A digital pre-distortion compensation method and system based on genetic algorithm

Abstract

The application discloses a digital pre-distortion compensation method based on a genetic algorithm, and comprises the following steps: acquiring a plurality of initial signal characteristics and initial pre-distortion coefficients; obtaining a first population and a second population according to the initial signal characteristics and the initial pre-distortion coefficients; processing the first population and the second population respectively by using a genetic algorithm to obtain a first lookup table and a second lookup table respectively; acquiring a corresponding first pre-distortion coefficient in the first lookup table according to a to-be-compensated baseband signal; when it is judged that the first pre-distortion coefficient meets a preset accuracy requirement, the first pre-distortion coefficient is used for compensation; or when it is judged that the first pre-distortion coefficient does not meet the preset accuracy requirement, a corresponding second pre-distortion coefficient is acquired in the second lookup table, and the second pre-distortion coefficient is used for compensation. By setting the first lookup table and the second lookup table, different rules are used for lookup table searching of signals with different requirements, and the pre-distortion compensation efficiency and accuracy can be further improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of signal processing, and particularly relates to a digital predistortion compensation method and system based on a genetic algorithm. BACKGROUND

[0002] In the field of current high-efficiency non-constant envelope modulation communication systems, orthogonal frequency division multiplexing (OFDM) and orthogonal amplitude modulation (QAM) and other technologies are favored due to their significant improvement in channel capacity. However, these technologies also face challenges: the time-varying nature of their signal envelope leads to a high peak-to-average ratio (PAR), which significantly affects the radio frequency power amplifier (PA). The nonlinear characteristics of the PA when processing such signals easily cause intermodulation distortion (IMD), which in turn increases spectral regrowth, reduces the adjacent channel power ratio (ACPR), causes adjacent channel interference (ACI), and exacerbates in-band distortion, increasing the error rate of the receiver and threatening the quality of signal transmission. To address the problem of spectral regrowth, the traditional strategy is to operate the PA in the linear region, i.e., to use the power backoff technique, but this sacrifices power efficiency and increases system cost.

[0003] Digital baseband predistortion technology, as the mainstream solution to this problem, mainly includes polynomial-based predistortion methods. This method constructs a characteristic curve of the PA through indirect learning and uses a finite-order polynomial to approximate the actual output behavior of the PA. Subsequently, a characteristic inverse polynomial model is applied to predistort the signal before transmission. The advantage of this method is that it is easy to implement, particularly suitable for low-order models, and does not require additional storage resources. However, its limitations are also apparent: low-order models may be limited by insufficient accuracy, while high-order models may be affected by increased computational complexity, which affects processing speed. SUMMARY

[0004] To solve the above problems in the prior art, the present application provides a digital predistortion compensation method and system based on a genetic algorithm. The technical problem to be solved by the present application is solved by the following technical scheme:

[0005] A digital predistortion compensation method based on a genetic algorithm, comprising:

[0006] Obtaining a plurality of initial signal characteristics and initial predistortion coefficients, wherein the initial signal characteristics and initial predistortion coefficients are obtained according to a polynomial predistortion model, and the initial signal characteristics include amplitude values and phase values;

[0007] Obtaining a first population and a second population according to the initial signal characteristics and initial predistortion coefficients, wherein the individuals in the first population have amplitude values and initial predistortion coefficients; and the individuals in the second population have amplitude values, phase values, and initial predistortion coefficients;

[0008] Genetic algorithms are used to process the first population and the second population respectively to obtain the first lookup table and the second lookup table;

[0009] The first pre-distortion coefficient is obtained from the first lookup table based on the baseband signal to be compensated. When it is determined that the first pre-distortion coefficient meets the preset accuracy requirement, the first pre-distortion coefficient is used for compensation. Or, when it is determined that the first pre-distortion coefficient does not meet the preset accuracy requirement, the second pre-distortion coefficient is obtained from the second lookup table and used for compensation.

[0010] In one specific implementation, a genetic algorithm is used to process the first population, including:

[0011] The initial predistortion coefficients are binary encoded, and the binary encoding is marked according to the amplitude value to obtain a gene pool. A first number of binary encodings are randomly selected from the gene pool as each individual in the first population.

[0012] Calculate the fitness value of each individual in the first population;

[0013] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0014] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected for mutation operation to form a progeny population.

[0015] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude values ​​and predistortion coefficients that meet the conditions are stored to form the first lookup table.

