Civil air defense maneuvering command communication relay system based on adaptive networking intelligent perception

Abstract

The invention discloses a civil air defense maneuvering command communication relay system based on adaptive networking intelligent perception, which comprises a dynamic networking module used for generating a layered adaptive network topology, an intelligent perception module used for collecting environmental parameters and generating dynamic clusters, a route optimization module used for solving an optimal path by adopting a mixed integer programming model, and a routing optimization module used for carrying out routing optimization on the optimal path. And the reward function and the fault-tolerant module are updated through a Q-learning algorithm, the multipath survival probability is calculated, and the spectrum is reconstructed based on the compressed sensing model. Therefore, the adaptive topology can be generated through hierarchical dynamic networking and real-time environment perception, the communication path is optimized by combining mixed integer programming and the Q-learning algorithm, the throughput, the time delay and the energy consumption are balanced, and the communication reliability and the command efficiency in a complex environment are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and specifically refers to a civil air defense mobile command communication relay system based on adaptive networking and intelligent perception. Background Art

[0002] With the rapid development of information technology, the application requirements of civil air defense mobile command communication systems in emergency response, disaster relief, and complex environments have become increasingly prominent. Currently, mobile command communication systems need to achieve efficient and stable information transmission in dynamic environments to ensure the real-time and reliability of command and dispatch. In the prior art, by introducing mechanisms such as dynamic networking, environmental perception, and intelligent routing, the flexibility and adaptability of communication networks have been improved to a certain extent. For example, the application of hierarchical network topologies, link quality assessment, and multipath transmission technologies provides basic support for mobile communication systems. However, in the face of complex scenarios with high dynamics and multiple interferences, how to further improve the real-time reconstruction ability of network topologies, optimize resource allocation efficiency, and enhance the anti-destruction and fault tolerance of systems remains an important direction for technological development. Summary of the Invention

[0003] The present invention aims to solve at least to some extent the technical problems in the above-mentioned technology.

[0004] To this end, the present invention discloses a civil air defense mobile command communication relay system based on adaptive networking and intelligent perception, including:

[0005] A dynamic networking module for generating a hierarchical adaptive network topology G(t) = <N(t), L(t), W(t)>, where:

[0006] N(t) is the set of nodes at time t, including mobile command vehicles, UAV relays, and fixed base stations with three-dimensional coordinates n i ∈R 3 ;

[0007] L(t) is the set of dynamic links, satisfying

[0008] W(t) is the link weight matrix, and the weight calculation satisfies and α, β, γ are dynamically adjusted through Kalman filtering;

[0009] An intelligent perception module for collecting environmental parameters ψ(t) = {EMI(t), PathLoss(t), Mobility(t), ThreatLevel(t)} and generating dynamic clusters;

[0010] A routing optimization module using a mixed integer programming model min∑ (i,j)∈L W ij X ijSolve the optimal path and update the reward function through the Q-learning algorithm

[0011] Fault-tolerant module, calculate the multipath survival probability And based on the compressive sensing model Reconstruct the spectrum.

[0012] According to the air defense mobile command communication relay system based on adaptive networking and intelligent perception disclosed in the present invention, it can generate an adaptive topology through hierarchical dynamic networking and real-time environment perception, optimize the communication path by combining mixed integer programming and the Q-learning algorithm, and balance throughput, delay and energy consumption. The calculation of multipath survival probability and compressive sensing spectrum reconstruction enhance the fault tolerance ability, and significantly improve the communication reliability and command efficiency in complex environments.

[0013] In addition, the air defense mobile command communication relay system based on adaptive networking and intelligent perception disclosed in the present invention may also have the following additional technical features:

[0014] In an embodiment of the present invention, the dynamic clustering module executes a cluster head election algorithm, and the cluster head probability is: Where CQI i is the channel quality indication of node i, is the remaining energy.

[0015] In an embodiment of the present invention, the electromagnetic interference detection of the environmental parameter ψ(t) satisfies: And the dynamic path loss model is: Where η is the environmental attenuation factor, v ij is the relative speed of nodes i, j.

[0016] In an embodiment of the present invention, the bandwidth constraint of the routing optimization module satisfies: And the node degree constraint is ∑ j X ij ≤Degree max where X ij ∈{0,1} is the link activation variable.

[0017] In an embodiment of the present invention, the multipath redundant transmission of the fault-tolerant module adopts a tensor decomposition model:

[0018] In an embodiment of the present invention, the intelligent perception module integrates an LSTM-GAN joint prediction model: Where ∈ GAN is the adversarial generation correction term, which is used to predict the network state at the future Δt moment.

[0019] In one embodiment of the present invention, the relative speed in the dynamic path loss model where θ ij (t) is the included angle between the moving directions of nodes i and j.

[0020] In one embodiment of the present invention, in the Q-learning algorithm of the routing optimization module, the parameters λ1, λ2, and λ3 are dynamically adjusted by a fuzzy logic controller to satisfy: where μ k is the membership function of the network state NetState.

