Underwater communication method, device, equipment and medium

Abstract

The invention discloses an underwater communication method, device and equipment and a medium, and relates to the technical field of underwater communication, and the method comprises the steps: determining the optimal communication parameters of each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a twin network; the twin network is a network which is constructed based on an underwater sensor communication network and is updated in real time; the optimal communication parameters comprise an optimal communication position, an optimal transmission mode and optimal transmission power; determining a next underwater sensor node and a current navigation plan of each autonomous underwater vehicle based on the navigation information and the optimal communication positions of all the autonomous underwater vehicles in the twin network; after the autonomous underwater vehicle autonomously sails to the corresponding optimal communication position based on the current sailing plan, data information of the next underwater sensor node is collected through the autonomous underwater vehicle based on the optimal transmission mode and the optimal transmission power; and skipping to the step of determining the optimal communication parameter until the underwater communication is finished. And underwater communication can be completed.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater communication, and particularly to an underwater communication method, device, equipment and medium. Background Art

[0002] Currently, the Underwater Acoustic Sensor Network (UASN) has become a research hotspot in the academic community due to its huge commercial and military value. Sensor data collection is an important part of the underwater acoustic sensor network, but it faces problems such as excessive energy consumption and difficult communication. To solve this problem, Autonomous Underwater Vehicles (AUVs) are widely used in sensor data collection. Due to their limited battery power and relatively slow cruising speed, a single AUV often leads to high energy consumption and long delay in the data collection process, affecting the timeliness of data transmission and the overall efficiency of the network. Therefore, in order to improve the data collection efficiency, the mode of multi-AUV collaborative work has become the focus of research.

[0003] There have been many different studies on multi-AUV data collection. Some studies have adopted evolutionary algorithms. For example, the Voronoi hybrid ant colony optimization algorithm is used for multi-AUV adaptive ocean sampling, the differential evolution algorithm is used for path planning in an underwater environment with a turbulent vector field, and the improved grey wolf optimization algorithm is used for path optimization in an environment with obstacles and ocean currents. However, these methods usually require complete and accurate environmental information, which is difficult to obtain in a dynamically changing ocean environment. And reinforcement learning also provides a new solution for the trajectory planning of AUVs (Autonomous Underwater Vehicles). Related studies include an underwater planning method based on proximal policy optimization, a deep reinforcement learning path planning method based on a double deep Q network, and an integrated method for data collection and collision avoidance based on a double deep Q network. These methods utilize the self-learning ability and can optimize the path planning and data collection strategy in an unknown environment. However, most of the existing technologies only focus on path planning. Once an AUV enters the preset communication range of the node to be collected, it will be assumed to have collected successfully. This assumption exaggerates the collection rate. In a harsh underwater environment, the propagation distance does not determine the communication result. And they determine the collection location after planning the path of the AUV. Such a design limits the channel quality, thereby affecting the allocation of communication power and rate, resulting in low collection performance.

[0004] In summary, with the continuous development of ocean research, underwater acoustic sensor networks have become one of the research hotspots in the academic community, and sensor data collection is crucial for the normal operation of underwater acoustic sensor network applications. To reduce sensor energy consumption and extend network lifespan, autonomous underwater vehicles (AUVs) have begun to be widely used to assist in data collection in underwater acoustic sensor networks. However, the coordination and path planning of multi-AUV systems are very complex, especially in dynamic or uncertain underwater environments. In such an environment, AUVs must handle multiple problems. First, the data collection task requires AUVs to collect data from sensors located at different positions and ensure data integrity in a harsh underwater communication environment. Second, collision avoidance is also a key issue because there are various obstacles in the underwater environment, which poses higher requirements for the navigation systems of AUVs. Finally, energy consumption management is also a challenge. Especially under limited energy conditions, AUVs need to optimize their action paths and task arrangements to extend their operation time. Considering these factors comprehensively, AUV systems must possess a high degree of self-adaptability and intelligent decision-making capabilities to effectively cope with complex environmental conditions and complete tasks.

