Wireless communication method and device for underwater lamp

Abstract

The invention provides a wireless communication method and device for an underwater lamp. The method comprises the following steps: constructing an underwater communication environment model according to an underwater communication environment; generating an optimal communication strategy according to the model parameters of the underwater communication environment model; based on underwater environment data monitored in real time, an optimal communication frequency band and transmitting power are selected through an optimal communication strategy; and performing adaptive control on the light of the underwater lamp according to the optimal communication frequency band and the transmitting power. Through the implementation of the scheme of the invention, communication parameters are dynamically adjusted based on underwater communication environment modeling and reinforcement learning optimization of a communication strategy in combination with real-time monitoring data, so that the problems of fixed channel selection and power control and lack of environment adaptivity in traditional underwater lamp wireless communication are solved, the communication stability is enhanced, and the communication efficiency is improved. And the remote controllability and effectiveness of the underwater lamp in a complex underwater environment are ensured.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular, to a wireless communication method and apparatus for underwater lamps. Background Art

[0002] In underwater lighting and communication systems, traditional underwater lamp control methods usually rely on wired communication or wireless communication methods with fixed parameters. However, the complexity of the underwater environment, including severe signal attenuation, multipath effects, environmental noise interference, etc., makes traditional wireless communication methods face greater stability problems in the application of underwater lamps. In addition, in the prior art, underwater wireless communication usually uses fixed frequency bands and preset transmission powers, lacking the ability to adaptively adjust to dynamic environmental changes, resulting in unstable communication quality and even communication interruptions under different underwater environmental conditions. Especially in deep water, high turbidity or strong interference environments, traditional communication methods are difficult to ensure the reliability of remote control, affecting the normal operation of underwater lamps. Summary of the Invention

[0003] The present application provides a wireless communication method and apparatus for underwater lamps, which are used to solve the problem that it is difficult to ensure the reliability of remote control of underwater lamps in complex environments in related technologies.

[0004] In a first aspect of the present application, a wireless communication method for underwater lamps is provided. The wireless communication method for underwater lamps includes: Constructing an underwater communication environment model according to the underwater communication environment; Generating an optimal communication strategy according to the model parameters of the underwater communication environment model; Based on the underwater environment data monitored in real time, selecting an optimal communication frequency band and transmission power through the optimal communication strategy; Adaptive control of the light of the underwater lamp according to the optimal communication frequency band and the transmission power.

[0005] Optionally, in a first implementation manner of the first aspect of the present application, the step of constructing an underwater communication environment model according to the underwater communication environment includes: Obtaining a channel attenuation coefficient according to the underwater signal propagation path, and determining initial channel characteristic data in combination with ray tracing; Obtaining channel state parameters under different interference conditions by analyzing the initial channel characteristic data; Generating channel state prediction data by analyzing the channel state parameters and the channel change trend through time series; Constructing an underwater communication environment model according to the channel state prediction data.

[0006] Optionally, in the second implementation manner of the first aspect of the present application, the step of generating an optimal communication strategy according to the model parameters of the underwater communication environment model includes: Determine a set of key variables for optimizing underwater communication according to the model parameters of the underwater communication environment model; Construct a reinforcement learning decision framework according to the set of key variables; Generate an initial communication strategy by training the reinforcement learning decision framework; Train the initial communication strategy through a double deep Q-network to generate the optimal communication strategy for the underwater lamp.

[0007] Optionally, in the third implementation manner of the first aspect of the present application, the step of selecting an optimal communication frequency band and transmission power through the optimal communication strategy based on real-time monitored underwater environment data includes: Determine a set of channel state parameters under different environmental conditions according to the real-time monitored underwater environment data and the optimal communication strategy; Determine the current channel quality according to the set of channel state parameters and the Markov decision process, and generate a communication frequency band ranking table in combination with historical communication data; Determine the optimal communication frequency band with the highest channel quality by parsing the communication frequency band ranking table; Calculate the signal-to-noise ratio of the optimal communication frequency band at different transmission power levels through a power allocation algorithm to generate transmission power optimization parameters; Dynamically adjust the transmission power during the communication process according to the transmission power optimization parameters and the real-time communication link state data.

[0008] Optionally, in the fourth implementation manner of the first aspect of the present application, the step of adaptively controlling the light of the underwater lamp according to the optimal communication frequency band and the transmission power includes: Obtain real-time light output data and ambient light monitoring data of the underwater lamp through a built-in sensor according to the optimal communication frequency band and the transmission power to generate initial light state data; Construct a light control model according to the initial light state data; Determine the LED drive control parameters of the pulse width modulation signal according to the light control model; Output a control signal corresponding to the LED drive control parameters by performing pulse width modulation on the LED drive signal, and generate a feedback control index in combination with the communication link state data; Dynamically adjust the light brightness and color temperature of the underwater lamp by analyzing the feedback control index.

[0009] Optionally, in the fifth implementation manner of the first aspect of the present application, the method further includes: Obtain historical delay samples according to the transmission delay data of the wireless control signal; Determine the delay change trend in different communication frequency bands according to the historical delay samples and the set of channel state parameters, and generate a delay estimation model; Determine the lighting control error under different delay conditions according to the delay estimation model and the channel prediction data of the optimal communication strategy; Compensate the lighting control error according to the Smith predictor to generate a delay compensation parameter; Preprocess the wireless control instruction according to the delay compensation parameter, and generate a synchronization control signal in combination with the signal control parameter of the lighting control model; Correct the wireless control instruction according to the synchronization control signal, and update the lighting state of the underwater lamp according to the corrected wireless control instruction.