[0021] In one embodiment of the present invention, the rank R of the tensor decomposition model is determined by the singular value threshold method: R = argmax r (σ r ≥δσ1), where σ r is the r-th singular value, and δ ∈ (0, 1) is a preset threshold.

[0022] In one embodiment of the present invention, the topology reconstruction time of the dynamic networking module is less than 50 ms.

[0023] The additional content and advantages of the present invention will be given in the following description, or can be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The technical solutions and beneficial effects of the present invention will become obvious and easy to understand from the following content in conjunction with the drawings, where:

[0025] Figure 1 is the system framework diagram of the civil air defense mobile command communication relay system based on adaptive networking intelligent perception of the present invention;

[0026] Figure 2 is the core working flow diagram of the civil air defense mobile command communication relay system based on adaptive networking intelligent perception of the present invention;

[0027] Figure 3 is the module interaction and data flow diagram of the civil air defense mobile command communication relay system based on adaptive networking intelligent perception of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0029] The civil air defense mobile command communication relay system based on adaptive networking and intelligent perception disclosed by the present invention will be described below with reference to the accompanying drawings.

[0030] As Figure 1 , Figure 2 and Figure 3 shown, a civil air defense mobile command communication relay system based on adaptive networking and intelligent perception includes:

[0031] A dynamic networking module for generating a hierarchical adaptive network topology G(t) = <N(t), L(t), W(t)>, where:

[0032] N(t) is the node set at time t, including a mobile command vehicle, a drone relay, and a fixed base station with three-dimensional coordinates n i ∈R 3 ;

[0033] L(t) is the set of dynamic links, satisfying

[0034] W(t) is the link weight matrix, and the weight calculation satisfies and α, β, γ are dynamically adjusted through Kalman filtering;

[0035] An intelligent perception module for collecting environmental parameters ψ(t) = {EMI(t), PathLoss(t), Mobility(t), ThreatLevel(t)} and generating dynamic clustering;

[0036] A routing optimization module that uses a mixed integer programming model min∑ (i,j)∈L W ij X ij to solve the optimal path and update the reward function through the Q-learning algorithm

[0037] A fault tolerance module that calculates the multipath survival probability and reconstructs the spectrum based on the compressive sensing model ;

[0038] In addition, as a possibility, the dynamic clustering module executes a cluster head election algorithm, and the cluster head probability is: where CQI i is the channel quality indication of node i, is the remaining energy.

[0039] As a possibility, the electromagnetic interference detection of the environmental parameters ψ(t) satisfies: and the dynamic path loss model is: where η is the environmental attenuation factor, and v ij is the relative velocity of nodes i and j.

[0040] As a possibility, the bandwidth constraint of the routing optimization module is satisfied as: and the node degree constraint is ∑ j X ij ≤Degree max , where X ij ∈{0,1} is the link activation variable.

[0041] As a possibility, the multipath redundant transmission of the fault tolerance module adopts a tensor decomposition model:

[0042] As a possibility, the intelligent perception module integrates an LSTM-GAN joint prediction model: where ∈ GAN is the adversarial generation correction term for predicting the network state at the future time Δt.

[0043] As a possibility, in the dynamic path loss model, the relative velocity where θ ij (t) is the included angle of the movement directions of nodes i and j.

[0044] As a possibility, in the Q-learning algorithm of the routing optimization module, the parameters λ1, λ2, and λ3 are dynamically adjusted by a fuzzy logic controller to satisfy: where μ k is the membership function of the network state NetS tate.

[0045] As a possibility, the rank R of the tensor decomposition model is determined by the singular value threshold method: R = argmax r (σ r ≥δσ1), where σ r is the r-th singular value, and δ ∈(0,1) is the preset threshold.

[0046] As a possibility, the topology reconstruction time of the dynamic networking module is less than 50 ms.

[0047] Specifically, when the mobile command vehicle (carrying an on-vehicle terminal), the UAV relay group (equipped with low-altitude communication nodes), and the fixed base station (equipped with a solar power supply module) temporarily deployed in the disaster area enter the disaster area, the dynamic networking module collects the three-dimensional coordinates of each node in real time (such as the coordinates of the command vehicle (x1, y1, z1), the coordinates of the UAV (x2, y2, h), where h is the flight altitude), and constructs the initial node set N(t).

[0048] Through the link quality function Dynamically evaluate the links between nodes:

[0049] Calculate the Euclidean distance between nodes, combined with the real-time signal-to-noise ratio SNR ij (Calculated by received signal strength) and the remaining energy of node j Generate a dynamic link set L(t).

[0050] The link weight matrix W(t) is based on And α, β, γ are dynamically adjusted by Kalman filtering. For example, when the electromagnetic interference in the disaster area increases, increase α to preferentially select high-reliability links.

