119 results about "Weather prediction" patented technology

This application discloses a method, system, and controller for predicting flight routes. The method includes dividing each segment of the flight route to be predicted into multiple sub-segments and obtaining the starting coordinates of each sub-segment; obtaining a weather forecast dataset based on the combined reflectance of various latitude and longitude grid points within a preset area; the preset area includes the area covered by the flight route; traversing each sub-segment of the flight route to be predicted according to the following method: obtaining a preset range centered on the starting point of the sub-segment; obtaining the percentage of latitude and longitude grid points within the preset range whose combined reflectance is greater than a combined reflectance threshold based on the weather forecast dataset; if the percentage is less than or equal to a first percentage threshold, the sub-segment does not need to be rerouted; if the percentage is greater than the first percentage threshold, the sub-segment needs to be rerouted. The flight route prediction method provided in this application can improve the objectivity, accuracy, and reliability of flight route prediction results.

The present invention provides a distributed power generation system, a control method for the distributed power generation system, and an output control device that can more appropriately reduce the amount of electricity purchased from the power grid and more effectively utilize the generated electricity. [Solution] A distributed power system is provided, comprising: a distributed power source; a power converter that converts the power supplied from the distributed power source into AC power corresponding to the load and supplies the converted AC power to the load; an output control device that controls the operation of power conversion by the power converter; and a power generation forecasting device that stores a power generation forecasting model that enables the prediction of the amount of power generated by the distributed power source based on weather forecasts at the locations where the distributed power source is installed, predicts the amount of power generated by the distributed power source after a predetermined time based on the weather forecasting data and the power generation forecasting model, and outputs power generation forecasting information including the predicted value of the amount of power generated, thereby enabling the planning of the demand power required by the load in advance.

This application provides a photovoltaic power prediction method and apparatus. The method includes: preprocessing real-time photovoltaic power data, meteorological observation data, and weather forecast data at the current moment to obtain power increment data corresponding to the current moment; constructing multi-dimensional features based on the power increment data to generate a real-time feature set; determining the predicted power increment corresponding to each prediction step according to the real-time feature set, and superimposing it with the real-time photovoltaic power data at the current moment to generate an initial predicted power result corresponding to each prediction step; and outputting the photovoltaic power prediction result by performing power constraint and smoothing processing on the initial predicted power result. This application superimposes power increments at multiple prediction steps and applies physical constraints and temporal verification to the prediction results, which can maintain the continuity and physical rationality of power changes during multi-timescale prediction, and enhance the accuracy of the prediction results in actual scheduling scenarios.

The application discloses a kind of short-acting rain prediction methods of fusing satellite cloud picture and radar echo, it is related to short-acting rain weather prediction field, the specific steps of this method are as follows: synchronous acquisition preprocessed satellite cloud picture and radar echo data, respectively with symmetric time series deep learning architecture extraction feature, generate dimension alignment's rainfall probability discrete distribution;Unified distribution is obtained by double mode confrontation fusion;Probability confidence calibration is carried out, and the distribution of confidence interval is generated;According to magnitude interval mapping, the output different magnitude rainfall probability and confidence interval are calculated, and the grid point prediction is completed;The application adopts symmetric time series deep learning architecture to process multi-modal data, realizes macroscopic and microscopic collaborative representation, improves the completeness and consistency of rainfall probability generation;Combined with historical sample calibration deviation, the original logic and features are retained, and the standardized grid point prediction results are output;Optimize each link in whole process, so that the prediction result is more in line with the actual, and the business adaptability and application value are improved.

The present application relates to the field of weather prediction, and specifically relates to a short-time strong convective precipitation intensity prediction method, system, device and medium, comprising: obtaining a plurality of sets of historical meteorological data of a target area; calculating an atmospheric stability index based on atmospheric vertical profile data; constructing a training sample of the atmospheric stability index, ground observation data, radar echo data and precipitation intensity label corresponding to each set of historical meteorological data; inputting the training sample into a pre-constructed ensemble tree model to predict the predicted precipitation intensity; training the ensemble tree model based on the predicted precipitation intensity and the precipitation intensity label to obtain a precipitation intensity prediction model; inputting the meteorological data of the target area into the precipitation intensity prediction model to obtain the short-time strong convective precipitation intensity of the target area. The present application can adjust the precipitation intensity output according to the real stability state of the atmosphere, thereby significantly improving the estimation ability of the strong convective precipitation intensity.

