Article
Computer Science, Artificial Intelligence
Vishalteja Kosana, Kiran Teeparthi, Santhosh Madasthu
Summary: Accurate wind speed prediction is crucial for optimal operation and planning, but the unstable and stochastic nature of wind poses challenges. This study proposes a hybrid approach that utilizes an encoder and a decoder to improve prediction accuracy and address uncertainty modeling difficulties. The encoder, a one-dimensional convolutional neural network, extracts important characteristics and forms a latent representation, while the decoder, a bidirectional long short term memory network, interprets these characteristics to predict wind speed. The hybrid approach is validated and outperforms benchmark models by 42% in real-time wind data from a measuring station in Colorado.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Green & Sustainable Science & Technology
Qiuling Yang, Changhong Deng, Xiqiang Chang
Summary: In this paper, a wind speed prediction method based on data decomposition of improved singular spectrum analysis (ISSA) is proposed. The ISSA is used to decompose the wind speed sequence and remove noise components using singular entropy. The experimental results show that the proposed method can effectively improve the prediction accuracy.
Article
Environmental Sciences
Ting Zhu, Wenbo Wang, Min Yu
Summary: Wind power generation is a rapidly growing renewable energy source, but its volatility and instability pose challenges to power system operation. Accurate wind speed prediction is crucial for grid management and the stability of the power system. This paper presents a novel method that decomposes, merges, and predicts wind speed sub-components, resulting in accurate short-term wind speed prediction.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Energy & Fuels
Sung-ho Hur
Summary: Wind speed prediction is crucial in enhancing wind turbine control and condition monitoring. A novel scheme involving estimation and prediction stages, utilizing an Extended Kalman filter for estimation and extrapolation as well as machine learning for prediction, is proposed and tested using data from a high-fidelity aeroelastic model.
Article
Thermodynamics
Fei Wang, Shuang Tong, Yiqian Sun, Yongsheng Xie, Zhao Zhen, Guoqing Li, Chunmei Cao, Neven Duic, Dagui Liu
Summary: This paper proposes an ultra-short-term wind speed hybrid prediction method based on wind process pattern forecasting. By dividing the wind process into different patterns and selecting the corresponding prediction model based on the pattern, the proposed method can reliably forecast future wind speeds.
Article
Thermodynamics
Nai-Zhi Guo, Ke-Zhong Shi, Bo Li, Liang-Wen Qi, Hong-Hui Wu, Zi-Liang Zhang, Jian-Zhong Xu
Summary: Accurate short-term wind power prediction plays a vital role in wind farm control and the integration of wind energy into the power system. Incorporating wake effects into a physics-inspired neural network model improves the accuracy of wind power prediction by over 20% compared to traditional models. Considering wake effects is recommended for enhancing the accuracy of short-term wind power prediction.
Article
Environmental Sciences
Deepak Gupta, Narayanan Natarajan, Mohanadhas Berlin
Summary: Wind energy is a potential renewable energy source globally. Accurate prediction of wind speed is crucial for estimating wind power accurately. Hybrid machine learning models were used in this study for short-term wind speed prediction, with LDMR model outperforming others in prediction accuracy and ELM model being computationally faster.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Energy & Fuels
Priya R. Kamath, Kedarnath Senapati
Summary: This paper introduces a modified S-transform (CBST) for wind speed prediction, which uses artificial neural network for predicting subseries at different frequencies, and compares it with methods based on wavelet transform and empirical mode decomposition.
Article
Energy & Fuels
Yan Han, Lihua Mi, Lian Shen, C. S. Cai, Yuchen Liu, Kai Li, Guoji Xu
Summary: A hybrid wind speed prediction model based on WRF simulation and optimized by a multivariate data decomposition method and deep learning algorithm is proposed in this study. The model outperforms other comparative models in terms of wind speed prediction accuracy.
Article
Chemistry, Physical
Ayse Tugba Dosdogru, Asli Boru Ipek
Summary: Energy sources are crucial for national economic growth, with wind energy playing a significant role in low-carbon energy technologies. This study focuses on improving wind speed prediction by utilizing a hybrid approach of XGBoost, AdaBoost, and ANN, aiming to provide more accurate results for wind speed forecasting.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2022)
Article
Computer Science, Artificial Intelligence
Haize Hu, Yunyi Li, Xiangping Zhang, Mengge Fang
Summary: In this paper, a new hybrid model based on gray wolf algorithm (GWO) and support vector machine (SVM) is proposed for accurate wind speed prediction. The model combines Neo4j, k-means clustering, GWO, and SVM to preprocess and analyze data, optimize parameters, and accurately predict wind speed. Experimental results demonstrate the model's high accuracy, stability, and acceptable time complexity, which can provide a scientific basis for improving the operation security and stability of power systems.
