- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Design of Short-Term Forecasting Model of Distributed Generation Power for Solar Power Generation
摘要： Background/Objectives: For efficient PhotoVoltaic (PV) power generation, computing and information technologies are increasingly used in irradiance forecasting and correction. Today the majority of PV modules are used for grid-connected power generation, so solar generation forecasting that predicts available PV output ahead is essential for integrating PV resources into electricity grids. This paper proposes a short-term solar power forecasting system that employs Neural Network (NN) models to forecast irradiance and PV power. Methods/Statistical Analysis: The proposed system uses the weather observations of a ground weather station, the medium-term weather forecasts of a physical model, and the short-term weather forecasts of the Weather Research and Forecasting (WRF) model as input. To increase prediction accuracy, the proposed system performs forecast corrections and determines the correction coefficients based on the characteristics and temperature of PV modules. The proposed system also analyzes the inclination angle of PV modules to predict PV power outputs. Results: In the correlation analysis of the forecasted and measured irradiance, R2 was over 0.85 for all look-ahead periods, indicating a high correlation between the two data. Conclusion/Application: In the future, the proposed forecasting system for solar power generation resources will be further refined and run in real environments.
关键词： Photovoltaic Power Forecasts,Wind Power,Forecasting System,Solar Energy,Distributed Power Generation
更新于2025-09-23 15:22:29
-
A spatiotemporal probabilistic model-based temperature-augmented probabilistic load flow considering PV generations
摘要： The probabilistic steady‐state forecasting of a PV‐integrated power system requires a suitable forecasting model capable of accurately characterizing the uncertainties and correlations among multivariate inputs. The critical and foremost difficulties in the development of such a model include the accurate representation of the characterizing features such as complex nonstationary pattern, non‐Gaussianity, and spatial and temporal correlations. This paper aims at developing an improved high‐dimensional multivariate spatiotemporal model through enhanced preprocessing, transformation techniques, principal component analysis, and a suitable time series model that is capable of accurately modeling the trend in the variance of uncertain inputs. The proposed model is applied to the probabilistic load flow carried out on the modified Indian utility 62‐bus transmission system using temperature‐augmented system model for an operational planning study. A detailed discussion of various results has indicated the effectiveness of the proposed model in capturing the aforesaid characterizing features of uncertain inputs.
关键词： PV generation,probabilistic load flow,operational planning,spatiotemporal correlation,steady‐state forecasting
更新于2025-09-23 15:22:29
-
New Optical Properties of Ice Crystals for Multi-Class Cloud Microphysics
摘要： New optical properties of ice crystals were implemented in a general circulation model (GCM). Ebert and Curry’s (1992) and Fu’s (1996) parametrizations are widely used in the GCM radiation scheme. However, the validity of the data is limited to an effective radius (size) of 130 or 140 μm. This limit exceeds the median of the effective radius of snow (~200 μm), which is computed from the multi-class cloud microphysics scheme. A comparable amount of snow exists in the upper atmosphere near the lower part of ice clouds. Although the cross section of snow (extinction probability) is smaller than cloud ice, its impact on radiation has not been properly considered so far. We constructed a new lookup table of optical properties based on recent data for an extended effective radius up to 500 μm. The old data (< 130 μm) also need to be updated with a more recent and elaborate method. We processed extensive data provided by Yang et al. (2013) and linked to the radiation module of the Korean Integrated Model (KIM). The new optical properties change the shortwave scattering features, thus increasing the heating rate. This tendency is checked in both one-dimensional and global weather forecast simulations. With the new optical properties, KIM shows better performance by reducing bias with respect to the Integrated Forecasting Systems (IFS) analysis data.
