Signal interference suppression method with combination of multi-level carrier wave coordination and dynamic optical path compensation

Abstract

The invention relates to the technical field of optical communication, and discloses a multi-level carrier wave coordination and dynamic optical path compensation combined signal interference suppression method, which comprises the following steps that: a transmitting unit transmits a cognitive probe carrier wave and a data carrier wave to an optical path; the receiving unit receives and processes the transmitted cognitive probe carrier wave to generate cognitive probe carrier wave data; the cooperative intelligent controller updates a dynamic optical path twinborn model based on the data, evaluates model parameter confidence, determines a self-adaptive cognitive probe carrier detection strategy according to the model parameter confidence, and instructs a transmitting unit to reconfigure transmission of cognitive probe carriers; and the cooperative intelligent controller cooperatively adjusts emission parameters of the data carrier and controls the dynamic optical path compensation unit to compensate the optical path based on a high-confidence-coefficient optical path twinborn model. Dynamic interference in an optical path can be actively coped with, and the signal transmission quality, reliability and environmental adaptability of an optical communication system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of optical communication technology, and in particular to a signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation. Background Art

[0002] With the explosive growth of global data traffic, the requirements for the bandwidth capacity, transmission distance, and flexibility of optical communication networks are becoming increasingly stringent. Optical fiber, as the primary medium for information transmission, offers the advantages of low loss and enormous bandwidth, but it is not an ideal transmission channel. When optical signals travel long distances through optical fibers, they are inevitably affected by the cumulative effects of various physical effects. These effects include linear impairments such as chromatic dispersion (CD) and polarization mode dispersion (PMD), as well as nonlinear effects that become more pronounced at higher optical powers, such as self-phase modulation (SPM), cross-phase modulation (XPM), and four-wave mixing (FWM). These physical impairments can lead to signal waveform distortion, pulse broadening, increased phase noise, and crosstalk between different wavelength channels, ultimately limiting the system's transmission performance and the achievable bit rate-distance product.

[0003] Further complicating matters, the aforementioned optical path impairment characteristics are not static but rather exhibit significant dynamics. Environmental factors such as temperature fluctuations, mechanical vibration, stress on optical cables, aging of optical components within the network, and dynamic reconfiguration of optical paths can all cause the physical parameters of optical fiber links to drift and fluctuate rapidly or slowly over time. For example, PMD characteristics are particularly sensitive to environmental changes, with their instantaneous values potentially changing on the order of milliseconds or even microseconds. This dynamic uncertainty poses significant challenges to the stable and reliable operation of optical communication systems, making traditional static or slow adaptive compensation solutions difficult to address.

[0004] Existing optical communication systems employ a range of technologies to monitor and compensate for these impairments. For example, optical performance monitoring (OPM) modules are deployed to monitor key link parameters, such as optical signal-to-noise ratio (OSNR) and dispersion. At the receiver, digital signal processing (DSP) technology is widely used to compensate for linear impairments, such as electronic dispersion compensation (EDC) and adaptive PMD equalization using digital filters. For nonlinear effects, researchers have also proposed compensation algorithms such as digital back-propagation (DBP).

[0005] However, current technologies still have numerous shortcomings when addressing complex and dynamic optical network environments. Many existing optical performance monitoring methods often provide incomplete, inadequate, or limitedly accurate optical path status information, making it difficult to accurately and dynamically capture the instantaneous changes in all key impairment parameters. This results in compensation mechanisms often lagging behind actual optical path changes or being based on inaccurate channel models, thus impacting compensation effectiveness. When multiple impairments coexist and intertwine, existing technologies struggle to effectively decouple them and provide targeted, precise compensation. Furthermore, there is often a lack of efficient coordination mechanisms and a unified, real-time understanding of optical path status between transmitter parameter configuration (such as modulation format, transmit power, and precoding), adjustment of physical compensation components in the optical path (such as tunable dispersion compensators and dynamic gain equalizers), and signal processing at the receiver. This uncoordinated, "independent" compensation approach can easily lead to local optimality in overall system performance, hindering the full potential of optical fiber links. Especially when facing rapidly changing optical path conditions, existing systems generally lack the comprehensive ability to actively and intelligently adjust detection strategies to focus on the damage parameters with the highest uncertainty, and perform global optimization and collaborative compensation on this basis.

[0006] Therefore, there is an urgent need for a technical solution that can accurately perceive the dynamic optical path status in real time and, on this basis, perform multi-level, intelligent collaborative interference suppression to effectively improve the transmission performance, reliability, and adaptability of optical communication systems in complex dynamic environments. Summary of the Invention

[0007] The present invention aims to solve the problems of insufficient complex dynamic interference suppression capability, inaccurate optical path status perception, and low degree of multi-component collaborative optimization in existing optical communication systems.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: A first aspect of the present invention provides a signal interference suppression method combining multi-level carrier collaboration and dynamic optical path compensation.

[0009] This method achieves active perception, precise modeling, adaptive adjustment, and collaborative suppression of signal interference in optical communication systems by introducing an innovative collaborative mechanism. 1. Active optical path perception and interference feature extraction based on cognitive probe carrier: This method first launches specially designed cognitive probe carriers (Cognitive Probe Carriers (CPCs)) into the optical path. These CPCs are not traditional fixed pilot signals, but instead have a specific signal structure that makes them highly sensitive to impairments and interference factors in the optical fiber link, such as chromatic dispersion, polarization mode dispersion (PMD), nonlinear effects, and various types of crosstalk and noise. CPCs are transmitted at low power to minimize the impact on data carriers (DCs).

[0010] At the receiving end or at a designated monitoring point in the optical path, the transmitted CPCs signal is captured and analyzed, and information such as signal distortion, attenuation, phase change, and intermodulation products are extracted to form cognitive probe carrier data. These data reflect the instantaneous state of the optical path and the existing interference characteristics.

[0011] 2. Construction, update, and confidence assessment of the dynamic optical path twin model (OPT): This method further utilizes the acquired cognitive probe carrier data , and optionally, historical performance feedback from the data carrier , to dynamically build and update an Optical Path Twin (OPT), that is This OPT is a digital real-time representation of the physical characteristics of the actual optical path and the signal propagation effect. The state vector of OPT is Can include the dispersion coefficient of each segment of the optical path , PMD vector , nonlinear coefficient , and specific interference source characteristics Estimation of parameters.