This invention discloses a lightweight modeling method, apparatus, system, and storage medium for high-dimensional data meteorological forecasting tasks, belonging to the technical field of computation, extrapolation, or counting. The method constructs prediction vectors and target variables from the original high-dimensional data required for the target meteorological forecasting task. Through an improved variational autoencoder strategy, it reconstructs latent predictor variables that influence or potentially influence the target variables from the prediction vectors. It then selects latent variables highly correlated with the original predictor variables to construct a candidate predictor variable dataset. After removing candidate variables that are significantly uncorrelated with the target variables and those with strong linear correlations from the candidate predictor variable dataset, it performs key predictor variable selection and constructs a lightweight prediction model based on the key predictor variables. This invention significantly reduces the dimensionality of the model input data while maintaining prediction accuracy, and enhances the model's prediction accuracy by constructing predictor variables that influence the target variables and have clear physical meaning.

The application discloses a power meteorological data fusion method and system based on multi-source meteorological prediction and a storage medium, and combines power meteorological monitoring and multi-source numerical weather prediction data. Through error analysis on the multi-source numerical weather prediction data, the numerical weather prediction is changed from single deterministic prediction to multi-source fusion prediction, which is beneficial to the real application of meteorological information to actual business work of the power grid. The application can provide precision evaluation of different prediction data sources, provide multi-source prediction fusion data, improve prediction precision, and provide technical support for power meteorological fine prediction.

The application discloses a numerical weather prediction optimization method and system based on meteorological resource coupling, belongs to the technical field of numerical weather prediction, focuses on the multi-source data in the target area, and constructs a double-dimension correlation between the power grid and the meteorology, integrates the meteorological resources, and is targeted to gather the power grid output, so that the subsequent numerical weather prediction is more in line with the power prediction requirements of the power grid, and through the correlation matrix and the comprehensive influence coefficient, the qualitative coupling relationship is converted into quantitative indexes, linear and nonlinear are considered, and therefore the prediction accuracy under complex weather and complex terrain is greatly improved, high-precision meteorological driving data is provided for photovoltaic short-term power prediction, and the problem that the existing numerical weather prediction is mostly based on single dimension for prediction, so that it is difficult to guarantee the numerical accuracy when facing environmental changes is solved.

The application discloses a fire-fighting situation evolution prediction method based on dynamic deep learning and belongs to the technical field of fire fighting. Through construction of a basic database and a dynamic model library, the basic database comprises local weather data in previous years, real-time weather data, short-term weather prediction data, building detailed data (including stair modeling data) and historical fire case data; the dynamic model library comprises a weather-fire correlation model, a stair modeling and air power simulation model and a dynamic deep learning prediction model, the model library is pre-trained by using the basic database data, stair modeling and air power simulation are realized, and the model library is in line with the actual building: the model is specially made for the stair, airflow influence is simulated, the fire spread in key passages such as staircases can be accurately predicted, and the effect of solving the pain point that the prior art ignores building details is achieved.

The image shown in "Image Diagram" is for displaying weather forecasts and information. This image is used to perform operations that enable the display of information regarding snow depth. Specifically, as shown in the "Reference Diagram Showing the Names of Each Part," this image has a graph area and play / stop buttons. The graph area contains an area graph that shows the snow depth over time, a depth bar which is the vertical axis of the area graph, and a time bar. The line of the area graph shows the snow depth. The area between the line and the horizontal axis of the area graph is colored with a predetermined color. The depth bar is represented by different colors in stages according to the snow depth. The time bar shows the present and is positioned to overlap with the area graph. The right side of the time bar represents the future, and the left side of the time bar represents the past. When the play / stop button is operated (tapped), time passes, and the area graph moves from right to left as time passes. The playback stops when the play / stop button is operated again. This allows the user to visually grasp the snow depth.

