A method for selecting communication paths for underwater sensor network nodes

By deploying environmental sensors and machine learning algorithms in the underwater sensor network, dynamically selecting communication paths and modes, the problem that static rules in the prior art are difficult to adapt to complex environments, and efficient and stable underwater communication is achieved.

CN118827503BActive Publication Date: 2024-11-15ZHEJIANG FORESTRY UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411306505.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-11-15
Estimated Expiration
2044-09-19

AI Technical Summary

Technical Problem

The communication path selection method of existing underwater sensor networks relies on static rules and is difficult to adapt to complex and changeable underwater environments, resulting in low communication efficiency and unstable data transmission, lack of real-time monitoring and dynamic adjustment mechanisms, and cannot fully utilize environmental parameter data. , affects the reliability and efficiency of the network.

Method used

Deploy environmental sensors on the underwater sensor network nodes to collect water flow velocity, water temperature and water turbidity parameters in real time, build a path transmission quality model through machine learning algorithms, combine multi-objective optimization algorithms to perform dynamic path selection, and judge appropriateness based on environmental conditions communication mode, real-time monitoring and update path selection and mode to improve communication quality.

Benefits of technology

It significantly improves the communication path selection efficiency and transmission quality of the underwater sensor network, improves the transmission efficiency and reliability of the network, ensures the stability of communication quality under different environmental conditions, and supports the sustainable development and application expansion of underwater communication.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118827503B_ABST
    Figure CN118827503B_ABST
Patent Text Reader

Abstract

The present invention provides a method for selecting a communication path for an underwater sensor network node, and relates to the field of underwater communication technology. The present invention deploys environmental sensors to monitor the flow velocity, temperature and turbidity parameters of the underwater environment in real time, and obtains the amount of data successfully received and the total amount of data sent by each communication path in historical data, calculates the data transmission effectiveness and transmission success rate of each communication path, constructs a transmission quality prediction model, and dynamically selects the best communication path based on a multi-objective optimization algorithm. At the same time, the method can automatically adjust the communication mode and path according to environmental changes, thereby achieving a stable communication channel and efficient data transmission, adapting to complex underwater environments, and ultimately improving the overall performance of the underwater monitoring system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of underwater communication technology, and in particular to a method for selecting a communication path for an underwater sensor network node. Background Art

[0002] As an emerging monitoring and data collection technology, underwater sensor networks are widely used in marine environmental monitoring, resource exploration, military reconnaissance and other fields. Due to the complexity of the underwater environment, factors such as water flow velocity, temperature changes and water turbidity will have a significant impact on signal propagation, resulting in a reduced success rate of data transmission. Traditional communication path selection methods mostly rely on static rules or fixed strategies, and fail to fully consider changes in the dynamic environment, resulting in delays, packet loss and energy consumption during the communication process. In addition, existing technologies usually lack real-time monitoring and feedback mechanisms, and fail to adjust communication strategies in time to cope with changes in environmental conditions. Therefore, developing a dynamic communication path selection method based on real-time environmental parameters and intelligent algorithms can significantly improve the communication efficiency and stability of underwater sensor networks, which is an important direction to solve the current technical bottleneck.

[0003] The prior art has the following deficiencies:

[0004] Existing communication path selection methods for underwater sensor networks often rely on static rules and are difficult to adapt to the complex and changeable underwater environment, resulting in low communication efficiency and unstable data transmission. In addition, traditional methods usually lack real-time environmental monitoring and dynamic adjustment mechanisms, fail to fully utilize environmental parameter data, and thus cannot accurately evaluate the transmission quality of different paths. The limitations of this static and single strategy make the network vulnerable to environmental factors, resulting in communication failures or delays, affecting the reliability and efficiency of the overall underwater monitoring system. Therefore, there is an urgent need for an intelligent solution that can analyze environmental data in real time and dynamically optimize path selection to improve the quality and stability of underwater communications.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method for selecting a communication path for an underwater sensor network node to solve the problems raised in the above background technology.

