38 results about "Solar irradiance" patented technology

This disclosure provides a digital twin system and method for solar high-temperature heat pump steam supply with energy storage coupling, belonging to the field of solar high-temperature heat pump technology. The system includes a data acquisition module, a time-series prediction module, a digital twin module, a system control module, and a feedback verification module. The data acquisition module collects and preprocesses historical and real-time multi-source data. The time-series prediction module predicts solar irradiance and heat consumption at multiple future moments based on machine learning. The digital twin module calculates future terminal parameters using real-time and predicted data based on a physical information model. The system control module generates and executes a heat pump advance control scheme based on optimization objectives. The feedback verification module compares actual and predicted parameters to correct the digital twin model. This invention achieves proactive prediction, advance control, and closed-loop optimization of industrial steam supply systems, solving the control lag and energy-saving optimization problems caused by solar energy volatility and complex system coupling.

The application provides an XGBoost-based distributed photovoltaic power generation amount prediction method and system, relates to the photovoltaic power generation technical field, and collects historical power generation amount data of a distributed photovoltaic power station and corresponding hourly solar irradiance data of a geographical position, performs periodic mapping of a [0, 2pi] interval on a time stamp, and calculates sine and cosine characteristics, so as to take the processed time period characteristics and the solar irradiance data as input, train an XGBoost regression model, and realize power generation amount prediction. The application does not need an additional abnormal point screening step, has natural robustness by means of the weighted tree integration mechanism of XGBoost, and has a lightweight model structure, fast training and prediction speed, can significantly reduce the consumption of computing resources while ensuring a prediction accuracy of more than 95%, is suitable for multi-station distributed deployment scenes, and can effectively support intelligent power grid dispatching and distributed energy management.

This invention belongs to the field of meteorological data analysis technology, and provides a method and system for predicting solar irradiance based on the screening of key meteorological factors. The method involves acquiring solar irradiance observation data and candidate meteorological factor data, constructing a historical dataset of candidate factors, and preprocessing it to form a sample dataset for screening key meteorological factors. A clear-sky irradiance benchmark is constructed based on the physical mechanism of radiative transfer and evaluated to obtain a mechanism consistency score. Linear and nonlinear correlation indices between candidate factors and target irradiance are calculated to obtain a statistical contribution score. An irradiance prediction base model is trained, and an interpretability attribution algorithm is used to evaluate and obtain an interpretability score. The mechanism consistency score, statistical contribution score, and interpretability score are integrated to determine the set of key meteorological factors affecting solar irradiance and their contribution weights. This invention provides a reliable input element foundation and decision support for solar irradiance prediction and photovoltaic-related businesses.

A method for training a solar irradiance forecasting model for an area of interest, the method includes collecting a training database comprising, for each sub-period of a past period of time, solar irradiance measurements of the area of interest, determining, for each sub-period, a forecast of the solar irradiance on the basis of a baseline forecast model and of the solar irradiance measurements for said sub-period, determining, for each sub-period, an error metric, called variability, identifying the sub-periods, called more informative sub-periods, whose variability is above a predetermined variability threshold, compiling a refined training database on the basis of the solar irradiance measurements of the more informative sub-periods, and training the solar irradiance forecasting model on the basis of the refined training database.

This invention proposes a photovoltaic-storage-charging coordinated control method and system based on multi-energy complementarity. The method includes the following sub-steps: establishing a photovoltaic power generation model, an energy storage system model, and a charging load model respectively; acquiring historical solar irradiance information, charging information, and electricity price information, and constructing a prediction model based on a neural network to predict and output the solar irradiance, charging load demand power, and electricity price for future periods; constructing an objective optimization function with annual net cost and power deviation rate as optimization objectives; formulating a photovoltaic-storage-charging coordinated control strategy, using an improved whale optimization algorithm to solve the objective optimization function, generating a charging and discharging power sequence based on the obtained optimal solution, and inputting it into the system for execution. This method achieves coordinated optimization control of photovoltaic power generation, energy storage, and charging systems, reduces annual net cost, reduces power deviation, and improves the overall system operating efficiency and reliability.

