File(s) under permanent embargo
Weighted autocorrelation based prediction Interval optimization for wind power generation
conference contribution
posted on 2018-01-01, 00:00 authored by Hussain Mohammed Dipu Kabir, Anwar HosenAnwar Hosen, Abbas KhosraviAbbas Khosravi, Saeid NahavandiIn this paper, an optimization methodology for the weighted autocorrelation based prediction interval is proposed and applied for the prediction of the wind power generation. The Coverage Width Based Criterion (CWC) is applied as the optimization criterion. The improved execution steps are as follows- At first, the string of 20 recent samples is autocorrelated with the similar strings of previous samples. Then, the samples next to the highest normalized correlation values and corresponding indexes are selected. After that, the amplitudes of the matched samples are adjusted by multiplying the value with the amplitude of recent string and by dividing by the amplitude of matched strings. These amplitude-adjusted samples are the prediction value for the next sample. Each prediction values are given a weight depending on the ratio of the amplitude of the string and the value of normalized correlation. The weight equation is trained with the CWC equation to find the optimum relation between amplitude and correlation values. The probability density distribution is derived from the weighted autocorrelation values. Finally, least relevant areas from corners are discarded to achieve the required coverage with smaller PI width. However, as the level of uncertainty changes over time, discarding historical percentile may result in a different coverage on later targets. Therefore, the percentage of discarding is also optimized with the CWC. Wind power generation is predicted and different weight equation and discarding percentages are achieved.
History
Event
Neural Networks. Conference (2018 : Rio De Janeiro, Brazil)Pagination
1 - 6Publisher
IEEELocation
Rio De Janeiro, BrazilPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2018-07-08End date
2018-07-13eISSN
2161-4407ISBN-13
9781509060146Language
engPublication classification
E Conference publication; E1 Full written paper - refereedTitle of proceedings
IJCNN 2018: Proceedings of the International Joint Conference on Neural NetworksUsage metrics
Keywords
CorrelationBarsMathematical modelWind power generationArtificial neural networksPrediction algorithmsOptimizationScience & TechnologyTechnologyComputer Science, Artificial IntelligenceComputer Science, Hardware & ArchitectureEngineering, Electrical & ElectronicComputer ScienceEngineeringPrediction Interval (PI)AutocorrelationRegressionNeural Network (NN)ForecastPROPAGATIONFORECASTSNeural, Evolutionary and Fuzzy ComputationSimulation and Modelling
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC