Adaptive interference suppression carrier communication system for complex electromagnetic environments

Abstract

The present invention provides an adaptive interference suppression carrier communication system based on a complex electromagnetic environment, which relates to the technical field of communication systems and solves the problems of poor adaptability, weak anti-interference ability, lack of coordination and security of existing communication systems in complex electromagnetic environments. The system includes: an environmental perception module, which is used to deeply perceive the environment and use AI to identify known and unknown interference; a cognitive decision engine, which uses AI to generate multi-domain control instructions according to the environment, internal, collaborative and security status; an adaptive transceiver control module, which performs adaptive parameter adjustment across multiple domains; a distributed collaborative module, which realizes information sharing, federated learning and collaborative resource management between nodes; and an intrinsic security enhancement module, which performs active security mechanisms such as dynamic heterogeneous redundancy, mimicry defense and physical layer authentication. The present invention also discloses a corresponding communication method. The present invention can significantly improve the robustness, adaptability, efficiency and security of the communication system in a complex electromagnetic environment.

Description

Technical Field

[0001] The present invention relates to the technical field of communication systems, and in particular to an adaptive interference suppression carrier communication system oriented to complex electromagnetic environments. Background Art

[0002] With the rapid development and widespread application of wireless communication technology, electromagnetic spectrum resources are becoming increasingly congested, and the electromagnetic environment faced by wireless communication systems is becoming increasingly complex. This complex electromagnetic environment often contains interference signals of various types, with time-varying power and uncertain direction, and even signals with deceptive or intelligent countermeasure properties. Furthermore, these signals are compounded by channel effects such as multipath fading and Doppler shift.

[0003] Existing communication anti-interference technologies, such as simple filtering, spread spectrum, frequency hopping, or fixed-parameter beamforming, are often designed for specific, known interference patterns. However, they have the following limitations when faced with complex, unknown, dynamic, and diverse electromagnetic environments:

[0004] Lack of collaborative capabilities: Most systems are single-point optimized and lack the ability to coordinate and resist interference between network nodes, making it difficult to cope with distributed interference.

[0005] These limitations significantly reduce the reliability, availability, and data transmission efficiency of communication systems in complex electromagnetic environments, making it difficult to meet the stringent communication resilience requirements of scenarios such as emergency communications and critical industrial control. Therefore, there is an urgent need for an adaptive interference mitigation communication system that can intelligently perceive the environment, make autonomous decisions, collaborate, and possess inherent security capabilities. Summary of the Invention

[0006] Technical problems solved

[0007] In response to the shortcomings of the existing technology, the present invention provides an adaptive interference suppression carrier communication system based on complex electromagnetic environments, which solves the technical problems in the existing technology that the communication system has poor adaptability, limited anti-interference ability, lack of coordination and inherent security mechanisms in complex electromagnetic environments.

[0008] Technical Solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: Based on an adaptive interference suppression carrier communication system for complex electromagnetic environments, the adaptive interference suppression carrier communication system includes the following components:

[0010] An environmental perception module is configured to: monitor electromagnetic signals within a preset frequency band, extract multi-dimensional features of the electromagnetic signals, and generate environmental situation information including interference information and channel state information based on the multi-dimensional features; identify the type of detected interference signals based on the multi-dimensional features, and identify interference signals of unknown types using a pre-trained classification model or anomaly detection algorithm; and include the interference type identification result or unknown interference indication in the environmental situation information;

[0011] The multi-dimensional features include one or more of spectral features, time domain features, and spatial domain features;

[0012] A cognitive decision engine configured to receive environmental situation information and internal state information of the adaptive interference suppression carrier communication system; and generate control instructions covering multiple communication parameter domains based on the environmental situation information and the internal state information using a pre-trained artificial intelligence model.

[0013] The multiple communication parameter domains include two or more of a frequency domain, a time domain, a spatial domain, a power domain, a waveform domain, a coding domain, and a modulation domain;

[0014] an adaptive transceiver control module, the adaptive transceiver control module being configured to: receive the control instruction; and configure communication parameters of a physical layer or a media access control layer of the system according to the control instruction, so as to perform adaptive adjustment across the plurality of communication parameter domains;

[0015] a distributed collaboration module, the distributed collaboration module being configured to: interact with other communication nodes in the network, the information interaction including sharing interference information and local link quality information generated by the environment perception module, and providing information obtained from other nodes to the cognitive decision engine as network collaboration information;

[0016] An intrinsic security enhancement module, configured to execute at least one intrinsic security mechanism according to instructions from the cognitive decision engine or a preset security policy;

[0017] The inherent security mechanism includes at least one of the following:

[0018] Dynamic heterogeneous redundancy: Dynamically select one or a group of redundant processing modules from multiple functionally equivalent but different implementations to process communication signals;

[0019] Mimicry defense: Fast, pseudo-random parameter switching across multiple communication parameter dimensions (including frequency, time, spread spectrum code, and waveform parameters);

[0020] Physical layer authentication: Extract fingerprint information based on the channel characteristics or RF characteristics of the received signal and compare it with the fingerprint database of trusted nodes to verify the node identity.

