Digital predistortion compensation method and system based on genetic algorithm

Abstract

The invention discloses a digital pre-distortion compensation method based on a genetic algorithm. The method comprises the following steps: acquiring a plurality of initial signal features and initial pre-distortion coefficients; obtaining a first population and a second population according to the initial signal features and the initial pre-distortion coefficient; respectively processing the first population and the second population by adopting a genetic algorithm to respectively obtain a first lookup table and a second lookup table; acquiring a corresponding first pre-distortion coefficient in the first lookup table according to a baseband signal to be compensated, and when the first pre-distortion coefficient is judged to meet a preset precision requirement, performing compensation by using the first pre-distortion coefficient, or when the first pre-distortion coefficient is judged to not meet the preset precision requirement, performing compensation by using the first pre-distortion coefficient. And obtaining a corresponding second pre-distortion coefficient in the second lookup table so as to perform compensation by using the second pre-distortion coefficient. By setting the first lookup table and the second lookup table, the signals with different requirements are looked up by adopting different rules, so that the pre-distortion compensation efficiency and accuracy can be further improved.

Description

Technical Field

[0001] The invention belongs to the field of signal processing, and in particular relates to a digital predistortion compensation method and system based on a genetic algorithm. Background Art

[0002] In the current field of high-efficiency non-constant envelope modulation communication systems, technologies such as orthogonal frequency division multiplexing (OFDM) and quadrature amplitude modulation (QAM) are highly favored because they significantly improve channel capacity. However, these technologies also face challenges: the time-varying nature of their signal envelopes leads to high average-to-peak ratio (PAR), which has a significant impact on the RF power amplifier (PA). The nonlinear characteristics of the PA are prone to cause intermodulation distortion (IMD) when processing such signals, which in turn increases spectrum regrowth, reduces adjacent channel power ratio (ACPR), causes adjacent channel interference (ACI), and aggravates in-band distortion, increasing the receiver bit error rate and threatening signal transmission quality. To deal with the spectrum regrowth problem, the traditional strategy is to make the PA work in the linear region, that is, to use power back-off technology, but this sacrifices power efficiency and increases system cost.

[0003] Digital baseband predistortion technology is the mainstream solution to alleviate this problem, mainly including polynomial-based predistortion methods. This method constructs the characteristic curve of the PA through indirect learning and uses finite-order polynomials to approximate the actual output behavior of the PA. Subsequently, before the signal is sent, a polynomial model with opposite characteristics is applied to predistort the signal. The advantage of this method is that it is easy to implement, especially for low-order models, and does not require additional storage resources. However, its limitations are also obvious: low-order models may be limited by insufficient accuracy, while high-order models may affect processing speed due to increased computational complexity. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a digital predistortion compensation method and system based on genetic algorithm. The technical problem to be solved by the present invention is achieved through the following technical solutions:

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

[0006] Acquire a number 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 the initial predistortion coefficient, 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] Using a genetic algorithm to process the first population and the second population respectively, to obtain a first lookup table and a second lookup table respectively;

[0009] A corresponding first predistortion coefficient is obtained in the first lookup table according to the baseband signal to be compensated, and when it is determined that the first predistortion coefficient meets the preset accuracy requirement, the first predistortion coefficient is used for compensation, or when it is determined that the first predistortion coefficient does not meet the preset accuracy requirement, a corresponding second predistortion coefficient is obtained in the second lookup table to use the second predistortion coefficient for compensation.

[0010] In a specific embodiment, the first population is processed using a genetic algorithm, comprising:

[0011] Binary-encode the initial predistortion coefficients, and mark the binary codes according to amplitude values ​​to obtain a gene pool, and randomly select a first number of binary codes from the gene pool as each individual in a first population;

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

[0013] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0014] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0015] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values ​​and pre-distortion coefficients that meet the conditions are stored to form a first lookup table.

[0016] In a specific embodiment, the process of updating the gene pool is:

[0017] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value corresponding to any one of the half of the individuals with lower fitness is unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

[0018] In a specific implementation, the initial predistortion coefficients are real-coded, and the real-codes are labeled according to amplitude values ​​and phase values ​​to obtain a gene pool, and a third number of binary codes are randomly selected from the gene pool as each individual in the second population;

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

[0020] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0021] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0022] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values, phase values ​​and pre-distortion coefficients that meet the conditions are stored to form a second lookup table.

