11 results about "Underwater wireless sensor networks" patented technology

The invention relates to an underwater wireless sensor network path sensing routing method based on deep reinforcement learning, which comprises the following steps that: firstly, a node constructs and periodically updates a transmission preference model based on local and neighbor node interaction information; secondly, deploying a deep reinforcement learning model at each underwater sensor node to perform distributed routing strategy learning; and finally, generating a global guide vector by the sink node according to the routing path information of the received data packet, reversely spreading the global guide vector to the source node, fusing the global guide vector with a local transmission preference vector of the node to generate a guide reward, optimizing the deep reinforcement learning model, and updating a routing strategy. According to the method, the problems of difference and complexity of underwater transmission tasks can be solved, and the network data transmission efficiency and the overall service quality are improved in combination with local preference and global guidance while the node online learning is kept to adapt to the dynamic underwater environment.

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 invention discloses a soft synchronization TDMA (Time Division Multiple Access) protocol implementation method for an underwater wireless sensor network, belongs to the technical field of underwater wireless communication, and solves the problems of difficulty in synchronization and high conflict rate of the existing UWSNs in an underwater sound environment with long propagation delay. According to the method, the initial time of an active window is distributed to each sensor node in the network at equal intervals, a periodic frame structure with the windows capable of being overlapped is established, and flexible adjustment of the frame length is achieved so as to optimize time delay; window random jitter is introduced to realize cross-period decoupling of the synchronization error, and the cumulative effect of the synchronization error is relieved; an access moment is randomly selected in an active window according to truncation cosine-distribution, and data packet transmission is performed at the access moment in the window, so that the conflict rate is remarkably reduced, the throughput and the channel utilization rate are improved, the end-to-end delay is shortened, and the access fairness is improved on the premise that strict global synchronization is not needed; the method is suitable for resource-limited underwater sensor nodes and UWSNs scenes such as marine environment monitoring, deep sea exploration and national defense communication.

The invention relates to a data acquisition and transmission system. The data acquisition and transmission system comprises a sea-based information acquisition unit, underwater wireless sensor network equipment and a shore-based data processing unit which perform data interaction through a preset integrated data link, the underwater wireless sensor network equipment acquires deep marine environment data and transmits the deep marine environment data to the sea-based information acquisition unit; the sea-based information acquisition unit is used for acquiring offshore data or receiving deep marine environment data acquired by the underwater wireless sensor network equipment; after the deep ocean environment data and the offshore data are preprocessed, the preprocessed deep ocean environment data and the preprocessed offshore data are transmitted to the shore-based data processing unit; and the shore-based data processing unit receives the preprocessed deep marine environment data and the preprocessed offshore data sent by the sea-based information acquisition unit, and carries out fusion processing and storage on the preprocessed deep marine environment data and the preprocessed offshore data. Therefore, the operation stability of the data acquisition and transmission system can be improved.

The invention relates to a double-perception online fountain code transmission system and method based on deep reinforcement learning. The system is applied to an underwater wireless sensor network, and comprises a network modeling module which is used for constructing an underwater acoustic sensor network model of a three-dimensional hierarchical clustering topology by adopting a fuzzy clustering algorithm according to spatial distribution and residual energy of nodes, and determining a transmission mechanism of half-duplex underwater acoustic communication; the reinforcement learning optimization module is used for modeling a decoding process of an online fountain code into a Markov decision process and training an agent in combination with a deep learning algorithm to generate an optimal coding degree sequence; and the coding transmission execution module is used for executing the optimal coding degree sequence to generate a coding data packet, performing multi-hop transmission, and performing coding degree switching based on limited feedback triggering until the aggregation node recovers all original data. Based on a half-duplex underwater acoustic communication mechanism, channel conflicts are avoided, the optimal coding degree sequence can be dynamically matched with a decoding state, and the data transmission reliability in an extreme underwater environment is improved.

The application relates to a three-dimensional underwater wireless sensor network dynamic positioning method, which comprises the following steps: step S1, calculating the minimum hop number and the average hop distance between each unknown node and a beacon node in a three-dimensional underwater wireless sensor network; step S2, converting the signal strength between the unknown node and the beacon node into the communication radius distance between the two, improving the HH-VBF underwater routing protocol, selecting the next hop node and transmitting information by using the improved HH-VBF underwater routing protocol, and calculating the updated minimum hop number; step S3, calculating the average hop distance of each unknown node to the beacon node and optimizing the average hop distance; step S4, calculating the coordinates of the unknown node; and step S5, tracking the target of the unknown node. Compared with the prior art, the application realizes real-time positioning and accurate tracking of unknown sensor nodes in a dynamic three-dimensional underwater environment.

