- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Daily Photovoltaic Power Prediction Enhanced by Hybrid GWO-MLP, ALO-MLP and WOA-MLP Models Using Meteorological Information
摘要： Solar energy is a safe, clean, environmentally-friendly and renewable energy source without any carbon emissions to the atmosphere. Therefore, there are many studies in the field of solar energy in order to obtain the maximum solar radiation during the day time, to estimate the amount of solar energy to be produced, and to increase the efficiency of solar energy systems. In this study, it was aimed to predict the daily photovoltaic power production using air temperature, relative humidity, total horizontal solar radiation and diffuse horizontal solar radiation parameters as multi-tupled inputs. For this purpose, grey wolf, ant lion and whale optimization algorithms were integrated to the multilayer perceptron. In addition, the effects of sigmoid, sinus and hyperbolic tangent activation functions on the prediction performance were analyzed in detail. As a result of overall accuracy indictors achieved, the grey wolf optimization algorithm-based multilayer perceptron model was found to be more successful and competitive for the daily photovoltaic power prediction. Furthermore, many meaningful patterns were revealed about the constructed models, input tuples and activation functions.
关键词： prediction,photovoltaic power,meteorological input,artificial neural networks,metaheuristic optimization
更新于2025-09-16 10:30:52
-
[IEEE 2019 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) - Macao, Macao (2019.12.1-2019.12.4)] 2019 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) - An Adaptive Ramp-Rate Control for Photovoltaic System to Mitigate Output Fluctuation
摘要： Data missing in collections of time series occurs frequently in practical applications and turns out to be a major menace to precise data analysis. However, most of the existing methods either might be infeasible or could be inefficient to predict the missing values in large-scale coevolving time series. Also, the evolving of time series needs to be handled properly to adapt to the temporal characteristic. Furthermore, more massive volume of data is generated in many areas than ever before. In this paper, we have taken up the challenge of missing data prediction in coevolving time series by employing temporal dynamic matrix factorization techniques. First, our approaches are optimally designed to largely utilize both the interior patterns of each time series and the information of time series across multiple sources to build an initial model. Based on the idea, we have imposed hybrid regularization terms to constrain the objective functions of matrix factorization. Then, temporal dynamic matrix factorization is proposed to effectively update the initial already trained models. In the process of dynamic matrix factorization, batch updating and fine-tuning strategies are also employed to build an effective and efficient model. Extensive experiments on real-world data sets and synthetic data set demonstrate that the proposed approaches can effectively improve the performance of missing data prediction. Even when the missing ratio reaches as high as 90%, our proposed methods still show low prediction errors. Dynamic performance demonstrates that the methods can obtain satisfactory effectiveness and efficiency. Furthermore, we have also demonstrated how to take advantage of the high processing power of Apache Spark to perform missing data prediction in large-scale coevolving time series.
关键词： time series,missing data prediction,Apache Spark,Matrix factorization
更新于2025-09-16 10:30:52
-
[IEEE 2019 Joint Conference of the IEEE International Frequency Control Symposium anEuropean Frequency and Time Forum (EFTF/IFC) - Orlando, FL, USA (2019.4.14-2019.4.18)] 2019 Joint Conference of the IEEE International Frequency Control Symposium and European Frequency and Time Forum (EFTF/IFC) - Optical Fiber Spool with Ultralow Acceleration Sensitivity
摘要： This paper presents a power-aware scheduling algorithm based on efficient distribution of the computing workload to the resources on heterogeneous CPU-GPU architectures. The scheduler manages the resources of several computing nodes with a view to reducing the peak power. The algorithm can be used in concert with adjustable power state software services in order to further reduce the computing cost during high demand periods. Although our study relies on GPU workloads, the approach can be extended to other heterogeneous computer architectures. The algorithm has been implemented in a real CPU-GPU heterogeneous system. Experiments prove that the approach presented reduces peak power by 10 percent compared to a system without any power-aware policy and by up to 24 percent with respect to the worst case scenario with an execution time increase in the range of 2 percent. This leads to a reduction in the system and service costs.
