An Interval-Valued Neural Network Approach for Uncertainty Quantification in Short-Term Wind Speed Prediction
Authors:
- 26 February 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 26 (11) , 2787-2800
Abstract
We consider the task of performing prediction with neural networks (NNs) on the basis of uncertain input data expressed in the form of intervals. We aim at quantifying the uncertainty in the prediction arising from both the input data and the prediction model. A multilayer perceptron NN is trained to map interval-valued input data onto interval outputs, representing the prediction intervals (PIs) of the real target values. The NN training is performed by nondominated sorting genetic algorithm-II, so that the PIs are optimized both in terms of accuracy (coverage probability) and dimension (width). Demonstration of the proposed method is given in two case studies: 1) a synthetic case study, in which the data have been generated with a 5-min time frequency from an autoregressive moving average model with either Gaussian or Chi-squared innovation distribution and 2) a real case study, in which experimental data consist of wind speed measurements with a time step of 1 h. Comparisons are given with a crisp (single-valued) approach. The results show that the crisp approach is less reliable than the interval-valued input approach in terms of capturing the variability in input.Keywords
This publication has 39 references indexed in Scilit:
- Reliable prediction intervals with regression neural networksNeural Networks, 2011
- Uncertainties in smart grids behavior and modeling: What are the risks and vulnerabilities? How to analyze them?Energy Policy, 2011
- On the role of complete lattices in mathematical morphology: From tool to uncertainty modelInformation Sciences, 2011
- Comparison of bootstrapped artificial neural networks and quadratic response surfaces for the estimation of the functional failure probability of a thermal–hydraulic passive systemReliability Engineering & System Safety, 2010
- Forecasting models for interval-valued time seriesNeurocomputing, 2008
- Latin hypercube sampling and the propagation of uncertainty in analyses of complex systemsReliability Engineering & System Safety, 2003
- Interval type-2 fuzzy logic systems: theory and designIEEE Transactions on Fuzzy Systems, 2000
- Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approachIEEE Transactions on Evolutionary Computation, 1999
- Uncertainty and sensitivity analysis in the presence of stochastic and subjective uncertaintyJournal of Statistical Computation and Simulation, 1997
- Muiltiobjective Optimization Using Nondominated Sorting in Genetic AlgorithmsEvolutionary Computation, 1994