[0012] The OPT renewal process can be summarized as follows: ; in, represents an update algorithm based on, for example, Kalman filtering, particle filtering, or machine learning, which integrates new observations into the existing model. is the parameter set of the algorithm.

[0013] One of the key innovations is that this method will adjust the parameters of the OPT model The confidence evaluation mechanism is introduced into the estimation of . Confidence It reflects the reliability or accuracy of the current parameter estimate, and its evaluation can be expressed as: ; in, is the variance of the parameter estimate, is a measure of the quality of the relevant CPC data, is the confidence evaluation function, as its parameters.

[0014] 3. Adaptive cognitive probe carrier detection strategy based on OPT confidence: Another core innovation of this method is that it does not use a fixed CPC detection scheme, but rather uses the confidence evaluation results of the OPT model parameters. , dynamically adjust and optimize the CPC detection strategy for the next cycle . It can be expressed as: ; in, is the strategy generation function. Specifically, if the confidence of some parameters in OPT Below the preset threshold , or its rapid changes indicate that the model's understanding of these aspects is not accurate or is outdated. The system will instruct CPCs to adjust their transmission parameters, for example: Increase the transmit power (within the permitted range) of CPCs that are more sensitive to detecting these low-confidence parameters.

[0015] Changing the signal waveform or sequence of CPCs can enhance the detection of specific effects.

[0016] Adjust the spectral position or spatial placement of CPCs (if supported) to more precisely focus on optical path segments or effects with high uncertainty.

[0017] Increase the frequency or density of detection of these parameters. This adaptive detection mechanism allows detection resources to be intelligently directed to where information is most needed, effectively improving the overall accuracy and timeliness of OPT and forming an on-demand perception closed loop.

[0018] 4. Multi-level collaborative interference suppression based on high-precision OPT: After obtaining a high confidence and high precision OPT model Finally, the method performs multi-level coordinated adjustments through a collaborative intelligent controller (CIC) to suppress signal interference on the data carrier: Data carrier transmission parameter optimization: CIC utilization Predict the transmission performance of the data carrier under the current channel conditions and optimize the transmission parameters of the data carrier accordingly , such as modulation format, coding scheme, power allocation, digital predistortion coefficients or precoding matrix, to maximize predefined performance indicators (such as expected transmission quality, rate, etc.).

[0019] ; Dynamic optical path compensation unit coordinated adjustment: At the same time, CIC Accurately estimate optical path impairments (such as accumulated dispersion and instantaneous PMD) and generate control signals , used to adjust the settings of dynamic compensation units in the optical path (such as tunable dispersion compensators, polarization controllers, dynamic gain equalizers, etc.).

[0020] ; This coordinated adjustment of the transmitter (data carrier) and the transmission link (optical path compensation unit) is based on the same precise OPT model, calibrated in real time by CPCs. This ensures the global optimality and consistency of each adjustment measure, thereby enabling more effective response to complex and time-varying interference.

[0021] By iteratively executing the above steps, this method establishes a closed-loop adaptive interference suppression system with a perception-modeling-decision-execution mechanism. Its innovations are reflected in the following aspects: by introducing a cognitive probe carrier with an adaptive detection strategy, the depth and accuracy of dynamic optical path environment perception are significantly improved; by constructing and calibrating an optical path twin model in real time and introducing a confidence assessment mechanism, a reliable basis is provided for subsequent collaborative control; and ultimately, unprecedented deep collaboration between data carrier optimization and optical path dynamic compensation is achieved, enabling more effective suppression of complex dynamic interference that is difficult for traditional methods to handle.

[0022] A second aspect of the present invention provides a signal interference suppression system combining multi-level carrier coordination with dynamic optical path compensation.

[0023] A transmitting unit: configured to transmit cognitive probe carriers and data carriers on demand in the optical path. Specifically, the transmitting unit can transmit cognitive probe carriers with specific initial parameters based on instructions from the collaborative intelligent controller, and reconfigure and transmit these cognitive probe carriers based on a subsequently determined adaptive cognitive probe carrier detection strategy. Simultaneously, the transmitting unit also configures and transmits data carriers based on instructions from the collaborative intelligent controller.

[0024] A receiving unit (or monitoring unit): configured to receive the cognitive probe carrier after optical path transmission and process the received cognitive probe carrier to generate cognitive probe carrier data reflecting optical path characteristics and interference conditions. This receiving unit can also be used to monitor the performance of the data carrier.

[0025] A collaborative intelligent controller: As the core control center of the system, the controller is operatively connected to the transmitting unit and the receiving unit (or monitoring unit) and is configured to perform the following core functions: Receive and process cognitive probe carrier data from the receiving unit.

[0026] The optical path twin model used to characterize the optical path characteristics is continuously updated and calibrated based on the received cognitive probe carrier data and optional data carrier performance feedback.

[0027] Perform confidence assessment on parameters or predictions in optical path twin models.

[0028] According to the confidence evaluation results of the optical path twin model, the adaptive cognitive probe carrier detection strategy for subsequent transmission of the cognitive probe carrier is dynamically determined and adjusted, and the configuration instructions related to the strategy are sent to the transmitting unit.

[0029] Based on the updated optical path twin model with higher confidence, decisions are made to generate instructions for collaboratively adjusting the data carrier transmission parameters and send them to the transmitting unit, and / or generate instructions for collaboratively adjusting the settings of one or more dynamic optical path compensation units in the optical path and send them to the corresponding compensation units to actively and accurately suppress the signal interference suffered by the data carrier.

[0030] Through the collaborative work of various units, the system achieves closed-loop perception of the optical path status and adaptive collaborative suppression of interference, embodying the same innovative principles and technical advantages as at the method level.

[0031] A third aspect of the present invention provides a computer-readable storage medium.

[0032] The computer-readable storage medium stores computer-executable instructions. When executed by one or more processors (e.g., the processors integrated into the collaborative intelligent controller), these instructions enable the processors (or a system including the processors) to perform all or part of the steps of the signal interference suppression method combining multi-level carrier collaboration and dynamic optical path compensation described in the first aspect, particularly the core algorithm logic related to data processing, model updating, strategy generation, and control decision-making. This allows the core intelligent control functions of the present invention to be implemented and deployed via software.

