Optimization method for video transmission network cdrs

Abstract

The application discloses an optimization method for a video transmission network CDR. The method comprises the following steps: acquiring an environment characteristic and a control parameter vector, wherein the control parameter vector is constructed based on a fuzzy controller of the video transmission network CDR; generating an initial value of a spore population based on the control parameter vector; iteratively optimizing the spore population by using an optimization method with an adaptive exploration and utilization strategy, so that the spore population is adapted to optimal video transmission quality under the environment characteristic; each spore of the spore population corresponds to a value of the control parameter vector; and after the iterative optimization is completed, the spore with the highest fitness in the spore population is taken as a value of a target control parameter vector and is issued to the fuzzy controller. The application can realize adaptive optimization of clock data recovery in a complex and dynamically changing video transmission environment, and improve the robustness of clock data recovery.

Description

Technical Field

[0001] This invention relates to the field of high-speed video information transmission technology, and in particular to an optimization method for video transmission network (CDR) and corresponding computer-readable storage media, terminal equipment and computer program products. Background Technology

[0002] High-speed video transmission is a key component of modern electronic systems, widely used in automotive electronics (ADAS, autonomous driving), remote control (on-site monitoring, teleoperation vision), and high-end industrial automation (machine vision)—fields with extreme requirements for real-time performance, reliability, and image quality. These applications often involve harsh operating conditions such as wide temperature range variations, strong electromagnetic interference, and changing operating environments, while simultaneously needing to handle the continuously increasing data rates brought about by high-definition and even ultra-high-definition video. The stable and reliable transmission of video signals relies heavily on high-performance clock data recovery (CDR) technology to ensure accurate recovery of clock and data from signals that may contain noise and jitter, guaranteeing the final video quality. However, with the continuous improvement of application demands and the increasing complexity of working environments, traditional CDR technology faces unprecedented challenges.

[0003] The CDR (Continuous Data Retrieval) technology widely used in existing high-speed video transmission systems is largely based on classical loop control theory. However, facing increasingly complex and dynamically changing application environments, especially harsh conditions such as wide temperature ranges, variable operating conditions, and temperature disturbances, existing CDR systems lack rapid response and adaptability. This leads to problems such as decreased clock data recovery accuracy, limited dynamic signal tracking capabilities, and difficulty in guaranteeing long-term operational performance. These issues constitute the core bottleneck of existing video transmission, restricting its performance under harsh and dynamic conditions. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide an optimization method for CDR in video transmission networks, aiming to achieve adaptive optimization of clock data recovery and improve the robustness of clock data recovery in complex and dynamically changing video transmission application environments.

[0005] To achieve the above objectives, according to a first aspect of the present invention, an optimization method for video transmission network (CDR) is provided, comprising:

[0006] Environmental features and control parameter vectors are obtained, wherein the control parameter vectors are constructed based on the fuzzy controller of the video transmission network (CDR);

[0007] An initial value for the spore population is generated based on the control parameter vector. An optimization method with an adaptive exploration and utilization strategy is used to iteratively optimize the spore population so that it adapts to the optimal video transmission quality under the environmental characteristics. Each spore in the spore population corresponds to a value of the control parameter vector.

[0008] After iterative optimization is completed, the spore with the highest fitness in the spore population is used as the value of the target control parameter vector and sent to the fuzzy controller.

[0009] Furthermore, the control parameter vector includes the membership parameters of each fuzzy set of the fuzzy controller and the control adjustment amount of each fuzzy rule; the control adjustment amount includes the proportional gain, integral gain, and fractional order of the fuzzy controller.

[0010] The initial values ​​of the spore population are generated based on the control parameter vector, including:

[0011] Based on the size of the spore population and the dimension of the control parameter vector Generate size is A chaotic matrix, wherein the columns of the chaotic matrix correspond to the dimensions of the control parameter vector, and the rows of the chaotic matrix correspond to the spores in the spore population;

[0012] The elements of each column vector of the chaotic matrix are mapped to the value space of the corresponding dimension of the control parameter vector to obtain the values ​​of each dimension of the spore. After the mapping is completed, a total of The spores mentioned above The number of spores is the initial value of the spore population.

[0013] Furthermore, the adaptive exploration and exploitation strategy includes using an adaptive operator to control the probability of using a global exploration strategy and a local exploitation strategy in each iteration;

[0014] An optimization method with an adaptive exploration and utilization strategy is used to iteratively optimize the spore population to adapt it to the optimal video transmission quality under the environmental characteristics, including:

[0015] Based on the number of iteration stages , Determine the first Each iteration phase The value of the adaptive operator is , , ;

[0016] For the Round iteration, Generate a random number for each spore in the spore population, wherein the first spore is the spore of the spore population. The random number corresponding to each spore is ,

[0017] like Then the first The first spore executes a global exploration strategy; otherwise, the second spore... Each spore employs a localized utilization strategy.

[0018] Furthermore, the number Equal to the maximum number of iterations in optimization The adaptive operator follows the formula that changes with the number of iterations. Adjustment:

[0019] ,

[0020] in, It is the first The value of the adaptive operator in the next iteration. and These are the upper and lower limits of the adaptive operator's values.

[0021] Furthermore, the optimization method is a fungal growth optimization method, wherein the global exploration strategy is used to simulate hyphal branching growth, and the local utilization strategy is used to simulate protoplasmic flow to nutrient source concentration.

[0022] The global exploration strategy is:

[0023] ;

[0024] The local exploitation strategy is:

[0025] ;

[0026] in, It is the 1st in the spore population The starting position of the current round of the spores. New locations after exploration or utilization It refers to the current position of three spores randomly selected from the spore population. It is the current position of the spore with the highest fitness in the spore population; It is an exploratory factor. It is the step size scaling factor. It is a random scalar step size generated based on the Levy distribution; It is a factor of utilization. It is the current position of a spore randomly selected from the spore population.

[0027] Furthermore, the environmental characteristics include temperature. Interference amplitude and interference frequency The optimal video transmission quality under the environmental characteristics mentioned includes the long-term bit error rate under the environmental characteristics within a preset monitoring period.

[0028] An optimization method with an adaptive exploration and utilization strategy is used to iteratively optimize the spore population to adapt it to the optimal video transmission quality under the environmental characteristics, including:

[0029] For the Round iteration, It is the 1st in the spore population The spores mentioned above start from the beginning position of the current round. A new location after exploration or utilization;

[0030] If the new position The fitness is better than that of the original position. The fitness mentioned above will then be the first The position of each spore is updated to the new position. Otherwise, keep the original position. ;

[0031] Furthermore, if the new position If the fitness of a spore is better than the optimal fitness in the spore population, then the optimal spore in the spore population is updated to the spore with the best fitness. The spores mentioned.

[0032] Furthermore, the first The spores at position fitness The long-term bit error rate compared to the output of the offline-trained neural network model Inversely proportional:

[0033] The input to the neural network model is the first... The location of the spores The temperature The interference amplitude and the interference frequency The output is the corresponding long-term bit error rate. .

[0034] According to a second aspect of the present invention, a computer-readable storage medium is provided having a program stored thereon that, when executed by a processor, implements the steps of the optimization method for a video transmission network (CDR) as described in the first aspect of the present invention.