PATTERN RECOGNITION
(2022)
Article
Thermodynamics
Bowen Yan, Ruifang Shen, Ke Li, Zhenguo Wang, Qingshan Yang, Xuhong Zhou, Le Zhang
Summary: This paper proposes a method that predicts wind speed at multiple locations using both spatial and temporal data, and introduces three deep learning models. These models combine ConvLSTM, ResNet, and 3D convolution to extract spatial and temporal correlations between multi-site wind speeds. The experiments show that the CoReSTL model achieves the best prediction results.
Article
Green & Sustainable Science & Technology
Fei Sun, Tongdan Jin
Summary: This paper proposes a hybrid wind speed prediction model that combines linear time series regression with a nonlinear machine learning algorithm to forecast wind speeds using multivariate input and multi-step output capability. The model determines the input neurons based on meteorological features and lag observations, and the output neurons based on the forecasting horizon. The model was trained, validated, and tested using hourly meteorological records from multiple cities, and it outperformed other methods in predicting wind speeds 3 to 24 hours in advance.
Article
Energy & Fuels
Zhenhua Xiong, Yan Chen, Guihua Ban, Yixin Zhuo, Kui Huang
Summary: In this paper, a hybrid algorithm based on gradient descent and meta-heuristic optimization is proposed to enhance the accuracy of wind power prediction and reduce computational burden. The experimental results demonstrate that the hybrid algorithm outperforms the traditional Back Propagation (BP) algorithm in terms of accuracy, stability, and efficiency.
Article
Thermodynamics
Jikai Duan, Hongchao Zuo, Yulong Bai, Jizheng Duan, Mingheng Chang, Bolong Chen
Summary: This study presents a novel hybrid forecasting system that significantly enhances the accuracy of wind speed prediction, achieving superior prediction results compared to other models through a process of decomposition, prediction, and error correction.
Article
Green & Sustainable Science & Technology
Cameron Bracken, Nathalie Voisin, Casey D. Burleyson, Allison M. Campbell, Z. Jason Hou, Daniel Broman
Summary: This study presents a methodology and dataset for examining compound wind and solar energy droughts, as well as the first standardized benchmark of energy droughts across the Continental United States (CONUS) for a 2020 infrastructure. The results show that compound wind and solar droughts have distinct spatial and temporal patterns across the CONUS, and the characteristics of energy droughts are regional. The study also finds that compound high load events occur more often during compound wind and solar droughts than expected.
Article
Green & Sustainable Science & Technology
Ning Zhang, Yanghao Yu, Jiawei Wu, Ershun Du, Shuming Zhang, Jinyu Xiao
Summary: This paper provides insights into the optimal configuration of CSP plants with different penetrations of wind power by proposing an unconstrained optimization model. The results suggest that large solar multiples and TES are preferred in order to maximize profit, especially when combined with high penetrations of wind and photovoltaic plants. Additionally, the study demonstrates the economy and feasibility of installing electric heaters (EH) in CSP plants, which show a linear correlation with the penetration of variable energy resources.
Article
Green & Sustainable Science & Technology
M. Szubel, K. Papis-Fraczek, S. Podlasek
Article
Green & Sustainable Science & Technology
J. Silva, J. C. Goncalves, C. Rocha, J. Vilaca, L. M. Madeira
Summary: This study investigated the methanation of CO2 in biogas and compared two different methanation reactors. The results showed that the cooled reactor without CO2 separation achieved a CO2 conversion rate of 91.8%, while the adiabatic reactors achieved conversion rates of 59.6% and 67.2%, resulting in an overall conversion rate of 93.0%. Economic analysis revealed negative net present worth values, indicating the need for government monetary incentives.
Article
Green & Sustainable Science & Technology
Yang Liu, Yonglan Xi, Xiaomei Ye, Yingpeng Zhang, Chengcheng Wang, Zhaoyan Jia, Chunhui Cao, Ting Han, Jing Du, Xiangping Kong, Zhongbing Chen
Summary: This study investigated the effect of using nanofiber membrane composites containing Prussian blue-like compound nanoparticles (PNPs) to relieve ammonia nitrogen inhibition of rural organic household waste during high-solid anaerobic digestion and increase methane production. The results showed that adding NMCs with 15% PNPs can lower the concentrations of volatile fatty acids and ammonia nitrogen, and increase methane yield.
