- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Non-uniform distribution of sulfur vapor and its influence on Cu2ZnSnS4 thin film solar cells
摘要： Deep neural network with recurrent structure was proposed in the recent years and has been applied to time series forecasting. Many optimization algorithms are developed under the assumption of invariant and stationary data distributions, which is invalid for the non-stationary data. A novel optimization algorithm for modeling non-stationary time series is proposed in this paper. A moving window and exponential decay weights are used in this algorithm to eliminate the effects of the history gradients. The regret bound of the new algorithm is analyzed to ensure the convergency of the calculation. Simulations are done on short-term power load data sets, which are typically non-stationary. The results are superior to the existing optimization algorithms.
关键词： Recursive neural network,ADAptive Moment estimation,Time series forecast,Non-stationary data,Optimization method
更新于2025-09-11 14:15:04
-
Study of Short-Term Photovoltaic Power Forecast Based on Error Calibration under Typical Climate Categories
摘要： With the increasing permeability of photovoltaic (PV) power production, the uncertainties and randomness of PV power have played a critical role in the operation and dispatch of the power grid and ampli?ed the abandon rate of PV power. Consequently, the accuracy of PV power forecast urgently needs to be improved. Based on the amplitude and ?uctuation characteristics of the PV power forecast error, a short-term PV output forecast method that considers the error calibration is proposed. Firstly, typical climate categories are de?ned to classify the historical PV power data. On the one hand, due to the non-negligible diversity of error amplitudes in different categories, the probability density distributions of relative error (RE) are generated for each category. Distribution ?tting is performed to simulate probability density function (PDF) curves, and the RE samples are drawn from the ?tted curves to obtain the sampling values of the RE. On the other hand, based on the ?uctuation characteristic of RE, the recent RE data are utilized to analyze the error ?uctuation conditions of the forecast points so as to obtain the compensation values of the RE. The compensation values are adopted to sequence the sampling values by choosing the sampling values closest to the compensation ones to be the ?tted values of the RE. On this basis, the ?tted values of the RE are employed to correct the forecast values of PV power and improve the forecast accuracy.
关键词： Latin hypercube sampling,error calibration,photovoltaic power forecast,nonparametric kernel density estimation,typical climate categories
更新于2025-09-11 14:15:04
-
Short Term Prediction of Photovoltaic Power Based on FCM and CG-DBN Combination
摘要： Affected by many factors, the photovoltaic output power is characterized by nonlinearity, volatility and instability. Therefore, short-term forecasting models are required to have multiple inputs, levels, and categories. In order to solve the above problems and improve the accuracy of predictions, this paper proposes a combined model prediction method based on similar-day clustering and the use of Conjugate Gradient (CG) to improve Deep Belief Network (DBN). The initial method uses fuzzy C-Means Clustering Algorithm (FCM) to perform similar-day clustering on the original data according to the degree of membership. The CG-DBN prediction model is then designed according to the category, with the model ultimately being used to perform the short-term prediction of the PV output power. The proposed scheme uses data from Zhejiang Longyou power station for experimental analysis and verification, and the results were compared with the back propagation neural networks model, Support Vector Machine (SVM) model, and traditional deep belief network. The model’s predicted results are compared. Finally, it is concluded that, in the short-term PV power load forecasting, the prediction performance of the FCM and CG-DBN combination forecast model is better than the above three models and has strong feasibility in short-term PV power forecasting.
关键词： Depth belief network,Photovoltaic short-term forecast,Similar day clustering,Combined forecasting model
更新于2025-09-11 14:15:04
-
Data-Driven Photovoltaic Generation Forecasting based on Bayesian Network with Spatial-Temporal Correlation Analysis
摘要： Spatio-temporal analysis has been recognized as one of the most promising techniques to improve the accuracy of photovoltaic (PV) generation forecasts. In recent years, PV generation data of a number of PV systems distributed in a geographical locale have become increasingly available. This paper conducts a thorough investigation of the spatial-temporal correlation amongst PV generation data of distributed PV systems. PV generation data of different PV systems located at different sites may exhibit similar time varying patterns. To quantify such spatial correlation, a suitable spatial similarity metric is chosen and its applicability is examined. To evaluate the temporal correlations amongst PV generation data collected from distributed PV systems, a shape-based distance metric is proposed. A data-driven inference model, built on a Bayesian network, is developed for a very short-term PV generation forecast (less than 30 minutes). The model utilizes historic PV generation and weather data, and incorporates the above spatial similarity and temporal correlation to support the PV output forecast. The experiment results show that the proposed method achieves a promising performance compared to a number of baseline methods.
关键词： Photovoltaic (PV) output,Spatial and temporal correlation,Bayesian networks,Forecast
更新于2025-09-11 14:15:04
-
PV module fault diagnosis based on micro-converters and day-ahead forecast
摘要： The employment of solar micro-converter allows a more detailed monitoring of the PV output power at the single module level; thus, machine learning techniques are capable to track the peculiarities of modules in the PV plants such as regular shadings. In this way it is possible to compare in real-time the day-ahead forecast power with the actual one in order to better evaluate faults or anomalous trends which might have occurred in the PV plant. This paper presents a method for an effective fault diagnosis; this method is based on the day-ahead forecast of the output power from an existing PV module, linked to a micro-converter, and on the outcome of the neighbor PV modules. Finally, this paper proposes also the analysis of the most common error definitions with new mathematical formulations, by comparing their effectiveness and immediate comprehension, in view of increasing power forecasting accuracy and performing both real-time and offline analysis of PV modules performance and possible faults.