[0021] Preferably, the spatial features extracted by the environmental perception module include signal arrival direction information, and the environmental situation information is constructed into an interference map data structure, which includes frequency, power, direction and type information of the interference signal.

[0022] Preferably, the artificial intelligence model utilized by the cognitive decision engine is a deep reinforcement learning model; and the state space input of the deep reinforcement learning model also includes network collaboration information received from other network nodes and system security status information; the reward function of the deep reinforcement learning model jointly optimizes communication throughput, bit error rate, latency, power consumption and safety indicators.

[0023] Preferably, the distributed collaboration module is also configured to: participate in distributed model training based on federated learning, wherein multiple nodes collaboratively train at least one shared artificial intelligence model for interference identification, channel prediction or strategy generation, and the original perception data of the node does not leave the local node during the training process, execute the distributed resource negotiation protocol, and collaborate with other nodes to allocate communication resources or perform interference suppression operations.

[0024] Preferably, the communication parameter adjustment configured by the adaptive transceiver control module (ATCM) includes at least one of the following:

[0025] Select among multiple candidate waveforms (including OFDM, FBMC, and DSSS) based on the environmental situation information or service requirements, and adaptively adjust key parameters of the selected waveform (including cyclic prefix length, subcarrier spacing, and filter parameters);

[0026] Based on the environmental situation information (interference type and channel quality), select between multiple channel coding schemes (including LDPC, Polar Code, Fountain Code), and adaptively adjust the coding rate and modulation mode;

[0027] According to the environmental situation information (DOA of the interference signal), the multi-antenna system is controlled to perform adaptive beamforming or spatial nulling.

[0028] Preferably, the adaptive interference suppression carrier communication method comprises the following steps:

[0029] Sp1. Using an environmental sensing module (ESM) to monitor electromagnetic signals within a preset frequency band, extract multi-dimensional features of the electromagnetic signals (including at least one or more of spectrum, time domain, and spatial domain features), and generate environmental situation information including interference information and channel state information. The environmental situation information generated by the environmental sensing module includes signal arrival direction information and is constructed into an interference map data structure.

[0030] Sp2. Using a pre-trained classification model or anomaly detection algorithm, identify the type of interference signal or indicate unknown interference, and include the result in the environmental situation information;

[0031] Sp3, cognitive decision-making step: using the pre-trained artificial intelligence model in the cognitive decision engine (CDE), based on the environmental situation information and the internal state information of the system, to generate control instructions covering multiple communication parameter domains (including at least two or more of the frequency, time, space, power, waveform, coding, and modulation domains);

[0032] Sp4. Using an adaptive transceiver control module (ATCM), according to the control instruction, configure the communication parameters of the physical layer (PHY) and the media access control layer (MAC) of the system to perform adaptive adjustment across the multiple communication parameter domains.

[0033] Preferably, the artificial intelligence model used in the cognitive decision-making step is a deep reinforcement learning model, and the step further includes:

[0034] Sp3.1. Using network collaboration information and system security status information received from other network nodes as additional state inputs to the deep reinforcement learning model;

[0035] Sp3.2. Jointly optimize the reward function of multiple communication objectives to train or guide the deep reinforcement learning model.

[0036] Preferably, the method further comprises:

[0037] Distributed collaboration step: using a distributed collaboration module to share interference information and link quality information with other communication nodes in the network, and using the acquired information in the cognitive decision-making step;

[0038] Intrinsic security enhancement step: Utilize the intrinsic security enhancement module to execute at least one security mechanism among dynamic heterogeneous redundancy, mimicry defense or physical layer authentication according to the instructions or preset policies generated by the cognitive decision step.

[0039] Beneficial effects

[0040] The present invention provides an adaptive interference suppression carrier communication system for complex electromagnetic environments. It has the following beneficial effects:

[0041] 1. Through intelligent environmental perception and AI-driven cognitive decision-making, it can adapt to complex, dynamic, and even unknown electromagnetic environments in real time and accurately, significantly improving the survivability and reliability of communication systems under strong interference. It can perform joint optimization and adaptive adjustment across multiple dimensions such as frequency, time, space, power, waveform, coding, and modulation, achieving more refined and effective interference suppression and avoidance.

[0042] 2. Through distributed collaborative modules, intelligent sharing and collaborative decision-making between nodes are realized, improving the overall anti-interference capability and resource utilization efficiency of the network. Security mechanisms such as dynamic heterogeneous redundancy, mimicry defense, and physical layer authentication are deeply integrated into the communication system, transforming passive defense into active immunity, and effectively countering intelligent and targeted attacks.

