Radiation control network node cooperative communication method and system

Abstract

The invention provides a radiation control network node cooperative communication method and system, and relates to the technical field of computers, and the method comprises the steps: obtaining background radiation data in a target area and the original information content of to-be-sent data of each node; obtaining independent initial virtual radiation potential energy of each network node according to the background radiation data and the original information content; establishing a coupling relationship for all nodes according to the initial virtual radiation potential energy to obtain a continuous situation game field; obtaining a potential energy adjustment vector according to the continuous situation game field; deciding the transmitting state of the node according to the potential energy adjustment vector to obtain a transmitting spectrum form; the method comprises the following steps: performing closed-loop processing on a communication process according to an emission spectrum form, and iteratively updating historical background radiation data by taking a radiation state generated by actual emission as new environment feedback data until virtual radiation potential energy of a node does not change any more, so as to obtain a steady-state communication strategy enabling a network radiation mode to converge to a background.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method and system for collaborative communication between nodes in a radiation control network. Background Technology

[0002] In wireless communication networks operating in complex electromagnetic environments, especially in covert cooperative scenarios with stringent requirements for low observability, ensuring reliable communication between nodes while effectively "hiding" their radiated signal characteristics within dynamically changing background noise is a key challenge in this field. The core of this problem lies in the fact that the transmission behaviors of each node in the network superimpose and interact with the time-varying electromagnetic environment, forming a dynamic, coupled system. Its overall radiation characteristics are not simply the sum of the behaviors of each node, and communication efficiency depends on this coupling relationship. Existing technologies typically treat radiation control and communication optimization as two relatively independent problems, for example, employing power control based on fixed thresholds, spectrum agility based on preset modes, or information scheduling strategies based on local channel states. These methods essentially rely on predefined rules or simplified modeling of the environment, failing to inherently and integratedly mathematically link and coordinate the formation of the overall network radiation pattern with the spatiotemporal distribution of information flow at the system level. As a result, in dynamic adversarial environments, significant trade-offs often need to be made between communication performance and stealth performance, making it difficult to achieve adaptive and global convergence of the network radiation pattern and the background environment in terms of statistical characteristics. This limits the overall survival and mission effectiveness of collaborative networks in highly adversarial and complex electromagnetic environments.

[0003] Based on the shortcomings of the existing technologies, there is an urgent need for a method and system for collaborative communication between nodes in a radiation control network. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for cooperative communication among nodes in a radiation control network, thereby improving the aforementioned problems. To achieve this objective, the technical solution adopted by this invention is as follows:

[0005] Firstly, this application provides a method for cooperative communication between nodes in a radiation control network, including:

[0006] Acquire background radiation data in the target area and the raw information content of the data to be transmitted by each node;

[0007] Based on the background radiation data and the original information content, the local channel gain of each node is fused, and by constructing a scalar function coupled with the instantaneous communication needs of the node and the environmental background, the independent initial virtual radiation potential of each network node is obtained.

[0008] Based on the initial virtual radiation potential energy, the coupling relationship of all nodes is established. By defining a functional that maps the overall radiation characteristics of the network to the communication information flow as a common action, a continuous situational game field describing the interaction of nodes is obtained.

[0009] Based on the continuous situational game field, the virtual radiation potential energy of each node is co-evolved. By solving the variational problem that makes the system action tend to be static and interacting with the potential energy gradient information between nodes, the potential energy adjustment vector is obtained.

[0010] The emission state of the node is decided based on the potential energy adjustment vector. By mapping the potential energy vector to a point in the radiation parameter space that conforms to physical constraints, the emission spectrum of each node at the next moment is obtained.

[0011] The communication process is closed-loop processed according to the transmitted spectrum pattern. By using the radiation state generated by the actual transmission as new environmental feedback data, the historical background radiation data is iteratively updated until the virtual radiation potential energy of the node no longer changes, thus obtaining a steady-state communication strategy that makes the network radiation pattern converge to the background.

[0012] Secondly, this application also provides a radiation control network node cooperative communication system, comprising:

[0013] The acquisition module is used to acquire background radiation data in the target area and the original information content of the data to be transmitted by each node;

[0014] The fusion module is used to fuse the local channel gain of each node based on the background radiation data and the original information content. By constructing a scalar function coupled with the instantaneous communication needs of the node and the environmental background, the independent initial virtual radiation potential of each network node is obtained.

[0015] The module is used to establish coupling relationships between all nodes based on the initial virtual radiation potential energy. By defining a functional that maps the overall radiation characteristics of the network to the communication information flow as a common action, a continuous situational game field describing node interactions is obtained.

[0016] The evolution module is used to perform collaborative evolution of the virtual radiation potential energy of each node according to the continuous situation game field. It obtains the potential energy adjustment vector by solving the variational problem that makes the system action tend to static and by exchanging the potential energy gradient information between nodes.

[0017] The decision module is used to make decisions on the emission state of the node based on the potential energy adjustment vector. By mapping the potential energy vector to a point in the radiation parameter space that conforms to physical constraints, the emission spectrum of each node at the next moment is obtained.

[0018] The output module is used to perform closed-loop processing of the communication process based on the transmitted spectrum pattern. By using the radiation state generated by the actual transmission as new environmental feedback data, the historical background radiation data is iteratively updated until the virtual radiation potential energy of the node no longer changes, thus obtaining a steady-state communication strategy that makes the network radiation pattern converge to the background.

[0019] The beneficial effects of this invention are as follows:

[0020] This invention constructs a collaborative optimization framework based on virtual radiation potential energy and a continuous situational game field, enabling each node in the network to adaptively adjust its transmission spectrum according to the dynamic environment and its own communication needs. Ultimately, this achieves the convergence and fusion of the overall radiation characteristics of the network and the background electromagnetic environment, thus achieving a dynamic unity of covert communication and reliable transmission. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating a radiation control network node cooperative communication method as described in an embodiment of the present invention.

[0023] Figure 2 This is a schematic diagram of the structure of a radiation control network node cooperative communication system as described in an embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a radiation control network node cooperative communication device as described in an embodiment of the present invention.