[0033] The present invention provides a signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation. It has the following beneficial effects: 1. This invention achieves in-depth, accurate, and efficient dynamic perception of optical network status by introducing a cognitive probe carrier that can adaptively adjust detection strategies, combined with confidence assessment of optical path twin model parameters. The system intelligently focuses detection resources on the most uncertain or volatile optical path characteristics, thereby acquiring the highest-value channel information with minimal overhead, significantly improving the real-time characterization capabilities of complex dynamic optical links.

[0034] 2. Based on a high-fidelity optical twin model continuously calibrated by a cognitive probe carrier, this invention enables precise co-optimization of data carrier transmission parameters and the settings of dynamic compensation units in the optical path. This joint adjustment, based on a unified and precise understanding of the channel, ensures targeted optimization and compensation at every critical node in signal generation and transmission, effectively combating various linear and nonlinear interferences and significantly enhancing the transmission robustness and spectral efficiency of the optical communication system.

[0035] 3. This invention builds a complete closed-loop adaptive interference mitigation framework, from active perception and precise modeling to intelligent decision-making and coordinated execution. This end-to-end intelligent collaborative mechanism enables the system to proactively adapt to changing service demands and environmental interference in optical networks without relying on prior knowledge of interference types. This provides critical physical layer adaptability and performance guarantees for the evolution of future optical networks toward higher capacity and greater complexity. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a system architecture block diagram of the present invention; Figure 2 Schematic diagram of the method of the present invention.

[0037] Among them, 110 is a transmitting unit; 101 is an optical path; 120 is a receiving unit; 130 is a collaborative intelligent controller; and 140 is a dynamic optical path compensation unit. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are mainly used to explain the present invention and are not intended to limit the scope of protection of the present invention.

[0039] Please see the attached Figure 1 -Attached Figure 2 The present invention provides a signal interference suppression method that combines multi-level carrier collaboration and dynamic optical path compensation, aiming to perceive and suppress complex and dynamically changing signal interference in optical communication links in an active and intelligent manner.

[0040] like Figure 2 As shown, the method may include the following steps: S100: The transmitting unit transmits a cognitive probe carrier according to an initial strategy.

[0041] During system initialization or stable operation, the transmitter unit 110 transmits one or more sets of specially designed cognitive probe carriers (CPCs) into the optical path 101 according to an initial cognitive probe carrier (CPC) transmission strategy that is preset or determined by the collaborative intelligent controller 130. These cognitive probe carriers have predetermined signal characteristics that make them highly sensitive to specific physical impairments (such as chromatic dispersion, polarization mode dispersion, and nonlinear effects) and interference sources (such as crosstalk and noise) in the optical path 101.

[0042] S200: The receiving unit captures and processes the transmitted cognitive probe carrier to generate data.

[0043] After being transmitted through the optical path 101, the receiving unit 120 (or a monitoring unit deployed in the middle of the optical path) captures the cognitive probe carrier. The receiving unit 120 processes the received cognitive probe carrier signal, such as signal amplification, filtering, demodulation and feature extraction, to generate cognitive probe carrier data. This data quantitatively reflects the changes in signal distortion, power attenuation, phase rotation, spectrum broadening, etc. experienced by the cognitive probe carrier during transmission along the optical path 101, and contains the current state information of the optical path 101.

[0044] S300, the collaborative intelligent controller uses the cognitive probe carrier data to update the optical path twin model.

[0045] The collaborative intelligent controller 130 receives the cognitive probe carrier data from the receiving unit 120 The optical path twin model (OPT) module within the collaborative intelligent controller 130 uses this real-time data to update or calibrate the optical path twin model used to digitally characterize the characteristics of the optical path 101. The model It is a dynamic mathematical model whose state vector contains estimates of key optical path parameters, such as the accumulated dispersion of each link segment. , differential group delay , nonlinear coefficient and the equivalent parameters of specific interference The model update process can be abstractly expressed as: ; in, is the OPT model state at the previous moment, is the cognitive probe carrier data obtained at the current moment, Optional historical performance feedback from the data carrier (such as bit error rate, signal-to-noise ratio, etc.), Represents one or more model updating algorithms, such as an extended Kalman filter, an unscented Kalman filter, or a machine learning-based regression model.

[0046] S400, the collaborative intelligent controller evaluates the confidence of the optical path twin model parameters.

[0047] The OPT model module in the collaborative intelligent controller 130 further updates the optical path twin model The confidence or uncertainty of the estimated parameters in the model is assessed. parameters , its confidence The posterior variance of the parameter can be estimated based on , CPC data quality indicators used to estimate this parameter The confidence level is calculated based on factors such as the stability of historical parameter changes. Confidence evaluation helps determine the reliability of the current model's description of various aspects of the optical path state.

[0048] S500: The collaborative intelligent controller determines the cognitive probe carrier detection strategy for the next cycle based on the model confidence.

[0049] Based on the optical path twin model The confidence evaluation results of the status and its parameters , the adaptive CPC detection strategy module in the collaborative intelligent controller 130 determines the next cycle Cognitive probe carrier detection strategy This decision is intended to prioritize improving the detection accuracy of low-confidence or rapidly changing optical path parameters by adjusting the CPC's emission parameters. For example, if the parameter Confidence Below a certain threshold, the policy module may decide to increase the detection To make the CPC signal more sensitive, the transmission power can be increased, its waveform characteristics can be changed, or its detection frequency can be increased.

[0050] S600. The collaborative intelligent controller instructs the transmitting unit to reconfigure the cognitive probe carrier according to the new strategy.

[0051] The collaborative intelligent controller 130 uses the newly determined adaptive cognitive probe carrier detection strategy This information is converted into specific configuration instructions and sent to the transmitter 110. The transmitter 110 then reconfigures the transmission parameters of the cognitive probe carrier for the next round of optical path detection. This step ensures dynamic optimization of CPC detection behavior, enabling detection resources to be intelligently allocated where they are most needed.

[0052] S700, the collaborative intelligent controller collaboratively adjusts the data carrier transmission and optical path compensation unit based on the high confidence model.

[0053] With an updated and more confident optical path twin model Based on the above, the multi-level cooperative interference suppression module of the cooperative intelligent controller 130 makes a decision to suppress the signal interference to the data carrier (DC) in the optical path 101. This includes two aspects of cooperation: First, the collaborative intelligent controller 130 Predict the transmission performance of the data carrier under the current optical path conditions and optimize the transmission parameters of the data carrier accordingly , such as adjusting the modulation format, forward error correction (FEC) scheme, transmit power spectrum shape or digital predistortion (DPD) coefficients, these instructions are also sent to the transmitting unit 110.

