38 results about "Underwater sensor networks" patented technology

The invention provides a visual underwater sensor network simulation method, and relates to the technical field of underwater sensor networks, and the method comprises the steps: configuring network simulation parameters which comprise topological structure parameters, channel parameters and simulation parameters; inputting the channel parameters into an underwater acoustic calculation tool to generate an underwater acoustic multipath channel for simulation; the bit error rate BER of the multi-carrier MFSK underwater acoustic communication algorithm under the underwater acoustic multipath channel condition is calculated, and the bit error rate BER is input into the OTcl script; performing network simulation on the configured OTcl script by using an underwater network simulator; and displaying a network simulation result through a visual interface. The underwater sensor network simulation result can be displayed through the visual interface, the defect that current NS2-based underwater sensor network simulation software does not have a visual interface is overcome, a good man-machine interaction interface can be provided for a user, the development efficiency is improved, and the user is helped to better evaluate the performance of the underwater sensor network.

The invention discloses an underwater data acquisition method and system, and relates to the field of underwater sensor networks, and the method comprises the steps: dividing a network topology structure with underwater sensors as network nodes into a plurality of clusters, and selecting cluster head nodes; predicting the follow-up moving position of each underwater sensor through a multi-layer water flow model, and obtaining the data information value quantity of each underwater sensor when the underwater sensor moves along with water flow through a data information value quantity model; under the condition that the transmission condition is met, transmitting the data to a cluster head node in a multi-hop transmission mode; and carrying out data acquisition by using the predicted moving position of each cluster head node in the subsequent time when the AUV sails to the predicted moving position, and selecting an acquisition path with the shortest sailing time from all the acquisition paths to complete data acquisition of all the cluster head nodes. According to the invention, accurate data collection can be carried out based on actual dynamic changes of underwater network nodes.

The invention discloses a dynamic symbol interval underwater acoustic communication time delay-error code joint optimization method based on reinforcement learning, and belongs to the technical field of underwater acoustic communication. The method comprises the following steps: setting a symbol interval adjustment range; a depth deterministic policy gradient (DDPG) algorithm is adopted, an Actor-Critic network architecture is combined, channel state information and system performance indexes are sensed in real time, and symbol intervals are dynamically adjusted; designing a weighted reward function, fusing an error rate excitation item, a time delay penalty item and an action smoothing item, and balancing the conflict between the time delay and the error rate through a weight dynamic adjustment strategy; the Actor and Critic network parameters are updated, and soft update of the target network is carried out; channel state time sequence characteristics are extracted by using a sliding window and a long short term memory (LSTM) network, and the adaptive capacity to a time-varying channel is enhanced; an action space is explored in combination with an epsilon greedy strategy, and an emergency rollback mechanism is introduced, so that the model convergence efficiency and the strategy optimization precision are improved. Compared with a traditional fixed symbol interval method, the method can reduce the bit error rate and time delay, and is suitable for underwater sensor networks, unmanned underwater vehicles and other scenes.

The invention relates to the technical field of marine monitoring, in particular to a Transform-based marine organism population anomaly monitoring method and system. The method comprises the following steps: acquiring marine organism population data of different monitoring points, including remote sensing satellite image data, time sequence measurement data of an underwater sensor network and high-resolution image data acquired by an unmanned aerial vehicle; preprocessing the acquired marine organism population data; performing feature screening on the marine organism data based on a gate control mechanism; carrying out anomaly detection on the screened features on the basis of a Transform model; and outputting an anomaly detection result and feeding back the anomaly detection result to the Transform model for retraining. According to the self-adaptive feature screening method based on the gate control mechanism, the features most relevant to the marine organism population change can be automatically recognized and screened out, and therefore interference of data redundancy and noise is reduced.

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.