[0005] In summary, how to complete underwater communication is an urgent problem to be solved currently. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide an underwater communication method, device, equipment and medium that can complete underwater communication. The specific solutions are as follows:

[0007] In the first aspect, the present application discloses an underwater communication method, including:

[0008] Determining the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a twin network; the twin network is a network constructed based on the underwater sensor communication network and updated in real time; the optimal communication parameters include the optimal communication position, the optimal transmission mode, and the optimal transmission power;

[0009] Based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle, determining the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle;

[0010] After the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan, collecting data information of the next underwater sensor node by the autonomous underwater vehicle based on the optimal transmission mode and the optimal transmission power;

[0011] Jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the multi-objective evolutionary algorithm and based on the twin network until the underwater communication ends.

[0012] Among them, determining the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle includes:

[0013] According to the Markov decision process in the multi-agent reinforcement learning algorithm and based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle, determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle.

[0014] Among them, the reward function corresponding to the Markov decision process includes an objective reward term related to the distance length from the optimal communication position.

[0015] Among them, determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the multi-objective evolutionary algorithm and based on the twin network includes:

[0016] Determine the optimal communication parameters corresponding to each autonomous underwater vehicle through the MOEA / D algorithm and based on the twin network.

[0017] Among them, determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the MOEA / D algorithm and based on the twin network includes:

[0018] Construct a multi-objective optimization model corresponding to each autonomous underwater vehicle in the twin network based on the data successful acquisition probability, sensor node energy consumption, and the moving distance of the autonomous underwater vehicle;

[0019] Decompose the multi-objective optimization model through the MOEA / D algorithm to obtain a number of single-objective optimization models, and determine the optimal communication parameters corresponding to each autonomous underwater vehicle according to the single-objective optimization models.

[0020] Among them, decomposing the multi-objective optimization model through the MOEA / D algorithm to obtain a number of single-objective optimization models includes:

[0021] Use the Chebyshev method to decompose the multi-objective optimization model to obtain a number of single-objective optimization models.

[0022] In a second aspect, the present application discloses an underwater communication device, including:

[0023] A first determination module, configured to determine optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a siamese network; the siamese network is a network constructed based on an underwater sensor communication network and updated in real time; the optimal communication parameters include an optimal communication position, an optimal transmission mode, and an optimal transmission power;

[0024] A second determination module, configured to determine a next underwater sensor node and a current navigation plan corresponding to each autonomous underwater vehicle based on the navigation information of all the autonomous underwater vehicles in the siamese network and the optimal communication position of each autonomous underwater vehicle;

[0025] A data acquisition module, configured to, after the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan, collect data information of the next underwater sensor node through the autonomous underwater vehicle based on the optimal transmission mode and the optimal transmission power;

[0026] A jump module, configured to jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a siamese network until underwater communication ends.

[0027] Wherein, the second determination module is specifically configured to determine a next underwater sensor node and a current navigation plan corresponding to each autonomous underwater vehicle according to a Markov decision process in a multi-agent reinforcement learning algorithm and based on the navigation information of all the autonomous underwater vehicles in the siamese network and the optimal communication position of each autonomous underwater vehicle.

[0028] In a third aspect, the present application discloses an electronic device, including:

[0029] A memory, configured to store a computer program;

[0030] A processor, configured to execute the computer program to implement the underwater communication method disclosed above.

[0031] In a fourth aspect, the present application discloses a computer-readable storage medium, configured to store a computer program; wherein, when the computer program is executed by a processor, the underwater communication method disclosed above is implemented.