[0010] Optionally, in the sixth implementation manner of the first aspect of the present application, the method further includes: Obtain the historical operation data of the underwater lamp, and generate a lamp operation state data set in combination with the historical optimal communication strategy; Parse the lamp operation state data set to construct a remote monitoring model for the underwater lamp, and determine a set of characteristic parameters affecting the change of the lamp state; Determine the optimal sending timing of the wireless control instruction according to the set of characteristic parameters and the transmission state of the wireless control signal, and generate a wireless control instruction optimization parameter; Update the wireless control instruction according to the wireless control instruction optimization parameter.

[0011] The second aspect of the present application provides a wireless communication device for an underwater lamp, and the wireless communication device for an underwater lamp includes: A construction module, configured to construct an underwater communication environment model according to the underwater communication environment; A generation module, configured to generate an optimal communication strategy according to the model parameters of the underwater communication environment model; A selection module, configured to select an optimal communication frequency band and transmit power through the optimal communication strategy based on the underwater environment data monitored in real time; A control module, configured to adaptively control the lighting of the underwater lamp according to the optimal communication frequency band and the transmit power.

[0012] In a third aspect of the embodiments of the present application, an electronic device is provided, including a memory and a processor. The processor is configured to execute a computer program stored on the memory. When the processor executes the computer program, the steps in the wireless communication method for underwater lamps provided in the first aspect of the embodiments of the present application are implemented.

[0013] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the wireless communication method for underwater lamps provided in the first aspect of the embodiments of the present application are implemented.

[0014] In summary, according to a wireless communication method and device for underwater lamps provided by the solution of the present application, an underwater communication environment model is constructed according to the underwater communication environment; an optimal communication strategy is generated according to the model parameters of the underwater communication environment model; based on the underwater environment data monitored in real time, the optimal communication frequency band and transmission power are selected through the optimal communication strategy; and the light of the underwater lamp is adaptively controlled according to the optimal communication frequency band and the transmission power. Through the implementation of the solution of the present application, based on underwater communication environment modeling, reinforcement learning is used to optimize the communication strategy, and combined with real-time monitoring data, the communication parameters are dynamically adjusted to solve the problems of fixed channel selection and power control and lack of environmental adaptability in traditional underwater lamp wireless communication, thereby enhancing communication stability and ensuring the remote controllability and effectiveness of underwater lamps in complex underwater environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic flowchart of the wireless communication method for underwater lamps provided by the embodiments of the present application; Figure 2 It is a schematic diagram of program modules of the wireless communication device for underwater lamps provided by the embodiments of the present application; Figure 3 It is a schematic structural diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to make the objects, features, and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0017] To solve the problem that it is difficult to ensure the reliability of remote control of underwater lamps in complex environments in related technologies, an embodiment of the present application provides a wireless communication method for underwater lamps, as follows Figure 1 FIG. Figure 1 is a schematic flowchart of the wireless communication method for underwater lamps provided in this embodiment. The wireless communication method for underwater lamps includes the following steps: Step 110: Construct an underwater communication environment model according to the underwater communication environment; Specifically, the process of constructing an underwater communication environment model according to the underwater communication environment involves an in-depth analysis of the underwater channel characteristics. Since the underwater environment has a strong attenuation effect on the propagation of wireless signals, it is first necessary to obtain the relevant parameters of the underwater signal propagation path, including the channel attenuation coefficient, noise interference factors, and environmental characteristics. The ray tracing method can be used to simulate the propagation of signals under different depth, turbidity, and temperature conditions, and combined with the channel attenuation model to calculate the signal loss. By analyzing the initial channel characteristic data, the channel state parameters under different interference conditions can be determined, and based on the time series analysis method, the channel change trend can be predicted to generate the channel state prediction data for subsequent optimization. On this basis, the underwater communication environment model is constructed using the prediction data, enabling the communication strategy to be adjusted according to different environmental changes.

[0018] The step of constructing an underwater communication environment model according to the underwater communication environment includes: obtaining the channel attenuation coefficient according to the underwater signal propagation path, and determining the initial channel characteristic data in combination with ray tracing; obtaining the channel state parameters under different interference conditions by analyzing the initial channel characteristic data; generating the channel state prediction data by analyzing the channel state parameters and the channel change trend through time series analysis; constructing the underwater communication environment model according to the channel state prediction data.

[0019] Specifically, in this embodiment, when obtaining the channel attenuation coefficient according to the underwater signal propagation path, the ray tracing algorithm is used to model the transmission of optical signals or radio signals in water, and the signal loss data under different depths, temperatures, and turbidities are obtained. The energy attenuation rate on each propagation path is determined by collecting the actual water area environment data. Then, combined with the multipath propagation theory, the initial channel characteristic data are determined. At the same time, the initial channel characteristic data reflect the arrival time, amplitude, and phase information of the signals on each path in water, and its data structure can be represented in matrix form, reflecting the comprehensive influence after the signal undergoes multiple reflections, refractions, and scatterings in the underwater environment. Subsequently, the initial channel characteristic data are analyzed, and the channel state parameters under different interference conditions are extracted through frequency domain and time domain transformation methods. These parameters include signal-to-noise ratio (SNR), bit error rate (BER), and the relative delay and amplitude attenuation information of multipath components. And the data decomposition technology is used to denoise the channel characteristic data to eliminate the random interference caused by environmental noise, biological activities, and water flow disturbances. On this basis, through time series analysis of the obtained channel state parameters and channel change trends, using statistical regression and trend detection algorithms, the channel state prediction data are generated. This process takes into account the continuity of the channel state in a short time and long-term change characteristics, thereby constructing a prediction model that reflects the channel state at future moments. The key formula in this prediction model is: , where represents the predicted value of the channel state at future time , represents the channel state parameter measured at time t, is the prediction time interval, is the scale factor, is the integration time window, is the integration variable, is the damping coefficient. This formula is used to comprehensively consider the average change amount and the degree of state mutation of the recent channel state, and suppress the larger change amount through the exponential function, so as to generate the channel state parameters for future moment prediction. Finally, according to the channel state prediction data, by using the prediction data as input parameters, an underwater communication environment model is constructed. This model integrates the channel attenuation characteristics, interference distribution, and prediction state data, and can comprehensively reflect the dynamic characteristics of the channel in the underwater environment, thereby providing accurate and real-time environmental basic data for the generation of subsequent optimal communication strategies.

