317 results about "Solar irradiance" patented technology

Provided in the present invention is a power prediction method for distributed photovoltaic power stations, the method comprising: acquiring a satellite cloud image of distributed photovoltaic power stations at a historical moment and a satellite cloud image of the distributed photovoltaic power stations at a current moment to predict satellite cloud image features at a future moment; selecting several photovoltaic power stations to install solar irradiance collection apparatuses, and on the basis of the satellite cloud images, collected solar irradiance, and location information of the photovoltaic power stations, calculating the solar irradiance of all the photovoltaic power stations; on the basis of the satellite cloud image features at the future moment and the collected solar irradiance of the photovoltaic power stations, obtaining the solar irradiance of the distributed photovoltaic power stations at the future moment; and on the basis of the solar irradiance of the distributed photovoltaic power stations at the future moment and weather forecast information at the future moment, predicting the power of the distributed photovoltaic power stations at the future moment. In the solution of the present invention, solar irradiance data is expanded, and a mapping relationship between satellite cloud images and solar irradiance and a mapping relationship between solar irradiance and power are constructed by means of prediction, so that the power of distributed photovoltaic power stations is predicted, thereby improving the prediction precision.

The invention relates to the technical field of solar irradiance prediction, and discloses a solar irradiance prediction method and system based on data fusion, and the method comprises the steps: obtaining a cloud layer gray image, a wind speed vector, a terrain elevation, a slope inclination angle, a solar azimuth angle and an elevation angle, calculating the movement speed and direction of a cloud layer based on the cloud layer image and the wind speed vector, and obtaining a prediction result. Calculating a shielding path in combination with a terrain elevation and a sun position; generating a terrain shielding influence coefficient matrix; fusing a gradient and shielding data to generate a dynamic effect graph; performing cloud-ground shielding analysis based on the dynamic effect graph and a cloud trajectory to obtain cloud-ground coupling influence distribution; using a random forest algorithm to fuse the coupling distribution and the shielding coefficient to calculate an initial irradiance probability, and forming a preliminary prediction result; and inputting the time sequence prediction model, the cloud trajectory and the shielding coefficient into a trained time sequence prediction network, and outputting an optimization result. According to the method, prediction requirements under complex terrains and rapid weather changes can be met.

The invention discloses a real-time calculation method and system for distributed photovoltaic power generation meteorological elements, and solves the technical problem of regional distributed photovoltaic power generation meteorological information loss. The method comprises the following steps: selecting adjacent sites based on power station operation data, and repairing target site data by using adjacent site data; constructing an irradiance calculation model by using the reconstructed power data, and establishing a model among numerical weather forecast, distributed photovoltaic station power, irradiance and environment temperature; and based on the established model, calculating the solar irradiance and temperature of the position of the distributed photovoltaic station by taking the real-time power and the current value of the numerical weather forecast as input. In order to complement the power of the distributed photovoltaic station, a meteorological information calculation model is established, a high-cost-performance and high-precision solution is provided for complementing the meteorological information of distributed photovoltaic power generation, and the accuracy of output power prediction of the distributed photovoltaic station is improved.

A system and method are disclosed for AI-orchestrated multi-source renewable energy harvesting and decentralized trading. A plurality of energy harvesting nodes convert renewable resources, including solar irradiance, wind, hydrodynamic flow, salinity gradients, geothermal heat, and waste-heat streams, into electrical power. Each node includes a sensor array that measures operating and environmental parameters and an edge AI processing unit that predicts performance degradation and computes control actions to maximize net power output subject to stress constraints. A power conversion subsystem conditions the generated power for delivery to storage, microgrids, or utility grids. A blockchain-based orchestration layer receives validated energy summaries, tokenizes discrete energy quanta as digital energy tokens with provenance metadata, and executes smart contracts for peer-to-peer trading, dynamic pricing, and programmable revenue distribution. A fleet-level AI coordination module performs federated learning across nodes and coordinates dispatch and curtailment among heterogeneous modalities, improving portfolio efficiency, grid stability, and environmental accounting.

