Intelligent collection and analysis method and system for marine meteorological and hydrological data

Abstract

The present application relates to the technical field of data analysis, in particular to a kind of intelligent collection and analysis method and system of marine meteorological hydrographic data, comprising the following steps: S1, communication node deployment and initial configuration;S2, based on the real-time energy state and data flow load of communication node, dynamically adjust the role of communication node in multi-hop transmission network;S3, dynamic path optimization and load balancing: utilize the dynamic path optimization algorithm based on reinforcement learning, in combination with the channel quality parameter of relay node, the transmission path of data is optimized;S4, when energy collection rate is insufficient, switch to standby battery power supply;S5, the data transmitted through multi-hop transmission network is converged to central node, and meteorological and hydrographic data are analyzed by preset central processing unit.The present application ensures the reliability and load balancing of data transmission path, effectively avoids single node overload and network bottleneck, and improves the overall network operation efficiency.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a method and system for intelligently collecting and analyzing marine meteorological and hydrological data. Background Art

[0002] Real-time monitoring of the marine meteorological and hydrological environment plays an important role in extreme weather forecasting, marine ecological protection, and resource management. It usually requires the collection of multi-dimensional data such as wind speed, wind direction, air temperature, humidity, current speed, seawater temperature, and salinity. However, traditional data collection mainly relies on a single node or wired network. Due to limitations in energy consumption, channel quality, and transmission range, it is difficult to achieve long-term, wide-coverage, and stable data collection and transmission.

[0003] Existing technologies have the following shortcomings: First, node energy is limited, which can easily lead to link interruptions and monitoring blind spots; second, data transmission is affected by high packet loss rates and signal attenuation, making it difficult to maintain link stability; third, there is a lack of dynamic path optimization and load balancing strategies, resulting in low network efficiency. Therefore, a comprehensive solution that integrates energy management, transmission optimization, and intelligent data analysis is urgently needed to improve the reliability and efficiency of the monitoring network. Summary of the Invention

[0004] The present invention provides a method and system for intelligent collection and analysis of marine meteorological and hydrological data.

[0005] A method for intelligently collecting and analyzing marine meteorological and hydrological data comprises the following steps:

[0006] S1, communication node deployment and initial configuration: multiple communication nodes are distributed in the target sea area, each of which is integrated with a meteorological sensor and a hydrological sensor; the communication nodes form a multi-hop transmission network through ad hoc networking. The meteorological sensor collects wind speed, wind direction, air temperature, and humidity, while the hydrological sensor collects ocean current speed, seawater temperature, and salinity;

[0007] S2, energy perception and role allocation of relay nodes: based on the real-time energy status of communication nodes (such as remaining energy, power collection rate) and data traffic load, dynamically adjust the role of communication nodes in the multi-hop transmission network, where;

[0008] High-energy nodes are preferentially assigned as relay nodes, responsible for receiving and forwarding data;

[0009] Low-energy nodes are dynamically adjusted to terminal nodes, responsible only for local data collection and transmission;

[0010] S3, Dynamic Path Optimization and Load Balancing: Utilizes a dynamic path optimization algorithm based on reinforcement learning, combined with the channel quality parameters of relay nodes, to optimize data transmission paths. A data load balancing strategy distributes the tasks of relay nodes, extending the overall network uptime.

[0011] S4, energy compensation and recovery mechanism for multi-hop transmission: For data links interrupted due to energy exhaustion of some relay nodes, a backup battery management system is used to compensate for the interruption. When the energy collection rate is insufficient, the backup battery is used for power supply.

[0012] S5, data collection and analysis result output: The data transmitted through the multi-hop transmission network is aggregated to the central node, and the meteorological and hydrological data are analyzed by the preset central processing unit, including extreme weather event identification and hydrological parameter change trend analysis, and the analysis report is output.