关键词： weather forecasting,optical properties,cloud microphysics,ice crystals,radiation scheme
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Improving Wind Forcing with Scatterometer Observations for Operational Storm Surge Forecasting in the Adriatic Sea
摘要： Reliable storm surge predictions rely on accurate atmospheric model simulations, especially of the sea surface pressure and wind vector. The Adriatic Sea is among the regional seas of the Mediterranean basin experiencing the highest tidal excursions, particularly in its northern side, the Gulf of Venice, where storm surge predictions are therefore of great importance. Unfortunately, sea surface wind forecasts in the Adriatic Sea are known to be underestimated. A numerical method aiming at reducing the bias between scatterometer wind observations and atmospheric model winds, has been developed. The method is called “wind bias mitigation” and uses the scatterometer observations to reduce the bias between scatterometer observations and the modeled sea surface wind, in this case that supplied by the European Centre for Medium-Range Weather Forecasts (ECMWF) global atmospheric model. We have compared four mathematical approaches to this method, for a total of eight different formulations of the multiplicative factor ?ws which compensates the model wind underestimation, thus decreasing the bias between scatterometer and model. Four datasets are used for the assessment of the eight different bias mitigation methods: a collection of 29 storm surge events (SEVs) cases in the years 2004-2014, a collection of 48 SEVs in the years 2013-2016, a collection of 364 cases of random sea level conditions in the same period, and a collection of the seven SEVs in 2012-2016 that were worst predicted. The statistical analysis shows that the bias mitigation procedures supplies a mean wind speed more accurate than the standard forecast, when compared with scatterometer observations, in more than 70% of the analyzed cases.
关键词： Sea surface wind,Atmospheric model,Forecasting,Adriatic Sea,Scatterometer,Storm surge
更新于2025-09-23 15:21:21
-
Short-Term Photovoltaic Power Forecasting Using a Convolutional Neural Networka??Salp Swarm Algorithm
摘要： The high utilization of renewable energy to manage climate change and provide green energy requires short-term photovoltaic (PV) power forecasting. In this paper, a novel forecasting strategy that combines a convolutional neural network (CNN) and a salp swarm algorithm (SSA) is proposed to forecast PV power output. First, the historical PV power data and associated weather information are classified into five weather types, such as rainy, heavy cloudy, cloudy, light cloudy and sunny. The CNN classification is then used to determine the prediction for the next day’s weather type. Five models of CNN regression are established to accommodate the prediction for different weather types. Each CNN regression is optimized using a salp swarm algorithm (SSA) to tune the best parameter. To evaluate the performance of the proposed method, comparisons were made to the SSA based support vector machine (SVM-SSA) and long short-term memory neural network (LSTM-SSA) methods. The proposed method was tested on a PV power generation system with a 500 kWp capacity located in south Taiwan. The results showed that the proposed CNN-SSA could accommodate the actual generation pattern better than the SVM-SSA and LSTM-SSA methods.
关键词： convolutional neural network,salp swarm algorithm,renewable energy,day ahead forecasting,PV power forecasting
更新于2025-09-23 15:21:01
-
Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing
摘要： A main challenge towards ensuring large-scale and seamless integration of photovoltaic systems is to improve the accuracy of energy yield forecasts, especially in grid areas of high photovoltaic shares. The scope of this paper is to address this issue by presenting a uni?ed methodology for hourly-averaged day-ahead photovoltaic power forecasts with improved accuracy, based on data-driven machine learning techniques and statistical post-processing. More speci?cally, the proposed forecasting methodology framework comprised of a data quality stage, data-driven power output machine learning model development (arti?cial neural networks), weather clustering assessment (K-means clustering), post-processing output optimisation (linear regressive correction method) and the ?nal performance accuracy evaluation. The results showed that the application of linear regression coe?cients to the forecasted outputs of the developed day-ahead photovoltaic power production neural network improved the performance accuracy by further correcting solar irradiance forecasting biases. The resulting optimised model provided a mean absolute percentage error of 4.7% when applied to historical system datasets. Finally, the model was validated both, at a hot as well as a cold semi-arid climatic location, and the obtained results demonstrated close agreement by yielding forecasting accuracies of mean absolute percentage error of 4.7% and 6.3%, respectively. The validation analysis provides evidence that the proposed model exhibits high performance in both forecasting accuracy and stability.
关键词： Performance,Forecasting,Machine learning,Photovoltaic,Arti?cial neural networks,Clustering
更新于2025-09-23 15:21:01
-
An Ensemble Learner-Based Bagging Model Using Past Output Data for Photovoltaic Forecasting
摘要： As the world is aware, the trend of generating energy sources has been changing from conventional fossil fuels to sustainable energy. In order to reduce greenhouse gas emissions, the ratio of renewable energy sources should be increased, and solar and wind power, typically, are driving this energy change. However, renewable energy sources highly depend on weather conditions and have intermittent generation characteristics, thus embedding uncertainty and variability. As a result, it can cause variability and uncertainty in the power system, and accurate prediction of renewable energy output is essential to address this. To solve this issue, much research has studied prediction models, and machine learning is one of the typical methods. In this paper, we used a bagging model to predict solar energy output. Bagging generally uses a decision tree as a base learner. However, to improve forecasting accuracy, we proposed a bagging model using an ensemble model as a base learner and adding past output data as new features. We set base learners as ensemble models, such as random forest, XGBoost, and LightGBMs. Also, we used past output data as new features. Results showed that the ensemble learner-based bagging model using past data features performed more accurately than the bagging model using a single model learner with default features.