[0025] The diagram is labeled as follows: 800, a collaborative communication device for nodes in a radiation control network; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, acquisition module; 902, fusion module; 903, construction module; 904, evolution module; 905, decision module; 906, output module. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] In complex scenarios such as dense urban spectrum environments or emergency communications after natural disasters, numerous non-cooperative wireless signals of varying origins and intensity exist (e.g., radiation from other communication systems, industrial equipment, and temporarily deployed rescue equipment), constituting dynamic and non-stationary background electromagnetic noise. Distributed monitoring networks operating in this environment (e.g., sensor clusters or drone swarms) need to transmit data of varying urgency (e.g., critical disaster alerts and routine status updates). If each node transmits independently based solely on limited local channel information and employs preset power control or spectrum access strategies, the resulting radiated signals not only easily form "radiation fingerprints" that can be identified and tracked by external passive detection systems in a dynamically changing background, but also, due to the random superposition of signals in the time and frequency domains, generate statistically anomalous and unpredictable interference characteristics, significantly increasing the risk of the entire network being identified, interfered with, or even located by external systems. Therefore, the core technical challenge for achieving robust collaborative operation in such highly dynamic and highly adversarial electromagnetic scenarios is how to enable the overall emission characteristics of such distributed networks, which are composed of the radiation superposition of all nodes, to adaptively "imitate" and "integrate" into the statistical characteristics of dynamic background noise through local interaction and collaborative decision-making, in the absence of central scheduling and under conditions of rapid changes in the external electromagnetic background, while ensuring that information flows of different urgency can be transmitted reliably and with low latency.

[0029] Example 1:

[0030] This embodiment provides a method for collaborative communication between nodes in a radiation control network.

[0031] See Figure 1 The figure shows that the method includes steps S100 to S600.

[0032] Step S100: Obtain background radiation data in the target area and the original information content of the data to be transmitted by each node;

[0033] In step S100, acquiring background radiation data in the target area specifically refers to each node in the network using its radio frequency receiving channel to perform broadband spectrum sampling within a preset frequency band during communication gaps or dedicated listening time slots. This yields a series of received signal power measurements at discrete frequency points arranged in chronological order. These measurements constitute the most direct observation samples of environmental electromagnetic activity. The raw information content of the data to be transmitted by each node includes reading complete data packets from the node's protocol stack's transmit buffer. This includes not only protocol header information such as source and destination identifiers for routing, type fields indicating quality of service, and timeliness parameters defining lifetimes, but also the raw application layer payload bitstream that is neither compressed nor encrypted. These data collectively form the foundation for subsequent collaborative decision-making.

[0034] Step S200: Based on the background radiation data and the original information content, the local channel gain of each node is fused, and the independent initial virtual radiation potential of each network node is obtained by constructing a scalar function coupled with the instantaneous communication needs of the node and the environmental background.

[0035] Step S200 transforms the background radiation data and raw observation data into a unified internal state representation capable of mathematical operations and global coordination. Its design stems from a fundamental contradiction in reality: a node's transmission decisions must simultaneously respond to rapidly changing channel conditions, dynamically fluctuating background noise, and varying data urgency. Simply weighting and summing these inputs of different dimensions, even those with inconsistent units, is ineffective. Therefore, this step constructs a scalar function coupled to the node's instantaneous communication needs and environmental background, essentially creating a mathematical converter. This converter integrates the physical link quality represented by the local channel gain, the dynamic environmental threats implied in the background radiation data, and the service urgency extracted from the raw information content into a complex-form initial virtual radiation potential. This potential is not directly equivalent to transmission power but rather an abstract strategy variable that integrates the node's situation and intentions for subsequent global game theory.

[0036] Step S300: Establish coupling relationships for all nodes based on the initial virtual radiation potential energy. By defining a functional that maps the overall radiation characteristics of the network to the communication information flow as a common action, a continuous situational game field describing node interactions is obtained.

[0037] Step S300 addresses the fundamental problem of multi-node collaboration: the decisions of individual nodes can influence others through mutual interference via the wireless medium, collectively shaping the overall, observable radiation characteristics of the network. If nodes make independent decisions based solely on their own virtual radiation potential, their behavior may be conflicting or redundant on a macroscopic level. This step aims to establish coupling relationships between nodes at the system level, mathematically constructing a continuous situational field covering the entire physical region from the discretely distributed initial virtual radiation potentials of all nodes. A functional mapping the overall radiation characteristics of the network to the communication information flow is defined as the common action. Its physical meaning lies in setting a unified optimization objective for the entire network system: not only to ensure efficient information flow transmission but also to ensure that the overall pattern formed by the superposition of radiation from all nodes satisfies a certain overall constraint. This continuous situational game field is the mathematical framework describing the strategic interactions of nodes under this global coupling constraint.

[0038] Step S400: Based on the continuous situational game field, the virtual radiation potential energy of each node is co-evolved. By solving the variational problem that makes the system action tend to be static, and interacting with the potential energy gradient information between nodes, the potential energy adjustment vector is obtained.

[0039] Step S400 is the specific process within the global game framework that drives the strategies of each node to evolve towards a better direction. Each node's current virtual radiative potential energy corresponds to a temporary state in the game field, but this state may not necessarily stabilize the overall system's action. This step, by solving a variational problem that makes the system's action tend towards a static state, essentially seeks the direction in which the system evolves towards a better equilibrium state. The potential gradient information between interacting nodes mimics a local negotiation mechanism; each node not only calculates the impact of its own policy change on the global objective but also receives similar impact information from its neighbors. Through the comprehensive processing of this gradient information, each node can calculate a potential adjustment vector, which indicates how its own virtual radiative potential energy should be adjusted to approach system equilibrium. This is a distributed, gradient-optimized, collaborative convergence process.

[0040] Step S500: Make a decision on the emission state of the node based on the potential energy adjustment vector. By mapping the potential energy vector to a point in the radiation parameter space that conforms to physical constraints, the emission spectrum of each node at the next moment is obtained.

[0041] Step S500 translates the abstract decision intention into concrete physical actions. The potential energy adjustment vector is a directional indicator existing in the mathematical space within the algorithm, while the radio transmitter can only operate within a space defined by physical parameters such as center frequency, bandwidth, modulation method, and transmit power. This step solves the problem from cooperative strategy to engineering implementation by mapping the potential energy vector to a point in the radiation parameter space that conforms to physical constraints. This mapping process requires interpreting the radiation intention implied by the potential energy vector. For example, its amplitude may correspond to the overall constraint on the transmitted energy, and its phase may correspond to the subtle requirements on the time-frequency structure of the signal. Among all hardware-featured combinations of transmit parameters, the step seeks the set of parameters that best reflects this intention and is most favorable to the current environment, thereby synthesizing the specific transmit spectrum shape of the node at the next moment.