This invention discloses a method and system for detecting the backsheet temperature of photovoltaic modules, relating to the field of photovoltaic operation monitoring technology. The method includes: calculating local temperature rise values ​​based on an optical fiber thermal zone address chain and marking trusted optical fiber clips; acquiring solar irradiance, ambient wind speed, dust accumulation, module voltage, and module current, and performing operational condition correction on the local temperature rise values ​​to obtain operational condition-corrected temperature rise values; calculating the temperature rise response difference, unit irradiance temperature rise response, and residual temperature rise based on the operational condition-corrected temperature rise values, and calculating the comprehensive score of the thermal zone response and the output power deviation; using the comprehensive score of the thermal zone response and the output power deviation to screen for anomalies in the corresponding thermal zones, obtaining thermoelectrically correlated abnormal thermal zones; this invention solves the problem of difficulty in correlating and locating local thermal anomalies and electrical output anomalies on the backsheet by constructing an optical fiber thermal zone address chain.

This application provides a tiered operation system and method for an integrated molten salt thermal energy storage solar-assisted coal-fired power generation system, belonging to the technical field of solar-assisted coal-fired power generation systems. The system provided includes a coal-fired power plant subsystem, a solar field subsystem, and a processing system. It adjusts the heat transfer oil flow rate of the PTC collector field and the molten salt flow rate of the molten salt thermal energy storage system according to the actual solar thermal energy input. It calculates the mass flow rate and pressure of each stage of extraction steam in each high-pressure heater in the high-pressure heater group based on the matrix heat balance equation and the Stodola formula. It switches the connection relationship between the salt-water heat exchanger and each high-pressure heater in the high-pressure heater group according to the load level and the actual solar thermal energy input, realizing tiered steam extraction substitution. The tiered operation system and method for an integrated molten salt thermal energy storage solar-assisted coal-fired power generation system provided in this application are used to achieve dynamic switching of extraction steam levels under different loads and solar irradiance conditions.

This invention relates to the field of photovoltaic power generation technology, and discloses a method, apparatus, equipment, and medium for optimizing the installation surface parameters of photovoltaic fixed supports. The method includes: acquiring site range data, installation tilt angle range data, installation spacing range data, and a pre-constructed solar irradiance calculation model for the target photovoltaic deployment area; traversing the installation tilt angle range data and installation spacing range data to determine multiple parameter groups, each parameter group containing values ​​for installation tilt angle and installation spacing; determining the total effective light-receiving area of ​​photovoltaic modules that can be deployed under the corresponding parameter group's deployment method based on each parameter group and the site range data; calculating the total solar radiation of the corresponding parameter group based on each parameter group, the total effective light-receiving area of ​​the corresponding parameter group, and the solar irradiance calculation model; and determining the target parameter group based on the total solar radiation of multiple parameter groups, thus achieving standardization and streamlining of the installation surface parameter optimization process.

This invention provides a method and system for zoned ventilation control of ventilated curtain walls, relating to the field of air conditioning and ventilation control technology. The invention divides the ventilated curtain wall area into several monitoring zones, collecting real-time data on air temperature, humidity, carbon dioxide concentration, temperature difference, wind speed, air volume, solar irradiance, fan power, and energy consumption parameters. It calculates air quality index, air-temperature synergy optimization index, and energy efficiency index. For unqualified or abnormal zones, it automatically generates ventilation enhancement strategies, adaptive ventilation adjustment strategies, and fan optimization strategies. Through multi-parameter correlation analysis, it establishes zoned temperature field and airflow models, identifies abnormal zones, and generates optimized operation and maintenance strategies, achieving balanced air quality, optimized ventilation effect, and energy consumption control. This system can be used in applications involving air conditioning, humidification, ventilation, and airflow as a shield, improving indoor environmental comfort and energy efficiency.