[0016] In one specific implementation, the process of updating the gene pool is as follows:

[0017] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude value among the individuals with lower fitness is unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficient corresponding to the amplitude value is recalculated. The result is then compared with the individuals added to the gene pool, and the better individual is selected as the gene pool individual.

[0018] In one specific implementation, the initial predistortion coefficients are encoded in real numbers, and the real number encoding is marked according to the amplitude value and phase value to obtain a gene pool. A third number of binary codes are randomly selected from the gene pool as each individual in the second population.

[0019] Calculate the fitness value of each individual in the second population;

[0020] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0021] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected for mutation operation to form a progeny population.

[0022] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude value, phase value, and predistortion coefficient that meet the conditions are stored to form a second lookup table.

[0023] In one specific implementation, the process of updating the gene pool is as follows:

[0024] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude and phase values ​​of the individuals in the lower fitness half are unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficients corresponding to the amplitude values ​​are recalculated. The results are then compared with the individuals added to the gene pool, and the better individuals are selected as the gene pool individuals.

[0025] This invention also provides a digital predistortion compensation system based on a genetic algorithm, comprising:

[0026] An initialization module is used to acquire several initial signal features and initial predistortion coefficients, wherein the initial signal features and initial predistortion coefficients are obtained based on a polynomial predistortion model, and the initial signal features include amplitude values ​​and phase values;

[0027] The population establishment module is used to obtain a first population and a second population based on the initial signal characteristics and the initial predistortion coefficient, wherein individuals in the first population have amplitude values ​​and initial predistortion coefficients; and individuals in the second population have amplitude values, phase values, and initial predistortion coefficients.

[0028] The first genetic module is used to process the first population using a genetic algorithm to obtain a first lookup table;

[0029] The second genetic module is used to process the second population using a genetic algorithm to obtain the second lookup table;

[0030] The compensation module is used to obtain the corresponding first pre-distortion coefficient from the first lookup table based on the baseband signal to be compensated. When it is determined that the first pre-distortion coefficient meets the preset accuracy requirement, the first pre-distortion coefficient is used for compensation. Or, when it is determined that the first pre-distortion coefficient does not meet the preset accuracy requirement, the corresponding second pre-distortion coefficient is obtained from the second lookup table and the second pre-distortion coefficient is used for compensation.

[0031] In one specific implementation, a genetic algorithm is used to process the first population, including:

[0032] The initial predistortion coefficients are binary encoded, and the binary encoding is marked according to the amplitude value to obtain a gene pool. A first number of binary encodings are randomly selected from the gene pool as each individual in the first population.

[0033] Calculate the fitness value of each individual in the first population;

[0034] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0035] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected for mutation operation to form a progeny population.

[0036] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude values ​​and predistortion coefficients that meet the conditions are stored to form the first lookup table.

[0037] In one specific implementation, the process of updating the gene pool is as follows:

[0038] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude value among the individuals with lower fitness is unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficient corresponding to the amplitude value is recalculated. The result is then compared with the individuals added to the gene pool, and the better individual is selected as the gene pool individual.

[0039] In one specific implementation, the initial predistortion coefficients are encoded in real numbers, and the real number encoding is marked according to the amplitude value and phase value to obtain a gene pool. A third number of binary codes are randomly selected from the gene pool as each individual in the second population.

[0040] Calculate the fitness value of each individual in the second population;

[0041] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0042] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected for mutation operation to form a progeny population.

[0043] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude value, phase value, and predistortion coefficient that meet the conditions are stored to form a second lookup table.

[0044] In one specific implementation, the process of updating the gene pool is as follows:

[0045] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude and phase values ​​of the individuals in the lower fitness half are unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficients corresponding to the amplitude values ​​are recalculated. The results are then compared with the individuals added to the gene pool, and the better individuals are selected as the gene pool individuals.

[0046] The beneficial effects of this invention are:

[0047] This invention discloses a digital predistortion compensation method based on a genetic algorithm, comprising: acquiring several initial signal features and initial predistortion coefficients, wherein the initial signal features and initial predistortion coefficients are obtained according to a polynomial predistortion model, and the initial signal features include amplitude values ​​and phase values; obtaining a first population and a second population based on the initial signal features and initial predistortion coefficients, wherein individuals in the first population have amplitude values ​​and initial predistortion coefficients; and individuals in the second population have amplitude values, phase values, and initial predistortion coefficients; processing the first population and the second population respectively using a genetic algorithm to obtain a first lookup table and a second lookup table respectively; obtaining a corresponding first predistortion coefficient from the first lookup table based on the baseband signal to be compensated; when it is determined that the first predistortion coefficient meets a preset accuracy requirement, using the first predistortion coefficient for compensation; or when it is determined that the first predistortion coefficient does not meet the preset accuracy requirement, obtaining a corresponding second predistortion coefficient from the second lookup table for compensation. Thus, by optimizing parameters through a genetic algorithm, not only are the parameters of the polynomial predistortion model improved, but the lookup accuracy of the lookup table is also improved. Secondly, by setting up a first lookup table and a second lookup table and using different rules to search the lookup table for signals with different requirements, the efficiency and accuracy of predistortion compensation can be further improved.

