New energy power generation prediction system and method

Abstract

The invention provides a new energy power generation prediction system and method, and relates to the field of power generation prediction. An environment monitoring and prediction system is connected with a power generation management and microalgae culture system; according to the environment monitoring and prediction system, an environment monitoring module is connected with a data preprocessing module, the data preprocessing module is connected with a prediction module, and the prediction module is used for modeling and analyzing collected data so as to predict the power generation efficiency of the ocean temperature difference and wave energy power generation device and the microalgae culture pond and periodically update a power generation prediction model. New and old data are fused through iterative training; the power generation management and microalgae culture system comprises a power generation management module, the power generation management module is connected with an ocean temperature difference and wave energy power generation device and a microalgae culture pond, and when it is predicted that the power generation efficiency of the power generation device is low, illumination and nutrition supply of the microalgae culture pond is dynamically adjusted to optimize the microalgae growth rate and biomass. And the efficiency of the power generation device is compensated through biofuel generated by the microalgae, so that the overall power generation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of power generation prediction, and in particular to a new energy power generation prediction system and method. Background Art

[0002] As the global energy crisis intensifies and environmental pollution becomes increasingly serious, new energy power generation technology has become the key to energy transformation; the development and utilization of clean energy such as solar energy, wind energy, and ocean energy not only helps to reduce greenhouse gas emissions, but is also the only way to achieve sustainable development.

[0003] Currently, many technical solutions are dedicated to using ocean energy to generate electricity, such as tidal energy, wave energy, and temperature difference energy. These solutions usually use physical devices to capture the energy of waves or tides and convert it into electrical energy through mechanical or hydraulic systems. However, these technologies often operate independently and lack comprehensive utilization and efficiency optimization.

[0004] In the prior art, when the ocean temperature difference and the wave energy power generation device are used together to generate electricity, there will often be a power generation gap during a specific period of time, resulting in a low overall power generation efficiency. The present invention proposes a new energy power generation prediction system, which not only improves the power generation efficiency through the integration of environmental monitoring and power generation management, and the application of a microalgae cultivation system, but also realizes the organic combination of energy production and environmental protection through the photosynthesis and biological adsorption characteristics of microalgae. Summary of the invention

[0005] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides a new energy power generation prediction system and method to solve the above-mentioned problem that when the ocean temperature difference and the wave energy power generation device are combined to generate electricity, there will often be power generation gaps in specific periods, thereby resulting in low overall power generation efficiency.

[0006] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a new energy power generation prediction system and method, including: an environmental monitoring and prediction system connected to a power generation management and microalgae cultivation system; The environmental monitoring and prediction system consists of an environmental monitoring module connected to a data preprocessing module, which is connected to a prediction module. The prediction module is used to model and analyze the collected data to predict the ocean temperature difference and the power generation efficiency of the wave energy power generation device and the microalgae cultivation pond, regularly update the power generation prediction model, and integrate new and old data through iterative training.

[0007] The power generation management and microalgae cultivation system includes a power generation management module, which connects the ocean temperature difference with the wave energy power generation device and the microalgae cultivation pond. The microalgae cultivation pond maintains the growth of microalgae through an electric drive unit, and the microalgae cultivation pond compensates for the insufficient efficiency of the power generation device through an efficiency compensation mechanism. The efficiency compensation mechanism monitors the efficiency of the power generation device through a prediction module. When it is predicted that the power generation efficiency of the power generation device is low, the lighting and nutrient supply of the microalgae cultivation pond are dynamically adjusted to optimize the growth rate and biomass of the microalgae, and then the efficiency of the power generation device is compensated by the biofuel produced by the microalgae, so as to improve the overall power generation efficiency.

[0008] Preferably, the environmental monitoring module is used to collect key environmental data in real time through a sensor network, including temperature changes at multiple depths on the ocean surface and deep layers, the movement of waves on the sea surface, and the speed and direction of ocean currents at the seabed, and after data preprocessing, transmit the data to the prediction module via radio signals.