[0043] 3. The system has the ability of autonomous learning and intelligent decision-making, reducing manual intervention and improving operational efficiency and response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a system structure block diagram of the present invention;

[0045] Figure 2 This is a functional block diagram of the ESM of the present invention;

[0046] Figure 3 Schematic diagram of the CDE workflow of the present invention;

[0047] Figure 4 Schematic diagram of the federated learning process in DCM of the present invention;

[0048] Figure 5 Schematic diagram of the mimicry defense mechanism in the ESEM of the present invention;

[0049] Figure 6 This is a flow chart of the communication method of the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. Specific embodiment one:

[0052] like Figures 1-6As shown, this embodiment provides an adaptive interference suppression carrier communication system for complex electromagnetic environments. The system aims to provide highly reliable, efficient, resilient and secure wireless communication capabilities in complex, dynamic electromagnetic environments, and even those containing malicious attacks, through the precise design and intelligent collaboration of its internal functional modules. The system mainly includes the following core components: Environmental Perception Module (ESM), Cognitive Decision Engine (CDE), Adaptive Transceiver Control Module (ATCM), Distributed Collaboration Module (DCM) and Intrinsic Security Enhancement Module (ESEM). These modules are interconnected through internal high-speed data buses or dedicated interfaces, and work closely with the system's radio frequency front end (RFFE), antenna subsystem, and physical layer (PHY), media access control layer (MAC) and other protocol stack parts.

[0053] Environmental Sensing Module (ESM) reference Figure 1 and Figure 2 ,ESM plays the role of system environment sensor, and its core task is to accurately, comprehensively and in real time perceive and understand the electromagnetic environment in which the system is located.

[0054] Signal Monitoring and Multi-Dimensional Feature Extraction: The ESM receives broadband RF signals through the antenna subsystem and RFFE, performs necessary amplification, filtering, and high-precision analog-to-digital conversion (using a 16-bit ADC with a sampling rate greater than 500 MSPS), and generates a digital intermediate frequency (IF) or baseband IQ data stream. This data stream is then fed into the internal signal processing unit (utilizing an FPGA for parallel processing capabilities). The signal processing unit performs a series of operations:

[0055] Wideband spectrum analysis (PSD calculation via FFT).

[0056] Signal detection (using CFAR detector to identify potential signals).

[0057] Multi-dimensional feature extraction: For the detected signal, multi-dimensional features are extracted in parallel and meticulously, which include at least one or more of spectral features, time domain features, and spatial domain features:

[0058] Spectrum characteristics: center frequency, precise bandwidth (3dB, 6dB), power (peak, average), power spectrum density shape (flatness, roll-off factor), sideband characteristics, number of carriers (for multi-carrier signals), etc.

[0059] Time domain characteristics: pulse width, arrival time (TOA), pulse repetition interval (PRI) and its jitter pattern (for pulse interference); signal envelope characteristics, zero-crossing rate, symbol rate (for digital modulation signals), etc.

[0060] Spatial characteristics: Utilizes multi-antenna data and DOA estimation algorithm units (MUSIC, ESPRIT) to calculate the signal direction of arrival (DOA) information, including azimuth and / or elevation angles and their estimation accuracy.

[0061] Cyclostationary characteristics, statistical characteristics (peak-to-average ratio, kurtosis), modulation domain characteristics (preliminary identification), etc.

[0062] Environmental situation information generation, interference identification and unknown detection: The extracted multi-dimensional feature vectors are fed into the AI ​​analysis unit (which can be implemented based on SoC, embedded GPU or AI coprocessor).

[0063] Interference Type Identification: This unit uses a pre-trained classification model to identify the type of detected interference signals based on the multi-dimensional features. This model is a deep neural network, likely combining CNN layers (to extract local patterns in spectrograms or time-spectrograms) with LSTM / GRU layers (to process the signal's time series characteristics or cyclic feature evolution). Finally, a fully connected layer and softmax are used to output the probability of each known interference type. The model is trained using simulated and measured data containing a large number of labeled samples, using backpropagation and optimizers such as Adam to minimize cross-entropy loss.

[0064] Unknown Interference Identification: This unit also utilizes anomaly detection algorithms to identify unknown interference signals. A common approach is to train an autoencoder model. This model, consisting of an encoder and a decoder, is trained only on known interference samples, with the goal of minimizing the reconstruction error (MSELoss). When a new signal's feature vector is input, if the reconstruction error after passing it through the autoencoder is significantly higher than normal (exceeding a threshold), it is labeled as unknown interference.

[0065] Finally, the ESM integrates all analysis results (including channel state information) to generate environmental situation information including interference information and channel state information, and explicitly includes the interference type identification result or unknown interference indication in the environmental situation information.

[0066] Interference map data structure: To facilitate CDE understanding and use, the environmental situation information is preferably structured into an interference map data structure. This structure systematically organizes the perception results and can be a dynamically updated list or database, where each entry corresponds to a detected interference source or an affected frequency band / directional area, and contains information such as the frequency range, peak / average power, estimated direction of arrival (DOA), identified type (or marked as unknown), and a confidence score.

[0067] ESM outputs this comprehensive, detailed, and real-time environmental situation information (including interference maps) to CDE.

[0068] The Cognitive Decision Engine (CDE) is the intelligent decision-making center of the system. Its detailed working mechanism is as follows: Figure 3 Information Input and State Construction: The CDE receives environmental status information (from the ESM) and the system's internal state information (from the ATCM, etc.). Crucially, it also receives network collaboration information from other network nodes via the DCM, as well as system security status information provided by the ESEM. This information collectively defines the state space input to the DRL model. This state information requires preprocessing before input into the model.

