calculate the fitness value of the iterative population according to a preset fitness function, and dynamically adjust the crossover probability and mutation probability of the adaptive genetic algorithm based on the fitness value;

[0193] A third unit is configured to construct a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and perform constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function;

[0194] a fourth unit, configured to calculate a constraint violation degree of an individual in the population, determine a penalty factor according to the constraint violation degree, adaptively adjust the fitness value of the individual using the penalty factor, and update the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree;

[0195] The fifth unit is used to determine whether the number of iterations reaches a preset iteration threshold based on the constraint parameters, and output an optimal resource allocation solution when the condition is met.

[0196] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0197] processor;

[0198] a memory for storing processor-executable instructions;

[0199] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0200] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0201] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0202] Finally, 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for adaptively optimizing and configuring multi-source signal interference parameters, characterized in that: include: Acquire historical interference effectiveness data and real-time interference parameter status data of the signal interference source to be optimized, and construct an interference effectiveness evaluation model based on the historical interference effectiveness data; Adopting an adaptive genetic algorithm to iteratively optimize the resource allocation scheme of the signal interference source to be optimized, calculating the fitness value of the iterative population according to a preset fitness function, and dynamically adjusting the crossover probability and mutation probability of the adaptive genetic algorithm based on the fitness value; constructing a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and performing constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function; Calculating the constraint violation degree of individuals in the population, determining a penalty factor according to the constraint violation degree, adaptively adjusting the individual fitness value by the penalty factor, and updating the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree; Determine whether the number of iterations reaches a preset iteration threshold based on the constraint parameters, and output the optimal resource allocation solution when the condition is met; Extracting interference effectiveness evaluation features based on the historical interference effectiveness data, establishing an influence relationship between the historical power allocation data and the historical frequency band coverage data of the interference source and the historical interference gain data, forming an interference effectiveness evaluation matrix, and establishing an effectiveness evaluation function for each interference source based on the interference effectiveness evaluation matrix, wherein the effectiveness evaluation function is used to predict the interference gain under different power allocation and frequency band coverage; Constructing an interference effectiveness evaluation module according to the effectiveness evaluation function, optimizing and adjusting evaluation parameters of the interference effectiveness evaluation module using the historical interference effectiveness data, and generating an interference effectiveness evaluation model that meets a preset evaluation accuracy; Establishing a fitness function for the resource allocation scheme of the signal interference source to be optimized, encoding the resource allocation scheme of the signal interference source to be optimized according to the fitness function to obtain an initial population, calculating the fitness value of each individual in the initial population, and calculating the maximum fitness value and the average fitness value of the population based on the fitness value of each individual; Dynamically adjust the crossover probability according to the difference between the fitness value of the individual to be crossed and the maximum fitness value of the population and the average fitness value of the population; when the fitness value of the individual to be crossed is greater than the average fitness value of the population, adopt a dynamically compressed crossover probability; when the fitness value of the individual to be crossed is less than or equal to the average fitness value of the population, adopt a fixed maintained crossover probability; Dynamically adjust the mutation probability according to the difference between the fitness value of the individual to be mutated, the maximum fitness value of the population, and the average fitness value of the population. When the fitness value of the individual to be mutated is less than the maximum fitness value of the population, a dynamic compression mutation probability is adopted. When the fitness value of the individual to be mutated is greater than or equal to the maximum fitness value of the population, a fixed maintenance mutation probability is adopted. Obtaining transmit power, antenna gain, frequency band, and beam pointing angle of multiple interference sources, constructing a power constraint matrix element based on a ratio of the transmit power to the antenna gain, constructing a frequency constraint matrix element based on an overlap integral of the frequency band, and constructing a space constraint matrix element based on a deviation of the beam pointing angle; Combining the power constraint matrix elements, the frequency constraint matrix elements, and the space constraint matrix elements to form a dynamic resource constraint matrix, wherein the dynamic resource constraint matrix is used to characterize the power constraint relationship, the frequency constraint relationship, and the space constraint relationship between interference sources; Obtaining an expected interference efficiency value and a current interference efficiency value, constructing an efficiency penalty term based on a square difference between the expected interference efficiency value and the current interference efficiency value, and multiplying the efficiency penalty term by a dynamic weight to obtain a comprehensive efficiency penalty value; Calculating a constraint penalty item based on the dynamic resource constraint matrix, wherein the constraint penalty item is obtained by applying constraint type weights to the power constraint matrix elements, the frequency constraint matrix elements, and the space constraint matrix elements respectively; Calculating power violation, frequency violation and space violation according to the dynamic resource constraint matrix; Correcting the original fitness value according to the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value, and correcting the efficiency-corrected fitness value based on the power violation, the frequency violation, and the space violation to obtain a final fitness value; Calculating a constraint violation degree for each interference source, where the constraint violation degree is obtained by summing the product of the ratio of the product of the transmit power and the antenna gain and the square of the deviation of the power constraint threshold and the dynamic weight; Constructing an individual penalty factor based on the constraint violation degree, wherein the individual penalty factor is calculated by an exponential function of a basic penalty coefficient and a weighted sum of the violation degrees, wherein the weighted sum of the violation degrees is weighted by the constraint type weight; Calculating a group collaborative penalty factor based on the individual penalty factors, wherein the group collaborative penalty factor is obtained by a weighted sum of the mean of the individual penalty factors and the violation variance, and the violation variance is multiplied by a smoothing coefficient; The gradient of the constraint violation degree with respect to the constraint parameter is calculated based on the group coordination penalty factor, and the constraint parameter is dynamically updated based on the gradient.