[0009] Preferably, the prediction module models and analyzes the data collected by the environmental monitoring module through a machine algorithm. First, the collected data is feature engineered to extract key variables, and a preliminary power generation prediction model is constructed using a machine learning algorithm. After the model is constructed, new data is continuously introduced through an iterative algorithm for incremental training, and the model is regularly updated in combination with historical data to gradually optimize the accuracy and stability of the model. At the same time, an error correction algorithm is used to analyze the deviation between the predicted value and the actual value, and the model parameters are adjusted to reduce systematic deviations. A probability processing method is also used to generate a probability distribution of the prediction results through multiple random simulations to ensure that the model output value has high confidence and stability. In addition, based on the real-time updated environmental data and the real-time power generation data of the power generation device, the impact of the power generation device efficiency on the growth of microalgae and carbon dioxide absorption is predicted, and the operating parameters of the microalgae culture pond are dynamically corrected, and the efficiency compensation mechanism of the microalgae culture pond is started when it is predicted that the power generation efficiency of the power generation device is low.

[0010] Preferably, the power generation management module utilizes the temperature difference between the warm water on the ocean surface and the cold water in the deep layer to drive the evaporation and condensation of the low-boiling-point working fluid, thereby driving the turbine to generate electricity, and works in coordination with the wave power generation system, wherein wave power generation converts the kinetic energy of waves on the sea surface into mechanical energy, and then converts it into electrical energy. According to the power generation prediction results output by the prediction module, the power generation power is adjusted in real time, and the power generation is transmitted to the prediction module.

[0011] Preferably, the microalgae cultivation pond maintains the growth demand of microalgae through an electric drive unit, and monitors microalgae growth-related parameters in real time through sensors, and dynamically adjusts power distribution and microalgae cultivation conditions according to the growth demand of microalgae and the efficiency of power generation equipment; it also includes the adsorption of pollutants in seawater by microalgae, and transmitting data of related parameters to a prediction module for predicting the future energy demand of the power generation system and the production of microalgae fuel, and optimizing the power generation strategy and microalgae cultivation parameters based on these prediction results, wherein the pollutants include heavy metals and microplastics, and the related parameters include light intensity, temperature, carbon dioxide concentration, microalgae growth rate, CO2 absorption efficiency and pollutant capture amount.

[0012] Preferably, the electric drive unit is a key part of the microalgae cultivation pond to maintain the microalgae growth environment; it makes full use of the electricity generated by the power generation device, wherein by equipping with a high-brightness, adjustable artificial light source, according to the requirements of different microalgae varieties for light intensity, light quality and light duration, the natural lighting conditions are accurately simulated to ensure that the microalgae can carry out efficient photosynthesis; an electric-driven pump is used to work in coordination with an advanced temperature control unit, the pump transports seawater at a specific flow rate and path, and the temperature control unit accurately controls the seawater temperature according to a preset temperature range and real-time monitoring data, simulates the ocean temperature difference environment, and creates a suitable growth temperature range for the microalgae. In addition, when necessary, the electric heater is directly involved to cope with the temperature requirements under special circumstances. Although it consumes electrical energy, it can achieve accurate control of the temperature of the microalgae cultivation pond, ensure that the microalgae grows and reproduces in a stable and suitable environment, thereby improving the efficiency of biofuel output in the microalgae cultivation pond, and achieving synergy and complementarity when the power generation device is inefficient. The power generation device is an ocean temperature difference and wave energy power generation device, and the artificial light source is a high-efficiency LED lamp.

[0013] Preferably, temperature sensors are installed at multiple depth points on the ocean surface and in the deep layers to monitor temperature changes at different depths in real time; wave frequency and height sensors are installed on buoys or floating platforms on the sea surface to measure wave movement in real time through GPS and ultrasonic technology; sensors for current strength and direction are installed on fixed stations on the seabed to monitor the speed and direction of the currents.

