TIME SERIESFORECASTINGWITHTRANSFORMER AND INFORMERMODELS

Konduri, Issac Babu

Please use this identifier to cite or link to this item: http://localhost:8081/jspui/handle/123456789/18851

Full metadata record

DC Field	Value	Language
dc.contributor.author	Konduri, Issac Babu	-
dc.date.accessioned	2026-02-05T06:58:54Z	-
dc.date.available	2026-02-05T06:58:54Z	-
dc.date.issued	2024-06	-
dc.identifier.uri	http://localhost:8081/jspui/handle/123456789/18851	-
dc.guide	Pillai, G.N.	en_US
dc.description.abstract	Timeseriesforecastingwiththehelpofadvancedmachinelearninganddeeplearn- ing models,specificallyTransformersandtheInformer,isappliedtothreediverse datasets fromtheMonashTimeSeriesRepository.Thepedestriancountsdatasetin- cludes hourlycountsofpedestriansinMelbournebeginninginMay2009,asrecorded by 66sensorsinthecity,withdataavailablethroughApril30,2020.Thesolarenergy dataset encompassessolarpowerproductionrecordsfrom137photovoltaicplantsin Alabama, sampledevery10minutesthroughout2006,capturinghigh-frequencyvari- ations insolarenergyoutput.Theelectricitydemanddatasetcontainsfivetimeseries corresponding tothehalf-hourlypowerconsumptionoffiveAustralianstates:South Australia, Queensland,Tasmania,Victoria,andNewSouthWales.Emphasizingtheim- portance ofaccurateforecasting,theresearchleveragestheTransformerandInformer model, designedforefficienthandlingoflong-sequencetimeseriesdata.Thestudy demonstrates substantialimprovementsinforecastingaccuracycomparedtotraditional models. Thesefindingshighlightthepotentialofadvanceddeeplearningmodelsto enhance decision-makingprocessesinenergyplanning,urbanmanagement,andinfras- tructure developmentbyprovidingreliableandcomprehensiveforecasts.	en_US
dc.language.iso	en	en_US
dc.publisher	IIT, Roorkee	en_US
dc.title	TIME SERIESFORECASTINGWITHTRANSFORMER AND INFORMERMODELS	en_US
dc.type	Dissertations	en_US
Appears in Collections:	MASTERS' THESES (MFSDS & AI)

Files in This Item:

File	Description	Size	Format
22565008_KONDURI ISSAC BABU.pdf		4.06 MB	Adobe PDF	View/Open

Show simple item record