This application relates to the technical field of interval prediction and discloses a method, apparatus, computer device, and storage medium for solar irradiance interval prediction, which includes obtaining a historical environmental parameter dataset and a first environmental parameter dataset within a target prediction period, determining a first environmental sample dataset, establishing a target solar irradiance prediction model, inputting the first environmental parameter dataset into the target solar irradiance prediction model to obtain a solar irradiance prediction result within the target prediction period, and performing interval prediction on the solar irradiance prediction result within the target prediction period using an autonomous sampling method based on the first environmental sample dataset to obtain a target solar irradiance interval prediction result within the target prediction period. This application considers not only the similarity and regularity of the historical data but also the complexity and accuracy of the model. Furthermore, using the autonomous sampling method to perform interval prediction on the solar irradiance prediction result effectively improves the reliability and confidence of the prediction result.

A method for ultra-short-term solar irradiance prediction based on a deep learning decomposition ensemble model is disclosed. First, solar irradiance data and solar zenith angle data are arranged into solar irradiance sequences and solar zenith angle sequences. Then, the solar irradiance sequences are reconstructed and decomposed into m subsequences. Based on the frequency range of the m subsequences, they are further divided into random component sets and trend component sets. Next, the data from the random component sets is input into a stochastic prediction module to obtain a stochastic prediction output feature matrix. Then, the data from the trend component sets and the solar zenith angle sequence are input into a periodic prediction module to obtain a periodic prediction output feature matrix. Finally, the stochastic prediction output feature matrix and the periodic prediction output feature matrix are fused and passed through a decoder based on a fully connected layer to obtain the prediction result. This method can achieve high prediction stability.

This application relates to the field of photovoltaic curtain wall technology and discloses an AI-based intelligent photovoltaic curtain wall system, including a curtain wall frame with multiple photovoltaic windows inside. Photovoltaic panels are installed at the photovoltaic windows. An equipment cage is located on one side of the top of the curtain wall frame, containing a drive component. The drive component is connected to a linkage horizontal frame, which in turn connects to multiple linkage vertical plates. The linkage vertical plates are connected to their corresponding photovoltaic panels via photovoltaic traction plates. An AI control box, electrically connected to the drive component, is located on the top of the equipment cage. The AI ​​control box receives environmental data such as solar irradiance, weather type, season and date, photovoltaic panel temperature, ambient temperature and humidity, and atmospheric pressure, and controls the drive component to move the linkage horizontal frame up and down. This, in turn, adjusts the synchronous opening and closing of multiple photovoltaic panels via the linkage vertical plates and photovoltaic traction plates. This system can intelligently adjust the opening and closing state of the photovoltaic panels according to changes in the external environment.

The application provides a photovoltaic panel sun tracking control method and system, the method comprising: based on the geographical position and time information of a photovoltaic power station, calculating the reference theoretical position of the sun through an astronomical algorithm to generate a sun reference position sequence; acquiring local environment sensing data and external weather forecast data of the photovoltaic power station, predicting the geometric shading relationship of the cloud layer to the sun in the future period based on the data, and calculating the prediction curve of the solar irradiance reaching the photovoltaic panel position; constructing a feedforward optimization model and solving, outputting the optimized feedforward instruction of the photovoltaic panel posture in the future period; collecting the rapid light sensing deviation signal and the absolute attitude feedback signal of the photovoltaic panel in real time, and weighting and fusing with the feedforward control instruction to generate a motor driving instruction to drive the photovoltaic panel to move to track the sun; the method can improve the tracking accuracy of the photovoltaic panel to the sun, effectively improve the power generation efficiency, and also reduce the mechanical loss and movement risk, and guarantee the stable and reliable operation of the system.