[0069] AI-based intelligent decision-making:

[0070] Model Type and Implementation: The core of CDE is to use a pre-trained AI model for decision making, preferably a deep reinforcement learning (DRL) model. Algorithms such as PPO (Proximal Policy Optimization) or SAC (Soft Actor-Critic) are used.

[0071] PPO: Stabilizing policy updates via a truncated surrogate objective function combined with GAE estimation advantages.

[0072] SAC: Introducing the maximum entropy objective to encourage exploration, using TwinQ-networks and target networks to stabilize learning.

[0073] The neural network of the DRL model can include CNN, RNN (LSTM / GRU), Transformer, or a combination thereof. A Transformer-based architecture can be used to handle state dependencies using the self-attention mechanism.

[0074] Training: DRL models are primarily trained through offline simulation, requiring significant interaction and computational resources. The design of the reward function is crucial. The reward function of the deep reinforcement learning model is designed to jointly optimize communication throughput, bit error rate, latency, power consumption, and safety metrics. A weighted sum R = Σw_imetric_i is used, with weights w_i being dynamically adjustable.

[0075] Multi-domain control command generation: The actor network of the DRL model outputs action vectors, which the CDE parses into control commands covering multiple communication parameter domains. These domains include at least two or more of the frequency domain, time domain, spatial domain, power domain, waveform domain, coding domain, and modulation domain. The CDE sends the control commands to the ATCM.

[0076] Adaptive Transceiver Control Module (ATCM), command reception and parsing: ATCM receives the control commands (from CDE).

[0077] Parameter Configuration and Execution: The ATCM configures the system's physical layer (PHY) or media access control layer (MAC) communication parameters based on the control instructions to perform adaptive adjustments across the multiple communication parameter domains. Specific configuration actions include at least one or more of the following:

[0078] Waveform selection and parameterization:

[0079] Select among multiple candidate waveforms: select OFDM, FBMC, DSSS, etc. according to the environmental situation information or business requirements.

[0080] Adaptively adjust the key parameters of the selected waveform: adjust the cyclic prefix (CP) length and subcarrier spacing of OFDM; adjust the filter parameters of FBMC.

[0081] Coding and modulation adjustment:

[0082] Select between multiple channel coding schemes: LDPC, Polar Code, Fountain Code, etc. are selected based on the environmental situation information (especially the interference type and channel quality).

[0083] Adaptive adjustment of coding rate and modulation mode: Select the optimal combination from the MCS list based on real-time link quality feedback.

[0084] Airspace Handling Control:

[0085] According to the environmental situation information (especially the DOA of the interference signal), the multi-antenna system is controlled to perform adaptive beamforming (using the MMSE criterion w=αR_nn^{-1}a(θ_d) to calculate the weight) or spatial zeroing (using the ZF criterion w=P_nulla(θ_d) to calculate the weight).

[0086] Distributed Collaboration Module (DCM) realizes network collaboration.

[0087] Inter-node information exchange: The DCM exchanges information with other communication nodes in the network. This information exchange includes at least sharing interference information generated by the Environment Sensing Module (ESM) and sharing local link quality information.

[0088] Information is supplied to CDE: DCM and provides information obtained from other nodes (possibly after fusion) to the cognitive decision engine (CDE) as network collaborative information.

[0089] Advanced Collaboration Capabilities: DCM is also configured to perform:

[0090] Participate in distributed model training based on Federated Learning (FL): Figure 4 As shown, at least one shared AI model for interference identification, channel prediction, or policy generation is collaboratively trained. This utilizes the FedAvg process: nodes train locally and only upload model updates (not raw data) to the aggregator for aggregation. During training, the node's raw sensory data never leaves the local node.

[0091] Execute distributed resource negotiation protocol: Implement and execute distributed resource negotiation protocol (based on signaling or optimization algorithms such as ADMM), and collaborate with other nodes to allocate communication resources or perform interference suppression operations.

[0092] The Endogenous Security Enhancement Module (ESEM) provides endogenous security capabilities.

[0093] Execution trigger: ESEM actions are initiated based on the instructions of the cognitive decision engine (CDE) or the system's preset security policies.

[0094] The implemented built-in security mechanisms include at least one of the following:

[0095] Dynamic Heterogeneous Redundancy (DHR): Dynamically selects one or a group of redundant processing modules from multiple functionally equivalent but different implementations to process the current communication signal. The selection mechanism can be based on instructions or random strategies.

[0096] Mimic Defense: See Figure 5 The control system performs rapid, pseudo-random parameter switching across multiple communication parameter dimensions (including frequency, time, spreading code, waveform parameters, etc.). The switching sequence is generated by a CSPRNG (AES-CTR), and the sender and receiver rely on a synchronization mechanism to maintain consistency.

