Article
Mathematics, Interdisciplinary Applications
Monem A. Mohammed, Layla A. Ahmed
Summary: Wind energy is a fast and economical method of electrical power generation in the energy industry. This study proposes a wavelet function derived from two different Lucas polynomials and compares an artificial neural network (ANN) with a wavelet-artificial neural network (WNN) for wind speed forecasting. The continuous wavelet transform (CWT) is used with different wavelets to transform the wind speed data. The results show that the proposed wavelet-ANN model achieved the best performance in terms of various evaluation criteria.
DISCRETE DYNAMICS IN NATURE AND SOCIETY
(2023)
Article
Thermodynamics
Cem Emeksiz, Mustafa Tan
Summary: A hybrid model combining CEEMDAN, LMD, Hurst, and BPNN is proposed for wind speed prediction, showing better accuracy compared to traditional methods with a decrease in MAPE values by 41.16% and 78.80%.
Article
Computer Science, Information Systems
Paulo S. G. de Mattos Neto, Joao F. L. de Oliveira, Domingos S. de O. Santos Junior, Hugo Valadares Siqueira, Manoel H. N. Marinho, Francisco Madeiro
Summary: The integration of wind power into traditional electricity grids is challenging due to the unpredictable nature of wind speed. Wind speed forecasting is crucial for decision-making in the energy sector, and this paper proposes a method to improve its accuracy by combining linear and nonlinear forecasts with exogenous variables. Results show that this method outperforms statistical techniques, Machine Learning models, and hybrid systems in most cases.
INFORMATION SCIENCES
(2021)
Article
Engineering, Marine
Jingjing Liu, Xinli Yang, Denghui Zhang, Ping Xu, Zhuolin Li, Fengjun Hu
Summary: In this paper, the authors propose an adaptive graph-learning convolutional network (AGLCN) that can automatically infer hidden associations among multi-nodes. The model integrates the temporal and graph convolutional modules to capture temporal and spatial features in the data. Experimental results on real-world multi-node wind speed data show that the model achieves state-of-the-art performance in multi-scale wind speed predictions. Moreover, the learned graph can reveal spatial correlations from a data-driven perspective.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Ziheng Gao, Zhuolin Li, Lingyu Xu, Jie Yu
Summary: In this study, a dynamic adaptive spatio-temporal graph neural network (DASTGN) is proposed to capture the dynamic spatial dependencies in ocean meteorology data. Experimental results show that the DASTGN improves the performance of the baseline model by 3.05% and 3.69% in terms of MAE and RMSE, respectively.
APPLIED SOFT COMPUTING
(2023)
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
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
Computer Science, Artificial Intelligence
Xiaoyang Zheng, Dongqing Jia, Zhihan Lv, Chengyou Luo, Junli Zhao, Zeyu Ye
Summary: Wind energy is an important part of the power system and accurate wind speed forecasting is essential for its stable and safe utilization. This paper proposes a Legendre multiwavelet-based neural network model, which combines the properties of Legendre multi-wavelets and the self-learning capability of neural networks. The model achieves optimal performance and high prediction accuracy, especially in multi-step prediction.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Thermodynamics
Wenjun Jiang, Pengfei Lin, Yang Liang, Huanxiang Gao, Dongqin Zhang, Gang Hu
Summary: This study proposes a novel hybrid deep learning model for wind speed forecasting, which captures pairwise dependencies and temporal features of atmospheric variables. The model outperforms existing models and significantly improves forecasting accuracy. The research findings indicate the substantial potential of this approach in wind farm operational contexts.
Article
Computer Science, Artificial Intelligence
Xiaobo Zhang
Summary: This paper develops a hybrid versatile forecasting framework that provides detailed information about future wind speed uncertainty and demonstrates its value in the decision-making process of wind power operation and management through experiments.
APPLIED INTELLIGENCE
(2023)
Article
Engineering, Civil
Yaodong Liu, Zidong Xu, Hao Wang, Yawei Wang, Jianxiao Mao, Yiming Zhang
Summary: This paper proposes an ensemble Quantile Regression Neural Network (QRNN) model based on Wavelet decomposition (WD) and least absolute shrinkage and selection operator (LASSO) for probabilistic short-term wind speed forecasting. Experimental results show that the proposed model can enhance the performance of short-term wind speed forecasting and reduce the uncertainty of the prediction results.
Article
Computer Science, Artificial Intelligence
Wei Sun, Bin Tan, Qiqi Wang
Summary: Improving the reliability of wind speed forecasting in wind power generation is crucial, and this study introduces a hybrid forecasting system using secondary decomposition and neural network, demonstrating the competitive strength of this combination strategy.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Yue Yu, Kun She, Jinhua Liu, Xiao Cai, Kaibo Shi, O. M. Kwon
Summary: In recent years, deep learning super-resolution models for progressive reconstruction have achieved great success. However, these models ignore the information contained in the lower subspaces and do not explore the correlation between features in the wavelet and spatial domain, resulting in not fully utilizing the auxiliary information brought by multi-resolution analysis. Therefore, we propose a super-resolution network based on the wavelet multi-resolution framework (WMRSR) to capture the auxiliary information contained in multiple subspaces and to be aware of the interdependencies between spatial domain and wavelet domain features.
Article
Green & Sustainable Science & Technology
Jikai Duan, Mingheng Chang, Xiangyue Chen, Wenpeng Wang, Hongchao Zuo, Yulong Bai, Bolong Chen
Summary: This paper proposes a new hybrid model for wind speed forecasting using empirical mode decomposition and a combination of multiple neural networks. Experimental results demonstrate that the proposed model has better accuracy and stability, making it a reliable method for wind speed forecasting.