[0020] It should be noted that, based on the channel state prediction data, constructing an underwater communication environment model mainly involves using the prediction data as key input parameters and combining mathematical modeling methods and statistical analysis methods to comprehensively describe the dynamic characteristics of the underwater channel. First, the channel state prediction data obtained from the time series prediction process can provide the expected values of indicators such as signal-to-noise ratio, bit error rate, and signal delay within a certain period in the future. These data reflect the state change trends of the underwater channel at different time periods. Then, by selecting the key indicators from the prediction data and using multivariate statistical analysis methods, each indicator is combined according to a certain weight to construct a comprehensive parameter function describing the underwater communication environment. This function can be expressed as: , where represents the comprehensive communication environment parameter at time t, represents the i-th channel state parameter (such as signal-to-noise ratio, bit error rate, etc.), is the bias term, is the weight of each indicator, represents the amplitude of the periodic interference, is the angular frequency of the interference signal, is the phase angle. This formula is used to integrate multiple prediction indicators into a unified descriptive variable, thus facilitating the characterization of the overall change characteristics of the underwater communication environment. Subsequently, according to the change trend of the comprehensive communication environment parameter , methods such as curve fitting, nonlinear regression, or other statistical modeling methods are used to correct and optimize the parameters. Finally, a mathematical model reflecting the dynamic characteristics of the underwater channel is formed. This model includes the possible state changes of the underwater channel at future times and can provide a set of parameter values as the basic data for generating subsequent communication strategies. Finally, by comparing and verifying the mathematical model and its parameters with real-time monitoring data, it can be ensured that the constructed underwater communication environment model has the accuracy and continuity to describe environmental changes, thus providing sufficient basis for generating subsequent optimal communication strategies and providing necessary environmental description support for the wireless communication process of underwater lamps.

[0021] Step 120: Generate an optimal communication strategy according to the model parameters of the underwater communication environment model; Specifically, in the process of generating an optimal communication strategy based on the model parameters of the underwater communication environment model, it is necessary to determine the set of key variables that affect communication quality. The establishment of a reinforcement learning decision framework enables the wireless communication system to dynamically adjust communication parameters in a complex environment. The agent takes the parameters of the underwater communication environment model as input, uses the channel state data as state variables, and optimizes communication performance by adjusting actions such as communication frequency band, transmission power, and modulation method. Through the training of the reinforcement learning framework, an initial communication strategy can be generated, and the double deep Q-network is used to optimize it to obtain the optimal communication strategy. This strategy can combine real-time environmental data and dynamically adjust communication parameters to adapt to the complex and changeable underwater environment.

[0022] In an optional implementation manner of this embodiment, the steps of generating an optimal communication strategy based on the model parameters of the underwater communication environment model include: determining a set of key variables for optimizing underwater communication according to the model parameters of the underwater communication environment model; constructing a reinforcement learning decision framework according to the set of key variables; generating an initial communication strategy by training the reinforcement learning decision framework; and training the initial communication strategy through a double deep Q-network to generate the optimal communication strategy of the underwater lamp.

[0023] Specifically, in this embodiment, based on the model parameters provided by the underwater communication environment model, by statistically analyzing data such as channel attenuation, signal-to-noise ratio, interference level, time delay, and multipath effect, a set of key variables that have the greatest impact on underwater communication performance is determined. For example, the average signal-to-noise ratio, channel stability index, and interference change rate. These variables form a vector describing the environmental state after data screening and sorting, and are used as the input of the subsequent reinforcement learning decision framework. Then, a reinforcement learning decision framework is constructed based on the set of key variables, where the state is defined as a multi-dimensional vector composed of the above key variables, and the actions correspond to various adjustment options of the wireless communication parameters of the underwater lamp, including communication frequency band, transmission power, modulation method, and data packet size. The reward function evaluates the effects of each state-action pair based on factors such as communication success rate, transmission delay, and energy consumption. Subsequently, by training this decision framework on a large amount of historical and simulation data, an initial communication strategy is generated. This strategy can select corresponding communication parameters according to the current environmental state and meet the real-time decision-making requirements of underwater communication in a complex dynamic environment. Further, a double deep Q-network is used to train the initial communication strategy. This method uses two parallel deep neural networks to calculate the expected value of the current action and the value of the target action respectively, thereby reducing the bias in policy update, and obtaining a more robust communication strategy through comparison and update. In this process, a key Q-value update formula is designed, and the formula is: , where represents the expected value of taking action a in state s, T is the observation time window, represents the immediate reward obtained by taking action a at time t, is a penalty term reflecting state and action uncertainty or risk, is a regulation factor used to balance the proportion of reward and risk. This formula calculates the average return within the entire time window through integration and comprehensively considers environmental uncertainty, thereby providing a basis for updating the parameters of the double deep Q-network. For example, at a certain moment, if the signal-to-noise ratio is high and the interference is small, then the value is large, while when the channel fluctuates violently, will increase accordingly, making the overall value decrease, thereby guiding the network to select other actions to obtain better communication effects. Finally, through continuous training and iteration of the double deep Q-network, an optimal communication strategy for underwater lamps is generated. This strategy can dynamically adjust communication parameters according to real-time underwater environmental changes, thereby providing efficient and accurate control decision support for the wireless communication of underwater lamps.