[0042] Step S600: Perform closed-loop processing on the communication process according to the transmission spectrum pattern. By using the radiation state generated by the actual transmission as new environmental feedback data, iteratively update the historical background radiation data until the virtual radiation potential energy of the node no longer changes, and obtain a steady-state communication strategy that makes the network radiation pattern converge to the background.

[0043] Step S600 introduces a feedback loop, enabling the entire method to adapt to environmental changes and model errors. Communicating according to the emission spectrum pattern is an active exploration of the environment by the algorithm. The radiation state generated by the actual emission is superimposed on complex environmental background noise, forming a mixed signal that the receiving node can measure. By using the radiation state generated by the actual emission as new environmental feedback data, nodes can observe the effects of their actions in the real world. This feedback is fused with historical background radiation data and iteratively updated, driving the virtual radiation potential energy of the nodes to continuously adjust until there is no longer a significant driving adjustment trend between the overall network strategy and the environmental feedback. At this point, the network radiation pattern is considered to have converged to the background, resulting in a steady-state communication strategy that adapts to the dynamic environment. The steady-state communication strategy includes a set of radiation behavior rules continuously followed by each node, determined by the converged virtual radiation potential energy. These rules make the emission spectrum pattern of each node a deterministic function of its local environmental perception and data content, ultimately driving the overall network radiation characteristics to statistically align with the dynamic background noise.

[0044] Further, step S200 includes steps S210 to S230.

[0045] Step S210: Perform dynamic background feature extraction processing based on background radiation data, and obtain the dynamic change pattern of background radiation in the time-frequency dimension by performing spectral analysis on the instantaneous radiation power value sequence at each frequency point.

[0046] Step S220: Quantify the urgency and importance of the original information content. By parsing the protocol header information and content structure of the data packet, the communication urgency corresponding to the data unit is obtained.

[0047] Step S230: Based on the dynamic change pattern and communication urgency, nonlinear fusion processing is performed in conjunction with the local channel gain. By constructing a complex potential function with the channel state as the basis and embedding background dynamics and data urgency as modulation terms, the initial virtual radiation potential energy is obtained.

[0048] Specifically, step S210 first performs spectral analysis on the instantaneous radiated power value sequence at each frequency point to extract the dynamic change pattern of background radiation in the time-frequency dimension. This processing aims to identify the changing period, sudden patterns, and stable intervals of environmental electromagnetic noise from discrete power samples, thereby refining the irregular radiation data into a quantifiable characteristic description of environmental rhythm and uncertainty. This is the foundation for nodes to perceive and adapt to non-stationary electromagnetic environments. Next, step S220 processes the original information content by deeply analyzing the protocol header information (such as service type and time to live) and content structure (such as the semantics or data patterns of specific fields) of the data packets. From this, the communication urgency corresponding to the data unit is derived. This urgency is a quantitative indicator that integrates the priority specified by the protocol and the semantic importance of the application layer, ensuring that the algorithm can distinguish between critical alarms and regular data, and achieve differentiated resource adaptation. The formula for calculating the communication urgency is:

[0049] ;

[0050] In the formula, The higher the value, the more urgent the data unit needs to be processed. Content sensitivity factors are used to reflect the inherent importance or degree of abnormality of the data content itself. This is the protocol priority factor; This refers to the length of the data packet. The remaining valid time; Total allowable delay; , This is an adjustment coefficient used to adjust the weight of protocol priority and packet length factors on urgency. It is a very small constant used to prevent the denominator from being zero.

[0051] Step S230 nonlinearly fuses the dynamic change pattern and communication urgency obtained in the preceding steps with the local channel gain measured at the node. The core of this process is the construction of a complex potential function. This function uses the complex channel gain, which characterizes the physical link quality, as its basis. It embeds the dynamic threat change pattern representing the environment as a suppression term into the function's magnitude, couples the urgency representing service urgency as an enhancement term, and further modulates the phase angle of the function with their product. The innovation of this construction lies in creating a complex potential that simultaneously encodes "transmission intensity tendency" and "transmission phase / timing tendency." The amplitude component integrates channel and service requirements, while the phase component couples environmental dynamics with data urgency. This allows the algorithm to prioritize covert adjustments to the signal's phase (i.e., time-frequency structure) rather than conventionally increasing power when the environment is complex and volatile and the data is critical. This provides an initial state quantity at the mathematical abstraction level that reflects objective conditions and embeds covert intelligent communication decision-making guidance for subsequent cooperative game theory. The expression for the complex potential function is as follows:

[0052] ;

[0053] In the formula, This represents the initial virtual radiation potential energy. Local channel gain represents the channel state information from a node to its target receiver, including amplitude attenuation and phase rotation. This is a dynamic change mode; the larger the value, the faster and more unstable the environmental electromagnetic background changes over time. For the urgency of communication; As a background dynamics suppression factor, this term incorporates background dynamics into the potential energy in an exponentially decaying manner. As a factor that enhances urgency; This is the initial phase offset; As a dynamic-urgency coupling phase factor, this term will incorporate background dynamics. With communication urgency They are coupled in a product form to jointly modulate the phase of the potential energy; This represents the multiplication operation between the imaginary unit and the subsequent phase expression.

[0054] Further, step S300 includes steps S310 to S330.

[0055] Step S310: Calculate the potential energy distribution of network nodes based on the initial virtual radiation potential energy. By solving the potential energy interpolation function with node coordinates as the independent variable, obtain the potential energy distribution surface that describes the continuous change of the entire physical deployment area.

[0056] Step S320: Based on the potential energy distribution surface, the radiation interference mode is derived. By calculating the Laplace operator of the surface, the expected radiation interference gradient vector field reflecting the superposition of node potential energy at any position is obtained.

[0057] Step S330: Construct the global information flow divergence based on the expected radiation interference gradient vector field and the information transmission requirements of the nodes. By defining a functional with the gradient field divergence and the local information entropy change rate as the core, a continuous situation game field is obtained. The steady-state solution of the continuous situation game field corresponds to the optimal balance between the network radiation characteristics and the information flow in spatial distribution.