关键词： Power management,prediction,multi-GPU,power capping,power measurement,scheduling
更新于2025-09-16 10:30:52
-
A Hybrid Probabilistic Estimation Method for Photovoltaic Power Generation Forecasting
摘要： Because of stochastic nature of weather conditions, the predictability of photovoltaic (PV) power generation is poor. Compared with the point prediction, the probabilistic prediction of PV power generation can provide more information about the underlying uncertainties, which is beneficial to the stability and safety of grid dispatching and power system. Based on random forest (RF), fuzzy C-means (FCM), sparse Gaussian process (SPGP), improved grey wolf optimizer (IMGWO) algorithm, a hybrid probabilistic estimation method, in this paper, is proposed to predict the probability of PV power generation for every hour in one day. RF algorithm is firstly used to reduce multidimensional input variables. And according to the weather patterns, FCM method is adopted to divide data and get the similar samples. Finally, a hybrid forecasting method combines SPGP and IMGWO is applied to forecast the test data. With the simulation and experimental results, the validity and reliability of the proposed model (IMGWOSP) is verified. The results show that the proposed model has improved both accuracy and practicability, so the stability and safety of grid dispatching and power system can be improved.
关键词： PV power forecast,Spare Gaussian process regression,Probability prediction,Improved grey wolf optimizer algorithm
更新于2025-09-12 10:27:22
-
Determination of the superficial citral content on microparticles: An application of NIR spectroscopy coupled with chemometric tools
摘要： This work evaluates near-infrared (NIR) spectroscopy coupled with chemometric tools for determining the superficial content of citral (????????) on microparticles. To perform this evaluation, using spray drying, citral was encapsulated in a matrix of dextrin using twelve combinations of citral:dextrin ratios (CDR) and inlet air temperatures (IAT). From each treatment, six samples were extracted, and their ???????? and NIR absorption spectral profiles were measured. Then, the spectral profiles, pretreated and randomly divided into modeling and validation datasets, were used to build the following prediction models: principal component analysis-multilinear regression (PCA-MLR), principal component analysis-artificial neural network (PCA-ANN), partial least squares regression (PLSR) and an artificial neural network (ANN). During the validation stage, the models showed ??2 values from 0.73 to 0.96 and a root mean squared error (RMSE) range of [0.061–0.140]. Moreover, when the models were compared, the full and optimized ANN models showed the best fits. According to this study, NIR coupled with chemometric tools has the potential for application in determining ???????? on microparticles, particularly when using ANN models.
关键词： Food composition,Food science,Spectroscopy,Food chemistry,MLR,PCA,PLSR,Prediction,Chemometrics,Food analysis,ANN
更新于2025-09-12 10:27:22
-
2D Image-To-3D Model: Knowledge-Based 3D Building Reconstruction (3DBR) Using Single Aerial Images and Convolutional Neural Networks (CNNs)
摘要： In this study, a deep learning (DL)-based approach is proposed for the detection and reconstruction of buildings from a single aerial image. The pre-required knowledge to reconstruct the 3D shapes of buildings, including the height data as well as the linear elements of individual roofs, is derived from the RGB image using an optimized multi-scale convolutional–deconvolutional network (MSCDN). The proposed network is composed of two feature extraction levels to ?rst predict the coarse features, and then automatically re?ne them. The predicted features include the normalized digital surface models (nDSMs) and linear elements of roofs in three classes of eave, ridge, and hip lines. Then, the prismatic models of buildings are generated by analyzing the eave lines. The parametric models of individual roofs are also reconstructed using the predicted ridge and hip lines. The experiments show that, even in the presence of noises in height values, the proposed method performs well on 3D reconstruction of buildings with di?erent shapes and complexities. The average root mean square error (RMSE) and normalized median absolute deviation (NMAD) metrics are about 3.43 m and 1.13 m, respectively for the predicted nDSM. Moreover, the quality of the extracted linear elements is about 91.31% and 83.69% for the Potsdam and Zeebrugge test data, respectively. Unlike the state-of-the-art methods, the proposed approach does not need any additional or auxiliary data and employs a single image to reconstruct the 3D models of buildings with the competitive precision of about 1.2 m and 0.8 m for the horizontal and vertical RMSEs over the Potsdam data and about 3.9 m and 2.4 m over the Zeebrugge test data.
关键词： convolutional neural networks,deep learning,building reconstruction,building detection,depth prediction
更新于2025-09-12 10:27:22
-
Machine learning–assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials
摘要： In the process of finding high-performance materials for organic photovoltaics (OPVs), it is meaningful if one can establish the relationship between chemical structures and photovoltaic properties even before synthesizing them. Here, we first establish a database containing over 1700 donor materials reported in the literature. Through supervised learning, our machine learning (ML) models can build up the structure-property relationship and, thus, implement fast screening of OPV materials. We explore several expressions for molecule structures, i.e., images, ASCII strings, descriptors, and fingerprints, as inputs for various ML algorithms. It is found that fingerprints with length over 1000 bits can obtain high prediction accuracy. The reliability of our approach is further verified by screening 10 newly designed donor materials. Good consistency between model predictions and experimental outcomes is obtained. The result indicates that ML is a powerful tool to prescreen new OPV materials, thus accelerating the development of the OPV field.