The application discloses a global average sea clutter near real-time estimation method, system, device and storage medium, including the following steps: obtaining multi-source satellite-borne radar historical backscattering coefficient data, and performing time and space matching and binning on the ERA5 wind field; an average sea clutter estimation model is established according to a geophysical model function fitting; the satellite-borne microwave scatterometer wind field is corrected in deviation and fused with a numerical weather prediction wind field, so that a high-coverage, continuous near real-time global sea surface wind field is obtained; the relative azimuth is calculated in combination with radar observation parameters and fused wind direction, and global average sea clutter data is obtained by using the model; the application improves the precision and application range of sea clutter estimation under the condition of medium and small incident angles, provides a high-quality input wind field through a multi-source wind field fusion technology, realizes rapid, stable and near real-time estimation of global average sea clutter, has high timeliness and business feasibility, and can meet the needs of near real-time sea clutter monitoring and ocean remote sensing application.

The application discloses a photovoltaic power prediction method, system and equipment based on dynamic correction and physical constraints, comprising obtaining data of a target photovoltaic power station and preprocessing; based on the geographical position and prediction time of the power station, adding solar position parameters and time period characteristics respectively; obtaining a preliminary power prediction sequence after fusing the characteristics; based on the element deviation between numerical weather forecast data and observed meteorological data in a historical time window, combining time decay weight, dynamically generating correction weight, and weighting and correcting the preliminary power prediction sequence to obtain a corrected power sequence; applying non-negativity constraint and installed capacity upper limit constraint to the corrected power sequence to obtain a final power prediction result. The application generates a preliminary prediction through a time series model, dynamically corrects the result based on historical prediction deviation, and finally applies physical constraints to obtain more accurate and actual photovoltaic power prediction values.

The present application belongs to the technical field of photovoltaic power generation, and relates to a kind of photovoltaic power station virtual irradiance calculation method and system based on multi-source fusion. Including: the photovoltaic module or group string in photovoltaic power station is regarded as virtual irradiation table node, and the current, voltage, temperature data and geographic position coordinates of each node are collected;The initial virtual irradiance of each node is obtained by back calculation according to the current, voltage and temperature data;The initial virtual irradiance data is fused with satellite cloud data and numerical weather forecast data, and the measured data of physical irradiation table is used for dynamic correction to obtain corrected irradiance data;The irradiance spatial distribution information of photovoltaic power station is generated based on geographic position coordinates and corrected irradiance data, and abnormal state recognition is carried out based on distribution information. The present application realizes low-cost, high-precision, high-spatial-resolution power station-level irradiance monitoring, and provides reliable data support for power generation power prediction, performance evaluation and fine operation and maintenance of photovoltaic power station.

This disclosure provides a method and system for identifying snow accumulation in photovoltaic power plants based on multi-source fusion and hierarchical lag. The method includes: collecting numerical weather forecast data, environmental monitoring data, electrical operation data, and physical mechanism data to construct a multi-source feature dataset; calculating the gain attenuation index and voltage deviation of each inverter to form snow accumulation feature indicators; identifying the inefficient state of a single inverter based on these indicators, and statistically calculating the proportion of inefficient inverters across the entire plant to generate a plant-level inefficiency proportion coefficient; inputting this coefficient into a time-series state machine with a hierarchical lag holding mechanism, and combining it with ambient temperature to determine the snow accumulation state of the photovoltaic array; finally, performing time-domain filtering verification on the snow accumulation state sequence to generate a snow accumulation event report. This invention requires no additional hardware and effectively solves the problems of high false alarm rate and fluctuating state during the snow melting period in existing technologies by utilizing plant-level statistical features and hierarchical lag logic, achieving accurate identification and quantitative assessment of snow accumulation events.

The application provides a photovoltaic power station power prediction method, system, device and medium based on cluster modeling prediction technology, which comprises the following steps: step 1, dividing photovoltaic power stations in a target area to obtain a plurality of clusters; step 2, determining a reference power station of each cluster; step 3, using the obtained reference power station to predict the power curve of each cluster in combination with a preset mesoscale weather prediction model; and step 4, using a preset electric energy calculation model to calculate a confidence interval curve, using the obtained confidence interval curve to correct the predicted power curve to obtain a predicted power curve corresponding to each cluster; and the application can improve the accuracy of regional photovoltaic power prediction.