The invention relates to the technical field of photovoltaic power generation, in particular to a photovoltaic effective solar irradiance measurement method, which comprises the following steps of: converting optical power into irradiance and tracing the irradiance to an SI unit system by taking trap detection transmitted by a low-temperature radiation meter as an optical power standard device and combining a precise diaphragm; respectively collecting the output voltage of the total radiometer, the output voltage of the monitoring radiometer, the zenith angle of the total radiometer in the non-shielding state and the solar irradiance output by the absolute radiometer when the total radiometer is in the shielding state and the non-shielding state, and calibrating the total radiometer; angle response, temperature response, sensitivity linear response and spectral response data of the total radiometer and the photovoltaic module under different influence parameters are obtained, a correction coefficient set is obtained through fitting and used for conducting temperature, angle, irradiance linearity and spectral mismatch correction on the irradiance measured by the total radiometer, photovoltaic effective solar irradiance data are obtained, and the photovoltaic effective solar irradiance data are obtained. Accurate measurement of the solar irradiance for photovoltaic power generation is realized.

The invention discloses a large-range high-frequency all-sky earth surface solar irradiance machine learning estimation method and system suitable for a cloudy area, and relates to the technical field of irradiance estimation, and the method comprises the steps: obtaining earth surface radiation observation data, generating a station position table, and constructing a training data set; constructing a ground solar radiation degree model, and dividing the training data set into a training set and a test set according to a proportion of 80% to 20%; determining hyper-parameters of the Xgboost algorithm through parameter search, training the model on the training set, and checking the model by using the test set; new satellite reflectivity is used for observing data and meteorological elements, data cleaning is carried out, and the model is input to estimate the space-time distribution of the total solar radiation irradiance of the earth surface. According to the method, the space and time precision of radiation inversion is improved, the complex nonlinear characteristics and data interaction relation are accurately captured, efficient inversion of the earth surface solar radiation degree is achieved, and the prediction performance and generalization ability of the model are remarkably improved.

The invention provides a multi-source feature fusion method for abnormal value self-correction and meta-learning confrontation of cloud cluster shielding features of a power distribution network in extreme weather. The method comprises the following steps: step S110, extracting and predicting cloud cluster shielding features; step S120, screening out meteorological variables with relatively high correlation with the solar irradiance; step S130, based on the cloud cluster shielding characteristics in the step S110, generating a cloud cluster shielding space range; step S140, executing abnormal value detection and correction for the space range shielded by the cloud cluster generated in the step S130; and step S150, fusing the corrected cloud cluster shielding features with meteorological variables based on a generative adversarial network algorithm of meta learning. Compared with a traditional method, focusing of a sudden change area under extreme weather is more accurate, and the high precision and efficiency of cloud cluster shielding feature extraction and prediction are remarkably improved.

The invention discloses a composite new energy electric power spot transaction auxiliary decision-making system and method, and belongs to the technical field of electric power transaction. The data collection module is used for continuously collecting a wind speed real-time monitoring value, solar irradiance measurement data, dynamic electricity price information of an electric power spot market, historical transaction records and charge state and charge and discharge capacity data of an energy storage battery; the prediction optimization module is connected with the data acquisition module and comprises a wind speed sudden change prediction sub-module and a cloud layer shielding sudden change prediction sub-module; the multi-source collaborative decision-making module is used for receiving an output result of the prediction optimization module and comprises a strategy generation unit, a risk assessment unit, a scheme screening unit and a decision-making execution unit; and the feedback learning module is used for executing closed-loop optimization after each transaction is completed. According to the invention, through four technical innovations of a special mutation prediction model, three-level collaborative dynamic optimization, self-learning risk prevention and control and energy storage life protection, the prediction precision in composite new energy electric power spot transaction is effectively improved.

The present application relates to the technical field of interval prediction, and discloses a solar irradiance interval prediction method and apparatus, a computer device, and a storage medium. The method comprises: acquiring a historical environment parameter data set and a first environment parameter data set within a prediction pending period, and determining a first environment sample data set; establishing a target solar irradiance prediction model; inputting the first environment parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within the prediction pending period; on the basis of the first environment sample data set, using a bootstrap sampling method to perform interval prediction on the solar irradiance prediction result within the prediction pending period to obtain a target solar irradiance interval prediction result within the prediction pending period. According to the present application, both the similarity and regularity of historical data and the complexity and accuracy of the model are considered. Furthermore, using the bootstrap sampling method to perform interval prediction on the solar irradiance prediction result effectively improve the reliability and confidence of the prediction result.

