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
Computer Science, Information Systems
Solui Yu, Jin Hur
Summary: This study proposed an enhanced performance evaluation metric for wind power ramp event forecasting, and analyzed the forecasting results using this metric. The results highlight the advantages of the proposed metric over the widely used confusion matrix for performance evaluation, which has more detailed and visually based analytical capabilities. The study is important for real-time curtailment forecasting and decision-making in high wind power scenarios.
Article
Green & Sustainable Science & Technology
Yanting Li, Zhenyu Wu, Yan Su
Summary: This paper proposes an adaptive short-term wind power prediction method that automatically detects concept drifts and updates the forecast model, improving prediction accuracy.
Article
Energy & Fuels
Ravi Pandit, Davide Astolfi, Anh Minh Tang, David Infield
Summary: Offshore wind turbines have gained popularity worldwide in recent years due to their ability to generate a large amount of electrical power. However, they are vulnerable to damage from high-speed winds, making accurate weather forecasting crucial for optimizing their operation and maintenance. This paper proposes three sequential data-driven techniques for long-term weather forecasting and compares their strengths and weaknesses. The study results suggest that the proposed technique can generate realistic and reliable weather forecasts and respond well to seasonality.
Article
Mathematics
Chin-Wen Liao, I-Chi Wang, Kuo-Ping Lin, Yu-Ju Lin
Summary: The study developed a Fuzzy Seasonal LSTM (FSLSTM) model to forecast monthly wind power output in Taiwan, and found that FSLSTM outperformed other methods in terms of forecasting accuracy, providing reliable prediction values for Taiwan's wind power output dataset.
Article
Thermodynamics
Sahra Khazaei, Mehdi Ehsan, Soodabeh Soleymani, Hosein Mohammadnezhad-Shourkaei
Summary: This article proposes a high-accuracy hybrid approach for short-term wind power forecasting using historical data of wind farm and Numerical Weather Prediction (NWP) data, including three stages: wind direction forecasting, wind speed forecasting, and wind power forecasting. The method involves outlier detection, decomposition of time series, feature selection, and prediction using Multilayer Perceptron (MLP) neural network, with evaluation showing very high accuracy when tested with data from the Sotavento wind farm in Spain.
Article
Automation & Control Systems
Jianqi An, Feng Yin, Min Wu, Jinhua She, Xin Chen
Summary: The study proposes a short-term wind power prediction method based on multisource wind speed fusion, which significantly increases the accuracy of wind power generation prediction compared to conventional methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
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
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
Energy & Fuels
Shuai Hu, Yue Xiang, Hongcai Zhang, Shanyi Xie, Jianhua Li, Chenghong Gu, Wei Sun, Junyong Liu
Summary: Wind power generation is rapidly growing worldwide, but its stochastic nature presents challenges. This study proposes a hybrid short-term wind power forecasting method that integrates corrected numerical weather prediction and spatial correlation, improving forecasting accuracy.
Article
Environmental Sciences
Karla Pereyra-Castro, Ernesto Caetano
Summary: In this study, extreme wind ramps at different geographical sites in Mexico were characterized, and it was found that mid-latitude systems are the main cause of winter storms while downdraft contributes to summer storms. The study also showed that using statistical techniques can improve wind forecasting by reducing biases and enhancing the prediction accuracy of positive and negative wind ramps.
Article
Automation & Control Systems
Md Alamgir Hossain, Evan Gray, Junwei Lu, Md Rabiul Islam, Md Shafiul Alam, Ripon Chakrabortty, Hemanshu Roy Pota
Summary: This article proposes a novel framework, CEMOLS, to improve the prediction accuracy of very short-term wind power generation. The framework combines CEEMDAN, MBO, and LSTM models and demonstrates an improvement in forecasting accuracy compared to the benchmark model.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Thermodynamics
Shilin Sun, Yuekai Liu, Qi Li, Tianyang Wang, Fulei Chu
Summary: This paper proposes a novel method to enhance the reliability of wind condition knowledge by considering the spatial information of surrounding wind turbines and achieve wind power modeling using transformer neural networks based on the multi-head attention mechanism. Experimental results show that the proposed method outperforms other approaches, especially in large steps forecasting, with significantly better average values of mean absolute error.