[0014] Preferably, the system uses a combination of wireless transmission and satellite communication; each sensor node in the sensor network has wireless communication capabilities, can collect collected data through relay stations, and send it to a control center on land via a satellite communication system.

[0015] Preferably, multiple wireless communication networks are established between the relay buoys deployed on the sea surface and the fixed stations on the seabed, and each buoy or station is equipped with redundant communication modules to prevent single point failures; then when the environmental data is collected to the relay station through the wireless network, the data is packaged and transmitted to the land control center through the satellite communication system; the satellite link adopts the high-bandwidth, low-latency Ku band, which can support the real-time transmission of massive data; AES-256 encryption technology is applied in the data transmission process to ensure the security and confidentiality of the data.

[0016] Preferably, the prediction module first performs feature engineering on the data collected from the environmental monitoring module, extracts key variables, and then uses a machine learning algorithm to build a preliminary power generation prediction model; after the model is built, the system continuously introduces new data for incremental training through an iterative algorithm, and regularly updates the model in combination with historical data, gradually optimizing the accuracy and stability of the model; the key variables are temperature difference, wave frequency, and ocean current intensity.

[0017] Preferably, in order to further improve the prediction accuracy, the prediction module uses an error correction algorithm to analyze the residuals between the predicted value and the actual value and adjust the model parameters to reduce systematic deviations. It also uses the probability processing method of Markov Chain Monte Carlo (MCMC) to generate the probability distribution of the prediction results through multiple random simulations to ensure that the model output value has high confidence and stability.

[0018] Preferably, the predicted value is the new energy power generation calculated by the prediction model based on environmental data, while the actual value is the actual power generation or ecological impact data collected by monitoring equipment during the operation of the power generation system; the residual refers to the difference between the predicted value and the actual value, which is usually used to measure the accuracy of the model prediction. The smaller the residual, the higher the accuracy of the prediction model; when performing error correction, the prediction model will analyze the distribution of the residual, identify the pattern of the deviation of the predicted value from the actual value, and reduce this difference by adjusting the model parameters or introducing new data features to improve the overall accuracy and stability of the model.

[0019] Preferably, the power generation management module includes a deep-sea pumping device for transporting deep cold water to the power generation system and reducing heat loss through multi-layer insulation pipes; the temperature difference between the warm water on the ocean surface and the deep cold water is mainly used to drive the evaporation and condensation of the low-boiling-point working fluid, drive the turbine to generate electricity, and work in conjunction with the wave power generation system to adjust the power output in real time according to the prediction results; the wave power generation system converts the kinetic energy of the waves into electrical energy through mechanical movement, and outputs energy in conjunction with the temperature difference power generation system, and the low-boiling-point working fluid is isobutane.

[0020] Preferably, the latest nano-insulation materials are used on deep-sea pumping equipment and cold water pipes. Such materials can effectively reduce heat loss, thereby improving the efficiency of temperature difference power generation. For example, aerogel materials have extremely low thermal conductivity, which can significantly reduce the temperature decay during transmission and maintain efficient energy transfer. In addition, aerogel materials are highly corrosive in deep-sea environments and can easily cause damage to equipment during long-term use. By applying intelligent anti-corrosion materials with self-healing polymer coatings, the durability of the equipment can be improved, and tiny cracks can be automatically repaired when damaged, thereby extending the life of the equipment and reducing maintenance costs.

[0021] Preferably, coatings based on the self-healing mechanism of polymer chains are used on key components such as deep-sea power generation equipment, pipelines and turbines, which can spontaneously polymerize and fill the damage when cracks appear; these materials can automatically repair themselves through chemical reactions when they suffer from small cracks or mechanical damage, ensuring that the equipment can operate stably and for a long time in harsh marine environments.

