Short-Term Load Forecasting by Artificial Intelligent Technologies Edited by Wei-Chiang Hong, Ming-Wei Li and Guo-Feng Fan Printed Edition of the Special Issue Published in Energies www.mdpi.com/journal/energies Short-Term Load Forecasting by Artificial Intelligent Technologies Short-Term Load Forecasting by Artificial Intelligent Technologies SpecialIssueEditors Wei-ChiangHong Ming-WeiLi Guo-FengFan MDPI•Basel•Beijing•Wuhan•Barcelona•Belgrade SpecialIssueEditors Wei-ChiangHong Ming-WeiLi Guo-FengFan JiangsuNormalUniversity HarbinEngineeringUniversity PingdingshanUniversity China China China EditorialOffice MDPI St.Alban-Anlage66 4052Basel,Switzerland ThisisareprintofarticlesfromtheSpecialIssuepublishedonlineintheopenaccessjournalEnergies (ISSN1996-1073)from2018to2019(availableat:https://www.mdpi.com/journal/energies/special issues/ShortTermLoadForecasting) Forcitationpurposes,citeeacharticleindependentlyasindicatedonthearticlepageonlineandas indicatedbelow: LastName,A.A.; LastName,B.B.; LastName,C.C.ArticleTitle. JournalNameYear,ArticleNumber, PageRange. ISBN978-3-03897-582-3(Pbk) ISBN978-3-03897-583-0(PDF) (cid:2)c 2019bytheauthors. ArticlesinthisbookareOpenAccessanddistributedundertheCreative Commons Attribution (CC BY) license, which allows users to download, copy and build upon publishedarticles,aslongastheauthorandpublisherareproperlycredited,whichensuresmaximum disseminationandawiderimpactofourpublications. ThebookasawholeisdistributedbyMDPIunderthetermsandconditionsoftheCreativeCommons licenseCCBY-NC-ND. Contents AbouttheSpecialIssueEditors . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii Prefaceto”Short-TermLoadForecastingbyArtificialIntelligentTechnologies”. . . . . . . . . ix Ming-WeiLi,JingGeng,Wei-ChiangHongandYangZhang HybridizingChaoticandQuantumMechanismsandFruitFlyOptimizationAlgorithmwith LeastSquaresSupportVectorRegressionModelinElectricLoadForecasting Reprintedfrom:Energies2018,11,2226,doi:10.3390/en11092226 . . . . . . . . . . . . . . . . . . . 1 YongquanDong,ZichenZhangandWei-ChiangHong AHybridSeasonalMechanismwithaChaoticCuckooSearchAlgorithmwithaSupportVector RegressionModelforElectricLoadForecasting Reprintedfrom:Energies2018,11,1009,doi:10.3390/en11041009 . . . . . . . . . . . . . . . . . . . 23 AshfaqAhmad,NadeemJavaid,AbdulMateen,MuhammadAwaisandZahoorAliKhan Short-TermLoadForecastinginSmartGrids:AnIntelligentModularApproach Reprintedfrom:Energies2019,12,164,doi:10.3390/en12010164. . . . . . . . . . . . . . . . . . . . 44 SeonHyeogKim,GyulLee,Gu-YoungKwon,Do-InKimandYong-JuneShin DeepLearningBasedonMulti-DecompositionforShort-TermLoadForecasting Reprintedfrom:Energies2018,11,3433,doi:10.3390/en11123433 . . . . . . . . . . . . . . . . . . . 65 Fu-ChengWangandKuang-MingLin Impacts of Load Profiles on the Optimization of Power Management of a Green Building EmployingFuelCells Reprintedfrom:Energies2019,12,57,doi:10.3390/en12010057 . . . . . . . . . . . . . . . . . . . . 82 HabeeburRahman,IniyanSelvarasanandJahithaBegumA Short-TermForecastingofTotalEnergyConsumptionforIndia-ABlackBoxBasedApproach Reprintedfrom:Energies2018,11,3442,doi:10.3390/en11123442 . . . . . . . . . . . . . . . . . . . 98 JihoonMoon,YongsungKim,MinjaeSonandEenjunHwang HybridShort-TermLoadForecastingSchemeUsingRandomForestandMultilayerPerceptron Reprintedfrom:Energies2018,11,3283,doi:10.3390/en11123283 . . . . . . . . . . . . . . . . . . . 119 MiguelLo´pez,CarlosSans,SergioValeroandCarolinaSenabre EmpiricalComparisonofNeuralNetworkandAuto-RegressiveModelsinShort-TermLoad Forecasting Reprintedfrom:Energies2018,11,2080,doi:10.3390/en11082080 . . . . . . . . . . . . . . . . . . . 139 Mar´ıadelCarmenRuiz-Abello´n,AntonioGabaldo´nandAntonioGuillamo´n LoadForecastingforaCampusUniversityUsingEnsembleMethodsBasedonRegressionTrees Reprintedfrom:Energies2018,11,2038,doi:10.3390/en11082038 . . . . . . . . . . . . . . . . . . . 158 GregoryD.Merkel,RichardJ.PovinelliandRonaldH.Brown Short-TermLoadForecastingofNaturalGaswithDeepNeuralNetworkRegression Reprintedfrom:Energies2018,11,2008,doi:10.3390/en11082008 . . . . . . . . . . . . . . . . . . . 