[0023] In a specific embodiment, the process of updating the gene pool is:

[0024] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value and phase value corresponding to any one of the half of the individuals with lower fitness are unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

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

[0026] An initialization module, used to obtain a number 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;

[0027] A population establishment module, used for obtaining a first population and a second population according to the initial signal characteristics and the initial pre-distortion coefficient, wherein the individuals in the first population have an amplitude value and an initial pre-distortion coefficient; and the individuals in the second population have an amplitude value, a phase value and an initial pre-distortion coefficient;

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

[0029] A second genetic module, used for processing the second population using a genetic algorithm to obtain a second lookup table;

[0030] a compensation module, configured to obtain a corresponding first predistortion coefficient in the first lookup table according to a baseband signal to be compensated, and when it is determined that the first predistortion coefficient meets a preset accuracy requirement, use the first predistortion coefficient for compensation, or when it is determined that the first predistortion coefficient does not meet the preset accuracy requirement, obtain a corresponding second predistortion coefficient in the second lookup table to use the second predistortion coefficient for compensation.

[0031] In a specific embodiment, the first population is processed using a genetic algorithm, comprising:

[0032] Binary-encode the initial predistortion coefficients, and mark the binary codes according to amplitude values ​​to obtain a gene pool, and randomly select a first number of binary codes from the gene pool as each individual in a first population;

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

[0034] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0035] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0036] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values ​​and pre-distortion coefficients that meet the conditions are stored to form a first lookup table.

[0037] In a specific embodiment, the process of updating the gene pool is:

[0038] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value corresponding to any one of the half of the individuals with lower fitness is unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

[0039] In a specific implementation, the initial predistortion coefficients are real-coded, and the real-codes are labeled according to amplitude values ​​and phase values ​​to obtain a gene pool, and a third number of binary codes are randomly selected from the gene pool as each individual in the second population;

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

[0041] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0042] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0043] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values, phase values ​​and pre-distortion coefficients that meet the conditions are stored to form a second lookup table.

[0044] In a specific embodiment, the process of updating the gene pool is:

[0045] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value and phase value corresponding to any one of the half of the individuals with lower fitness are unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

[0046] Beneficial effects of the present invention:

[0047] A digital predistortion compensation method based on a genetic algorithm of the present invention comprises: obtaining a number 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; obtaining a first population and a second population according to the initial signal characteristics and the initial predistortion coefficients, wherein individuals in the first population have amplitude values ​​and initial predistortion coefficients; individuals in the second population have amplitude values, phase values ​​and initial predistortion coefficients; using a genetic algorithm to process the first population and the second population respectively, and obtaining a first lookup table and a second lookup table respectively; obtaining a corresponding first predistortion coefficient in the first lookup table according to a baseband signal to be compensated, and 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 in the second lookup table, and using the second predistortion coefficient for compensation. In this way, by performing parameter optimization through a genetic algorithm, not only the polynomial predistortion model parameters are improved, but also the search accuracy of the lookup table is improved. Secondly, by setting the first lookup table and the second lookup table to use different rules to perform lookup table searches for signals with different requirements, the efficiency and accuracy of pre-distortion compensation can be further improved.

[0048] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of a digital pre-distortion compensation method based on a genetic algorithm provided by an embodiment of the present invention;

[0050] Figure 2 The present invention provides a digital pre-distortion compensation system module block diagram based on a genetic algorithm. DETAILED DESCRIPTION

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

[0052] Embodiment 1

[0053] See also Figure 1 , Figure 1 The present invention provides a digital pre-distortion compensation method based on a genetic algorithm, which includes:

[0054] Obtain 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; it should be noted that, generally, in scenarios with low accuracy requirements, a two-dimensional preset table of amplitude values ​​and initial predistortion coefficients is sufficient, while in scenarios with high accuracy requirements, the influence of phase values ​​needs to be considered. In addition, the polynomial predistortion model is a common predistortion processing method in the field, but this method is difficult to update.

[0055] Obtaining a first population and a second population according to the initial signal characteristics and the initial predistortion coefficient, 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;

[0056] Using a genetic algorithm to process the first population and the second population respectively, to obtain a first lookup table and a second lookup table respectively;

[0057] Specifically, in a specific implementation, using a genetic algorithm to process the first population includes:

[0058] Binary-encode the initial predistortion coefficients, and mark the binary codes according to amplitude values ​​to obtain a gene pool, and randomly select a first number of binary codes from the gene pool as each individual in a first population;

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

[0060] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0061] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0062] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values ​​and pre-distortion coefficients that meet the conditions are stored to form a first lookup table.

