Data-Driven Power Prediction for Proton Exchange Membrane Fuel Cell Reactor Systems.

Enhancing high-performance proton exchange membrane fuel cell (PEMFC) technology is crucial for the widespread adoption of hydrogen energy, a leading renewable resource. In this research, we introduce an innovative and cost-effective data-driven approach using the BP-AdaBoost algorithm to accurately predict the power output of hydrogen fuel cell stacks. The algorithm's effectiveness was validated with experimental data obtained from an advanced fuel cell testing platform, where the predicted power outputs closely matched the actual results. Our findings demonstrate that the BP-AdaBoost algorithm achieved lower RMSE and MAE, along with higher R2, compared to other models, such as Partial Least Squares Regression (PLS), Support Vector Machine (SVM), and back propagation (BP) neural networks, when predicting power output for electric stacks of the same type. However, the algorithm's performance decreased when applied to electric stacks with varying material compositions, highlighting the need for more sophisticated models to handle such diversity. These results underscore the potential of the BP-AdaBoost algorithm to improve PEMFC efficiency while also emphasizing the necessity for further research to develop models capable of accurately predicting power output across different types of PEMFC stacks.

LSTM Short-Term Wind Power Prediction Method Based on Data Preprocessing and Variational Modal Decomposition for Soft Sensors.

Soft sensors have been extensively utilized to approximate real-time power prediction in wind power generation, which is challenging to measure instantaneously. The short-term forecast of wind power aims at providing a reference for the dispatch of the intraday power grid. This study proposes a soft sensor model based on the Long Short-Term Memory (LSTM) network by combining data preprocessing with Variational Modal Decomposition (VMD) to improve wind power prediction accuracy. It does so by adopting the isolation forest algorithm for anomaly detection of the original wind power series and processing the missing data by multiple imputation. Based on the process data samples, VMD technology is used to achieve power data decomposition and noise reduction. The LSTM network is introduced to predict each modal component separately, and further sum reconstructs the prediction results of each component to complete the wind power prediction. From the experimental results, it can be seen that the LSTM network which uses an Adam optimizing algorithm has better convergence accuracy. The VMD method exhibited superior decomposition outcomes due to its inherent Wiener filter capabilities, which effectively mitigate noise and forestall modal aliasing. The Mean Absolute Percentage Error (MAPE) was reduced by 9.3508%, which indicates that the LSTM network combined with the VMD method has better prediction accuracy.

Ultra-Short-Term Offshore Wind Power Prediction Based on PCA-SSA-VMD and BiLSTM.

In order to realize the economic dispatch and safety stability of offshore wind farms, and to address the problems of strong randomness and strong time correlation in offshore wind power forecasting, this paper proposes a combined model of principal component analysis (PCA), sparrow algorithm (SSA), variational modal decomposition (VMD), and bidirectional long- and short-term memory neural network (BiLSTM). Firstly, the multivariate time series data were screened using the principal component analysis algorithm (PCA) to reduce the data dimensionality. Secondly, the variable modal decomposition (VMD) optimized by the SSA algorithm was applied to adaptively decompose the wind power time series data into a collection of different frequency components to eliminate the noise signals in the original data; on this basis, the hyperparameters of the BiLSTM model were optimized by integrating SSA algorithm, and the final power prediction value was obtained. Ultimately, the verification was conducted through simulation experiments; the results show that the model proposed in this paper effectively improves the prediction accuracy and verifies the effectiveness of the prediction model.

Short-Term Wind Power Prediction Based on Encoder-Decoder Network and Multi-Point Focused Linear Attention Mechanism.