[0013] Optionally, the communication nodes in S1 form a multi-hop transmission network through a self-organizing network, specifically including:

[0014] S11, initial connection establishment: After the communication node is deployed, it sends its own unique identification and location information by broadcasting, receives broadcast information from neighboring communication nodes, and establishes an initial connection between communication nodes;

[0015] S12, communication adjacency matrix generation: each communication node calculates the signal strength between itself and the adjacent communication node based on the received adjacent communication node information, generates a communication adjacency matrix, and determines the available communication paths;

[0016] S13, dynamic routing construction: using the distributed self-organizing network algorithm, each node selects the best transmission path according to the data transmission delay parameters of the path in the communication adjacency matrix, forming a multi-hop transmission network covering the entire target sea area.

[0017] Optionally, the S2 specifically includes:

[0018] S21, energy state calculation: Each communication node N i Periodically collect its own residual energy E i and power acquisition rate Calculate the comprehensive energy state index E state,i ;

[0019] S22, data traffic load evaluation: Each communication node N i Statistics of data traffic load L processed per unit time i ;

[0020] S23, role allocation strategy: based on comprehensive energy state index E state,i and data traffic load L i, adjust the role of the communication node and define the node role weight W i , W i Represents the communication node N i The role weight, according to W i Dynamically assign node roles to values:

[0021] If W i ≥W th , node N i Assigned as a relay node, responsible for receiving and forwarding data;

[0022] If W i <W th Node N i Assigned as a terminal node, only responsible for local data collection and transmission, where W th is the role assignment threshold, which can be set to the mean of the node role weights.

[0023] Optionally, the node role weight W i : Among them, E max Indicates the maximum comprehensive energy state of all communication nodes in the network, L max It represents the maximum data traffic load of all communication nodes in the multi-hop transmission network. α and β are the weight coefficients of energy and load, respectively, satisfying α + β = 1.

[0024] Optionally, the S3 specifically includes:

[0025] S31, channel quality parameter collection and evaluation: relay node N i Periodic collection and neighboring nodes N j The channel quality parameters between them include packet loss rate P loss,ij and signal strength S ij , conduct a comprehensive evaluation of the channel quality and calculate the channel quality score R ij ;

[0026] S32, define the state, action, and reward function of reinforcement learning, where:

[0027] The state space includes: the channel quality score R of the current relay node ij , data traffic load L i , residual energy E i ;

[0028] The action space includes: selecting the next relay node for each data packet;

[0029] The reward function is designed as: Among them, R Cis the reward value, λ1, λ2, λ3 are weight coefficients, which respectively indicate that nodes with low packet loss rate, high residual energy and low load are given priority. Each relay node calculates the current reward value R through the reward function C ;

[0030] S33, dynamic path adjustment and load balancing: During data transmission, the reinforcement learning algorithm scores the real-time channel quality R ij And the reward value R C , dynamically adjust the data transmission path.

[0031] Optionally, the step S33 includes scoring the channel quality R according to the real-time channel quality score. ij And the reward value R C , comprehensive evaluation node N i The path priority is obtained, and the path weight W is obtained ij , the reinforcement learning algorithm selects the path with the highest weight W in the state space ij Next hop node N j , build the transmission path:

[0032] After each transmission, W is updated in real time according to the new channel quality parameters and node load. ij and path selection strategies.

[0033] Optionally, the channel quality score R ij Calculated as:

[0034] R ij =γ·(1-P loss,ij )+δ·S ij , where R ij is node N i and N j Channel quality score; loss,ij is the packet loss rate, ranging from [0,1], S ij is the signal strength between communication nodes, γ and δ are the weight coefficients of channel parameters.

[0035] Optionally, the S4 specifically includes:

[0036] S41, Energy status monitoring and evaluation: Each relay node N i Real-time monitoring of its remaining energy E i and power acquisition rate Calculate the energy available time T of the node availbale,i :

[0037] Among them, P avg is the average energy consumption of the communication nodes, is the energy acquisition rate, Tavailable,i is the available time of the communication node in the current energy state;

[0038] S42, energy compensation triggering: When the energy state of the node is lower than the preset energy threshold, the backup battery management system is triggered, and energy compensation is triggered.