[0097] Physical layer authentication (PHY Authentication): Extracts fingerprint information based on the channel characteristics or RF characteristics of the received signal. This fingerprint vector is then compared with the fingerprint templates of trusted nodes stored in a secure database (calculating Euclidean distance, cosine similarity, or using an SVM classifier). Identity is confirmed only if a match is found. Specific embodiment two:

[0099] like Figure 6 As shown, the adaptive interference suppression carrier communication method includes the following steps:

[0100] Sp1. Utilize an Environmental Sensing Module (ESM) to monitor electromagnetic signals within a preset frequency band, extract multi-dimensional features of the electromagnetic signals (including at least one or more of the spectrum, time domain, and spatial domain features), and generate environmental situation information containing interference information and channel state information. The environmental situation information generated by the Environmental Sensing Module includes signal arrival direction information and is constructed into an interference map data structure. Environmental Sensing (Enhanced): The ESM monitors signals, extracts multi-dimensional features, and generates environmental situation information. Ensure that the information contains DOA information and is constructed into an interference map data structure.

[0101] Sp2. Use pre-trained classification models or anomaly detection algorithms to identify the type of interference signal or indicate unknown interference, and include the results in the environmental situation information. Interference identification: The AI ​​unit inside the ESM uses a pre-trained classification model to identify the type of interference and uses an anomaly detection algorithm to indicate unknown interference, and the results are included in the environmental situation information;

[0102] Sp3, cognitive decision-making step: using the pre-trained artificial intelligence model in the cognitive decision engine (CDE), based on environmental situation information and the system's internal state information, to generate control instructions covering multiple communication parameter domains (including at least two or more of the frequency, time, space, power, waveform, coding, and modulation domains);

[0103] The artificial intelligence model used in the cognitive decision-making step is a deep reinforcement learning model. The steps include:

[0104] Sp3.1. Use the network collaboration information and system security status information received from other network nodes as additional state inputs to the deep reinforcement learning model;

[0105] Sp3.2. Jointly optimizing reward functions for multiple communication objectives to train or guide deep reinforcement learning models;

[0106] Sp4, using an adaptive transceiver control module (ATCM), according to control instructions, to configure the communication parameters of the physical layer (PHY) and the media access control layer (MAC) of the system to perform adaptive adjustment across multiple communication parameter domains;

[0107] Distributed collaboration step: Use the distributed collaboration module to share interference information and link quality information with other communication nodes in the network, and use the acquired information in the cognitive decision step;

[0108] Intrinsic security enhancement step: Utilize the intrinsic security enhancement module to execute at least one security mechanism among dynamic heterogeneous redundancy, mimicry defense, or physical layer authentication according to the instructions or preset policies generated by the cognitive decision step. Specific embodiment three:

[0110] Based on the technical solutions of the first and second embodiments, a practical application case is further described:

[0111] In countries prone to natural disasters such as earthquakes and typhoons, establishing a stable and reliable emergency communication network immediately after a disaster is crucial for saving lives and coordinating rescue efforts. However, disaster areas are often plagued by damaged infrastructure, power outages, spectrum chaos, and poor channel conditions, posing a severe challenge to traditional communication systems. The deployment of the "Intelligent Sense and Disturbance Prevention" Cognitive Collaborative Adaptive Resilient Carrier Communication System (CCARCS) is designed to provide unprecedented communication assurance capabilities in this extremely complex electromagnetic environment. Its breakthrough lies in the unprecedented integration of deep environmental perception, AI cognitive decision-making, multi-domain adaptive execution, distributed intelligent collaboration, and inherent active safety.

[0112] In practical applications, the CCARCS system, deployed on command vehicles, individual terminals, and drones, first uses its Environmental Sensing Module (ESM) to precisely "profile" the chaotic spectrum in the disaster area. This far exceeds the simple energy detection of traditional spectrum analyzers. Leveraging its broadband monitoring capabilities and multi-dimensional feature extraction techniques (spectral, temporal, spatial, and cyclostationary), the ESM can precisely distinguish broadband impulse noise from damaged power facilities, stray radiation from temporary generators, intermodulation interference between a large number of different rescue equipment (even legacy analog radios), and atypical signals caused by atmospheric disturbances or unusual geological activity. Its breakthrough lies in its built-in AI analysis unit: pre-trained deep learning models such as CNN+LSTM can quickly identify known or similar interference types, while anomaly detection algorithms such as autoencoders can "pick" and label previously unknown interference signals from the background, a feat difficult to achieve with traditional rule-based or template matching methods. Combined with the DOA estimation of multiple antenna arrays, the high-precision, dynamically updated "interference map" (including frequency, power, direction, type, confidence, etc.) generated by ESM provides an unprecedented, comprehensive and accurate situational information foundation for the intelligent decision-making of the entire system.

[0113] Based on this sophisticated "battlefield intelligence," the Cognitive Decision Engine (CDE), the system's intelligent core, demonstrates revolutionary autonomous decision-making capabilities. It receives situational information from the ESM, combines it with local terminal status (such as remaining battery life and priority of pending data), critical interference intelligence and link quality reports shared by other rescue nodes via the Distributed Collaboration Module (DCM), and security status reports from the Endogenous Security Enhancement Module (ESEM), and leverages its deep reinforcement learning (DRL) models (such as PPO / SAC) for a holistic approach. This AI-driven decision-making process is a true breakthrough. It no longer relies on rigid, pre-set rules. Instead, it draws on learned experience to autonomously generate optimal control command combinations across the entire spectrum of communication parameters (frequency, time, space, power, waveform, coding, and modulation) in real time within a complex, multi-dimensional state space. For example, its built-in multi-objective reward function automatically prioritizes reliability (such as selecting a strong error-correcting code) and low latency for high-priority vital sign data transmission requests, even at the expense of throughput or increased instantaneous power consumption. When transmitting general disaster imagery, it may prioritize spectral efficiency and energy conservation.