Wind energy is a clean energy source that is characterised by significant uncertainty. The electricity generated from wind power also exhibits strong unpredictability, which when integrated can have a substantial impact on the security of the power grid. In the context of integrating wind power into the grid, accurate prediction of wind power generation is crucial in order to minimise damage to the grid system. This paper proposes a novel composite model (MLL-MPFLA) that combines a multilayer perceptron (MLP) and an LSTM-based encoder-decoder network for short-term prediction of wind power generation. In this model, the MLP first extracts multidimensional features from wind power data. Subsequently, an LSTM-based encoder-decoder network explores the temporal characteristics of the data in depth, combining multidimensional features and temporal features for effective prediction. During decoding, an improved focused linear attention mechanism called multi-point focused linear attention is employed. This mechanism enhances prediction accuracy by weighting predictions from different subspaces. A comparative analysis against the MLP, LSTM, LSTM-Attention-LSTM, LSTM-Self_Attention-LSTM, and CNN-LSTM-Attention models demonstrates that the proposed MLL-MPFLA model outperforms the others in terms of MAE, RMSE, MAPE, and R2, thereby validating its predictive performance.

Solar Power Prediction Using Dual Stream CNN-LSTM Architecture.

The integration of solar energy with a power system brings great economic and environmental benefits. However, the high penetration of solar power is challenging due to the operation and planning of the existing power system owing to the intermittence and randomicity of solar power generation. Achieving accurate predictions for power generation is important to provide high-quality electric energy for end-users. Therefore, in this paper, we introduce a deep learning-based dual-stream convolutional neural network (CNN) and long short-term nemory (LSTM) network followed by a self-attention mechanism network (DSCLANet). Here, CNN is used to learn spatial patterns and LSTM is incorporated for temporal feature extraction. The output spatial and temporal feature vectors are then fused, followed by a self-attention mechanism to select optimal features for further processing. Finally, fully connected layers are incorporated for short-term solar power prediction. The performance of DSCLANet is evaluated on DKASC Alice Spring solar datasets, and it reduces the error rate up to 0.0136 MSE, 0.0304 MAE, and 0.0458 RMSE compared to recent state-of-the-art methods.

An Adaptive Hybrid Model for Wind Power Prediction Based on the IVMD-FE-Ad-Informer.

Accurate wind power prediction can increase the utilization rate of wind power generation and maintain the stability of the power system. At present, a large number of wind power prediction studies are based on the mean square error (MSE) loss function, which generates many errors when predicting original data with random fluctuation and non-stationarity. Therefore, a hybrid model for wind power prediction named IVMD-FE-Ad-Informer, which is based on Informer with an adaptive loss function and combines improved variational mode decomposition (IVMD) and fuzzy entropy (FE), is proposed. Firstly, the original data are decomposed into K subsequences by IVMD, which possess distinct frequency domain characteristics. Secondly, the sub-series are reconstructed into new elements using FE. Then, the adaptive and robust Ad-Informer model predicts new elements and the predicted values of each element are superimposed to obtain the final results of wind power. Finally, the model is analyzed and evaluated on two real datasets collected from wind farms in China and Spain. The results demonstrate that the proposed model is superior to other models in the performance and accuracy on different datasets, and this model can effectively meet the demand for actual wind power prediction.

Prediction of Electric Power Production and Consumption for the CETATEA Building Using Neural Networks.

Economic and social development is hardly influenced by electric power production and consumption. In this context of the energy supply pressure, energy production and consumption must be monitored and controlled in an intelligent way. Due to the availability of large data measurements, prediction algorithms based on neural networks are widely used in accurate power prediction. Firstly, the particularity of our work is represented by the size of the dataset consisting of 4 years of continuous real-time data measurements collected from the CETATEA photovoltaic power plant, a research site for renewable energies located in Cluj-Napoca, Romania. Secondly, the high granularity of the dataset with more than 4.2 million unified production and consumption power values recorded every 30 s guarantees the overall prediction accuracy of the system. Performance metrics used to evaluate the prediction accuracy are the mean bias error, the mean square error, the convergence time of the prediction system, the test performance, and the train mean performance. Test results indicate that the predicted unified electric power production and consumption closely resembles the unified electric power measured values.

Experimentally Verified Analytical Models of Piezoelectric Cantilevers in Different Design Configurations.