[0032] It can be seen that in this application, the optimal communication parameters corresponding to each autonomous underwater vehicle are determined through a multi-objective evolutionary algorithm and based on a Siamese network; the Siamese network is a network constructed based on an underwater sensor communication network and updated in real time; the optimal communication parameters include the optimal communication position, the optimal transmission mode, and the optimal transmission power; based on the navigation information of all the autonomous underwater vehicles in the Siamese network and the optimal communication position of each autonomous underwater vehicle, the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle are determined; after the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan, data information of the next underwater sensor node is collected by the autonomous underwater vehicle based on the optimal transmission mode and the optimal transmission power; jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the multi-objective evolutionary algorithm and based on the Siamese network until underwater communication ends. Thus, it can be seen that multiple autonomous underwater vehicles in this application act together, and the optimal communication parameters corresponding to each autonomous underwater vehicle are determined respectively, and path planning is obtained based on the optimal communication parameters, which can improve the success rate of data collection and the success rate of underwater communication; this application uses a multi-objective evolutionary algorithm to calculate the optimal communication parameters corresponding to each autonomous underwater vehicle, improving the accuracy of parameter calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0034] Figure 1 It is a flowchart of an underwater communication method disclosed in this application;

[0035] Figure 2 It is a schematic structural diagram of an underwater communication device disclosed in this application;

[0036] Figure 3 It is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to 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. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0038] With the continuous development of ocean research, underwater acoustic sensor networks have become one of the research hotspots in the academic community, and sensor data acquisition is crucial for the normal operation of underwater acoustic sensor network applications. To reduce sensor energy consumption and extend the network lifespan, autonomous underwater vehicles (AUVs) have begun to be widely used to assist in data acquisition in underwater acoustic sensor networks. However, the coordination and path planning of multi-AUV systems are very complex, especially in dynamic or uncertain underwater environments. In such an environment, AUVs must handle multiple problems. First, the data acquisition task requires AUVs to collect data from sensors located at different positions and ensure data integrity in a harsh underwater communication environment. Second, collision avoidance is also a key issue because there are various obstacles in the underwater environment, which poses higher requirements for the AUV's navigation system. Finally, energy consumption management is also a challenge. Especially under limited energy conditions, AUVs need to optimize their action paths and task arrangements to extend the operation time. Considering these factors comprehensively, AUV systems must have a high degree of adaptability and intelligent decision-making capabilities to effectively cope with complex environmental conditions and complete tasks.

[0039] Therefore, an embodiment of this application proposes an underwater communication solution that can complete underwater communication.

[0040] An embodiment of this application discloses an underwater communication method. Refer to Figure 1 as shown, this method includes:

[0041] Step S11: Determine the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a twin network; the twin network is a network constructed based on an underwater sensor communication network and updated in real time; the optimal communication parameters include the optimal communication location, the optimal transmission mode, and the optimal transmission power.

[0042] In this embodiment, an autonomous underwater vehicle is an unmanned submersible that can navigate and perform tasks autonomously underwater; an underwater acoustic sensor network (underwater sensor communication network) is a system for data acquisition and communication through acoustic wave transmission underwater, used for monitoring and analyzing the underwater environment.

[0043] In this embodiment, determining the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a siamese network includes: determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the MOEA / D algorithm and based on the siamese network. It should be noted that this application models the process of a single AUV communicating with a single sensor node and transforms it into a multi-objective optimization problem. By adjusting parameters such as the communication position, communication power, and communication mode of the AUV in the siamese network, efforts are made to optimize multiple objectives, including the communication success probability, AUV movement energy consumption, and sensor transmission energy consumption. To solve this multi-objective optimization problem, this application proposes the MOEA / D optimization algorithm, which can find a set of optimal communication parameters to achieve the best performance during the communication process. The MOEA / D algorithm decomposes the multi-objective optimization problem into a series of single-objective optimization problems and finds the global optimal solution by co-optimizing each sub-problem. These optimized communication parameters can not only improve the communication success rate but also guide the path planning module to reach the optimal communication position.