[0035] According to a third aspect of the present invention, a terminal device is provided, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the optimization method for video transmission network CDR as described in the first aspect of the present invention.

[0036] According to a fourth aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps in the optimization method for video transmission network CDR as described in the first aspect of the present invention.

[0037] The embodiments of the present invention have at least one of the following advantages or beneficial effects:

[0038] This invention, through acquiring environmental characteristics and control parameter vectors, and using an optimization method with an adaptive exploration strategy to iteratively optimize the spore population, enables the CDR in the video transmission network to adaptively adjust control parameters in complex and dynamically changing application environments to achieve optimal video transmission quality. Compared to traditional CDR technology with fixed parameters or simple feedback adjustment, this adaptive optimization method can better cope with harsh working conditions such as wide temperature range variations, strong electromagnetic interference, and changing operating conditions, significantly improving the robustness and adaptability of clock data recovery.

[0039] The optimization method of this invention is used for slow control of fuzzy controllers. Combined with the fast and slow control dual-layer architecture of fuzzy controllers, it can respond to environmental changes on a large time scale, enabling high-speed video transmission systems to continuously adapt to long-term drift, environmental changes and device aging, and significantly enhancing the overall robustness and stability of the system under harsh conditions such as wide temperature range and strong interference.

[0040] The optimization method of this invention employs an adaptive operator during iteration, enabling a dynamic balance between global exploration and local exploitation during the optimization process. In the initial iteration phase, a larger adaptive operator value and a global exploration strategy are used to quickly find potential optimal solution regions in the parameter space. As iteration progresses, the adaptive operator value is gradually reduced, increasing the probability of executing the local exploitation strategy. This allows for a more refined search near the already found optimal regions, further improving the accuracy of the solution. This strategy ensures global search capability, avoiding getting trapped in local optima, while effectively improving optimization efficiency in the later stages, quickly converging to the global optimum, thereby achieving high-precision optimization of the CDR system control parameters.

[0041] The optimization method of this invention innovatively introduces mechanisms such as chaotic mapping and Levy flight. Chaotic mapping is used to generate the initial spore population, making the initial population more evenly distributed and covering a wider area in the parameter space, which helps the algorithm escape local optima early and improves global search capability. The Levy flight mechanism further enhances the algorithm's global exploration capability through its randomly generated large step jumps, effectively preventing the algorithm from getting trapped in local optima too early. The introduction of these innovative mechanisms enables the optimization algorithm to find the optimal solution more efficiently when facing complex optimization problems, providing a more powerful technical solution for the optimization of CDR systems.

[0042] The optimization method of this invention uses an offline trained neural network model to directly predict the long-term bit error rate (BER) as the spore fitness based on environmental features and candidate parameter vectors. This avoids time-consuming and potentially system-impacting real-time online performance measurements during the optimization iteration process, making the optimization process more efficient and feasible, and the evaluation results more objective and accurate.

[0043] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0044] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0045] Figure 1 This is a schematic diagram of the main flow of an optimization method for CDR in a video transmission network according to an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram illustrating an application scenario of an optimization method for video transmission network CDR in another embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the main flow of an optimization method for CDR in a video transmission network according to another embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram illustrating the fast control layer adaptive capability of applying the optimization method of the present invention in another embodiment of the present invention.

[0049] Figure 5 This is a schematic diagram illustrating the adaptive capability of the slow control layer in another embodiment of the present invention, applying the optimization method of the present invention.

[0050] Figure 6 This is a schematic diagram illustrating the peak suppression performance gain of the feedforward compensation module in response to instantaneous temperature pulse disturbances in another embodiment of the present invention.

[0051] Figure 7 This is a schematic diagram of the main modules of a terminal device according to an embodiment of the present invention. Detailed Implementation

[0052] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0053] Example 1

[0054] Figure 1 This is a schematic diagram illustrating the main flow of an optimization method for video transmission network CDR according to an embodiment of the present invention. This embodiment is for reference. Figure 1 The main inventive concept of this invention will be described in detail. For example... Figure 1 As shown, the optimization method for video transmission network CDR in this embodiment of the present invention includes the following steps S101 to S103.

[0055] Step S101: Obtain environmental features and control parameter vectors, wherein the control parameter vectors are constructed based on the fuzzy controller of the video transmission network (CDR).

[0056] Step S102: Based on the control parameter vector, generate an initial value for the spore population, and use an optimization method with an adaptive exploration and utilization strategy to iteratively optimize the spore population so that the spore population adapts to the optimal video transmission quality under the environmental characteristics; each spore in the spore population corresponds to a value of the control parameter vector.

[0057] Step S103: After the iterative optimization is completed, the spore with the highest fitness in the spore population is sent to the fuzzy controller as the value of the target control parameter vector.

[0058] Understandably, a fuzzy controller is an intelligent controller based on fuzzy logic and fuzzy inference. The core of a fuzzy controller is fuzzy logic and fuzzy inference, achieved through steps such as fuzzification, fuzzy inference, and defuzzification. Specifically, fuzzification converts the system's input variables from membership parameters of fuzzy sets to membership degrees of fuzzy sets. For example, it converts temperature from a specific numerical value to fuzzy states such as "cold," "moderate," and "hot." Fuzzy inference, based on predefined fuzzy rules, infers from the fuzzy states of the input variables to derive fuzzy values ​​for the control output. Fuzzy rules are typically expressed in the form of "if <condition> is satisfied, then <operation>" (i.e., IF-THEN), for example: "If the temperature is cold, then the heating power should be high." Defuzzification converts the fuzzy output values ​​obtained from fuzzy inference into specific control adjustment quantities for actual control.

[0059] Specifically, in this embodiment and some embodiments of the present invention, the input to the fuzzy control is the instantaneous phase error of the CDR output. and its rate of change The control parameter vector includes the membership parameters of each fuzzy set of the fuzzy controller and the control adjustment amount of each fuzzy rule; the control adjustment amount includes the proportional gain, integral gain and fractional order of the fuzzy controller.

[0060] Understandably, in this embodiment and some embodiments of the present invention, iterative optimization involves assigning a value to the control parameter vector for each spore in the spore population, and then using an iterative optimization method to find the optimal value. Specifically, in this embodiment and some embodiments of the present invention, the initial value of the spore population generated based on the control parameter vector in step S102 includes steps S102a1 to S102a2.

[0061] Step S102a1, based on the size of the spore population and the dimension of the control parameter vector Generate size is A chaotic matrix, wherein the columns of the chaotic matrix correspond to the dimensions of the control parameter vector, and the rows of the chaotic matrix correspond to the spores in the spore population.

[0062] Step S102a2: Map the elements of each column vector of the chaotic matrix to the value space of the corresponding dimension of the control parameter vector to obtain the values ​​of each dimension of the spore. After completing the mapping, a total of... The spores mentioned above The number of spores is the initial value of the spore population.

[0063] More specifically, in this embodiment and some embodiments of the present invention, step S102a1 uses Logistic chaotic mapping to generate a chaotic matrix, and the iterative formula for each row of the chaotic matrix is: , , , ;in, It is the first chaotic matrix Line number The elements of the column.