[0063] In a specific embodiment, the process of updating the gene pool is:

[0064] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value corresponding to any one of the half of the individuals with lower fitness is unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

[0065] In a specific implementation, the initial predistortion coefficients are real-coded, and the real-codes are labeled according to amplitude values ​​and phase values ​​to obtain a gene pool, and a third number of binary codes are randomly selected from the gene pool as each individual in the second population;

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

[0067] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0068] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0069] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values, phase values ​​and pre-distortion coefficients that meet the conditions are stored to form a second lookup table.

[0070] In a specific embodiment, the process of updating the gene pool is:

[0071] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value and phase value corresponding to any one of the half of the individuals with lower fitness are unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

[0072] A corresponding first predistortion coefficient is obtained in the first lookup table according to the baseband signal to be compensated, and when it is determined that the first predistortion coefficient meets the preset accuracy requirement, the first predistortion coefficient is used for compensation, or when it is determined that the first predistortion coefficient does not meet the preset accuracy requirement, a corresponding second predistortion coefficient is obtained in the second lookup table to use the second predistortion coefficient for compensation.

[0073] The digital pre-distortion compensation method based on a genetic algorithm of this embodiment optimizes parameters through a genetic algorithm, which not only improves the polynomial pre-distortion model parameters, but also improves the search accuracy of the lookup table. Secondly, by setting the first lookup table and the second lookup table to use different rules for lookup table search for signals with different requirements, the efficiency and accuracy of pre-distortion compensation can be further improved.

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

[0075] An initialization module, used to obtain a number 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;

[0076] A population establishment module, used for obtaining a first population and a second population according to the initial signal characteristics and the initial pre-distortion coefficient, wherein the individuals in the first population have an amplitude value and an initial pre-distortion coefficient; and the individuals in the second population have an amplitude value, a phase value and an initial pre-distortion coefficient;

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

[0078] A second genetic module, used for processing the second population using a genetic algorithm to obtain a second lookup table;

[0079] a compensation module, configured to obtain a corresponding first predistortion coefficient in the first lookup table according to a baseband signal to be compensated, and when it is determined that the first predistortion coefficient meets a preset accuracy requirement, use the first predistortion coefficient for compensation, or when it is determined that the first predistortion coefficient does not meet the preset accuracy requirement, obtain a corresponding second predistortion coefficient in the second lookup table to use the second predistortion coefficient for compensation.

[0080] In a specific embodiment, the first population is processed using a genetic algorithm, comprising:

[0081] Binary-encode the initial predistortion coefficients, and mark the binary codes according to amplitude values ​​to obtain a gene pool, and randomly select a first number of binary codes from the gene pool as each individual in a first population;

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

[0083] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0084] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0085] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values ​​and pre-distortion coefficients that meet the conditions are stored to form a first lookup table.

[0086] In a specific embodiment, the process of updating the gene pool is:

[0087] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value corresponding to any one of the half of the individuals with lower fitness is unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

[0088] In a specific implementation, the initial predistortion coefficients are real-coded, and the real-codes are labeled according to amplitude values ​​and phase values ​​to obtain a gene pool, and a third number of binary codes are randomly selected from the gene pool as each individual in the second population;

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

[0090] The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool;

[0091] After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected to perform a mutation operation to form a progeny population;

[0092] The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values, phase values ​​and pre-distortion coefficients that meet the conditions are stored to form a second lookup table.

[0093] In a specific embodiment, the process of updating the gene pool is:

[0094] After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value and phase value corresponding to any one of the half of the individuals with lower fitness are unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

[0095] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0096] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification.

[0097] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment), or computer program products. Therefore, the present application may adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware, which are collectively referred to as "modules" or "systems" herein. Moreover, the present application may adopt the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program codes. The computer program is stored / distributed in a suitable medium, provided together with other hardware or as a part of hardware, or may adopt other distribution forms, such as by Internet or other wired or wireless telecommunication systems.