This paper deals with analytical modelling of piezoelectric energy harvesting systems for generating useful electricity from ambient vibrations and comparing the usefulness of materials commonly used in designing such harvesters for energy harvesting applications. The kinetic energy harvesters have the potential to be used as an autonomous source of energy for wireless applications. Here in this paper, the considered energy harvesting device is designed as a piezoelectric cantilever beam with different piezoelectric materials in both bimorph and unimorph configurations. For both these configurations a single degree-of-freedom model of a kinematically excited cantilever with a full and partial electrode length respecting the dimensions of added tip mass is derived. The analytical model is based on Euler-Bernoulli beam theory and its output is successfully verified with available experimental results of piezoelectric energy harvesters in three different configurations. The electrical output of the derived model for the three different materials (PZT-5A, PZZN-PLZT and PVDF) and design configurations is in accordance with lab measurements which are presented in the paper. Therefore, this model can be used for predicting the amount of harvested power in a particular vibratory environment. Finally, the derived analytical model was used to compare the energy harvesting effectiveness of the three considered materials for both simple harmonic excitation and random vibrations of the corresponding harvesters. The comparison revealed that both PZT-5A and PZZN-PLZT are an excellent choice for energy harvesting purposes thanks to high electrical power output, whereas PVDF should be used only for sensing applications due to low harvested electrical power output.

Data-Driven Prediction of Vessel Propulsion Power Using Support Vector Regression with Onboard Measurement and Ocean Data.

The fluctuation of the oil price and the growing requirement to reduce greenhouse gas emissions have forced ship builders and shipping companies to improve the energy efficiency of the vessels. The accurate prediction of the required propulsion power at various operating condition is essential to evaluate the energy-saving potential of a vessel. Currently, a new ship is expected to use the ISO15016 method in estimating added resistance induced by external environmental factors in power prediction. However, since ISO15016 usually assumes static water conditions, it may result in low accuracy when it is applied to various operating conditions. Moreover, it is time consuming to apply the ISO15016 method because it is computationally expensive and requires many input data. To overcome this limitation, we propose a data-driven approach to predict the propulsion power of a vessel. In this study, support vector regression (SVR) is used to learn from big data obtained from onboard measurement and the National Oceanic and Atmospheric Administration (NOAA) database. As a result, we show that our data-driven approach shows superior performance compared to the ISO15016 method if the big data of the solid line are secured.

Grain yield genetic gains and changes in physiological related traits for CIMMYT's High Rainfall Wheat Screening Nursery tested across international environments.

The effects of climate change together with the projected future demand represents a huge challenge for wheat production systems worldwide. Wheat breeding can contribute to global food security through the creation of genotypes exhibiting stress tolerance and higher yield potential. The objectives of our study were to (i) estimate the annual grain yield (GY) genetic gain of High Rainfall Wheat Yield Trials (HRWYT) grown from 2007 (15th HRWYT) to 2016 (24th HRWYT) across international environments, and (ii) determine the changes in physiological traits associated with GY genetic improvement. The GY genetic gains were estimated as genetic progress per se (GYP) and in terms of local checks (GYLC). In total, 239 international locations were classified into two groups: high- and low-rainfall environments based on climate variables and trial management practices. In the high-rainfall environment, the annual genetic gains for GYP and GYLC were 3.8 and 1.17 % (160 and 65.1 kg ha-1 yr-1), respectively. In the low-rainfall environment, the genetic gains were 0.93 and 0.73 % (40 and 33.1 kg ha-1 yr-1), for GYP and GYLC respectively. The GY of the lines included in each nursery showed a significant phenotypic correlation between high- and low-rainfall environments in all the examined years and several of the five best performing lines were common in both environments. The GY progress was mainly associated with increased grain weight (R2 = 0.35 p < 0.001), days to maturity (R2 = 0.20, p < 0.001) and grain filling period (R2 = 0.06, p < 0.05). These results indicate continuous GY genetic progress and yield stability in the HRWYT germplasm developed and distributed by CIMMYT.

Comprehensive mechanical power analysis in sprint running acceleration.

