The accurate prediction of photovoltaic(PV)power generation is an important basis for hybrid grid scheduling.With the expansion of the scale of PV power plants and the popularization of distributed PV,this study propo...The accurate prediction of photovoltaic(PV)power generation is an important basis for hybrid grid scheduling.With the expansion of the scale of PV power plants and the popularization of distributed PV,this study proposes a multilayer PV power generation prediction model based on transfer learning to solve the problems of the lack of data on new PV bases and the low accuracy of PV power generation prediction.The proposed model,called DRAM,concatenates a dilated convolutional neural network(DCNN)module with a bidirectional long short-term memory(BiLSTM)module,and integrates an attention mechanism.First,the processed data are input into the DCNN layer,and the dilation convolution mechanism captures the spatial features of the wide sensory field of the input data.Subsequently,the temporal characteristics between the features are extracted in the BiLSTM layer.Finally,an attention mechanism is used to strengthen the key features by assigning weights to efficiently construct the relationship between the features and output variables.In addition,the power prediction accuracy of the new PV sites was improved by transferring the pre-trained model parameters to the new PV site prediction model.In this study,the pre-training of models using data from different source domains and the correlations between these pre-trained models and the target domain were analyzed.展开更多
This study examines the effects of the inclusion of co-benefits on the potential capacity of advanced thermal plants with a linear programming model in the CDM （clean development mechanism） in India＇s power sector....This study examines the effects of the inclusion of co-benefits on the potential capacity of advanced thermal plants with a linear programming model in the CDM （clean development mechanism） in India＇s power sector. It investigates how different marginal damage costs of air pollutants affect the potential capacity of NGCC （natural gas combined cycle） and IGCC （integrated gasification combined cycle） by CDM projects with a scenario analysis. Three results are found from this analysis. First, IGCC and NGCC are installed at lower CER （certified emission reductions） prices when the marginal damage costs of air pollutants are added to the CER prices. Second, the CER prices of $1/tCO2 correspond with the sum of marginal damage costs of air pollutants of $150/t for NGCC and $30/t for IGCC in India＇s power sector. Thus, including the co-benefits into CDM attracts developing countries such as India where coal resource is redundant. Third, the SOx and NOx reduction benefits attained from the CDM projects become large in a grid where IGCC is installed.展开更多
This study examines the effects of nuclear phase-out and newly implemented FIT （feed-in tariff） at the TEPCO （Tokyo Electric Power Company） jurisdiction. A power generation mix linear programming model is develope...This study examines the effects of nuclear phase-out and newly implemented FIT （feed-in tariff） at the TEPCO （Tokyo Electric Power Company） jurisdiction. A power generation mix linear programming model is developed for the TEPCO jurisdiction up to 2030. Three results are found from this analysis. First, coal-fired power plants compensate for an abolishment of nuclear power generation when power mix is analyzed to maximum profits. Second, it is clarified that FIT provides competitiveness to wind power for potential and photovoltaics at the location where 15% of efficiency is expected at the TEPCO jurisdiction. Third, implementing FIT can decrease fossil-fuel dependency and CO2 emissions as much as planned nuclear power generation. However, system costs increase 4.61 trillion.展开更多
基金Science and Technology Project of State Grid Ningxia Electric Power Co.,Ltd Research on Distributed Photovoltaic Fine Power Prediction Technology for Day-Ahead Scheduling,5229NX230007.
文摘The accurate prediction of photovoltaic(PV)power generation is an important basis for hybrid grid scheduling.With the expansion of the scale of PV power plants and the popularization of distributed PV,this study proposes a multilayer PV power generation prediction model based on transfer learning to solve the problems of the lack of data on new PV bases and the low accuracy of PV power generation prediction.The proposed model,called DRAM,concatenates a dilated convolutional neural network(DCNN)module with a bidirectional long short-term memory(BiLSTM)module,and integrates an attention mechanism.First,the processed data are input into the DCNN layer,and the dilation convolution mechanism captures the spatial features of the wide sensory field of the input data.Subsequently,the temporal characteristics between the features are extracted in the BiLSTM layer.Finally,an attention mechanism is used to strengthen the key features by assigning weights to efficiently construct the relationship between the features and output variables.In addition,the power prediction accuracy of the new PV sites was improved by transferring the pre-trained model parameters to the new PV site prediction model.In this study,the pre-training of models using data from different source domains and the correlations between these pre-trained models and the target domain were analyzed.
文摘This study examines the effects of the inclusion of co-benefits on the potential capacity of advanced thermal plants with a linear programming model in the CDM （clean development mechanism） in India＇s power sector. It investigates how different marginal damage costs of air pollutants affect the potential capacity of NGCC （natural gas combined cycle） and IGCC （integrated gasification combined cycle） by CDM projects with a scenario analysis. Three results are found from this analysis. First, IGCC and NGCC are installed at lower CER （certified emission reductions） prices when the marginal damage costs of air pollutants are added to the CER prices. Second, the CER prices of $1/tCO2 correspond with the sum of marginal damage costs of air pollutants of $150/t for NGCC and $30/t for IGCC in India＇s power sector. Thus, including the co-benefits into CDM attracts developing countries such as India where coal resource is redundant. Third, the SOx and NOx reduction benefits attained from the CDM projects become large in a grid where IGCC is installed.
文摘This study examines the effects of nuclear phase-out and newly implemented FIT （feed-in tariff） at the TEPCO （Tokyo Electric Power Company） jurisdiction. A power generation mix linear programming model is developed for the TEPCO jurisdiction up to 2030. Three results are found from this analysis. First, coal-fired power plants compensate for an abolishment of nuclear power generation when power mix is analyzed to maximum profits. Second, it is clarified that FIT provides competitiveness to wind power for potential and photovoltaics at the location where 15% of efficiency is expected at the TEPCO jurisdiction. Third, implementing FIT can decrease fossil-fuel dependency and CO2 emissions as much as planned nuclear power generation. However, system costs increase 4.61 trillion.