[0024] It should be noted that the expression formula of the double deep Q-network is designed as: , which is used to update the value of taking action a in the current state s, where represents the immediate reward, is the discount factor, whose value ranges between 0 and 1 and is used to balance the proportion of current reward and future reward. s′ represents the next state transferred to, and represents the optimal action predicted by the main network parameters in the next state. The target network parameters are denoted as , and its role is to reduce the estimation bias in the update process. The integration interval represents averaging the expected Q value over a period of time in the future, thereby considering the fluctuations caused by time changes in the underwater communication environment. is the selected time window. The introduced exponential weight term is used to correct the expected channel reliability, where represents the channel reliability index corresponding to the selected action a′ in state s′. This index can be quantified by measuring the signal-to-noise ratio, bit error rate, etc. is the preset reliability threshold, is a regulation constant used to control the influence degree of the deviation of the actual channel reliability from the threshold on the Q value update. By integrating and normalizing the Q value within the time window, the interference of short-term noise on the decision-making can be smoothed out, ensuring the robustness of the communication strategy in the complex underwater environment. For example, in a certain underwater communication process, if the channel reliability index in the state transition s′ is much lower than the threshold When this occurs, the exponential weight will significantly decay the Q value, thereby reducing the contribution of this action to the policy update; the entire formula combines immediate rewards, future expected rewards, and environmental reliability correction, constituting a risk-sensitive double deep Q-network update mechanism, thereby generating an optimal communication strategy that better meets the requirements of underwater lamp wireless communication.

[0025] Step 130: Based on the real-time monitored underwater environmental data, select the optimal communication frequency band and transmit power through the optimal communication strategy; Specifically, when selecting the optimal communication frequency band and transmit power through the optimal communication strategy based on the real-time monitored underwater environmental data, it is necessary to combine real-time sensing data and historical communication data to determine the set of channel state parameters under different environmental conditions. The Markov decision process can be used to calculate the current channel quality and generate a communication frequency band ranking table in combination with historical data to select the optimal communication frequency band. The power allocation algorithm can calculate the signal-to-noise ratio at different transmit power levels, thereby generating transmit power optimization parameters. Combining the real-time communication link state, dynamically adjust the transmit power during the communication process to ensure the stability of the communication signal while reducing power consumption.

[0026] In an alternative implementation manner of this embodiment, the step of selecting the optimal communication frequency band and transmit power through the optimal communication strategy based on the real-time monitored underwater environmental data includes: determining the set of channel state parameters under different environmental conditions according to the real-time monitored underwater environmental data and the optimal communication strategy; determining the current channel quality according to the set of channel state parameters and the Markov decision process, and generating a communication frequency band ranking table in combination with historical communication data; determining the optimal communication frequency band with the highest channel quality by parsing the communication frequency band ranking table; calculating the signal-to-noise ratio of the optimal communication frequency band at different transmit power levels through the power allocation algorithm to generate transmit power optimization parameters; dynamically adjusting the transmit power during the communication process according to the transmit power optimization parameters and the real-time communication link state data.

[0027] Specifically, in this embodiment, after obtaining indicators such as temperature, turbidity, water flow velocity, and background noise according to the real-time monitored underwater environmental data and the optimal communication strategy, the data fusion technology is used to constitute the set of channel state parameters under different environmental conditions. This set includes signal-to-noise ratio, bit error rate, channel delay, and multipath fading characteristics. The data is collected by multiple sensors and fused through sensors to form a vector describing the comprehensive state of the underwater channel. Subsequently, using the Markov decision process, perform state transition probability analysis on this vector and historical communication data, and generate a communication frequency band ranking table. The state transition matrix reflects the probability distribution of the underwater channel from one state to another state, providing a basis for further selecting the frequency band. For this purpose, a calculation formula for channel quality is designed: , where R represents the channel quality indicator, T is the observation time window, represents the channel state parameter at time t, Φ is the non - linear mapping function. This formula is used to comprehensively reflect the cumulative effect and dynamic characteristics of the channel state change over time, so as to calculate the average quality of each frequency band within a certain time through integration. After parsing the communication frequency band ranking table, the frequency band with the highest channel quality is determined as the optimal communication frequency band according to this indicator. At the same time, the signal - to - noise ratio at different transmit power levels under the selected frequency band is calculated, and a power optimization model is established using the power allocation algorithm. This model is based on the formula: , to model the non - linear relationship between the transmit power P and the channel state function where is the optimized signal - to - noise ratio. The channel state function describes the coupling effect between power and channel state parameters. This formula is used to calculate the signal - to - noise ratio under different power conditions and determine the corresponding transmit power optimization parameters. Then, using the wireless control link state data obtained from real - time monitoring, the obtained transmit power optimization parameters are combined with the communication conditions in the current environment, and a dynamic adjustment strategy is used to adjust the transmit power online, so as to ensure the stability of the wireless communication performance within the selected frequency band in the complex underwater environment. For example, in a certain water area, when the monitoring data shows that the signal attenuation is obvious due to the increase in water turbidity, the system increases the transmit power according to the power optimization parameters, thereby compensating for the attenuation loss. Finally, through this adaptive adjustment process, high communication quality and transmission efficiency are maintained under different time periods and different environmental conditions.