[0044] In this embodiment, determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the MOEA / D algorithm and based on the siamese network includes: constructing a multi-objective optimization model corresponding to each autonomous underwater vehicle in the siamese network based on the data successful acquisition probability, sensor node energy consumption, and the movement distance of the autonomous underwater vehicle; decomposing the multi-objective optimization model through the MOEA / D algorithm to obtain a number of single-objective optimization models, and determining the optimal communication parameters corresponding to each autonomous underwater vehicle according to the single-objective optimization models.

[0045] In this embodiment, decomposing the multi-objective optimization model through the MOEA / D algorithm to obtain a number of single-objective optimization models includes: decomposing the multi-objective optimization model using the Chebyshev method to obtain a number of single-objective optimization models.

[0046] It should be noted that the construction process of the multi-objective optimization problem is as follows: when the transmission power of the sensor node is p, the successful transmission probability of the sensor data is: ;

[0047] where L represents the data transmission distance;

[0048] Bit error rate The derivation formula of is:

[0049] ;

[0050] where erfc represents the complementary error function; I (real part) and J (imaginary part) represent the partitioning of the signal constellation in two dimensions, indicating the number of points in the real and imaginary part directions. I×J represents the number of points in the signal constellation;

[0051] represents the signal-to-noise ratio, specifically expressed as: ;

[0052] where is the communication rate, is the channel bandwidth; SNR is the abbreviation of SIGNAL-NOISE RATIO, representing the signal-to-noise ratio;

[0053] The energy consumption of the sensor node can be expressed as: ;

[0054] where represents the communication rate in the selected communication mode, represents the preamble time of the data packet, p represents the transmission power of the sensor node; The mobile energy consumption of the AUV moving to the communication position can be simply considered to be positively correlated with the moving distance, and the moving distance can be expressed as:

[0055] ;

[0056] where represents the current position of the AUV, represents the communication position;

[0057] Therefore, the problem can be formulated as a multi-objective optimization problem:

[0058] ;

[0059] Then, a multi-objective optimization algorithm based on MOEA / D is proposed to solve this problem. MOEA / D is a decomposition-based multi-objective evolutionary algorithm, which decomposes the multi-objective optimization problem into a set of single-objective optimization problems. Using weight vectors, the multi-objective optimization problem can be transformed into a single-objective optimization problem in various ways. Each weight vector corresponds to a decomposed single-objective optimization problem, and there are different similarities among these single-objective optimization problems. According to the corresponding weight vector, its neighbor problems can be determined. In this application, the Chebyshev method is used for problem decomposition, and the decomposed single-objective optimization problem can be expressed as:

[0060] ;

[0061] where m represents the number of optimization objectives, represents a weight vector, represents the reference point representation. Additionally, the optimization strategy of this application only depends on the current state of the system (the current state of the twin network), which enables it to be easily integrated into the path planning algorithm based on reinforcement learning, further enhancing the intelligence level of the system.

[0062] The MOEA / D process steps are as follows:

[0063] (1), Generate a set of weight vectors and delete the weight vectors with weak preference for key indicators. Then obtain the final set of weight vectors and reset the initial state ;

[0064] (2), Select a neighborhood for each vector;

[0065] (3), Generate the initial population and calculate the reference point ;

[0066] (4), For all Use the crossover operation of the genetic algorithm to generate new solutions ;

[0067] (5), Evaluate the fitness of the new solutions , and then update the population and the reference point .

[0068] Step S12: Based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle, determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle.

[0069] In this embodiment, the determining the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle includes:

[0070] According to the Markov decision process in the multi-agent reinforcement learning algorithm and based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle, determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle.

[0071] In this embodiment, the reward function corresponding to the Markov decision process includes an objective reward term related to the distance length from the optimal communication position.

[0072] It should be noted that the reinforcement learning algorithm can gradually optimize the behavior strategy of the AUV by continuously learning and adapting in a dynamically changing environment. Combining the optimization of communication parameters and path planning, the AUV can achieve efficient and reliable communication and data collection in a complex underwater environment.