[0054] Second, the collaborative intelligent controller 130 Accurately estimate the accumulated impairments in the optical path (such as total dispersion and instantaneous PMD vector) to generate control signals , used to adjust the settings of one or more dynamic optical path compensation units (LPUs) 140 (such as tunable dispersion compensation modules, polarization controllers, dynamic gain equalizers, etc.) coupled to the optical path 101.

[0055] S800: The system iteratively executes the above steps to form closed-loop adaptive control.

[0056] The system continuously iterates through steps S100 to S700, forming a closed adaptive control loop. Through this continuous cycle of perception, modeling, decision-making, and execution, the system dynamically tracks changes in the optical path environment and optimizes signal transmission and compensation strategies in real time, effectively suppressing all types of dynamic interference and ensuring the quality and reliability of data transmission.

[0057] In this embodiment of the present invention, to achieve the transmission of the cognitive probe carrier in step S100 and the generation of cognitive probe carrier data in step S200, the system utilizes a series of carefully designed and controlled cognitive probe carriers. The following details the design, configuration, transmission, reception, and processing of these cognitive probe carriers.

[0058] First, before transmitting the cognitive probe carrier, the method of the present invention includes a step for selecting and configuring cognitive probe carrier characteristics. This step is led by the collaborative intelligent controller 130 or executed according to its preset logic. The selection and configuration are based on a comprehensive consideration of historical optical path data, current detection requirements (for example, which parameters in the optical path twin model have low confidence), and system operational objectives (for example, whether to focus on fast link change tracking or detailed nonlinear effect characterization).

[0059] The core design of the cognitive probe carrier lies in its known signal structure and sensitivity to specific optical path effects. Unlike data carriers, the waveform, sequence, or spectral characteristics of the cognitive probe carrier are predefined and known to the system. This enables the receiver to accurately quantify the various physical effects experienced by the signal in the optical path by comparing the received distorted signal with an ideal reference signal.

[0060] The cognitive probe carriers in the embodiments of the present invention may include, but are not limited to, one or more of the following types. The collaborative intelligent controller 130 may dynamically select or combine them based on detection requirements: 1. Broadband linear frequency modulation signals (Chirp Signals) or multi-tone comb spectrum signals: This type of cognitive probe carrier is particularly suitable for accurately measuring the accumulated dispersion (CD) of optical fibers.

[0061] For a linear frequency modulation signal, its instantaneous frequency changes linearly with time. ,in is the starting frequency, is the frequency modulation slope. Dispersion causes different frequency components to have different group delays. By analyzing the pulse broadening of the received signal or the phase distortion after frequency demodulation, the dispersion value can be accurately extracted.

[0062] For a multi-tone comb spectrum signal, it contains multiple discrete tones with known frequency intervals. By measuring the relative arrival time differences of these tones at the receiver or relative phase difference , the dispersion slope and cumulative dispersion of the link can be calculated.

[0063] 2. Specific polarization state or polarization scanning signal: This type of cognitive probe carrier is used to detect and quantify polarization mode dispersion (PMD) effects.

[0064] It can transmit light with a specific input state of polarization (SOP), such as linearly polarized light or circularly polarized light, and estimate the differential group delay (DGD) and principal state of polarization (PSP) by analyzing the polarization variation, polarization-dependent loss (PDL), or pulse splitting / broadening caused by PMD in the received signal.

[0065] Another approach is to transmit a cognitive probe carrier that rapidly switches or continuously scans between multiple predetermined polarization states. The receiver can more comprehensively characterize PMD by analyzing the output signal characteristics corresponding to different input polarization states, for example using Jones matrix eigenvalue analysis or Mueller matrix analysis.

[0066] 3. Multi-tone signals are used for nonlinear effect detection: By transmitting two or more tones of known frequency and power, nonlinear effects in optical fibers, such as four-wave mixing (FWM) and cross-phase modulation (XPM), can be detected.

[0067] For example, transmitting two main tones and If there is a significant FWM effect, a region located at and The power of these new components is Nonlinear coefficient of optical fiber , link length, and main tone power, etc. The intensity of nonlinear damage can be evaluated indirectly.

[0068] For XPM, a cognitive probe carrier can act as a “victim” signal and observe how its phase or spectrum is affected by a nearby strong data carrier (the “aggressor” signal).

[0069] 4. Low-power signals modulated with a pseudo-random binary sequence (PRBS): Using a long-period PRBS sequence to modulate a low-power optical carrier can be used to comprehensively evaluate various linear impairments of the optical path, such as attenuation, dispersion, and some noise characteristics. The PRBS sequence has good autocorrelation characteristics, facilitating synchronization and channel impulse response estimation at the receiver.

[0070] In the step of configuring the transmission parameters of the cognitive probe carrier, the collaborative intelligent controller 130 not only determines which type of CPC to use, but also determines its specific transmission parameters. Key parameters include: Transmit power : As mentioned before, it is usually much lower than the data carrier power, e.g. ,in It is a safety margin, for example, 10 dB to 20 dB. The specific value can be dynamically adjusted by the CIC based on the current link loss, detection sensitivity requirements, and interference tolerance for data services.

[0071] Signal bandwidth or chip rate / symbol rate: This is selected based on the bandwidth characteristics of the effect to be detected. For example, detecting fast-changing PMD may require a CPC with higher time resolution.

[0072] Spectrum location: The center frequency or band of the CPC can be placed in the band of a data traffic channel (e.g., achieved by very low power), in a guard band, or in a dedicated monitoring channel.

[0073] Transmission time slot or duty cycle: For time-division multiplexed CPC, the transmission duration and repetition period are controlled by the CIC to balance the real-time detection performance and system overhead.

[0074] Subsequently, during step S100 , transmitter unit 110 actually transmits the cognitive probe carrier. Based on detailed configuration instructions (including CPC type, waveform parameters, power, time-frequency resources, etc.) provided by collaborative intelligent controller 130, transmitter unit 110 utilizes its internal light source, modulator (e.g., Mach-Zehnder modulator, phase modulator), and possibly arbitrary waveform generator (AWG) to generate and precisely inject the selected cognitive probe carrier into optical path 101.