[0028] Step 140: Adaptively control the light of the underwater lamp according to the optimal communication frequency band and the transmit power.

[0029] Specifically, when adaptively controlling the light of the underwater lamp according to the optimal communication frequency band and the transmit power, first, the real - time light output data and ambient light monitoring data of the underwater lamp need to be obtained, and combined with the communication parameters to generate the initial light state data. Based on this data, a light control model is constructed, and the LED drive control parameters of the pulse - width modulation signal are determined. By performing pulse - width modulation on the LED drive signal, the corresponding control signal can be output, and a feedback control index is generated in combination with the communication state data. On this basis, the feedback control index is analyzed, and the light brightness and color temperature are adjusted based on the pulse - width modulation (PWM, Pulse Width Modulation) signal, so that the underwater lamp can change dynamically according to environmental requirements and meet the requirements of remote control.

[0030] In an alternative implementation of this embodiment, the steps of adaptively controlling the light of the underwater lamp according to the optimal communication frequency band and the transmission power include: obtaining the real-time light output data and ambient light monitoring data of the underwater lamp through the built-in sensor according to the optimal communication frequency band and the transmission power, and generating the initial light state data; constructing a light control model according to the initial light state data; determining the LED drive control parameters of the pulse width modulation signal according to the light control model; outputting a control signal corresponding to the LED drive control parameters by performing pulse width modulation on the LED drive signal, and generating a feedback control index in combination with the communication link state data; dynamically adjusting the light brightness and color temperature of the underwater lamp by analyzing the feedback control index.

[0031] Specifically, in this embodiment, the signal obtained from the real-time light output data and ambient light monitoring data of the underwater lamp collected by the built-in sensor according to the optimal communication frequency band and the transmission power contains the luminous intensity of the underwater lamp itself and the background light intensity information of the surrounding environment. After these data are processed by data fusion, the initial light state data is formed. This data not only reflects the current brightness and color temperature of the LED, but also contains the changing trend of the ambient light, thus providing accurate input for subsequent light control. Then, based on the obtained initial light state data, a mathematical model is constructed to describe the relationship between the light output of the underwater lamp and the control signal, thereby establishing a light control model. This model can adopt a nonlinear dynamic system modeling method based on state feedback, and use the mapping relationship between the light output and the ambient light conditions in the collected data to construct a function that describes the interaction between the control variable and the output response. Subsequently, based on the mapping relationship in the light control model, the LED drive control parameters of the pulse width modulation signal are determined. The determined control parameters reflect the duty cycle adjustment range of the pulse width modulation (PWM) signal in the LED drive circuit, and a key formula is fitted through experimental data. The formula is expressed as: , where represents the LED drive control parameter, and respectively represent the target brightness and the target color temperature, and respectively represent the actual brightness and color temperature measured at time t, and are the nonlinear adjustment coefficients of the brightness and color temperature errors, is the complementary error function, is the hyperbolic tangent function, t is the time integration window, is a normalization factor. This formula takes into account the error variation within the time window through integration processing, uses the hyperbolic tangent function to smooth and compress the luminance error, and the complementary error function performs a non-linear mapping on the color temperature error, thereby generating an LED driving parameter that comprehensively considers the luminance and color temperature errors. Subsequently, by applying pulse width modulation to the LED driving signal, the output control signal can control the on / off state of the switching tube in the LED driving circuit, thereby precisely adjusting the actual output of the light. At the same time, the output LED driving control signal is fused with the status data obtained from the wireless control link to generate a feedback control index, which reflects the deviation between the light output of the underwater lamp under the current communication state and the expected target. Finally, through the analysis of the feedback control index and combined with the dynamic response characteristics in the light control model, the light luminance and color temperature of the underwater lamp are adjusted in real-time dynamically, so as to ensure that the light output can be continuously optimized according to the environmental conditions and control instructions, and ensure that the underwater lamp always maintains an ideal lighting effect under different environments.

[0032] In an optional implementation manner of this embodiment, historical delay samples are obtained according to the transmission delay data of the wireless control signal; the delay change trend under different communication frequency bands is determined according to the historical delay samples and the set of channel state parameters, and a delay estimation model is generated; according to the delay estimation model and the channel prediction data of the optimal communication strategy, the light control error under different delay conditions is determined; the light control error is compensated according to the Smith predictor to generate a delay compensation parameter; the wireless control instruction is preprocessed according to the delay compensation parameter, and a synchronous control signal is generated in combination with the signal control parameter of the light control model; the wireless control instruction is corrected according to the synchronous control signal, and the light state of the underwater lamp is updated according to the corrected wireless control instruction.