[0039] Optionally, the S4 specifically includes:

[0040] S41, Energy status monitoring and evaluation: Each relay node N i Real-time monitoring of its remaining energy E i and power acquisition rate Calculate the energy available time T of the node available,i :

[0041] Among them, P avg is the average energy consumption of the communication nodes, is the energy acquisition rate, T available,i is the available time of the communication node in the current energy state;

[0042] S42, energy compensation triggering: When the energy state of the node is lower than the preset energy threshold, the backup battery management system is triggered, and energy compensation is triggered.

[0043] An intelligent collection and analysis system for marine meteorological and hydrological data, used to implement the above-mentioned intelligent collection and analysis method for marine meteorological and hydrological data, includes the following modules:

[0044] Communication node module: distributed in the target sea area, used to collect meteorological and hydrological data, and form a multi-hop transmission network through self-organizing network;

[0045] Role allocation module: dynamically senses the energy status and data load of communication nodes and adjusts the roles of communication nodes;

[0046] Path optimization and load balancing module: optimizes data transmission paths based on reinforcement learning algorithms and distributes relay node tasks through load balancing strategies;

[0047] Energy compensation and recovery module: uses a backup battery management system to compensate for energy-depleted relay nodes and restore links;

[0048] Data analysis and output module: Analyzes meteorological and hydrological data gathered at the central node, including identification of extreme weather events and analysis of hydrological parameter change trends.

[0049] Beneficial effects of the present invention:

[0050] The present invention deploys communication nodes in the target sea area and combines self-organizing network technology to build a multi-hop transmission network, thereby achieving efficient collection and transmission of meteorological and hydrological data. The dynamic path optimization algorithm combines the channel quality parameters and energy status of the relay nodes to ensure the reliability and load balancing of the data transmission path, effectively avoiding single-node overload and network bottlenecks, and improving the overall network operation efficiency.

[0051] The present invention monitors the remaining energy and data traffic load of communication nodes in real time, and uses an energy-aware algorithm to dynamically allocate roles, ensuring that high-energy nodes are prioritized as relay nodes to undertake data forwarding tasks, while low-energy nodes are used as terminal nodes to reduce the task burden, effectively extending the overall operation time of the network, and is particularly suitable for long-term ocean monitoring scenarios.

[0052] The present invention utilizes a reinforcement learning algorithm combined with channel quality parameters to optimize the data transmission path, and disperses relay node tasks through a load balancing strategy to avoid overloading of a single node, thereby improving the stability and efficiency of network transmission. At the same time, it significantly reduces the delay and packet loss rate in data transmission, and adopts a backup battery management system to compensate for energy-depleted nodes to ensure the continuity of the data link. At the same time, it dynamically switches the power supply mode and routing path to quickly bypass failed nodes, thereby enhancing the network's self-healing ability and reliability, and ensuring the continuity of data collection and transmission in harsh marine environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 Schematic diagram of a method according to an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of dynamic path optimization and load balancing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0057] It should be noted that references in the specification to "one embodiment," "an embodiment," "an exemplary embodiment," "some embodiments," etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not every embodiment necessarily includes such specific features, structures, or characteristics. In addition, when specific features, structures, or characteristics are described in conjunction with an embodiment, it is within the knowledge of persons skilled in the relevant art to implement such features, structures, or characteristics in conjunction with other embodiments (whether or not explicitly described).

[0058] In general, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending at least in part on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0059] like Figure 1-Figure 2 As shown, a method for intelligent collection and analysis of marine meteorological and hydrological data includes the following steps:

[0060] S1, communication node deployment and initial configuration: multiple communication nodes are distributed in the target sea area, each of which is integrated with meteorological sensors and hydrological sensors; the communication nodes form a multi-hop transmission network through self-organizing networks, meteorological sensors collect wind speed, wind direction, temperature, and humidity, and hydrological sensors collect ocean current speed, seawater temperature, and salinity;

[0061] S2, energy perception and role allocation of relay nodes: based on the real-time energy status of communication nodes (such as remaining energy, power collection rate) and data traffic load, dynamically adjust the role of communication nodes in the multi-hop transmission network, where;

[0062] High-energy nodes are preferentially assigned as relay nodes, responsible for receiving and forwarding data;

[0063] Low-energy nodes are dynamically adjusted to terminal nodes, responsible only for local data collection and transmission;

[0064] S3, Dynamic Path Optimization and Load Balancing: Utilizes a dynamic path optimization algorithm based on reinforcement learning, combined with the channel quality parameters of relay nodes, to optimize data transmission paths. A data load balancing strategy distributes the tasks of relay nodes, extending the overall network uptime.

