Multitasking recurrent neural network for photovoltaic power generation prediction

Article Energy & Fuels

Estimating the spatial distribution of solar photovoltaic power generation potential on different types of rural rooftops using a deep learning network applied to satellite images

Tao Sun et al.

Summary: This article proposes a new method using satellite images to estimate the spatial distribution of rural rooftop photovoltaic (PV) power generation potential. By using a revised deep learning network and a calculation method for PV panel potential, accurate spatial distribution information of rooftop PV power generation potential in rural areas can be obtained. The research was applied in a village and a town in northern China, achieving high accuracy.

APPLIED ENERGY (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Evolutionary Multitask Optimization With Adaptive Knowledge Transfer

Hao Xu et al.

Summary: Evolutionary Multitask Optimization (EMTO) uses evolutionary algorithms (EAs) to solve multiple optimization tasks simultaneously, utilizing knowledge transfer to improve performance. The proposed adaptive EMTO (AEMTO) framework adjusts knowledge transfer in a synergistic way, effectively addressing negative knowledge transfer and enhancing overall performance.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2022)

添加到收藏夹

Article Energy & Fuels

A Multi-step ahead photovoltaic power forecasting model based on TimeGAN, Soft DTW-based K-medoids clustering, and a CNN-GRU hybrid neural network

Qing Li et al.

Summary: This study proposes a multi-step ahead photovoltaic power forecasting model that combines TimeGAN, soft DTW-based K-medoids clustering algorithms, and a hybrid neural network model computed by CNN and GRU. The model enhances forecasting accuracy through data augmentation, clustering, and network integration, and is tested on real datasets.

ENERGY REPORTS (2022)

添加到收藏夹

Article Energy & Fuels

Short-term solar power forecasting: Investigating the ability of deep learning models to capture low-level utility-scale Photovoltaic system behaviour

A. A. du Plessis et al.

Summary: This study investigates the importance of PV system forecasting and proposes an aggregated inverter-level forecasting methodology to enhance forecasting accuracy. Results demonstrate that this new approach can outperform traditional methods in certain weather types and forecast horisons.

APPLIED ENERGY (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

Deep learning neural networks for short-term photovoltaic power forecasting

A. Mellit et al.

Summary: This paper develops and compares different types of deep learning neural networks (DLNN) for short-term output PV power forecasting, showing very good accuracy in one-step prediction within a 1-minute time horizon and acceptable results in multi-step prediction.

RENEWABLE ENERGY (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

The coordinated optimal design of a PV-battery system with multiple types of PV arrays and batteries: A case study of power smoothing

Yinghua Jiang et al.

Summary: This work investigates the complementary characteristics of various PV arrays and batteries, proposing a coordinated optimization approach to achieve the minimum total cost of a PV-battery system with multi-type PV arrays and batteries. A case study demonstrates that utilizing multiple PV arrays and batteries can improve the system's economy, stability, and curtailment rate.

JOURNAL OF CLEANER PRODUCTION (2021)

添加到收藏夹

Article Energy & Fuels

Optimally configured Gated Recurrent Unit using Hyperband for the long-term forecasting of photovoltaic plant

Ameer Tamoor Khan et al.

Summary: The photovoltaic generation inherits the instability due to solar irradiation variability and non-availability, leading to grid management, planning, and operation issues. Researchers have proposed algorithms to forecast the power generation of photovoltaic plants, with the Hyperband Gated Recurrent Unit model achieving promising results by optimizing hyperparameters selection.

RENEWABLE ENERGY FOCUS (2021)

添加到收藏夹

Article Energy & Fuels