[0033] Specifically, in this embodiment, after obtaining the wireless control signal transmission delay data, historical delay samples are obtained through statistical and screening processes. These samples record the delay values generated during the transmission of the lamp control signal in different time periods, reflecting the dynamic characteristics of signal transmission in the underwater environment, and thus providing a basis for subsequent analysis. Then, by combining the historical delay samples with the previously obtained set of channel state parameters, the trend of delay variation in each communication frequency band is analyzed through probability statistics methods, and a delay estimation model is generated using state transition probability modeling. This model describes the law of signal transmission delay varying with time in different frequency bands, providing a basis for predicting the delay at future moments. Subsequently, the delay estimation model is combined with the channel prediction data included in the optimal communication strategy. By comparing the expected delay with the actual measured delay, the lighting control error caused by control delay under different delay conditions is determined. This error reflects the degree to which the lighting response deviates from the expected state due to transmission delay. On this basis, a Smith predictor is used to compensate for the lighting control error, and a delay compensation parameter is generated. Its corresponding calculation formula is expressed as: , where is the delay compensation parameter at time t, T represents the compensation time window, represents the lighting control error measured at time , and the function is used as a weight function to weight the error. The square root integral in the denominator is used to normalize the error energy. The purpose of this formula is to comprehensively consider the distribution of errors over a past period of time and perform smooth compensation for the control deviation caused by transmission delay. Subsequently, the generated delay compensation parameter is used to preprocess the wireless control instruction to be sent. Combining with the signal control parameters pre-determined in the lighting control model, a synchronous control signal is generated through a certain data fusion algorithm. This signal is used to correct the uncertainty caused by delay in the wireless control instruction, so that the finally transmitted control signal can more accurately reflect the real-time lighting regulation requirements. Finally, the lighting state of the underwater lamp is updated according to the corrected wireless control instruction, so that the lamp can maintain an output state consistent with the expected control target in the complex underwater environment. The whole process is continuously carried out through links such as data acquisition, model construction, formula compensation, and signal fusion, so as to ensure that the delay compensation of the wireless control signal during transmission reaches the expected effect.

[0034] In an alternative implementation of this embodiment, historical operation data of the underwater lamp is obtained, and a lamp operation status data set is generated in combination with the historical optimal communication strategy; by analyzing the lamp operation status data set, a remote monitoring model of the underwater lamp is constructed, and a set of characteristic parameters affecting the change of the lamp status is determined; according to the set of characteristic parameters and the transmission status of the wireless control signal, the optimal transmission timing of the wireless control instruction is determined, and an optimization parameter of the wireless control instruction is generated; the wireless control instruction is updated according to the optimization parameter of the wireless control instruction.

[0035] Specifically, in this embodiment, through the built-in sensor and data recording system, historical operation data of the underwater lamp in different operation cycles is obtained, including LED output intensity, color temperature fluctuation, energy consumption index, and ambient light conditions, and combined with the parameter record of the historical optimal communication strategy, these data are fused into a comprehensive lamp operation status data set, which reflects the dynamic working conditions of the underwater lamp under different water area conditions. Subsequently, statistical analysis and data mining techniques are used to analyze the data set, and methods such as time series analysis, clustering, and regression are used to construct a remote monitoring model of the underwater lamp. This model can extract key characteristic parameters from the data, such as brightness volatility, color temperature drift rate, and energy consumption change trend, so as to determine the set of characteristic parameters affecting the change of the lamp status, and these parameters constitute an important basis for describing the dynamic behavior of the lamp. Then, combined with transmission status indicators such as delay and packet loss rate in the wireless control signal transmission process, by establishing a dynamic timing matching model, the transmission timing of the lamp control instruction is optimized, and an optimization parameter of the wireless control instruction is generated. The core calculation formula is expressed as: , where represents the optimal transmission moment, represents the set of candidate time intervals, is the normalization constant, is the integration time window, represents the actual lamp output status recorded at time t, and The lamp status predicted by the remote monitoring model. This formula is used to calculate the average deviation between the actual status and the predicted status within a given time window, and the moment with the smallest deviation is selected as the transmission time of the wireless control instruction, thereby generating the optimization parameters of the wireless control instruction. Finally, the wireless control instruction is updated according to the optimization parameters, that is, the transmission timing and content of the control signal are adjusted, so that the control instruction can be transmitted to the underwater lamp at the best time, so that the light output of the lamp can be well matched with the current environment and operating status. For example, if the ambient light suddenly changes within a certain period, resulting in a deviation in the output status of the lamp, the remote monitoring model will calculate a new optimal transmission moment through comprehensive analysis of historical data and transmission status, and update the control instruction in time to ensure that the control signal arrives at the moment when the lamp is most sensitive to the response and the deviation is the smallest, so that the brightness and color temperature of the lamp can be quickly adjusted to the expected state. The whole process is closely connected through links such as data fusion, model construction, dynamic timing optimization and instruction update, providing a remote monitoring and control system with rapid response and accurate decision-making for the wireless control of underwater lamps.

[0036] A wireless communication method for underwater lamps provided by the solution of the present application. An underwater communication environment model is constructed according to the underwater communication environment; an optimal communication strategy is generated according to the model parameters of the underwater communication environment model; based on the underwater environment data monitored in real time, the optimal communication frequency band and transmission power are selected through the optimal communication strategy; the light of the underwater lamp is adaptively controlled according to the optimal communication frequency band and transmission power. Through the implementation of the solution of the present application, an underwater communication environment is modeled, the communication strategy is optimized by reinforcement learning, and the communication parameters are dynamically adjusted in combination with real-time monitoring data to solve the problems of fixed channel selection and power control and lack of environmental adaptability in traditional underwater lamp wireless communication, thereby enhancing communication stability and ensuring the remote controllability and effectiveness of underwater lamps in complex underwater environments.

[0037] Figure 2 A wireless communication device for underwater lamps provided by an embodiment of the present application. The wireless communication device for underwater lamps can be used to implement the wireless communication method for underwater lamps in the foregoing embodiments. As Figure 2 shown, the wireless communication device for underwater lamps mainly includes: A construction module 10 for constructing an underwater communication environment model according to the underwater communication environment; A generation module 20 for generating an optimal communication strategy according to the model parameters of the underwater communication environment model; A selection module 30 for selecting the optimal communication frequency band and transmission power through the optimal communication strategy based on the underwater environment data monitored in real time; A control module 40 for adaptively controlling the light of the underwater lamp according to the optimal communication frequency band and transmission power.

[0038] In an alternative implementation of this embodiment, the construction module is specifically configured to: obtain the channel attenuation coefficient according to the underwater signal propagation path, and determine the initial channel characteristic data in combination with ray tracing; obtain the channel state parameters under different interference conditions by analyzing the initial channel characteristic data; generate the channel state prediction data by analyzing the channel state parameters and the channel change trend through time series analysis; and construct an underwater communication environment model according to the channel state prediction data.

[0039] In an alternative implementation of this embodiment, the generation module is specifically configured to: determine a set of key variables for optimizing underwater communication according to the model parameters of the underwater communication environment model; construct a reinforcement learning decision framework according to the set of key variables; generate an initial communication policy by training the reinforcement learning decision framework; and generate an optimal communication policy for the underwater lamp by training the initial communication policy through a double deep Q-network.

[0040] In an alternative implementation of this embodiment, the selection module is specifically configured to: determine a set of channel state parameters under different environmental conditions according to the real-time monitored underwater environment data and the optimal communication policy; determine the current channel quality according to the set of channel state parameters and the Markov decision process, and generate a communication frequency band ranking table in combination with historical communication data; determine the optimal communication frequency band with the highest channel quality by analyzing the communication frequency band ranking table; calculate the signal-to-noise ratio of the optimal communication frequency band at different transmit power levels through a power allocation algorithm to generate transmit power optimization parameters; and dynamically adjust the transmit power during the communication process according to the transmit power optimization parameters and the real-time communication link state data.

[0041] In an alternative implementation of this embodiment, the control module is specifically configured to: obtain the real-time light output data and ambient light monitoring data of the underwater lamp through the built-in sensor according to the optimal communication frequency band and the transmit power to generate initial light state data; construct a light control model according to the initial light state data; determine the LED drive control parameters of the pulse width modulation signal according to the light control model; output a control signal corresponding to the LED drive control parameters by performing pulse width modulation on the LED drive signal, and generate a feedback control index in combination with the communication link state data; and dynamically adjust the light brightness and color temperature of the underwater lamp by analyzing the feedback control index.

[0042] In an alternative implementation of this embodiment, the wireless communication device further includes: a correction module. The correction module is configured to: obtain historical delay samples according to the transmission delay data of the wireless control signal; determine the delay change trend under different communication frequency bands according to the historical delay samples and the set of channel state parameters, and generate a delay estimation model; determine the lighting control error under different delay conditions according to the delay estimation model and the channel prediction data of the optimal communication strategy; compensate the lighting control error according to the Smith predictor to generate a delay compensation parameter; preprocess the wireless control command according to the delay compensation parameter, and generate a synchronization control signal in combination with the signal control parameter of the lighting control model; correct the wireless control command according to the synchronization control signal, and update the lighting state of the underwater lamp according to the corrected wireless control command.

[0043] In an alternative implementation of this embodiment, the wireless communication device further includes: an update module. The update module is configured to: obtain the historical operation data of the underwater lamp, and generate a lamp operation state data set in combination with the historical optimal communication strategy; construct a remote monitoring model for the underwater lamp by analyzing the lamp operation state data set, and determine a set of characteristic parameters affecting the change of the lamp state; determine the optimal transmission timing of the wireless control command according to the set of characteristic parameters and the transmission state of the wireless control signal, and generate a wireless control command optimization parameter; update the wireless control command according to the wireless control command optimization parameter.

[0044] A wireless communication device for an underwater lamp provided by the solution of the present application constructs an underwater communication environment model according to the underwater communication environment; generates an optimal communication strategy according to the model parameters of the underwater communication environment model; selects an optimal communication frequency band and transmission power through the optimal communication strategy based on the real-time monitored underwater environment data; adaptively controls the lighting of the underwater lamp according to the optimal communication frequency band and transmission power. Through the implementation of the solution of the present application, based on underwater communication environment modeling, reinforcement learning is used to optimize the communication strategy, and combined with real-time monitored data, the communication parameters are dynamically adjusted to solve the problems of fixed channel selection and power control and lack of environmental adaptability in traditional underwater lamp wireless communication, thereby enhancing communication stability and ensuring the remote controllability and effectiveness of underwater lamps in complex underwater environments.

[0045] According to the solution provided by the present application Figure 3 An electronic device provided for an embodiment of the present application. This electronic device can be used to implement the wireless communication method for an underwater lamp in the foregoing embodiment, and mainly includes: A memory 301, a processor 302, and a computer program 303 stored on the memory 301 and executable on the processor 302. The memory 301 and the processor 302 are communicatively connected. When the processor 302 executes the computer program 303, the wireless communication method for underwater lamps in the foregoing embodiments is implemented. Among them, the number of processors can be one or more.

[0046] The memory 301 can be a high-speed random access memory (RAM), or a non-volatile memory, such as a disk memory. The memory 301 is used to store executable program codes, and the processor 302 is coupled to the memory 301.

