201 results about "Numerical weather forecast" patented technology

The invention discloses a photovoltaic power generation power prediction method and system based on a large language model. The method comprises the following steps: converting historical power data and numerical weather forecast data into time sequence embedded representation; through cross-modal semantic alignment, semantic embedding representation is generated; constructing a natural language prompt containing task context information, encoding the natural language prompt into prompt embedding, combining prompt embedding with semantic embedding representation to form a fusion input sequence, inputting the fusion input sequence into a pre-trained large language model, and outputting implicit features; synchronously generating an initial power prediction result and a weather prediction result obtained by correcting the numerical weather prediction data through a parallel collaborative prediction mechanism; and taking the meteorological prediction result as a correction signal, performing joint optimization on the preliminary power prediction result, and outputting a power generation power prediction value. According to the method, the problem of deep fusion of heterogeneous data is effectively solved, and the prediction accuracy is improved.

The invention discloses a high-precision distributed photovoltaic output prediction method and system based on micrometeorology and feature hierarchical clustering, and relates to the technical field of distributed photovoltaic output prediction.The method comprises the steps that numerical weather forecast data are collected, an initial micrometeorological field is generated through space-time alignment and self-adaptive KNN interpolation, and the initial micrometeorological field is subjected to feature clustering; a WRF-LES system and a bidirectional LSTM are combined to establish cross-scale mapping, a dynamic residual correction field is fused to generate hectometer-level high-resolution micrometeorological data, and the problem of insufficient resolution of traditional numerical forecasting is solved. MIC and PA-DTW are used for jointly analyzing the characteristics of the power station, and dynamic clustering is achieved through a sliding time window and incremental spectral clustering. According to the method, a physical information graph network and causal expansion convolution are coupled to extract features, federal learning cross-power-station cooperative training is combined, the distributed photovoltaic output prediction precision and robustness are improved, and privacy security is considered.

The invention discloses a drainage basin intelligent flood control scheduling method and system based on digital twinborn, and relates to the technical field of flood control and disaster mitigation, and the method comprises the steps: collecting static data and dynamic data of a drainage basin, building a hydrological and hydrodynamic coupling model based on the static data and the dynamic data, and forming a drainage basin digital twinborn body; inputting the received numerical weather forecast into the digital twin of the watershed for simulation, generating a plurality of flood routing scenes in a future time period, and calculating a dynamic flood risk probability graph; the method comprises the following steps: constructing a simulation training environment by using historical flood data and a high-precision drainage basin digital twinborn body, carrying out offline training on a scheduling strategy network in the simulation training environment based on a reinforcement learning algorithm, and outputting a scheduling instruction according to a real-time drainage basin state to complete training of the scheduling strategy network. According to the method, the core problem that the traditional method is insufficient in decision timeliness and weak in adaptive capacity in an uncertain environment is effectively solved.

The invention relates to the technical field of photovoltaic prediction, in particular to a distributed photovoltaic power prediction method and system based on high-dimensional gridding numerical weather forecast, and the method comprises the steps: carrying out the standardization of the numerical weather forecast data and photovoltaic power historical data of a target region, and achieving the time-space alignment based on a preset grid, generating a gridding data set; utilizing convolution processing to extract local space features, and converting and fusing the local space features into a feature sequence containing space and historical time sequence information at the same time; modeling is carried out through an encoder-decoder architecture, an encoder excavates historical power dependence, and a decoder dynamically couples future meteorological characteristics with historical power through an attention mechanism and outputs a grid-level predicted value; aggregating to obtain a system total power prediction result; by establishing a unified space-time grid, refined alignment of data is realized, cross-space-time dynamic fusion is performed in combination with convolution and an attention mechanism, and prediction precision and stability can be kept in complex weather.