[0099] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A digital predistortion compensation method based on genetic algorithm, characterized in that: include: Acquire a number 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; Obtaining a first population and a second population according to the initial signal characteristics and the initial predistortion coefficient, 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; Using a genetic algorithm to process the first population and the second population respectively, to obtain a first lookup table and a second lookup table respectively; A corresponding first predistortion coefficient is obtained in the first lookup table according to the baseband signal to be compensated, and when it is determined that the first predistortion coefficient meets the preset accuracy requirement, the first predistortion coefficient is used for compensation, or when it is determined that the first predistortion coefficient does not meet the preset accuracy requirement, a corresponding second predistortion coefficient is obtained in the second lookup table to use the second predistortion coefficient 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, comprising: Binary-encode the initial predistortion coefficients, and mark the binary codes according to amplitude values ​​to obtain a gene pool, and randomly select a first number of binary codes from the gene pool as each individual in a first population; Calculating the fitness value of each individual in the first population; The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool; After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected to perform a mutation operation to form a progeny population; The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values ​​and pre-distortion coefficients that meet the conditions are stored to form a 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: After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value corresponding to any one of the half of the individuals with lower fitness is unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

4. The digital predistortion compensation method based on genetic algorithm according to claim 1, characterized in that: Performing real number encoding on the initial predistortion coefficients, and marking the real number encoding according to the amplitude value and the phase value to obtain a gene pool, and randomly selecting a third number of binary codes from the gene pool as each individual in the second population; Calculating the fitness value of each individual in the second population; The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool; After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected to perform a mutation operation to form a progeny population; The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values, phase values ​​and pre-distortion coefficients 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: After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value and phase value corresponding to any one of the half of the individuals with lower fitness are unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

6. A digital predistortion compensation system based on genetic algorithm, characterized in that: include: An initialization module, used to obtain a number 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; A population establishment module, used for obtaining a first population and a second population according to the initial signal characteristics and the initial pre-distortion coefficient, wherein the individuals in the first population have an amplitude value and an initial pre-distortion coefficient; and the individuals in the second population have an amplitude value, a phase value and an initial pre-distortion coefficient; A first genetic module, used to process the first population using a genetic algorithm to obtain a first lookup table; A second genetic module, used for processing the second population using a genetic algorithm to obtain a second lookup table; a compensation module, configured to obtain a corresponding first predistortion coefficient in the first lookup table according to a baseband signal to be compensated, and when it is determined that the first predistortion coefficient meets a preset accuracy requirement, use the first predistortion coefficient for compensation, or when it is determined that the first predistortion coefficient does not meet the preset accuracy requirement, obtain a corresponding second predistortion coefficient in the second lookup table to use the second predistortion coefficient 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, comprising: Binary-encode the initial predistortion coefficients, and mark the binary codes according to amplitude values ​​to obtain a gene pool, and randomly select a first number of binary codes from the gene pool as each individual in a first population; Calculating the fitness value of each individual in the first population; The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool; After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a second preset number of individuals are selected to perform a mutation operation to form a progeny population; The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values ​​and pre-distortion coefficients that meet the conditions are stored to form a 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: After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value corresponding to any one of the half of the individuals with lower fitness is unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

9. The digital predistortion compensation system based on genetic algorithm according to claim 6, characterized in that: Performing real number encoding on the initial predistortion coefficients, and marking the real number encoding according to the amplitude value and the phase value to obtain a gene pool, and randomly selecting a third number of binary codes from the gene pool as each individual in the second population; Calculating the fitness value of each individual in the second population; The gene pool is updated by taking half of the individuals with higher fitness as parent individuals and adding half of the individuals with lower fitness into the gene pool; After randomly selecting the other half of the individuals from the gene pool to perform a crossover operation with the half of the individuals with higher fitness, a fourth preset number of individuals are selected to perform a mutation operation to form a progeny population; The above operation is iteratively performed until the fitness of each individual in the offspring population meets the preset conditions, then the iteration is stopped, and the amplitude values, phase values ​​and pre-distortion coefficients 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: After adding half of the individuals with lower fitness to the gene pool, determine whether the amplitude value and phase value corresponding to any one of the half of the individuals with lower fitness are unique. If so, adjust the parameters of the polynomial pre-distortion model, recalculate the initial pre-distortion coefficient corresponding to the amplitude value, and compare it with the individuals added to the gene pool to select the better individual as the gene pool individual.

Images