Improving the accuracy of daily solar radiation prediction by climatic data using an efficient hybrid deep learning model: Long short-term memory (LSTM) network coupled with wavelet transform

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 123, С. 106199 - 106199

Опубликована: Март 31, 2023

Язык: Английский

---

Automatic interpretation of strain distributions measured from distributed fiber optic sensors for crack monitoring

Measurement, Год журнала: 2023, Номер 211, С. 112629 - 112629

Опубликована: Фев. 24, 2023

Язык: Английский

---

Data-driven prediction and optimization toward net-zero and positive-energy buildings: A systematic review

Building and Environment, Год журнала: 2023, Номер 242, С. 110578 - 110578

Опубликована: Июль 4, 2023

Язык: Английский

---

A novel approach based on integration of convolutional neural networks and echo state network for daily electricity demand prediction

Energy, Год журнала: 2023, Номер 275, С. 127430 - 127430

Опубликована: Апрель 8, 2023

Predicting electricity demand data is considered an essential task in decisions taking, and establishing new infrastructure the power generation network. To deliver a high-quality prediction, this paper proposes hybrid combination technique, based on deep learning model of Convolutional Neural Networks Echo State Networks, named as CESN. Daily from four sites (Roderick, Rocklea, Hemmant Carpendale), located Southeast Queensland, Australia, have been used to develop proposed prediction model. The study also analyzes five other machine learning-based models (support vector regression, multilayer perceptron, extreme gradient boosting, neural network, Light Gradient Boosting) compare evaluate outcomes approach. results obtained experimental showed that able obtain highest performance compared existing developed for daily forecasting. Based statistical approaches utilized study, approach presents accuracy among models. algorithm excellent accurate forecasting method, which outperformed state art algorithms are currently problem.

Язык: Английский

---

Advancing short-term solar irradiance forecasting accuracy through a hybrid deep learning approach with Bayesian optimization

Results in Engineering, Год журнала: 2024, Номер 23, С. 102461 - 102461

Опубликована: Июнь 26, 2024

The optimization of solar energy integration into the power grid relies heavily on accurate forecasting irradiance. In this study, a new approach for short-term irradiance is introduced. This method combines Bayesian Optimized Attention-Dilated Long Short-Term Memory and Savitzky-Golay filtering. methodology implemented to analyze data obtained from probe situated in Douala, Cameroon. Initially, unprocessed augmented by integrating distinctive irradiation variables, filter with Optimization used enhance its quality. Subsequently, multiple deep learning models, including Memory, Bidirectional Artificial Neural Networks, Additive Attention Mechanism, Mechanism Dilated Convolutional layers, are trained evaluated. Out all models considered, proposed approach, which attention mechanism dilated convolutional demonstrates exceptional performance best convergence accuracy forecasting. further utilized fine-tune polynomial window size optimize hyperparameters models. results show Symmetric Mean Absolute Percentage Error 0.6564, Normalized Root Square 0.2250, 22.9445, surpassing previous studies literature. Empirical findings highlight effectiveness enhancing research contributes field introducing novel pre-processing techniques, hybrid architecture, development benchmark dataset. These advancements benefit both researchers plant managers, improving capabilities.

Язык: Английский

---

Read-First LSTM model: A new variant of long short term memory neural network for predicting solar radiation data

Energy Conversion and Management, Год журнала: 2024, Номер 305, С. 118267 - 118267

Опубликована: Март 7, 2024

Язык: Английский

---

Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 102995 - 102995

Опубликована: Янв. 1, 2025

Язык: Английский

---

Hybrid Convolutional Neural Network-Multilayer Perceptron Model for Solar Radiation Prediction

Cognitive Computation, Год журнала: 2022, Номер 15(2), С. 645 - 671

Опубликована: Ноя. 7, 2022

Язык: Английский

---

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation

Atmospheric Pollution Research, Год журнала: 2023, Номер 14(6), С. 101766 - 101766

Опубликована: Апрель 18, 2023

Язык: Английский

---

A Review on Neural Network Based Models for Short Term Solar Irradiance Forecasting

Applied Sciences, Год журнала: 2023, Номер 13(14), С. 8332 - 8332

Опубликована: Июль 19, 2023

The accuracy of solar energy forecasting is critical for power system planning, management, and operation in the global electric grid. Therefore, it crucial to ensure a constant sustainable supply consumers. However, existing statistical machine learning algorithms are not reliable due sporadic nature data. Several factors influence performance irradiance, such as horizon, weather classification, evaluation metrics. we provide review paper on deep learning-based irradiance models. These models include Long Short-Term Memory (LTSM), Gated Recurrent Unit (GRU), Neural Network (RNN), Convolutional (CNN), Generative Adversarial Networks (GAN), Attention Mechanism (AM), other hybrid Based our analysis, perform better than conventional applications, especially combination with some techniques that enhance extraction features. Furthermore, use data augmentation improve useful, networks. Thus, this expected baseline analysis future researchers select most appropriate approaches photovoltaic forecasting, wind electricity consumption medium term long term.

Язык: Английский

---