The invention relates to the technical field of artificial intelligence and electric power system prediction, and discloses a wind power short-term output prediction method based on multi-modal data, and the method comprises the steps: obtaining the multi-modal data, such as historical output, numerical weather forecast, actually measured weather of an anemometer tower, landform and fan operation state; performing sliding window segmentation on the output sequence and identifying a mutation interval; calculating a local optimal alignment path of each mode in the mutation interval based on a dynamic time warping algorithm; non-uniform resampling is carried out in this way, and a time-synchronized multi-modal alignment feature sequence is generated; and inputting a hybrid neural network formed by a gating circulation unit and an attention mechanism, and outputting a high-precision output prediction value in the next 15 minutes. The system comprises corresponding function modules. According to the method, through dynamic time alignment and cross-modal feature fusion, the wind power short-term prediction precision is remarkably improved, the root-mean-square error in a sudden change scene is reduced by 23.7%, and reliable support is provided for power grid dispatching.

The invention discloses a multi-drive process multi-factor agricultural non-point source pollution prediction method based on coupling meteorological numerical forecasting. The method comprises the following steps: firstly, introducing numerical weather forecast data, and constructing a high-precision weather driving field with kilometer-level space and hour-level time resolution by combining WRF dynamic downscaling, DEM terrain correction and conservation resampling; secondly, establishing a multi-drive process coupling model system which comprises a meteorological drive layer, a hydrological response layer, a pollutant migration layer and a crop feedback layer and is used for simulating runoff production, sediment erosion, nitrogen and phosphorus migration and transformation and crop transpiration and root nutrient absorption processes; thirdly, performing precision verification on a simulation result by using observation data, and identifying key meteorological and hydrological factors through an error transfer matrix and a sensitivity analysis method; and finally, realizing parameter adaptive correction by adopting a long short-term memory network, finishing parameter optimization in combination with a multi-target genetic algorithm, packaging the model chain through a containerization technology, and realizing cross-platform deployment and visual output of a pollution load result. The method can be used for agricultural non-point source pollution prediction and management.

The invention provides a multi-scale photovoltaic power prediction method and system fusing numerical weather forecast and a physical information neural network, relates to the technical field of photovoltaic power prediction, and realizes rolling prediction of future meteorological parameters and horizontal radiation intensity through numerical weather forecast. The authenticity and the stability of the meteorological data are effectively improved by combining quantile mapping and cascade correction of the time sequence mode attention neural network; and through combined modeling of a physical information neural network and a time sequence characteristic network, meteorological and radiation data subjected to multi-level correction and conversion are deeply fused with a photovoltaic system physical law, and high-precision prediction of photovoltaic power is realized. The whole prediction process has automatic anomaly elimination and deletion complementation capabilities, the prediction robustness under complex meteorological conditions and extreme environments is enhanced, and the sequential response and physical consistency of photovoltaic power are optimized, so that the engineering applicability and intelligent level of the system are greatly improved.

The RIME-RF spatial downscaling-based photovoltaic output prediction method comprises the steps of collecting photovoltaic power data and local meteorological observation LMD data of a photovoltaic power station in a target area, extracting common data of numerical weather forecast NWP data and the local meteorological observation LMD data, and constructing an input feature set; the method comprises the following steps: optimizing hyper-parameters of a random forest (RF) algorithm based on a frost ice optimization (RIME) algorithm, constructing an RIME-RF model, and performing spatial downscaling on numerical weather forecast NWP data; a VMD-CNN-GRU-SE attention mechanism photovoltaic power prediction model optimized based on BKA is adopted, original numerical weather forecast NWP data is combined with photovoltaic power data to train the prediction model, and numerical weather forecast NWP data after spatial downscaling is combined with the photovoltaic power data to train the prediction model. According to the prediction method, changes of fine meteorological factors influencing the photovoltaic power can be more accurately captured, downscaling errors are remarkably reduced, and short-term power prediction precision is improved.