[0048] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0049] Figure 1 This is a schematic flowchart of a digital predistortion compensation method based on a genetic algorithm provided in an embodiment of the present invention;

[0050] Figure 2 This is a block diagram of a digital predistortion compensation system based on a genetic algorithm provided in an embodiment of the present invention. Detailed Implementation

[0051] The present invention will be further described in detail below with reference to specific embodiments, but the implementation of the present invention is not limited thereto.

[0052] Example 1

[0053] Please see Figure 1 , Figure 1 This is a schematic flowchart of a digital predistortion compensation method based on a genetic algorithm provided in an embodiment of the present invention, including:

[0054] Several initial signal features and initial predistortion coefficients are obtained, wherein the initial signal features and initial predistortion coefficients are obtained based on a polynomial predistortion model. The initial signal features include amplitude values ​​and phase values. It should be noted that, generally, in scenarios with low accuracy requirements, a two-dimensional preset table can be constructed using amplitude values ​​and initial predistortion coefficients. However, in scenarios with high accuracy requirements, the influence of phase values ​​also needs to be considered. Furthermore, the polynomial predistortion model is a common predistortion processing method in this field, but updating this method is quite difficult.

[0055] Based on the initial signal characteristics and the initial predistortion coefficient, a first group and a second group are obtained, wherein individuals in the first group have amplitude values ​​and initial predistortion coefficients; and individuals in the second group have amplitude values, phase values, and initial predistortion coefficients.

[0056] Genetic algorithms are used to process the first population and the second population respectively to obtain the first lookup table and the second lookup table;

[0057] Specifically, in one embodiment, a genetic algorithm is used to process the first population, including:

[0058] The initial predistortion coefficients are binary encoded, and the binary encoding is marked according to the amplitude value to obtain a gene pool. A first number of binary encodings are randomly selected from the gene pool as each individual in the first population.

[0059] Calculate the fitness value of each individual in the first population;

[0060] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0061] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected for mutation operation to form a progeny population.

[0062] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude values ​​and predistortion coefficients that meet the conditions are stored to form the first lookup table.

[0063] In one specific implementation, the process of updating the gene pool is as follows:

[0064] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude value among the individuals with lower fitness is unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficient corresponding to the amplitude value is recalculated. The result is then compared with the individuals added to the gene pool, and the better individual is selected as the gene pool individual.

[0065] In one specific implementation, the initial predistortion coefficients are encoded in real numbers, and the real number encoding is marked according to the amplitude value and phase value to obtain a gene pool. A third number of binary codes are randomly selected from the gene pool as each individual in the second population.

[0066] Calculate the fitness value of each individual in the second population;

[0067] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0068] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected for mutation operation to form a progeny population.

[0069] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude value, phase value, and predistortion coefficient that meet the conditions are stored to form a second lookup table.

[0070] In one specific implementation, the process of updating the gene pool is as follows:

[0071] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude and phase values ​​of the individuals in the lower fitness half are unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficients corresponding to the amplitude values ​​are recalculated. The results are then compared with the individuals added to the gene pool, and the better individuals are selected as the gene pool individuals.

[0072] The first pre-distortion coefficient is obtained from the first lookup table based on the baseband signal to be compensated. When it is determined that the first pre-distortion coefficient meets the preset accuracy requirement, the first pre-distortion coefficient is used for compensation. Or, when it is determined that the first pre-distortion coefficient does not meet the preset accuracy requirement, the second pre-distortion coefficient is obtained from the second lookup table and used for compensation.

[0073] This embodiment presents a digital predistortion compensation method based on a genetic algorithm. By optimizing parameters using a genetic algorithm, it not only improves the parameters of the polynomial predistortion model but also enhances the accuracy of the lookup table. Furthermore, by setting up a first lookup table and a second lookup table and applying different rules to look up signals with different requirements, the efficiency and accuracy of predistortion compensation can be further improved.