[0064] More specifically, in this embodiment and some embodiments of the present invention, in step S102a2, for the first spore population... spores The Dimension, corresponding to the elements in the chaotic matrix ,spore The Dimension (i.e., corresponding to the first) The control parameter vector of the spore is the first The value space of (dimensional) is Then the first spores The Dimensional parameters By generating chaotic matrix elements Initialize by mapping to the above value range:

[0065]

[0066] in, and It is the first of the control parameter vectors Upper and lower bounds of the dimension parameter.

[0067] Understandably, initialization in this way yields the result from... spores (of the control parameter vector) The initial spore population consists of spores with 10 initial values. Compared to standard random initialization, this initialization method allows the initial spore population to be more evenly distributed and cover a wider area in the search space, which helps the algorithm escape local optima early and improves global search capabilities.

[0068] Specifically, in this embodiment and some embodiments of the present invention, the adaptive exploration and utilization strategy includes using an adaptive operator to control the probability of using a global exploration strategy and a local utilization strategy in each iteration; the step S102 uses an optimization method with an adaptive exploration and utilization strategy to iteratively optimize the spore population so that the spore population adapts to the optimal video transmission quality under the environmental characteristics, including steps S102b1 to S102b3.

[0069] Step S102b1, based on the number of iteration stages , Determine the first Each iteration phase The value of the adaptive operator is , , ;

[0070] Step S102b2, for the first Round iteration, Generate a random number for each spore in the spore population, wherein the first spore is the spore of the spore population. The random number corresponding to each spore is ,

[0071] Step S102b3, if Then the first The first spore executes a global exploration strategy; otherwise, the second spore... Each spore employs a localized utilization strategy.

[0072] It is understandable that in this embodiment and some embodiments of the present invention, the adaptive operator The search strategy of the iterative optimization method can be dynamically adjusted at different stages. In the initial stages ( (smaller) A large value makes random numbers... The probability is relatively high, and the optimization method tends to adopt a global exploration strategy. When the iteration reaches several stages in the later stages ( (larger) The value is small, making random numbers The probability is relatively small, so optimization methods tend to employ local exploitation strategies.

[0073] It is understandable that the number of iteration stages in the embodiments of the present invention... The number of iterations shall not exceed the maximum number of iterations. Specifically, in some other embodiments of the present invention, when the number of... Equal to the maximum number of iterations in optimization At that time, that is The adaptive operator follows the formula as the number of iterations increases. Adjustment:

[0074] ,

[0075] in, It is the first The value of the adaptive operator in the next iteration. and These are the upper and lower bounds of the adaptive operator's values. It is usually close to 1, for example, 0.9. It is usually close to 0, for example, 0.1.

[0076] It is understandable that in some embodiments of the present invention, in the initial stage ( (smaller) The value is relatively large (close to) ), making random numbers The probability of finding the target is relatively high, so optimization methods tend to employ an exploration strategy, resulting in a broad global search. As the number of iterations increases... The increase, Linear decrease, making As the probability of finding a promising solution gradually increases, the optimization method tends to employ a more exploitative strategy, namely, performing a fine-grained local search around the current optimal solution to accelerate convergence. This adaptive mechanism ensures that the optimization method has sufficient global exploration capability in the early stages to discover promising regions, and sufficient local exploitation capability in the later stages to improve the accuracy of the solution.

[0077] Specifically, in this embodiment and some embodiments of the present invention, the optimization method is a fungal growth optimization method, wherein the global exploration strategy is used to simulate mycelial branching growth, and the local utilization strategy is used to simulate protoplasm flow to nutrient source concentration;

[0078] The global exploration strategy is:

[0079] ;

[0080] The local exploitation strategy is:

[0081] ;

[0082] in, It is the 1st in the spore population The starting position of the current round of the spores. New locations after exploration or utilization It refers to the current position of three spores randomly selected from the spore population. It is the current position of the spore with the highest fitness in the spore population; It is an exploratory factor. This is the step size scaling factor, used to control the step size of Levy flight to control the influence intensity of Levy flight, and its value is between 0.01 and 0.1. It is a random scalar step size generated based on the Levy distribution; It is a factor of utilization. It is the current position of a spore randomly selected from the spore population.

[0083] More specifically, in this embodiment and some embodiments of the present invention, It is an exploration factor that decreases with each iteration. This is a utilization factor that decreases with each iteration to improve the search breadth of the algorithm in the early stages of iteration and the convergence accuracy in later stages. For example, in this embodiment and some embodiments of the present invention, , ;in, This represents generating random numbers that follow a standard normal distribution (mean 0, variance 1). Representative Generates Obedience The algorithm uses randomly selected numbers that are uniformly distributed between the given values. This dynamic adjustment strategy helps the algorithm escape local optima early on and quickly lock into the global optimum later on.

[0084] Understandably, the introduction of Levy flight aims to enhance the algorithm's global exploration capability through its occasional large step jumps, effectively preventing the algorithm from getting trapped in local optima prematurely. More specifically, in this embodiment and some embodiments of the present invention, the random scalar step size... The generation is based on two random variables that follow a normal distribution. and The calculation formula is as follows:

[0085] ;

[0086] in, Follows a mean of 0 and a standard deviation of The normal distribution It follows a standard normal distribution (mean 0, standard deviation 1). The calculation formula is as follows:

[0087] ;

[0088] in, It is the exponent of the Levy distribution, for example, 1.5. It is the Gamma function.

[0089] Understandably, in this embodiment and some embodiments of the present invention, Levy flight is used to provide occasional large-step jumps during the search, which helps to escape local optima and improve global search efficiency. The incorporation of the Levy flight strategy allows spores to not only undergo local mutations based on population information during the exploration phase, but also to make large-scale jumps with a certain probability, thereby more effectively exploring areas that have not been fully searched.

[0090] Specifically, in this embodiment and some embodiments of the present invention, the environmental characteristics include temperature. Interference amplitude and interference frequency The optimal video transmission quality under the environmental characteristics includes the long-term bit error rate under the environmental characteristics within a preset monitoring period. In step S102, for the first... Round iteration, It is the 1st in the spore population The spores mentioned above start from the beginning position of the current round. A new location after exploration or utilization; if the new location The fitness is better than that of the original position. The fitness mentioned above will then be the first The position of each spore is updated to the new position. Otherwise, retain the original position. Furthermore, if the new position If the fitness of a spore is better than the optimal fitness in the spore population, then the optimal spore in the spore population is updated to the spore with the best fitness. The spores mentioned.

[0091] Specifically, in this embodiment and some embodiments of the present invention, the first The spores at position fitness The long-term bit error rate compared to the output of the offline-trained neural network model Inversely proportional: More specifically, the first The spores at position fitness Calculate using the following formula:

[0092] ;

[0093] in, This represents a neural network model trained offline, where the input to the neural network model is the first... The location of the spores The temperature The interference amplitude and the interference frequency The output is the corresponding long-term bit error rate. As can be seen from the formula, the lower the long-term bit error rate, the higher the fitness.

[0094] Understandably, the long-term bit error rate predicted by the trained neural network model is generally... The fitness is not equal to zero; therefore, in this embodiment and some embodiments of the present invention, the fitness is... The formula excludes the long-term bit error rate. The case where it equals zero.

