COA-CNN-LSTM: Coati optimization algorithm-based hybrid deep learning model for PV/wind power forecasting in smart grid applications

Applied Energy, Год журнала: 2023, Номер 349, С. 121638 - 121638

Опубликована: Июль 27, 2023

Язык: Английский

---

State-of-the-art review on energy and load forecasting in microgrids using artificial neural networks, machine learning, and deep learning techniques

Electric Power Systems Research, Год журнала: 2023, Номер 225, С. 109792 - 109792

Опубликована: Сен. 8, 2023

Язык: Английский

---

The usage of 10-fold cross-validation and grid search to enhance ML methods performance in solar farm power generation prediction

Cleaner Engineering and Technology, Год журнала: 2023, Номер 15, С. 100664 - 100664

Опубликована: Июль 28, 2023

It is essential to have accurate projections of the quantity solar energy that will be generated in future improve competitiveness power plants market and reduce dependence both economy society on fossil fuels. This can accomplished by having a better understanding amount future. We used databases containing information about California span 2019 through 2021. These years encompass state's forecast. data were analysis. The 10-fold cross-validation Grid search has been enhance performance decision tree, light gradient boosting machine, an extra tree Solar Farm Power Generation Prediction.

Язык: Английский

---

Achieving wind power and photovoltaic power prediction: An intelligent prediction system based on a deep learning approach

Energy, Год журнала: 2023, Номер 283, С. 129005 - 129005

Опубликована: Сен. 9, 2023

Язык: Английский

---

Solar and wind power data from the Chinese State Grid Renewable Energy Generation Forecasting Competition

Scientific Data, Год журнала: 2022, Номер 9(1)

Опубликована: Сен. 21, 2022

Accurate solar and wind generation forecasting along with high renewable energy penetration in power grids throughout the world are crucial to days-ahead scheduling of systems. It is difficult precisely forecast on-site due intermittency fluctuation characteristics energy. Solar data from sources beneficial for development data-driven models. In this paper, an open dataset consisting collected stations, including six farms eight stations China, provided. Over two years (2019-2020), weather-related were at 15-minute intervals. The was used Renewable Energy Generation Forecasting Competition hosted by Chinese State Grid 2021. process collection, processing, potential applications described. use promising models optimization electricity demand response (DR) programs grid.

Язык: Английский

---

A novel interval forecasting system based on multi-objective optimization and hybrid data reconstruct strategy

Expert Systems with Applications, Год журнала: 2023, Номер 217, С. 119539 - 119539

Опубликована: Янв. 12, 2023

Язык: Английский

---

Combined electricity load-forecasting system based on weighted fuzzy time series and deep neural networks

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 132, С. 108375 - 108375

Опубликована: Апрель 16, 2024

Язык: Английский

---

Simultaneous sizing and scheduling optimization for PV-wind-battery hybrid systems with a modified battery lifetime model: A high-resolution analysis in China

Applied Energy, Год журнала: 2024, Номер 360, С. 122812 - 122812

Опубликована: Фев. 10, 2024

Язык: Английский

---

Hybrid prediction method for solar photovoltaic power generation using normal cloud parrot optimization algorithm integrated with extreme learning machine

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 22, 2025

As the energy crisis environmental concerns rise, harnessing renewable sources like photovoltaics (PV) is critical for sustainable development. However, seasonal variability and random intermittency of solar power pose significant forecasting challenges, threatening grid stability. Therefore, this paper proposes a novel hybrid method, NCPO-ELM, to adequately capture spatial temporal dependencies within meteorological data crucial accurate predictions. To effectively optimize performance Extreme Learning Machine (ELM), Normal Cloud Parrot Optimization (NCPO) algorithm developed, inspired by Pyrrhura Molinae parrots' flock behavior cloud model theory. NCPO integrates five unique search strategies utilizes structure explore exploit. By introducing normal generate samples with specific distributions, enhances solution space coverage. subsequently employed Single-Layer Feedforward Network (SLFN) hidden layer hyperparameters, yielding optimal weights biases output layer, thereby reducing benchmark ELM's sensitivity noise instability from initialization. The actual results PV stations across different regions demonstrate that proposed NCPO-ELM shows superior prediction accuracy compared existing approaches, particularly time series diverse characteristics variations.

Язык: Английский

---

Prediction of Short-Term Solar Irradiance Using the ProbSparse Attention Mechanism for a Sustainable Energy Development Strategy

Sustainability, Год журнала: 2025, Номер 17(3), С. 1075 - 1075

Опубликована: Янв. 28, 2025

Sustainability refers to a development approach that meets the needs of present generation without compromising ability future generations meet their own needs. Solar energy is an inexhaustible and renewable resource. From perspective resource utilization, solar power has high degree sustainability. Therefore, one most important ways transform structure promote sustainable economy society, it great significance for promoting construction resource-conserving environmentally friendly society. However, resources also exhibit strong unpredictability; therefore, this paper proposes novel artificial intelligence (AI) model short-term irradiance prediction in photovoltaic generation. Leveraging ProbSparse attention mechanism within encoder-decoder architecture, AI efficiently captures both short- long-term dependencies input sequence. The dingo algorithm innovatively redesigned optimize hyperparameters proposed model, enhancing convergence. Data preprocessing involves feature selection based on mutual information, multiple imputations data cleaning, median filtering. Evaluation metrics include mean absolute error (MAE), root square (RMSE), coefficient determination (R2). demonstrates improved efficiency robust performance prediction, contributing advancements management electrical systems.

Язык: Английский

---