Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a s...Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a single prediction model is hard to capture temporal features effectively, resulting in diminished predictionaccuracy. In this study, a hybrid deep learning framework that integrates attention mechanism, convolution neuralnetwork (CNN), improved chaotic particle swarm optimization (ICPSO), and long short-term memory (LSTM), isproposed for short-term household load forecasting. Firstly, the CNN model is employed to extract features fromthe original data, enhancing the quality of data features. Subsequently, the moving average method is used for datapreprocessing, followed by the application of the LSTM network to predict the processed data. Moreover, the ICPSOalgorithm is introduced to optimize the parameters of LSTM, aimed at boosting the model’s running speed andaccuracy. Finally, the attention mechanism is employed to optimize the output value of LSTM, effectively addressinginformation loss in LSTM induced by lengthy sequences and further elevating prediction accuracy. According tothe numerical analysis, the accuracy and effectiveness of the proposed hybrid model have been verified. It canexplore data features adeptly, achieving superior prediction accuracy compared to other forecasting methods forthe household load exhibiting significant fluctuations across different seasons.展开更多
To better understand the mechanisms of hydrogen peroxide(H_(2)O_(2))’s decomposition and reactive oxygen species(ROS)’s formation on the catalyst’s surface is always a critical issue for the environmental applicati...To better understand the mechanisms of hydrogen peroxide(H_(2)O_(2))’s decomposition and reactive oxygen species(ROS)’s formation on the catalyst’s surface is always a critical issue for the environmental application of Fenton/Fenton-like reaction.We here report a new approach to activate H_(2)O_(2) in a co-catalytic Fenton system with oxygen incorporated MoS2,namely MoS_(2−x) O_(x) nanosheets.The MoS_(2−x) O_(x) nanosheets assisted co-catalytic Fenton system exhibited superior degradation activity of emerging antibiotic contaminants(e.g.,sulfamethoxazole).Combining density functional theory(DFT)calculation and experimental investigation,we demonstrated that oxygen incorporation could improve the intrinsic conductivity of MoS_(2−x) O_(x) nanosheets and accelerate surface/interfacial charge transfer,which further leads to the efficacious activation of H_(2)O_(2).Moreover,by tuning the oxygen proportion in MoS_(2−x) O_(x) nanosheets,we are able to modulate the generation of ROS and further direct the oriented-conversion of H_(2)O_(2) to surface-bounded superoxide radical(·O_(2−surface)).It sheds light on the generation and transformation of ROS in the engineered system(e.g.,Fenton,Fenton-like reaction)for efficient degradation of persistent pollutants.展开更多
基金the Shanghai Rising-Star Program(No.22QA1403900)the National Natural Science Foundation of China(No.71804106)the Noncarbon Energy Conversion and Utilization Institute under the Shanghai Class IV Peak Disciplinary Development Program.
文摘Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a single prediction model is hard to capture temporal features effectively, resulting in diminished predictionaccuracy. In this study, a hybrid deep learning framework that integrates attention mechanism, convolution neuralnetwork (CNN), improved chaotic particle swarm optimization (ICPSO), and long short-term memory (LSTM), isproposed for short-term household load forecasting. Firstly, the CNN model is employed to extract features fromthe original data, enhancing the quality of data features. Subsequently, the moving average method is used for datapreprocessing, followed by the application of the LSTM network to predict the processed data. Moreover, the ICPSOalgorithm is introduced to optimize the parameters of LSTM, aimed at boosting the model’s running speed andaccuracy. Finally, the attention mechanism is employed to optimize the output value of LSTM, effectively addressinginformation loss in LSTM induced by lengthy sequences and further elevating prediction accuracy. According tothe numerical analysis, the accuracy and effectiveness of the proposed hybrid model have been verified. It canexplore data features adeptly, achieving superior prediction accuracy compared to other forecasting methods forthe household load exhibiting significant fluctuations across different seasons.
基金the National Natural Science Foundation of China(Nos.42077293 and 22006088)Natural Science Foundation of Guangdong Province(Nos.2019A1515011692 and 2019QN01L797)+2 种基金Shenzhen Municipal Science and Technology Innovation Committee(Nos.JCYJ20190809181413713 and WDZC20200817103015002)Y.X.H.also thanks the financial support from Overseas Cooperation Research Fund of Tsinghua Shenzhen International Graduate School(Nos.HW2020002 and QD2021010N)This work was also supported by the China Postdoctoral Science Foundation(No.2019M66067).
文摘To better understand the mechanisms of hydrogen peroxide(H_(2)O_(2))’s decomposition and reactive oxygen species(ROS)’s formation on the catalyst’s surface is always a critical issue for the environmental application of Fenton/Fenton-like reaction.We here report a new approach to activate H_(2)O_(2) in a co-catalytic Fenton system with oxygen incorporated MoS2,namely MoS_(2−x) O_(x) nanosheets.The MoS_(2−x) O_(x) nanosheets assisted co-catalytic Fenton system exhibited superior degradation activity of emerging antibiotic contaminants(e.g.,sulfamethoxazole).Combining density functional theory(DFT)calculation and experimental investigation,we demonstrated that oxygen incorporation could improve the intrinsic conductivity of MoS_(2−x) O_(x) nanosheets and accelerate surface/interfacial charge transfer,which further leads to the efficacious activation of H_(2)O_(2).Moreover,by tuning the oxygen proportion in MoS_(2−x) O_(x) nanosheets,we are able to modulate the generation of ROS and further direct the oriented-conversion of H_(2)O_(2) to surface-bounded superoxide radical(·O_(2−surface)).It sheds light on the generation and transformation of ROS in the engineered system(e.g.,Fenton,Fenton-like reaction)for efficient degradation of persistent pollutants.