The invention relates to the technical field of new energy, and discloses a photovoltaic array fault intelligent diagnosis method and system, and the method comprises the steps: collecting the historical operation data, assembly temperature and solar irradiance data of a photovoltaic string in a normal state and a fault state, and taking the data as an original sample feature data set; preprocessing the original sample data, and randomly dividing the original sample data into a training data set, a verification data set and a test data set; based on an LSTM-CNN-ArcLoss fusion network algorithm, constructing an intelligent fault diagnosis model of the photovoltaic array; and inputting the training data set, the verification data set and the test data set into a photovoltaic array intelligent fault diagnosis model, and outputting a photovoltaic string fault classification result by the photovoltaic array intelligent fault diagnosis model. The method not only can effectively reduce the operation and maintenance difficulty, save the operation and maintenance cost and improve the operation efficiency, but also assists the photovoltaic power station to continuously, stably and efficiently operate, and has certain engineering application value and economic and social benefits.

The invention discloses a solar irradiance prediction system and method based on dual attention multi-modal fusion. The method comprises the following steps: performing spatial feature extraction on a sky imaging observation map after preprocessing and time synchronization by using a MobileNetV2 network to obtain a sky imaging time sequence feature sequence; inputting the sky imaging time sequence feature sequence into a DAT model to obtain a global sky imaging time sequence feature sequence, a local sky imaging time sequence feature sequence and a local convolution position coding residual term; obtaining an aggregated sky imaging time sequence feature sequence according to the global sky imaging time sequence feature sequence, the local sky imaging time sequence feature sequence and the local convolution position coding residual item; performing time-dependent modeling on the meteorological observation data by adopting a long short-term memory network to obtain a meteorological observation data feature sequence; and performing feature fusion on the aggregated sky imaging time sequence feature sequence and the meteorological observation data feature sequence through a trans-attention mechanism to obtain a fused joint feature sequence for solar irradiance prediction.

The embodiment of the invention provides a method and device for determining the numerical value of solar irradiance in a preset time period, and relates to the technical field of solar energy. The method comprises the following steps: acquiring satellite cloud picture extrapolation data information and radar extrapolation data information, and performing data fusion processing on the satellite cloud picture extrapolation data information and the radar extrapolation data information to obtain fused feature data information; inputting the fused feature data information into a weather typing model, and processing the fused feature data information based on the weather typing model to obtain cloud picture feature data information; and inputting the cloud picture feature data information into a solar irradiance model, and performing prediction according to the cloud picture feature data information based on the solar irradiance model to obtain a numerical value of the solar irradiance in a preset time period. By adopting the technical scheme, the numerical value of the solar irradiance in the preset time period can be accurately predicted, so that the precision and timeliness of the numerical value of the solar irradiance can be met.

The invention relates to a photovoltaic power interval prediction method based on time sequence decomposition and conformal quantile regression, and the method comprises the steps: collecting historical power data, solar irradiance data, temperature data, relative humidity data and wind speed data of a photovoltaic power station, supplementing missing values in the photovoltaic power data through employing a linear interpolation method, and carrying out the prediction of the photovoltaic power interval. Secondly, normalizing all data by using a Z-Score standard method, dividing the processed data into a training set, a calibration set and a test set, constructing a time sequence decomposition model based on a NeuralProphet framework, obtaining a deterministic prediction model, training two conditional quantile models respectively by using a quantile regression method, and obtaining a time sequence decomposition model based on the NeuralProphet framework; the method comprises the following steps: determining a power interval upper limit and lower limit prediction model according with a preset confidence level, deploying the model in a calibration set, calculating to obtain an empirical quantile, inputting test data into the constructed model, determining a final prediction interval, and realizing interval prediction of ultra-short-term photovoltaic power.

The invention discloses a preparation method of a composite micro-groove super-hydrophobic low-ice-adhesion photo-thermal film. The preparation method comprises the following steps: (1) constructing a low-elasticity-modulus photo-thermal composite sponge substrate through a solvothermal method; (2) uniformly coating the surface of a substrate with a polydimethylsiloxane (PDMS) precursor solution by adopting an aerosol-assisted deposition technology, and carrying out thermocuring to form a functional composite interface layer; and (3) constructing a multi-stage scallop surface-imitating micro-nano groove composite structure on the surface of the interface layer by using a femtosecond laser micro-nano processing technology. The prepared film has super-hydrophobicity, the surface of the film is in a Cassie-Baxter wetting state with a 164-degree contact angle and a 1-degree rolling angle, and the film has a surface self-cleaning function. Under the icing condition, the adhesion strength of an ice layer of the system is obviously reduced to 2.57 kPa, the static delay icing time is effectively prolonged to 1587 s, and the system has the photo-thermal response characteristic and can realize rapid icing ablation under the standard solar irradiance; the preparation method has the characteristics of high process controllability, environment friendliness and the like, and is suitable for large-scale continuous production.