[0022] Preferably, the microalgae cultivation pond monitors the temperature changes, carbon dioxide absorption rate and pollutant adsorption of the deep cold water discharge outlet and the surrounding sea area in real time through sensors, and transmits the data to the prediction module for predicting microalgae growth and biofuel production.

[0023] Preferably, the power generation management and microalgae cultivation system calculates the impact of different discharge depths, discharge volumes and discharge locations on power generation efficiency and microalgae cultivation, and selects the optimal discharge plan for microalgae cultivation through simulation and optimization algorithms; then the system monitors the actual effect of cold water discharge in real time, and continuously evaluates the impact on microalgae growth and pollutant capture efficiency through a feedback mechanism. If water quality changes are detected or the adsorption capacity of microalgae exceeds a preset threshold, the discharge depth will be adjusted immediately, the cold water discharge volume will be reduced, or the discharge location will be changed to ensure the high efficiency of microalgae cultivation and the balance of the environment while maintaining power generation efficiency.

[0024] Preferably, the efficiency compensation mechanism is that when the prediction module monitors that the efficiency of the power generation device is insufficient, the light intensity, light quality and duration of the artificial light source are dynamically adjusted according to the efficiency of the power generation device and the growth requirements of the microalgae to ensure the photosynthesis efficiency of the microalgae, and then the temperature is optimized by using an electric-driven pump and temperature control system to ensure the key temperature range in winter and reasonably utilize the natural low temperature in summer to maintain a suitable growth temperature for the microalgae; then the timing and dosage of nutrient addition are adjusted according to the efficiency of the power generation device, the carbon dioxide supply is reasonably controlled, and the nutrient utilization efficiency is improved. Finally, the microalgae absorbs carbon dioxide through photosynthesis, and the microalgae biologically absorbs pollutants in seawater, and the biomass produced by its growth is used for biofuel production. Therefore, when the efficiency of the power generation device is insufficient, the overall system efficiency is compensated by improving the growth rate of the microalgae, biomass accumulation and biofuel output, thereby achieving coordinated and stable operation of the system.

[0025] (III) Beneficial effects The present invention provides a new energy power generation prediction system and method. It has the following beneficial effects: 1. This method accurately predicts the ocean temperature difference and the power generation efficiency of the wave power generation device and the microalgae cultivation pond, so that the power generation management module can adjust the power in real time according to the prediction, making the energy output more stable; the microalgae cultivation pond efficiency compensation mechanism intervenes when the power generation device is inefficient, and uses microalgae biofuel to compensate, thereby improving the overall energy utilization efficiency, reducing energy waste, and ensuring a continuous supply of electricity.

[0026] 2. This method uses microalgae to absorb carbon dioxide generated during the power generation process and capture marine pollutants through its biological characteristics, thereby achieving carbon neutrality and environmental purification. Microalgae can not only effectively reduce carbon dioxide emissions, but also purify the discharged water, making power generation and marine ecological protection complement each other.

[0027] 3. In this method, the deep-sea pumping device and pipeline adopt advanced insulation and anti-corrosion materials to reduce heat loss, extend equipment life, and ensure efficient and stable temperature difference power generation; the microalgae breeding pool monitors and absorbs pollutants while ensuring its own growth to achieve environmental balance. The overall system improves the adaptability and reliability in harsh marine environments and promotes the sustainable development of new energy development and utilization. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Embodiment 1: The embodiment of the present invention provides a new energy power generation prediction system and method. The embodiment describes the operation process of the ocean temperature difference and wave energy power generation device in the new energy power generation prediction system, which mainly relies on the real-time ocean environment data collected by the environment monitoring module and achieves efficient and stable power generation effect through dynamic adjustment of the power generation management module; The specific operation is to first deploy temperature sensors on the surface and deep layers of the ocean. Temperature sensors are installed at multiple depth points such as the surface layer of 0 to 5 meters, the thermocline layer of 10 to 50 meters and the deep layer of 200 to 1000 meters to monitor the temperature changes of each layer in real time. For example, the surface temperature is about 30°C and the deep temperature is about 5°C. This temperature difference provides the necessary conditions for thermoelectric power generation. Wave sensors are installed on buoys, and GPS and ultrasonic technology are used to measure the frequency, height and direction of waves in real time. Ocean current sensors are installed on fixed stations on the seabed to monitor the speed and direction of ocean currents in order to fully grasp the dynamics of the ocean.