Systems, apparatus, articles of manufacture, and methods are disclosed to predict solar irradiance. The prediction of solar irradiance includes to record data collected by the sensor, the data corresponding to a future weather condition; package the data for transmission to a server, wherein to package the data further includes to: record data for the sensor at a sampling interval; and tag the data with a label corresponding to collection of the data by the sensor; and transmit the data to the server, the server to determine a solar irradiance model by performing image processing of an image received from a collection device; determining a characteristic of a cloud in the image; and determining a solar irradiance model based on the determined characteristic.

This invention provides a method, apparatus, computer equipment, and medium for estimating solar resources in a photovoltaic power station, belonging to the field of photovoltaic power generation. The method includes: acquiring aerial photographs of a photovoltaic power station in a target area with complex terrain; reconstructing a 3D point cloud based on a structure-reconstruction-motion algorithm; performing 3D terrain reconstruction and 3D photovoltaic module reconstruction based on the reconstructed 3D point cloud; constructing a 3D scene of the photovoltaic power station and setting the spectral attributes of scene elements; dynamically adjusting the solar zenith angle and azimuth angle parameters to simulate the transmission process of downward solar radiation in the 3D scene, and outputting the absorptive photosynthetically active radiation value at the photovoltaic module level; and determining the impact of terrain shading on the light-receiving efficiency of the photovoltaic modules based on multiple instantaneous simulations. This effectively quantifies the impact of terrain shading on the light-receiving efficiency of photovoltaic modules, thereby significantly improving the estimation accuracy of solar irradiance and power generation for mountainous photovoltaic power stations.

An automatic hot spot fault diagnosis method and system for a photovoltaic power station module, the method comprising: collecting local environmental data, power output data, and module temperature data of a target photovoltaic power station; on the basis of the environmental data and the power output data, obtaining a relationship between environmental factors and power output; acquiring output power of photovoltaic modules in different plots under different dust accumulation conditions, and obtaining a relationship between different dust accumulation conditions and power output; and on the basis of characteristics of power loss caused by module hot spots and the module temperature data, determining a hot spot fault level for a photovoltaic power station module. Solar irradiance data and photovoltaic module temperature data are collected, and detection and recognition algorithms for partial shading issues are combined, so as to achieve automatic diagnosis of photovoltaic module hot spot faults and determination of an optimal photovoltaic module cleaning cycle, thereby effectively improving the power generation efficiency and yield of the photovoltaic power station.

This invention belongs to the field of photovoltaic power generation prediction. It discloses a day-ahead photovoltaic prediction method and device based on meteorological sensitivity time-segment clustering. It utilizes the dual similarity between meteorological characteristics and solar irradiance characteristics during power generation periods for power matching and adopts a multi-layer matching correction mechanism. This effectively alleviates the limitations of traditional prediction methods in handling nonlinear and non-stationary meteorological data, while reducing the cumulative error of multi-day continuous prediction and improving the stability and reliability of prediction results to a certain extent.

The invention relates to a self-contained ultraviolet radiation monitoring device configured to record and query solar irradiance levels in the 280 to 360 nanometer range in real time. The system comprises an ultraviolet radiation sensor that generates voltage signals proportional to the radiation intensity, an embedded system module that acquires and transmits these signals every minute via Wi-Fi wireless communication using the MQTT protocol, and a self-contained solar charging system consisting of a solar panel, a charge controller, and a 12-volt AGM battery. The data is received by a single-board computer connected to the electrical grid, which acts as a local server. This server stores the information in a local database and allows its querying through a web application accessible from mobile or desktop devices connected to the same wireless network.The system operates only during the day and automatically shuts down at night. The invention requires no internet connection or subscriptions and allows direct access to the collected information.