[0065] S4, energy compensation and recovery mechanism for multi-hop transmission: For data links interrupted due to energy exhaustion of some relay nodes, a backup battery management system is used to compensate for the interruption. When the energy collection rate is insufficient, the backup battery is used for power supply.

[0066] S5, data collection and analysis result output: The data transmitted through the multi-hop transmission network is aggregated to the central node, and the meteorological and hydrological data are analyzed by the preset central processing unit, including extreme weather event identification and hydrological parameter change trend analysis, and the analysis report is output.

[0067] The communication nodes in S1 form a multi-hop transmission network through self-organizing networks, which specifically includes:

[0068] S11, initial connection establishment: After the communication node is deployed, it sends its own unique identification and location information by broadcasting, receives broadcast information from neighboring communication nodes, and establishes an initial connection between communication nodes;

[0069] S12, communication adjacency matrix generation: each communication node calculates the signal strength between itself and the adjacent communication node based on the received adjacent communication node information, generates a communication adjacency matrix, and determines the available communication paths;

[0070] The signal strength S between communication nodes ij :S ij =P t -L ij , where S ij Represents node N i and N j The signal strength between t is node N i The transmission power, L ij Represents node N i to N j The path loss is calculated as:

[0071] L ij =20log 10 (d ij )+α, where α is the environmental factor, d ij Indicates the geographical distance between two nodes, which depends on the signal propagation environment of the target sea area (such as open water or sea area with many obstacles);

[0072] Generate the communication adjacency matrix A = [a ij ],in: Among them, S th is the threshold of signal strength, and the node pairs that meet the threshold condition are considered as available communication paths.

[0073] S13, dynamic routing construction: using the distributed self-organizing network algorithm, each node selects the best transmission path according to the data transmission delay parameters of the path in the communication adjacency matrix, forming a multi-hop transmission network covering the entire target sea area.

[0074] Using the communication adjacency matrix A and path delay parameter Dij Construct a transmission path, where: Among them, D ij is the communication node N i to N j The path delay, v c is the propagation speed of the signal in the transmission medium, T p is node N j The processing delay, which represents the time it takes for a node to process a data packet, is based on the path delay parameter D ij ,The shortest path method is used to select the transmission path, forming a multi-hop transmission network covering the entire target sea area.

[0075] S2 specifically includes:

[0076] S21, energy state calculation: Each communication node N i Periodically collect its own residual energy E i and power acquisition rate Calculate the comprehensive energy state index E state,i :

[0077] Among them, E i Represents the communication node N i The current remaining energy, Represents the communication node N i The electric energy acquisition rate, T represents the time interval of the prediction cycle;

[0078] S22, data traffic load evaluation: Each communication node N i Statistics of data traffic load L processed per unit time i :

[0079] Among them, L i Represents node N i Data traffic load, Q ij Represents node N i From the neighboring node N j The amount of data received, n represents the number of nodes N i The total number of connected neighboring nodes;

[0080] S23, role allocation strategy: based on comprehensive energy state index E state,i and data traffic load L i , adjust the role of the communication node and define the node role weight W i , W i Represents the communication node N i The role weight, according to W i Dynamically assign node roles to values:

[0081] If W i ≥W th , node N i Assigned as a relay node, responsible for receiving and forwarding data;

[0082] If W i <W th Node N i Assigned as a terminal node, only responsible for local data collection and transmission, where W th is the role assignment threshold, which can be set to the mean of the node role weights.

[0083] Node role weight W i : Among them, E max Indicates the maximum comprehensive energy state of all communication nodes in the network, L max It represents the maximum data traffic load of all communication nodes in the multi-hop transmission network. α and β are the weight coefficients of energy and load, respectively, satisfying α + β = 1; α = 0.7, β = 0.3.