[0030] After data collection is completed, each node in the sensor network collects data to the relay site through the wireless communication module, and then transmits it to the control center on land via the satellite communication system. AES-256 encryption is used during data transmission to ensure security. The prediction module of the control center first performs feature engineering on the collected data, extracts key variables such as temperature difference, wave frequency, and ocean current intensity, and uses machine learning algorithms to build a power generation prediction model. Through incremental training and regular updates of historical data, the system continuously optimizes the prediction accuracy of the model. For the predicted value of the model output, the prediction module generates a probability distribution of the prediction result through the Markov Chain Monte Carlo method (MCMC) to ensure that the model output has a high degree of confidence.

[0031] After obtaining the power generation prediction result of the prediction model, the power generation management module starts the deep-sea pumping device to transport deep cold water to the power generation system through a multi-layer aerogel insulation pipe. The temperature difference between the warm water on the ocean surface and the deep cold water drives the evaporation and condensation process of isobutane, a low-boiling-point working fluid, to drive the turbine to generate electricity. At the same time, the wave energy power generation system converts kinetic energy into mechanical energy through wave movement, and then converts it into electrical energy, combined with temperature difference power generation output; the power generation management module dynamically adjusts the power generation power, the turbine speed or the blade angle of the wave energy device according to the power generation prediction data of the prediction module, and optimizes the power generation efficiency. When the performance of the wave energy power generation device is detected to be declining, the system will give priority to the deployment of temperature difference power generation to maintain the stability of the system output.

[0032] Embodiment 2: This embodiment, based on the first embodiment, describes in detail the operation process of the microalgae cultivation pond, especially when the power generation device is inefficient, how to maintain the microalgae growth environment through the electric drive unit and activate the efficiency compensation mechanism to achieve a dynamic balance of power generation efficiency.

[0033] In the daily operation of the system, the microalgae breeding pond simulates natural lighting conditions through high-brightness and adjustable LED lights to provide the microalgae with the lighting environment required for photosynthesis; these LED lights can be carefully created according to the type of microalgae, such as Chlorella, strictly in accordance with their requirements for 2000 to 3000 lux light intensity and the appropriate ratio of blue light to red light and 12 to 14 hours / day of light duration, to create a lighting environment that suits their photosynthesis; at the same time, the electric pump system transports seawater at a specific flow rate of 10 to 20 cubic meters / hour, and the temperature control unit accurately regulates the seawater temperature within a preset temperature range of 20 to 25°C, simulating the ocean temperature difference environment and creating a suitable growth temperature for the microalgae; when the temperature is too low, the electric heater will intervene to ensure the stable growth of the microalgae.

[0034] Various sensors in the system continuously monitor various parameters closely related to the growth of microalgae, and obtain key data such as real-time light intensity of 2200 lux, temperature maintained at 23°C, CO2 concentration in the range of 500 to 800 ppm, microalgae growth rate increasing by 0.5% to 1% per hour, carbon dioxide absorption efficiency of 30% to 40%, and pollutant capture of heavy metal adsorption of 1 to 2 mg / L and microplastic adsorption of 0.5 to 1 mg / L. These data will be immediately transmitted to the prediction module, which will predict future power generation and microalgae fuel production based on these data, and use this as a basis to further optimize the power generation strategy and reasonably set the parameters of the breeding pond.