[0051] Collect environmental parameters ψ(t) = {EMI(t), PathLoss(t), Mobility(t), ThreatLevel(t)}:

[0052] The electromagnetic interference EMI(t) detects the total intensity of interference signals from various electronic devices in the disaster area;

[0053] The path loss adopts the model Where the relative speed of the nodes The environmental attenuation factor η is set according to the building density in the disaster area (e.g., η = 2.5 in the rubble area).

[0054] Based on the cluster head election algorithm Select nodes with high remaining energy and good channel quality (such as fixed base stations) as cluster heads to form a hierarchical network structure of "command vehicle - UAV cluster - fixed base station cluster" to reduce the energy consumption of multi-hop transmission.

[0055] When the command vehicle transmits rescue data to the rear command post, the routing optimization module aims to minimize the weight sum min∑ (i,j)∈L W ij X ij Subject to bandwidth constraints And the node degree constraint ∑ j X ij ≤Degree max , and solve the initial optimal path through mixed integer programming (such as command vehicle → UAV A → fixed base station → command post).

[0056] At the same time, the Q-learning algorithm dynamically adjusts the reward function parameters λ1, λ2, λ3 according to the real-time network state:

[0057] When the data traffic in the disaster area suddenly increases, the fuzzy logic controller increases λ1 (throughput weight) and preferentially selects high-bandwidth links. When the energy of the UAV is lower than the threshold, increase λ3 (energy consumption weight) to avoid excessive consumption of the UAV's power.

[0058] If the link of UAV A is interrupted due to a battery failure, the fault-tolerant module calculates the multipath survival probability Activate the backup path (command vehicle → UAV B → temporary relay node → command post). Based on the compressive sensing model Reconstruct the spectrum of the interfered frequency band to restore the signal transmission of the interrupted link and ensure data is not lost.

[0059] In summary, according to the civil air defense mobile command communication relay system based on adaptive networking and intelligent perception disclosed in the present invention, it can generate an adaptive topology through hierarchical dynamic networking and real-time environment perception, optimize the communication path by combining the mixed integer programming and Q-learning algorithms, and balance throughput, latency, and energy consumption. The calculation of the multipath survival probability and the compressive sensing spectrum reconstruction enhance the fault tolerance ability, significantly improving the communication reliability and command efficiency in complex environments.

[0060] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A civil air defense mobile command communication relay system based on adaptive networking intelligent perception, characterized in that, including: a dynamic networking module for generating a hierarchical adaptive network topology G(t) = <N(t), L(t), W(t)>, where: N(t) is the set of nodes at time t, including the three-dimensional coordinates n i ∈R 3 of the mobile command vehicle, the UAV relay, and the fixed base station; L(t) is a set of dynamic links that satisfy $W(t)$ is the link weight matrix, and the weight calculation satisfies and $\alpha$, $\beta$, $\gamma$ are dynamically adjusted through Kalman filtering; an intelligent sensing module for collecting environmental parameters ψ(t) = {EMI(t), PathLoss(t), Mobility(t), ThreatLevel(t)} and generating dynamic clusters; The routing optimization module uses a mixed-integer programming model min∑ (i,j)∈L W ij X ij to solve the optimal path and update the reward function through the Q-learning algorithm Fault-tolerant module, calculating the multipath survival probability and based on the compressive sensing model reconstruct the spectrum.

2. The civil air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 1, characterized in that, The dynamic clustering module executes a cluster head election algorithm, and the cluster head probability is: where CQI i is the channel quality indication of node i, is the remaining energy.

3. The civil air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 2, characterized in that, The electromagnetic interference detection of the environmental parameter ψ(t) satisfies: And the dynamic path loss model is: Where η is the environmental attenuation factor, and v ij is the relative velocity of nodes i and j.

4. The civil air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 1, wherein, The bandwidth constraint of the described routing optimization module is satisfied as follows: And the node degree constraint is ∑ j X ij ≤Degree max , where X ij ∈{0,1} is the link activation variable.

5. The civil air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 1, wherein, The multipath redundant transmission of the fault tolerance module adopts a tensor decomposition model:

6. The air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 1, characterized in that The intelligent perception module integrates an LSTM-GAN joint prediction model: where ∈ GAN is an adversarial generation correction term for predicting the network state at a future time of Δt.

7. The air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 3, characterized in that The relative speed in the dynamic path loss model where θ ij (t) is the included angle of the moving directions of nodes i and j.

8. The civil air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 1, wherein, In the Q - learning algorithm of the said routing optimization module, the parameters λ1, λ2, λ3 are dynamically adjusted by a fuzzy logic controller, satisfying: where μ k is the membership function of the network state NetState.

9. The civil air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 1, characterized in that, The rank R of the tensor decomposition model is determined by the singular value threshold method: R = argmax r (σ r ≥δσ1), where σ r is the r-th singular value, and δ ∈ (0, 1) is a preset threshold.

10. The civil air defense mobile command communication relay system based on adaptive networking intelligent perception according to claim 1, characterized in that the topology reconstruction time of the dynamic networking module is less than 50 ms.

Images