☆ 4.6 Article

Deep-Learning Model Selection and Parameter Estimation from a Wind Power Farm in Taiwan

APPLIED SCIENCES-BASEL (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Thermodynamics

Multi-step-ahead wind speed forecasting based on a hybrid decomposition method and temporal convolutional networks

Dan Li et al.

Summary: This paper presents a hybrid decomposition method combining EPT and CEEMDAN for wind speed prediction, integrated with TCN for individual component forecasting. Experimental results demonstrate the significant advantages of this approach in accuracy and stability.

ENERGY (2022)

添加到收藏夹

Article Engineering, Multidisciplinary

New Hybrid Deep Neural Architectural Search-Based Ensemble Reinforcement Learning Strategy for Wind Power Forecasting

Seyed Mohammad Jafar Jalali et al.

Summary: This study proposes a data-driven model called DOCREL based on deep learning and reinforcement learning for wind power forecasting. It extracts effective features using mutual information and optimizes the structure of deep CLSTM models using an improved evolutionary whale optimization algorithm. The proposed deep RL-based ensemble algorithm integrates models to achieve low wind power forecasting errors. Compared to other deep learning models, DOCREL demonstrates excellent performance in two case studies.

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

OPFaceNet: OPtimized Face Recognition Network for noise and occlusion affected face images using Hyperparameters tuned Convolutional Neural Network

Gurukumar Lokku et al.

Summary: Face recognition is an important research topic in computer vision applications and serves as the fundamental biometric security system. This paper introduces a novel face recognition network model, OPFaceNet, which is capable of recognizing face images affected by noise and occlusion. By optimizing the Fitness Sorted Rider Optimization Algorithm (FS-ROA), the proposed CNN model achieves a good recognition rate of 97.2% and demonstrates robustness against occlusion and noise variations across diverse datasets.

APPLIED SOFT COMPUTING (2022)

添加到收藏夹

Article Biology

Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics: A bioinformatics study on biomedical and biological cases

Sajjad Nematzadeh et al.

Summary: This study introduces a method for tuning hyperparameters of machine learning algorithms using Grey Wolf Optimization (GWO) and Genetic algorithm (GA) metaheuristics. By applying 11 different algorithms on various datasets, it shows improved performance in training phases. The metaheuristic methods demonstrate better performance and faster convergence compared to Exhaustive Grid Search (EGS), making them suitable for complex datasets and users who are not experts in analytical statistics and data science algorithms.

COMPUTATIONAL BIOLOGY AND CHEMISTRY (2022)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Multiagent Reinforcement Learning for Hyperparameter Optimization of Convolutional Neural Networks

Arman Iranfar et al.

Summary: Nowadays, DCNNs are widely used in various fields, but designing a DCNN that surpasses the state of the art is a manual and time-consuming task. In this study, a MARL-based approach is proposed to optimize the hyperparameters of DCNNs, reducing human effort. Our method can reduce model size, training time, and inference time without sacrificing accuracy.

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS (2022)

添加到收藏夹

Article Energy & Fuels

Numerical Weather Prediction and Artificial Neural Network Coupling for Wind Energy Forecast

Lorenzo Donadio et al.

Summary: The study proposed two hybrid NWP and ANN models for wind power forecasting over complex terrain, where one directly predicts wind power and the other predicts wind speed first and then converts it to power. Model 2 performed well, showing lower error rates compared to other models in the same category.

ENERGIES (2021)

添加到收藏夹

Article Thermodynamics

A combined forecasting system based on statistical method, artificial neural networks, and deep learning methods for short-term wind speed forecasting

Ping Jiang et al.

Summary: Wind speed forecasting is becoming increasingly important as the use of wind energy in electricity systems grows. A combined prediction system has been proposed in this study, integrating multiple forecasting methods to provide accurate point and interval forecasts for wind speed. This system is deemed more useful for the scheduling and management of electric power systems compared to other benchmark models.

ENERGY (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

Applications of reinforcement learning in energy systems

A. T. D. Perera et al.

Summary: Energy systems are transitioning to accommodate renewable energy technologies and face challenges in controlling energy flows. Research has shown potential for reinforcement learning in improving performance, but certain complexities remain unresolved, indicating room for further development.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

添加到收藏夹

Article Thermodynamics

A deep learning-based evolutionary model for short-term wind speed forecasting: A case study of the Lillgrund offshore wind farm

Mehdi Neshat et al.

Summary: This study utilizes a novel hybrid deep learning-based evolutionary approach for wind speed prediction. Experimental results demonstrate that the new approach outperforms other machine learning models and hybrid models in terms of accuracy and robustness in the short term.

ENERGY CONVERSION AND MANAGEMENT (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting

Wen-Hui Lin et al.

Summary: Studies have shown that changes in climate impact wind power forecasting, and traditional machine learning models may not meet engineering requirements. Therefore, deep learning networks are applied for wind power prediction, with the TCN algorithm achieving accurate long-term forecasting results.

APPLIED SCIENCES-BASEL (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Temporal Convolutional Networks for the Advance Prediction of ENSO

Jining Yan et al.

SCIENTIFIC REPORTS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Novel suboptimal approaches for hyperparameter tuning of deep neural network [under the shelf of optical communication]

M. A. Amirabadi et al.

PHYSICAL COMMUNICATION (2020)

添加到收藏夹

Article Energy & Fuels

Short-term prediction for wind power based on temporal convolutional network

Ruijin Zhu et al.

ENERGY REPORTS (2020)

添加到收藏夹

Article Engineering, Civil

Modified fuzzy Q-learning based wind speed prediction

Rajneesh Sharma et al.

JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Reinforcement-Learning-Based Energy Storage System Operation Strategies to Manage Wind Power Forecast Uncertainty

Eunsung Oh et al.

IEEE ACCESS (2020)

添加到收藏夹

Review Thermodynamics

Deterministic wind energy forecasting: A review of intelligent predictors and auxiliary methods

Hui Liu et al.

ENERGY CONVERSION AND MANAGEMENT (2019)

添加到收藏夹

Article Optics

Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm

Woo-Young Lee et al.

OPTIK (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Light Gated Recurrent Units for Speech Recognition

Mirco Ravanelli et al.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2018)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Temporal Convolutional Networks for Action Segmentation and Detection

Colin Lea et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Energy & Fuels

Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model

Erasmo Cadenas et al.

ENERGIES (2016)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.