[0058] Specifically, step S310 first calculates the discrete initial virtual radiation potential energy of each node using a potential energy interpolation function with the node's physical coordinates as the independent variable, constructing a continuous potential energy distribution surface covering the entire deployment area. This surface mathematically represents the continuous spatial distribution of the network's "radiation intention," merging the previously isolated node states into a continuous field, providing a foundation for analyzing the spatial interactions between nodes from a global perspective. The potential energy interpolation function of the discrete node potential energy into a continuous spatial surface is expressed as:

[0059] ;

[0060] In the formula, Let be a continuous potential energy distribution surface function, representing the coordinates of the two-dimensional deployment region. The interpolated potential energy values ​​at the point form a continuous potential energy distribution surface; , These represent the x and y coordinates of the two-dimensional deployment area, respectively. The total number of nodes in the network; For nodes The initial virtual radiation potential energy (complex number) represents the intensity and tendency of the node's radiation intention; , They are nodes The known physical x-coordinate and y-coordinate; This is the interpolation kernel function, used to control the smooth expansion of the potential energy value as it decays with spatial distance; This is the scale parameter.

[0061] Step S320, based on this continuous surface, applies the Laplace operator for differentiation to derive the radiation interference mode. Physically, this involves calculating the curvature or divergence at each point on the surface, resulting in a predicted radiation interference gradient vector field. This vector field clearly reveals the expected flow trend and intensity change of radiation energy at any point in space due to the superposition of potential energies at all nodes, quantifying the potential interference effect of mutual reinforcement or cancellation of radiation between nodes. The differentiation formula is:

[0062] ;

[0063] In the formula, For coordinates The expected radiation interference gradient vector field value (scalar field) at the point, a positive value indicates that there is a net outflow (source) of radiation energy at that point, and a negative value indicates a net inflow (sink). The Laplace operator is used to calculate the local curvature or divergence of a scalar field at a point. It is a surface function for continuous potential energy distribution; , These represent the x and y coordinates of the two-dimensional deployment area, respectively. This is the symbol for partial differentials.

[0064] Step S330 combines the gradient vector field representing physical interference with the core task of the nodes—information transmission requirements. A continuous situational game field is constructed by defining a functional that correlates the gradient field divergence with the local information entropy change rate. Here, the gradient field divergence describes the "source" and "sink" of radiated energy in space, i.e., the aggregation or diffusion pattern of network radiation; while the information entropy change rate characterizes the efficiency of information transmission and the rate of uncertainty reduction. This functional correlates these two, meaning the optimization objective is set as finding a network state that achieves an optimal trade-off and balance between the spatial distribution pattern of radiated energy (concealment requirements) and the efficiency of information transmission (communication effectiveness). This continuous situational game field is a mathematical model describing the distributed strategy interaction of all nodes under this unified objective. Its steady-state solution corresponds to the global collaborative strategy that achieves the optimal balance between network radiation characteristics and information flow in spatial distribution. The continuous situational game field functional is expressed as:

[0065] ;

[0066] In the formula, For continuous state game field functionals; The entire physical deployment area of ​​the network; Represents the expected radiation interferometry gradient vector field value The divergence, whose squared term is used to penalize the violent accumulation or diffusion of radiant energy in space; For coordinates The expected radiative interference gradient vector field value at the location; It is a surface function for continuous potential energy distribution; Represents information entropy; Indicates time; The differential symbol; For the trade-off factor ( ), used to adjust the relative weights of the two objectives of radiation concealment and "communication effectiveness" in global optimization.

[0067] Further, step S400 includes steps S410 to S430.

[0068] Step S410: Calculate the local steady-state deviation of nodes based on the continuous situation game field. By calculating the first-order variation of each node with respect to the continuous situation game field under the current potential energy, the local deviation vector is obtained.

[0069] Step S420: Based on the local deviation vector, perform neighborhood gradient information interaction and synthesis. By nonlinearly coupling the local deviation vector of a node with the corresponding vector of a node in its communication neighborhood, the synthetic evolution driving force of each node is obtained.

[0070] Step S430: Solve the variational problem iteratively based on the synthetic evolution driving force. By performing iterative search in the virtual potential energy space in the opposite direction of the synthetic evolution driving force, with the goal of minimizing the change in the system action, the potential energy adjustment vector is obtained by convergence.

[0071] Specifically, step S410 starts from the continuous situation game field and calculates the first-order variation of each node in the global continuous situation game field under the current virtual radiation potential energy configuration to obtain its local deviation vector. This vector mathematically characterizes the degree and direction of the direct impact of a small change in the state of a single node on the global performance objective (i.e., the balance between radiation concealment and information flow efficiency), thus interpreting the macroscopic system optimization objective as a specific local adjustment pressure perceptible to each node. Step S420 then introduces a cooperative mechanism based on this local information. A node nonlinearly couples its own local deviation vector with the corresponding vectors of other nodes in its communication neighborhood using a grid. This nonlinear processing can retain and synthesize the differences in the intensity and direction of the adjustment needs of different nodes, generating a synthetic evolutionary driving force. This synthetic evolutionary driving force reflects both the degree of disruption to the system balance by the node itself and the constraints and pulls imposed on it by the states of neighboring nodes, thus transforming the local adjustment pressure into a cooperative evolutionary direction that considers both itself and its neighbors. The formula for calculating the synthetic evolutionary driving force is as follows:

[0072] ;

[0073] In the formula, For nodes The driving force of synthetic evolution; , For nodes and his neighbors The local deviation vector; It is a sign function that preserves the phase (direction) when applied to complex numbers. It is a nonlinear mapping function used to compress the magnitude of the deviation vector; For nodes The set of communication neighbor nodes is determined by the communication radius and link quality; For the index of neighboring nodes; The neighbor coupling strength coefficient; Represents the norm.

[0074] Step S430 utilizes this synthetic evolutionary driving force to iteratively search in the solution space constituted by the virtual radiation potential energy along the opposite direction of this force, executing a distributed gradient descent process. The goal is to minimize the total system action defined by the continuous situational game field. Through continuous iteration, the virtual radiation potential energy of all nodes is synchronously adjusted along the direction determined by their respective cooperative driving forces. Eventually, the network state will converge to an equilibrium point where all driving forces tend to zero. The corresponding potential energy adjustment vector at this point indicates the specific adjustments required to move from the current state to the optimal system equilibrium. The entire process simulates a distributed cooperative evolutionary mechanism that self-organizes and approximates the globally optimal strategy based on local gradient information interaction.