关键词： ensemble,decision tree,bagging,Light GBM,lagged data,machine learning,random forest,XGBoost,photovoltaic power forecasting
更新于2025-09-23 15:21:01
-
Estimating Solar Insolation and Power Generation of Photovoltaic Systems Using Previous Day Weather Data
摘要： Day-ahead predictions of solar insolation are useful for forecasting the energy production of photovoltaic (PV) systems attached to buildings, and accurate forecasts are essential for operational efficiency and trading markets. In this study, a multilayer feed-forward neural network-based model that predicts the next day’s solar insolation by taking into consideration the weather conditions of the present day was proposed. The proposed insolation model was employed to estimate the energy production of a real PV system located in South Korea. Validation research was performed by comparing the model’s estimated energy production with the measured energy production data collected during the PV system operation. The accuracy indices for the optimal model, which included the root mean squared error, mean bias error, and mean absolute error, were 1.43 kWh/m2/day, ? 0.09 kWh/m2/day, and 1.15 kWh/m2/day, respectively. These values indicate that the proposed model is capable of producing reasonable insolation predictions; however, additional work is needed to achieve accurate estimates for energy trading.
关键词： neural network,energy production,photovoltaic systems,solar insolation,forecasting
更新于2025-09-23 15:21:01
-
[IEEE 2020 IEEE International Conference on Big Data and Smart Computing (BigComp) - Busan, Korea (South) (2020.2.19-2020.2.22)] 2020 IEEE International Conference on Big Data and Smart Computing (BigComp) - Transfer Learning for Photovoltaic Power Forecasting with Long Short-Term Memory Neural Network
摘要： Data-driven modeling is one of the research hotspots of photovoltaic (PV) power prediction. However, for some newly built PV power plants, there are not enough historical data to train an accurate model. Therefore, constructing a forecasting model for the PV plants lacking historical data is an urgent problem to be solved. In this paper, we propose a method to transfer the knowledge obtained from historical solar irradiance data to the output prediction. Firstly, the based on hyperparameters of the long short-term memory neural network (LSTM) are optimized and the weights in the neurons are pre-trained, then fine-tuning the deep transfer model with PV output data. In this way, knowledge can be transferred to PV output data. The from solar experimental results show that the proposed method can significantly reduce the prediction error.
关键词： Long short-term memory,Transfer learning,Photovoltaic power forecasting,Hyperparameter optimization,Data mining
更新于2025-09-23 15:21:01
-
An On-Line Low-Cost Irradiance Monitoring Network with Sub-Second Sampling Adapted to Small-Scale PV Systems
摘要： Very short-term solar forecasts are gaining interest for their application on real-time control of photovoltaic systems. These forecasts are intimately related to the cloud motion that produce variations of the irradiance field on scales of seconds and meters, thus particularly impacting in small photovoltaic systems. Very short-term forecast models must be supported by updated information of the local irradiance field, and solar sensor networks are positioning as the more direct way to obtain these data. The development of solar sensor networks adapted to small-scale systems as microgrids is subject to specific requirements: high updating frequency, high density of measurement points and low investment. This paper proposes a wireless sensor network able to provide snapshots of the irradiance field with an updating frequency of 2 Hz. The network comprised 16 motes regularly distributed over an area of 15 m × 15 m (4 motes × 4 motes, minimum intersensor distance of 5 m). The irradiance values were estimated from illuminance measurements acquired by lux-meters in the network motes. The estimated irradiances were validated with measurements of a secondary standard pyranometer obtaining a mean absolute error of 24.4 W/m2 and a standard deviation of 36.1 W/m2. The network was able to capture the cloud motion and the main features of the irradiance field even with the reduced dimensions of the monitoring area. These results and the low-cost of the measurement devices indicate that this concept of solar sensor networks would be appropriate not only for photovoltaic plants in the range of MW, but also for smaller systems such as the ones installed in microgrids.
关键词： pyranometer,irradiance monitoring network,very short-term solar forecasting,microgrids,cloud enhancement,wireless sensor network,lux-meter
更新于2025-09-23 15:21:01