The invention provides a wind field inversion method and device based on multi-source prior data, equipment and a medium, and the method comprises the steps: building a target function of a three-dimensional fusion wind field based on the multi-source prior data and a fluid mechanics model simulation wind field, carrying out the iterative optimization of the target function, and determining the three-dimensional fusion wind field; constructing an initial deep learning neural network model, taking the three-dimensional fusion wind field as a truth value label, inputting the urban underlying surface features, the terrain elevation and the numerical weather forecast wind field into the deep learning neural network model, and training to obtain a target deep learning neural network model; and inputting the new numerical weather forecast wind field, the urban underlying surface features and the terrain elevation into the target deep learning neural network model, and outputting a refined wind field. According to the technical scheme provided by the embodiment of the invention, through the trained deep learning neural network model, high-precision rapid inversion of the low-altitude wind field is realized without depending on laser radar and ground observation data and depending on prior information such as numerical prediction and terrain.

The invention relates to the technical field of power systems and automation thereof, in particular to a generative adversarial network-based source-load joint scene generation method, which comprises the following steps of: constructing a multi-source time sequence database and extracting weather, time, space and historical state driving factors; establishing a joint probability distribution model based on a vine connection function; taking a numerical weather forecast path and a date type as conditional input, constructing a generative adversarial network embedded with a physical constraint microloss function of the power system, and forming a physical information generator; performing dependent structure fidelity verification on the generated scene by using the joint probability distribution model; generator parameters are fixed, potential space vectors are optimized through a gradient ascending method to maximize power grid risk indexes, and a high-risk source-load joint scene set is generated. According to the technical scheme, accurate generation of the source-load joint scene which is physically feasible and reasonable in statistics and focuses on the high-risk working condition is realized, and the safe operation toughness and the risk early warning capability of the novel power system are remarkably improved.

The invention discloses a numerical weather forecast deviation correction method and system based on physical conservation optimization. The method comprises the following steps: acquiring a specified prognostic variable in a numerical weather forecast system; inputting the prognostic variable into a prediction deviation correction model pre-trained by a loss function based on physical conservation optimization so as to obtain a deviation correction prediction result of numerical weather prediction; in the loss function of the physical conservation optimization, the physical conservation optimization refers to adding part or all of Coriolis force and barometric gradient force loss, static equation constraint derivation loss and vertical integral loss to the loss function of the value weather forecast deviation correction model. The invention aims to solve the problem of systematic deviation correction in mid-term numerical forecasting, better capture the complex dependency relationship in meteorological data, quantify the uncertainty of numerical weather forecasting and improve the forecasting precision.

The invention provides a micrometeorological prediction method and system, and belongs to the technical field of meteorological prediction. The method comprises the following steps: acquiring data of an unmanned aerial vehicle sensor, a ground meteorological station, satellite remote sensing and numerical weather forecast, and respectively constructing feature vectors of data sources; performing weighted average fusion on the multi-source feature vectors based on an attention mechanism at a target space-time position to obtain a fusion feature matrix; and training a target neural network by using the fusion feature matrix of the plurality of space-time positions, and taking the trained target neural network as a micro-meteorological prediction model to realize high-precision prediction of future micro-meteorological elements. According to the method, multi-source heterogeneous data and a deep learning technology are fused, the temporal-spatial resolution and accuracy of micrometeorological prediction are effectively improved, and the method is particularly suitable for unmanned aerial vehicle flight safety early warning and route dynamic optimization.

The invention discloses a transformer area distribution transformer reverse heavy overload prediction method and system, and the method comprises the steps: obtaining data which comprises the historical electrical quantity characteristics of a photovoltaic user, the numerical weather forecast characteristics of the geographic position of a transformer area, and a prior graph structure formed according to the topological graph of the transformer area; preprocessing the data to construct a data set; the method comprises the steps of establishing a space-time diagram prediction model, inputting historical electrical quantity characteristics and numerical weather forecast characteristics of N photovoltaic users and a prior diagram structure into the model to obtain a future K-step area distribution transformer load prediction result, performing heavy overload judgment based on a prediction value, and finally obtaining a future K-step area distribution transformer reverse heavy overload prediction result. According to the method, the topological structure of the power distribution network, the electrical characteristic data and the numerical weather forecast characteristics are comprehensively utilized, high-precision prediction of the multi-time-step power of the photovoltaic grid-connected system is achieved through the space-time diagram neural network model, and the method is suitable for application scenes such as operation optimization and early warning management of the power distribution network with distributed photovoltaic access.