[0007] A method for selecting a communication path for an underwater sensor network node, the specific steps comprising:

[0008] Step 1: deploy environmental sensors on each node of the underwater sensor communication network to collect environmental parameters, analyze the collected environmental parameters, and obtain the transmission effectiveness of each communication path of the underwater sensor network node, wherein the environmental parameters include water flow velocity, water temperature, and water turbidity;

[0009] Step 2: Obtain the amount of data successfully received and the total amount of data sent by each communication path from historical data, calculate the transmission success rate of each communication path in the underwater sensor communication network, analyze the transmission success rate of each communication path and the transmission effectiveness of the underwater sensor network, and obtain the transmission quality of each communication path;

[0010] Step 3: Build a path transmission quality model based on a machine learning algorithm, input the transmission effectiveness and transmission success rate of each communication path as a training set, and use the transmission quality of the timestamp corresponding to the path as a label to train the path transmission quality model;

[0011] Step 4: Collect the current environmental parameters in real time, obtain the transmission quality of each communication path at the current moment through the path transmission quality model, perform dynamic path selection based on the multi-objective optimization algorithm, calculate the comprehensive score of each communication path, and confirm the best path;

[0012] Step 5: Determine the current communication environment, determine the communication mode, and establish a communication channel on the selected optimal path;

[0013] Step 6: Monitor the transmission quality of the current communication path in real time. If the current transmission quality is lower than the set threshold, update the path selection and communication mode.

[0014] Furthermore, the specific logic for obtaining the transmission validity of each sensor is as follows:

[0015] Water flow sensors, temperature sensors and turbidity sensors are installed at each sensor network node. The mean value of the environmental parameters collected by the environmental sensors of each node is calibrated as the environmental parameters of the communication path. The water flow velocity, water temperature and water turbidity at the moment are ,The formula for obtaining the transmission validity of the communication path of the underwater sensor network node is:

[0016] ;

[0017] in, for Moment The transmission effectiveness of each path, for Moment The turbidity of the path, for Moment The water temperature of the path, is the optimal value of temperature, and is the environmental impact coefficient, ,and .

[0018] Furthermore, the specific logic for obtaining the transmission quality of the path where each node sensor is located is:

[0019] The success rate of each communication path is the percentage of the amount of data successfully received on each communication path to the total amount of data sent. The formula for obtaining the success rate of each communication path is:

[0020] ;

[0021] in, for Moment The transmission success rate of each path, for Moment The amount of data successfully received by the path, Easy maintenance Moment The total amount of data sent by the path;

[0022] The transmission quality of each communication path is calculated based on the formula:

[0023] ;

[0024] in, for Moment The transmission quality of each path, is the weight coefficient, ,and .

[0025] Furthermore, the specific logic for constructing the path transmission quality model is as follows:

[0026] The environmental parameters, the amount of data successfully received and the total amount of data sent on each communication path are obtained, and the transmission effectiveness and transmission success rate of each communication path are calculated. The transmission effectiveness, transmission success rate and transmission quality of the corresponding timestamp of each communication path are used to generate a sample data set. The sample data set is divided into a training set and a test set with a division ratio of 7:3. The transmission effectiveness and transmission success rate of each communication path are input, and the transmission quality of the path corresponding to the timestamp is used as the label. The reinforcement learning method is used to implement the training set and the test set. The algorithm trains the path transmission quality model, and then inputs the trained path transmission quality model into the test set for testing. The change in value is used to evaluate the indicator. Change value When , it indicates that the path transmission quality model training is completed.

[0027] Furthermore, the specific logic for determining the best path is as follows:

[0028] By analyzing the current environmental parameters, inputting the transmission effectiveness and transmission success rate of each communication path at the current moment, the transmission quality of each communication path at the current moment is obtained, and the comprehensive score of each communication path at the current moment is calculated. The formula for calculating the comprehensive score of each communication path is:

[0029] ;

[0030] in, For the current moment The overall score of the paths, is the output of the model at the current moment. The transmission quality of each path, For the current moment The energy consumption of each path is expressed in , is the weight factor;

[0031] The comprehensive scores of each communication path are sorted, and the communication path with the highest comprehensive score is selected as the best communication path at the current moment.

[0032] Furthermore, the specific logic for determining the current communication mode is:

[0033] The current communication environment is judged. If the current water flow velocity is greater than the preset water flow velocity threshold, acoustic communication is selected. If the current water turbidity is less than the preset water turbidity threshold and the water temperature is within If the above conditions are not met, choose optical communication. If the above conditions are not met, choose radio communication. After determining the communication mode, establish a communication channel on the selected optimal path. is the minimum water temperature threshold, The maximum water temperature threshold.

[0034] Furthermore, the specific logic for determining the current communication status is:

[0035] The transmission quality of each communication path is monitored in real time. If the current transmission quality is lower than the preset transmission quality threshold, steps 4 to 5 are re-executed to update the path selection and communication mode.

[0036] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0037] The present invention combines the underwater water flow velocity, water temperature and water turbidity to analyze and determine the communication path, significantly improving the communication path selection efficiency and transmission quality of the underwater sensor network. By adjusting the path selection in real time and adopting a suitable communication mode, the transmission efficiency and reliability of the network are maximized. In addition, the combination of dynamic path selection and multi-mode communication enables the underwater sensor network to maintain a high communication quality under different environmental conditions. This innovative step not only improves the performance of the overall solution, but also provides strong support for the sustainable development and application expansion of underwater communications, and promotes the advancement and industrial application of related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0039] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0040] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0041] Example:

[0042] See also Figure 1 The present invention provides a method for selecting a communication path for an underwater sensor network node, the specific steps of which include:

[0043] Step 1: deploy environmental sensors on each node of the underwater sensor communication network to collect environmental parameters, analyze the collected environmental parameters, and obtain the transmission effectiveness of each communication path of the underwater sensor network node, wherein the environmental parameters include water flow velocity, water temperature, and water turbidity;

[0044] In this embodiment, the specific logic for obtaining the transmission validity of each sensor is as follows:

[0045] Along the flow direction, from the water inlet to the water outlet, a sensor network node is marked every 100 meters, and each tributary intersection is also marked as a sensor network node. A water flow sensor, a temperature sensor, and a turbidity sensor are installed at each sensor network node. The mean value of the environmental parameters collected by the environmental sensors of each node is calibrated as the environmental parameters of the communication path. The water flow velocity, water temperature and water turbidity at the moment are ,The formula for obtaining the transmission validity of the communication path of the underwater sensor network node is:

[0046] ;

[0047] in, for Moment The transmission effectiveness of each path, for Moment The turbidity of the path, for Moment The water temperature of the path, is the optimal value of temperature, and is the environmental impact coefficient, ,and .

[0048] In the communication path selection method for underwater sensor network nodes, monitoring water flow velocity, water temperature and water turbidity is of great significance. Water flow velocity directly affects the quality and stability of signal propagation. Strong water flow may cause signal attenuation or interference, thus affecting the success rate of data transmission. Real-time monitoring of water flow velocity can help identify which paths are more reliable at specific flow rates, thereby optimizing communication paths. Water temperature affects underwater sound speed and signal propagation characteristics. At different temperatures, the propagation speed and attenuation characteristics of sound waves will be different, which may cause signal delay or distortion. By monitoring water temperature, the transmission quality of the signal can be more accurately predicted, and the best path can be selected. The turbidity of the water body affects the propagation of light and sound waves. Higher turbidity may cause stronger signal attenuation and noise interference. Monitoring water turbidity helps to assess the clarity of the environment, thereby judging the reliability of signal transmission.

[0049] This formula effectively evaluates the effectiveness of each path in the underwater sensor, thereby giving priority to paths with high effectiveness when selecting paths. When the water turbidity increases, the effectiveness of the path will decrease because high turbidity will increase signal attenuation and interference, thereby reducing communication quality; when the water temperature deviates from the optimal temperature, the difference between the water temperature and the optimal temperature becomes larger, thereby reducing the effectiveness of the path. Deviating from the optimal temperature will cause changes in the speed of sound and distortion of signal propagation, further reducing the effectiveness.

[0050] The optimal temperature here is the water temperature of the path with the highest transmission quality in historical data. In many practical applications, the turbidity of water often has a more direct and obvious impact on transmission effectiveness than temperature changes, so the environmental impact coefficient is set It is reasonable. This constraint ensures that transmission effectiveness is a normalized metric, ensuring that the total contribution of the weighted combination of the two factors is 100%.

