Based on the analysis of the grain supply and demand gap’s current situation in China, this paper establishes an indicator system for the influence factors of grain supply and demand gap. Then this paper calculates t...Based on the analysis of the grain supply and demand gap’s current situation in China, this paper establishes an indicator system for the influence factors of grain supply and demand gap. Then this paper calculates the correlation degree between the main grain varieties’ supply and demand gap and its influence factors. The results show that sown area and unit yield have the greatest impact on wheat supply and demand gap;per capita disposable income and unit yield have the greatest impact on corn supply and demand gap;per capita disposable income and agricultural mechanization level have the greatest impact on the supply and demand gap of soybean and rice. From the analysis results, we can obtain the difference between the factors affecting the grain supply and demand gap, and provide a certain theoretical basis and new ideas for the balance of grain supply and demand in China.展开更多
混合储能系统具有储能容量大、调节能力强等优点,有助于提高综合能源系统(integrated energy system,IES)的需求响应能力。首先,构建了一种电-氢-热混合储能系统(electric-hydrogen-thermal hybrid energy storage system,EHT-HESS),其...混合储能系统具有储能容量大、调节能力强等优点,有助于提高综合能源系统(integrated energy system,IES)的需求响应能力。首先,构建了一种电-氢-热混合储能系统(electric-hydrogen-thermal hybrid energy storage system,EHT-HESS),其中采用电解槽(electrolytic cell,EC)、蒸气重整反应(steam methane reforming,SMR)装置、储氢、热电联产氢燃料电池(hydrogen fuel cell,HFC)设备,实现电、气向氢能的转换,以及以氢能作为中间模态的“制氢-储氢-放氢/电/热”功能。其次,建立考虑EHT-HESS的IES需求响应策略优化模型,其中考虑IES响应电价和气价,同时根据富余风电量,进行购电、购气、用电、用热、用氢等策略决策的综合需求响应(integrated demand response,IDR)行为;并采用信息间隙决策理论(information gap decision theory,IGDT)计入概率分布未知的风电严重不确定性,采用基于综合范数的分布鲁棒优化(distributionally robust optimization,DRO)方法计入概率分布不完备的电价严重不确定性。最后,算例验证了模型和方法的合理性及有效性,并表明IES装设热电联产HFC构建EHT-HESS可实现氢能向电能与热能的转换,有助于增加风电消纳量,增加IDR决策的鲁棒性。展开更多
城市不同区域网约车供需缺口预测可为车辆调度策略提供支持,从而提高车辆运行效率和乘客服务水平.为实现网约车供需缺口短时预测,提出一种基于时空数据挖掘的深度学习预测模型(Spatio-Temporal Deep Learning Model, S-TDL).该模型由时...城市不同区域网约车供需缺口预测可为车辆调度策略提供支持,从而提高车辆运行效率和乘客服务水平.为实现网约车供需缺口短时预测,提出一种基于时空数据挖掘的深度学习预测模型(Spatio-Temporal Deep Learning Model, S-TDL).该模型由时空变量模型、空间属性变量模型和环境变量模型3个子模型融合而成,可捕捉时空关联性、区域差异性和环境变化对供需缺口的影响.同时,提出特征聚类—最大信息系数两阶段特征选择方法,筛选与供需缺口相关性强的特征变量,提高训练效率,减少过拟合.滴滴出行实例分析证明,特征选择后的STDL模型预测精度显著优于BP神经网络、长短期记忆网络和卷积神经网络.展开更多
文摘Based on the analysis of the grain supply and demand gap’s current situation in China, this paper establishes an indicator system for the influence factors of grain supply and demand gap. Then this paper calculates the correlation degree between the main grain varieties’ supply and demand gap and its influence factors. The results show that sown area and unit yield have the greatest impact on wheat supply and demand gap;per capita disposable income and unit yield have the greatest impact on corn supply and demand gap;per capita disposable income and agricultural mechanization level have the greatest impact on the supply and demand gap of soybean and rice. From the analysis results, we can obtain the difference between the factors affecting the grain supply and demand gap, and provide a certain theoretical basis and new ideas for the balance of grain supply and demand in China.
文摘城市不同区域网约车供需缺口预测可为车辆调度策略提供支持,从而提高车辆运行效率和乘客服务水平.为实现网约车供需缺口短时预测,提出一种基于时空数据挖掘的深度学习预测模型(Spatio-Temporal Deep Learning Model, S-TDL).该模型由时空变量模型、空间属性变量模型和环境变量模型3个子模型融合而成,可捕捉时空关联性、区域差异性和环境变化对供需缺口的影响.同时,提出特征聚类—最大信息系数两阶段特征选择方法,筛选与供需缺口相关性强的特征变量,提高训练效率,减少过拟合.滴滴出行实例分析证明,特征选择后的STDL模型预测精度显著优于BP神经网络、长短期记忆网络和卷积神经网络.