[0084] S3 specifically includes:

[0085] S31, channel quality parameter collection and evaluation: relay node N i Periodic collection and neighboring nodes N j The channel quality parameters between them include packet loss rate P loss,ij and signal strength S ij , conduct a comprehensive evaluation of the channel quality and calculate the channel quality score R ij ;

[0086] S32, define the state, action, and reward function of reinforcement learning, where:

[0087] The state space includes: the channel quality score R of the current relay node ij , data traffic load L i , residual energy E i ;

[0088] The action space includes: selecting the next relay node for each data packet;

[0089] The reward function is designed as: Among them, R C is the reward value, λ1, λ2, λ3 are weight coefficients, λ1 = 0.4, λ2 = 0.3, λ3 = 0.3, respectively indicating that nodes with low packet loss rate, high residual energy and low load are given priority. Each relay node calculates the current reward value R through the reward function C ;

[0090] S33, dynamic path adjustment and load balancing: During data transmission, the reinforcement learning algorithm scores the real-time channel quality R ij And the reward value R C , dynamically adjust the data transmission path.

[0091] S33 includes scoring R according to the real-time channel quality ij And the reward value R C , comprehensive evaluation node N i The path priority is obtained, and the path weight W is obtained ij :

[0092] W ij =R C +R ij , where W ij Represents slave node N i To node N j The reinforcement learning algorithm selects the path with the highest weight W in the state space. ij Next hop node N j , build the transmission path:

[0093] After each transmission, W is updated in real time according to the new channel quality parameters and node load. ij and path selection strategies.

[0094] After each transmission is completed, the reward value R is calculated based on the transmission result. C Conduct feedback updates to further optimize the path selection strategy.

[0095] Channel quality score R ij Calculated as:

[0096] R ij =γ·(1-P loss,ij )+δ·S ij , where R ij is node N i and N j Channel quality score; loss,ij is the packet loss rate, ranging from [0,1], S ij is the signal strength between communication nodes, γ, δ are the weight coefficients of channel parameters, γ = 0.5, δ = 0.5.

[0097] S4 specifically includes:

[0098] S41, Energy status monitoring and evaluation: Each relay node N i Real-time monitoring of its remaining energy E i and power acquisition rate Calculate the energy available time T of the node available,i :

[0099] Among them, P avg is the average energy consumption of the communication nodes, is the energy acquisition rate, T available,i is the available time of the communication node in the current energy state;

[0100] S42, energy compensation triggering: When the energy state of the node is lower than the preset energy threshold, the backup battery management system is triggered. When energy compensation is triggered, the backup battery management system automatically completes the following operations:

[0101] a) Switch to backup battery power: Switch the node power supply mode from energy harvesting to backup battery power, optimize the battery discharge strategy, limit power supply to non-critical tasks, and support only data forwarding and link maintenance.

[0102] b) Dynamically adjust node load: reduce the node's transmission power and communication frequency to extend the use time of the backup battery.

[0103] S4 specifically includes:

[0104] S41, Energy status monitoring and evaluation: Each relay node N i Real-time monitoring of its remaining energy E i and power acquisition rate Calculate the energy available time T of the node available,i :

[0105] Among them, P avg is the average energy consumption of the communication nodes, is the energy acquisition rate, T available,i is the available time of the communication node in the current energy state;

[0106] S42, energy compensation triggering: When the energy state of the node is lower than the preset energy threshold, the backup battery management system is triggered. When energy compensation is triggered, the backup battery management system automatically completes the following operations:

[0107] a) Switch to backup battery power: Switch the node power supply mode from energy harvesting to backup battery power, optimize the battery discharge strategy, limit power supply to non-critical tasks, and support only data forwarding and link maintenance.

[0108] b) Dynamically adjust node load: reduce the node's transmission power and communication frequency to extend the use time of the backup battery.