[0073] Specifically, this application models the path planning problem as a multi-agent Markov process (MDP). By defining the state space , action space , observation space and reward function , a multi-agent reinforcement learning algorithm is proposed to solve this Markov process. The state space contains all the states of the AUV and can be expressed as:

[0074] ;

[0075] where each state includes the position information, speed, remaining energy, etc. of the AUV;

[0076] The action space represents the set of executable actions for each AUV:

[0077] ;

[0078] where each action can be operations such as moving forward, turning, stopping, etc.;

[0079] The observation space defines the observation information for each AUV:

[0080] ;

[0081] Each observation value includes the acoustic signal intensity of the surrounding environment, the positions of other AUVs, etc.

[0082] The reinforcement learning algorithm adopts a centralized training and distributed execution architecture. During the training phase, each AUV shares the observation space and action space to improve the training effect. In the execution phase, each AUV decides which actions to execute based on its own observation information. To cope with the complex marine environment, penalty terms for situations such as disconnection, obstacle collision, and out-of-bounds are added to the reward function to improve the robustness of the AUV. In addition, to optimize the efficiency of the AUV reaching the optimal communication position, a reward term related to the distance from the optimal communication position is also added to the reward function. In addition, to improve the efficiency of the AUV reaching the optimal communication position, the distance from the optimal communication position is added to the reward function to improve performance. Therefore, the reward function can be expressed as:

[0083] ;

[0084] Among them, indicates whether an obstacle is collided with, indicates the penalty for colliding with an obstacle, indicates whether there is an association between AUVs, indicates the penalty for AUV disconnection, indicates whether the communication position is reached, indicates the fixed reward for reaching the communication position, indicates the energy consumption of AUV movement, and the specific calculation is:

[0085] ;

[0086] , is the energy consumption coefficient, represents the distance between two positions, and speed represents the current speed of the AUV.

[0087] The algorithm uses a centralized training and distributed execution architecture. In the training stage, each AUV shares the observation space and action space to improve the training effect; in the execution stage, each AUV determines the action to be executed only based on its own observation information. Each AUV maintains four neural networks: Q network , target Q network , policy network , target policy network . Each AUV updates The loss formula of is as follows:

[0088] ;

[0089] Among them, contains the observations of all AUVs, contains the actions of all AUVs, E represents the maximum likelihood estimation, represents the target value of the Q network, which can be expressed as:

[0090] ;

[0091] According to the updated Q network, the policy of each AUV can be updated, and the policy gradient can be expressed as:

[0092] ;

[0093] represents the gradient of the policy network with respect to the action, represents the gradient of the Q network with respect to the action.

[0094] It should be noted that the multi-agent reinforcement learning algorithm process is as follows:

[0095] Input: The maximum number of episodes E, the maximum number of rounds T, the size of the batch M (there are T rounds in the multi-agent reinforcement learning algorithm process, and each T round contains E small rounds. T represents a total time, and this step divides the time into time periods, operating from the first time period to the last time period; f represents the AUV index to distinguish different AUVs, and M represents the number of samples);

[0096] Output: The final behavior policy;

[0097] 1: for episode = 1 to E do;

[0098] 2: Reset the initial state ;

[0099] 3: for t = 1 to T do;

[0100] 4: Obtain the observation ;

[0101] 5: Select and execute an action ;

[0102] 6: Obtain the reward and the new observation ;

[0103] 7: Put , , , into the experience replay buffer;

[0104] 8: Update the initial state to ;

[0105] 9: Obtain a random sample M from the experience replay buffer;

[0106] 10: Update the critic and actor networks;

[0107] 11: Update the target network;

[0108] 12: end for;

[0109] 13: end for。

[0110] Step S13: After the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan, the autonomous underwater vehicle collects the data information of the next underwater sensor node based on the optimal transmission mode and the optimal transmission power.

[0111] Step S14: Jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the multi-objective evolutionary algorithm and based on the twin network until the underwater communication ends.