Article
Green & Sustainable Science & Technology
Zhong Ge, Xiaodong Wang, Jian Li, Jian Xu, Jianbin Xie, Zhiyong Xie, Ruiqu Ma
Summary: This study evaluates the thermodynamic, exergy, and economic performance of a double-stage organic flash cycle (DOFC) using ten eco-friendly hydrofluoroolefins. The influences of key parameters on performance are analyzed, and the advantages of DOFC over single-stage type are quantified.
Article
Green & Sustainable Science & Technology
Nicolas Kirchner-Bossi, Fernando Porte-Agel
Summary: This study investigates the optimization of power density in wind farms and its sensitivity to the available area size. A novel genetic algorithm (PDGA) is introduced to optimize power density and turbine layout. The results show that the PDGA-driven solutions significantly reduce the levelized cost of energy (LCOE) compared to the default layout, and exhibit a convex relationship between area and LCOE or power density.
Article
Green & Sustainable Science & Technology
Chunxiao Zhang, Dongdong Li, Lin Wang, Qingpo Yang, Yutao Guo, Wei Zhang, Chao Shen, Jihong Pu
Summary: In this study, a novel reversible liquid-filled energy-saving window that effectively regulates indoor solar radiation heat gain is proposed. Experimental results show that this window can effectively reduce indoor temperature during both summer and winter seasons, while having minimal impact on indoor illuminance.
Article
Green & Sustainable Science & Technology
Alessandro L. Aguiar, Martinho Marta-Almeida, Mauro Cirano, Janini Pereira, Leticia Cotrim da Cunha
Summary: This study analyzed the Brazilian Equatorial Shelf using a high-resolution ocean model and found significant tidal variations in the area. Several hypothetical barrages were proposed with higher annual power generation than existing barrages. The study also evaluated the installation effort of these barrages.
Article
Green & Sustainable Science & Technology
Francesco Superchi, Nathan Giovannini, Antonis Moustakis, George Pechlivanoglou, Alessandro Bianchini
Summary: This study focuses on the optimization of a hybrid power station on the Tilos island in Greece, aiming to increase energy export and revenue by optimizing energy fluxes. Different scenarios are proposed to examine the impact of different agreements with the grid operator on the optimal solution.
Article
Green & Sustainable Science & Technology
Peimaneh Shirazi, Amirmohammad Behzadi, Pouria Ahmadi, Sasan Sadrizadeh
Summary: This research presents two novel energy production/storage/usage systems to reduce energy consumption and environmental effects in buildings. A biomass-fired model and a solar-driven system integrated with photovoltaic thermal (PVT) panels and a heat pump were designed and assessed. The results indicate that the solar-based system has an acceptable energy cost and the PVT-based system with a heat pump is environmentally superior. The biomass-fired system shows excellent efficiency.
Article
Green & Sustainable Science & Technology
Zihao Qi, Yingling Cai, Yunxiang Cui
Summary: This study aims to investigate the operational characteristics of the solar-ground source heat pump system (SGSHPS) in Shanghai under different operation modes. It concludes that tandem operation mode 1 is the optimal mode for winter operation in terms of energy efficiency.
Article
Green & Sustainable Science & Technology
L. Bartolucci, S. Cordiner, A. Di Carlo, A. Gallifuoco, P. Mele, V. Mulone
Summary: Spent coffee grounds are a valuable biogenic waste that can be used as a source of biofuels and valuable chemicals through pyrolysis and solvent extraction processes. The study found that heavy organic bio-oil derived from coffee grounds can be used as a carbon-rich biofuel, while solvent extraction can extract xantines and p-benzoquinone, which are important chemicals for various industries. The results highlight the promising potential of solvent extraction in improving the economic viability of coffee grounds pyrolysis-based biorefineries.
Article
Green & Sustainable Science & Technology
Luiza de Queiroz Correa, Diego Bagnis, Pedro Rabelo Melo Franco, Esly Ferreira da Costa Junior, Andrea Oliveira Souza da Costa
Summary: Building-integrated photovoltaics, especially organic solar technology, are important for reducing greenhouse gas emissions in the building sector. This study analyzed the performance of organic panels laminated in glass in a vertical installation in Latin America. Results showed that glass lamination and vertical orientation preserved the panels' performance and led to higher energy generation in winter.
Article
Green & Sustainable Science & Technology
Zhipei Hu, Shuo Jiang, Zhigao Sun, Jun Li
Summary: This study proposes innovative fin arrangements to enhance the thermal performance of latent heat storage units. Through optimization of fin distribution and prediction of transient melting behaviors, it is found that fin structures significantly influence heat transfer characteristics and melting behaviors.