[0095] It is understood that in other embodiments of the present invention, the first The spores at position fitness Calculate using the following formula: ;in, For a minimum value, such as 10 to the power of -15, the long-term bit error rate in this formula is... It can be equal to zero.

[0096] Specifically, in this embodiment and some embodiments of the present invention, the neural network model adopts a fully connected multilayer perceptron (MLP) structure, which aims to establish a nonlinear mapping relationship between control parameters and environmental states to system performance indicators (long-term bit error rate) in order to meet the fitting requirements of complex nonlinear system responses.

[0097] Specifically, in this embodiment and some embodiments of the present invention, the number of input layer nodes of the neural network model is set to... D +3, of which D The dimension of the control parameter vector (e.g., 105 dimensions in this embodiment) is 3, corresponding to the three environmental features: temperature, interference amplitude, and interference frequency. The output layer of the neural network model contains one neuron, which outputs the predicted long-term bit error rate within a preset monitoring period. Between the input and output layers, there are three hidden layers, with the number of neurons in each hidden layer set to 0.5 to 2 times the number of nodes in the input layer (e.g., 64 to 256 nodes). The layers are fully connected, and a non-linear activation function (Sigmoid function) is introduced.

[0098] Specifically, to achieve offline training of the neural network model, this embodiment and some embodiments of the present invention construct a system simulation platform containing the core circuit model and channel model of the CDR system. In the simulation platform, random combinations of temperature, interference amplitude, and frequency covering the operating range are set, and multiple sets of control parameter vectors are randomly generated. The simulation is run and the long-term bit error rate (BER) within the corresponding preset monitoring period (e.g., 1 day, 15 days, 1 month, 1 year, etc.) is recorded, thereby constructing a sample dataset. Further, the sample dataset is divided into a training set and a validation set. Backpropagation and gradient descent optimization are used, with the goal of minimizing the mean square error between the predicted BER and the actual BER, iteratively updating the network weights and biases until the error on the validation set converges to a preset threshold. Through the above settings, the neural network model in this embodiment of the present invention can internalize the dynamic characteristics of the CDR system, thereby replacing circuit simulation in the optimization process, achieving fitness evaluation, and making the optimization process more efficient and feasible.

[0099] Example 2

[0100] Figure 2This is a schematic diagram illustrating an application scenario of an optimization method for video transmission network CDR according to another embodiment of the present invention. This embodiment is for reference only. Figure 2 This invention provides a detailed description of its application in specific scenarios. For details not described in this embodiment, please refer to Embodiment 1.

[0101] like Figure 2 As shown, the fractional-order clock data recovery (FOCDR) core module is the foundation for clock data recovery in video transmission in this embodiment. Its input is the reference clock phase information extracted from the front end of the high-speed transceiver (SerDes) of the corresponding camera. Its output is a stable clock phase. (This is the recovery clock in a general sense; the specific feedback to the PD / PFD is the frequency-divided phase.) FOCDR is subject to parameter regulation by a two-layer adaptive control module consisting of a fast control layer (FCL) and a slow control layer (SCL) and a feedforward module.

[0102] Specifically, such as Figure 2 As shown, FOCDR mainly consists of the following components:

[0103] Phase / Frequency Detector (PD / PFD): Its core function is to compare the phase of the input reference clock. Phase with locally generated feedback clock and output phase error signal Feedback clock phase The output clock phase of the digitally controlled oscillator (DCO) The frequency is obtained by dividing the frequency using a frequency divider. The output of PD / PFD can be expressed as:

[0104]

[0105] in, It is the phase detector gain, and this error signal Drive the entire CDR loop.

[0106] Fractional-Order Loop Filter (FO-LF): This filter receives the error signal from the PD / PFD. As input, and output control signal And superimposed compensation control signal For a digitally controlled oscillator (DCO), the design of its transfer function introduces a fractional order. It allows for dynamic adjustment of parameters, both of which are determined in real time by the Fast Control Layer (FCL). Its continuous-time domain transfer function... for:

[0107]

[0108] in, It is proportional gain. It is integral gain, a fractional-order operator. Within the specified frequency range The interior can be approximated as:

[0109] ;

[0110] in, It is the approximation order, a fixed integer such as 5 or 7 pre-selected based on the system's requirements for approximation accuracy and the trade-offs in hardware resources. Bring into Bilinear transformation is applied in the middle and later stages. The z-domain transfer function of the fractional-order loop filter in the discrete-time domain is obtained, and its common denominator is rearranged into the following form:

[0111]

[0112] In the discrete-time domain of a digital signal, the behavior of this filter is described by a difference equation. In this embodiment, an IIR (Infinite Impulse Response) filter approximation method is used. This method has advantages in terms of resource consumption and operating speed, making it more suitable for high-performance hardware implementation. The z-domain transfer function mentioned above... The equivalent time-domain difference equation has the following form:

[0113] ;

[0114] Generally speaking, and equal ; and It is by , , , , , The function. Whenever the algorithm is updated. , , , , , Then, a new set is calculated. and Coefficients. In hardware, this is executed through a series of pipelined multiply-accumulate (MAC) units, implemented using combinational logic and lookup tables (LUTs), where the coefficients... and It is loaded into the corresponding register in real time. The filter characteristics are changed immediately in the next clock cycle. The final calculation result is output to the numerically controlled oscillator.

[0115] Digitally Controlled Oscillator (DCO): The DCO operates based on the control signal output from the FO-LF. After feedforward compensation, the output frequency of the signal is adjusted. Its nominal center frequency is... (Default value), gain is For control signals Compensation control signal for feedforward compensation Provided by the feedforward module, it is used to offset the DCO frequency shift caused by sudden temperature changes. This refers to the tuning sensitivity of the DCO, which represents the frequency change caused by a unit change in the control signal, and the instantaneous frequency of the DCO output. for:

[0116]

[0117] The clock phase of the DCO output It is the integral of its frequency:

[0118]

[0119] Frequency divider: Located between the DCO output and the PD / PFD feedback input, its division ratio is... This can be set by the user or the system. The clock frequency after frequency division is... The corresponding phase Feedback is sent to PD / PFD and participates in the error. The calculation. The recovered DCO output clock can then be used. The input video data stream is sampled and processed to output a clean video data stream.

[0120] The core module of FOCDR forms a negative feedback control loop through the aforementioned components, and its basic goal is to drive the phase error. Approaching zero, causing the feedback clock phase Accurately track the phase of the input reference clock This allows us to obtain a clean and stable clock from the raw data stream.

[0121] Specifically, in this embodiment and some embodiments of the present invention, the two-layer adaptive control module and the feedforward module adjust the key parameters in this loop ( , , These mechanisms (such as FOCDR, etc.) enable adaptive behavior and collectively optimize the core performance of FOCDR.

[0122] Understandably, in this embodiment and some embodiments of the present invention, a fractional-order loop filter (FO-LF) is used, by introducing a fractional order. Compared to traditional CDRs, these parameters provide greater freedom for the entire system, exhibit more diverse loop characteristics, and give the adaptive control system more adjustment space, thus providing the basic conditions for the entire system to withstand harsh conditions and operate under multiple conditions.