[0051] Step 2: Obtain the amount of data successfully received and the total amount of data sent by each communication path from historical data, calculate the transmission success rate of each communication path in the underwater sensor communication network, analyze the transmission success rate of each communication path and the transmission effectiveness of the underwater sensor network, and obtain the transmission quality of each communication path;

[0052] In this embodiment, the specific logic for obtaining the transmission quality of the path where each node sensor is located is:

[0053] The success rate of each communication path is the percentage of the amount of data successfully received on each communication path to the total amount of data sent. The formula for obtaining the success rate of each communication path is:

[0054] ;

[0055] in, for Moment The transmission success rate of each path, for Moment The amount of data successfully received by the path, Easy maintenance Moment The total amount of data sent by the path;

[0056] The transmission quality of each communication path is calculated based on the formula:

[0057] ;

[0058] in, for Moment The transmission quality of each path, is the weight coefficient, ,and .

[0059] The success rate of each communication path is defined by the ratio of the amount of data successfully received to the amount of data sent. When the amount of data successfully received increases (assuming the amount sent remains unchanged), the success rate will increase, and the transmission quality of the path will also increase. Conversely, if the amount of data received decreases and the success rate decreases, the transmission quality of the path will also decrease. If the effectiveness of the path increases, it means that the environmental conditions for signal propagation on the path are better, such as lower turbidity and water temperature closer to the optimal, which will lead to an increase in the success rate and thus improve the overall transmission quality. Similarly, if the effectiveness of the path decreases, the transmission quality will also decrease accordingly. Description of the transmission success rate Overall transmission quality The impact is greater than the transmission effectiveness This setting shows that the proportion of successfully received data is the main factor affecting the final transmission quality. The transmission success rate is a quantitative direct indicator that can truly reflect the actual situation of data transmission. Even if the environmental factors are good, if the successful acceptance rate is low, the transmission quality will naturally be seriously affected, so it is logical to give it a higher weight. Compared with the transmission effectiveness, the successful reception rate may be more sensitive to changes. For example, in some cases, even if the environmental conditions are good, if the data loss rate is high, the transmission quality of the entire system will be impaired. Therefore, emphasizing the impact of the transmission success rate helps to prioritize the actual reception situation in data transmission. By putting and The sum of is limited to 1 to ensure that the two weight coefficients are within a standardized range. This makes the weight represented by each coefficient easier to understand and compare.

[0060] Step 3: Build a path transmission quality model based on a machine learning algorithm, input the transmission effectiveness and transmission success rate of each communication path as a training set, and use the transmission quality of the timestamp corresponding to the path as a label to train the path transmission quality model;

[0061] In this embodiment, the specific logic for constructing the path transmission quality model is:

[0062] The environmental parameters, the amount of data successfully received and the total amount of data sent on each communication path are obtained, and the transmission effectiveness and transmission success rate of each communication path are calculated. The transmission effectiveness, transmission success rate and transmission quality of the corresponding timestamp of each communication path are used to generate a sample data set. The sample data set is divided into a training set and a test set with a division ratio of 7:3. The transmission effectiveness and transmission success rate of each communication path are input, and the transmission quality of the path corresponding to the timestamp is used as the label. The reinforcement learning method is used to implement the training set and the test set. The algorithm trains the path transmission quality model, and then inputs the trained path transmission quality model into the test set for testing. The change in value is used to evaluate the indicator. Change value When , it indicates that the path transmission quality model training is completed.

[0063] It is a reinforcement learning algorithm suitable for scenarios that require learning through trial and error. In path transmission quality optimization, the system may need to learn the best strategy in a complex and dynamic environment. To effectively deal with this situation, Change value This is a smaller threshold, suitable for tasks with higher accuracy requirements. When the set threshold is reached, it is considered that the value has converged and a higher accuracy rate can be achieved for prediction. Therefore, the model training is considered complete at this time.