[0114] The CDE's intelligent instructions are then quickly and accurately executed by the Adaptive Transceiver Control Module (ATCM), a critical step in translating decisions into physical layer resilience. The innovative value of the ATCM lies in its extreme flexibility and multi-dimensional linkage capabilities. It goes beyond simply adjusting the rate to enable deep physical layer reconfiguration. For example, when the CDE determines that narrowband interference is severe and adjacent spectrum is available, the ATCM switches to the FBMC waveform, which has stronger spectrum shaping capabilities, to avoid interference. When the CDE determines that the channel is experiencing severe fast fading due to building obstruction and movement, it selects a coded modulation scheme with better diversity performance and may instruct the multi-antenna system to perform space-time block coding (STBC) or receive diversity combining. Once the ESM pinpoints the direction of a strong interference source, the ATCM calculates and applies adaptive beamforming weights, creating deep spatial nulling in that direction at the receiver, or precisely directing energy to the target receiving node at the transmitter, significantly improving the signal-to-noise ratio of a specific link. At the same time, according to the real-time channel quality, the OFDM cyclic prefix (CP) length is dynamically adjusted to adapt to the changing multipath environment, and LDPC, Polar, and even Fountain codes are selected and the code rate is fine-tuned to achieve the best balance between rate and reliability.

[0115] Network-level resilience is provided by the Distributed Collaboration Module (DCM), whose core innovation lies in the implementation of swarm intelligence and resource sharing. Rescue teams are widely distributed, and the perception and decision-making capabilities of individual nodes are limited. Through the DCM, nodes can efficiently share key interference information summaries and link status. Furthermore, based on the Federated Learning (FL) mechanism, all nodes can collaboratively train an interference identification model or channel prediction model adapted to the current disaster area's unique electromagnetic environment without exposing local raw data. This significantly improves the accuracy and timeliness of global situational awareness, which is unmatched by traditional distributed systems. Furthermore, the DCM supports a distributed resource negotiation protocol, enabling nodes from different rescue teams to intelligently coordinate the use of spectrum, time slots, and power, avoiding "internal consumption"-like mutual interference and maximizing overall network communication efficiency within limited resources. This collaborative capability ensures that even if some nodes fail or become isolated, the network maintains maximum connectivity and service capabilities.

[0116] Finally, the Endogenous Security Enhancement Module (ESEM) provides a solid security foundation for rescue communications. Its breakthrough lies in deeply integrating security capabilities into the communications system itself, enabling proactive defense. In the chaotic disaster environment, preventing malicious interference, information theft, or identity forgery is crucial. ESEM's physical layer authentication utilizes each device's unique channel or RF "fingerprint" for authentication, effectively preventing attempts to access the network by counterfeit devices. In the face of potential malicious interference or signal analysis attacks, the CDE can instruct the ESEM to initiate mimicry defense. This utilizes high-speed, pseudo-random multi-dimensional parameter transitions (frequency, time, encoding, waveform micro-parameters, etc.) driven by a CSPRNG, making communication signals difficult to track, lock, or decode, significantly enhancing survivability. Furthermore, the Dynamic Heterogeneous Redundancy (DHR) mechanism provides backup for critical processing links. Even if a software implementation is attacked, the system can switch to another heterogeneous implementation, ensuring uninterrupted core functionality.

[0117] In summary, the CCARCS system, through its deeply integrated intelligent perception, AI cognitive decision-making, multi-domain adaptive execution, distributed collaboration, and the coordinated application of a series of breakthrough technologies, can build an emergency communication network with high resilience, high efficiency, and high security that far exceeds the capabilities of traditional communication systems in the extremely complex electromagnetic environment after large-scale disasters such as earthquakes, providing strong technical support for saving lives and coordinating rescue. Specific embodiment four:

[0119] Based on the technical solutions of the first and second embodiments, a practical application case is further described:

[0120] Autonomous driving technology, especially L4 / L5 highly automated driving and convoy operation, places unprecedented demands on ultra-high reliability, ultra-low latency (URLLC), and high security for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Traditional V2X communication technology faces enormous challenges in high-density urban environments with numerous high-rise buildings, congested wireless signals, and potential for malicious interference. The application of the "Intelligent Sense of Disturbance" cognitive collaborative adaptive resilient carrier communication system (CCARCS) is designed to provide autonomous driving fleets with a revolutionary communication solution that can ensure safe and efficient collaboration in such harsh environments. Its innovative value lies in its intelligent adaptability to extremely complex environments and its embedded active safety protection mechanism.