[0075] Further, step S500 includes steps S510 to S530.

[0076] Step S510: Decode the radiation intent based on the potential energy adjustment vector. By analyzing the amplitude and phase components of the vector into constraints on the transmit power spectral density and perturbation requirements on the signal modulation phase, the spectral masking constraints and signal structure constraints are obtained.

[0077] Step S520: Perform a feasible transmission parameter subspace search based on spectral masking constraints and signal structure constraints. In the parameter space consisting of center frequency, bandwidth, power spectrum shape, and modulation constellation diagram, solve for the parameter combination that satisfies all constraints and is closest to the statistical characteristics of the current background radiation data to obtain the optimal candidate transmission parameter set.

[0078] Step S530: Synthesize the transmission spectrum shape based on the optimal candidate transmission parameter set. By mapping the parameter set to a baseband signal expression with specific time-frequency energy distribution and phase continuity, the transmission spectrum shape is obtained.

[0079] Specifically, the core task of step S510 is to translate the abstract mathematical decision (potential energy adjustment vector) into executable physical layer constraints. The magnitude of this vector is analyzed as a constraint on the transmitted power spectral density, which determines the upper and lower limits of the energy distribution of the signal in different frequency bands, i.e., spectral masking constraints; its phase component is analyzed as a perturbation requirement on the signal modulation phase, which defines a specific phase jump or continuous change pattern introduced on the basic modulation format, i.e., signal structure constraints. This decoding process decomposes the global strategy intention obtained from co-evolution into specific specifications for the two dimensions of the transmitted signal's "energy" and "morphology". Under this specification, step S520 searches for feasible combinations of transmitted parameters in a high-dimensional search space composed of multi-dimensional parameters such as center frequency, bandwidth, power spectral shape, and modulation constellation diagram. The goal is to find a solution that must simultaneously satisfy all the constraints generated in step S510, and among all feasible solutions, the corresponding signal time-frequency statistical characteristics (such as higher-order moments, cyclostationary characteristics, etc.) are closest to the statistical characteristics of the current real-time background radiation data. This process is a constraint-satisfying problem with the optimization objective of mimicking the background, resulting in a set of optimal candidate transmission parameters. Step S530 then completes the generation from the parameter set to the final transmittable waveform, mapping the optimal candidate transmission parameter set into a time-domain expression with specific time-frequency energy distribution and phase continuity through transmission spectrum morphology synthesis. This expression not only encodes the parameters determined in step S520 but also ensures that the generated signal has the desired characteristics in the time and frequency domains, such as a specific spectral shape, constant envelope or low peak-to-average power ratio, and precisely controlled phase trajectory, thus ultimately obtaining a transmission spectrum morphology that satisfies both the concealment constraint (spectral and statistical characteristics closely resemble the background) and has effective communication capability (can be correctly demodulated). The transmission spectrum morphology synthesis formula is expressed as:

[0080] ;

[0081] In the formula, This is the time-domain expression of the synthesized baseband transmitted signal (time-domain waveform), i.e., the transmitted spectrum shape. This is a time-varying amplitude term used to control the instantaneous power of the signal in order to achieve a specific time-domain envelope or match the time-varying background radiation intensity. For pulse shaping function, parameters For symbol period, Roll-off factor; For fine frequency offset, it is used to precisely embed signal energy into specific grooves or weak energy regions of the background noise spectrum; The information modulation phase term is composed of the modulation symbol sequence to be transmitted. and modulation index Together they form; This is a phase perturbation term introduced artificially. For effective phase perturbation bandwidth; Indicates time; This indicates the multiplication operation between the imaginary unit and the subsequent phase expression; It represents pi (π).

[0082] Further, step S600 includes steps S610 to S630.

[0083] Step S610: Observe the actual radiation spatial characteristics based on the transmitted spectrum pattern. By measuring and separating the statistical moments of the mixed radiation field formed by the current transmitted signal superimposed with background noise at the receiving node, the radiation disturbance characteristics that reflect the actual generation after a complete communication interaction are obtained.

[0084] Step S620: Dynamically correct the background radiation data based on the radiation disturbance characteristics. By fusing the disturbance characteristics with historical background radiation data, a time-varying environmental radiation state estimation model is constructed to obtain the updated background radiation data.

[0085] Step S630: Perform global equilibrium convergence determination based on the updated background radiation data and the virtual radiation potential energy of the current node. Calculate the norm change rate of the potential energy adjustment vector of all nodes in the network. When the norm change rate is lower than a preset threshold, determine that the system has reached steady state and obtain the steady-state communication strategy.

[0086] Specifically, step S610 is responsible for evaluating the actual effect of a communication action. After the node transmits according to the transmission spectrum pattern, the receiving node obtains the mixed radiation field through high-precision measurement, and uses high-order statistical moment analysis to separate and quantify the radiation disturbance characteristics actually introduced by this network communication action from the mixed signal. This step directly obtains the observable effect of the signal after real complex propagation and superposition, providing the algorithm with real-world feedback data on the action effect. Step S620 uses this feedback for learning and cognitive update, fusing the newly observed radiation disturbance characteristics with historical background radiation data, and constructing a time-varying environmental radiation state estimation model to dynamically correct and update the understanding of the environmental background, thereby obtaining more accurate background radiation data that better reflects the latest situation. This enables the system to track the non-stationary evolution process of the environment itself. Preferably, the environmental radiation state estimation model is based on the Bayesian filtering framework, and achieves dynamic tracking and state update of non-stationary background radiation by adaptively fusing the newly observed disturbance characteristics with historical estimates, as expressed in the following expression:

[0087] ;

[0088] In the formula, In time Estimated frequency points The background radiation power spectral density, i.e., the updated background radiation data; In time Historical background radiation power spectral density estimation; In time The total power spectral density of the mixed radiation field measured by the receiving node includes the raw observations of the network's own transmitted signals and the real background noise; In time The frequency domain representation of the extracted radiative perturbation feature vectors; It is a time-varying decay factor; Contribution ratio coefficient to disturbance; The feature normalization factor; Represents the norm.

[0089] Step S630 performs a macro-level balance determination based on the updated environmental perception and the current state of the system. This is achieved by calculating the norm change rate of the potential adjustment vectors of all nodes in the network; this indicator quantifies the overall policy adjustment activity of the network. When this change rate falls below a preset threshold characterizing system stability, it indicates that further iterative adjustments can no longer significantly improve global performance, and a dynamic balance has been reached between the behavioral policies of each node and the environmental state. At this point, the system determines that it has acquired and entered a steady-state communication strategy. This strategy signifies that the network has adaptively learned how to coordinate the behavior of each node in the current dynamic environment so that its collective radiation pattern continuously converges to the background.