[0123] Specifically, in this embodiment and some embodiments of the present invention, a two-level fuzzy adaptive control is employed. This involves the division of labor and efficient collaboration between a Fast Control Layer (FCL) and a Slow Control Layer (SCL) to dynamically optimize the performance of the Fractional Clock Data Recovery (FOCDR) core. Considering the stringent real-time response requirements of high-speed video transmission and the speed limitations of complex optimization algorithms in hardware implementation, the system employs a complementary combination of a Fast Control Layer and a Slow Optimization Layer with a slower timescale. The FCL uses a fuzzy control strategy to directly adjust the parameters of the FOCDR core loop filter to achieve adjustment capabilities. The Slow Control Layer utilizes intelligent algorithms to continuously optimize the characteristics of the Fast Control Layer based on long-term performance indicators, improving the system's adaptability to long-term drift and aging effects.

[0124] Understandably, the stability and continuity of the clock are crucial in high-speed video transmission. An overly sensitive control system may introduce unnecessary disturbances due to large-scale, high-frequency adjustments to the CDR loop parameters, negatively impacting the smooth transmission of the video signal. Therefore, specifically, in this embodiment and some embodiments of the present invention, a fuzzy control strategy is used to construct the Fast Control Layer (FCL), leveraging the good adaptability of fuzzy control to complex systems and its inherent smooth control characteristics. Fuzzy logic processes imprecise and fuzzy information based on empirical knowledge, making the parameter adjustment process of the FCL more gradual and robust when responding to loop dynamics. This avoids system oscillations or performance degradation caused by overly drastic or frequent control actions, thereby ensuring the quality and reliability of video transmission. In this embodiment and some embodiments of the present invention, the FCL is used to respond to the dynamic changes of the CDR on a small timescale of microseconds to milliseconds, adjusting the proportional gain of the fractional-order loop filter (FO-LF) in real time through a fuzzy logic controller. Integral coefficient Fractional order And a series of control parameters.

[0125] The inputs to the FCL are two key state variables that characterize the current dynamics of the FOCDR loop: instantaneous phase error. and its rate of change This constitutes the input vector of the FCL:

[0126] ;

[0127] in, Provided directly by the phase / frequency detector (PD / PFD), Depend on Calculated using first-order backward difference (e.g., within the FCL), it reflects the trend of phase error variation:

[0128] ；

[0129] Specifically, in this embodiment and some embodiments of the present invention, the fuzzy controller used in the Fast Control Layer (FCL) adjusts the CDR loop parameters through fuzzification, fuzzy inference based on fuzzy rules, and defuzzification, as detailed below.

[0130] A. Blurring

[0131] The process of blurring is to... Mapping to predefined fuzzy sets, the FCL determines the degree to which an input value belongs to each fuzzy set (i.e., its membership degree). Specifically, for any input value, the FCL calculates its membership degree with all fuzzy sets in parallel, thus determining the degree of membership of the current input to the fuzzy sets. The FCL can be designed as a parallel pipelined hardware logic module to ensure running speed. For each input, its five corresponding triangular membership functions are implemented by hardware units. Each unit uses a parallel comparator to determine the input value. The fuzzy set to which it belongs is then used to calculate the specific membership value using subtractors and multipliers. In this embodiment, the input is divided into 5 fuzzy sets, which are for illustrative purposes only and not for limitation.

[0132] Specifically, targeting Five fuzzy sets were defined: {Negative Large (NB), Negative Small (NS), Zero (ZE), Positive Small (PS), Positive Large (PB)}; [This is for...] Five fuzzy sets are also defined: {Negative Large (DNB), Negative Small (DNS), Zero (DZE), Positive Small (DPS), Positive Large (DPB)}.

[0133] The membership value of each fuzzy set is described by a triangular membership function. The triangular membership function consists of three vertex parameters. definition:

[0134]

[0135] and These are the points on the left and right bases of the triangle (with a membership degree of 0). These are the vertices of the triangle (with a membership degree of 1), representing typical values ​​or centers of the fuzzy set (these vertex parameters are optimized and configured by the Slow Control Layer (SCL) to adjust the control behavior of the FCL).

[0136] B. Fuzzy reasoning

[0137] After fuzzification, the input is evaluated to determine its membership in a fuzzy set, followed by fuzzy inference. Fuzzy inference is the core decision-making process of FCL, which determines the direction and intensity of output adjustments based on a pre-defined rule base. The core of this rule base is a set of fuzzy rules in the form of "IF-THEN". These rules comprehensively cover the input variables. and All combinations of fuzzy states, and specify the output variable for each case. , , Adjustments to control parameters, such as: Based on the current degree of membership of the input, each rule is adjusted as follows:

[0138] IF is AND is THEN is AND is AND .

[0139] That is, if < ,and If > is true, then < for ,and for ,and for >;Among them,

[0140] It represents the specific fuzzy set to which the input belongs. The output represents the set of corresponding output adjustment values. According to the definition of membership functions, there can be overlap between membership functions, and the input may belong to different fuzzy sets simultaneously. Therefore, multiple rules will be triggered simultaneously during the calculation process. Thus, it is necessary to calculate the trigger strength of multiple rules to obtain the final output. For the ... The degree to which a rule is activated by the current input, i.e., its trigger strength. To calculate:

[0141]

[0142] in, It is input In fuzzy sets membership degree It is input In fuzzy sets The membership degree. In this embodiment, fuzzy rules are implemented as a large lookup table (LUT). The trigger strength of each rule. It is implemented by a set of parallel comparators.

[0143] C. Defuzzification

[0144] Defuzzification is the process of synthesizing the outputs of all activated rules into a final, precise output vector of the fuzzy controller. The process of constructing a control adjustment vector from control adjustment values ​​involves merging the fuzzy suggestions from all activated rules into a single executable output value. Use a weighted average formula to synthesize each trigger intensity:

[0145] ；

[0146] in, They are the first In the rules The specified output value.

[0147] The incremental output vector calculated by FCL The actual operating parameters of the FO-LF are updated using only multipliers and adders. The update process is as follows:

[0148] ；

[0149] The parameters obtained from these dynamic calculations are directly substituted into the mathematical model of the fractional-order loop filter (FO-LF). This adjustment changes the filtering characteristics (gain and phase response) of the FO-LF in real time, thereby altering its output. Ultimately, the control signal Superimposed compensation control signal They jointly drive the DCO, affecting its output frequency. and phase This adjustment mechanism forms a closed-loop adaptive control system where the FCL (Fuzzy Logic Controller) performs rapid adjustments. The adjustment criterion is the output of the fuzzy rule base, which is based on the current phase error. and error change rate This is derived from a comprehensive judgment of the fuzzy state. When both the error and the rate of change of error are large and in the same direction, it may be necessary to increase... To speed up the response; when the error is close to zero or overshoot occurs, it may be necessary to reduce the speed. To enhance stability. Fractional order. and The adjustment criteria are also based on the output of the fuzzy rule base. Changing the value of affects the phase margin and gain margin of the loop filter, thus impacting the system's dynamic performance and its ability to suppress jitter at specific frequencies. When the system requires stronger low-frequency jitter tracking capability, The characteristics of the filter can be changed. FCL adjusts these two parameters in real time, with each control cycle (synchronized with the CDR loop's operating clock) based on the latest... and The update is performed. The goal is to bring the instantaneous phase error to zero as quickly as possible and maintain stability.