This invention provides a bimetallic MOF-derived carbon-based photothermal-electric conversion phase change material and its preparation method, relating to the field of solar energy conversion and storage materials technology. The method involves adding cobalt nitrate hexahydrate, zinc nitrate hexahydrate, and 2-methylimidazole to a GO suspension, and obtaining a GO@ZnCo-MOF precursor through in-situ growth. The precursor is then calcined at high temperature under an inert atmosphere to obtain a porous rGO@Co / C photothermal framework. Finally, PCMs are encapsulated within the pores of the rGO@Co / C framework using a physical wetting method to obtain the bimetallic MOF-derived carbon-based photothermal-electric conversion phase change material. The phase change composite material prepared by this invention can effectively buffer the impact of solar irradiance intensity fluctuations on system stability. During periods of intermittent or no-light conditions, the material maintains a constant system temperature through a latent heat release mechanism of phase change.

This invention discloses a method for preparing a wood-based solar interface evaporator and its application, belonging to the field of solar evaporation seawater desalination technology. Using natural wood as raw material, a superhydrophilic wood aerogel (WA) is prepared through delignification and freeze-drying. MOF material is grafted onto the porous channel surface of WA using in-situ grafting technology to obtain MOF@WA. Porous lignin carbon (PLC) is prepared from lignin through high-temperature carbonization and activation. PLC is dispersed in a chitosan / acetic acid aqueous solution, coated onto the surface of MOF@WA, and dried to obtain a PLC@MOF@WA wood-based evaporator. This evaporator exhibits high photothermal conversion efficiency and evaporation rate, and can be used for solar-driven water evaporation at a solar irradiance of 1 kW / m². 2 Its evaporation rate reaches 2.5594 kg·m³. ‑2 ·h ‑1 It can effectively purify seawater at a low cost.

The present application relates to the technical field of power control, and particularly relates to a risk assessment method and device for distributed photovoltaic access to a medium and low voltage distribution network. The solar irradiance, residential load and commercial load of the distributed photovoltaic access to the medium and low voltage distribution network are obtained. The solar irradiance is input into a self-adaptive partitioned hybrid estimation model to obtain a hybrid probability density function value. Based on the hybrid probability density function value, the residential load and the commercial load, a joint distribution function is determined. Based on the joint distribution function, a three-element Gaussian function is determined. Based on the three-element Gaussian function and the output correlation scenario of Monte Carlo, the output data of the solar irradiance node, the output data of the residential load node and the output data of the commercial load node are determined. Based on the output data of the solar irradiance node, the output data of the residential load node and the output data of the commercial load node, the risk index value of the corresponding node is determined. In this way, the present application can accurately assess the risk of the medium and low voltage distribution network.

The application discloses a kind of solar irradiance scene generation method considering multiple time dimensions and related devices, comprising: obtaining extraterrestrial radiation data of target geographic position, daily clearness index sequence is constructed based on the extraterrestrial radiation data of target geographic position;Get symbolic aggregate approximation sequence;Get several types of daily clearness state DCS;State transition vector is constructed, and the DCS sequence of continuous multiple days is generated based on the state transition vector and several types of daily clearness state DCS;In each type of daily clearness state DCS in the DCS sequence, a corresponding SAX symbol sequence is randomly selected, and the daily clarity index sequence is generated according to the conditional probability distribution corresponding to each symbol in the selected SAX symbol sequence, the daily clarity index sequence is substituted into clearness radiation model, and the total radiation data of time in day is calculated, and the solar irradiance scene is constructed based on the total radiation data of time in day, the method and related devices generate solar irradiance scene, and the scene authenticity and diversity are higher.

Disclosed are a short-term irradiance prediction method based on image processing and multimodal data fusion, a device thereof and a storage medium in the field of solar irradiance prediction. The method includes the following steps: acquiring irradiance data, and carrying out blurring processing on the irradiance data, where the irradiance data which has been subjected to blurring processing includes time information and irradiance information; converting the time information into an image layer containing the position of the sun, and drawing a circular area with the solar imaging center coordinate as the center and the radius r to obtain a time information layer image; fusing a normally exposed all-sky image, an underexposed all-sky image and a time information layer image, inputting the fused image data into a pre-built short-term solar irradiance prediction model, outputting a short-term irradiance prediction value.