180 Fu-ChengWang,Yi-ShaoHsiaoandYi-ZheYang TheOptimizationofHybridPowerSystemswithRenewableEnergyandHydrogenGeneration Reprintedfrom:Energies2018,11,1948,doi:10.3390/en11081948 . . . . . . . . . . . . . . . . . . . 192 v JingZhao,YaoqiDuanandXiaojuanLiu Uncertainty Analysis of Weather Forecast Data for Cooling Load Forecasting Based on the MonteCarloMethod Reprintedfrom:Energies2018,11,1900,doi:10.3390/en11071900 . . . . . . . . . . . . . . . . . . . 211 BenjaminAuder,JairoCugliari,YannigGoude,Jean-MichelPoggi ScalableClusteringofIndividualElectricalCurvesforProfilingandBottom-UpForecasting Reprintedfrom:Energies2018,11,1893,doi:10.3390/en11071893 . . . . . . . . . . . . . . . . . . . 229 MagnusDahl,AdamBrun,OliverS.KirsebomandGormB.Andresen ImprovingShort-TermHeatLoadForecastswithCalendarandHolidayData Reprintedfrom:Energies2018,11,1678,doi:10.3390/en11071678 . . . . . . . . . . . . . . . . . . . 251 MerganiA.Khairalla,XuNing,NashatT.AL-JalladandMusaabO.El-Faroug Short-TermForecastingforEnergyConsumptionthroughStackingHeterogeneousEnsemble LearningModel Reprintedfrom:Energies2018,11,1605,doi:10.3390/en11061605 . . . . . . . . . . . . . . . . . . . 267 JiyangWang,YuyangGaoandXuejunChen A Novel Hybrid Interval Prediction Approach Based on Modified Lower Upper Bound EstimationinCombinationwithMulti-ObjectiveSalpSwarmAlgorithmforShort-TermLoad Forecasting Reprintedfrom:Energies2018,11,1561,doi:10.3390/en11061561 . . . . . . . . . . . . . . . . . . . 288 XingZhang Short-TermLoadForecastingforElectricBusChargingStationsBasedonFuzzyClusteringand LeastSquaresSupportVectorMachineOptimizedbyWolfPackAlgorithm Reprintedfrom:Energies2018,11,1449,doi:10.3390/en11061449 . . . . . . . . . . . . . . . . . . . 318 WeiSunandChongchongZhang AHybridBA-ELMModelBasedonFactorAnalysisandSimilar-DayApproachforShort-Term LoadForecasting Reprintedfrom:Energies2018,11,1282,doi:10.3390/en11051282 . . . . . . . . . . . . . . . . . . . 336 YunyanLi,YuanshengHuangandMeimeiZhang Short-TermLoadForecastingforElectricVehicleChargingStationBasedonNicheImmunity LionAlgorithmandConvolutionalNeuralNetwork Reprintedfrom:Energies2018,11,1253,doi:10.3390/en11051253 . . . . . . . . . . . . . . . . . . . 354 YixingWang,MeiqinLiu,ZhejingBaoandSenlinZhang Short-Term Load Forecasting with Multi-Source Data Using Gated Recurrent Unit Neural Networks Reprintedfrom:Energies2018,11,1138,doi:10.3390/en11051138 . . . . . . . . . . . . . . . . . . . 372 ChengdongLi,ZixiangDing,JianqiangYi,YishengLvandGuiqingZhang DeepBeliefNetworkBasedHybridModelforBuildingEnergyConsumptionPrediction Reprintedfrom:Energies2018,11,242,doi:10.3390/en11010242. . . . . . . . . . . . . . . . . . . . 391 Ping-HuanKuoandChiou-JyeHuang AHighPrecisionArtificialNeuralNetworksModelforShort-TermEnergyLoadForecasting Reprintedfrom:Energies2018,11,213,doi:10.3390/en11010213. . . . . . . . . . . . . . . . . . . . 417 vi About the Special Issue Editors Wei-ChiangHong’sresearchinterestsmainlyincludecomputationalintelligence(neuralnetworks, evolutionarycomputation)andtheapplicationofforecastingtechnology(ARIMA,Supportvector regression,andChaostheory). In May 2012, one of his papers was named the “Top Cited Article 2007–2011” of Applied Mathematical Modelling, Elsevier Publisher. In Aug. 2014, he was nominated for the award “Outstanding Professor Award”, by Far Eastern Y. Z. Hsu Science and Technology Memorial Foundation (Taiwan). In Nov. 2014, he was nominated for the “Taiwan Inaugural Scopus Young ResearcherAward–ComputerScience”,byElsevierPublisher,inthePresidents’ForumofSoutheast andSouthAsiaandTaiwanUniversities. InJun. 2015, hewasnamedasoneofthe“Top10Best Reviewers”ofAppliedEnergyin2014. InAug. 