ENERGY CONVERSION AND MANAGEMENT
(2023)
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
Energy & Fuels
Bogdan Bochenek, Jakub Jurasz, Adam Jaczewski, Gabriel Stachura, Piotr Sekula, Tomasz Strzyzewski, Marcin Wdowikowski, Mariusz Figurski
Summary: In the Polish power system, renewable energy sources like wind and solar energy play a growing role with high variability and low dispatchability. This study explores the prediction of day-ahead wind power at the national level in Poland using machine learning methods, achieving accuracy with a mean absolute percentage error of 26.7% and root mean square error of 4.5% for 2020. Seasonal and daily variations in prediction errors were observed, with higher errors in summer and daytime.
Article
Geosciences, Multidisciplinary
Huajin Li, Yusen He, He Yang, Yong Wei, Songlin Li, Jianqiang Xu
Summary: This study used a data-driven approach to predict rainfall through time-series modeling and optimally pruned extreme learning machine, with results showing that the proposed framework outperformed other benchmarking machine learning algorithms in six case studies.
Article
Automation & Control Systems
Tinghui Ouyang, Witold Pedrycz, Orion F. Reyes-Galaviz, Nick J. Pizzi
Summary: This study proposes a development scheme for describing large numeric data by building a limited collection of representative information granules using clustering algorithms, with experimental results showing good performance.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Computer Science, Artificial Intelligence
Tinghui Ouyang
Summary: A new improved ELM-AE architecture is proposed in this paper, utilizing low-rank matrix factorization to learn optimal low-dimensional features. This allows for arbitrary setting of the hidden layer dimension and enhances features' non-linear ability.
Article
Green & Sustainable Science & Technology
Zhenhao Tang, Gengnan Zhao, Tinghui Ouyang
Article
Automation & Control Systems
Tinghui Ouyang, Witold Pedrycz, Nick J. Pizzi
Summary: Rule-based models are effective in analyzing complex nonlinear system behaviors. Utilizing DBSCAN to construct information granules can enhance model accuracy. Experiments showed that the rule-based modeling approach proposed in this paper performs the best in analyzing system behaviors.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Chemistry, Multidisciplinary
Tinghui Ouyang, Vicent Sanz Marco, Yoshinao Isobe, Hideki Asoh, Yutaka Oiwa, Yoshiki Seo
Summary: In the face of increasing applications of AI models, it is crucial for designers to construct safety-critical systems, especially in life- and property-related fields. Corner case data, as a major factor affecting the safety of AI models, and its related detection techniques play an important role in the AI design phase and quality assurance. This paper introduces three modified versions of distance-based-SA (DSA) for detecting corner cases in classification problems, showing feasibility and usefulness through experiment analysis on various datasets. The developed DSA tools demonstrate improved performance in describing corner cases' behaviors through qualitative and quantitative experiments.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Tinghui Ouyang, Xun Shen
Summary: The paper introduces a new ELM-AE model based on approximation of hybrid high-order polynomial functions to address issues in existing models and improve the effectiveness of feature learning.
APPLIED INTELLIGENCE
(2022)
Article
Engineering, Geological
Huajin Li, Yusen He, Qiang Xu, Jiahao Deng, Weile Li, Yong Wei
Summary: Landslides are catastrophic natural hazards that can cause loss of life, property damage, and economic disruption. In this study, an image-based two-phase data-driven framework is proposed for detecting and segmenting landslide regions using satellite images. This framework outperforms other benchmarking algorithms in accurately segmenting landslides.
Article
Computer Science, Artificial Intelligence
Tinghui Ouyang
Summary: In this paper, a new rule-based modeling approach is proposed to analyze the dynamic behaviors of complex systems in the era of big data. This approach incorporates structural information mining and granular computing, and uses DBSCAN and granular fuzzy intervals to reflect system behaviors on uncertainty. Experimental analysis demonstrates the superiority of the proposed approach in various design scenarios.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Tinghui Ouyang, Xinhui Zhang
Summary: This paper proposes an advanced rule-based modeling method based on DBSCAN-inspired granular descriptors to model complex nonlinear and non-numeric systems. The method enhances the representation ability of rules by obtaining data structures through the DBSCAN clustering algorithm and constructing granular descriptors. Experimental results demonstrate that the proposed method outperforms conventional rule-based modeling method FCM in both modeling and time consumption.