Article
Thermodynamics
Xuguang Wang, Xiao Li, Jie Su
Summary: In this study, a tiled convolutional neural network (TCNN) based-model is proposed to predict the distribution of future wind speed. The distribution deviation between historical and future wind speed is minimized by weighting the loss contribution of historical data. A branch accumulation error decreasing (BED) rule is introduced to adaptively determine the optimal mode number for the variational mode decomposition (VMD) method. Two hybrid models, which employ both the distribution drift correction process and BED rule-based decomposition process, are proposed. The effectiveness of the proposed models is verified using data from two different wind farms in China. Compared with traditional short-term wind speed forecasting models, the proposed models show considerably better robustness to the distribution drift of the wind speed and achieve significantly higher forecasting accuracy in both the one-step ahead and multistep ahead wind speed forecasting scenarios.
Article
Green & Sustainable Science & Technology
Maria Alejandra Zuniga Alvarez, Kodjo Agbossou, Alben Cardenas, Sousso Kelouwani, Loic Boulon
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2020)
Article
Energy & Fuels
David Toquica, Kodjo Agbossou, Roland Malhame, Nilson Henao, Sousso Kelouwani, Alben Cardenas
Review
Construction & Building Technology
Luis Rueda, Kodjo Agbossou, Alben Cardenas, Nilson Henao, Sousso Kelouwani
BUILDING AND ENVIRONMENT
(2020)
Article
Computer Science, Information Systems
Cristina Guzman, Alben Cardenas, Kodjo Agbossou
IEEE SYSTEMS JOURNAL
(2020)
Article
Construction & Building Technology
William Devia, Kodjo Agbossou, Alben Cardenas
Summary: Home Energy Management systems are rapidly developing, supported by smart appliances and new smart-grid frameworks, to implement demand-side management strategies effectively. The research achieved the goal of reducing the energy consumption profile of heating systems during peak demand periods using optimization algorithms and an agent-based architecture, resulting in significant cost reduction and peak-to-average ratio decrease.
ENERGY AND BUILDINGS
(2021)
Article
Energy & Fuels
David L. Alvarez, Diego F. Rodriguez, Alben Cardenas, F. Faria da Silva, Claus Leth Bak, Rodolfo Garcia, Sergio Rivera
Summary: This paper addresses a methodology for optimal decision making for electrical systems, aiming to prioritize the replacement and maintenance of a power asset fleet by optimizing return of investment. The methodology considers risk index, replacement and maintenance costs, and company revenue, estimating and predicting risk index for each asset based on condition records and failure consequences, and using Monte Carlo simulations to evaluate asset failure impact on reliability, environment, legality, and finance. The methodology was implemented in PywerAPM for assessing optimal decisions, and applied to the power transformer fleet of the New England IEEE 39 Bus System to rank the fleet by risk index and estimate optimal replacement and maintenance.
Article
Robotics
Amin Ghobadpour, Alben Cardenas, German Monsalve, Hossein Mousazadeh
Summary: This article analyzes the energy behavior of a Photovoltaic/Fuel Cell Agricultural Mobile Robot (PV/FCAMR) and proposes an approach based on optimization algorithms to determine the sizes of the FC and battery. The results show that the proposed arrangement can extend the FCAMR autonomy by 350% and adding a PV system can increase the vehicle's range by up to 5%.
Article
Energy & Fuels
German Monsalve, Alben Cardenas, Diego Acevedo-Bueno, Wilmar Martinez
Summary: The battery State of Charge (SoC) is critical for agricultural robots in managing battery and energy. This paper evaluates the limits of SoC estimation using RC model and Thevenin model for LFP and SLA batteries. The results show that the RC model is not suitable for LFP battery, while the Thevenin model performs well for both chemistries.
Article
Engineering, Mechanical
Ingrid J. Moreno, Dina Ouardani, Daniel Chaparro-Arce, Alben Cardenas
Summary: This paper proposes a real-time hardware-in-the-loop emulation method for low-cost agricultural robots to validate path tracking strategies. It reduces costs and time spent in the early development stages and contributes to progress in this research area.
Review
Engineering, Mechanical
Amin Ghobadpour, German Monsalve, Alben Cardenas, Hossein Mousazadeh
Summary: The agriculture sector is facing challenges such as population growth, increasing energy demands, and global warming, which require methods to achieve energy independence and reduce emissions. Electrification of vehicles and renewable energy sources are essential for smart farming, while autonomous robot technology and green fuels are important for meeting food demands and addressing environmental issues.
Article
Engineering, Mechanical
Alben Cardenas, Cristina Guzman, Wilmar Martinez
Summary: Electric Vehicle (EV) technologies offer a leading-edge solution for clean transportation, but face challenges such as high prices and infrastructure requirements. In winter, peak power demand for EV charging may stress the grid, posing a threat to its stability.
Proceedings Paper
Engineering, Industrial
J. A. Dominguez, A. W. Dante, K. Agbossou, N. Henao, J. Campillo, A. Cardenas, S. Kelouwani
2020 IEEE 29TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE)
(2020)
Proceedings Paper
Computer Science, Theory & Methods
Cristina Guzman, Alben Cardenas, Kodjo Agbossou, Mamadou Doumbia
DATA-DRIVEN MODELING FOR SUSTAINABLE ENGINEERING, ICEASSM 2017
(2020)
Article
Computer Science, Information Systems
Sayed Saeed Hosseini, Kodjo Agbossou, Sousso Kelouwani, Alben Cardenas, Nilson Henao
Proceedings Paper
Engineering, Electrical & Electronic
S. Hosseini, N. Henao, S. Kelouwani, K. Agbossou, A. Cardenas
2019 IEEE 28TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE)
(2019)
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.