This invention discloses a greenhouse environment control system and method based on crop organ phenotypic information, belonging to the field of greenhouse environment control technology. The method includes: acquiring historical datasets and weather forecast data; constructing a greenhouse environment prediction model; inputting the historical datasets and weather forecast data into the greenhouse environment prediction model to obtain greenhouse environmental data for the next 24 hours; constructing a crop growth prediction model; combining current environmental information and crop organ phenotypic growth information from the previous 7 days to predict crop organ phenotypic growth information to obtain predicted crop growth values; obtaining crop target values; acquiring actual crop growth values ​​using a crop organ phenotypic information acquisition platform and comparing them with the predicted values ​​to obtain the difference; determining whether to adjust the crop target values ​​based on the difference, and thus adjusting greenhouse environmental parameters. This invention incorporates crop organ phenotypic information feedback into greenhouse environment optimization and control technology, improving the yield and quality of greenhouse crops.

The application discloses a coal-powder storage and release mechanism-based thermal power generating unit control method and system, and relates to the technical field of electric power energy production and heat supply. According to historical power grid load data, historical electric power market transaction information and weather forecast information, a power grid load prediction result in a future time period is predicted; according to the power grid load prediction result in the future time period and current time boiler state data, pulverizing state data and external coal bunker state, a control strategy is determined; the control strategy is a coal-powder storage strategy or a release strategy; in the case that the control strategy is the coal-powder storage strategy, a pulverizing system and a powder feeding device are controlled to store coal powder in an auxiliary external powder bunker to a target storage amount; in the case that the control strategy is the release strategy, a release instruction is sent to the auxiliary external powder bunker, so that the auxiliary external powder bunker delivers coal powder to a boiler of the thermal power generating unit according to the release strategy. The method can accurately regulate and control the thermal power generating unit.

This invention relates to the field of new energy power generation technology and discloses a multi-model fusion wind speed correction method and apparatus. The method includes: constructing a first wind speed correction model based on radar three-dimensional wind field data, numerical weather prediction data, and measured wind speed data at wind turbine hub height; constructing a second wind speed correction model using statistical algorithms based on wind speed forecast data and wind speed observation data; constructing a third wind speed correction model using data-driven algorithms based on wind speed forecast data, wind speed observation data, and terrain data; acquiring real-time wind condition data; and performing wind speed correction based on the real-time wind condition data using the first, second, and third wind speed correction models to obtain the wind speed correction result. This invention effectively solves the adaptability problem under complex meteorological conditions and improves the accuracy of wind speed correction.

The application is suitable for the technical field of irrigation control systems, and provides an intelligent irrigation water resource control system for water distribution in irrigation areas, which comprises a control center, a sensor unit, an irrigation unit, a pump suction unit and a silt-cleaning pond, the control center comprises a real-time data module, a data-driven model and a real-time data fusion module, the real-time data module is used for receiving multi-source real-time data, the multi-source real-time data comprises soil moisture content, environmental temperature and humidity of the irrigation area and weather forecast data, the data-driven model comprises crop water requirement and growth conditions, the real-time data fusion module trains a model according to multi-source real-time data and historical data, takes a digital twin as a simulation environment, and simulates and deduces different irrigation schemes in multiple future periods before each irrigation decision, the application predicts the irrigation based on the digital twin and weather forecast, avoids the 'collision' with rainfall, and can save water by 15% to 25% in expectation.

The application relates to a greenhouse ground source heat pump heating device control method, which comprises the following steps: S1, collecting greenhouse environment information and weather forecast information; S2, calculating a target heating temperature according to the greenhouse environment information and the weather forecast information; S3, judging whether to start the ground source heat pump by comparing a current indoor environment temperature with the target heating temperature, if yes, executing step S4, otherwise returning to step S2; and S4, further calculating a water outlet target temperature, and setting the water outlet temperature as the target temperature, and then returning to step S2. Compared with the prior art, the application can fully utilize historical data and weather prediction information, dynamically adjust the starting condition of the ground source heat pump and the setting temperature of the water outlet, and is suitable for different outdoor environments, so that the energy saving and consumption reduction effect is achieved; the application has strong universality, can be applied to greenhouses of different regions and different crops by adjusting a correction model, and has important significance for actual ground source heat pump heating system regulation and control.