2. The method according to claim 1, characterized in that Establishing a fitness function for the resource allocation scheme of the signal interference source to be optimized, and encoding the resource allocation scheme of the signal interference source to be optimized according to the fitness function to obtain an initial population includes: Establishing a fitness function for a resource allocation scheme for the signal interference source to be optimized based on the interference effectiveness, resource constraints, and performance targets of the signal interference source to be optimized, wherein the fitness function includes an interference effectiveness term and a resource constraint penalty term; The resource allocation scheme of the signal interference source to be optimized is real-number encoded according to interference power, frequency bandwidth and time allocation to generate an initial population with a preset size.

3. The method according to claim 1, characterized in that Calculating the power violation, frequency violation, and space violation according to the dynamic resource constraint matrix; correcting the original fitness value according to the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value; and correcting the efficiency-corrected fitness value based on the power violation, the frequency violation, and the space violation to obtain a final fitness value includes: The dynamic resource constraint matrix includes a power constraint matrix, a frequency constraint matrix, and a space constraint matrix; obtaining node power, frequency set, and space distance parameters, and obtaining an original power violation based on the power constraint matrix by summing the product of the square of the deviation of the node power ratio and the power constraint matrix element and the dynamic weight; Based on the frequency constraint matrix, the original frequency violation is calculated by summing the ratio of the intersection and union of the frequency sets, the square of the deviation of the frequency constraint matrix elements, and the frequency weight; based on the spatial constraint matrix, the original spatial violation is calculated by summing the ratio of the spatial distance to the maximum distance, the square of the deviation of the spatial constraint matrix elements, and the spatial weight; and the original power violation, the original frequency violation, and the original spatial violation are subjected to noise filtering to obtain a filtered violation; The original fitness value is corrected using the comprehensive efficiency penalty value to obtain an efficiency-corrected fitness value, the filtering violation is weightedly fused based on the efficiency-corrected fitness value to obtain an overall violation, and the efficiency-corrected fitness value is corrected using the overall violation to obtain a final fitness value, which is calculated as the difference between the efficiency-corrected fitness value and the product term of the overall violation.

4. A system for adaptively optimizing and configuring multi-source signal interference parameters, for implementing the method according to any one of claims 1 to 3, characterized in that: include: The first unit is configured to obtain historical interference effectiveness data and real-time interference parameter status data of the signal interference source to be optimized, and to construct an interference effectiveness evaluation model based on the historical interference effectiveness data; The second unit is used to optimize and iterate the resource allocation scheme of the signal interference source to be optimized using an adaptive genetic algorithm, calculate the fitness value of the iterative population according to a preset fitness function, and dynamically adjust the crossover probability and mutation probability of the adaptive genetic algorithm based on the fitness value; A third unit is configured to construct a dynamic resource constraint matrix and an adaptive penalty function based on the interference effectiveness evaluation model, and perform constraint verification and fitness correction on the resource allocation scheme based on the dynamic resource constraint matrix and the adaptive penalty function; a fourth unit, configured to calculate a constraint violation degree of an individual in the population, determine a penalty factor according to the constraint violation degree, adaptively adjust the fitness value of the individual using the penalty factor, and update the constraint parameters of the dynamic resource constraint matrix based on the constraint violation degree; The fifth unit is used to determine whether the number of iterations reaches a preset iteration threshold based on the constraint parameters, and output an optimal resource allocation solution when the condition is met.

5. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images