Provided in the present invention is an energy-balanced and high-efficiency routing method. The method uses a power control mechanism to reduce the energy consumption. The method includes a routing establishment stage and a data transmission stage. In the routing establishment stage, an aggregation node broadcasts a beacon packet at the maximum transmitting power to establish an initial path, and a receiving node updates a routing table according to beacon information and forwards the beacon packet. In a data forwarding stage, the present invention provides a new forwarding factor, and energy efficiency and an energy balance are comprehensively taken into consideration to select as an optimal next hop a node having a high energy efficiency and relatively sufficient energy, thereby prolonging the life cycle of a network. In addition, the present invention further provides a data protection and network reconstruction mechanism to deal with problems such as network topology changes and data forwarding failures, which are caused by node movements. Compared with other typical routing methods, the present invention exhibits a superior performance in terms of reducing the network energy consumption and prolonging the life cycle of a network.

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 invention discloses an underwater communication energy supply network system based on MEMS acoustic modulation and piezoelectric energy collection, which combines an MEMS acoustic modulation technology and the energy collection capability of a piezoelectric material to realize a self-energy-supply wireless communication network of underwater equipment. An underwater communication node in the system sends and receives sound wave signals in water through an MEMS acoustic transducer for data communication, and meanwhile, a piezoelectric energy collection module is used for converting electric energy from environmental mechanical vibration such as water flow and waves to provide continuous power supply for a communication module, a sensor and the like without depending on a battery or an external power supply. According to the system, the reliability and efficiency of underwater acoustic communication are improved by adopting a specific acoustic modulation strategy, and efficient storage and utilization of energy are realized through the energy management circuit, so that underwater nodes can stably operate for a long time. The method is suitable for marine environment monitoring, underwater Internet of Things and other scenes, and the cruising ability and the data transmission efficiency of the underwater 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.

The invention discloses a multi-mode communication-based multi-resource collaborative optimization method and system in an underwater Internet of Things data acquisition system. The method comprises the steps of constructing a UIoT data acquisition system communication model; acquiring a signal-to-noise ratio of the underwater acoustic channel according to the channel gain on the underwater acoustic channel and the variance of the environmental noise between the buoy collector and the USN; obtaining the signal-to-noise ratio of the water-optical channel according to the channel gain between the buoy collector and the USN on the water-optical channel; by jointly regulating and controlling four-dimensional communication resources of an underwater acoustic channel allocation variable, a water-optical channel allocation variable, an underwater acoustic power allocation variable and a water-optical power allocation variable, a mathematical representation model of a UIoT data acquisition system is constructed for an optimization problem of minimizing the total power overhead of all USNs in the system under the condition that the constraint of a service transmission rate is met; and solving the mathematical representation model of the UIoT data acquisition system to obtain a multi-resource collaborative optimization result of the UIoT data acquisition system. According to the invention, the data acquisition efficiency and accuracy of the UIoT data acquisition system are improved, and the power consumption of the system is remarkably reduced.

The present invention relates to a trust management method for underwater sensor networks based on federated deep reinforcement learning, and its steps include: Step 1: Construction of a trust management framework; Step 2: Trust modeling of deep reinforcement learning; Step 3: Update of the federated learning trust model. The trust management method for underwater sensor networks based on federated deep reinforcement learning proposed by the present invention aims at the characteristics of the cross-domain heterogeneous underwater sensor network environment, and uses technical methods such as deep reinforcement learning and federated learning to improve the prediction accuracy of the trust model and reduce the trust update cost, thereby enhancing the overall trust management efficiency in the underwater sensor network composed of heterogeneous devices.

The application provides a kind of visual underwater sensor network simulation method, it is related to underwater sensor network technical field, the method includes: configuration network simulation parameter, network simulation parameter includes topological structure parameter, channel parameter and simulation parameter;Channel parameter is input underwater acoustic computing tool, generates for simulated underwater acoustic multipath channel;Calculate the bit error rate BER of multi-carrier MFSK underwater acoustic communication algorithm under the condition of underwater acoustic multipath channel, and input OTcl script to the bit error rate BER;Complete configuration OTcl script is used underwater network simulator to carry out network simulation;Network simulation result is displayed through visual interface.The application can display underwater sensor network simulation result through visual interface, solve the defect that current underwater sensor network simulation software based on NS2 does not have visual interface, can provide good man-machine interactive interface for user, improve development efficiency, help user to better evaluate the performance of underwater sensor network.