[0090] Further, step S610 includes steps S611 to S613.

[0091] Step S611: Based on the known spatial relationship between the transmitted spectrum and the network nodes, perform mixed radiation field sampling processing at the receiving node. By synchronously measuring the received signal in the time-frequency two-dimensional space, obtain the original observation sample set containing its own transmitted signal, the transmitted signals of neighboring nodes, and background noise.

[0092] Step S612: Perform radiation contribution deconvolution processing based on the original observation sample set. By constructing and solving a system of linear equations with the node spectrum shape as the basis function and the spatial path loss as the coefficient, the signal component intensity of each signal component at the receiving point is obtained.

[0093] Step S613: Based on the signal component intensity and the original observation sample set, construct the perturbation feature statistics and obtain the radiation perturbation feature vector by calculating the higher-order cross-cumulative quantity between the signal component intensity and the background noise.

[0094] Specifically, in step S611, based on the known transmission spectrum pattern and the spatial relationship between network nodes, the receiving node synchronously measures the received mixed signal in a two-dimensional space of time and frequency domains. This synchronous measurement implies the joint capture of the signal's time-varying characteristics and spectral components, resulting in a raw set of observation samples. Mathematically, this set is a multidimensional array containing the echo of the receiving node's own transmitted signal, versions of the transmitted signals from all neighboring nodes after attenuation and delay along different spatial paths, and the complete information of the linear superposition of environmental background noise. The goal of step S612 is to decouple the independent contribution of each node from the mixed observations, a typical blind source separation or deconvolution problem. The technique involves constructing and solving a system of linear equations: using each known transmission spectrum pattern as a basis function, and the path loss of the signal propagating in space (related to distance) as the coefficients to be solved. By solving this system of equations, the estimated signal component strength of each signal component at the receiving point can be obtained. This process essentially uses known emission "fingerprints" (spectral morphology) and geometric relationships to inversely deduce the actual contribution intensity of each emission source at the observation point, thereby decomposing the mixed field into a series of independently analyzable signal components. This step does not directly measure the total power, but rather quantifies the individual impact of each controllable radiation source in the network through calculation. The linear equations describe the effect at each observation frequency. The system of equations above describes how the received mixed signal is composed of a linear superposition of the signals transmitted by all known nodes. Equations (corresponding to) (each frequency point), in the following format:

[0095] ;

[0096] In the formula, In the first frequency points Above, the complex signal value measured by the receiving node; This represents the total number of transmitting nodes to be separated in the network, including the target node and its neighbors; For the first Spatial path loss factor of each node. For the first The known transmission spectrum of each node at frequency points The value on; For the first The signal component strength of each node represents the node's signal strength. The equivalent amplitude and initial phase of the signal when it arrives at the receiving point; In the first In this embodiment, the background noise and model error at each frequency point are assumed to be random variables with a mean of zero. This represents the total number of observed frequency points; For the index of the node; This is the index of the frequency point.

[0097] In step S613, higher-order cross-cumulants are mathematical tools capable of characterizing higher-order statistical dependencies between random variables. They are highly sensitive to characteristics such as the non-Gaussianity and nonlinear phase coupling of signals. In the scenario of this invention, simple power measurements cannot distinguish between accidental energy fluctuations and intentional communication signals, while calculating higher-order cross-cumulants can capture subtle but identifiable statistical distribution changes caused by deterministic communication signals (even with low power) injected into background noise. The resulting radiated perturbation feature vector is a more robust and profound mathematical description of the statistical traces left by the current network communication behavior on the local electromagnetic environment, providing a more refined and reliable input for subsequent environmental model updates than simple intensity values.

[0098] Example 2:

[0099] like Figure 2 As shown, this embodiment provides a radiation control network node cooperative communication system, the system including:

[0100] The acquisition module 901 is used to acquire background radiation data in the target area and the original information content of the data to be transmitted by each node.

[0101] The fusion module 902 is used to fuse the local channel gain of each node based on the background radiation data and the original information content. By constructing a scalar function coupled with the instantaneous communication needs of the node and the environmental background, the independent initial virtual radiation potential of each network node is obtained.

[0102] Module 903 is used to establish the coupling relationship of all nodes based on the initial virtual radiation potential energy. By defining a functional that maps the overall radiation characteristics of the network to the communication information flow as a common action, a continuous situational game field describing the interaction of nodes is obtained.

[0103] Evolution module 904 is used to perform collaborative evolution of the virtual radiation potential energy of each node according to the continuous situation game field. It obtains the potential energy adjustment vector by solving the variational problem that makes the system action tend to static and by exchanging the potential energy gradient information between nodes.

[0104] The decision module 905 is used to make decisions on the emission state of the node based on the potential energy adjustment vector. By mapping the potential energy vector to a point in the radiation parameter space that conforms to physical constraints, the emission spectrum of each node at the next moment is obtained.

[0105] The output module 906 is used to perform closed-loop processing of the communication process based on the transmission spectrum pattern. By using the radiation state generated by the actual transmission as new environmental feedback data, the historical background radiation data is iteratively updated until the virtual radiation potential energy of the node no longer changes, thus obtaining a steady-state communication strategy that makes the network radiation pattern converge to the background.

[0106] In one specific embodiment of this application, the fusion module 902 includes:

[0107] The first fusion unit is used to perform dynamic background feature extraction processing based on background radiation data. By performing spectral analysis on the instantaneous radiation power value sequence at each frequency point, the dynamic change pattern of background radiation in the time-frequency dimension is obtained.

[0108] The second fusion unit is used to quantify the urgency and importance of the original information content. By parsing the protocol header information and content structure of the data packet, the communication urgency corresponding to the data unit is obtained.

[0109] The third fusion unit is used to perform nonlinear fusion processing based on the dynamic change pattern and communication urgency, combined with the local channel gain. It obtains the initial virtual radiation potential energy by constructing a complex potential function with the channel state as the basis and embedding background dynamics and data urgency as modulation terms.