The application discloses a double-layer breathing roof execution end cooperative control method based on multiple non-electric variable representation quantities, and belongs to the technical field of operation control of sun-shading, shielding and opening and closing devices at building openings. The inner layer and the outer layer of the double-layer breathing roof are internally provided with a reversible sun-shading plate and upper and lower layer movable sun-shading louvers, and constitute adjustable sun-shading and shielding devices at the roof opening. According to indoor and outdoor temperatures, humidity, solar radiation, rainfall intensity and lighting requirements, the method cooperatively adjusts three light-shading postures of the reversible sun-shading plate, i.e., high reflection, heat absorption and vertical lighting, and the opening and closing angles and the opening and closing states of the upper and lower layer movable sun-shading louvers, so as to adjust the light-shading area, the light-shading position and the shielding state of the roof opening, realize the cooperative control between sun-shading, lighting, rainproof and opening and closing, and stably switch the light-shading and shielding states according to priorities and minimum holding time.

This invention discloses a flexible operation method and system for a carbon capture power plant coupled with solar energy and membrane absorption. This invention relates to the field of energy optimization technology and includes the following steps: obtaining the initial liquid level values ​​of the rich solvent and lean solvent storage tanks, and collecting predicted data on electricity prices and solar irradiance during the control period; calculating the heat supplied to the reboiler by the solar thermal collector based on the solar irradiance; automatically introducing steam extracted from the turbine to supplement the heat load if the heat supply is insufficient; constructing an optimization decision model with the goal of maximizing overall operating benefits, where the decision variables are the rich solvent mass flow rate and absorbent concentration entering the reboiler at each time period; outputting the optimal rich solvent mass flow rate and corresponding absorbent concentration; and controlling the rich solvent flow rate entering the reboiler by adjusting the conveying equipment to achieve optimized operation. This invention improves the safety and stability of resource utilization and further optimizes the overall efficiency of carbon capture.

The application relates to the field of photovoltaic irrigation technology, in particular to a self-circulation irrigation landscape belt construction method and system integrated with photovoltaic power supply, which comprises the following steps: collecting the surface temperature of a solar irradiance cell panel, output voltage, soil moisture content, pipe flow rate and lift pressure, generating a photovoltaic power supply distribution map and an irrigation energy consumption mapping table, forming energy supply control parameters according to the energy flow supply-demand difference and the balance state, adjusting pump driving and valve control logic and establishing an energy-water coordinated control matrix, and completing the topological reconstruction of the irrigation water flow recovery branch and the photovoltaic power supply loop. In the application, the spatiotemporal coupling relationship between energy supply change and irrigation demand is constructed, the pump driving valve control and water supplement path are linked and corrected, the irrigation matching degree and energy utilization rate are improved, the water and electricity circulation continuity and operation stability of the landscape belt are enhanced, the water supply mismatch and pressure fluctuation are relieved, the vegetation water supplement balance is improved, and the circulation loss and maintenance pressure are reduced.

This invention discloses a fast MPPT system based on photovoltaic model fitting, comprising: a photovoltaic model parameter identification and fitting module, which constructs the objective function and error function required for model parameter identification and solves them using a cloud drift optimization algorithm; a maximum power point voltage search module, which, before each MPPT start, inputs the real-time ambient temperature T and solar irradiance G into an offline-trained BP neural network to obtain the current model parameters, and uses a goat optimization algorithm to search for the maximum power point voltage within a dynamic boundary determined by the open-circuit voltage; and a photovoltaic reference voltage control output module, which uses a dual closed-loop structure to receive the maximum power point voltage, and sets the PWM duty cycle of the buck and boost switches in segments according to the PID output value, so that the photovoltaic array operates at the maximum power point. The fast MPPT system based on photovoltaic model fitting provided by this invention intelligently and quickly locks the maximum power point through a herd of goats, and then uses dual closed-loop fine voltage control to keep the array in a state of high-efficiency power generation.