[0035] When the power generation efficiency of the power generation device decreases due to changes in the external environment or equipment factors, the system will activate the efficiency compensation mechanism of the microalgae breeding pond. After detecting a decrease in power generation, for example, when wave energy power generation decreases by 20%, the prediction module will dynamically adjust the light intensity and carbon dioxide supply of the microalgae breeding pond. For example, the light intensity of the LED lamp will be increased to 2500 lux, the lighting time will be extended to 14 to 16 hours / day, and the carbon dioxide supply will be increased to 800-1000ppm to improve the photosynthesis efficiency of the microalgae. In addition, the temperature setting of the temperature control unit is adjusted according to the environmental requirements of the microalgae to ensure that the temperature in the breeding pond is appropriate.

[0036] Under environmental optimization, the growth of microalgae is accelerated, increasing carbon dioxide absorption and pollutant adsorption, thereby rapidly accumulating biomass. The microalgae are then processed to extract renewable biofuels, such as biodiesel, and this part of the fuel is used to generate electricity in the system, compensating for the insufficient efficiency of the power generation equipment and achieving an improvement in the overall power generation efficiency.

[0037] In order to further refine the implementation process, the startup and maintenance of the microalgae culture pond are considered; during the startup phase, the microalgae culture pond needs to be thoroughly cleaned and disinfected to ensure that there are no harmful organisms or pollutants that affect the growth of the microalgae, and then according to the type and growth stage of the microalgae, add appropriate amounts of nutrients and microalgae seedlings to the pond. In the early stages of microalgae growth, the growth of the microalgae needs to be closely monitored, and the light, temperature and nutrient supply need to be adjusted in time to ensure the healthy growth of the microalgae.

[0038] As the microalgae grow, the system adjusts the farming conditions based on the data provided by the sensors. For example, if the system detects a drop in CO2 concentration, it will automatically increase the CO2 supply to meet the needs of microalgae photosynthesis. If the temperature exceeds the preset range, the temperature control unit will adjust the cooling or heating system to maintain a suitable growth temperature. These automated adjustments reduce human intervention and improve farming efficiency.

[0039] During the maturity period of the microalgae, the system will predict the optimal harvesting time based on the growth rate and biomass accumulation of the microalgae. During the harvest, the microalgae will be collected and sent to processing facilities to extract biofuels. These biofuels can compensate for power generation when power generation efficiency is low, and can also be supplied to other industries as renewable energy. After the microalgae are harvested, the breeding ponds will be cleaned and disinfected to prepare for the growth of the next batch of microalgae.

[0040] In addition, the system will regularly evaluate the performance of the microalgae cultivation ponds, including biofuel production, CO2 absorption efficiency and pollutant capture; these evaluation results are used to optimize the cultivation strategy and improve the energy output and environmental benefits of the system; through this continuous monitoring and adjustment, the microalgae cultivation ponds can adapt to changing environmental conditions and ensure the efficient and stable operation of the new energy power generation prediction system.

[0041] In summary, this embodiment demonstrates the efficient operation of the microalgae cultivation pond in the new energy power generation prediction system, and how to achieve a dynamic balance of power generation efficiency through the power drive unit and the efficiency compensation mechanism when the power generation device is insufficient; this integrated system not only improves energy utilization efficiency, but also makes a positive contribution to environmental protection.

[0042] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A new energy power generation prediction system and method, characterized in that: include: Environmental monitoring and prediction systems connect power generation management and microalgae cultivation systems; The environmental monitoring and prediction system is composed of an environmental monitoring module connected to a data preprocessing module, which is connected to a prediction module. The prediction module is used to model and analyze the collected data to predict the ocean temperature difference and the power generation efficiency of the wave energy power generation device and the microalgae cultivation pond, regularly update the power generation prediction model, and integrate new and old data through iterative training; The power generation management and microalgae cultivation system includes a power generation management module, which connects the ocean temperature difference with the wave energy power generation device and the microalgae cultivation pond. The microalgae cultivation pond maintains the growth of microalgae through an electric drive unit, and the microalgae cultivation pond compensates for the insufficient efficiency of the power generation device through an efficiency compensation mechanism. The efficiency compensation mechanism monitors the efficiency of the power generation device through a prediction module. When it is predicted that the power generation efficiency of the power generation device is low, the lighting and nutrient supply of the microalgae cultivation pond are dynamically adjusted to optimize the growth rate and biomass of the microalgae, and then the efficiency of the power generation device is compensated by the biofuel produced by the microalgae, so as to improve the overall power generation efficiency.