[0075] When executing the aforementioned step S200, the receiving unit 120 (or a designated monitoring point) receives and initially processes the transmitted cognitive probe carrier. This includes standard operations such as photoelectric conversion, amplification, and filtering. The key lies in the subsequent digital signal processing step, which aims to obtain the received cognitive probe carrier, which may have been severely distorted. Extract useful information from it.

[0076] This process includes: 1. Precise synchronization: Leveraging the known structure of the cognitive probe carrier (such as the specific header of the PRBS sequence, the starting phase of the chirp signal, and the frequency relationship of the multi-tone signal), the receiver performs time synchronization, carrier frequency offset correction, and phase recovery.

[0077] 2. Channel effect quantification: For amplitude information, measure the received signal power The path attenuation is obtained by comparing it with the nominal transmit power (or equivalent transmit power calibrated by other means).

[0078] For phase information, the phase change experienced by the signal is extracted by comparing it with the locally recovered carrier or by differential detection. , used to analyze phase noise or nonlinear phase shift.

[0079] As for dispersion, as mentioned above, the accumulated dispersion is estimated by analyzing the group delay difference of different frequency components or the signal characteristics after demodulation. .

[0080] For PMD, the DGD value is estimated by a polarization analyzer or a digital signal processing algorithm (such as polarization demultiplexing based on the constant modulus algorithm (CMA) or independent component analysis (ICA)). and the principal polarization state .

[0081] For nonlinear effects, the power of intermodulation products such as FWM is detected by spectrum analysis. , or analyze the nonlinear phase shift and amplitude noise introduced by XPM / SPM through constellation diagram.

[0082] 3. Feature parameter extraction and data vector construction: Organize the above quantized physical quantities or estimated channel parameters into a feature vector, i.e. cognitive probe carrier data .For example, is the average received power, is the estimated dispersion value, is the DGD value, is the FWM product power, etc. This data vector is then transmitted to the collaborative intelligent controller 130 for subsequent optical path twin model update (step S300).

[0083] Through the above-mentioned design, adaptive configuration, transmission and reception processing of the cognitive probe carrier, the present invention can obtain rich and targeted optical path status information, laying the foundation for subsequent modeling and collaborative interference suppression.

[0084] In these embodiments of the present invention, to update the optical path twin model described in step S300 and assess the confidence of the model parameters described in step S400, the collaborative intelligent controller 130 integrates and runs a dynamic optical path twin model (OPT) module. This module is responsible for constructing, maintaining, and evaluating a digital model that accurately represents the physical properties and signal transmission effects of the optical path 101 in real time.

[0085] This optical twin model The core of the model is a mathematical expression that aims to simulate the various linear and nonlinear effects encountered by optical signals when propagating in actual optical fiber links. The model can be regarded as a The state vector of the evolution contains the estimated values of several key parameters in the optical path. Specifically, the state vector Parameters may include but are not limited to the following: Accumulated dispersion :Indicates the distance from the starting point to the position in the light path At wavelength Next, at the time The total accumulated dispersion. In a simplified model, it can be the total accumulated dispersion of the entire link .

[0086] Polarization mode dispersion (PMD) related parameters: for example, the differential group delay (DGD) value of the link or its segments and the principal state of polarization (PSP) direction vector For dynamic PMD, these parameters are time-varying.

[0087] Effective nonlinear coefficient : A parameter that characterizes the intensity of nonlinear effects in a specific section of an optical fiber, which may be affected by factors such as temperature and stress.

[0088] Link attenuation coefficient : Describes the power attenuation rate of an optical signal at a specific position and wavelength in an optical fiber.

[0089] Nonlinear Interference (NLI) Contribution Factor : Used to quantify the impact of nonlinear noise generated in a specific link segment or a specific frequency range on the signal.

[0090] Other specific interference source parameters: for example, crosstalk coupling strength at a specific location , or additional loss or reflection introduced by point damage (such as bad splices) .

[0091] The granularity of the model can be adjusted based on application requirements and computing resources. For example, it can be a lumped parameter model of the entire end-to-end link, or a more refined multi-span model where the fiber segment between each optical amplifier is modeled separately.

[0092] Initialization of the optical path twin model, i.e. The establishment of can be based on a variety of information sources. For example, the factory nominal parameters of optical fibers and components, theoretical values from a network design database, or an initial, relatively comprehensive cognitive probe carrier scan can be used to obtain a preliminary estimate.

[0093] During the operation of the system, the iterative update of the optical path twin model (corresponding to step S300) is its core function. This update process uses the cognitive probe carrier data obtained from the receiving unit 120 To continuously correct and calibrate the model parameters. As shown in the above formula As shown, the update function A variety of advanced estimation algorithms can be used.

[0094] A commonly used method is based on the Kalman filter and its variants, such as the extended Kalman filter (EKF) or the unscented Kalman filter (UKF), which is particularly suitable for dealing with the state estimation problem of dynamic systems with noise.

[0095] Under this framework, the state evolution of the OPT model can be expressed as: ; in, is a discrete moment The model state vector, is the state transition matrix, describing how the model parameters change from Evolving to moment (for slowly varying parameters, Close to the unit array), represents the known effects of external inputs or controls on the model (if any), is the process noise vector, and its covariance matrix is , which represents the uncertainty of the model itself.

[0096] Observation data of cognitive probe carrier The relationship between and the model state (observation equation) can be expressed as: ; in, is a (usually nonlinear) observation function that transforms the current model state and the CPC parameters of the known launch ( ) is mapped to the expected CPC measurement, is the observation noise vector, and its covariance matrix is The Kalman filter recursively gives the optimal estimate of the model state and its covariance matrix through two steps: prediction and update. .

[0097] For scenarios with highly nonlinear or non-Gaussian noise, particle filters provide an alternative effective update mechanism. Particle filters approximate the posterior probability distribution of the model state through a set of weighted random samples (particles), enabling them to better handle complex systems.

[0098] In addition, machine learning methods, such as neural network-based regression models or Gaussian Process Regression (GPR), can also be used to implement These models can learn from cognitive probe carrier data (and optionally historical model state and data carrier feedback To the updated model parameters Training such models requires sufficient data, which can come from high-precision simulations, laboratory measurements, or historical operation records of actual deployed systems.

[0099] After the OPT model parameters are updated, step S400 is executed to evaluate the confidence of the model parameters. Quantify the system's parameters The degree of confidence in the current estimate. A high confidence level means that the parameter estimate is relatively accurate and reliable, while a low confidence level indicates that the parameter may have large uncertainties and requires further exploration or calibration.

