17 results about "Underwater sensor networks" patented technology

The invention discloses a reinforcement learning routing optimization method considering a dynamic underwater sound environment and node mobility. The method comprises the following steps: performing parameter initialization on an underwater sensor network; monitoring and updating underwater environment parameters and node positions in real time, and dynamically updating a network topology connection state; during data transmission, constructing a multi-dimensional state vector, selecting a routing action by adopting an epsilon-greedy strategy, and generating a routing decision; if the data packet transmission fails when the routing action is executed, ending the iteration, otherwise, calculating a multi-target reward value; updating the Q value table to optimize the routing decision; and monitoring network performance indexes in real time, adaptively adjusting reinforcement learning parameters of the intelligent agent for next iteration, and outputting an adaptive routing selection model until an iteration termination condition is met. According to the method, time-varying channel and node mobility challenges can be intelligently dealt with, and multi-objective optimization balance of energy consumption, delay and stability is realized while the data delivery rate is remarkably improved.

The invention discloses an anti-cavity underwater acoustic sensor network non-uniform clustering routing protocol based on particle swarm optimization, and relates to underwater communication. Through integrating hole node evaluation into a fitness function of a particle swarm optimization algorithm, collaborative optimization of cluster head selection and hole avoidance is realized according to node residual energy, node depth and node degree information, so that connectivity and stability of a network are improved. Meanwhile, an inter-cluster cooperative data transmission mechanism is provided, and through a cluster head-gateway load balancing strategy, premature failure caused by frequent relay tasks of individual cluster heads is reduced, so that the network load balance is improved, and the life cycle is prolonged. Besides, on the basis of a classic Dijkstra algorithm, an edge weighting function is constructed in combination with hop count, node residual energy and inter-node distance, and a cluster head traversal termination principle is introduced to optimize path search efficiency and reduce network overhead, so that reliability, energy efficiency and overall communication performance of the underwater acoustic sensor network are remarkably improved.

The application discloses a kind of underwater wireless sensor network node positioning method based on matrix completion, steps are as follows: S1: the Euclidean distance between two different sensor nodes is obtained by TOA ranging method, so as to obtain the Euclidean distance matrix of underwater sensor network node;S2: the Euclidean distance matrix is recovered and completed using the matrix completion algorithm based on non-convex rank approximation, and the distance measurement between all nodes in the network is obtained;S3: the relative coordinates of all nodes underwater are calculated using MDS-MAP algorithm, the relative coordinates of conventional nodes are converted into absolute coordinates by the position of a part of anchor nodes, and the coordinates of conventional nodes are output.The application can not only accurately recover and complete the missing distance matrix, but also effectively handle the influence of Gaussian noise and outlier noise, with good robustness and accuracy.Using the position information of a small number of anchor nodes, the relative position is converted into absolute position, with high node positioning accuracy.

The application discloses a kind of link quality-based directional underwater sensor network routing protocol systems, including multiple underwater sensor nodes.The application link quality-based directional underwater sensor network routing protocol system and system, can select the next hop node of good link quality for first node, so that first node can be directed to the next hop node and send target data;Since the link quality between first node and next hop node is good, and the data transmission between first node and next hop node is directional, it is beneficial to reduce the noise interference received, reduce the energy consumption of sending end and receiving end, improve the overall communication efficiency of directional underwater sensor network, realize the overall high reliability of directional underwater sensor network.The application is widely used in underwater communication technical field.

This invention relates to an intelligent routing method for underwater sensor networks. The method includes: real-time acquisition of state data and link status of all sensor nodes in the underwater sensor network; updating the topology, state space, and action space of the underwater sensor network; invoking a pre-built GNNPPO model; obtaining the optimal routing path based on the updated topology, state space, and action space; distributing the optimal routing path to the source node and intermediate forwarding nodes holding the data packets; and transmitting the data packets hop-by-hop to the target node based on the optimal routing path. The GNNPPO model is a graph neural network (GNN) replacing the fully connected layer PPO network. The GNN includes Actor-GNN and Critic-GNN modules with different readout functions. Compared with existing technologies, this invention achieves dynamic information updating and flexible propagation in underwater sensor networks, as well as rapid adaptation to dynamic topology changes.

The application discloses an underwater sensor network cross-layer MAC protocol implementation method and system, and belongs to the technical field of underwater acoustic wireless sensor networks. The protocol constructs a clustering network structure, combines OFDM physical layer technology and TDMA medium access control, dynamically allocates transmission modes, subcarrier numbers, transmission powers and symbol numbers, so as to meet node differentiated rate requirements and adapt to underwater acoustic channel characteristics. The NSGA-OT algorithm is adopted to solve a multi-objective optimization problem, and the network throughput and total energy consumption are simultaneously optimized under the guarantee of the bit error rate constraint. The application overcomes the problems that the existing MAC protocol ignores node differentiated rate requirements and wastes resources, and improves data transmission reliability, network life cycle and real-time performance.