关键词： organic photovoltaics,molecular design,machine learning,high-performance materials,efficiency prediction
更新于2025-09-12 10:27:22
-
Thickness validation of modeling tools for laser cutting applications
摘要： Laser cutting of metal sheets is a well-established industrial process, however, major process changes are constantly being introduced by newer technologies, e.g. new laser technologies, higher power sources, polarization and beam shaping control units, and gas flow optimizations. The multi-physical nature of the laser cutting process makes detailed simulations complex and demanding in terms of computational and implementation efforts. The gap between accurate modeling and industrial requirements makes an experimental approach often more economically realistic. Nevertheless, efficient assessment models that utilize a trade-off between model complexity and accuracy of the response to be assessed are attractive. Such models can be used for further technological development by efficiently supporting engineers in designing and selecting optical systems. This paper revisits model assumptions of an in-house developed laser cutting model as it is validated for larger thicknesses. This model assesses polarization and beam shaping effects on the cutting performance of thin sheets. In this work, dedicated cutting experiments to assess the maximum cutting speed of stainless steel 304L of 2, 6, and 10 mm thickness for a wide range of focal point positions are conducted and compared to the model prediction. The results show that R2 of this comparison decreases from 0.99 for 2 mm thickness, to 0.58 for 10 mm. It can be concluded that the trend prediction accuracy degrades for thicker plates. Analysis of the experiments and simulation data for 10 mm plates reveals two possible phenomena that become more important with thickness: multiple reflections and instability of the melt flow dynamics.
关键词： Thickness,Modelling,Prediction,Maximum cutting speed,Laser cutting
更新于2025-09-12 10:27:22
-
Analytical prediction of laser mediated polymer melt and damage width
摘要： Far-field (remote) laser net-shape scanning has revolutionary potential across numerous applications which involve localized heating of materials. It offers a very high degree of manufacturing flexibility in concert with process repeatability, traceability and low cycle energy usage when compared to traditional tooling-based solutions if the material response can be accurately predicted. The functional mechanism of such processes is localized heating; in this work, an analytical model of the line width of phase change occurring between a 3mm thick virgin polypropylene, PP, sheet and a visually transparent 25μm thick PP film is presented. Validation of the model is provided empirically by the scanned application of a CO2 laser exhibiting a Gaussian beam profile onto reference materials at varying incident spot diameters, powers and traverse velocities. This work is of value for process parameter prediction, as this analytically based method is computationally light, enabling its real-time implementation in manufacturing environments.
关键词： Net-shape,Width,Prediction,Melt,Polymer
更新于2025-09-12 10:27:22
-
Prediction of Point of Impact of Anti-Ship Missile - An Approach Combining Target Geometic Features, Circular Error Probable (CEP) and Laser Fuze
摘要： In attacking a large ship such as an aircraft carrier, if the fuze is able to estimate the point of impact (POI) of the anti-ship missile at the end of the trajectory in real time, combined with the POI to control the different standoff, the damage effect can be effectively improved. Given that the sea surface and the deck have different reflectivity when irradiated by a laser with a wavelength of 1.06μm, this paper proposes a method for predicting the POI of an anti-ship missile by making use of known typical target geometric features, CEP and laser fuze detection information. Firstly the reflection characteristics of the sea surface and the deck were tested at a wavelength of 1.06μm, and the experiment proved that the reflectivity of the sea surface and the deck are significantly different. On this basis, the geometric features model of a typical target and the ideal missile-target distance model were established, and the missile-target distance model in consideration of CEP was further derived. Combined with the target geometric features, CEP and the detection information of the four-way laser detection device, Monte Carlo method was used to simulate the prediction of POI of the anti-ship missile. It was also shown that the POI prediction accuracy of the anti-ship missile can be effectively improved by analyzing the detection information of the multiple ballistic experience points of the anti-ship missile, and the uncertainty of POI prediction can be reduced.
关键词： Laser fuze,CEP,POI prediction,Anti-ship missile,Target geometric features
更新于2025-09-12 10:27:22