The invention relates to the technical field of aerospace meteorology, and particularly discloses a domestic numerical weather forecast mode-based evaporation waveguide height determination method, which comprises the following steps of: obtaining meteorological coupling data output by a domestic numerical weather forecast mode CMA-MESO; determining parameters according to the meteorological coupling data and a turbulent flux algorithm COARE; constructing a temperature vertical profile and a specific humidity vertical profile according to the parameters, the Monin-Obchhoff similarity theory and an NPS model; constructing a modified refractive index profile according to the temperature vertical profile and the specific humidity vertical profile; and determining the height of the evaporation waveguide according to the height corresponding to the lowest point of the corrected refractive index profile. The method is suitable for determining the evaporation waveguide height in a domestic business meteorological mode.

The invention discloses a wind power prediction error decoupling evaluation method considering unit faults and real-time capacity changes. The method comprises the following steps: combining an actual wind power plant prediction process, and dividing wind power prediction into three links of numerical weather prediction, wind-electricity model conversion and power correction; for a power correction link, a unit fault prediction model is constructed, capacity reduction caused by faults is pre-judged in advance, a health index and a capacity attenuation coefficient are combined, a fault unit is removed in real time, the available capacity of the unit is dynamically corrected, and the equivalent actual capacity is calculated according to the health index in a weighted mode; finally, the equivalent actual capacity of the remaining unit is introduced into an error decoupling model, and quantitative evaluation is conducted on prediction errors caused by all links. And determining the proportion of the prediction error caused by each link, and determining the wind power error source after considering the unit fault and the capacity attenuation. The method can realize accurate decoupling of the wind power prediction error, and is suitable for wind power plant power prediction scenes with frequent meteorological sudden change and equipment aging.

The invention belongs to the technical field of power generation power prediction, and particularly relates to a photovoltaic power prediction method based on multi-source data fusion and deep learning, and the method comprises the steps: firstly obtaining the historical power, satellite irradiance and numerical weather forecast data of a photovoltaic power station; performing preprocessing such as space-time alignment, missing value processing and abnormal value elimination, and constructing periodic time features; training a deep learning model taking a long short-term memory network as a core by using the processed data so as to capture a complex nonlinear time sequence relationship between the weather and the power; inputting the satellite and forecast data in a to-be-predicted time period into the model, and outputting a future multi-step power predicted value; and finally, carrying out online deviation correction and physical amplitude limiting post-processing to obtain a final prediction result. By effectively fusing multi-source data and deep learning, the precision and practicability of short-term photovoltaic power prediction are remarkably improved.

The invention provides a wind power prediction method and system based on a multivariate combination prediction model and a medium, and relates to the technical field of machine learning, and the method comprises the steps: obtaining a historical wind power data time sequence and a historical numerical weather forecast data time sequence of a wind power plant; analyzing a nonlinear dependency relationship by using correlation, and optimally training a multi-modal parallel time sequence prediction model by using a variational mode decomposition algorithm in combination with a sliding window length; and based on the final sliding window length, constructing an input sample, inputting the input sample into a multi-mode parallel time sequence prediction model, outputting future prediction values of a plurality of intrinsic mode function components, and carrying out summation to obtain a wind power prediction result. According to the method and the device, the technical problem of insufficient wind power prediction precision caused by strong volatility and nonlinearity of a wind power sequence and limited learning ability of a single prediction model in the prior art can be solved, and the wind power prediction precision is improved by combining variational mode decomposition with a machine learning model for prediction.