Sprint running is a common feature of many sport activities. The ability of an athlete to cover a distance in the shortest time relies on his/her power production. The aim of this study was to provide an exhaustive description of the mechanical determinants of power output in sprint running acceleration and to check whether a predictive equation for internal power designed for steady locomotion is applicable to sprint running acceleration. Eighteen subjects performed two 20 m sprints in a gym. A 35-camera motion capture system recorded the 3D motion of the body segments and the body center of mass (BCoM) trajectory was computed. The mechanical power to accelerate and rise BCoM (external power, Pext ) and to accelerate the segments with respect to BCoM (internal power, Pint ) was calculated. In a 20 m sprint, the power to accelerate the body forward accounts for 50% of total power; Pint accounts for 41% and the power to rise BCoM accounts for 9% of total power. All the components of total mechanical power increase linearly with mean sprint velocity. A published equation for Pint prediction in steady locomotion has been adapted (the compound factor q accounting for the limbs' inertia decreases as a function of the distance within the sprint, differently from steady locomotion) and is still able to predict experimental Pint in a 20 m sprint with a bias of 0.70 ± 0.93 W kg-1 . This equation can be used to include Pint also in other methods that estimate external horizontal power only.

ACES: a machine learning toolbox for clustering analysis and visualization.

BACKGROUND: Studies that aim at explaining phenotypes or disease susceptibility by genetic or epigenetic variants often rely on clustering methods to stratify individuals or samples. While statistical associations may point at increased risk for certain parts of the population, the ultimate goal is to make precise predictions for each individual. This necessitates tools that allow for the rapid inspection of each data point, in particular to find explanations for outliers. RESULTS: ACES is an integrative cluster- and phenotype-browser, which implements standard clustering methods, as well as multiple visualization methods in which all sample information can be displayed quickly. In addition, ACES can automatically mine a list of phenotypes for cluster enrichment, whereby the number of clusters and their boundaries are estimated by a novel method. For visual data browsing, ACES provides a 2D or 3D PCA or Heat Map view. ACES is implemented in Java, with a focus on a user-friendly, interactive, graphical interface. CONCLUSIONS: ACES has been proven an invaluable tool for analyzing large, pre-filtered DNA methylation data sets and RNA-Sequencing data, due to its ease to link molecular markers to complex phenotypes. The source code is available from https://github.com/GrabherrGroup/ACES .

Effect of trabeculectomy on the accuracy of intraocular lens calculations in patients with open-angle glaucoma.

BACKGROUND: The objective of the study is to examine the effect of trabeculectomy on intraocular lens power calculations in patients with open-angle glaucoma (OAG) undergoing cataract surgery. DESIGN: The design is retrospective data analysis. PARTICIPANTS: There are a total of 55 eyes of 55 patients with OAG who had a cataract surgery alone or in combination with trabeculectomy. METHODS: We classified OAG subjects into the following groups based on surgical history: only cataract surgery (OC group), cataract surgery after prior trabeculectomy (CAT group), and cataract surgery performed in combination with trabeculectomy (CCT group). MAIN OUTCOME MEASURES: Differences between actual and predicted postoperative refractive error. RESULTS: Mean error (ME, difference between postoperative and predicted SE) in the CCT group was significantly lower (towards myopia) than that of the OC group (P = 0.008). Additionally, mean absolute error (MAE, absolute value of ME) in the CAT group was significantly greater than in the OC group (P = 0.006). Using linear mixed models, the ME calculated with the SRK II formula was more accurate than the ME predicted by the SRK T formula in the CAT (P = 0.032) and CCT (P = 0.035) groups. CONCLUSIONS: The intraocular lens power prediction accuracy was lower in the CAT and CCT groups than in the OC group. The prediction error was greater in the CAT group than in the OC group, and the direction of the prediction error tended to be towards myopia in the CCT group. The SRK II formula may be more accurate in predicting residual refractive error in the CAT and CCT groups.

Unveiling value patterns via deep reinforcement learning in heterogeneous data analytics.

