基于动态组合残差修正的预测方法
|
摘要
本文建立了一种基于残差修正的组合预测方法,并基于该方法证明了针对多个单一的预测方法根据其在某个时间段的相对预测误差的大小选择组合选项可以进一步提高预测精度.提出了针对不同时间段可根据各种单项预测模型的相对预测误差的大小动态选取相对预测误差最小的两种模型构成组合残差来修正基本方法的预测误差,以提高预测精度.最后通过实际空调负荷预测对其进行了验证,结果表明这种动态组合残差修正的预测方法相对于基于多个固定单一预测方法的组合预测方法,可以进一步改善预测效果.
In order to further improve the accuracy, a forecasting method with combined residual error correction is used in this paper. Based on the forecasting method, the residual error correction model and its combination ways are analyzed among some single forecasting methods, and the very high accuracy of the combination method with two minimum relative prediction errors is proven within a certain period.And then one forecasting method with dynamical combined residual error correction is proposed, based on choosing two minimum relative prediction errors to form the correction model during different periods. A study case indicates that the combination ways proposed in this paper can further improve the accuracy of combination forecast.
In order to further improve the accuracy, a forecasting method with combined residual error correction is used in this paper. Based on the forecasting method, the residual error correction model and its combination ways are analyzed among some single forecasting methods, and the very high accuracy of the combination method with two minimum relative prediction errors is proven within a certain period.And then one forecasting method with dynamical combined residual error correction is proposed, based on choosing two minimum relative prediction errors to form the correction model during different periods. A study case indicates that the combination ways proposed in this paper can further improve the accuracy of combination forecast.
引文
[1]Tsai S B.Using grey models for forecasting China's growth trends in renewable energy consumption[J].Clean Technologies and Environmental Policy,2016,18(2):563-571.
[2]Feng S J,Ma Y D,Song Z L,et al.Forecasting the energy consumption of China by the grey prediction model[J].Energy Sources,Part B:Economics,Planning and Policy,2012,7(4):376-389.
[3]Lee Y C,Wu C H,Tsai S B.Grey system theory and fuzzy time series forecasting for the growth of green electronic materials[J].International Journal of Production Research,2014,52(10):2931-2945.
[4]Mokarram M.Modeling of multiple regression and multiple linear regressions for prediction of groundwater quality(case study:north of Shiraz)[J].Modeling Earth Systems and Environment,2016,2(3):1-7.
[5]Keshavarzi A,Sarmadian F.Comparison of artificial neural network and multivariate regression methods in prediction of soil cation exchange capacity(case study:Ziaran region)[J].Desert,2010,15:167-174.
[6]Paulo C,Miguel R,Jose N.Evolving time series forecasting ARMA models[J].Journal of Heuristics,2004,10:415-429.
[7]Abner C R N,Cicero A M,Mauro R.Comparative study on local and global strategies for confidence estimation in neural networks and extensions to improve their predictive power[J].Neural Computing and Applications,2013,22(7):1519-1530.
[8]Khosravi A,Nahavandi S,Creighton D.Comprehensive review of neural network-based prediction intervals and new advances[J].IEEE Transactions on Neural Networks,2011,22(9):1341-1356.
[9]Khosravi A,Nahavandi S,Creighton D.Lower upper bound estimation method for construction of neural networkbased prediction intervals[J].IEEE Transactions on Neural Networks,2011,22(3):337-346.
[10]Amrita K,Suchandan K D,Prem K S.Estimation of scale deposition in the water walls of an operating indian coal fired boiler:Predictive modeling approach using artificial neural networks[J].Journal of the Institution of Engineers(India):Series D,2016,97(1):39-46.
[11]Lu T,Viljanen M.Prediction of indoor temperature and relative humidity using neural network models:Model comparison[J].Neural Computing&Applications,2009,18:345-357.
[12]Rapach D E,Strauss J K.Forecasting U.S.employment growth using forecast combining methods[J].J Forecast,2008,27:75-93.
[13]朱大奇,史慧.神经网络原理及应用网.北京:科学出版社,2013.Zhu D Q,Shi H.The theory and application of neural network[M].Beijing:Science Press,2013.
[14]唐小我.组合预测方法研究的若干新成果[J].预测,1992,11(5):39-46.Tang X W.Some new results of combination forecasting study[J].Forecasting,1992,11(5):39-46.
[15]王景,刘良栋,王作义.组合预测方法的现状和发展[J].预测,1997,16(6):37-38.Wang J,Liu L D,Wang Z Y.The status and development of combination forecasting study[J].Forecasting,1997,16(6):37-38.