[0110] In one specific embodiment of this application, the construction module 903 includes:

[0111] The first building unit is used to calculate the potential energy distribution of network nodes based on the initial virtual radiation potential energy. By solving the potential energy interpolation function with node coordinates as independent variables, a potential energy distribution surface describing the continuous change of the entire physical deployment area is obtained.

[0112] The second building unit is used to derive the radiation interference mode based on the potential energy distribution surface. By calculating the Laplacian operator of the surface, the expected radiation interference gradient vector field reflecting the superposition of node potential energy at any position is obtained.

[0113] The third building unit is used to construct the global information flow divergence based on the expected radiation interference gradient vector field and the information transmission requirements of the nodes. By defining a functional with the gradient field divergence and the local information entropy change rate as the core, a continuous situation game field is obtained. The steady-state solution of the continuous situation game field corresponds to the optimal balance between the network radiation characteristics and the information flow in spatial distribution.

[0114] Example 3:

[0115] Corresponding to the above method embodiments, this embodiment also provides a radiation control network node cooperative communication device. The radiation control network node cooperative communication device described below and the radiation control network node cooperative communication method described above can be referred to each other.

[0116] Figure 3 This is a block diagram illustrating a radiation control network node cooperative communication device 800 according to an exemplary embodiment. Figure 3 As shown, the radiation control network node cooperative communication device 800 may include: a processor 801 and a memory 802. The radiation control network node cooperative communication device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0117] The processor 801 controls the overall operation of the radiation control network node cooperative communication device 800 to complete all or part of the steps in the radiation control network node cooperative communication method described above. The memory 802 stores various types of data to support the operation of the radiation control network node cooperative communication device 800. This data may include, for example, instructions for any application or method operating on the radiation control network node cooperative communication device 800, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using 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 storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the radiation control network node collaborative communication device 800 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0118] In an exemplary embodiment, a radiation control network node cooperative communication device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the aforementioned radiation control network node cooperative communication method.

[0119] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the radiation control network node cooperative communication method described above. For example, the computer-readable storage medium may be the memory 802 including program instructions described above, which may be executed by a processor 801 of a radiation control network node cooperative communication device 800 to complete the radiation control network node cooperative communication method described above.

[0120] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for cooperative communication among nodes in a radiation control network, characterized in that, include: Acquire background radiation data in the target area and the raw information content of the data to be transmitted by each node; Based on the background radiation data and the original information content, the local channel gain of each node is fused, and by constructing a scalar function coupled with the instantaneous communication needs of the node and the environmental background, the independent initial virtual radiation potential of each network node is obtained. Based on the initial virtual radiation potential energy, the coupling relationship of all nodes is established. By defining a functional that maps the overall radiation characteristics of the network to the communication information flow as a common action, a continuous situational game field describing the interaction of nodes is obtained. Based on the continuous situational game field, the virtual radiation potential energy of each node is co-evolved. By solving the variational problem that makes the system action tend to be static and interacting with the potential energy gradient information between nodes, the potential energy adjustment vector is obtained. The emission state of the node is decided based on the potential energy adjustment vector. By mapping the potential energy vector to a point in the radiation parameter space that conforms to physical constraints, the emission spectrum of each node at the next moment is obtained. The communication process is closed-loop processed according to the transmitted spectrum pattern. By using the radiation state generated by the actual transmission as new environmental feedback data, the historical background radiation data is iteratively updated until the virtual radiation potential energy of the node no longer changes, thus obtaining a steady-state communication strategy that makes the network radiation pattern converge to the background.

2. The radiation control network node cooperative communication method according to claim 1, characterized in that, Based on the background radiation data and the original information content, the local channel gain of each node is fused. By constructing a scalar function coupled to the instantaneous communication needs of the node and the environmental background, the independent initial virtual radiation potential of each network node is obtained, including: Based on the background radiation data, dynamic background feature extraction processing is performed, and by performing spectral analysis on the instantaneous radiation power value sequence at each frequency point, the dynamic change pattern of background radiation in the time-frequency dimension is obtained. The urgency and importance of the original information are quantified by parsing the protocol header information and content structure of the data packet to obtain the communication urgency corresponding to the data unit. Based on the dynamic change pattern and the communication urgency, nonlinear fusion processing is performed in conjunction with the local channel gain. By constructing a complex potential function with the channel state as the basis and embedding background dynamics and data urgency as modulation terms, the initial virtual radiation potential energy is obtained.

3. The radiation control network node cooperative communication method according to claim 1, characterized in that, Based on the initial virtual radiation potential energy, coupling relationships are established among all nodes. By defining a functional that maps the overall radiation characteristics of the network to the communication information flow as a common action, a continuous situational game field describing node interactions is obtained, including: The potential energy distribution of network nodes is calculated based on the initial virtual radiation potential energy. By solving the potential energy interpolation function with node coordinates as independent variables, a potential energy distribution surface describing the continuous change of the entire physical deployment area is obtained. The radiation interference mode is derived based on the potential energy distribution surface. By calculating the Laplace operator of the surface, the expected radiation interference gradient vector field reflecting the superposition of node potential energy at any position is obtained. Based on the expected radiation interference gradient vector field and the information transmission requirements of the nodes, the global information flow divergence is constructed. By defining a functional with the gradient field divergence and the local information entropy change rate as the core, the continuous situation game field is obtained. The steady-state solution of the continuous situation game field corresponds to the optimal balance between network radiation characteristics and information flow in spatial distribution.

4. The radiation control network node cooperative communication method according to claim 1, characterized in that, Based on the continuous situational game field, the virtual radiation potential energy of each node is co-evolved. By solving a variational problem that makes the system action tend to static, and by interacting with the potential energy gradient information between nodes, a potential energy adjustment vector is obtained, including: The local steady-state deviation of nodes is calculated based on the continuous situation game field. The local deviation vector is obtained by calculating the first-order variation of each node with respect to the continuous situation game field under the current potential energy. Based on the local deviation vector, neighborhood gradient information is exchanged and synthesized. By nonlinearly coupling the local deviation vector of a node with the corresponding vector of a node in its communication neighborhood, the synthetic evolution driving force of each node is obtained. The variational problem is solved iteratively based on the said synthetic evolution driving force. By performing an iterative search in the virtual potential energy space in the opposite direction of the said synthetic evolution driving force, with the goal of minimizing the change in the system action, the potential energy adjustment vector is obtained by convergence.