Article
Chemistry, Multidisciplinary
Xinhui Zhang, Xun Shen, Tinghui Ouyang
Summary: This paper proposes a new DBSCAN extension algorithm for online clustering, which combines DBSCAN, granular computing, and fuzzy rule-based modeling. The algorithm overcomes the limitations of traditional clustering algorithms in dealing with nonlinear spatial datasets, and shows superior performance in terms of accuracy and computation overhead reduction compared to conventional methods and existing DBSCAN variants.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Xinhui Zhang, Tinghui Ouyang
Summary: This paper proposes an advanced method for forming three-way decision classification rules, which uses information granules and information entropy to describe uncertainty and form fuzzy rules to solve classification problems. Experimental results show that classification rules considering uncertain data perform better in decision-making processes and have an improvement compared to traditional methods.
APPLIED SCIENCES-BASEL
(2022)
Article
Geosciences, Multidisciplinary
Huajin Li, Qiang Xu, Yusen He, Xuanmei Fan, He Yang, Songlin Li
Summary: This study proposed a deep learning framework based on long short-term memory to model and predict sharp deformation of landslides, demonstrating its accuracy in identifying future sharp deformations. The use of Hurst exponent in prediction errors helped reveal abnormal patterns in sharp deformation, providing valuable support for on-site risk analysis and decision-making by geological engineers.
GEOMATICS NATURAL HAZARDS & RISK
(2021)
Article
Automation & Control Systems
Xun Shen, Tinghui Ouyang, Zhengxi Chen, Shuang Zhao, Jiaxin Fang, Yahui Zhang
Summary: This study models the dynamics of DAB converters using a hybrid automaton approach and designs a current stress policy using a randomized computation method. The results indicate that the quadruple-phase-shift method performs better in terms of current stress.
IEEE CONTROL SYSTEMS LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Tinghui Ouyang, Chongwu Wang, Zhangjun Yu, Robert Stach, Boris Mizaikoff, Guang-Bin Huang, Qi-Jie Wang
Summary: This study suggests utilizing spectroscopic gas sensing methods and a deep learning network algorithm to measure NOx concentrations in sustainable developments, showing the effectiveness of the approach in emission monitoring.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Green & Sustainable Science & Technology
Seyed Majid Hashemzadeh, Mohammed A. Al-Hitmi, Hadi Aghaei, Vafa Marzang, Atif Iqbal, Ebrahim Babaei, Seyed Hossein Hosseini, Shirazul Islam
Summary: This article proposes an interleaved high step-up DC-DC converter topology with an ultra-high voltage conversion ratio for renewable energy applications. The converter utilizes an interleaved structure to reduce the input source current ripple, which is advantageous for solar PV sources. By employing voltage multiplier cells and coupled inductor techniques, the topology enhances the output voltage. The article provides comprehensive operation modes and steady-state analyses, compares the proposed structure with other similar converter topologies, and validates the mathematical analysis with experimental results.
IET RENEWABLE POWER GENERATION
(2024)
Article
Green & Sustainable Science & Technology
Gang Xu, Zixuan Guo
Summary: This paper proposes a two-stage resilience enhancement strategy for the recovery of critical loads after disasters. The first stage utilizes a heuristic algorithm to determine the post-disaster topology, while the second stage incorporates user demand response to maximize the socio-economic value of the recovery.
IET RENEWABLE POWER GENERATION
(2024)
Article
Green & Sustainable Science & Technology
Faruk Oral
Summary: This study investigates the wind characteristics and electricity generation potential from wind energy in the Bitlis-Rahva region in eastern Turkey. Wind data from the Bitlis meteorological station is analyzed using the WindPRO program to determine the wind speed distribution and predict turbine performance. The results show that the region has low wind energy capacity factor, indicating it is not efficient for wind energy investments. However, it is suggested that higher altitudes in the region may have better wind energy utilization.
IET RENEWABLE POWER GENERATION
(2024)
Article
Green & Sustainable Science & Technology
Yingjie Tang, Zheren Zhang, Zheng Xu
Summary: This paper investigates the modular multilevel matrix converter with symmetrically integrated energy storage for low frequency AC system. An evaluation method for the minimum required number of active submodules is presented, and the influences of operating conditions on the minimum required number of active submodules are studied. Issues about the converter control system are also discussed in this paper.
IET RENEWABLE POWER GENERATION
(2024)