[0100] The confidence level can be assessed based on one or more of the following factors: 1. Estimated variance or uncertainty interval: If a Kalman filter is used, the state covariance matrix of its output is The diagonal elements of Directly given parameters Estimated variance. Confidence level Usually with Inversely proportional, for example ,in is a scaling factor. For particle filters, uncertainty can be assessed by calculating the dispersion (such as variance or entropy) of the particle distribution corresponding to a specific parameter.

[0101] For some machine learning models (such as Gaussian process regression or Bayesian neural networks), it is possible to directly output the variance or confidence interval of the prediction.

[0102] 2. Cognitive probe carrier data quality : If used to estimate parameters If the CPC measurement data itself has a low signal-to-noise ratio, is subject to strong interference, or has sparse data points, then even if the estimation algorithm is advanced, the confidence level of the obtained parameters should be reduced accordingly.

[0103] 3. Residuals between model predictions and actual observations: Comparison based on the current OPT model The predicted value of CPC behavior and the actual received CPC data Consistently large residuals may mean that the model is not describing that parameter accurately, thus reducing confidence in it.

[0104] 4. Parameter rate of change or stability: If a parameter has recently exhibited large or unpredictable fluctuations, confidence in the validity of its current estimate for the near future may be reduced.

[0105] Taking these factors into consideration, the collaborative intelligent controller 130 can calculate a normalized confidence score for each key parameter in the OPT model. This will serve as an important basis for the subsequent adaptive cognitive probe carrier detection strategy adjustment (step S500) and multi-level collaborative interference suppression decision (step S700).

[0106] Through this dynamically constructed, continuously updated and confidence-aware OPT model, the present invention provides a solid and reliable optical path status information foundation for subsequent intelligent decision-making.

[0107] In a specific embodiment of the present invention, to implement the determination of the cognitive probe carrier detection strategy described in step S500 and the reconfiguration of cognitive probe carrier transmission based on the new strategy described in step S600, the collaborative intelligent controller 130 includes an adaptive cognitive probe carrier (CPC) detection strategy module. This module's core function is to intelligently adjust the transmission parameters of the cognitive probe carrier in the next cycle based on the confidence assessment results of the optical path twin (OPT) state and its parameters, thereby achieving more efficient and accurate perception of the optical path status.

[0108] The process of formulating this adaptive detection strategy first relies on the analysis of the current detection needs. The collaborative intelligent controller 130 reviews the model parameters provided by the OPT module. and its corresponding confidence When the confidence level of one or more parameters is lower than the preset threshold , or when these parameters have shown rapid changes in the recent period, or have a significant impact on the expected data carrier performance but the current estimate is uncertain, the system will consider that there is a high detection demand for these parameters.

[0109] After the detection requirements are analyzed, the detection strategy module converts these requirements into adjustment instructions for the specific transmission parameters of the cognitive probe carrier. Its objective function can be expressed as maximizing the utility of information acquisition in the next detection cycle. , while constraining the detection overhead (such as additional power consumption, occupied time and frequency resources, etc.) are within an acceptable range.

[0110] ; in, Represents the CPC launch strategy for the next detection cycle, which is a set of multiple CPC types and their launch parameters. Typically related to the degree to which the uncertainty of the OPT model is expected to be reduced, for example, to the degree to which the low confidence parameters are expected to be improved. or reduce its estimated variance The degree of correlation.

[0111] The specific adaptive adjustment mechanism can be reflected in the following aspects, which the collaborative intelligent controller 130 can flexibly combine and use according to actual conditions: 1. Dynamic selection or ratio adjustment of cognitive probe carrier types: If the OPT model indicates low confidence in the current dispersion estimate, the detection strategy module instructs the transmitter unit 110 to increase the number or frequency of transmissions of dispersion-sensitive CPC types (such as the aforementioned wideband chirp signal or multi-tone comb spectrum signal). Conversely, if the dispersion estimate is highly stable and confidence is high, the transmission of these CPC types can be appropriately reduced to allocate resources to other parameters with higher detection requirements.

[0112] 2. Adaptive adjustment of cognitive probe carrier transmission power: For those CPCs associated with low confidence OPT parameters, the system can moderately increase its transmit power. , to improve the signal-to-noise ratio (SNR) at the receiving end, thereby making the measurement data extracted from these CPCs More accurate, thus improving the estimation accuracy of related OPT parameters. The upper limit of power adjustment is limited by the interference to the data carrier and the threshold of the fiber nonlinear effect.

[0113] 3. Optimization of the cognitive probe carrier signal structure or waveform parameters: For example, if more precise detection of second-order PMD effects is needed, the detection strategy module might instruct the CPC to transmit with a specific pulse width or polarization modulation rate. If detection of nonlinear crosstalk in a specific frequency band is required, the CPC tone frequency can be adjusted to a region closer to or more sensitive to that crosstalk.

[0114] 4. Adjustment of the spectrum position or time slot allocation of the cognitive probe carrier: If the OPT model indicates that the performance fluctuation of a particular wavelength channel is large, more CPC resources (such as denser time slots or wider detection subbands) can be allocated to the wavelength channel. In the time division multiplexing scheme, for rapidly changing optical path parameters, the CPC transmission frequency can be increased (reduced). ) to improve the temporal resolution.

[0115] 5. Focus adjustment of the detection area or range (for systems supporting spatially resolved detection): If the system has the ability to inject or monitor CPC at different locations on the optical path (for example, by selecting different optical path segments through a reconfigurable optical add / drop multiplexer (ROADM)), and the OPT model can distinguish the parameter characteristics of different optical path segments, CPC detection resources can be preferentially directed to specific optical path segments with high parameter uncertainty.

[0116] The decision logic can be based on a rules engine, an optimization algorithm, or a reinforcement learning agent.

[0117] For example, a rule-based decision might contain the following rules: “IF AND THEN increase by AND select CPC waveform optimal for DGD estimation”.

[0118] Methods based on optimization algorithms attempt to solve the utility maximization problem mentioned above.

[0119] Based on the reinforcement learning method, the agent (strategy module of the collaborative intelligent controller 130) can learn the optimal CPC adjustment strategy by interacting with the optical path environment (simulated by the OPT model or directly through actual optical path feedback) , whose goal is to maximize the long-term accumulated detection utility or system performance.