The application discloses a wide-frequency scattering source cooperative positioning system based on an underwater sensor network, relates to the technical field of underwater sensor network positioning, and comprises the following parts: a distributed underwater sensor node group, which is arranged in an underwater monitoring area and cooperatively collects underwater acoustic signals of a wide-frequency scattering source; a parameter initialization configuration module; an air-frequency domain joint signal modeling module; a cooperative reconstruction base construction module; a sampling signal preprocessing module; a low-rank constraint optimization solving module; and a scattering source parameter solving module, which is used for solving positioning parameters of the wide-frequency scattering source according to a solved air-frequency joint distribution density matrix. The application effectively corrects the attenuation difference of the wide-frequency signal, improves the quality of the signal, and further improves the positioning precision. Through dynamic node position calibration and dynamic adjustment of the calibration period according to the ocean current velocity, the movement of the node can be effectively tracked, the real-time performance of the node position is ensured, and the positioning error caused by the movement of the node is avoided.

The application discloses a kind of underwater sensor network clustering parallel communication methods based on repeated calculation and improved K-means clustering, the method is not considered underwater energy propagation model in the current underwater LEACH protocol based on K-means clustering, and the lack of cluster head node broadcast parallel transmission time slot allocation information will increase its energy consumption, influence network communication rate, proposes to use underwater energy propagation model in K-means clustering to optimize the number of clustering, and to determine cluster head node and network clustering;Meanwhile, each node obtains its parallel transmission time slot by repeated calculation, i.e. The application can be applied to underwater sensor networks in network structures such as underwater ecological monitoring, early warning detection, disaster monitoring, etc.

The invention discloses an efficient self-adaptive routing protocol system of an underwater sensor network based on Q-learning and Bayesian optimization. According to the efficient self-adaptive routing protocol system of the underwater sensor network based on Q-learning and Bayesian optimization, hierarchical routing composed of intra-cluster routing and inter-cluster routing is executed, so that Q-learning application is realized, an efficient data forwarding path is easily found, and data forwarding from an underwater node to an aggregation node is realized; by executing Bayesian optimization, key network control parameters such as hyper-parameters and the like can be automatically adjusted, so that the whole routing system can adapt to different network conditions and continuously converge to a global performance optimal state. The method is widely applied to the technical field of underwater sensor networks.

The invention relates to the technical field of underwater wireless communication, in particular to an underwater wireless acousto-optic combined communication device and a communication method thereof, and the device comprises an acoustic communication module, an optical communication module, an environment sensing module, an energy management module and a cooperative control unit. The acoustic communication module is configured to realize long-distance and low-rate data transmission; the optical communication module is configured to realize short-distance and high-rate data transmission; the environment sensing module is configured to acquire a turbidity value, a communication distance value and an interference intensity value of an underwater environment in real time; the energy management module supplies power to the acoustic communication module and the optical communication module; the cooperative control unit is in communication connection with the acoustic communication module, the optical communication module and the environment sensing module. The system and the method have the advantages that modular integrated design is adopted, main devices are mature commercial products, the cost is controllable, maintenance and upgrading are easy, and the system and the method can be quickly adapted to various application scenes such as underwater sensor networks and unmanned underwater vehicle clusters.

Disclosed is an energy-balanced and efficient routing method that adopts a power control mechanism to reduce energy consumption, and the method involves two phases: routing establishment phase and data forwarding phase. In the routing establishment phase, a sink node broadcasts a beacon packet at a maximum transmission power to establish an initial path, and a receiving node updates the routing table according to beacon information and forwards the beacon packet. In the data forwarding phase, the present disclosure provides a new forwarding factor, which gives comprehensive consideration to energy efficiency and energy balance, selects a node with high energy efficiency and sufficient energy an optimal next-hop node, thereby extending the life cycle of the network. Further provided is a data protection and network recovery mechanism. Topological changes of the network, data forwarding failures and other problems caused by node movement can be solved.