[0074] Please refer to Figure 2 The present invention also provides a digital predistortion compensation system based on a genetic algorithm, comprising:

[0075] An initialization module is used to acquire several initial signal features and initial predistortion coefficients, wherein the initial signal features and initial predistortion coefficients are obtained based on a polynomial predistortion model, and the initial signal features include amplitude values ​​and phase values;

[0076] The population establishment module is used to obtain a first population and a second population based on the initial signal characteristics and the initial predistortion coefficient, wherein individuals in the first population have amplitude values ​​and initial predistortion coefficients; and individuals in the second population have amplitude values, phase values, and initial predistortion coefficients.

[0077] The first genetic module is used to process the first population using a genetic algorithm to obtain a first lookup table;

[0078] The second genetic module is used to process the second population using a genetic algorithm to obtain the second lookup table;

[0079] The compensation module is used to obtain the corresponding first pre-distortion coefficient from the first lookup table based on the baseband signal to be compensated. When it is determined that the first pre-distortion coefficient meets the preset accuracy requirement, the first pre-distortion coefficient is used for compensation. Or, when it is determined that the first pre-distortion coefficient does not meet the preset accuracy requirement, the corresponding second pre-distortion coefficient is obtained from the second lookup table and the second pre-distortion coefficient is used for compensation.

[0080] In one specific implementation, a genetic algorithm is used to process the first population, including:

[0081] The initial predistortion coefficients are binary encoded, and the binary encoding is marked according to the amplitude value to obtain a gene pool. A first number of binary encodings are randomly selected from the gene pool as each individual in the first population.

[0082] Calculate the fitness value of each individual in the first population;

[0083] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0084] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected for mutation operation to form a progeny population.

[0085] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude values ​​and predistortion coefficients that meet the conditions are stored to form the first lookup table.

[0086] In one specific implementation, the process of updating the gene pool is as follows:

[0087] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude value among the individuals with lower fitness is unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficient corresponding to the amplitude value is recalculated. The result is then compared with the individuals added to the gene pool, and the better individual is selected as the gene pool individual.

[0088] In one specific implementation, the initial predistortion coefficients are encoded in real numbers, and the real number encoding is marked according to the amplitude value and phase value to obtain a gene pool. A third number of binary codes are randomly selected from the gene pool as each individual in the second population.

[0089] Calculate the fitness value of each individual in the second population;

[0090] The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool.

[0091] After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected for mutation operation to form a progeny population.

[0092] The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude value, phase value, and predistortion coefficient that meet the conditions are stored to form a second lookup table.

[0093] In one specific implementation, the process of updating the gene pool is as follows:

[0094] After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude and phase values ​​of the individuals in the lower fitness half are unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficients corresponding to the amplitude values ​​are recalculated. The results are then compared with the individuals added to the gene pool, and the better individuals are selected as the gene pool individuals.

[0095] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0096] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification.

[0097] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0098] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects, all of which are collectively referred to herein as "modules" or "systems." Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The computer program may be stored / distributed in a suitable medium, provided with or as part of other hardware, or may take other distribution forms, such as via the Internet or other wired or wireless telecommunications systems.

[0099] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A digital predistortion compensation method based on genetic algorithm, characterized in that, include: Several initial signal features and initial predistortion coefficients are obtained, wherein the initial signal features and initial predistortion coefficients are obtained based on a polynomial predistortion model, and the initial signal features include amplitude values ​​and phase values; Based on the initial signal characteristics and the initial predistortion coefficient, a first group and a second group are obtained, wherein individuals in the first group have amplitude values ​​and initial predistortion coefficients; and individuals in the second group have amplitude values, phase values, and initial predistortion coefficients. Genetic algorithms are used to process the first population and the second population respectively to obtain the first lookup table and the second lookup table; The first pre-distortion coefficient is obtained from the first lookup table based on the baseband signal to be compensated. When it is determined that the first pre-distortion coefficient meets the preset accuracy requirement, the first pre-distortion coefficient is used for compensation. Or, when it is determined that the first pre-distortion coefficient does not meet the preset accuracy requirement, the second pre-distortion coefficient is obtained from the second lookup table and used for compensation.

2. The digital predistortion compensation method based on genetic algorithm according to claim 1, characterized in that, The first population is processed using a genetic algorithm, including: The initial predistortion coefficients are binary encoded, and the binary encoding is marked according to the amplitude value to obtain a gene pool. A first number of binary encodings are randomly selected from the gene pool as each individual in the first population. Calculate the fitness value of each individual in the first population; The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool. After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected for mutation operation to form a progeny population. The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude values ​​and predistortion coefficients that meet the conditions are stored to form the first lookup table.

