Article
Energy & Fuels
Petr Spodniak, Kimmo Ollikka, Samuli Honkapuro
Summary: As the share of wind power generation increases, markets closer to real time are becoming more important, playing a significant role in price risk hedging, capacity markets, and other decision making processes in the future.
Article
Thermodynamics
Yang Cui, Zhenghong Chen, Yingjie He, Xiong Xiong, Fen Li
Summary: This study proposes an improved hybrid model that utilizes long short-term memory and wind power ramp event prediction to forecast day-ahead wind power fluctuations. The model outperforms existing methods and provides guidance for the safe dispatching and economic operation of power systems.
Article
Engineering, Electrical & Electronic
Jean-Francois Toubeau, Pierre-David Dapoz, Jeremie Bottieau, Aurelien Wautier, Zacharie De Greve, Francois Vallee
Summary: This paper focuses on improving the accuracy of day-ahead prediction of onshore wind generation using LSTM networks to efficiently capture complex temporal dynamics. Different techniques for model recalibration during practical utilization are analyzed to continuously refine the prediction tool, and the financial savings from improved forecast accuracy are estimated.
ELECTRIC POWER SYSTEMS RESEARCH
(2021)
Article
Thermodynamics
Huijing Fan, Zhao Zhen, Nian Liu, Yiqian Sun, Xiqiang Chang, Yu Li, Fei Wang, Zengqiang Mi
Summary: This paper proposes a novel probabilistic forecasting method based on SDA, FCM, LSTM, and KDE, considering the correlation between wind power fluctuation patterns and forecasting errors. Simulation results show that introducing pattern recognition can improve the skill score of probabilistic forecasting by 36.50% on average.
Article
Energy & Fuels
Chenjia Hu, Yan Zhao, He Jiang, Mingkun Jiang, Fucai You, Qian Liu
Summary: This paper proposes a neural network model based on CEEMDAN-LSTM-TCN for predicting ultra-short term wind energy. By decomposing wind velocity data and establishing the model, it achieves real-time prediction of wind energy with good forecasting performance.
Article
Chemistry, Multidisciplinary
Oliver Probst, Luis Minchala
Summary: The proposed innovation reduces large drops in wind power by utilizing the self-regulating capabilities of wind turbines and wind measurement instrumentation, aiding in meeting system operators' requirements for power decrease rates.
APPLIED SCIENCES-BASEL
(2021)
Article
Energy & Fuels
Hui Huang, Qiliang Zhu, Xueling Zhu, Jinhua Zhang
Summary: This paper proposes an adaptive, data-driven stacking ensemble learning framework for the short-term output power forecasting of renewable energy. Five base-models are adaptively selected via determina tion coefficient (R-2) indices from twelve candidate models. The results demonstrate that the proposed stacking ensemble learning model has better prediction precision and stronger generalization performance compared to the benchmark models.
Article
Engineering, Electrical & Electronic
Bin Zhou, Haoran Duan, Qiuwei Wu, Huaizhi Wang, Siu Wing Or, Ka Wing Chan, Yunfan Meng
Summary: This paper introduces a hybrid forecasting model based on semi-supervised generative adversarial network for short-term wind power and ramp event prediction. By decomposing wind energy data time series and employing semi-supervised regression, non-linear and dynamic behaviors are extracted to enhance forecasting accuracy, along with a self-tuning forecasting strategy for improved performance.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2021)
Article
Economics
Xiao Hu, Jurate Jaraite, Andrius Kazukauskas
Summary: The study investigates the process of electricity price formation in the Swedish intraday market with a focus on wind power's influence. Results indicate that despite small trading volumes, the market operates properly, with intraday price premia responding primarily to wind power forecast errors and supply-demand imbalances. Forecast errors affect central and southern Sweden, but have minimal impact on the north, while unplanned nuclear plant outages do not affect intraday price premia.
Article
Economics
Erik Lundin
Summary: This study evaluates the impact of the 2011 Swedish electricity market splitting reform on the allocation of wind power. The findings show that 18% of projects by large developers after the reform were allocated to the high price zone, while small developers did not react to the reform. Similar results were confirmed using a nearest neighbor matching estimator.