The invention provides a new energy field station AGC distribution method for power distribution, and the method comprises the steps: obtaining the characteristic information of a target photovoltaic power station, and the characteristic information at least comprises the grid-connected point voltage value of the photovoltaic power station, the environment temperature of the photovoltaic power station, and the solar irradiance task profile data; based on the characteristic information, an improved droop control strategy is adopted to calculate the reactive power of the photovoltaic power station; obtaining a reactive power regulation margin based on the reactive power of the photovoltaic power station; generating an active power distribution instruction based on the reactive power regulation margin, the distribution instruction being used for distributing active power; a photovoltaic power supply fatigue loss model is established, a photovoltaic power supply fatigue loss result is obtained, and photovoltaic power supply loss at least comprises IGBT loss and capacitor loss; based on the photovoltaic power supply fatigue loss result, a photovoltaic reactive power optimal distribution model is established, and based on the photovoltaic reactive power optimal distribution model, a distribution strategy is generated, and the distribution strategy is used for distributing reactive power.

The invention relates to the technical field of photovoltaic power prediction, in particular to an ultra-short-term prediction system and method based on image analysis, and the system comprises an all-sky imaging data processing module, a cloud layer dynamic feature calculation module, a solar irradiance change prediction module, a photovoltaic power generation power calculation module and a prediction model optimization training module. According to the method, the cloud layer thickness, transparency, movement direction and coverage rate change are calculated, the cloud layer dynamic characteristic analysis precision is enhanced, and the radiation scattering coefficient is calculated in combination with the direct solar light shielding ratio, the cloud layer characteristics and the solar angle, so that the irradiance calculation is more accurate, the illumination change rate is analyzed, and the short-term irradiance trend is dynamically adjusted; the total power is calculated and the shielding influence is adjusted in combination with component arrangement, so that the power prediction is more practical, the input data is normalized, the time sequence sample is enhanced, the dynamic adjustment of the model parameters is optimized, and the adaptive capacity and the prediction stability are improved.

The invention provides a solar irradiance prediction method based on a multi-scale convolution echo state network, and the method comprises the steps: 1, obtaining the solar irradiance data of different time scales in different regions according to different set time and places; 2, dividing the solar irradiance data into four parts according to seasons, and then dividing the solar irradiance data into two parts according to training data and test data; step 3, combining the multi-scale convolutional neural network MCNN and the echo state network ESN to construct a multi-scale convolutional echo state network MCESN model; step 4, the MCNN in the MCESN model is trained, and the output connection matrix Wout of the ESN in the MCESN model is solved; and 5, performing solar irradiance prediction by using the MCESN model to obtain a prediction result. According to the method, the MCESN prediction model with high prediction precision and high training speed is designed; and the MCNN is adopted to extract solar irradiance characteristic information on different time scales so as to improve the prediction precision. And encoding and fitting the extracted feature information by adopting the ESN so as to improve the prediction efficiency.

The present invention provides a high-efficiency buoyancy-driven convection-based 3D solar evaporator designed for the simultaneous rejection of salt and stable evaporation of high salinity water. The product combines different strategies, including engineered wick structure, low tortuosity macrochannels and edge-preferential salt crystallization. As a result, this evaporator demonstrates a stable evaporation rate of at least 2.5 kg m−2 h−1 under solar irradiance of 1 kW m−2 with sea water or salt solution of salinity of over 8 wt %.

The invention discloses a distributed photovoltaic ultra-short-term solar irradiance prediction method based on multi-scale spatial-temporal feature fusion, and the method comprises the steps: constructing a multi-source spatial adjacency matrix through fusing a geographic distance adjacency matrix, a historical correlation matrix and a dynamic adjacency matrix generated by a graph self-attention network; therefore, the inter-site spatial dependency relationship is dynamically captured. Meanwhile, multi-scale time features are extracted in combination with a convolutional long-short-term memory network, dynamic weighted integration of spatial-temporal features is finally realized through a gating fusion unit, and high-precision prediction of future ultra-short-term irradiance is completed. A verification result on a certain eight distributed photovoltaic station data set shows that the model is remarkably superior to a traditional neural network model under different weather conditions, and particularly, the model shows higher adaptability and prediction precision in sudden change weather and an irradiance peak value interval; and reliable technical support can be provided for distributed photovoltaic power station power prediction and power grid dispatching.