[0121] The CCARCS system, deployed in every vehicle in the fleet, features an Environmental Sensing Module (ESM) that acts as an "electronic sentry." It not only monitors V2X-specific frequency bands (such as 5.9 GHz) but also scans surrounding ISM bands for potential interference. Its innovation lies in its ability not only to "see" interference but also to "understand" it. In densely populated urban areas, the ESM leverages sophisticated spectrum analysis and multi-dimensional feature extraction capabilities to distinguish complex interference signals from densely deployed Wi-Fi / Bluetooth devices, other vehicle sensors (radar, LiDAR), mobile base stations, and even power lines or traffic light controllers. Using AI classification models (such as CNN+LSTM), it can identify the patterns of these common interference sources. More importantly, in the severe multipath and NLOS environments caused by the urban canyon effect, the ESM accurately estimates the multipath delay spread and rapidly time-varying characteristics (Doppler shift) of the channel. Combined with Direction of Access (DOA) estimation, it can also preliminarily locate the primary interference source (such as a fixed, strong interfering transmitter or a nearby, unusual vehicle). The anomaly detection algorithm (Autoencoder) is responsible for identifying atypical and potentially malicious signals, such as GPS spoofing signals or V2X jamming attack signals. All of this information is integrated into a dynamic jamming map in real time to provide a basis for decision-making.

[0122] The system's core, the Cognitive Decision Engine (CDE), demonstrates AI-powered decision-making intelligence tailored for autonomous driving scenarios. It receives the ESM's precise environmental image and combines it with its own vehicle's sensor data (speed, acceleration, steering angle), driving intent, high-precision positioning information, and critical collaborative information (such as neighboring vehicle status, planned trajectory, and link quality) obtained from other vehicles in the platoon via the DCM. It also considers the ESEM's safety status. A breakthrough lies in the CDE's DRL model (PPO / SAC) trained to prioritize URLLC requirements. Its multi-objective reward function highly rewards control command transmission that meets millisecond latency and "five-nines" or higher reliability, while severely penalizing any communication failure that could compromise safety. Based on this, the CDE is able to make optimal communication decisions that are highly context-aware, predictive, and cross-domain. For example, when predicting an impending intersection with known high interference, the CDE preemptively instructs the ATCM to switch to the most robust communication mode. During high-speed platooning, the CDE adjusts waveform parameters based on real-time Doppler estimation. When a potential jamming attack is detected, the CDE collaborates with the ESEM to enhance safety.

[0123] The Adaptive Transceiver Control Module (ATCM) is responsible for translating the CDE's intelligent decisions into extremely flexible and responsive physical layer actions, a critical step in ensuring URLLC. Its innovative value lies in its deep, context-driven adaptive capabilities. When the CDE determines that the channel is experiencing severe NLOS and fast fading, the ATCM not only reduces the rate but may also switch to a coding scheme with greater diversity capabilities (such as low-rate Polar codes) and enable space-time coding (STBC). When strong co-channel interference needs to be mitigated, the ATCM utilizes a multi-antenna array to perform precise adaptive beamforming and spatial nulling, suppressing interference at the receiver. To combat urban multipath, the OFDM CP length is dynamically adjusted. To maximize the transmission success rate of short bursts, the MCS level and HARQ retransmission strategy are finely tuned. This real-time, joint, intelligent optimization of multiple dimensions, including waveform, coding, modulation, and spatial processing, is unmatched by traditional fixed-parameter or limited adaptive systems.

[0124] The Distributed Collaboration Module (DCM) plays a vital role in fleet scenarios. Its breakthrough lies in achieving efficient, reliable, and intelligent fleet-level collaboration. Vehicles need to frequently exchange large amounts of status and control information with extremely low latency. The DCM not only ensures the reliable transmission of this information, but also enables a higher level of collaboration: by sharing their respective interference perception results (possibly through federated learning to collaboratively train an interference prediction model adapted to the current urban area), the fleet can form a unified understanding of the electromagnetic environment and make better collective decisions (such as switching to a clean frequency band). By executing a low-latency optimized distributed resource negotiation protocol, vehicles within the fleet can avoid mutual interference in V2V communications and ensure that the priority transmission channel for critical control information is unobstructed. This swarm intelligence significantly improves the operational efficiency and safety of the entire fleet in complex environments.

[0125] Finally, the Endogenous Security Enhancement Module (ESEM) provides indispensable active security protection for autonomous driving fleet communications. Its innovation lies in internalizing defense as an inherent property of the system. In high-risk autonomous driving applications, preventing malicious manipulation is crucial. ESEM's physical layer authentication mechanism ensures the authenticity of the message source by verifying the "physical fingerprint" of inter-vehicle communications, effectively defending against forged identity and message injection attacks. When the system senses targeted interference or GPS spoofing attacks, the CDE will instruct ESEM to initiate mimicry defense, making it difficult for attackers to lock on to and destroy critical fleet collaborative communication links by performing unpredictable high-speed parameter jumps in frequency, time, coding and other dimensions. Dynamic Heterogeneous Redundancy (DHR) provides additional fault tolerance for software modules that process critical safety information and control instructions.

[0126] The CCARCS system, through its unique integration of intelligent perception, AI cognitive decision-making, multi-domain adaptive execution, distributed collaboration, and inherent safety technologies, provides a groundbreaking communications solution for the coordinated operation of autonomous vehicle fleets in high-density urban environments. It not only addresses the reliability and latency challenges of traditional V2X technology in complex electromagnetic environments, but also significantly enhances the system's anti-attack capabilities through embedded active safety mechanisms, laying a solid communications foundation for safe and efficient future intelligent transportation.