Article
Engineering, Electrical & Electronic
Guang Zheng Yu, Liu Lu, Bo Tang, Si Yuan Wang, C. Y. Chung
Summary: This article proposes an ultra-short-term wind power subsection forecasting method based on extreme weather identification. By accurately identifying extreme weather periods and combining improved GRU point forecasting with improved kernel density estimation-wind power probabilistic forecasting, the method effectively improves the accuracy of wind power prediction.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2023)
Article
Mathematics
Hyunsoo Kim, Jiseok Jeong, Changwan Kim
Summary: This study proposes an improved model for electricity demand forecasting, which enhances the accuracy of both peak and overall electricity demand predictions. By incorporating residual learning and LSTM, the model outperforms benchmark models and provides highly accurate forecasting information, facilitating load balancing for consumers and ensuring the stable operation of national power systems.
Review
Energy & Fuels
Guglielmo D'Amico, Filippo Petroni, Salvatore Vergine
Summary: This paper provides a general overview of the concept of ramp rate limitation and its applications in control strategies, focusing on its implementation in wind power production.
Article
Energy & Fuels
Moritz Lochmann, Heike Kalesse-Los, Michael Schaefer, Ingrid Heinrich, Ronny Leinweber
Summary: Although wind power predictions have shown improvement in the past decade, uncertainties still remain due to sudden large changes in wind speed. Analysis of a wind farm in Eastern Germany found that ramp events were most frequent in March and April, and least frequent in November and December. Furthermore, incorporating observational wind speed data significantly improved the performance of the wind power prediction tool, especially during ramp events.
Article
Green & Sustainable Science & Technology
Lazaro Endemano-Ventura, Javier Serrano Gonzalez, Juan Manuel Roldan Fernandez, Manuel Burgos Payan, Jesus Manuel Riquelme Santos
Summary: The paper presents a method to calculate the optimal bidding strategy for a wind power plant and validates it using real data and market conditions. The optimal bidding strategy mainly depends on the system deviation, showing more advantages in practical applications.
Article
Engineering, Environmental
Cristobal Gallego-Castillo, Alvaro Cuerva-Tejero, Mohanad Elagamy, Oscar Lopez-Garcia, Sergio Avila-Sanchez
Summary: This article presents a novel method for determining optimal autoregressive models to reproduce a predefined target autocovariance function, utilizing flexibility and genetic algorithms to optimize the generated time series.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Multidisciplinary Sciences
Alexandre Dias Tavares Costa, Steffanie Skau Amadei, Amanda Bertao-Santos, Tuany Rodrigues
Summary: Real-time PCR (qPCR) is a sensitive and precise technique for amplifying nucleic acid targets. Gelification technique is introduced to effectively preserve qPCR reagents and reduce setup time.
JOVE-JOURNAL OF VISUALIZED EXPERIMENTS
(2022)
Article
Energy & Fuels
Camila Correa-Jullian, Sergio Cofre-Martel, Gabriel San Martin, Enrique Lopez Droguett, Gustavo de Novaes Pires Leite, Alexandre Costa
Summary: This paper explores the application of machine learning and deep learning techniques in prognostics and health management, focusing on fault detection in wind turbine systems. The results show that quantum kernel methods perform comparably to traditional machine learning models and can outperform them in terms of dimensionality reduction.
Article
Environmental Sciences
Anne F. Van Loon, Sally Rangecroft, Gemma Coxon, Micha Werner, Niko Wanders, Giuliano Di Baldassarre, Erik Tijdeman, Marianne Bosman, Tom Gleeson, Alexandra Nauditt, Amir Aghakouchak, Jose Agustin Brena-Naranjo, Omar Cenobio-Cruz, Alexandre Cunha Costa, Miriam Fendekova, Graham Jewitt, Daniel G. Kingston, Jessie Loft, Sarah M. Mager, Iman Mallakpour, Ilyas Masih, Hector Maureira-Cortes, Elena Toth, Pieter Van Oel, Floris Van Ogtrop, Koen Verbist, Jean-Philippe Vidal, Li Wen, Meixiu Yu, Xing Yuan, Miao Zhang, Henny A. J. Van Lanen
Summary: Human activities both aggravate and alleviate streamflow drought, with water abstraction being the dominant aggravating factor and water transfers effectively reducing drought. Reservoir releases can alleviate drought in dry season but change flow seasonality. Land use has a smaller impact, with both positive and negative effects observed.
ENVIRONMENTAL RESEARCH LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Arthur Freire, Manuel Neto, Mirko Perkusich, Alexandre Costa, Kyller Gorgonio, Hyggo Almeida, Angelo Perkusich
Summary: Agile Software Development (ASD) is a popular method in software development, emphasizing teamwork and the value of individuals. However, there is no consensus regarding the factors for defining an ASD Teamwork construct. This paper presents a thematic network that synthesizes literature and provides a basis for researchers and practitioners to understand agile teams' dynamics.
INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING
(2022)
Article
Environmental Sciences
Iran E. Lima Neto, Pedro H. A. Medeiros, Alexandre C. Costa, Mario C. Wiegand, Antonio Ricardo M. Barros, Mario U. G. Barros
Summary: This study simulated and modeled phosphorus loading in tropical reservoirs, finding that internal phosphorus load dominates during the wet season and increases with reservoir age. By adjusting the model structure, the simulation accuracy of phosphorus concentration was improved.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Parasitology
Alexandre C. Costa, Ticiane F. Gomes, Rafaella P. Moreira, Tahissa F. Cavalcante, George L. Mamede
Summary: This study found that hydroclimatic variability influences dengue incidence, with seasonal DI being impacted by precipitation and temperature. Precipitation and minimum air temperature were identified as the main explanatory variables in the model, with a two-month lagged predictor playing an important role. While GLS regressions were able to reproduce the beginning, development, and end of the dengue season, there were limitations in accurately predicting DI peaks and low DI levels.
Article
Engineering, Civil
Helen Sheehan, Elizabeth Traiger, Daniel Poole, Lars Landberg
Summary: Modelling the flow over terrain is crucial for wind resource assessment and this study presents a new data-driven approach to predict wind speed and direction changes caused by orography. The findings show promising results and could potentially lead to the development of a fully data-driven CFD wind resource model.
JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS
(2022)
Article
Green & Sustainable Science & Technology
Baris Kale, Sophia Buckingham, Jeroen van Beeck, Alvaro Cuerva-Tejero
Summary: A validation study is conducted to test the performance of a generalized actuator disk model (GAD) implemented into a numerical weather prediction code in simulating the aerodynamic behavior of a real-scale wind turbine under varying atmospheric conditions. Multiple large-eddy simulations (LESs) are performed using the GAD model to calculate wind turbine-induced forces and validate against benchmarks and experimental data.
Article
Energy & Fuels
Mohammadreza Mohammadi, Majid Bastankhah, Paul Fleming, Matthew Churchfield, Ervin Bossanyi, Lars Landberg, Renzo Ruisi
Summary: This research presents a new engineering analytical model that predicts the effect of turbine yaw misalignment and inflow wind veer on wake flow distribution. Two methods are examined to consider the veered inflow, with the second method being more realistic by accounting for wind veer on wind velocity direction and yaw angle. The results demonstrate that the two methods provide similar outputs for small variations in wind direction, but the difference becomes more evident with an increase in wind veer. High-fidelity simulations were used to validate the model predictions.
Article
Engineering, Civil
Mohanad Elagamy, Cristobal Gallego-Castillo, Alvaro Cuerva-Tejero, Oscar Lopez-Garcia, Sergio Avila-Sanchez
Summary: In this study, a novel approach is proposed to optimize the calibration parameters of a vector autoregressive model for synthetic generation of turbulent wind fields. The approach is based on eigenanalysis of the companion matrix of the vector autoregressive model. The cross-power spectral density matrix for different turbulent wind conditions is considered as targets and compared with existing approaches for calibration of vector autoregressive model parameters, discussing the implications of determining the vector autoregressive model in the frequency or time domain.
JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS
(2023)
Article
Green & Sustainable Science & Technology
Baris Kale, Sophia Buckingham, Jeroen van Beeck, Alvaro Cuerva-Tejero
Summary: In this study, the GAL model is used to investigate the wake characteristics and aerodynamic performance of a wind turbine in stratified atmospheric boundary layer flows. The results show that the GAL model is capable of reproducing the observed wake behavior and the aerodynamic response of the wind turbine under varying atmospheric stability conditions.
Article
Computer Science, Information Systems
Alexandre Costa, Felipe Ramos, Mirko Perkusich, Ademar De Sousa Neto, Luiz Silva, Felipe Cunha, Thiago Rique, Hyggo Almeida, Angelo Perkusich
Summary: Forming effective teams for multiple projects is a challenging task, known as the Multiple Team Formation problem. Existing solutions do not work well for Scrum projects. Therefore, we developed a two-step approach, including a Structured Task Model and a Genetic Algorithm, to form teams for target projects. Our approach achieved high precision and acceptance rate, indicating the potential of providing teams close to project managers' expectations. The Structured Task Model also offers a promising way to build technical profiles for Scrum developers.
Article
Energy & Fuels
Luis A. Martinez-Tossas, Philip Sakievich, Matthew J. Churchfield, Charles Meneveau
Summary: This work revisits the filtered lifting line theory and provides a more general formulation for solving flow problems with significant changes in chord, such as wind turbine blades.