Yafeng Wen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yafeng Wen has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Gang-Jun Gong
North China Electric Power University No.2 Beinong Road
1 shared publication - Gangjun Gong
Beijing Engineering Research Center of Energy Electric Power Information Security, North China Electric Power University, Beijing 102206, China
1 shared publication - Hao Liu
CSSC Windpower Development Co., Ltd., Beijing 100097, China
1 shared publication - Jing Zhang
Beijing RETEC New Energy Technology Co., Ltd., Beijing 100079, China
1 shared publication Jing Zhao
Beijing China-power Information Technology Co. Ltd No.15 Xiaoying East Road
1 shared publication- Jixing Chen
Department of Electrical Engineering, School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 100096, China
1 shared publication
Latest Publications
- Open Access
Study on Atmospheric Stability and Wake Attenuation Constant of Large Offshore Wind Farm in Yellow Sea
Power generation estimation is one of the key steps in wind farm micro-sitting, and its accuracy is related to the wake decay constant in the wake model. Considering the influence of wind resource distribution in different regions, this study carried out interval optimization for the wake decay constant of offshore wind farms in the Yellow Sea region of China. Given the very small length of the sea surface roughness, atmospheric stability is a critical factor influencing the wake extent and recovery speed of offshore wind farms. WAsP 10 (Wind Atlas Analysis and Application software) simulates the wake of various scenarios, and the selection range of wake attenuation constant is investigated by combining the cases of two offshore wind farms in the Yellow Sea region. The study found that the higher the atmospheric stability, the larger the wake and the lower the wake attenuation coefficient. The Yellow Sea wind farm’s wake error system is between 0.03 and 0.04, and the forecast error can be controlled to within 3%. When simulating the wind farm at Yellow Sea offshore for improving power generation and economic evaluation, it is critical to select the correct value range of wake decay constant.
Open AccessStudy on Atmospheric Stability and Wake Attenuation Constant of Large Offshore Wind Farm in Yellow Sea
Power generation estimation is one of the key steps in wind farm micro-sitting, and its accuracy is related to the wake decay constant in the wake model. Considering the influence of wind resource distribution in different regions, this study carried out interval optimization for the wake decay constant of offshore wind farms in the Yellow Sea region of China. Given the very small length of the sea surface roughness, atmospheric stability is a critical factor influencing the wake extent and recovery speed of offshore wind farms. WAsP 10 (Wind Atlas Analysis and Application software) simulates the wake of various scenarios, and the selection range of wake attenuation constant is investigated by combining the cases of two offshore wind farms in the Yellow Sea region. The study found that the higher the atmospheric stability, the larger the wake and the lower the wake attenuation coefficient. The Yellow Sea wind farm’s wake error system is between 0.03 and 0.04, and the forecast error can be controlled to within 3%. When simulating the wind farm at Yellow Sea offshore for improving power generation and economic evaluation, it is critical to select the correct value range of wake decay constant.
- Open Access
Research on Short-Term Load Prediction Based on Seq2seq Model
Electricity load prediction is the primary basis on which power-related departments to make logical and effective generation plans and scientific scheduling plans for the most effective power utilization. The perpetual evolution of deep learning has recommended advanced and innovative concepts for short-term load prediction. Taking into consideration the time and nonlinear characteristics of power system load data and further considering the impact of historical and future information on the current state, this paper proposes a Seq2seq short-term load prediction model based on a long short-term memory network (LSTM). Firstly, the periodic fluctuation characteristics of users’ load data are analyzed, establishing a correlation of the load data so as to determine the model’s order in the time series. Secondly, the specifications of the Seq2seq model are given preference and a coalescence of the Residual mechanism (Residual) and the two Attention mechanisms (Attention) is developed. Then, comparing the predictive performance of the model under different types of Attention mechanism, this paper finally adopts the Seq2seq short-term load prediction model of Residual LSTM and the Bahdanau Attention mechanism. Eventually, the prediction model obtains better results when merging the actual power system load data of a certain place. In order to validate the developed model, the Seq2seq was compared with recurrent neural network (RNN), LSTM, and gated recurrent unit (GRU) algorithms. Last but not least, the performance indices were calculated. when training and testing the model with power system load data, it was noted that the root mean square error (RMSE) of Seq2seq was decreased by 6.61%, 16.95%, and 7.80% compared with RNN, LSTM, and GRU, respectively. In addition, a supplementary case study was carried out using data for a small power system considering different weather conditions and user behaviors in order to confirm the applicability and stability of the proposed model. The Seq2seq model for short-term load prediction can be reported to demonstrate superiority in all areas, exhibiting better prediction and stable performance.
Open AccessResearch on Short-Term Load Prediction Based on Seq2seq Model
Electricity load prediction is the primary basis on which power-related departments to make logical and effective generation plans and scientific scheduling plans for the most effective power utilization. The perpetual evolution of deep learning has recommended advanced and innovative concepts for short-term load prediction. Taking into consideration the time and nonlinear characteristics of power system load data and further considering the impact of historical and future information on the current state, this paper proposes a Seq2seq short-term load prediction model based on a long short-term memory network (LSTM). Firstly, the periodic fluctuation characteristics of users’ load data are analyzed, establishing a correlation of the load data so as to determine the model’s order in the time series. Secondly, the specifications of the Seq2seq model are given preference and a coalescence of the Residual mechanism (Residual) and the two Attention mechanisms (Attention) is developed. Then, comparing the predictive performance of the model under different types of Attention mechanism, this paper finally adopts the Seq2seq short-term load prediction model of Residual LSTM and the Bahdanau Attention mechanism. Eventually, the prediction model obtains better results when merging the actual power system load data of a certain place. In order to validate the developed model, the Seq2seq was compared with recurrent neural network (RNN), LSTM, and gated recurrent unit (GRU) algorithms. Last but not least, the performance indices were calculated. when training and testing the model with power system load data, it was noted that the root mean square error (RMSE) of Seq2seq was decreased by 6.61%, 16.95%, and 7.80% compared with RNN, LSTM, and GRU, respectively. In addition, a supplementary case study was carried out using data for a small power system considering different weather conditions and user behaviors in order to confirm the applicability and stability of the proposed model. The Seq2seq model for short-term load prediction can be reported to demonstrate superiority in all areas, exhibiting better prediction and stable performance.
- Open Access
- 1 January 2016
- Published by Atlantis Press SARL
Study on the Influence Factors of the Success Rate in Electric Information Acquisition System
- 1 January 2016
- Published by Atlantis Press SARL
Open AccessStudy on the Influence Factors of the Success Rate in Electric Information Acquisition System