“双碳”背景下风电的渗透率不断提高,将对电力系统的形态和运行机制产生深刻影响。本文提出了一种基于双向长短期记忆Bi-LSTM(bidirectional long short-term memory)循环神经网络的风储系统控制策略。采用双向长短时循环神经网络提取...“双碳”背景下风电的渗透率不断提高,将对电力系统的形态和运行机制产生深刻影响。本文提出了一种基于双向长短期记忆Bi-LSTM(bidirectional long short-term memory)循环神经网络的风储系统控制策略。采用双向长短时循环神经网络提取控制结果与风电场实际出力以及储能状态间的时序信息,通过构建基于双向长短时记忆循环神经网络的控制模型,使得风电场在多种运行工况下能够快速、准确地得到储能系统调节结果。基于实际风电场数据仿真结果表明,本文所提控制策略能够保证在一定经济效益的前提下,将风储系统控制误差保持在0.50%~1.37%。展开更多
Objective To investigate influence of immunosuppression strategy optimization on outcomes of renal transplant recipients in the last decades. Methods Data from 404 renal transplant recipients from Jan. 1st,2001 to Dec...Objective To investigate influence of immunosuppression strategy optimization on outcomes of renal transplant recipients in the last decades. Methods Data from 404 renal transplant recipients from Jan. 1st,2001 to Dec. 31st,2010 were analyzed retrospectively. The pa-展开更多
Background: In cardiology, it is controversial whether different therapy strategies influence prognosis after acute coronary syndrome. We examined and compared the long-term outcomes of invasive and conservative stra...Background: In cardiology, it is controversial whether different therapy strategies influence prognosis after acute coronary syndrome. We examined and compared the long-term outcomes of invasive and conservative strategies in patients with non-ST-segment elevation myocardial infarction (NSTEMI) and characterized the patients selected for an invasive approach. Methods: A total of 976 patients with acute NSTEMI were collected from December 2006 to October 2012 in the First Affiliated Hospital of Dalian Medical University Hospital. They are divided into conservative strategy (586 patients) and invasive strategy (390 patients) group. Unified tbllow-up questionnaire was performed by telephone contact (cut-off date was November, 2013). The long-term clinical events were analyzed and related to the different treatment strategies. Results: The median follow-up time was 29 months. Mortality was 28.7% (n = 168) in the conservative group and 2.1% (n = 8) in the invasive management at long-term clinical follow-up. The secondary endpoint (the composite endpoint) was 59.0% (n = 346) in the conservative group and 30.3% (n = 118) in the invasive management. Multivariate analysis showed that patients in the conservative group had higher all-cause mortality rates than those who had the invasive management (adjusted risk ratio [RR] = 7.795; 95% confidence interval [CI]: 3.796 16.006, P 〈 0.001), and the similar result was also seen in tile secondary endpoint (adjusted RR : 2.102; 95% (7: 1.694-2.610, P 〈 0.001 ). In the subgroup analysis according to each Thrombolysis in Myocardial Infarction risk score (TRS), log-rank analysis showed lower mortality and secondary endpoint rates in the invasive group with the intermediate and high-risk patients (TRS 3-7). Conclusions: An invasive strategy could improve long-term outcomes for NSTEMI patients, especially for intermediate and high-risk ones (TRS 3- 7).展开更多
Predicting wind speed accurately is essential to ensure the stability of the wind power system and improve the utilization rate of wind energy.However,owing to the stochastic and intermittent of wind speed,predicting ...Predicting wind speed accurately is essential to ensure the stability of the wind power system and improve the utilization rate of wind energy.However,owing to the stochastic and intermittent of wind speed,predicting wind speed accurately is difficult.A new hybrid deep learning model based on empirical wavelet transform,recurrent neural network and error correction for short-term wind speed prediction is proposed in this paper.The empirical wavelet transformation is applied to decompose the original wind speed series.The long short term memory network and the Elman neural network are adopted to predict low-frequency and high-frequency wind speed sub-layers respectively to balance the calculation efficiency and prediction accuracy.The error correction strategy based on deep long short term memory network is developed to modify the prediction errors.Four actual wind speed series are utilized to verify the effectiveness of the proposed model.The empirical results indicate that the method proposed in this paper has satisfactory performance in wind speed prediction.展开更多