[0127] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0128] The technical solutions provided by the embodiments of the present invention are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concepts of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

[0129] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further restrictions, an element defined by the statement "comprising a reference structure" does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0130] 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. An adaptive interference suppression carrier communication system for complex electromagnetic environments, characterized by: The adaptive interference suppression carrier communication system includes the following components: An environmental perception module, the environmental perception module is used to: monitor electromagnetic signals within a preset frequency band and extract multi-dimensional features of the electromagnetic signals; the multi-dimensional features include one or more of spectral features, time domain features, and spatial domain features; the spatial domain features extracted by the environmental perception module include signal arrival direction information, and the environmental situation information is constructed into an interference map data structure, the interference map data structure including information on the frequency, power, direction, and type of the interference signal; a cognitive decision engine configured to receive environmental situation information and internal state information of the adaptive interference suppression carrier communication system; multiple communication parameter domains, the multiple communication parameter domains comprising two or more of a frequency domain, a time domain, a spatial domain, a power domain, a waveform domain, a coding domain, and a modulation domain; An adaptive transceiver control module, the adaptive transceiver control module is used to receive control instructions; according to the control instructions, configure the communication parameters of the physical layer or the media access control layer of the system; A distributed collaboration module, which is used to interact with other communication nodes in the network; An intrinsic security enhancement module is used to execute an intrinsic security mechanism according to the instructions of the cognitive decision engine or a preset security policy.

2. The adaptive interference suppression carrier communication system based on complex electromagnetic environment according to claim 1 is characterized in that: The cognitive decision engine utilizes a pre-trained artificial intelligence model as a deep reinforcement learning model; and the state space input of the deep reinforcement learning model also includes network collaboration information received from other network nodes and system security status information; the reward function of the deep reinforcement learning model jointly optimizes communication throughput, bit error rate, latency, power consumption and safety indicators.

3. The adaptive interference suppression carrier communication system based on complex electromagnetic environment according to claim 1, characterized in that: The distributed collaboration module is also configured to: participate in distributed model training based on federated learning, wherein multiple nodes collaboratively train at least one shared artificial intelligence model for interference identification, channel prediction or strategy generation, and the original perception data of the node does not leave the local node during the training process, execute a distributed resource negotiation protocol, and collaborate with other nodes to allocate communication resources or perform interference suppression operations.

4. The adaptive interference suppression carrier communication system based on complex electromagnetic environment according to claim 1, characterized in that: The communication parameter adjustment configured by the adaptive transceiver control module (ATCM) includes at least one of the following: Selecting between a plurality of candidate waveforms according to the environmental situation information or business requirements, and adaptively adjusting key parameters of the selected waveform; Selecting between a plurality of channel coding schemes according to the environmental situation information and adaptively adjusting the coding rate and modulation mode; According to the environmental situation information, the multi-antenna system is controlled to perform adaptive beamforming or spatial nulling.

5. The method of the adaptive interference suppression carrier communication system for complex electromagnetic environments according to any one of claims 1 to 4, characterized in that: The adaptive interference suppression carrier communication method comprises the following steps: Sp1. Using an environmental perception module to monitor electromagnetic signals within a preset frequency band, extracting multi-dimensional features of the electromagnetic signals, and generating environmental situation information including interference information and channel state information, wherein the environmental situation information generated by the environmental perception module includes signal arrival direction information and is constructed into an interference map data structure; Sp2. Using a pre-trained classification model or anomaly detection algorithm, identify the type of interference signal or indicate unknown interference, and include the result in the environmental situation information; Sp3, cognitive decision-making step: using the pre-trained artificial intelligence model in the cognitive decision-making engine to generate control instructions covering multiple communication parameter domains based on the environmental situation information and the internal state information of the system; Sp4. Utilize the adaptive transceiver control module to configure the communication parameters of the physical layer and the media access control layer of the system according to the control instruction, so as to perform adaptive adjustment across the multiple communication parameter domains.

6. The adaptive interference suppression carrier communication method based on complex electromagnetic environment according to claim 5, characterized in that: The artificial intelligence model used in the cognitive decision-making step is a deep reinforcement learning model, and the step also includes: Sp3.

1. Using network collaboration information and system security status information received from other network nodes as additional state inputs to the deep reinforcement learning model; Sp3.

2. Jointly optimize the reward function of multiple communication objectives to train or guide the deep reinforcement learning model.

7. The adaptive interference suppression carrier communication method based on complex electromagnetic environment according to claim 5, characterized in that: The method further comprises: Distributed collaboration step: using a distributed collaboration module to share interference information and link quality information with other communication nodes in the network, and using the acquired information in the cognitive decision-making step; Intrinsic security enhancement step: Utilize the intrinsic security enhancement module to execute at least one security mechanism among dynamic heterogeneous redundancy, mimicry defense or physical layer authentication according to the instructions or preset policies generated by the cognitive decision step.

Images