Show simple item record

dc.contributor.authorJorge Caiado
dc.date.accessioned2017-05-08T21:48:41Z
dc.date.available2017-05-08T21:48:41Z
dc.date.copyrightMarch 2010
dc.date.issued2010
dc.identifier.other%28asce%29he%2E1943-5584%2E0000203.pdf
dc.identifier.urihttp://yetl.yabesh.ir/yetl/handle/yetl/63051
dc.description.abstractThis paper examines the daily water demand forecasting performance of double seasonal univariate time series models (Holt-Winters, ARIMA, and GARCH) based on multistep ahead forecast mean squared errors. A within-week seasonal cycle and a within-year seasonal cycle are accommodated in the various model specifications to capture both seasonalities. The study investigates whether combining forecasts from different methods could improve forecast accuracy. The results suggest that the combined forecasts perform quite well, especially for short-term forecasting. On the other hand, the individual forecasts from Holt-Winters exponential smoothing and GARCH models can improve forecast accuracy on specific days of the week.
dc.publisherAmerican Society of Civil Engineers
dc.titlePerformance of Combined Double Seasonal Univariate Time Series Models for Forecasting Water Demand
dc.typeJournal Paper
dc.journal.volume15
dc.journal.issue3
dc.journal.titleJournal of Hydrologic Engineering
dc.identifier.doi10.1061/(ASCE)HE.1943-5584.0000182
dc.treeJournal of Hydrologic Engineering:;2010:;Volume ( 015 ):;issue: 003
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record