Artificial intelligence has substantially improved the efficiency of data utilization across various sectors. However, the insufficient filtering of low-quality data poses challenges to uncertainty management, threatening system stability. In this study, we introduce a data-valuation approach employing deep reinforcement learning to elucidate the value patterns in data-driven tasks. By strategically optimizing with iterative sampling and feedback, our method is effective in diverse scenarios and consistently outperforms the classic methods in both accuracy and efficiency. In China's wind-power prediction, excluding 25% of the overall dataset deemed low-value led to a 10.5% improvement in accuracy. Utilizing just 42.8% of the dataset, the model discerned 80% of linear patterns, showcasing the data's intrinsic and transferable value. A nationwide analysis identified a data-value-sensitive geographic belt across 10 provinces, leading to robust policy recommendations informed by variances in power outputs and data values, as well as geographic climate factors.

The Current Burden and Future Solutions for Preoperative Cataract-Refractive Evaluation Diagnostic Devices: A Modified Delphi Study.

Purpose: To obtain consensus on the key areas of burden associated with existing devices and to understand the requirements for a comprehensive next-generation diagnostic device to be able to solve current challenges and provide more accurate prediction of intraocular lens (IOL) power and presbyopia correction IOL success. Patients and Methods: Thirteen expert refractive cataract surgeons including three steering committee (SC) members constituted the voting panel. Three rounds of voting included a Round 1 structured electronic questionnaire, Round 2 virtual face-to-face meeting, and Round 3 electronic questionnaire to obtain consensus on topics related to current limitations and future solutions for preoperative cataract-refractive diagnostic devices. Results: Forty statements reached consensus including current limitations (n = 17) and potential solutions (n = 23) associated with preoperative diagnostic devices. Consistent with existing evidence, the panel reported unmet needs in measurement accuracy and validation, IOL power prediction, workflow, training, and surgical planning. A device that facilitates more accurate corneal measurement, effective IOL power prediction formulas for atypical eyes, simplified staff training, and improved decision-making process for surgeons regarding IOL selection is expected to help alleviate current burdens. Conclusion: Using a modified Delphi process, consensus was achieved on key unmet needs of existing preoperative diagnostic devices and requirements for a comprehensive next-generation device to provide better objective and subjective outcomes for surgeons, technicians, and patients.

A survey on advanced machine learning and deep learning techniques assisting in renewable energy generation.

The sustainability of the earth depends on renewable energy. Forecasting the output of renewable energy has a big impact on how we operate and manage our power networks. Accurate forecasting of renewable energy generation is crucial to ensuring grid dependability and permanence and reducing the risk and cost of the energy market and infrastructure. Although there are several approaches to forecasting solar radiation on a global scale, the two most common ones are machine learning algorithms and cloud pictures combined with physical models. The objective is to present a summary of machine learning-based techniques for solar irradiation forecasting in this context. Renewable energy is being used more and more in the world's energy grid. Numerous strategies, including hybrids, physical models, statistical approaches, and artificial intelligence techniques, have been developed to anticipate the use of renewable energy. This paper examines methods for forecasting renewable energy based on deep learning and machine learning. Review and analysis of deep learning and machine learning forecasts for renewable energy come first. The second paragraph describes metaheuristic optimization techniques for renewable energy. The third topic was the open issue of projecting renewable energy. I will wrap up with a few potential future job objectives.

Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm.

The input features of existing wind power time-series data prediction models are difficult to indicate the potential relationships between data, and the prediction methods are based on deep learning, which makes the convergence of the models slow and difficult to be applied to the actual production environment. To solve the above problems, an ultra-short-term wind power prediction model based on the XGBoost algorithm combined with financial technical index feature engineering and variational ant colony algorithm is proposed. The model innovatively applies financial technical indicators from financial time series data to wind power time series data and creates a class of model input features that can highly condense the potential relationships between time series data. A bionic algorithm is used to search for the best computational parameters for financial technical indicators to reduce the reliance on financial experts' experience. Taking the German power company Tennet wind power data set as an example, the prediction model proposed in this study has an mean absolute error of 0.859 and a root mean square error of 1.329, and it takes only 244 ms to complete the prediction. Thus, this study provides a new solution for ultra-short-term wind power prediction.