[0112] In summary, the present application develops an optimal communication strategy considering the propagation characteristics of the real underwater acoustic channel. This strategy adaptively determines the collection location, communication rate, and power to improve the probability of successful collection and the energy efficiency of communication. Moreover, in combination with the communication strategy, the present application proposes an algorithm based on distributed deep reinforcement learning to determine the trajectories and acquisition order of multiple AUVs. This approach enhances the cooperation between AUVs and achieves efficient global collection with minimal motion energy consumption.

[0113] It can be seen that the present application determines the optimal communication parameters corresponding to each autonomous underwater vehicle through the multi-objective evolutionary algorithm and based on the twin network; the twin network is a network constructed based on the underwater sensor communication network and updated in real time; the optimal communication parameters include the optimal communication location, optimal transmission mode, and optimal transmission power; based on the navigation information of all autonomous underwater vehicles in the twin network and the optimal communication location of each autonomous underwater vehicle, determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle; after the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication location based on the corresponding current navigation plan, collect the data information of the next underwater sensor node through the autonomous underwater vehicle based on the optimal transmission mode and the optimal transmission power; jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle through the multi-objective evolutionary algorithm and based on the twin network until the underwater communication ends. Thus, it can be seen that multiple autonomous underwater vehicles in the present application act together, and respectively determine the optimal communication parameters corresponding to each autonomous underwater vehicle, and obtain the path planning based on the optimal communication parameters, which can improve the success rate of data collection and the success rate of underwater communication; the present application uses the multi-objective evolutionary algorithm to calculate the optimal communication parameters corresponding to each autonomous underwater vehicle, improving the accuracy of parameter calculation.

[0114] Correspondingly, the embodiment of the present application also discloses an underwater communication device. See Figure 2 As shown, the device includes:

[0115] The first determination module 11 is used to determine the optimal communication parameters corresponding to each autonomous underwater vehicle through the multi-objective evolutionary algorithm and based on the twin network; the twin network is a network constructed based on the underwater sensor communication network and updated in real time; the optimal communication parameters include the optimal communication location, optimal transmission mode, and optimal transmission power;

[0116] The second determination module 12 is configured to determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle.

[0117] The data acquisition module 13 is configured to, after the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan, collect the data information of the next underwater sensor node by the autonomous underwater vehicle based on the optimal transmission mode and the optimal transmission power.

[0118] The jump module 14 is configured to jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle by the multi-objective evolutionary algorithm and based on the twin network until the underwater communication ends.

[0119] Among them, for the more specific working processes of the above-mentioned various modules, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be elaborated herein.

[0120] It can be seen that this application determines the optimal communication parameters corresponding to each autonomous underwater vehicle by the multi-objective evolutionary algorithm and based on the twin network; the twin network is a network constructed based on the underwater sensor communication network and updated in real time; the optimal communication parameters include the optimal communication position, the optimal transmission mode, and the optimal transmission power; based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle, determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle; after the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan, collect the data information of the next underwater sensor node by the autonomous underwater vehicle based on the optimal transmission mode and the optimal transmission power; jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle by the multi-objective evolutionary algorithm and based on the twin network until the underwater communication ends. Thus, it can be seen that multiple autonomous underwater vehicles in this application act together, and respectively determine the optimal communication parameters corresponding to each autonomous underwater vehicle, and obtain the path planning based on the optimal communication parameters, which can improve the success rate of data collection and the success rate of underwater communication; this application uses the multi-objective evolutionary algorithm to calculate the optimal communication parameters corresponding to each autonomous underwater vehicle, improving the accuracy of parameter calculation.

[0121] Furthermore, the embodiment of this application also provides an electronic device. Figure 3 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure should not be considered as any limitation to the scope of use of this application.

[0122] Figure 3 Schematic diagram of the structure of an electronic device 20 provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the underwater communication method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0123] In this embodiment, the power supply 26 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and no specific limitation is imposed thereon here; the input / output interface 24 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0124] In addition, the memory 22, as a carrier for resource storage, may be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc. The resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. Among them, the computer program 221 may further include a computer program capable of completing other specific tasks in addition to the computer program capable of implementing the underwater communication method executed by the electronic device 20 disclosed in any of the foregoing embodiments.