[0064] Step 4: Collect the current environmental parameters in real time, obtain the transmission quality of each communication path at the current moment through the path transmission quality model, perform dynamic path selection based on the multi-objective optimization algorithm, calculate the comprehensive score of each communication path, and confirm the best path;

[0065] In this embodiment, the specific logic for determining the best path is:

[0066] By analyzing the current environmental parameters, inputting the transmission effectiveness and transmission success rate of each communication path at the current moment, the transmission quality of each communication path at the current moment is obtained, and the comprehensive score of each communication path at the current moment is calculated. The formula for calculating the comprehensive score of each communication path is:

[0067] ;

[0068] in, For the current moment The overall score of the paths, is the output of the model at the current moment. The transmission quality of each path, For the current moment The energy consumption of each path is expressed in , is the weight factor;

[0069] The comprehensive scores of each communication path are sorted, and the communication path with the highest comprehensive score is selected as the best communication path at the current moment.

[0070] The comprehensive score takes into account both the transmission quality and energy consumption of the path. Focusing only on the transmission quality may lead to the selection of a high-energy-consuming path. Although it can provide better services in the short term, it may lead to resource exhaustion in the long run. Considering energy consumption can help establish a more comprehensive path evaluation standard so that the final selected path achieves a good balance between performance and resource utilization. When the transmission quality of the path improves, the comprehensive score of the path also increases. Conversely, if the transmission quality of the path decreases, the comprehensive score of the path decreases. As energy consumption increases, the lower the comprehensive score, the energy consumption and the comprehensive score show an inverse relationship.

[0071] Step 5: Determine the current communication environment, determine the communication mode, and establish a communication channel on the selected optimal path;

[0072] In this embodiment, the specific logic for determining the current communication mode is:

[0073] The current communication environment is judged. If the current water flow velocity is greater than the preset water flow velocity threshold, acoustic communication is selected. If the current water turbidity is less than the preset water turbidity threshold and the water temperature is within If the above conditions are not met, choose optical communication. If the above conditions are not met, choose radio communication. After determining the communication mode, establish a communication channel on the selected optimal path. is the minimum water temperature threshold, The maximum water temperature threshold.

[0074] Choosing the appropriate communication mode according to environmental conditions can maximize the stability and reliability of the signal. The water flow rate directly affects the effectiveness of acoustic communication. When the water flow rate is high, the propagation of sound waves will be disturbed, which may cause signal distortion or attenuation. Therefore, it is reasonable to choose acoustic communication. Water turbidity affects the propagation of light. The light propagation distance in turbid waters is shorter, and the signal quality is difficult to guarantee. When the water turbidity is below the threshold, choosing optical communication can take advantage of better signal transmission effects. The water temperature affects the speed of sound and the refraction of the light signal. Setting the temperature range can ensure that optical communication is carried out under suitable water temperature conditions to avoid signal instability caused by temperature changes.

[0075] Step 6: Monitor the transmission quality of the current communication path in real time. If the current transmission quality is lower than the set threshold, update the path selection and communication mode.

[0076] In this embodiment, the specific logic for determining the current communication status is:

[0077] The transmission quality of each communication path is monitored in real time. If the current transmission quality is lower than the preset transmission quality threshold, steps 4 to 5 are re-executed to update the path selection and communication mode.

[0078] The communication environment may be affected by various factors, so the transmission quality of each communication path is not constant. Real-time monitoring can help adjust the path in time to avoid congestion and keep the transmission quality above the preset threshold. It can ensure the reliability and clarity of information transmission, reduce packet loss and delay, and help quickly identify faults or abnormal conditions and shorten fault recovery time.

[0079] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0080] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for selecting a communication path for an underwater sensor network node, characterized in that: The specific steps include: Step 1: deploy environmental sensors on each node of the underwater sensor communication network to collect environmental parameters, analyze the collected environmental parameters, and obtain the transmission effectiveness of each communication path of the underwater sensor network node, wherein the environmental parameters include water flow velocity, water temperature, and water turbidity; Step 2: Obtain the amount of data successfully received and the total amount of data sent by each communication path from historical data, calculate the transmission success rate of each communication path in the underwater sensor communication network, analyze the transmission success rate of each communication path and the transmission effectiveness of the underwater sensor network, and obtain the transmission quality of each communication path; Step 3: Build a path transmission quality model based on a machine learning algorithm, input the transmission effectiveness and transmission success rate of each communication path as a training set, and use the transmission quality of the timestamp corresponding to the path as a label to train the path transmission quality model; Step 4: Collect the current environmental parameters in real time, obtain the transmission quality of each communication path at the current moment through the path transmission quality model, perform dynamic path selection based on the multi-objective optimization algorithm, calculate the comprehensive score of each communication path, and confirm the best path; Step 5: Determine the current communication environment, determine the communication mode, and establish a communication channel on the selected optimal path; Step 6: Monitor the transmission quality of the current communication path in real time. If the current transmission quality is lower than the set threshold, update the path selection and communication mode.