This application provides a method, apparatus, terminal, and storage medium for generating a background error covariance matrix, relating to the field of numerical weather prediction technology. The method includes: constructing a short-term forecast sample set for a target numerical weather prediction; extracting control variables for each background error sample in the short-term forecast sample set; calculating the regression coefficients of each control variable to construct a balance operator; inputting the short-term forecast sample set into a pre-constructed characteristic length scale field generation model, outputting the characteristic length scale field of each background error sample, and constructing a horizontal correlation operator; calculating the vertical correlation scale of each control variable at each horizontal position to construct a vertical correlation operator; calculating the background error standard deviation of each control variable at each grid point to construct a standard deviation operator; and using the balance operator, horizontal correlation operator, vertical correlation operator, and standard deviation operator to obtain the background error covariance matrix. This application can reduce the computational complexity of the horizontal correlation operator and improve computational efficiency.

This invention discloses a multivariate probabilistic prediction method and system for photovoltaic power based on mixed evaluation scores. The method includes: acquiring input information from multiple photovoltaic power plants at the time to be predicted, the input information including historical photovoltaic power generation and numerical weather forecasts; inputting the input information into a deep learning model trained with mixed evaluation scores as the loss function, and outputting the construction parameters of a conditional multivariate Gaussian mixture model; generating weights, means, and covariance matrices of multiple Gaussian components according to the construction parameters through fixed rules, and substituting them into the joint probability density function formula modeled by the conditional multivariate Gaussian mixture model to obtain the joint probability density function of future photovoltaic power generation from multiple power plants, thereby achieving joint probabilistic prediction of power generation from multiple power plants. This invention significantly improves the overall accuracy of multivariate probabilistic prediction and can accurately capture the power correlation characteristics between multiple photovoltaic power plants.

This invention provides a method, system, equipment, and medium for ultra-short-term power prediction of photovoltaic power plants, comprising the following steps: Step 1, acquiring historical meteorological data and geographical information corresponding to the area where the target photovoltaic power plant is located, as well as historical operating data of each photovoltaic power plant; Step 2, performing data preprocessing on the acquired data to obtain preprocessed data; Step 3, extracting and selecting features from the preprocessed data to obtain multiple feature values; Step 4, training the constructed ultra-short-term power prediction model using the multiple feature values ​​to obtain a trained ultra-short-term power prediction model; Step 5, predicting future meteorological data for the area where the target power plant is located using a preset mesoscale weather prediction model, and combining the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power plant; This invention can improve the accuracy of ultra-short-term power prediction for photovoltaic power plants.

This invention discloses a method, system, equipment, and medium for predicting wind turbine output under icing conditions. The method includes the following steps: acquiring historical operating data of wind turbines in a target wind farm during the icing period; processing the historical operating data using a wind power calculation method to obtain wind power data; matching the wind power data with WRF simulation forecast data along the time dimension to form a training dataset; training the training dataset using a machine learning algorithm to obtain a wind speed optimization model; obtaining optimized wind speed data; and substituting the optimized wind speed data with the temperature and air pressure from the WRF simulation forecast data into the wind power calculation formula to obtain the wind turbine output prediction result. This invention combines the WRF numerical weather prediction model with N sets of algorithms to optimize the wind speed data output by the WRF model, capturing the nonlinear relationship between wind speed and wind power under icing conditions, and improving the accuracy of wind turbine output prediction.

The application relates to the technical field of dam safety operation and maintenance, and provides a reservoir dam safety monitoring method and system based on digital twinning, which comprises the following steps: a change relationship between dam body stress and displacement is constructed through a water level stress transmission path established by a reservoir dam digital twinning model and historical stress and displacement data; after real-time stress and weather prediction data are acquired, the water level stress is predicted based on the change of the water level in combination with a physical mechanism model and a big data driving algorithm, dam body displacement prediction caused by water level change is obtained, dam body displacement prediction is monitored and early warning is performed, dynamic simulation and safety evaluation of the dam operation state are realized, and the early identification ability and prediction accuracy of dam safety hazards are improved.