The invention relates to the technical field of irradiance estimation, in particular to an irradiance estimation method and device, electronic equipment and a storage medium, and the method comprises the following steps: obtaining ground site historical data of a research region, reanalysis data of the research region and an aerosol public data set; dividing weather types into clear sky samples and cloudy sky samples according to the obtained historical ground station data of the research area; inputting the clear sky sample, the reanalysis data and the aerosol public data set into a solar irradiance model to calculate clear sky expected irradiance GHIcs; obtaining observation data of a geostationary orbit meteorological satellite, and estimating a cloud cover coefficient CI by using satellite reflectivity; inputting the multi-cloud sky sample and the cloud cover coefficient CI into a cloud index-based semi-empirical model, and calculating a clear sky coefficient Kc; and multiplying the clear sky expected irradiance GHIcs by the clear sky coefficient Kc to obtain an irradiance estimation value under the all-sky condition. Through the improvement of the method, the regional adaptability and the estimation accuracy of irradiance estimation are improved.

Methods and systems for improving the charging of battery electric vehicles (BEVs) using solar irradiance. For example, a computing system may be configured to obtain sensor data from a plurality of vehicles, where the sensor data is indicative of sensor measurement data acquired by a perception sensor of the respective vehicle, a time the sensor measurement data was acquired, and a pose of the vehicle. The computing system may be configured to, based on the sensor data from the plurality of vehicles, determine a plurality of solar irradiance levels for a plurality of locations within a geographic area. The computing system may be configured to generate a map layer, the map layer being indicative of a respective solar irradiance level for each of the plurality of locations. The computing system may be configured to output the map layer for integration into map data associated with the geographic area.

The invention provides a solar energy-radio frequency energy dual-driven low-altitude polarization switching dynamic power management system, and relates to the technical field of low-altitude flight. The system integrates a high-efficiency solar energy collection unit and a radio frequency energy collection unit with dynamic polarization adaptive switching capability, is assisted by a high-performance hybrid energy storage unit, and carries out unified coordination control through an intelligent power management unit. The radio frequency energy collection unit adopts a reconfigurable antenna technology, can sense the polarization characteristic of an environment radio frequency signal in real time, and dynamically switches the polarization state of an antenna to maximize the instantaneous energy capture efficiency; the intelligent power management unit executes a dynamic and collaborative energy flow scheduling strategy based on comprehensive analysis of solar irradiance, environment radio frequency spectrum and polarization characteristics, energy storage unit state, future energy income and expenditure prediction and real-time load demand; and the energy self-sustaining capability, the task endurance time and the working stability of low-altitude equipment in a complex and changeable environment are improved.

The invention relates to the technical field of power control, in particular to a photovoltaic hydrogen production power feed-forward control method and system based on shadow space-time prediction. The method comprises the following steps: constructing a spatio-temporal data acquisition system, acquiring solar irradiance, atmospheric temperature, cloud layer motion trail and component surface shadow distribution data of a photovoltaic array area through a multi-dimensional sensor network, dividing a photovoltaic array into a plurality of monitoring units, and performing spatio-temporal alignment processing on real-time data, and forming a standardized data set comprising the spatial position, the timestamp and the multi-dimensional physical quantity. By constructing a multi-dimensional spatio-temporal data acquisition system, high-precision real-time sensing of photovoltaic array area shadow distribution and environmental parameters is realized, a prediction architecture fused with spatio-temporal characteristics is combined, spatial correlation between monitoring units and a time sequence rule of shadow migration are effectively captured, and prospective input is provided for power control.

The invention provides a photovoltaic power generation reliability evaluation and power prediction method considering a time-varying failure rate, and belongs to the field of renewable energy sources. The photovoltaic power generation reliability evaluation and power prediction method considering the time-varying failure rate comprises the following steps: predicting solar irradiance and temperature per hour from historical data by using Monte Carlo simulation based on a random diffusion process (SDP), and modeling a cloud transient state by using a jump diffusion process integrated in the SDP, and then establishing a reliability evaluation index and photovoltaic generating capacity prediction model of the photovoltaic system considering the time-varying failure rate, thereby more accurately evaluating the reliability of the photovoltaic power generation system and predicting the photovoltaic generating capacity.

The invention provides a photovoltaic power station generating capacity prediction method, and belongs to the technical field of photovoltaic power stations, and the method comprises the steps: carrying out the feature extraction of a photovoltaic module image, building a health state feature vector, inputting a multi-scale meteorological feature into a multi-scale meteorological fusion prediction model, and outputting a solar irradiance prediction sequence; and inputting the component health state feature vector into a component attenuation dynamic tracking model to output a power attenuation coefficient, calculating an initial power generation prediction value according to irradiance prediction and the attenuation coefficient, carrying out weighted fusion, and carrying out Kalman filtering smoothing processing and Box-Cox conversion equalization processing on a prediction deviation sequence to obtain a final prediction result. The technical problem that the prediction precision is insufficient due to the fact that photovoltaic power generation capacity prediction cannot give consideration to multi-time-scale meteorological changes and long-term attenuation characteristics of assemblies at the same time is solved.