关键词： PV system,day-ahead forecast,micro-inverter,Fault diagnosis
更新于2025-09-11 14:15:04
-
[IEEE 2018 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia) - Singapore (2018.5.22-2018.5.25)] 2018 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia) - Multi-Day-Ahead PV Power Output for Improved Radial Basis Function Neural Network
摘要： Photovoltaic (PV) power output forecasting is a crucial issue in the PV power industry and power company. Nevertheless, the disadvantage of the existing PV power output forecasting models is that (cid:3)(cid:4)(cid:5)(cid:6)(cid:7) (cid:8)(cid:9)(cid:3)(cid:5)(cid:10)(cid:7) (cid:11)(cid:12)(cid:10)(cid:8)(cid:13)(cid:5)(cid:7) (cid:14)(cid:5)(cid:15)(cid:3)(cid:4)(cid:5)(cid:13)(cid:7) (cid:16)(cid:17)(cid:18)(cid:3)(cid:17)(cid:15)(cid:3)(cid:11)(cid:8)(cid:10)(cid:7) and uncertain information between the irradiation and ambient temperature caused by moving cloud, which leads to short of forecasting accuracy. This paper is to present an improved radial basis function neural network structure (RBFNN) with multi-parameters forecasting scheme to overcome above drawbacks. Result of the case study acquired by the proposed scheme is compared with two typical artificial neural network forecasting methods including radial basis function neural network (RBFNN) and back propagation neural network (BPNN). It demonstrations that the proposed model leads to better precision for forecasting PV power output.
关键词： RBFNN,PV forecast,multi-parameters
更新于2025-09-10 09:29:36
-
GIST-PM-Asia v1: development of a numerical system to improve particulate matter forecasts in South Korea using geostationary satellite-retrieved aerosol optical data over Northeast Asia
摘要： To improve short-term particulate matter (PM) forecasts in South Korea, the initial distribution of PM composition, particularly over the upwind regions, is primarily important. To prepare the initial PM composition, the aerosol optical depth (AOD) data retrieved from a geostationary equatorial orbit (GEO) satellite sensor, GOCI (Geostationary Ocean Color Imager) which covers a part of Northeast Asia (113–146? E; 25–47? N), were used. Although GOCI can provide a higher number of AOD data in a semicontinuous manner than low Earth orbit (LEO) satellite sensors, it still has a serious limitation in that the AOD data are not available at cloud pixels and over high-re?ectance areas, such as desert and snow-covered regions. To overcome this limitation, a spatiotemporal-kriging (STK) method was used to better prepare the initial AOD distributions that were converted into the PM composition over Northeast Asia. One of the largest advantages in using the STK method in this study is that more observed AOD data can be used to prepare the best initial AOD ?elds compared with other methods that use single frame of observation data around the time of initialization. It is demonstrated in this study that the short-term PM forecast system developed with the application of the STK method can greatly improve PM10 predictions in the Seoul metropolitan area (SMA) when evaluated with ground-based observations. For example, errors and biases of PM10 predictions decreased by ～ 60 and ～ 70%, respectively, during the ?rst 6 h of short-term PM forecasting, compared with those without the initial PM composition. In addition, the in?uences of several factors on the performances of the short-term PM forecast were explored in this study. The in?uences of the choices of the control variables on the PM chemical composition were also investigated with the composition data measured via PILS-IC (particle-into-liquid sampler coupled with ion chromatography) and low air-volume sample instruments at a site near Seoul. To improve the overall performances of the short-term PM forecast system, several future research directions were also discussed and suggested.
关键词： particulate matter,short-term forecast,geostationary satellite,spatiotemporal-kriging,aerosol optical depth
更新于2025-09-04 15:30:14
-
[Institution of Engineering and Technology 12th European Conference on Antennas and Propagation (EuCAP 2018) - London, UK (9-13 April 2018)] 12th European Conference on Antennas and Propagation (EuCAP 2018) - Long-Term and Short-Term Atmospheric Impairments Forecasting for High Throughput Satellite Communication Systems
摘要： In this paper, three different methodologies are employed for the prediction of atmospheric attenuation for the performance evaluation of High Throughput Satellite Communication systems. The first one is based on numerical weather predictions and in particular the ECMWF forecasts that uses high resolution deterministic forecast and the probabilistic forecasts the perturbated products. The second methodology is based machine learning algorithms, which are advanced statistical methods. The two algorithms tested in this study are the random forest and the gradient boosting, both based on regression trees. Finally, the last method that is employed is the recurrent neural networks and in particular the Long Short Term Memory. These neural networks are used for the prediction of time series using memory blocks. All the algorithms are tested using data from the ALPHASAT experiment at Chilbolton and Chilton, UK. The obtained results are very encouraging.
关键词： radiowave propagation,forecast,Ka band and above,Satellite Communications,deep learning,machine learning
更新于2025-09-04 15:30:14