A hybrid wind speed forecasting model with two-stage data processing based on adaptive neuro-fuzzy inference systems and deep learning algorithms

Earth Science Informatics, Год журнала: 2025, Номер 18(1)

Опубликована: Янв. 1, 2025

Язык: Английский

---

A new paradigm based on Wasserstein Generative Adversarial Network and time-series graph for integrated energy system forecasting

Energy Conversion and Management, Год журнала: 2025, Номер 326, С. 119484 - 119484

Опубликована: Янв. 13, 2025

Язык: Английский

---

WindForecastX: a dynamic approach for accurate long-term wind speed prediction in wind energy applications

Ocean Dynamics, Год журнала: 2025, Номер 75(1)

Опубликована: Янв. 1, 2025

Язык: Английский

---

Short-term wind speed forecasting based on a novel KANInformer model and improved dual decomposition

Energy, Год журнала: 2025, Номер unknown, С. 135551 - 135551

Опубликована: Март 1, 2025

Язык: Английский

---

A new multi-objective ensemble wind speed forecasting system: Mixed-frequency interval-valued modeling paradigm

Energy, Год журнала: 2024, Номер 304, С. 131963 - 131963

Опубликована: Июнь 10, 2024

Язык: Английский

---

Artificial intelligence-based forecasting models for integrated energy system management planning: An exploration of the prospects for South Africa

Energy Conversion and Management X, Год журнала: 2024, Номер 24, С. 100772 - 100772

Опубликована: Окт. 1, 2024

Язык: Английский

---

A bi-level mode decomposition framework for multi-step wind power forecasting using deep neural network

Energy Conversion and Management X, Год журнала: 2024, Номер 23, С. 100650 - 100650

Опубликована: Июнь 22, 2024

The proportion of wind energy in global structure is growing rapidly, promoting the development power forecasting (WPF) technologies to solve uncertainty and intermittence generation. However, nonlinear stochastic features time series restrain accuracy multi-step prediction performance. A WPF (MS-WPF) approach based on a bi-level empirical mode decomposition (BLEMD) method BiLSTM neural network proposed this paper improve regional generators. Since always generated through coupled factors from both weather-to-power conversion, linearity feature first introduced as an aspect apart frequency decompose sequence data. BLEMD introduces Pearson product-moment correlation coefficient evaluate linearity-based algorithm designed accordingly. To further enhance precision release computation burdens, DL-based strategy, including network, CNN-BiLSTM mean weight estimation are implemented predict components separately. only relies local data, greatly reducing data acquisition cost. MS-WPF verified by 2.5kW turbine with horizons 5 seconds 30 seconds, 1.5MW 10 minutes 1 hour, 51MW farm hour 6 hours. comparative experimental results other cutting-edge methods indicated that has superior stable performance for prediction.

Язык: Английский

---

A synchronized multi-step wind speed prediction with adaptive features and parameters selection: Insights from an interaction model

Expert Systems with Applications, Год журнала: 2024, Номер 255, С. 124764 - 124764

Опубликована: Июль 14, 2024

Язык: Английский

---

A novel interpretability machine learning model for wind speed forecasting based on feature and sub-model selection

Expert Systems with Applications, Год журнала: 2024, Номер 255, С. 124560 - 124560

Опубликована: Июнь 27, 2024

Язык: Английский

---

Incorporating key features from structured and unstructured data for enhanced carbon trading price forecasting with interpretability analysis

Applied Energy, Год журнала: 2025, Номер 382, С. 125301 - 125301

Опубликована: Янв. 8, 2025

Язык: Английский

---