[16]Chert G J,Li K K,Chung T S.Application of all innovative combined forecasting method in power system load forecasting[J].Electric Power Systems Research,2001,59(2):131-137.
[17]Shen J C,Chang C H,Wu S J.Real-time correction of water stage forecast using combination of forecasted errors by time series models and Kalman filter method[J].Stochastic Environmental Research and Risk Assessment,2015,29(7):1903-1920.
[18]姚晔.集中空调系统状态空间建模及稳态优化节能控制研究[D].上海:上海交通大学,2005.Yao Y.State-space models of central air-conditioning system and stably optimal control for energy saving[D].Shanghai:Shanghai Jiongtong University,2005.
[19]Yao Y,Lian Z W.An innovative air-conditioning load forecasting model based on RBF neural network and combined residual error correction[J].International Journal of Refrigeration,2006,29:528-538.
[2]Feng S J,Ma Y D,Song Z L,et al.Forecasting the energy consumption of China by the grey prediction model[J].Energy Sources,Part B:Economics,Planning and Policy,2012,7(4):376-389.
[3]Lee Y C,Wu C H,Tsai S B.Grey system theory and fuzzy time series forecasting for the growth of green electronic materials[J].International Journal of Production Research,2014,52(10):2931-2945.
[4]Mokarram M.Modeling of multiple regression and multiple linear regressions for prediction of groundwater quality(case study:north of Shiraz)[J].Modeling Earth Systems and Environment,2016,2(3):1-7.
[5]Keshavarzi A,Sarmadian F.Comparison of artificial neural network and multivariate regression methods in prediction of soil cation exchange capacity(case study:Ziaran region)[J].Desert,2010,15:167-174.
[6]Paulo C,Miguel R,Jose N.Evolving time series forecasting ARMA models[J].Journal of Heuristics,2004,10:415-429.
[7]Abner C R N,Cicero A M,Mauro R.Comparative study on local and global strategies for confidence estimation in neural networks and extensions to improve their predictive power[J].Neural Computing and Applications,2013,22(7):1519-1530.
[8]Khosravi A,Nahavandi S,Creighton D.Comprehensive review of neural network-based prediction intervals and new advances[J].IEEE Transactions on Neural Networks,2011,22(9):1341-1356.
[9]Khosravi A,Nahavandi S,Creighton D.Lower upper bound estimation method for construction of neural networkbased prediction intervals[J].IEEE Transactions on Neural Networks,2011,22(3):337-346.
[10]Amrita K,Suchandan K D,Prem K S.Estimation of scale deposition in the water walls of an operating indian coal fired boiler:Predictive modeling approach using artificial neural networks[J].Journal of the Institution of Engineers(India):Series D,2016,97(1):39-46.
[11]Lu T,Viljanen M.Prediction of indoor temperature and relative humidity using neural network models:Model comparison[J].Neural Computing&Applications,2009,18:345-357.
[12]Rapach D E,Strauss J K.Forecasting U.S.employment growth using forecast combining methods[J].J Forecast,2008,27:75-93.
[13]朱大奇,史慧.神经网络原理及应用网.北京:科学出版社,2013.Zhu D Q,Shi H.The theory and application of neural network[M].Beijing:Science Press,2013.
[14]唐小我.组合预测方法研究的若干新成果[J].预测,1992,11(5):39-46.Tang X W.Some new results of combination forecasting study[J].Forecasting,1992,11(5):39-46.
[15]王景,刘良栋,王作义.组合预测方法的现状和发展[J].预测,1997,16(6):37-38.Wang J,Liu L D,Wang Z Y.The status and development of combination forecasting study[J].Forecasting,1997,16(6):37-38.
[16]Chert G J,Li K K,Chung T S.Application of all innovative combined forecasting method in power system load forecasting[J].Electric Power Systems Research,2001,59(2):131-137.
[17]Shen J C,Chang C H,Wu S J.Real-time correction of water stage forecast using combination of forecasted errors by time series models and Kalman filter method[J].Stochastic Environmental Research and Risk Assessment,2015,29(7):1903-1920.
[18]姚晔.集中空调系统状态空间建模及稳态优化节能控制研究[D].上海:上海交通大学,2005.Yao Y.State-space models of central air-conditioning system and stably optimal control for energy saving[D].Shanghai:Shanghai Jiongtong University,2005.
[19]Yao Y,Lian Z W.An innovative air-conditioning load forecasting model based on RBF neural network and combined residual error correction[J].International Journal of Refrigeration,2006,29:528-538.