The invention relates to the technical field of numerical weather forecast, in particular to a meteorological large model prediction method based on a data correction model, which comprises the following steps of: firstly acquiring multi-source atmospheric observation, screening observation by topology-optimal transmission quantum annealing, and constructing a weighted error covariance; applying mass, energy and earth rotation gradient, and generating a conservation assimilation field through diffusion implicit sampling; calculating a mutual information mask and coupling a cloud top optical flow fine tuning phase; cloud motion consistent field pulse codes are sent to the symplectic decomposition pulse neural network for neural form hardware reasoning, a pulse threshold is adjusted in a closed loop to control energy drift, and an uncertainty field is output through parallel disturbance reasoning. The method has the advantages of high resolution, low power consumption and probability prediction capability, and the extreme weather path and intensity prediction precision is obviously improved.

The invention discloses an end-to-end scheduling method and system for a multi-source weather-driven urban integrated energy system. The method comprises the following steps: constructing an integrated energy system model; constructing a source load prediction model based on multi-source numerical weather forecast data in combination with historical photovoltaic output data and power load and thermal load data; the method comprises the following steps: establishing a comprehensive energy system optimization scheduling model with minimization of system operation cost as an optimization target, designing a differentiable optimization layer, and reversely transmitting the gradient of the optimization target in the scheduling model to a source load prediction model parameter to the source load prediction model through a back propagation algorithm by the differentiable optimization layer, the parameters of the driving source load prediction model are updated, and end-to-end linkage optimization from prediction to scheduling is achieved; and periodically obtaining updated multi-source numerical weather forecast data and source load data, readjusting prediction model parameters, and executing optimization solution of the integrated energy system optimization scheduling model. According to the invention, cooperative training and iterative optimization of the prediction model and the scheduling decision are realized.

The invention discloses a coastal wind turbine group generation power multi-scale space-time prediction method, which mainly comprises the following steps: carrying out space interpolation and error correction on a target wind turbine position by adopting a numerical weather forecast statistical downscaling technology, generating a high-resolution wind speed prediction sequence covering a short term and a long term, aligning and splicing the predicted wind speed, the field actually-measured wind speed, the environment and the unit operation variables into node dynamic input characteristics; the method comprises the following steps: encoding longitude and latitude and time sequence monitoring data of N fans of a coastal fan group into graph nodes, determining an edge weight according to geographic distance and wake flow coupling, and forming a fan graph network containing static and dynamic characteristics; and inputting the static and dynamic feature sequences into a graph neural network comprising a space attention layer, a time recursion layer and a physical constraint regular term, completing model training, and outputting the generated power of each fan in a plurality of time steps in the future and the total power predicted value of the fan group. The method can provide powerful support for wind power plant operation scheduling, power grid-connected management and new energy consumption.

The invention relates to the technical field of meteorological disaster monitoring and early warning and numerical forecasting fusion, in particular to an extreme gale weather forecasting method based on a weather forecasting large model, which comprises the following steps: acquiring a numerical weather forecasting three-dimensional physical field, a weather radar, a weather satellite and ground meteorological observation and assimilating the numerical weather forecasting three-dimensional physical field into a consensus field; time advances, sinking potential energy and cold pool diagnosis are obtained through a micro-downburst calculation program, coarse-resolution gust is formed through boundary layer similarity mapping and a hysteresis kernel, and a fine-scale base map is generated under cold pool frontal surface limitation through optimal transmission of advection constraint; the conditional diffusion probability generation model outputs pixel gust distribution and a threshold exceeding probability and extracts a wind damage polygon; radar, satellites, lightning and ground gust are fused, monotonous normalized flow calibration is used, parameters are updated through intersection-to-parallel ratio and shape-preserving coverage inspection and online amplitude limitation, and the credibility of spatial positioning, occurrence time and probability description is improved.