2. A new energy power generation prediction system and method according to claim 1, characterized in that: The environmental monitoring module is used to collect key environmental data in real time through a sensor network, including temperature changes at multiple depths on the ocean surface and deep layers, the movement of waves on the sea surface, and the speed and direction of ocean currents at the seabed, and after data preprocessing, transmit it to the prediction module via radio signals.

3. A new energy power generation prediction system and method according to claim 1, characterized in that: The prediction module models and analyzes the data collected by the environmental monitoring module through machine algorithms, regularly updates the power generation prediction model, integrates new and old data through iterative training, continuously improves the prediction accuracy and corrects errors, and predicts the impact of the power generation device efficiency on the growth of microalgae and carbon dioxide absorption based on real-time updated environmental data and real-time operation data of the power generation device, dynamically corrects the operating parameters of the microalgae cultivation pond, and activates the efficiency compensation mechanism of the microalgae cultivation pond when it is predicted that the power generation efficiency of the power generation device is low.

4. A new energy power generation prediction system and method according to claim 1, characterized in that: The power generation management module uses the temperature difference between the warm water on the ocean surface and the cold water in the deep layer to drive the evaporation and condensation of low-boiling-point working fluids, drive the turbine to generate electricity, and work in coordination with the wave power generation system. It then adjusts the power generation power in real time based on the power generation prediction results output by the prediction module, and transmits the power generation to the prediction module.

5. A new energy power generation prediction system and method according to claim 1, characterized in that: The microalgae cultivation pond maintains the growth demand of microalgae through an electric drive unit, and monitors microalgae growth-related parameters in real time through sensors, and dynamically adjusts power distribution and microalgae cultivation conditions according to the growth demand of microalgae and the efficiency of power generation equipment; it also includes microalgae bio-absorption of pollutants in seawater, and transmitting data of related parameters to a prediction module for predicting the future energy demand of the power generation system and the production of microalgae fuel, and optimizing the power generation strategy and microalgae cultivation parameters based on these prediction results.

6. A new energy power generation prediction system and method according to claim 2, characterized in that: The sensor network includes temperature sensors, wave frequency and height sensors, and ocean current strength and direction sensors. The temperature sensors are installed at multiple depth points on the ocean surface and deep layers to monitor temperature changes at different depths in real time; the wave frequency and height sensors are installed on buoys and floating platforms on the sea surface to measure the movement of waves in real time through GPS and ultrasonic technology; the ocean current strength and direction sensors are installed on fixed stations on the seabed to monitor the speed and direction of ocean currents.

7. A new energy power generation prediction system and method according to claim 1, characterized in that: The prediction module first performs feature engineering on the data collected from the environmental monitoring module, extracts key variables, and uses a machine learning algorithm to build a preliminary power generation prediction model. After the model is built, the system continuously introduces new data for incremental training through an iterative algorithm, and regularly updates the model in combination with historical data, gradually optimizing the accuracy and stability of the model.

8. A new energy power generation prediction system and method according to claim 1 or 7, characterized in that: The prediction module uses an error correction algorithm to analyze the deviation between the predicted value and the actual value and adjust the model parameters to reduce the systematic deviation. It also adopts a probability processing method to generate the probability distribution of the prediction results through multiple random simulations to ensure that the model output value has high confidence and stability.