[0120] After determining the new detection strategy After that, the collaborative intelligent controller 130 converts it into specific control instructions and sends these instructions to the transmitting unit 110 in step S600. The transmitting unit 110 then reconfigures its internal signal generator, modulator, and power controller according to these instructions to transmit the cognitive probe carrier with the new parameters in the next detection cycle.

[0121] This adaptive detection mechanism eliminates blind or fixed transmission of cognitive probe carriers, instead providing intelligent guidance based on real-time feedback from optical path status and model confidence. This ensures that detection resources are efficiently used to address the most significant cognitive uncertainties, thereby obtaining the most critical and timely information on optical path status with minimal system overhead, providing high-quality input for subsequent interference suppression.

[0122] In a specific embodiment of the present invention, when the collaborative intelligent controller 130 obtains an updated optical path twin model with a higher confidence through the aforementioned steps S100 to S600, After that, a multi-level collaborative interference suppression process is initiated. This process aims to use precise optical path status information to proactively and collaboratively adjust the transmission parameters of the data carrier (DC) and the settings of the dynamic optical path compensation unit (LPU) in the optical path to minimize signal interference and ensure data transmission quality.

[0123] The collaborative interference suppression process is executed by the multi-level collaborative interference suppression module inside the collaborative intelligent controller 130, and its decision-making basis is the current high-confidence optical path twin model. The module performs optimization adjustments on two levels simultaneously: optimization of the data carrier transmitter and dynamic compensation during optical transmission.

[0124] First, regarding the collaborative optimization of data carrier transmission parameters, the collaborative intelligent controller 130 uses the optical path twin model The expected transmission performance under different data carrier configurations is predicted. Specifically, for a set of candidate data carrier transmission parameters , the system can be based on Estimate the expected signal quality indicators after its transmission, such as bit error rate (BER), signal-to-noise ratio (SNR), Q factor or mutual information (MI).

[0125] This prediction process can be expressed as ,in is a performance prediction function, which can be an analytical or semi-analytical calculation based on a physical model (e.g., transmission simulation considering the cumulative effects of dispersion, PMD, and nonlinear effects), or a machine learning model trained on historical data (e.g., an input and The features of , the output is neural network).

[0126] Then, the goal of the collaborative intelligent controller 130 is to select a set of optimal data carrier transmission parameters , so that under the current light path conditions, the predefined utility function Maximize. This utility function usually takes into account factors such as transmission quality, data rate, and power consumption: ; Limited by ,in is the set of allowed parameters.

[0127] Data carrier transmission parameters available for optimization include: 1. Modulation format (ModFormat): For example, select the most appropriate format from BPSK, QPSK, 8QAM, 16QAM, 64QAM, etc. Higher-order modulation formats can achieve higher spectral efficiency and data rates, but are more sensitive to channel impairments.

[0128] 2. Forward Error Correction (FEC) Scheme and Code Rate (FEC_Rate): Select FEC codes with different error correction capabilities and overheads, such as LDPC codes, Turbo codes, or polar codes at different rates. Stronger FEC can tolerate worse channel conditions, but at the expense of a certain net data rate.

[0129] 3. Transmit power spectrum density or total power (Power Spectrum, Power): Optimize the power allocation of each data subcarrier or adjust the total transmit power to obtain the best signal-to-noise ratio at the receiver while meeting the total power constraint and avoiding excessive nonlinear effects.

[0130] 4. Digital Pre-Distortion (DPD) or Pre-compensation Coefficients (PreDistCoeffs): If the transmitter has digital signal processing capabilities, it can be used according to Predicted linear impairments (such as dispersion) and nonlinear impairments are pre-distorted at the transmitter, allowing the signal to return to a closer-to-ideal state after traversing the actual optical path. For example, digital dispersion pre-compensation can be used for dispersion, while nonlinear pre-distortion based on Volterra series or other models can be used for certain nonlinear effects.

[0131] 5. Multiple-Input Multiple-Output (MIMO) Precoding Matrix (for Space Division Multiplexing or Polarization Multiplexing systems): Optimize the precoding matrix to decouple channels or maximize the transmission performance of a specific mode.

[0132] The collaborative intelligent controller 130 calculates the optimized data carrier transmission parameters The data is converted into configuration instructions and sent to the transmitting unit 110, which adjusts its internal modulator, encoder, power amplifier, digital signal processor, etc. accordingly.

[0133] Secondly, regarding the coordinated adjustment of the dynamic optical path compensation unit, the collaborative intelligent controller 130 is also based on the optical path twin model The control signals are used to adjust the settings of one or more dynamic optical path compensation units (LPUs) 140 deployed in the optical path 101. These compensation units are designed to counteract or mitigate accumulated signal impairments in the optical path in real time.

[0134] The types of adjustable dynamic optical path compensation units include: 1. Tunable Dispersion Compensator (TDC): For example, TDC based on fiber Bragg grating (FBG) or virtual imaging phased array (VIPA). The collaborative intelligent controller 130 uses the OPT model to Accumulated dispersion in the middle pair The accurate estimate of the dispersion compensation that the TDC needs to provide is calculated , and instructs TDC to adjust to this value.

[0135] 2. Polarization Controller (PC) and PMD Compensator: For dynamically changing PMD, a high-speed electro-optical polarization controller can be used to adjust the signal's polarization state to align with the link's instantaneous low-PMD axis or to coordinate with polarization demultiplexing at the receiver. More advanced PMD compensators (PMDCs) may include multiple tunable delay lines and polarization rotators. Their configuration parameters are optimized by the collaborative intelligent controller 130 based on the DGD and PSP information estimated by the OPT model.

[0136] 3. Dynamic Gain Equalizer (DGE) or Variable Optical Attenuator (VOA) Array: This array compensates for power imbalances between different wavelength channels in a wavelength division multiplexing (WDM) system caused by erbium-doped fiber amplifier (EDFA) gain flatness issues or other wavelength-related losses in the link. The intelligent controller 130 coordinates the attenuation of each DGE channel based on the OPT model's estimated attenuation for each channel.

[0137] For the Dynamic optical path compensation unit , its optimal setting Determined by the collaborative intelligent controller 130 in order to maximize the compensation effect or minimize a specific damage indicator: ; in, It is a control algorithm or mapping function for the compensation unit, which converts the current optical path model state and the target impairment type of the compensation unit (for example, total dispersion for TDC and polarization distortion for PC) into specific control voltages, tuning parameters, etc.