The invention discloses an interval generation and probability correction method and system for new energy power prediction, and belongs to the technical field of power system operation and control, and the method comprises the steps: generating a multi-dimensional environment feature code through numerical weather forecast data, and calling a basic point prediction model to obtain a point prediction result and basic probability distribution; inputting the multi-dimensional environment feature code and the point prediction result into a dual-channel dynamic interval generator to form a preliminary prediction interval, calculating a short-term error sequence based on the actual power of new energy power generation and historical prediction data, analyzing the trend characteristics of the short-term error sequence, and correcting the basic probability distribution according to the trend characteristics; and extracting a probability verification signal from the corrected probability distribution, feeding back the probability verification signal to an interval generator, carrying out optimization adjustment on the preliminary prediction interval, and outputting an optimized prediction interval. According to the technical scheme, the preliminary interval is generated by adopting a dual-channel mechanism, and feedback correction and closed-loop optimization are performed in combination with the short-term error trend, so that the adaptive capacity, accuracy and reliability of the prediction interval can be improved.

The invention relates to a wind power prediction method based on cross-modal space-time attention fusion. Accurate wind power prediction in different weather scenes is realized. The method comprises the following steps: preprocessing wind power numerical weather forecast data to obtain preprocessed data; performing feature extraction on the preprocessed data by adopting a Transform model to obtain a time feature; performing feature extraction on the preprocessed data by adopting a GAT model to obtain spatial features; performing dual-scale feature fusion on the time feature and the spatial feature by adopting a preset neural network to obtain a fused feature; and carrying out standardization processing on the fusion features to obtain standard wind power data.

The invention discloses a laser wind-finding radar and a data processing and assimilation method thereof. The method comprises the following steps: acquiring observation data of the laser wind-finding radar, atmospheric stability parameters and topographic relief feature data; a three-dimensional space weight distribution function is constructed based on the parameters, and initial influence weights of the observation points on surrounding grids are represented; dynamically adjusting the horizontal influence range and the vertical attenuation characteristic of the function according to the geomorphic stratification degree and the atmospheric vertical stratification change information, and generating dynamic weight distribution matched with the local atmospheric physical and topographic characteristics; the distribution serves as a space adjustment factor of an observation error covariance matrix and is introduced into a cost function, and the wind field analysis field and the dynamic weight distribution are synchronously optimized by minimizing the cost function; and outputting the optimized wind field analysis field for numerical weather forecast. According to the method, accurate and efficient fusion of observation information in three-dimensional variational assimilation is realized, and the authenticity and forecast reliability of wind field analysis under complex conditions are remarkably improved.

The invention discloses an emergency method for extreme weather prediction of a power system. The method comprises the following steps: comprehensively analyzing data from a meteorological satellite, a ground meteorological station and a radar detection system by using a multi-source data fusion algorithm; developing a precise weather prediction model by integrating numerical weather prediction, machine learning optimization and data visualization technologies; carrying out vulnerability analysis on the key components of the power system to establish a risk assessment model, and assessing the operation risk of the power system under the extreme weather event; based on a risk assessment result, a real-time monitoring system and an automatic early warning mechanism are established, and an early warning signal is sent to an electric power system operator in time; strategy measures are formulated and implemented according to different weather situations, so that reliable power supply of the key area is ensured; and according to geographical and climate conditions of different regions, configuration and function optimization are carried out on the power management software. Through accurate meteorological data processing and model prediction, the weather prediction accuracy is improved, and early warning information is sent out in time.

The invention discloses a stored photovoltaic power prediction method and device based on exogenous variable enhancement, and a medium. The method comprises the steps: obtaining the historical total generated power data of a stored photovoltaic station in a past period of time, and taking the historical total generated power data as an endogenous variable; acquiring historical state data of the energy storage equipment in the same period of time and numerical weather forecast data in a future period of time as exogenous variables; by means of the endogenous variables, the prediction result of the power of the stored photovoltaic station in a future period of time is calculated through a neural network-based stored photovoltaic station power prediction model, and then energy of the stored photovoltaic station in the future period of time is planned and reasonably dispatched; the device comprises a processor and a memory, and the processor realizes the prediction method when calling a computer program stored in the memory. A computer program is stored in the computer readable storage medium, and when the computer program is executed by the processor, the prediction method is implemented.