文摘“双碳”背景下风电的渗透率不断提高,将对电力系统的形态和运行机制产生深刻影响。本文提出了一种基于双向长短期记忆Bi-LSTM(bidirectional long short-term memory)循环神经网络的风储系统控制策略。采用双向长短时循环神经网络提取控制结果与风电场实际出力以及储能状态间的时序信息,通过构建基于双向长短时记忆循环神经网络的控制模型,使得风电场在多种运行工况下能够快速、准确地得到储能系统调节结果。基于实际风电场数据仿真结果表明,本文所提控制策略能够保证在一定经济效益的前提下,将风储系统控制误差保持在0.50%~1.37%。
文摘Objective To investigate influence of immunosuppression strategy optimization on outcomes of renal transplant recipients in the last decades. Methods Data from 404 renal transplant recipients from Jan. 1st,2001 to Dec. 31st,2010 were analyzed retrospectively. The pa-
文摘Background: In cardiology, it is controversial whether different therapy strategies influence prognosis after acute coronary syndrome. We examined and compared the long-term outcomes of invasive and conservative strategies in patients with non-ST-segment elevation myocardial infarction (NSTEMI) and characterized the patients selected for an invasive approach. Methods: A total of 976 patients with acute NSTEMI were collected from December 2006 to October 2012 in the First Affiliated Hospital of Dalian Medical University Hospital. They are divided into conservative strategy (586 patients) and invasive strategy (390 patients) group. Unified tbllow-up questionnaire was performed by telephone contact (cut-off date was November, 2013). The long-term clinical events were analyzed and related to the different treatment strategies. Results: The median follow-up time was 29 months. Mortality was 28.7% (n = 168) in the conservative group and 2.1% (n = 8) in the invasive management at long-term clinical follow-up. The secondary endpoint (the composite endpoint) was 59.0% (n = 346) in the conservative group and 30.3% (n = 118) in the invasive management. Multivariate analysis showed that patients in the conservative group had higher all-cause mortality rates than those who had the invasive management (adjusted risk ratio [RR] = 7.795; 95% confidence interval [CI]: 3.796 16.006, P 〈 0.001), and the similar result was also seen in tile secondary endpoint (adjusted RR : 2.102; 95% (7: 1.694-2.610, P 〈 0.001 ). In the subgroup analysis according to each Thrombolysis in Myocardial Infarction risk score (TRS), log-rank analysis showed lower mortality and secondary endpoint rates in the invasive group with the intermediate and high-risk patients (TRS 3-7). Conclusions: An invasive strategy could improve long-term outcomes for NSTEMI patients, especially for intermediate and high-risk ones (TRS 3- 7).
基金the Gansu Province Soft Scientific Research Projects(No.2015GS06516)the Funds for Distinguished Young Scientists of Lanzhou University of Technology,China(No.J201304)。
文摘Predicting wind speed accurately is essential to ensure the stability of the wind power system and improve the utilization rate of wind energy.However,owing to the stochastic and intermittent of wind speed,predicting wind speed accurately is difficult.A new hybrid deep learning model based on empirical wavelet transform,recurrent neural network and error correction for short-term wind speed prediction is proposed in this paper.The empirical wavelet transformation is applied to decompose the original wind speed series.The long short term memory network and the Elman neural network are adopted to predict low-frequency and high-frequency wind speed sub-layers respectively to balance the calculation efficiency and prediction accuracy.The error correction strategy based on deep long short term memory network is developed to modify the prediction errors.Four actual wind speed series are utilized to verify the effectiveness of the proposed model.The empirical results indicate that the method proposed in this paper has satisfactory performance in wind speed prediction.