The cluster head election method for improving LEACH algorithm and the improved LEACH routing protocol method belong to the technical field of routing soft security of underwater wireless sensor network, and particularly relate to a cluster head election process of underwater wireless sensor network; solve the problem that the existing cluster-based routing protocol ignores the security problem and the security of the cluster head election process is low; the method comprises the following steps: each node updates its own mse according to the trust evaluation result of the sink node on itself; each node uses an improved cluster head election threshold function T imp (n) to calculate the cluster head election threshold; each node compares the random number generated by itself with the cluster head election threshold; if it is less than the cluster head election threshold, the node becomes the cluster head node in the current large period. The improved cluster head election method for improving LEACH algorithm and the improved LEACH routing protocol method are suitable for providing a cluster-based routing protocol.

The application discloses a prediction compensation type opportunity routing forwarding timing control method for a mobile underwater wireless sensor network, and relates to the technical field of communication control, and comprises the following steps: S1, acquiring a current sending node candidate node list, predicting the position of the candidate node at a data packet predicted arrival time and a predicted propagation distance; S2, generating a priority adjustment factor through fuzzy logic, and then obtaining a dynamic comprehensive priority; S3, performing time reversal channel prediction by using a detection signal of the candidate node, obtaining a future propagation delay, and calculating a dynamic propagation delay compensation base value according to non-collision constraints of all candidate node pairs; S4, calculating a waiting time for each candidate node according to the dynamic comprehensive priority, the dynamic propagation delay compensation base value, a relative radial velocity and the predicted propagation distance; and S5, encapsulating the candidate node list and the waiting time into a data packet header and broadcasting, and the candidate node analyzes the own waiting time and starts a local timer, and inhibits forwarding or executes forwarding.

The invention discloses an underwater wireless sensor network routing method based on hole prediction and MARCOS multi-attribute decision. The method comprises the following steps: establishing a neighbor list; storing and updating the information received from the neighbor node; the method comprises the following steps: predicting whether adjacent nodes possibly escape from a node communication radius or not by establishing a safety area in a node communication range and dividing an escape area, and quantitatively evaluating the communication performance of the adjacent nodes from a safety area score, an escape area score and a forwarding performance score based on neighbor list information; introducing a multi-attribute decision-making method to dynamically fuse the safe area score, the escape area score and the forwarding performance score, and calculating a comprehensive forwarding priority; when a node forwards a data packet, the data packet is added according to a candidate node list of multi-attribute decision sorting, a next-level node carries out receiving and first-level time slice waiting, and meanwhile second-level time slice waiting is started according to whether forwarding succeeds or not. According to the method, the routing decision adaptivity is high, and the problems of high processing overhead and the like caused by routing holes are solved from the source.

The invention provides an underwater node positioning method and electronic equipment, and relates to the technical field of underwater wireless sensor networks. The method comprises the following steps: acquiring an initially received RSSI signal corresponding to each node of an underwater wireless sensor network, inputting the RSSI signal into a two-stage filtering model, outputting a filtered RSSI signal, and carrying out mean-median double-weight fusion to obtain a corrected RSSI signal; wherein the two-stage filtering model comprises IHADF and Gaussian filtering; real-time hydrological parameters are obtained, the corrected RSSI signals and the real-time hydrological parameters are input into the dynamic sound propagation path loss model, and an inter-node distance estimation value is output; the hydrological parameters comprise temperature, salinity and depth; and performing dimension reduction mapping based on the inter-node distance estimation value and the depth data corresponding to the nodes, mapping to a plane where the two-dimensional plane of the unknown node is located, and solving the three-dimensional coordinates of the unknown node by adopting a self-adaptive filtering algorithm fusing depth perception and sound velocity profile dynamic compensation. The problem that a traditional positioning algorithm is insufficient in adaptability can be systematically solved.

The invention relates to a multi-source iterative positioning method for an ocean wireless sensor network under a non-line-of-sight and layered propagation condition, which comprises the following steps: acquiring observation information received by a target node to be estimated from RSS and TOA of anchor nodes, introducing an NLOS error, and constructing an initial signal power model and an initial distance model; modeling a propagation path of the signal, and obtaining a compensation form of signal path propagation under the layering effect based on a modeling result; converting the initial signal power model and the initial distance model based on the compensation form to obtain a correction model, and obtaining an initial positioning objective function based on the correction model; respectively calculating the weight coefficients of the RSS and TOA by using the distance characteristics measured by the RSS and TOA, and obtaining a positioning objective function based on the weight coefficients; and performing initial position estimation based on the positioning target function, and performing fine advancing to obtain a final positioning estimation value. Compared with the prior art, the influence of the layering effect and the NLOS error on the positioning accuracy is considered at the same time, and more accurate positioning estimation is achieved.