[0150] Specifically, in this embodiment and some embodiments of the present invention, unlike the fast control layer, the slow control layer (SCL) operates on a longer time scale. The fungal growth optimizer is improved using the optimization method of the present invention, resulting in the improved fungal growth optimizer (IFGO). The key parameters of the membership function of the fuzzy controller and the weights of the fuzzy rules in the fast control layer (FCL) are adjusted to optimize the overall performance of the entire system under long-term operation.

[0151] Understandably, in this embodiment and some embodiments of the present invention, the slow control layer optimizes the characteristics of the fast control layer instead of directly adjusting the loop parameters to avoid potential "control conflicts" or mutual interference between different control layers, ensuring the coordination and stability of the entire adaptive system. The optimization process of SCL is an iterative optimization process that runs continuously in the background, aiming to find the membership function parameter configuration and rule weight configuration that optimizes the long-term performance of the CDR system for FCL. Its goal is to minimize the long-term average bit error rate (BER) under environmental constraints (temperature, interference factors, etc.). The parameters adjusted by SCL are the input variables of the fuzzy controller in FCL (phase error). and error change rate The membership function is defined by a set of parameters, and the weights corresponding to each rule in the FCL fuzzy rule base are also considered. (The phase error is used as an example.) and error change rate For example, they each have 5 fuzzy sets. Each fuzzy set's triangular membership function is defined by three vertex parameters. The IFGO algorithm finds the optimal combination of membership function parameters by minimizing the long-term average bit error rate (BER) under constraints of environmental features (temperature, interference factors, etc.). This means that SCL will try different membership function shapes and positions, as well as output adjustments. Each has a corresponding numerical value, and these control parameters to be optimized together constitute a complete set of control parameters (i.e., a control parameter vector). Specifically, in this embodiment, each control parameter vector... There are a total of 105 control parameters, or 105 dimensions, including the membership parameters of each fuzzy control set, totaling (3×5)×2=30. There are also 25 fuzzy rules, each corresponding to 3 parameters. There are a total of 75 parameters.

[0152] By adjusting the parameters in this set of control parameters, SCL alters the fuzzification method of FCL regarding phase error and error rate of change, as well as the relative contributions of different fuzzy rules to the final control output, thereby fine-tuning the response characteristics of the entire fuzzy control. SCL adjusts these weights using the IFGO method. By adjusting the rule weights, SCL can enhance or weaken the contribution of certain specific rules to the FCL output, thus finely adjusting the FCL control strategy to adapt to specific noise environments or system aging.

[0153] Figure 3 This is a flowchart illustrating the application of the optimization method of the present invention in this embodiment. Specifically, in this embodiment and some embodiments of the present invention, when environmental characteristics change or are subject to severe interference, or according to a preset cycle, the optimization method of the present invention is applied, including steps S301 to S309.

[0154] Step S301, based on the size of the spore population and the dimension of the control parameter vector Generate size is A chaotic matrix, wherein the columns of the chaotic matrix correspond to the dimensions of the control parameter vector, and the rows of the chaotic matrix correspond to the spores in the spore population.

[0155] Specifically, a chaotic matrix is ​​generated using a Logistic chaotic mapping, and the iterative formula for each row of the chaotic matrix is ​​as follows: , , , ;in, It is the first chaotic matrix Line number The elements of the column.

[0156] Step S302: Map the elements of each column vector of the chaotic matrix to the value space of the corresponding dimension of the control parameter vector to obtain the values ​​of each dimension of the spore. After completing the mapping, a total of The spores mentioned above The number of spores is the initial value of the spore population.

[0157] Specifically, the first spores The Dimensional parameters By generating chaotic matrix elements Initialize by mapping to the above value range:

[0158]

[0159] in, and It is the first of the control parameter vectors Upper and lower bounds of the dimension parameter.

[0160] Step S303, Iteration rounds ,

[0161] Step S304, calculate the current round The value of the adaptive operator :

[0162] ,

[0163] in, It is the first The value of the adaptive operator in the next iteration. and These are the upper and lower limits of the adaptive operator's values.

[0164] Step S305: Generate a random number for each spore in the spore population, wherein the first... The random number corresponding to each spore is ,like Then the first The first spore executes step S306, the global exploration strategy; otherwise, the second spore... Each spore is processed in step S307.

[0165] Step S306, the Each spore executes a global exploration strategy:

[0166] ;

[0167] in, It refers to the current position of three spores randomly selected from the spore population. It is the current position of the spore with the highest fitness in the spore population. It is an exploration factor that decreases with each iteration, used to improve the search breadth in the early stages of the algorithm and the convergence accuracy in the later stages; it is a step size scaling factor, a random scalar step size. Based on two random variables that follow a normal distribution and The generation and calculation formula is:

[0168] ;

[0169] in, Follows a mean of 0 and a standard deviation of The normal distribution It follows a standard normal distribution (mean 0, standard deviation 1). The calculation formula is as follows:

[0170] ;

[0171] in, The value is 1.6. It is the Gamma function.

[0172] Step S307, the Individual spores employ a localized utilization strategy: ; It is a utilization factor that decreases with each iteration, used to improve the search breadth of the algorithm in the early stages of iteration and the convergence accuracy in later stages. It is the current position of a spore randomly selected from the spore population.

[0173] Step S308, if the new position The fitness is better than that of the original position. The fitness mentioned above will then be the first The position of each spore is updated to the new position. Otherwise, retain the original position. Furthermore, if the new position If the fitness of a spore is better than the optimal fitness in the spore population, then the optimal spore in the spore population is updated to the spore with the best fitness. The spores mentioned.

[0174] In this embodiment and some embodiments of the present invention, the first The spores at position fitness Calculate using the following formula:

[0175] ;

[0176] in, This represents a neural network model trained offline, where the input to the neural network model is the first... The location of the spores The temperature The interference amplitude and the interference frequency The output is the corresponding long-term bit error rate. .

[0177] Step S309: Determine whether the iteration termination condition is met, such as reaching the maximum number of iterations or the rate of change of the optimal fitness being less than a preset threshold. If so, output the spore with the highest fitness in the spore population as the value of the target control parameter vector and send it to the fuzzy controller in the FCL. Otherwise, return to step S302.

[0178] Figure 4 This is a schematic diagram illustrating the fast control layer adaptive capability of applying the optimization method of the present invention in the scenario of this embodiment. For example... Figure 4 As shown, this demonstrates the rapid adaptive adjustment capability of FCL under conditions of sudden changes in input signal characteristics (such as jitter amplitude / frequency) or strong interference introduced by the channel. Specifically, as... Figure 4 As shown, the horizontal axis represents time, and the vertical axis represents instantaneous phase error. The figure includes two stages, representing normal signal / channel conditions and deteriorated signal / channel conditions, respectively. The red curve represents a traditional CDR system, which uses fixed or limited-range loop parameters. When signal / channel conditions deteriorate, the phase error increases significantly, resulting in large peak values, persistent oscillations, or long recovery times. The blue curve represents the system of this invention with FCL adaptation. FCL adjusts the fractional-order loop filter parameters in real time, which can more effectively suppress phase error fluctuations when signal / channel conditions deteriorate. The peak error is smaller, oscillations are quickly suppressed, and the system can adapt to new conditions and recover to a better operating state more quickly. (Refer to...) Figure 4 It is understandable that when dynamic signal characteristics change (temperature change) or severe interference occurs in the channel, applying the optimization method of this embodiment of the invention in the Fast Control Layer (FCL) can ensure the instantaneous performance and robustness of the system under complex dynamic inputs.