The invention relates to the technical field of flood control dispatching, and discloses a reservoir flood control water level dynamic control and flood recycling method and system, and the method comprises the steps: obtaining a surface rainfall forecast value of a reservoir basin based on real-time rainwater condition data and numerical weather forecast; a hydrodynamics and hydrology coupled drainage basin runoff model is driven, and an in-reservoir flood hydrograph in a predicted period is generated; judging the flood scale and grade based on the hydrograph, and when the flood is medium and small flood, calculating the dynamic flood control storage capacity of a downstream flood control object by adopting an equivalent flood control effect algorithm taking into account the pre-discharge scheduling capability; according to the dynamic flood control storage capacity, a dynamic flood control water level control value is obtained through backstepping of a water level-storage capacity relation curve of the reservoir; and finally, generating and executing a reservoir dispatching instruction based on the control value, and storing the water level of the reservoir to not exceed the dynamic value. The problems that a fixed flood control water level method is low in water resource utilization rate and inflexible in dispatching are solved, and flood resource efficient utilization on the premise of flood control safety is achieved.

The invention discloses a photovoltaic power station frequency modulation capacity prediction method based on space-time correlation. The method comprises the following steps: firstly, screening main influence factors in numerical weather forecast data and photovoltaic power data by adopting a Pearson's correlation coefficient method; then constructing a space-time fusion diffusion model combining a training time weight perception mechanism and a multi-layer attention mechanism, improving prediction performance and training efficiency, and fully mining time sequence characteristics of photovoltaic power and spatial correlation of different environments; in the data generation stage, a back diffusion method of a denoising diffusion implicit model is adopted to generate a plurality of photovoltaic power curves of a day to be predicted; finally, probability intervals of photovoltaic power under different confidence coefficients are obtained through kernel density analysis, difference calculation is conducted on the probability intervals and a grid-connected limit value curve of a power grid, and probability prediction of the frequency modulation capacity is achieved. According to the method, the probability prediction precision and the operation efficiency can be considered, and a theoretical basis and a practical tool are provided for frequency modulation capacity declaration and consumption under a new energy power system.

The invention belongs to the field of new energy power generation power prediction, and discloses a photovoltaic power prediction method in a snow covering scene and a related device. The prediction method comprises the steps of obtaining numerical weather forecast data, an accumulated snow coverage rate and an accumulated snow thickness forecast value in a snow covering scene in a prediction time period; inputting the numerical weather forecast data, the snow coverage rate and the snow thickness forecast value in the snow covering scene in the forecast time period into a pre-trained snow covering loss rate forecast model to obtain a loss rate forecast value; based on the loss rate prediction value, calculating to obtain a photovoltaic power prediction value in a snow covering scene in a prediction time period; wherein the pre-trained snow covering loss rate prediction model takes a DHKELM network as a basic training model, and is obtained by adopting layered unsupervised training. According to the method, the accuracy of photovoltaic power prediction under the snow covering condition is improved by predicting the snow covering rate and the snow thickness and fusing a physical mechanism and data driving.

The embodiment of the invention provides a dynamic resource scheduling method and system for a new energy station based on wind-solar power prediction, and the method comprises the steps: firstly generating an instructive SoC track and a deviation cost curve based on the wind-solar power prediction and a market electricity price curve in the next 24 hours, and setting an economically optimal strategic baseline and a deviation punishment mechanism for all-weather operation; secondly, intra-day high-frequency rolling prediction is carried out by using real-time numerical weather forecast data and SCADA data, so that the accuracy of short-time power prediction is improved, inherent errors of day-ahead prediction are made up, and the problem of scheduling difficulty caused by inaccurate prediction is solved. And finally, introducing an intra-day correction and decision-making mechanism based on model prediction control, and strictly controlling the deviation of a power grid dispatching instruction and intelligently balancing the deviation degree of a day-ahead SoC track while maximizing the benefit through rolling optimization solution.