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 provides a dynamic user grouping method for an underwater sensor network, through a dynamic programming method, in a case of continuous iteration, a purpose of two-user grouping of all nodes in the network is achieved, user grouping of non-orthogonal multiple access of the underwater acoustic sensor network is realized, the number of users needing to be regrouped when a new user accesses or a channel condition of an existing user seriously changes is reduced, network required overhead is reduced, and applicability of the non-orthogonal multiple access in the underwater acoustic sensor network is improved, in a case of serious change of a state of the underwater acoustic channel or new user joining, a relay node in the network continues to achieve high communication capacity through regrouping of a small number of users, and high dynamic expandability and robustness are shown. Therefore, the application improves the usability of the non-orthogonal multiple access technology in the underwater acoustic sensor network, and promotes further development of the underwater acoustic sensor network.

The application discloses a kind of sensing node communication systems and methods with self-healing mechanism, including node detection module, node communication module, pre-processing module, hybrid training module and self-healing control module.System is achieved by configuring multiple sensing nodes the periodic collection of multidimensional environmental parameters, based on self-organizing network sharing state information, construct local network health state atlas.Data after pre-processing is used for hybrid neural network training, long-term dependence features and local abnormal fluctuation features of node state are extracted therefrom to assess failure risk.When risk score exceeds threshold value, the system automatically performs dynamic routing reconstruction, standby link activation and other self-healing operations.The application improves the stability and adaptive capacity of underwater sensor network, and has wide application value.

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 present invention relates to the technical field of underwater sensor network relay resource allocation, and in particular to a relay-assisted underwater sensor network mode selection and resource allocation method. The relay-assisted underwater sensor network consists of a sink node (SN) and an underwater sensor node (USN), wherein the USN is randomly deployed in the sea to sense necessary information, and the SN is usually deployed on the sea surface to collect information sensed by all underwater sensor nodes. In order to avoid interference, the entire collection cycle is evenly divided into multiple time slots by using a time division multiple access method. In each time slot, the USN can use an acoustic signal to send corresponding information to the SN. If direct transmission is used, a user node far away from the SN consumes more energy than a user node close to the SN, resulting in node energy imbalance and reduced network life. Further considering the relay transmission mode through an amplification and forwarding protocol, the user network can not only transmit its own information, but also act as a relay to help other user networks.

The invention provides a distributed sensor network cooperative positioning method and device, equipment and a storage medium. Relates to the field of information fusion. The method comprises the following steps: on the basis of a distance extension formula combining RSSI ranging and a six-order Cayley-Menger determinant, constructing a rigid graph model of inter-node distance constraint, dynamically checking a network topology structure in combination with a graph theory judgment theory, and solving a node distance and a positioning coordinate by adopting a distributed optimization algorithm. The invention aims to solve the problems of high energy consumption, strong node density dependence and the like in the traditional DV-Hop algorithm, obviously enhance the robustness of the WSN under a poor signal condition or a sparse node scene, effectively inhibit errors caused by broken line paths and topology irregularity, and improve the robustness of the WSN. The method is suitable for multi-scene application such as underwater sensor network positioning, unmanned ship formation, Internet of Things, disaster early warning and smart cities.

A method for enhancing the coverage of a directed sensor network based on AUV. The present invention relates to a method for enhancing the coverage of a directed sensor network based on AUV. In the existing coverage enhancement method based on the virtual force algorithm, the present invention introduces a repulsive force to maintain a safe distance, considers the angle constraint that the path turning angle cannot be obtuse when planning the AUV movement path, and introduces a virtual moment of the unmonitored area when adjusting the sensor sensing angle of the AUV. The above improvements solve the problems that the existing methods do not consider the maneuverability characteristics and collision avoidance problems during the AUV navigation, improve the network coverage effect on the premise of ensuring the safety of the AUV and the rationality of the path planning point selection, and at the same time accelerate the convergence speed and reduce the AUV movement energy consumption, thereby improving the AUV deployment scheme for the two-dimensional underwater directed sensor network area coverage. The present invention belongs to the field of AUV-assisted underwater sensor network area coverage.

