Improving the Quality of Prediction Intervals Through Optimal Aggregation

Neural networks (NNs) are an effective tool to model nonlinear systems. However, their forecasting performance significantly drops in the presence of process uncertainties and disturbances. NN-based prediction intervals (PIs) offer an alternative solution to appropriately quantify uncertainties and disturbances associated with point forecasts. In this paper, an NN ensemble procedure is proposed to construct quality PIs. A recently developed lower-upper bound estimation method is applied to develop NN-based PIs. Then, constructed PIs from the NN ensemble members are combined using a weighted averaging mechanism. Simulated annealing and a genetic algorithm are used to optimally adjust the weights for the aggregation mechanism. The proposed method is examined for three different case studies. Simulation results reveal that the proposed method improves the average PI quality of individual NNs by 22%, 18%, and 78% for the first, second, and third case studies, respectively. The simulation study also demonstrates that a 3%-4% improvement in the quality of PIs can be achieved using the proposed method compared to the simple averaging aggregation method.

[1]  Saeid Nahavandi,et al.  Constructing Optimal Prediction Intervals by Using Neural Networks and Bootstrap Method , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Ken Nagasaka,et al.  Multiobjective Intelligent Energy Management for a Microgrid , 2013, IEEE Transactions on Industrial Electronics.

[3]  Stefan Preitl,et al.  Fuzzy Control Systems With Reduced Parametric Sensitivity Based on Simulated Annealing , 2012, IEEE Transactions on Industrial Electronics.

[4]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[5]  Herbert Dawid,et al.  Adaptive Learning by Genetic Algorithms, Analytical Results and Applications to Economic Models, 2nd extended and revised edition , 1999 .

[6]  Saeid Nahavandi,et al.  Prediction interval-based modelling of polymerization reactor: A new modelling strategy for chemical reactors , 2014 .

[7]  Tom Heskes,et al.  Practical Confidence and Prediction Intervals , 1996, NIPS.

[8]  Amir F. Atiya,et al.  Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals , 2011, IEEE Transactions on Neural Networks.

[9]  Conor Teljeur,et al.  USING PREDICTION INTERVALS FROM RANDOM-EFFECTS META-ANALYSES IN AN ECONOMIC MODEL , 2014, International Journal of Technology Assessment in Health Care.

[10]  Radu-Emil Precup,et al.  Iterative Data-Driven Tuning of Controllers for Nonlinear Systems With Constraints , 2014, IEEE Transactions on Industrial Electronics.

[11]  M. Hussain,et al.  Optimization and control of polystyrene batch reactor using hybrid based model , 2012 .

[12]  Ronald G. Harley,et al.  Recurrent Neural Networks Trained With Backpropagation Through Time Algorithm to Estimate Nonlinear Load Harmonic Currents , 2008, IEEE Transactions on Industrial Electronics.

[13]  A. Weigend,et al.  Estimating the mean and variance of the target probability distribution , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[14]  Shengli Wu,et al.  Effective Neural Network Ensemble Approach for Improving Generalization Performance , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Wei Wang,et al.  Application of Neural Network Ensembles to Incident Detection , 2007, 2007 IEEE International Conference on Integration Technology.

[16]  Saeid Nahavandi,et al.  Optimizing the quality of bootstrap-based prediction intervals , 2011, The 2011 International Joint Conference on Neural Networks.

[17]  stefanfausser.  neural-network-ensembles-rl 1.0 , 2015 .

[18]  Fabiano A.N. Fernandes,et al.  Neural network applications in polymerization processes , 2005 .

[19]  Mohd Azlan Hussain,et al.  Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation , 2011 .

[20]  Z. Zeybek,et al.  Generalized delta rule (GDR) algorithm with generalized predictive control (GPC) for optimum temperature tracking of batch polymerization , 2006 .

[21]  Xin Yao,et al.  Evolving artificial neural network ensembles , 2008, IEEE Computational Intelligence Magazine.

[22]  Stephen F. Witt,et al.  An Empirical Study of Forecast Combination in Tourism , 2009 .

[23]  James W. Taylor,et al.  Using combined forecasts with changing weights for electricity demand profiling , 2000, J. Oper. Res. Soc..

[24]  Dewei Li,et al.  Convergence Analysis and Digital Implementation of a Discrete-Time Neural Network for Model Predictive Control , 2014, IEEE Transactions on Industrial Electronics.

[25]  Saeid Nahavandi,et al.  Performance analysis of three advanced controllers for polymerization batch reactor: An experimental investigation , 2014 .

[26]  Bruce E. Hansen,et al.  Least-squares forecast averaging , 2008 .

[27]  Chia-Feng Juang,et al.  A Self-Evolving Interval Type-2 Fuzzy Neural Network With Online Structure and Parameter Learning , 2008, IEEE Transactions on Fuzzy Systems.

[28]  Evaristo Chalbaud Biscaia,et al.  Genetic algorithm development for multi-objective optimization of batch free-radical polymerization reactors , 2003, Comput. Chem. Eng..

[29]  Saeid Nahavandi,et al.  Combined Nonparametric Prediction Intervals for Wind Power Generation , 2013, IEEE Transactions on Sustainable Energy.

[30]  Todd E. Clark,et al.  Forecast Combination Across Estimation Windows , 2011 .

[31]  Saeid Nahavandi,et al.  Construction of Optimal Prediction Intervals for Load Forecasting Problems , 2010, IEEE Transactions on Power Systems.

[32]  Antony Browne,et al.  Neural network ensembles: combining multiple models for enhanced performance using a multistage approach , 2004, Expert Syst. J. Knowl. Eng..

[33]  K. Wallis,et al.  A Simple Explanation of the Forecast Combination Puzzle , 2009 .

[34]  Saeid Nahavandi,et al.  Evaluation and comparison of type reduction algorithms from a forecast accuracy perspective , 2013, 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[35]  Yongqian Liu,et al.  Neural Network Ensemble Method Study for Wind Power Prediction , 2011, 2011 Asia-Pacific Power and Energy Engineering Conference.

[36]  Abbas Khosravi,et al.  Uncertainty handling using neural network-based prediction intervals for electrical load forecasting , 2014 .

[37]  F. Mjalli,et al.  Hybrid modelling and kinetic estimation for polystyrene batch reactor using Artificial Neutral Network (ANN) approach , 2011 .

[38]  Francisco Cribari-Neto,et al.  Bootstrap prediction intervals in beta regressions , 2014, Comput. Stat..

[39]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  David W. Opitz,et al.  Actively Searching for an E(cid:11)ective Neural-Network Ensemble , 1996 .

[41]  J. T. Hwang,et al.  Prediction Intervals for Artificial Neural Networks , 1997 .

[42]  Saeid Nahavandi,et al.  Prediction interval-based neural network modelling of polystyrene polymerization reactor – A new perspective of data-based modelling , 2014 .

[43]  Mahmood Al-khassaweneh,et al.  Fault Diagnosis in Internal Combustion Engines Using Extension Neural Network , 2014, IEEE Transactions on Industrial Electronics.

[44]  Amir F. Atiya,et al.  Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances , 2011, IEEE Transactions on Neural Networks.

[45]  Ricardo Martinez-Botas,et al.  Electromagnetic Actuator Design Analysis Using a Two-Stage Optimization Method With Coarse–Fine Model Output Space Mapping , 2014, IEEE Transactions on Industrial Electronics.

[46]  Z. Dong,et al.  A Statistical Approach for Interval Forecasting of the Electricity Price , 2008, IEEE Transactions on Power Systems.