A new hybrid model for photovoltaic output power prediction.

Recently, with the development of renewable energy technologies, photovoltaic (PV) power generation is widely used in the grid. However, as PV power generation is influenced by external factors, such as solar radiation fluctuation, PV output power is intermittent and volatile, and thus the accurate PV output power prediction is imperative for the grid stability. To address this issue, based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), improved artificial rabbits optimization (IARO) and convolutional bidirectional long short-term memory (CBiLSTM), a new hybrid model denoted by CEEMDAN-IARO-CBiLSTM is proposed. In addition, inputs of the proposed model are optimized by analyzing influential factors of PV output power with Pearson correlation coefficient method. In order to verify the prediction accuracy, CEEMDAN-IARO-CBiLSTM is compared with other well-known methods under different weather conditions and different seasons. Specifically, for different weather conditions, MAE and RMSE of the proposed model decrease by at least 0.329 and 0.411, 0.086 and 0.021, and 0.140 and 0.220, respectively. With respect to different seasons, MAE and RMSE of the proposed model decrease by at least 0.270 and 0.378, 0.158 and 0.209, 0.210 and 0.292, and 1.096 and 1.148, respectively. Moreover, two statistical tests are conducted, and the corresponding results show that the prediction performance of CEEMDAN-IARO-CBiLSTM is superior to other well-known methods.

Long-sequence voltage series forecasting for internal short circuit early detection of lithium-ion batteries.

Accurate early detection of internal short circuits (ISCs) is indispensable for safe and reliable application of lithium-ion batteries (LiBs). However, the major challenge is finding a reliable standard to judge whether the battery suffers from ISCs. In this work, a deep learning approach with multi-head attention and a multi-scale hierarchical learning mechanism based on encoder-decoder architecture is developed to accurately forecast voltage and power series. By using the predicted voltage without ISCs as the standard and detecting the consistency of the collected and predicted voltage series, we develop a method to detect ISCs quickly and accurately. In this way, we achieve an average percentage accuracy of 86% on the dataset, including different batteries and the equivalent ISC resistance from 1,000 Ω to 10 Ω, indicating successful application of the ISC detection method.

Fuzzy-based prediction of solar PV and wind power generation for microgrid modeling using particle swarm optimization.

Regardless of their nature of stochasticity and uncertain nature, wind and solar resources are the most abundant energy resources used in the development of microgrid systems. In microgrid systems and distribution networks, the uncertain nature of both solar and wind resources results in power quality and system stability issues. The randomization behavior of solar and wind energy resources is controlled through the precise development of a power prediction model. Fuzzy-based solar PV and wind prediction models may more efficiently manage this randomness and uncertain character. However, this method has several drawbacks, it has limited performance when the volumes of wind and solar resources historical data are huge in size and it has also many membership functions of the fuzzy input and output variables as well as multiple fuzzy rules available. The hybrid Fuzzy-PSO intelligent prediction approach improves the fuzzy system's limitations and hence increases the prediction model's performance. The Fuzzy-PSO hybrid forecast model is developed using MATLAB programming of the particle swarm optimization (PSO) algorithm with the help of the global optimization toolbox. In this paper, an error correction factor (ECF) is considered a new fuzzy input variable. It depends on the validation and forecasted data values of both wind and solar prediction models to improve the accuracy of the prediction model. The impact of ECF is observed in fuzzy, Fuzzy-PSO, and Fuzzy-GA wind and solar PV power forecasting models. The hybrid Fuzzy-PSO prediction model of wind and solar power generation has a high degree of accuracy compared to the Fuzzy and Fuzzy-GA forecasting models. The rest of this paper is organized as: Section II is about the analysis of solar and wind resources row data. The Fuzzy-PSO prediction model problem formulation is covered in Section III. Section IV, is about the results and discussion of the study. Section V contains the conclusion. The references and abbreviations are presented at the end of the paper.