3. The digital predistortion compensation method based on genetic algorithm according to claim 2, characterized in that, The process of updating the gene pool is as follows: After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude value among the individuals with lower fitness is unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficient corresponding to the amplitude value is recalculated. The result is then compared with the individuals added to the gene pool, and the better individual is selected as the gene pool individual.

4. The digital predistortion compensation method based on genetic algorithm according to claim 1, characterized in that, The initial predistortion coefficients are encoded with real numbers, and the real numbers are marked according to the amplitude and phase values ​​to obtain a gene pool. A third number of real numbers are randomly selected from the gene pool as each individual in the second population. Calculate the fitness value of each individual in the second population; The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool. After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected for mutation operation to form a progeny population. The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude value, phase value, and predistortion coefficient that meet the conditions are stored to form a second lookup table.

5. The digital predistortion compensation method based on genetic algorithm according to claim 4, characterized in that, The process of updating the gene pool is as follows: After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude and phase values ​​of the individuals in the lower fitness half are unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficients corresponding to the amplitude values ​​are recalculated. The results are then compared with the individuals added to the gene pool, and the better individuals are selected as the gene pool individuals.

6. A digital predistortion compensation system based on a genetic algorithm, characterized in that, include: An initialization module is used to acquire several initial signal features and initial predistortion coefficients, wherein the initial signal features and initial predistortion coefficients are obtained based on a polynomial predistortion model, and the initial signal features include amplitude values ​​and phase values; The population establishment module is used to obtain a first population and a second population based on the initial signal characteristics and the initial predistortion coefficient, wherein individuals in the first population have amplitude values ​​and initial predistortion coefficients; and individuals in the second population have amplitude values, phase values, and initial predistortion coefficients. The first genetic module is used to process the first population using a genetic algorithm to obtain a first lookup table; The second genetic module is used to process the second population using a genetic algorithm to obtain the second lookup table; The compensation module is used to obtain the corresponding first pre-distortion coefficient from the first lookup table based on the baseband signal to be compensated. When it is determined that the first pre-distortion coefficient meets the preset accuracy requirement, the first pre-distortion coefficient is used for compensation. Or, when it is determined that the first pre-distortion coefficient does not meet the preset accuracy requirement, the corresponding second pre-distortion coefficient is obtained from the second lookup table and the second pre-distortion coefficient is used for compensation.

7. The digital predistortion compensation system based on genetic algorithm according to claim 6, characterized in that, The first population is processed using a genetic algorithm, including: The initial predistortion coefficients are binary encoded, and the binary encoding is marked according to the amplitude value to obtain a gene pool. A first number of binary encodings are randomly selected from the gene pool as each individual in the first population. Calculate the fitness value of each individual in the first population; The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool. After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected for mutation operation to form a progeny population. The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude values ​​and predistortion coefficients that meet the conditions are stored to form the first lookup table.

8. The digital predistortion compensation system based on genetic algorithm according to claim 7, characterized in that, The process of updating the gene pool is as follows: After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude value among the individuals with lower fitness is unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficient corresponding to the amplitude value is recalculated. The result is then compared with the individuals added to the gene pool, and the better individual is selected as the gene pool individual.

9. The digital predistortion compensation system based on genetic algorithm according to claim 6, characterized in that, The initial predistortion coefficients are encoded with real numbers, and the real numbers are marked according to the amplitude and phase values ​​to obtain a gene pool. A third number of real numbers are randomly selected from the gene pool as each individual in the second population. Calculate the fitness value of each individual in the second population; The gene pool is updated by adding half of the individuals with higher fitness as parents and half of the individuals with lower fitness to the gene pool. After randomly selecting one half of the individuals from the gene pool and performing a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected for mutation operation to form a progeny population. The above operations are performed iteratively until the fitness of each individual in the offspring population meets the preset conditions. Then the iteration stops, and the amplitude value, phase value, and predistortion coefficient that meet the conditions are stored to form a second lookup table.

10. The digital predistortion compensation system based on genetic algorithm according to claim 9, characterized in that, The process of updating the gene pool is as follows: After adding half of the individuals with lower fitness to the gene pool, it is determined whether any corresponding amplitude and phase values ​​of the individuals in the lower fitness half are unique. If so, the parameters of the polynomial predistortion model are adjusted, and the initial predistortion coefficients corresponding to the amplitude values ​​are recalculated. The results are then compared with the individuals added to the gene pool, and the better individuals are selected as the gene pool individuals.

Images