2. A method for selecting a communication path for an underwater sensor network node according to claim 1, characterized in that: The specific logic for obtaining the transmission validity of each sensor is as follows: Water flow sensors, temperature sensors and turbidity sensors are installed at each sensor network node. The mean value of the environmental parameters collected by the environmental sensors of each node is calibrated as the environmental parameters of the communication path. The water flow velocity, water temperature and water turbidity at the moment are ,The formula for obtaining the transmission validity of the communication path of the underwater sensor network node is: ; in, for Moment The transmission effectiveness of each path, for Moment The turbidity of the path, for Moment The water temperature of the path, is the optimal value of temperature, and is the environmental impact coefficient, ,and .

3. A method for selecting a communication path for an underwater sensor network node according to claim 2, characterized in that: The specific logic for obtaining the transmission quality of the path where each node sensor is located is: The success rate of each communication path is the percentage of the amount of data successfully received on each communication path to the total amount of data sent. The formula for obtaining the success rate of each communication path is: ; in, for Moment The transmission success rate of each path, for Moment The amount of data successfully received by the path, Easy maintenance Moment The total amount of data sent by the path; The transmission quality of each communication path is calculated based on the formula: ; in, for Moment The transmission quality of each path, is the weight coefficient, ,and .

4. The method for selecting a communication path for an underwater sensor network node according to claim 3, characterized in that: The specific logic for building the path transmission quality model is as follows: The environmental parameters, the amount of data successfully received and the total amount of data sent on each communication path are obtained, and the transmission effectiveness and transmission success rate of each communication path are calculated. The transmission effectiveness, transmission success rate and transmission quality of the corresponding timestamp of each communication path are used to generate a sample data set. The sample data set is divided into a training set and a test set with a division ratio of 7:

3. The transmission effectiveness and transmission success rate of each communication path are input, and the transmission quality of the path corresponding to the timestamp is used as the label. The reinforcement learning method is used to implement the training set and the test set. The algorithm trains the path transmission quality model, and then inputs the trained path transmission quality model into the test set for testing. The change in value is used to evaluate the indicator. Change value When , it indicates that the path transmission quality model training is completed.

5. The method for selecting a communication path for an underwater sensor network node according to claim 4, characterized in that: The specific logic for determining the best path is: By analyzing the current environmental parameters, inputting the transmission effectiveness and transmission success rate of each communication path at the current moment, the transmission quality of each communication path at the current moment is obtained, and the comprehensive score of each communication path at the current moment is calculated. The formula for calculating the comprehensive score of each communication path is: ; in, For the current moment The overall score of the paths, is the output of the model at the current moment. The transmission quality of each path, For the current moment The energy consumption of each path is , is the weight factor; The comprehensive scores of each communication path are sorted, and the communication path with the highest comprehensive score is selected as the best communication path at the current moment.

6. A method for selecting a communication path for an underwater sensor network node according to claim 5, characterized in that: The specific logic for determining the current communication mode is: The current communication environment is judged. If the current water flow velocity is greater than the preset water flow velocity threshold, acoustic communication is selected. If the current water turbidity is less than the preset water turbidity threshold and the water temperature is within If the above conditions are not met, choose optical communication. If the above conditions are not met, choose radio communication. After determining the communication mode, establish a communication channel on the selected optimal path. is the minimum water temperature threshold, The maximum water temperature threshold.

7. A method for selecting a communication path for an underwater sensor network node according to claim 6, characterized in that: The specific logic for judging the current communication status is: The transmission quality of each communication path is monitored in real time. If the current transmission quality is lower than the preset transmission quality threshold, steps 4 to 5 are re-executed to update the path selection and communication mode.