[0125] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the underwater communication method disclosed above is implemented.

[0126] For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details are not repeated here.

[0127] The various embodiments in this application are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts between the various embodiments, reference may be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and reference may be made to the description in the method part for related parts.

[0128] Those skilled in the art may further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0129] The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0130] Finally, it should also be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0131] The above has introduced in detail a method, device, equipment, and storage medium for underwater communication provided by this application. Specific examples are used herein to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. An underwater communication method, characterized in that: include: Determining the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a twin network; the twin network is a network built based on an underwater sensor communication network and updated in real time; the optimal communication parameters include an optimal communication position, an optimal transmission mode, and an optimal transmission power; Based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle, determining the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle; After the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan, the autonomous underwater vehicle collects data information of the next underwater sensor node based on the optimal transmission mode and the optimal transmission power; Jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a twin network until the underwater communication is completed.

2. The underwater communication method according to claim 1, characterized in that: The determining, based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle, the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle comprises: According to the Markov decision process in the multi-agent reinforcement learning algorithm and based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each of the autonomous underwater vehicles, the next underwater sensor node and the current navigation plan corresponding to each of the autonomous underwater vehicles are determined.

3. The underwater communication method according to claim 2, characterized in that: The reward function corresponding to the Markov decision process includes a target reward item related to the distance length from the optimal communication position.

4. The underwater communication method according to claim 1, characterized in that: The method of determining the optimal communication parameters corresponding to each autonomous underwater vehicle by a multi-objective evolutionary algorithm based on a twin network includes: The optimal communication parameters corresponding to each autonomous underwater vehicle are determined through the MOEA / D algorithm and based on the twin network.

5. The underwater communication method according to claim 4, characterized in that: The determining of the optimal communication parameters corresponding to each of the autonomous underwater vehicles by the MOEA / D algorithm and based on the twin network includes: Constructing a multi-objective optimization model corresponding to each of the autonomous underwater vehicles in the twin network based on the probability of successful data collection, energy consumption of sensor nodes, and moving distance of the autonomous underwater vehicle; The multi-objective optimization model is decomposed by the MOEA / D algorithm to obtain a number of single-objective optimization models, and the optimal communication parameters corresponding to each of the autonomous underwater vehicles are determined according to the single-objective optimization models.

6. The underwater communication method according to claim 5, characterized in that: The multi-objective optimization model is decomposed by the MOEA / D algorithm to obtain several single-objective optimization models, including: The multi-objective optimization model is decomposed by using the Chebyshev method to obtain several single-objective optimization models.

7. An underwater communication device, characterized in that: include: A first determination module is used to determine the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a twin network; the twin network is a network built based on an underwater sensor communication network and updated in real time; the optimal communication parameters include an optimal communication position, an optimal transmission mode, and an optimal transmission power; A second determination module is used to determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle; A data acquisition module, configured to collect data information of the next underwater sensor node based on the optimal transmission mode and the optimal transmission power by the autonomous underwater vehicle after the autonomous underwater vehicle autonomously navigates to the corresponding optimal communication position based on the corresponding current navigation plan; A jump module is used to jump to the step of determining the optimal communication parameters corresponding to each autonomous underwater vehicle through a multi-objective evolutionary algorithm and based on a twin network until the underwater communication is completed.

8. The underwater communication device according to claim 7, characterized in that: The second determination module is specifically used to determine the next underwater sensor node and the current navigation plan corresponding to each autonomous underwater vehicle according to the Markov decision process in the multi-agent reinforcement learning algorithm and based on the navigation information of all the autonomous underwater vehicles in the twin network and the optimal communication position of each autonomous underwater vehicle.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the underwater communication method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the underwater communication method according to any one of claims 1 to 6 is implemented.

Images