[0138] The synergy between the optimization of the data carrier transmitter and the adjustment of the physical compensation unit in the optical path is reflected in the fact that they are both based on the same high-confidence optical path twin model that is calibrated in real time by the cognitive probe carrier. This ensures that all adjustments are made based on a unified and precise understanding of the optical path status, avoiding conflicts or suboptimal results that may result from local optimization, thereby achieving global and in-depth suppression of signal interference.

[0139] Through the synergistic effect of these two levels, the present invention can more effectively deal with complex, dynamic and often multi-factor intertwined signal impairments in optical communication systems, thereby significantly improving the system's transmission performance, reliability and adaptability to environmental changes.

[0140] In a specific embodiment of the present invention, the core intelligent functions involved in steps S300 to S700, including cognitive probe carrier data processing, optical path twin model construction and updating, parameter confidence assessment, adaptive detection strategy generation, and multi-level collaborative interference suppression decision-making, are all performed by a collaborative intelligent controller (CIC) 130. The physical implementation of the collaborative intelligent controller 130 can take various forms, such as a centralized processing unit or a logically centralized but physically partially distributed control system.

[0141] The present invention also provides a computer device, comprising: a processor and a memory, wherein the memory stores a computer program executable by the processor, and the computer program executes the above method when executed by the processor.

[0142] The present invention also provides a storage medium on which a computer program is stored. When the computer program is run by a processor, the above method is executed.

[0143] Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0144] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation, characterized in that: The following steps are involved: transmitting a cognitive probe carrier in an optical path; generating cognitive probe carrier data based on the cognitive probe carrier after the optical path transmission; Based on the cognitive probe carrier data, updating the optical path twin model for characterizing the optical path characteristics; Determining an adaptive cognitive probe carrier detection strategy for subsequent transmission of the cognitive probe carrier based on a confidence evaluation of the optical path twin model; reconfiguring the transmission parameters of the cognitive probe carrier according to the adaptive cognitive probe carrier sounding strategy; as well as Based on the updated optical path twin model, the transmission parameters of the data carrier and / or the settings of the dynamic optical path compensation unit are collaboratively adjusted to suppress signal interference of the data carrier.

2. The signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation according to claim 1 is characterized in that: The step of updating the optical path twin model further includes: The optical path twin model is updated based on performance feedback data of the data carrier after transmission through the optical path.

3. The signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation according to claim 1 is characterized in that: The step of determining the adaptive cognitive probe carrier detection strategy includes: evaluating confidence levels of a plurality of parameters or predictions within the optical path twin model; At least one target parameter or prediction is identified that has a confidence level below a predetermined threshold or exhibits a high degree of uncertainty.

4. The signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation according to claim 3 is characterized in that: The step of reconfiguring the transmission parameters of the cognitive probe carrier according to the adaptive cognitive probe carrier sounding strategy includes modifying at least one of the following: the transmit power of one or more of the cognitive probe carriers; Signal waveform characteristics of one or more of the cognitive probe carriers; spectrum allocation for one or more of said cognitive probe carriers; or The detection density of the cognitive probe carrier, To enhance detection of light path characteristics associated with the identified at least one target parameter or prediction.

5. The signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation according to claim 1 is characterized in that: The step of collaboratively adjusting the transmission parameters of the data carrier includes: Using the updated optical path twin model, predicting the expected transmission performance of the data carrier under a set of candidate transmission parameters; and A subset of the candidate transmission parameters is selected, which is capable of optimizing a predefined performance indicator of the data carrier, and the candidate transmission parameters include at least one of a modulation format, a symbol rate, a forward error correction scheme, a subcarrier power allocation, a digital predistortion coefficient, or a precoding matrix.

6. The signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation according to claim 1 is characterized in that: The step of collaboratively adjusting the settings of the dynamic optical path compensation unit includes: Based on parameter estimates derived from the updated optical path twin model, control settings of one or more of the dynamic optical path compensation units are calculated, and the dynamic optical path compensation units include at least one of a tunable dispersion compensator, a polarization controller, a dynamic gain equalizer, or a reconfigurable optical add / drop multiplexer to offset specific optical path impairments identified by the optical path twin model.

7. The signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation according to claim 1 is characterized in that: The optical path twin model includes a state vector, which represents an estimated value of at least one of the following items in the optical path: The dispersion coefficient of a specific optical path segment, the polarization mode dispersion vector of a specific optical path segment, the nonlinear coefficient of a specific optical path segment, the characteristics of an environmental interference source, or the optical attenuation or gain distribution of a specific optical path segment.

8. The signal interference suppression method combining multi-level carrier coordination and dynamic optical path compensation according to claim 1 is characterized in that: The cognitive probe carrier includes a predefined pseudo-random sequence or a specific waveform that is sensitive to specific optical path impairments or interference types, and the cognitive probe carrier is transmitted at a power level significantly lower than a power level of the data carrier.

9. A signal interference suppression system combining multi-level carrier coordination and dynamic optical path compensation, for executing the method according to any one of claims 1 to 8, characterized in that: include: a transmitting unit, configured to transmit a cognitive probe carrier and a data carrier in the optical path, and reconfigure the transmission parameters of the cognitive probe carrier according to instructions from the collaborative intelligent controller; a receiving unit, configured to receive the cognitive probe carrier after being transmitted through the optical path, and generate cognitive probe carrier data based on the received cognitive probe carrier; The collaborative intelligent controller is used to: receiving the cognitive probe carrier data from the receiving unit; Based on the cognitive probe carrier data, updating the optical path twin model for characterizing the optical path characteristics; Evaluating the confidence of the optical path twin model; Determining an adaptive cognitive probe carrier sounding strategy for subsequent transmissions of the cognitive probe carrier based on the assessed confidence level, and providing instructions to the transmitting unit for reconfiguring transmission parameters of the cognitive probe carrier accordingly; as well as Based on the updated optical path twin model, an instruction for collaboratively adjusting the data carrier transmission parameters is generated to the transmitting unit, and / or an instruction for collaboratively adjusting the dynamic optical path compensation unit settings is generated to the dynamic optical path compensation unit to suppress signal interference of the data carrier.

10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the computer-executable instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 8.

Images