[0047] Furthermore, an embodiment of the present application also provides a computer-readable storage medium, which can be disposed in the electronic device in the foregoing embodiments. The computer-readable storage medium can be the memory in the foregoing Figure 3 illustrated embodiments.

[0048] A computer program is stored on the computer-readable storage medium. When the program is executed by the processor, the wireless communication method for underwater lamps in the foregoing embodiments is implemented. Furthermore, the computer-readable storage medium can also be various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk, or an optical disc that can store program codes.

[0049] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0050] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0051] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A wireless communication method for underwater lamps, characterized in that, Including: Construct an underwater communication environment model according to the underwater communication environment; Generate an optimal communication strategy based on the model parameters of the underwater communication environment model; Based on the underwater environment data monitored in real time, select the optimal communication frequency band and transmit power through the optimal communication strategy; Adaptive control the light of the underwater lamp according to the optimal communication frequency band and the transmit power.

2. The wireless communication method for underwater lamps according to claim 1, wherein The step of constructing an underwater communication environment model according to the underwater communication environment includes: Obtain the channel attenuation coefficient according to the underwater signal propagation path, and determine the initial channel characteristic data in combination with ray tracing; Obtain the channel state parameters under different interference conditions by analyzing the initial channel characteristic data; Generate channel state prediction data by analyzing the channel state parameters and the channel change trend through time series; Construct an underwater communication environment model according to the channel state prediction data.

3. The wireless communication method for an underwater lamp according to claim 1, characterized in that The step of generating an optimal communication strategy based on the model parameters of the underwater communication environment model includes: Determine a set of key variables for optimizing underwater communication according to the model parameters of the underwater communication environment model; Construct a reinforcement learning decision framework according to the set of key variables; Generate an initial communication strategy by training the reinforcement learning decision framework; Train the initial communication strategy through a double deep Q network to generate the optimal communication strategy of the underwater lamp.

4. The wireless communication method for an underwater lamp according to claim 3, wherein, The step of selecting the optimal communication frequency band and transmit power through the optimal communication strategy based on the underwater environment data monitored in real time includes: Determine a set of channel state parameters under different environmental conditions according to the underwater environment data monitored in real time and the optimal communication strategy; Determine the current channel quality according to the set of channel state parameters and the Markov decision process, and generate a communication frequency band ranking table in combination with historical communication data; Determine the optimal communication frequency band with the highest channel quality by analyzing the communication frequency band ranking table; Calculate the signal-to-noise ratio of the optimal communication frequency band at different transmit power levels through a power allocation algorithm to generate transmit power optimization parameters; Dynamically adjust the transmit power during the communication process according to the transmit power optimization parameters and the real-time communication link state data.

5. The wireless communication method for underwater lamps according to claim 4, characterized in that, The step of adaptively controlling the light of the underwater lamp according to the optimal communication frequency band and the transmit power includes: Obtain the real-time light output data and ambient light monitoring data of the underwater lamp through the built-in sensor according to the optimal communication frequency band and the transmit power, and generate initial light state data; Construct a light control model according to the initial light state data; Determine the LED drive control parameters of the pulse width modulation signal according to the light control model; Output a control signal corresponding to the LED drive control parameters by performing pulse width modulation on the LED drive signal, and generate a feedback control index in combination with the communication link state data; Dynamically adjust the light brightness and color temperature of the underwater lamp by analyzing the feedback control index.

6. The wireless communication method for an underwater lamp according to claim 5, characterized in that, The method further includes: Obtain historical delay samples according to the transmission delay data of the wireless control signal; Determine the delay change trend under different communication frequency bands based on the historical delay samples and the set of channel state parameters, and generate a delay estimation model; Determine the lighting control error under different delay conditions based on the delay estimation model and the channel prediction data of the optimal communication strategy; Compensate the lighting control error according to the Smith predictor to generate a delay compensation parameter; Preprocess the wireless control command according to the delay compensation parameter, and generate a synchronous control signal in combination with the signal control parameter of the lighting control model; Correct the wireless control command according to the synchronous control signal, and update the lighting state of the underwater lamp according to the corrected wireless control command.

7. The wireless communication method for an underwater lamp according to claim 6, characterized in that, The method further includes: Obtain the historical operation data of the underwater lamp, and generate a lamp operation state data set in combination with the historical optimal communication strategy; Construct a remote monitoring model for the underwater lamp by analyzing the lamp operation state data set, and determine a set of characteristic parameters affecting the change of the lamp state; Determine the optimal transmission timing of the wireless control command according to the set of characteristic parameters and the transmission state of the wireless control signal, and generate a wireless control command optimization parameter; Update the wireless control command according to the wireless control command optimization parameter.

8. A wireless communication device for an underwater lamp, characterized in that, The wireless communication device for underwater lamps includes: A construction module for constructing an underwater communication environment model according to the underwater communication environment; A generation module for generating an optimal communication strategy according to the model parameters of the underwater communication environment model; A selection module for selecting an optimal communication frequency band and transmission power through the optimal communication strategy based on the real-time monitored underwater environment data; A control module for adaptively controlling the lighting of the underwater lamp according to the optimal communication frequency band and the transmission power.

9. An electronic device, characterized in that, Including a memory and a processor, wherein: The processor is used to execute the computer program stored on the memory; When the processor executes the computer program, it implements the steps in the wireless communication method for underwater lamps according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the wireless communication method for underwater lamps according to any one of claims 1 to 7.

Images