5. The radiation control network node cooperative communication method according to claim 1, characterized in that, The emission state of a node is determined based on the potential energy adjustment vector. By mapping the potential energy vector to a point in a radiation parameter space that conforms to physical constraints, the emission spectrum of each node at the next time step is obtained, including: Radiation intent decoding is performed based on the potential energy adjustment vector. By resolving the amplitude and phase components of the vector into constraints on the transmit power spectral density and perturbation requirements on the signal modulation phase, spectral masking constraints and signal structure constraints are obtained. Based on the aforementioned spectral masking constraints and signal structure constraints, a feasible transmission parameter subspace search is performed. By solving for the parameter combination that satisfies all constraints and is closest to the statistical characteristics of the current background radiation data in the parameter space consisting of center frequency, bandwidth, power spectrum shape, and modulation constellation diagram, the optimal candidate transmission parameter set is obtained. The transmission spectrum shape is synthesized based on the optimal candidate transmission parameter set. The transmission spectrum shape is obtained by mapping the parameter set to a baseband signal expression with a specific time-frequency energy distribution and phase continuity.

6. The radiation control network node cooperative communication method according to claim 1, characterized in that, The communication process is closed-loop processed based on the transmitted spectrum pattern. By using the radiation state generated by the actual transmission as new environmental feedback data, historical background radiation data is iteratively updated until the virtual radiation potential energy of the nodes no longer changes. This yields a steady-state communication strategy that causes the network radiation pattern to converge to the background, including: Based on the transmitted spectrum pattern, actual radiation spatial characteristics are observed. By measuring and separating the statistical moments of the mixed radiation field formed by the current transmitted signal superimposed with background noise at the receiving node, the radiation disturbance characteristics that reflect the actual generation after a complete communication interaction are obtained. The background radiation data is dynamically corrected based on the radiation disturbance characteristics. By fusing the disturbance characteristics with historical background radiation data, a time-varying environmental radiation state estimation model is constructed to obtain the updated background radiation data. The global equilibrium convergence is determined based on the updated background radiation data and the virtual radiation potential energy of the current node. The norm change rate of the potential energy adjustment vector of all nodes in the network is calculated. When the norm change rate is lower than a preset threshold, the system is determined to have reached a steady state, and a steady-state communication strategy is obtained.

7. The radiation control network node cooperative communication method according to claim 6, characterized in that, Based on the transmitted spectrum pattern, actual radiation spatial characteristics are observed. By measuring and separating the statistical moments of the mixed radiation field formed by the current transmitted signal superimposed with background noise at the receiving node, the radiation disturbance characteristics reflecting the actual generation after a complete communication interaction are obtained, including: Based on the known spatial relationship between the transmitted spectrum pattern and the network nodes, a mixed radiation field sampling process is performed at the receiving node. By synchronously measuring the received signal in the time-frequency two-dimensional space, an original set of observation samples containing its own transmitted signal, the transmitted signals of neighboring nodes, and background noise is obtained. The radiation contribution deconvolution process is performed on the original set of observation samples. A system of linear equations with the node spectral shape as the basis function and the spatial path loss as the coefficient is constructed and solved to obtain the signal component intensity of each signal component at the receiving point. Based on the signal component intensity and the original observation sample set, perturbation feature statistics are constructed. By calculating the higher-order cross-cumulative quantity between the signal component intensity and the background noise, the radiation perturbation feature vector is obtained.

8. A radiation control network node cooperative communication system, characterized in that, include: The acquisition module is used to acquire background radiation data in the target area and the original information content of the data to be transmitted by each node; The fusion module is used to fuse the local channel gain of each node based on the background radiation data and the original information content. By constructing a scalar function coupled with the instantaneous communication needs of the node and the environmental background, the independent initial virtual radiation potential of each network node is obtained. The module is used to establish coupling relationships between all nodes based on the initial virtual radiation potential energy. By defining a functional that maps the overall radiation characteristics of the network to the communication information flow as a common action, a continuous situational game field describing node interactions is obtained. The evolution module is used to perform collaborative evolution of the virtual radiation potential energy of each node according to the continuous situation game field. It obtains the potential energy adjustment vector by solving the variational problem that makes the system action tend to static and by exchanging the potential energy gradient information between nodes. The decision module is used to make decisions on the emission state of the node based on the potential energy adjustment vector. By mapping the potential energy vector to a point in the radiation parameter space that conforms to physical constraints, the emission spectrum of each node at the next moment is obtained. The output module is used to perform closed-loop processing of the communication process based on the transmitted spectrum pattern. By using the radiation state generated by the actual transmission as new environmental feedback data, the historical background radiation data is iteratively updated until the virtual radiation potential energy of the node no longer changes, thus obtaining a steady-state communication strategy that makes the network radiation pattern converge to the background.

9. The radiation control network node cooperative communication system according to claim 8, characterized in that, The fusion module includes: The first fusion unit is used to perform dynamic background feature extraction processing based on the background radiation data, and to obtain the dynamic change pattern of background radiation in the time-frequency dimension by performing spectral analysis on the instantaneous radiation power value sequence of each frequency point. The second fusion unit is used to quantify the urgency and importance of the original information content, and obtain the communication urgency corresponding to the data unit by parsing the protocol header information and content structure of the data packet. The third fusion unit is used to perform nonlinear fusion processing based on the dynamic change mode and the communication urgency, combined with the local channel gain, to obtain the initial virtual radiation potential energy by constructing a complex potential function with the channel state as the basis and embedding background dynamics and data urgency as modulation terms.

10. The radiation control network node cooperative communication system according to claim 8, characterized in that, The building module includes: The first construction unit is used to calculate the potential energy distribution of network nodes based on the initial virtual radiation potential energy, and obtain a potential energy distribution surface that describes the continuous change of the entire physical deployment area by solving the potential energy interpolation function with node coordinates as independent variables. The second construction unit is used to perform radiation interference mode derivation processing based on the potential energy distribution surface. By calculating the Laplacian operator of the surface, the expected radiation interference gradient vector field reflecting the superposition of node potential energy at any position is obtained. The third construction unit is used to construct the global information flow divergence based on the expected radiation interference gradient vector field and the information transmission requirements of the nodes. By defining a functional with the gradient field divergence and the local information entropy change rate as the core, the continuous situation game field is obtained. The steady-state solution of the continuous situation game field corresponds to the optimal balance between the network radiation characteristics and the information flow in spatial distribution.

Images