The invention relates to the technical field of power prediction of a power system, and discloses a sample adaptive iterative training method and system for existing model tuning, and the method comprises the steps: obtaining the net load and solar irradiance data of a power distribution network; determining a payload-irradiance response intensity indicator based on the response slope within the local window; determining reference values of a truncation mode and a response mode according to statistical distribution of the indexes, and calculating a non-truncation probability of the sample in a normal power generation state; calculating the marginal response intensity of the prediction model to the solar irradiance; constructing a critical factor for capturing an inverter action boundary and a sample training weight by using a non-truncation probability; constructing a photovoltaic bistable constraint item, and constraining marginal response intensity to approach corresponding modal reference values in different states; and finally, performing parameter updating on the model based on the weighted prediction error and the bistable constraint term. According to the method, the problem of model tuning failure caused by equipment control truncation is effectively solved, and the prediction performance of the model under different operation conditions is ensured.

Lowest cost usage scheduling of an energy system during a time interval of interest is achieved by utilizing two components of learning and optimization. First, several learning methods are used to forecast energy production and if needed energy consumption of a given group of energy components as a function of historical production data, weather, and solar irradiance data collected from weather and geo reports. A classification approach is used to select the learning model. A classification approach is used to select the learning model and approach. Then, an optimization problem is formulated and solved to create the optimal schedule of energy usage during time intervals of interests for the given group of energy components subject to scheduling and equipment constraints. Accordingly, integrated iterative methods, programs, and systems are described aiming at minimizing the cost of energy consumption for the given group of energy components within time intervals of interest.

The invention relates to the technical field of atmospheric electric field simulation, and discloses an atmospheric electric field diurnal variation simulation method and system based on solar irradiance, and the method comprises the steps: obtaining historical atmospheric electric field data and synchronous environmental factor data, employing the time sequence analysis and neural network technology to extract time sequence features, generating a coupling data set, and obtaining a coupling data set; a multi-parameter model is constructed based on the coupled data set, and the multi-parameter model can accurately simulate the hysteresis effect of environmental factors on the atmospheric electric field through optimization of a convolutional neural network and a memory kernel function; independent component analysis is adopted to separate direct and scattering components of irradiance, a component action vector is generated, and the prediction performance of a multi-parameter model can be further optimized; according to the invention, efficient simulation and accurate prediction of the daily variation of the atmospheric electric field can be realized.

In one respect, disclosed is a device comprising an irradiance sensor and a diffuse isolator covering said irradiance sensor, wherein said diffuse isolator comprises a housing, baffles, aperture openings, and a window, and wherein said diffuse isolator is configured to block direct rays emanating from the sun, and wherein said diffuse isolator is configured to admit diffuse rays emanating from a region of the sky dome, and wherein said device is configured to measure diffuse solar irradiance at least from readings of said irradiance sensor. In another respect, disclosed is a device also comprising at least one additional irradiance sensor configured to view at least a substantial portion of the sky dome, and wherein said device is configured to measure diffuse solar irradiance at least from readings of said irradiance sensor and said at least one additional irradiance sensor.

The invention relates to the technical field of photovoltaic output prediction, in particular to a distributed photovoltaic output prediction method and system.The distributed photovoltaic output prediction method comprises the steps that historical time sequence data and historical photovoltaic power station output data of a distributed photovoltaic power station are collected and preprocessed, and the historical time sequence data comprise the solar irradiance, the temperature and humidity and the photovoltaic panel angle; establishing a photovoltaic output LSTM prediction model; and training the photovoltaic output LSTM prediction model by using the preprocessed historical time sequence data and historical photovoltaic power station output data, performing parameter optimization, and inputting the time sequence data acquired in real time to perform output prediction of the distributed photovoltaic power station. According to the invention, the precision of distributed photovoltaic output prediction is improved by processing historical data and optimizing the parameters of the photovoltaic output LSTM prediction model. According to the invention, not only weather-related data such as solar irradiance, temperature and humidity are considered, but also the angle of the photovoltaic panel is considered during distributed photovoltaic output, so that the accuracy of distributed photovoltaic output prediction is further improved.