The application discloses a kind of based on Q-learning and the efficient adaptive routing protocol system of underwater sensor network of bayesian optimization.The application based on Q-learning and the efficient adaptive routing protocol system of underwater sensor network of bayesian optimization, by executing the hierarchical routing consisting of intra-cluster routing and inter-cluster routing, to realize the application of Q-learning, to easily find efficient data forwarding path, realize the data forwarding of underwater node to sink node;By executing bayesian optimization, can automatically adjust hyperparameter and other key network control parameters, so that the entire routing system can be adaptive to different network conditions, continuously converges to the global performance optimal state.The application is widely used in the technical field of underwater sensor network.

This invention discloses a broadband scattering source cooperative localization system based on an underwater sensor network, belonging to the field of underwater sensor network localization technology. It includes: a distributed underwater sensor node group deployed in the underwater monitoring area to collaboratively acquire underwater acoustic signals from broadband scattering sources; a parameter initialization and configuration module; a spatial-frequency domain joint signal modeling module; a collaborative substrate reconstruction module; a sampled signal preprocessing module; a low-rank constraint optimization solution module; and a scattering source parameter calculation module, which calculates the localization parameters of the broadband scattering sources based on the solved spatial-frequency joint distribution density matrix. This system effectively corrects the attenuation differences of broadband signals, improves signal quality, and thus improves localization accuracy. Through dynamic node position calibration and dynamic adjustment of the calibration period according to ocean current velocity, it can effectively track node movement, ensuring real-time node position and avoiding localization errors caused by node movement.

This invention discloses a charging path planning method for underwater sensor networks based on an improved Spinehawk optimization algorithm, relating to the fields of underwater sensor network energy management and path planning technology. To address the problems of existing three-dimensional underwater multi-AUV charging path planning methods easily getting trapped in local optima and failing to fully consider dynamic environmental factors, this invention introduces Bernoulli chaotic mapping to enhance diversity in the population initialization stage of the Spinehawk optimization algorithm, introduces position-updating dynamic weight coefficients in the hunting strategy to balance exploration and exploitation, and introduces adaptive inertial weights in the escape strategy to enhance search capability. This improved algorithm is then applied to solve a three-dimensional multi-traveling salesman problem model with the objective of minimizing the total path, thereby planning cooperative charging paths for multiple AUVs. The planned paths are shorter, and AUV energy consumption is lower in calm waters and under varying water flow resistance, effectively increasing the number of surviving sensor nodes.

The invention discloses a method and a system for realizing a cross-layer MAC (Media Access Control) protocol of an underwater sensor network, and belongs to the technical field of underwater acoustic wireless sensor networks. According to the protocol, a clustering network structure is constructed, an OFDM physical layer technology and TDMA medium access control are combined, and transmission modes, the number of subcarriers, transmission power and the number of symbols are dynamically allocated, so that node differentiation rate requirements are met, and underwater acoustic channel characteristics are adapted. A multi-objective optimization problem is solved by adopting an NSGA-OT algorithm, and the network throughput and the total energy consumption are optimized at the same time under the condition that the bit error rate constraint is ensured. According to the invention, the problems that the existing MAC protocol neglects the node differentiation rate demand and wastes resources are solved, and the data transmission reliability, the network life cycle and the real-time performance are improved.

The application relates to an underwater sensor network node positioning method, which comprises the following steps: obtaining transparency data of each node in an underwater sensor network, combining depth, temperature and turbidity information to construct an initial three-dimensional space distribution model of the transparency data; adopting an adaptive Kalman filtering algorithm to iteratively optimize the initial three-dimensional space distribution model to obtain an optimized transparency three-dimensional distribution model; according to a mapping model of a sensor drift amount and a working time length and a time compensation function of the sensor drift amount, performing drift compensation on the optimized transparency three-dimensional distribution model; based on the drift-compensated transparency distribution model, judging the redundancy of the transparency data of each node, and performing dimensionality reduction compression on the redundant data; and adopting a data compression algorithm based on dictionary learning to adaptively compress the dimensionality-reduced and compressed transparency data.

This application provides a method, apparatus, device, and storage medium for cooperative localization in distributed sensor networks. It relates to the field of information fusion. The method includes: a distance extension formula based on a combination of RSSI ranging and a sixth-order Cayley-Menger determinant; constructing a rigid graph model with distance constraints between nodes; dynamically verifying the network topology using graph theory; and employing a distributed optimization algorithm to solve for node distances and positioning coordinates. This application aims to solve for the problems of high energy consumption and strong node density dependence in traditional DV-Hop algorithms, significantly enhancing the robustness of WSNs in scenarios with poor signal conditions or sparse nodes. It can effectively suppress errors caused by broken paths and topological irregularities, and is suitable for various applications such as underwater sensor network localization, unmanned surface vessel swarming, the Internet of Things, disaster early warning, and smart cities.