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.

The invention relates to an underwater acoustic communication intrusion detection method and system based on CNN-LSTM. The method comprises the following steps: constructing an underwater sensor network intrusion attack system consisting of a routing layer, an MAC (Media Access Control) layer and a physical layer on the basis of an underwater communication node, a relay node and a shore-based communication server; performing simulation attack on the underwater sensor network based on the intrusion attack system, and collecting attack data in the underwater sensor network in real time; performing iteration and intrusion detection in the improved CNN-LSTM fusion model to obtain a target CNN-LSTM fusion model for underwater acoustic communication intrusion detection; the improved CNN-LSTM fusion model is a CNN model and an LSTM model which are connected through an intermediate layer component. The intrusion of the network layer and the abnormal attacks of the MAC layer and the physical layer are considered, and intrusion detection is performed through the improved CNN-LSTM fusion model, so that the detection capability of the model on various network attacks is improved, and the underwater acoustic communication intrusion detection precision is improved.

The present invention discloses a method for modeling an underwater electromagnetic wave communication channel near the sea surface, and the present invention relates to the technical field of marine electromagnetic communication. This method for modeling an underwater electromagnetic wave communication channel near the sea surface can construct a simple and accurate underwater electromagnetic wave communication channel model near the sea surface. Using this model to evaluate the performance of underwater electromagnetic wave communication, and then guiding the design and implementation of underwater sensor networks, it overcomes the deficiencies and limitations of existing methods. This application can not only obtain the underwater electromagnetic wave communication channel response and link loss, but also obtain the attenuation change of the electromagnetic wave energy with distance in the transmission link. The entire derivation process has a clear physical meaning. Through the establishment and solution of this channel model, it helps to evaluate the performance of underwater electromagnetic wave communication, and then guides the design and implementation of underwater sensor networks.

The present invention relates to a method and system for underwater acoustic communication intrusion detection based on CNN-LSTM. The method comprises: constructing an underwater sensor network intrusion attack system composed of a routing layer, a MAC layer, and a physical layer based on underwater communication nodes, relay nodes, and a shore-based communication server; conducting a simulated attack on the underwater sensor network based on the intrusion attack system, and collecting attack data in the underwater sensor network in real time; performing iteration and intrusion detection in an improved CNN-LSTM fusion model to obtain a target CNN-LSTM fusion model for underwater acoustic communication intrusion detection; the improved CNN-LSTM fusion model connects CNN and LSTM models via an intermediate layer component. Since network layer intrusions, MAC layer and physical layer abnormal attacks are taken into account, intrusion detection is performed using the improved CNN-LSTM fusion model, thereby improving the model's detection capability for various network attacks, thereby improving the accuracy of underwater acoustic communication intrusion detection.

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.

The invention relates to a comprehensive data management and simulation system and method based on an underwater sensor network topology model, and belongs to the technical field of underwater acoustic communication networks and underwater positioning navigation, in particular to the comprehensive data management and simulation system and method based on the underwater sensor network topology model. The objective of the invention is to solve the problems of data dispersion, poor relevance of various data, low efficiency, low reliability, poor high flexibility and low simulation result accuracy of a distributed underwater positioning system. The comprehensive data management and simulation system based on the underwater sensor network topology model comprises an underwater communication subsurface buoy node, an underwater positioning subsurface buoy node, a water surface buoy node, an underwater cooperative target, an underwater acoustic transducer, a satellite antenna, a CTD, a data acquisition packaging device, a data recording loading processing device and an output recorder. The underwater cooperative target is used for sending underwater acoustic signals, and the underwater acoustic signals comprise underwater acoustic communication signals and underwater acoustic positioning signals.