[0109] An intelligent collection and analysis system for marine meteorological and hydrological data, used to implement the above-mentioned intelligent collection and analysis method for marine meteorological and hydrological data, includes the following modules:

[0110] Communication node module: distributed in the target sea area, used to collect meteorological and hydrological data, and form a multi-hop transmission network through self-organizing network;

[0111] Role allocation module: dynamically senses the energy status and data load of communication nodes and adjusts the roles of communication nodes;

[0112] Path optimization and load balancing module: optimizes data transmission paths based on reinforcement learning algorithms and distributes relay node tasks through load balancing strategies;

[0113] Energy compensation and recovery module: uses a backup battery management system to compensate for energy-depleted relay nodes and restore links;

[0114] Data analysis and output module: Analyzes meteorological and hydrological data gathered at the central node, including identification of extreme weather events and analysis of hydrological parameter change trends.

[0115] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0116] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for intelligent collection and analysis of marine meteorological and hydrological data, characterized in that: The following steps are involved: S1, communication node deployment and initial configuration: multiple communication nodes are distributed in the target sea area, and each communication node is integrated with meteorological sensors and hydrological sensors; The communication nodes form a multi-hop transmission network through self-organizing networks. The meteorological sensors collect wind speed, wind direction, air temperature, and humidity. The hydrological sensors collect ocean current speed, seawater temperature, and salinity. S2, energy perception and role allocation of relay nodes: based on the real-time energy status and data traffic load of communication nodes, dynamically adjust the roles of communication nodes in the multi-hop transmission network, where; High-energy nodes are preferentially assigned as relay nodes, responsible for receiving and forwarding data; Low-energy nodes are dynamically adjusted to terminal nodes, responsible only for local data collection and transmission; S3, Dynamic Path Optimization and Load Balancing: Utilizes a dynamic path optimization algorithm based on reinforcement learning, combined with the channel quality parameters of relay nodes, to optimize data transmission paths. A data load balancing strategy distributes the tasks of relay nodes, extending the overall network uptime. S4, energy compensation and recovery mechanism for multi-hop transmission: For data links interrupted due to energy exhaustion of some relay nodes, a backup battery management system is used to compensate for the interruption. When the energy collection rate is insufficient, the backup battery is used for power supply. S5, data collection and analysis result output: The data transmitted through the multi-hop transmission network is aggregated to the central node, and the meteorological and hydrological data are analyzed by the preset central processing unit, including extreme weather event identification and hydrological parameter change trend analysis, and the analysis report is output.

2. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 1, characterized in that: The communication nodes in S1 form a multi-hop transmission network through self-organizing networks, specifically including: S11, initial connection establishment: After the communication node is deployed, it sends its own unique identification and location information by broadcasting, receives broadcast information from neighboring communication nodes, and establishes an initial connection between communication nodes; S12, communication adjacency matrix generation: each communication node calculates the signal strength between itself and the adjacent communication node based on the received adjacent communication node information, generates a communication adjacency matrix, and determines the available communication paths; S13, dynamic routing construction: using the distributed self-organizing network algorithm, each node selects the best transmission path according to the data transmission delay parameters of the path in the communication adjacency matrix, forming a multi-hop transmission network covering the entire target sea area.

3. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 1, characterized in that: The S2 specifically includes: S21, energy state calculation: Each communication node N i Periodically collect its own residual energy E i and power acquisition rate Calculate the comprehensive energy state index E state,i ; S22, data traffic load evaluation: Each communication node N i Statistics of data traffic load L processed per unit time i ; S23, role allocation strategy: based on comprehensive energy state index E state,i and data traffic load L i , adjust the role of the communication node and define the node role weight W i , W i Represents the communication node N i The role weight, according to W i Dynamically assign node roles to values: If W i ≥W th , node N i Assigned as a relay node, responsible for receiving and forwarding data; If W i <W th Node N i Assigned as a terminal node, only responsible for local data collection and transmission, where W th is the role assignment threshold.

4. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 3, characterized in that: The node role weight W i : Among them, E max Indicates the maximum comprehensive energy state of all communication nodes in the network, L max It represents the maximum data traffic load of all communication nodes in the multi-hop transmission network. α and β are the weight coefficients of energy and load, respectively, satisfying α + β = 1.

5. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 3, characterized in that: The S3 specifically includes: S31, channel quality parameter collection and evaluation: relay node N i Periodic collection and neighboring nodes N j The channel quality parameters between them include packet loss rate P loss,ij and signal strength S ij , conduct a comprehensive evaluation of the channel quality and calculate the channel quality score R ij ; S32, define the state, action, and reward function of reinforcement learning, where: The state space includes: the channel quality score R of the current relay node ij , data traffic load L i , residual energy E i ; The action space includes: selecting the next relay node for each data packet; The reward function is designed as: Among them, Rc is the reward value, λ1, λ2, λ3 are weight coefficients, which respectively indicate the priority given to nodes with low packet loss rate, high residual energy and low load. Each relay node calculates the current reward value Rc through the reward function; S33, dynamic path adjustment and load balancing: During data transmission, the reinforcement learning algorithm scores the real-time channel quality R ij And the reward value Rc, dynamically adjust the data transmission path.

6. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 5, characterized in that: S33 includes scoring the channel quality R in real time. ij And reward value Rc, comprehensive evaluation node N i The path priority is obtained, and the path weight W is obtained ij : The reinforcement learning algorithm selects the path with the highest weight W in the state space ij Next hop node N j , build the transmission path: After each transmission, W is updated in real time according to the new channel quality parameters and node load. ij and path selection strategies.

7. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 6, characterized in that: The channel quality score R ij Calculated as: R ij =γ·(1-P loss,ij )+δ·S ij , where R ij is node N i and N j Channel quality score; loss,ij is the packet loss rate, ranging from [0,1], S ij is the signal strength between communication nodes, γ and δ are the weight coefficients of channel parameters.

8. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 1, characterized in that: The S4 specifically includes: S41, Energy status monitoring and evaluation: Each relay node N i Real-time monitoring of its remaining energy E i and power acquisition rate Calculate the energy available time T of the node available,i : Among them, P avg is the average energy consumption of the communication nodes, is the energy acquisition rate, T available,i is the available time of the communication node in the current energy state; S42, energy compensation triggering: When the energy state of the node is lower than the preset energy threshold, the backup battery management system is triggered, and energy compensation is triggered.

9. The method for intelligent collection and analysis of marine meteorological and hydrological data according to claim 1, characterized in that: The S5 specifically includes: S51, data preprocessing: preprocessing the meteorological and hydrological raw data gathered at the central node, including data format conversion, unifying the output data formats of different sensors into a standard data format; S52, Extreme Weather Event Identification: Use threshold method to identify extreme weather events, including: a) Extract characteristic parameters from preprocessed meteorological data, including wind speed, temperature, and humidity; b) Threshold determination: Compare characteristic parameters with preset extreme weather thresholds to identify whether there are events outside the normal range; S53, Hydrological Parameter Trend Analysis: Use time series analysis and statistical modeling methods to conduct trend analysis of key hydrological parameters, including: a) Parameter selection: Select current velocity, seawater temperature and salinity parameters; b) Time series modeling: using the moving average model to predict the changing trends of hydrological parameters; c) Abnormal fluctuation detection: Identify abnormal parameter fluctuations through rate of change calculation.

10. An intelligent collection and analysis system for marine meteorological and hydrological data, used to implement the intelligent collection and analysis method for marine meteorological and hydrological data according to any one of claims 1 to 9, characterized in that: Includes the following modules: Communication node module: distributed in the target sea area, used to collect meteorological and hydrological data, and form a multi-hop transmission network through self-organizing network; Role allocation module: dynamically senses the energy status and data load of communication nodes and adjusts the roles of communication nodes; Path optimization and load balancing module: optimizes data transmission paths based on reinforcement learning algorithms and distributes relay node tasks through load balancing strategies; Energy compensation and recovery module: uses a backup battery management system to compensate for energy-depleted relay nodes and restore links; Data analysis and output module: Analyzes meteorological and hydrological data gathered at the central node, including identification of extreme weather events and analysis of hydrological parameter change trends.

Images