Page - 352 - in Short-Term Load Forecasting by Artificial Intelligent Technologies

Energies2018,11, 1282 5.Conclusions With the development of society and technology, research to improve the precision of load forecasting has becomenecessary because short-termpower load forecasting can be regarded as avital componentof smart grids that cannotonly reduceelectricpower costs but also ensure the continuousflowofelectricitysupply. Thispaperselected22original indexesastheinfluential factorsof power loadandfactoranalysiswasemployedtodiscuss their correlationandeconomicconnotations, fromwhich it can be seen that the historical data occupied the largest contribution rate and the meteorological factor followedthereafter. Consequently, thepaper introducedtheautocorrelationand partialautocorrelationfunction to furtherexplore therelationshipbetweenhistorical loadandcurrent load.Consideringthe influenceofsimilarday,antcolonyclusteringwasadoptedtocluster thesample for the sakeof searching thedayswith analogous features. Finally, the extreme learningmachine optimizedbyabatalgorithmwasconductedtopredict thedays thatarechosento test. Thesimulation experimentcarriedout inYangquanCity inChinaverifiedtheeffectivenessandapplicabilityof the proposedmodel,andacomparisonwithbenchmarkmodels illustratedthesuperiorityof thenovel hybridmodelsuccessfully. AuthorContributions:W.S.conceivedanddesignedthispaper.C.Z.wrote thispaper. Conflictsof Interest:Theauthorsdeclarenoconflictof interest. References 1. Hernandez,L.;Baladron,C.;Aguiar, J.M.;Carro,B.;Sanchez-Esguevillas,A.J.;Lloret, J.;Massana, J.ASurvey onElectricPowerDemandForecasting: FutureTrends inSmartGrids,Microgrids andSmartBuildings. IEEECommun. Surv. Tutor. 2014,16, 1460–1495. [CrossRef] 2. Lv,Z.J.Applicationof regressionanalysis inpower loadforecasting.HebeiElectr. Power1987,1, 17–23. 3. Li,P.O.;Li,M.;Liu,D.C.Power loadforecastingbasedonimprovedregression.PowerSyst. Technol. 2006,30, 99–104. 4. Li,X.;Zhang,L.;Yao,S.;Huang,R.;Liu,S.;Lv,Q.;Zhang,L.ANewAlgorithmforPowerLoadForecasting BasedonTimeSeries.PowerSyst. Technol. 2006,31, 595–599. 5. Metaxiotis,K.;Kagiannas,A.Artificial intelligence inshort termelectric loadforecasting:Astate-of-the-art surveyfor theresearcher.EnergyConvers.Manag. 2003,44, 1525–1534. [CrossRef] 6. Hippert,H.S.;Pedreira,C.E.; Souza,R.C.NeuralNetworks forShort-TermLoadForecasting:AReviewand Evaluation. IEEETrans. PowerSyst. 2001,16, 44–55. [CrossRef] 7. Park,D.C.;El-Sharkawi,M.A.;Marks,R.J.;Atlas,L.E.;Damborg,M.J.ElectricLoadForecastingUsingan ArtificialNetwork. IEEETrans. PowerSyst. 1991,6, 422–449. [CrossRef] 8. Hernandez,L.;Baladrón,C.;Aguiar, J.M.;Carro,B.;Sanchez-Esguevillas,A.J.;Lloret, J. Short-TermLoad ForecastingforMicrogridsBasedonArtificialNeuralNetworks.Energies2013,6, 1385–1408. [CrossRef] 9. Yu,F.;Xu,X.Ashort-termloadforecastingmodelofnaturalgasbasedonoptimizedgeneticalgorithmand improvedBPneuralnetwork.Appl. Energy2014,134, 102–113. [CrossRef] 10. Hu,R.;Wen,S.;Zeng,Z.;Huang,T.Ashort-termpower loadforecastingmodelbasedonthegeneralized regressionneuralnetworkwithdecreasingstepfruitflyoptimizationalgorithm.Neurocomputing2017,221, 24–31. [CrossRef] 11. Li,Y.C.;Fang,T.J.;Yu,E.K.Studyonshort—Termloadforecastingusingsupportvectormachine.Proc. CSEE 2003,23, 55–59. 12. Zhao,D.F.;Wang,M.Short—Termloadforecastingbasedonsupportvectormachine.Proc. CSEE2002,22, 26–30. 13. Mesbah,M.;Soroush,E.;Azari,V.;Lee,M.;Bahadori,A.;Habibnia,S.Vapor liquidequilibriumprediction ofcarbondioxideandhydrocarbonsystemsusingLSSVMalgorithm. J.Supercrit. Fluids2015,97, 256–267. [CrossRef] 14. Huang,G.B.;Zhu,Q.Y.; Siew,C.K.Extreme learningmachine: Theoryandapplications.Neurocomputing 2006,70, 489–501. [CrossRef] 352