[0179] Figure 5 This is a schematic diagram illustrating the adaptive capability of the slow control layer in the scenario described in this embodiment, applying the optimization method of the present invention. (See diagram for example.) Figure 5As shown, SCL executes according to a preset cycle to cope with long-term parameter changes encountered by the system, such as device aging or slow environmental temperature drift, and maintain the system's high performance. The horizontal axis represents multiple working cycles of long-term operation, and the vertical axis represents a key long-term performance indicator, the average bit error rate (BER). The red curve represents the system without SCL optimization, whose performance gradually deteriorates over time (due to accumulated parameter drift), manifested as a gradual increase in the metric. The blue curve represents the system of this embodiment of the invention with SCL optimization. SCL actively combats the impact of parameter drift by periodically adjusting the membership function parameters of FCL, enabling the system's long-term performance to be maintained at a low and relatively stable level. Although there may be minor fluctuations caused by SCL optimization adjustments, SCL still makes an indispensable contribution to ensuring the long-term stability and reliability of the system.

[0180] Furthermore, such as Figure 2 As shown, in this embodiment and some embodiments of the present invention, a feedforward compensation (FC) module is also used to actively and quickly compensate for the direct impact of significant environmental disturbances on the FOCDR, thereby reducing the burden on the feedback control loop. In harsh environments such as automotive applications, there are transient disturbances such as drastic temperature changes that may cause rapid and large drift. Traditional feedback control systems respond slowly to such sudden changes and may lead to large instantaneous errors. To solve this problem and meet the requirements of transient robustness for high-speed video transmission, the present invention introduces a feedforward compensation module, aiming to achieve advanced and rapid disturbance cancellation. The module monitors the ambient temperature in real time. (From temperature sensor), and based on a temperature-dependent perturbation effect model, predict the impact of the current temperature Expected FOCDR output offset This embodiment uses a second-order polynomial function as the model for the impact of this disturbance:

[0181]

[0182] Among them, model coefficients These are fixed values ​​determined through a one-time offline characterization and calibration process. This process is described in detail below.

[0183] First, characterize the DCO: During the design verification or production testing phase of the DCO, place it in a temperature-controlled environment. Without closing the CDR main feedback loop or under a specific preset test mode, measure and record the actual output frequency or deviation from the nominal frequency of the DCO at multiple different ambient temperature points (covering the entire operating temperature range, which is typically -40 to +125°C in automotive applications). This will generate a raw dataset containing data pairs of (ambient temperature, DCO frequency deviation).

[0184] Secondly, model coefficient fitting is performed: standard curve fitting techniques are used, specifically least squares polynomial regression, to fit the second-order polynomial model to the collected original dataset. This fitting process calculates the coefficient set that best describes the DCO temperature drift characteristics. .

[0185] Finally, the coefficients are stored: the obtained set of coefficient values ​​are burned as fixed parameters or stored in the system's non-volatile memory for use by the feedforward compensation module during operation.

[0186] Specifically, in this embodiment and some embodiments of the present invention, the predicted output frequency after temperature perturbation... .

[0187] FOCDR requires a compensation control signal to eliminate the influence of external interference. The calculation is as follows:

[0188]

[0189] In this way, the relative change in DCO frequency caused by temperature is adjusted. This offsets the fluctuations, preventing them from becoming drastic due to temperature shifts. Figure 6 This is a schematic diagram illustrating the spike suppression performance gain of the feedforward compensation module in this embodiment when dealing with instantaneous temperature pulse disturbances. Specifically, as shown... Figure 6 As shown, comparing the instantaneous phase error curves of the same instantaneous and short-duration temperature pulse disturbance (e.g., a rapid temperature rise followed by a rapid fall) in two scenarios in this embodiment with and without the feedforward compensation module activated, the effectiveness of the feedforward compensation mechanism in suppressing transient spike disturbances is clearly demonstrated. The red curve shows the system response relying solely on the FOCDR module and dual-layer feedback control (FCL+SCL) (without feedforward compensation): during the temperature pulse, a significant instantaneous spike in phase error occurs, which the feedback control system then attempts to correct back to the baseline level. The blue curve shows the response of the complete system (FOCDR core + dual-layer feedback control + feedforward compensation module): because the feedforward compensation module pre-adjusts the compensation control signal according to the rapid temperature change. The instantaneous spike impact caused by temperature pulses on phase errors is significantly weakened or almost eliminated, and the system exhibits stronger disturbance suppression capability. This demonstrates the key role of the feedforward compensation module in rapidly suppressing and weakening predictable, short-term significant disturbances (especially temperature-related rapid transients), thereby effectively protecting the stability of clock data recovery.

[0190] Furthermore, it is understood that in this embodiment and some embodiments of the present invention, the feedforward compensation chooses to directly adjust the control signal of the DCO, rather than the loop filter parameters, because changing the control signal of the DCO can most quickly and directly correct the clock frequency, thereby rapidly offsetting the direct impact of disturbances such as temperature on the DCO frequency and quickly reducing phase error. At the same time, this adjustment of the DCO control signal does not change the filtering characteristics of the FO-LF. Therefore, the optimization method of Embodiment 1 of the present invention and the FCL and SCL collaborative optimization method in this embodiment do not conflict with the feedforward compensation, ensuring the synergy and effectiveness of the overall system control strategy.

[0191] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium.

[0192] Example 3

[0193] like Figure 7 As shown, Embodiment 3 of the present invention provides a terminal device, including at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps in the optimization method for video transmission network CDR as described in the first aspect of the present invention.

[0194] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripherals, voltage regulators, and power management circuits, via interfaces, as is well known in the art. Interfaces provide a connection between the bus and the transceiver, such as communication interfaces or user interfaces. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.

[0195] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.

[0196] Example 4

[0197] Embodiment 4 of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the optimization method for video transmission network CDR as described in the first aspect of the present invention.

[0198] Those skilled in the art will understand from the foregoing description that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes, but is not limited to, various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic storage devices, and optical storage devices.

[0199] Example 5

[0200] Embodiment 5 of the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the steps in the optimization method for video transmission network CDR as described in the first aspect of the present invention.

[0201] Based on the above detailed description of specific embodiments of the present invention, a clearer understanding of the present invention provides the following advantages:

[0202] This invention, through acquiring environmental characteristics and control parameter vectors, and using an optimization method with an adaptive exploration strategy to iteratively optimize the spore population, enables the CDR in the video transmission network to adaptively adjust control parameters in complex and dynamically changing application environments to achieve optimal video transmission quality. Compared to traditional CDR technology with fixed parameters or simple feedback adjustment, this adaptive optimization method can better cope with harsh working conditions such as wide temperature range variations, strong electromagnetic interference, and changing operating conditions, significantly improving the robustness and adaptability of clock data recovery.

[0203] The optimization method of this invention is used for slow control of fuzzy controllers. Combined with the fast and slow control dual-layer architecture of fuzzy controllers, it can respond to environmental changes on a large time scale, enabling high-speed video transmission systems to continuously adapt to long-term drift, environmental changes and device aging, and significantly enhancing the overall robustness and stability of the system under harsh conditions such as wide temperature range and strong interference.

[0204] The optimization method of this invention employs an adaptive operator during iteration, enabling a dynamic balance between global exploration and local exploitation during the optimization process. In the initial iteration phase, a larger adaptive operator value and a global exploration strategy are used to quickly find potential optimal solution regions in the parameter space. As iteration progresses, the adaptive operator value is gradually reduced, increasing the probability of executing the local exploitation strategy. This allows for a more refined search near the already found optimal regions, further improving the accuracy of the solution. This strategy ensures global search capability, avoiding getting trapped in local optima, while effectively improving optimization efficiency in the later stages, quickly converging to the global optimum, thereby achieving high-precision optimization of the CDR system control parameters.

[0205] The optimization method of this invention innovatively introduces mechanisms such as chaotic mapping and Levy flight. Chaotic mapping is used to generate the initial spore population, making the initial population more evenly distributed and covering a wider area in the parameter space, which helps the algorithm escape local optima early and improves global search capability. The Levy flight mechanism further enhances the algorithm's global exploration capability through its randomly generated large step jumps, effectively preventing the algorithm from getting trapped in local optima too early. The introduction of these innovative mechanisms enables the optimization algorithm to find the optimal solution more efficiently when facing complex optimization problems, providing a more powerful technical solution for the optimization of CDR systems.

[0206] The optimization method of this invention uses an offline trained neural network model to directly predict the long-term bit error rate (BER) as the spore fitness based on environmental features and candidate parameter vectors. This avoids time-consuming and potentially system-impacting real-time online performance measurements during the optimization iteration process, making the optimization process more efficient and feasible, and the evaluation results more objective and accurate.

[0207] The optimization method of this invention is applicable to various high-speed video transmission application scenarios, such as automotive electronics (ADAS, autonomous driving), remote control (on-site monitoring, remote operation vision), and high-end industrial automation (machine vision), which have extremely high requirements for real-time performance, reliability, and image quality. It can effectively solve the challenges faced by existing CDR technology in these fields, providing important technical support for the development of related industries, and has broad application prospects and significant practical implications.

[0208] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. An optimization method for video transport network clock data recovery (CDR), characterized in that, include: The environmental features and control parameter vectors are obtained, and the control parameter vectors are constructed based on the fuzzy controller for recovering the clock data (CDR) of the video transmission network. An initial value for the spore population is generated based on the control parameter vector. An optimization method with an adaptive exploration and utilization strategy is used to iteratively optimize the spore population so that it adapts to the optimal video transmission quality under the environmental characteristics. Each spore in the spore population corresponds to a value of the control parameter vector. The adaptive exploration and utilization strategy includes using an adaptive operator to control the probability of using a global exploration strategy and a local utilization strategy in each iteration. After iterative optimization is completed, the spore with the highest fitness in the spore population is used as the value of the target control parameter vector and sent to the fuzzy controller.

2. The method of claim 1, wherein, The control parameter vector includes the membership parameters of each fuzzy set of the fuzzy controller and the control adjustment amount of each fuzzy rule; the control adjustment amount includes the proportional gain, integral gain and fractional order of the fuzzy controller; The initial values ​​of the spore population are generated based on the control parameter vector, including: according to the size of the spore population and the dimension of the control parameter vector a chaotic matrix of size is generated, the columns of which correspond to the dimension of the control parameter vector and the rows of which correspond to the spores in the spore population; The elements of each column vector of the chaotic matrix are mapped to the value space of the corresponding dimension of the control parameter vector to obtain the values ​​of each dimension of the spore. After the mapping is completed, a total of The spores mentioned above The number of spores is the initial value of the spore population.

3. The method according to claim 1, characterized in that, An optimization method with an adaptive exploration and utilization strategy is used to iteratively optimize the spore population to adapt it to the optimal video transmission quality under the environmental characteristics, including: Based on the number of iteration stages , Determine the first Each iteration phase The value of the adaptive operator is , , The number of iteration stages; No more than the maximum number of iterations in the optimization process; For the In each iteration, a random number is generated for each spore in the spore population, where the first random number is... The random number corresponding to each spore is The first Round iteration belongs to the first Each iteration phase ; like Then the first The first spore executes a global exploration strategy; otherwise, the second spore... Each spore employs a localized utilization strategy.

4. The method according to claim 3, characterized in that, The number Equal to the maximum number of iterations in optimization The adaptive operator follows the formula that changes with the number of iterations. Adjustment: ， in, It is the first The value of the adaptive operator in the next iteration. and These are the upper and lower limits of the adaptive operator's values.

5. The method according to claim 3, characterized in that, The optimization method is a fungal growth optimization method, wherein the global exploration strategy is used to simulate hyphal branching growth, and the local utilization strategy is used to simulate protoplasm flow to nutrient source concentration. The global exploration strategy is: ； The local exploitation strategy is: ； in, It is the 1st in the spore population The starting position of the current round of the spores. New locations after exploration or utilization It refers to the current position of three spores randomly selected from the spore population. It is the current position of the spore with the highest fitness in the spore population; It is an exploratory factor. It is the step scaling factor. It is a random scalar step size generated based on the Levy distribution; It is a factor of utilization. It is the current position of a spore randomly selected from the spore population.

6. The method according to any one of claims 1-5, characterized in that, The environmental characteristics include temperature. Interference amplitude and interference frequency The optimal video transmission quality under the environmental characteristics mentioned includes the long-term bit error rate under the environmental characteristics within a preset monitoring period. An optimization method with an adaptive exploration and utilization strategy is used to iteratively optimize the spore population to adapt it to the optimal video transmission quality under the environmental characteristics, including: For the Round iteration, It is the 1st in the spore population The spores mentioned above start from the beginning position of the current round. A new location after exploration or utilization; If the new position The fitness is better than that of the original position. The fitness mentioned above will then be the first The position of each spore is updated to the new position. ; Otherwise, retain the original position. ; Furthermore, if the new position If the fitness of a spore is better than the optimal fitness in the spore population, then the optimal spore in the spore population is updated to the spore with the best fitness. The spores mentioned.

7. The method according to claim 6, characterized in that, No. The spores at position fitness The long-term bit error rate compared to the output of the offline-trained neural network model Inversely proportional: The input to the neural network model is the first... The location of the spores The temperature The interference amplitude and the interference frequency The output is the corresponding long-term bit error rate. .

8. A computer-readable storage medium, characterized in that, It stores a program that, when executed by a processor, implements the optimized method for recovering CDR for video transmission network clock data as described in any one of claims 1-7.

9. A terminal device, characterized in that, It includes a memory, a processor, and a program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the optimized method for recovering clock data (CDR) for video transmission networks as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the optimized method for recovering CDR (Clock Data Retrieval) for video transmission networks as described in any one of claims 1-7.

Images