2017,hewasnamedasoneofthe“BestReviewers” ofAppliedEnergyin2016. Ming-WeiLireceivedhisPh.D.degreeofengineeringfromDalianUniversityofTechnology,China, in2013.SinceSeptember2017,heisanassociateprofessorintheCollegeofShipbuildingEngineering ofHarbinEngineeringUniversity.HisresearchinterestsareIntelligentForecastingMethods,Hybrid EvolutionaryAlgorithm,IntelligentOceanandWaterConservancyEngineering,KeyTechnologies ofMarineRenewableEnergy. Guo-FengFanreceivedhisPh.D.degreeinEngineeringfromtheResearchCenterofMetallurgical Energy Conservation and Emission Reduction, Ministry of Education, Kunming University of Science and Technology, Kunming, in 2013. His research interests are ferrous metallurgy, energy forecasting, optimization, system identification. In Jan 2018, his paper was a “Top Cited Article” by Nuerocomputing, Elsevier Publisher. In Oct 2018, he won the title of Henan academic and technicalleader. vii Preface to ”Short-Term Load Forecasting by Artificial Intelligent Technologies” Inthelastfewdecades,short-termloadforecasting(STLF)hasbeenoneofthemostimportant researchissuesforachievinghigherefficiencyandreliabilityinpowersystemoperation,tofacilitate the minimization of its operation cost by providing accurate input to day-ahead scheduling, contingencyanalysis,loadflowanalysis,planning,andmaintenanceofpowersystem.Therearelots offorecastingmodelsproposedforSTLF,includingtraditionalstatisticalmodels(suchasARIMA, SARIMA,ARMAX,multi-variateregression,Kalmanfilter,exponentialsmoothing,andsoon)and artificial-intelligence-based models (such as artificial neural networks (ANNs), knowledge-based expertsystems,fuzzytheoryandfuzzyinferencesystems,evolutionarycomputationmodels,support vectorregression,andsoon).Recently,duetothegreatdevelopmentofevolutionaryalgorithms(EA), meta-heuristicalgorithms(MTA),andnovelcomputingconcepts(e.g.,quantumcomputingconcepts, chaoticmappingfunctions,andcloudmappingprocess,andsoon),manyadvancedhybridizations withthoseartificial-intelligence-basedmodelsarealsoproposedtoachievesatisfactoryforecasting accuracylevels. Inaddition, combiningsomesuperiormechanismswithanexistingmodelcould empower that model to solve problems it could not deal with before; for example, the seasonal mechanismfromARIMAmodelisagoodcomponenttobecombinedwithanyforecastingmodelsto helpthemtodealwithseasonalproblems. This book contains articles from the Special Issue titled “Short-Term Load Forecasting by ArtificialIntelligentTechnologies”,whichaimstoattractresearcherswithaninterestintheresearch areasdescribedabove. AsFanetal. [1]highlighted, theresearchtrendsofforecastingmodelsin theenergysectorinrecentdecadescouldbedividedintothreekindsofhybridorcombinedmodels: (1)hybridizingorcombiningtheartificialintelligentapproacheswitheachother;(2)hybridizingor combiningwithtraditionalstatisticalapproaches;and(3)hybridizingorcombiningwiththenovel evolutionary(ormeta-heuristic)algorithms.Thus,theSpecialIssue,inmethodologicalapplications, was also based on these three categories, i.e., hybridizing or combining any advanced/novel techniquesinenergyforecasting. Thehybridforecastingmodelsshouldhavesuperiorcapabilities overthetraditionalforecastingapproaches,andbeabletoovercomesomeinherentdrawbacks,and, eventually,toachievesignificantimprovementsinforecastingaccuracy. The22articlesinthiscompendiumalldisplayabroadrangeofcutting-edgetopicsofthehybrid advancedtechnologiesinSTLFfields. Theprefaceauthorsbelievethattheapplicationsofhybrid technologieswillplayamoreimportantroleinSTLFaccuracyimprovements,suchashybriddifferent evolutionary algorithms/models to overcome some critical shortcoming of a single evolutionary algorithm/modelortodirectlyimprovetheshortcomingsbytheoreticalinnovativearrangements. Based on these collected articles, an interesting (future research area) issue is how to guide researcherstoemployproperhybridtechnologyfordifferentdatasets.Thisisbecauseforanyanalysis models(includingclassificationmodels,forecastingmodels,andsoon),themostimportantproblem ishowtocatchthedatapattern,andtoapplythelearnedpatternsorrulestoachievesatisfactory performance,i.e.,thekeysuccessfactorishowtosuccessfullylookfordatapatterns.However,each modelexcelsincatchingdifferentspecificdatapatterns. Forexample,exponentialsmoothingand ARIMAmodelsfocusonstrictincreasing(ordecreasing)timeseriesdata,i.e.,linearpattern,though theyhaveaseasonalmodificationmechanismtoanalyzeseasonal(cyclic)change; duetoartificial learningfunctiontoadjustthesuitabletrainingrules,theANNmodelexcelsonlyifthehistoricaldata ix