运输航空业减排节能规划目标控制研究
|
摘要
研究运输航空业减排节能目标控制问题。通过对运输航空业能源结构的分析,选择综合能耗作为减排节能规划目标,对其进行合理预测进而有效控制,来满足国家对企业能耗控制和用能决策的需要。运输航空业综合能耗历史数据具有非线性、非平稳等特点,而传统预测方法都是单纯的基于历史能耗数据的趋势外推,对数据的平滑性要求比较苛刻,并未考虑国民生产总值和在役机队架次等多种因素的影响,导致预测的准确性和精度不高。因此,针对上述问题构建了改进能源弹性系数和支持向量回归两种预测模型,从宏观趋势和具体因素两个角度,对其进行因果测算。仿真结果表明,预测模型的精度和准确性相对比较高,两种方法交叉检验后得到合理的减排节能规划目标。
The problem of emission reduction targets control in the aviation industry is studied.Through the analysis of the air transportation industry energy structure,comprehensive energy consumption is selected as the energy-saving emission reduction planning target.In order to meet the needs of national energy consumption control and make energy consumption decisions,the comprehensive energy consumption is predicted reasonably and controlled effectively.The comprehensive energy consumption's historical data of transportation aviation industry is nonlinear and non-stationary.The traditional prediction methods are based on historical data of energy consumption trend of simple,and the requirements on the smoothness of data are relatively harsh.The impact of GDP and in-service fleet vehicles and other factors are not considered.So the accuracy and precision of prediction is not high.Therefore,aiming at this problem,two kinds of prediction models based on the improved energy elasticity coefficient and the support vector regression were constructed.From two aspects of macro trends and specific factors,the comprehensive energy consumption was calculated.The simulation results show that the precision and accuracy of the prediction model are relatively high,and the two methods can be used to obtain a reasonable energy-saving emission reduction target after cross checked.
The problem of emission reduction targets control in the aviation industry is studied.Through the analysis of the air transportation industry energy structure,comprehensive energy consumption is selected as the energy-saving emission reduction planning target.In order to meet the needs of national energy consumption control and make energy consumption decisions,the comprehensive energy consumption is predicted reasonably and controlled effectively.The comprehensive energy consumption's historical data of transportation aviation industry is nonlinear and non-stationary.The traditional prediction methods are based on historical data of energy consumption trend of simple,and the requirements on the smoothness of data are relatively harsh.The impact of GDP and in-service fleet vehicles and other factors are not considered.So the accuracy and precision of prediction is not high.Therefore,aiming at this problem,two kinds of prediction models based on the improved energy elasticity coefficient and the support vector regression were constructed.From two aspects of macro trends and specific factors,the comprehensive energy consumption was calculated.The simulation results show that the precision and accuracy of the prediction model are relatively high,and the two methods can be used to obtain a reasonable energy-saving emission reduction target after cross checked.
引文
[1]马湘山.哥本哈根会议与中国民航应对气候变化谈判[J].中国民用航空,2010,109(1):27-29.
[2]Chen,Jingjie Zhu,Yujuan Hu,Xiaona.On forecast method of thirteenth five-year ESER planning goals for transport airlines[J].Proceedings of the 28th Chinese Control and Decision Conference,CCDC,August 3.2016:6818-6822.
[3]马湘山.民航碳排放交易市场前景探索[J].中国民用航空,2014,179(1):24-26.
[4]华贲.低碳时代的中国城市能源规划[J].建筑科学,2010,26(12):33-39.
[5]龙惟定.城区需求侧能源规划[J].暖通空调HV&AC,2015,45(2):60-66.
[6]陈焕真.基于灰色马尔可夫模型的青岛市粮食产量预测[J].计算机仿真,2013,30(5).
[7]张卫国,赵越红.改进灰色神经网络模型在形变预测中的应用[J].计算机仿真,2016,33(6).
[8]柴建,等.中国航空燃油消费分析及预测[J].管理评论,2016,28(1):11-21.
[9]宋召青,龙玉峰,王康.基于支持向量机的迟滞系统建模及性能研究[J].计算机仿真,2015,32(3).
[10]谢国强.基于支持向量回归机的股票价格预测[J].计算机仿真,2012,29(4):379-382.
[11]K J Kim.Financial Time Series Forecasting Using Support Vector Machines[J].Neural Computing,2003,55(3):307-319.
[12]N Y Deng,Y J Tian.A New Method of Data Mining-Support Vector Machine[M].Beijing:Science Press,2004.
[13]苏璟,谭忠富,严菲.能源消费弹性系数计算方法及其实例分析[J].中国能源,2008,30(8):26-29.
[14]董力通,等.基于SVM的“弹性系数-投入产出”电力需求预测分析模型[J].中南大学学报(自然科学版),2012,43(6):2441-2444.
[15]陈静杰,邹迎欢.油耗预测中显著影响参数提取方法的仿真[J].计算机仿真,2013,30(6).
[16]何运成,刘坤,沈笑云,周波.飞机燃油消耗估计模型仿真研究[J].计算机仿真,2015,32(5).
[17]李清毅,等.基于网格搜索和支持向量机的灰熔点预测[J].浙江大学学报,2011,45(12):2181-2187.
[18]Zia Wadud.Decomposing the drivers of aviation fuel demand using simultaneous equation models[J].Energy,2015,83:551-559.
[2]Chen,Jingjie Zhu,Yujuan Hu,Xiaona.On forecast method of thirteenth five-year ESER planning goals for transport airlines[J].Proceedings of the 28th Chinese Control and Decision Conference,CCDC,August 3.2016:6818-6822.
[3]马湘山.民航碳排放交易市场前景探索[J].中国民用航空,2014,179(1):24-26.
[4]华贲.低碳时代的中国城市能源规划[J].建筑科学,2010,26(12):33-39.
[5]龙惟定.城区需求侧能源规划[J].暖通空调HV&AC,2015,45(2):60-66.
[6]陈焕真.基于灰色马尔可夫模型的青岛市粮食产量预测[J].计算机仿真,2013,30(5).
[7]张卫国,赵越红.改进灰色神经网络模型在形变预测中的应用[J].计算机仿真,2016,33(6).
[8]柴建,等.中国航空燃油消费分析及预测[J].管理评论,2016,28(1):11-21.
[9]宋召青,龙玉峰,王康.基于支持向量机的迟滞系统建模及性能研究[J].计算机仿真,2015,32(3).
[10]谢国强.基于支持向量回归机的股票价格预测[J].计算机仿真,2012,29(4):379-382.
[11]K J Kim.Financial Time Series Forecasting Using Support Vector Machines[J].Neural Computing,2003,55(3):307-319.
[12]N Y Deng,Y J Tian.A New Method of Data Mining-Support Vector Machine[M].Beijing:Science Press,2004.
[13]苏璟,谭忠富,严菲.能源消费弹性系数计算方法及其实例分析[J].中国能源,2008,30(8):26-29.
[14]董力通,等.基于SVM的“弹性系数-投入产出”电力需求预测分析模型[J].中南大学学报(自然科学版),2012,43(6):2441-2444.
[15]陈静杰,邹迎欢.油耗预测中显著影响参数提取方法的仿真[J].计算机仿真,2013,30(6).
[16]何运成,刘坤,沈笑云,周波.飞机燃油消耗估计模型仿真研究[J].计算机仿真,2015,32(5).
[17]李清毅,等.基于网格搜索和支持向量机的灰熔点预测[J].浙江大学学报,2011,45(12):2181-2187.
[18]Zia Wadud.Decomposing the drivers of aviation fuel demand using simultaneous equation models[J].Energy,2015,83:551-559.