Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand Forecasting

This work proposes a cascade model incorporating Long–Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP), which offers a more reliable model to forecast short-term (hourly) and medium horizon (week) water demand. The MLP model integrates the previously forecasted demand with exogenous variabl...

Full description

Saved in:
Bibliographic Details
Main Authors: Bruno Brentan, Ariele Zanfei, Martin Oberascher, Robert Sitzenfrei, Joaquin Izquierdo, Andrea Menapace
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/69/1/42
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342790237945856
author Bruno Brentan
Ariele Zanfei
Martin Oberascher
Robert Sitzenfrei
Joaquin Izquierdo
Andrea Menapace
author_facet Bruno Brentan
Ariele Zanfei
Martin Oberascher
Robert Sitzenfrei
Joaquin Izquierdo
Andrea Menapace
author_sort Bruno Brentan
collection DOAJ
description This work proposes a cascade model incorporating Long–Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP), which offers a more reliable model to forecast short-term (hourly) and medium horizon (week) water demand. The MLP model integrates the previously forecasted demand with exogenous variables, functioning as a filter to enhance the accuracy of the LSTM estimation. The LSTM model estimates, utilizing a univariate approach, the hourly forecasting of water demand for the entire available dataset and the minimum night flow. The algorithm considers various time series sizes for each DMA and predicts the water demand values for each hour throughout the week. Having forecasted all timesteps with the LSTM, a virtual online process can be implemented to enhance forecasting quality.
format Article
id doaj-art-d8cc8c244f0d4059bf44ee5459b3e0f3
institution Kabale University
issn 2673-4591
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-d8cc8c244f0d4059bf44ee5459b3e0f32025-08-20T03:43:15ZengMDPI AGEngineering Proceedings2673-45912024-09-016914210.3390/engproc2024069042Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand ForecastingBruno Brentan0Ariele Zanfei1Martin Oberascher2Robert Sitzenfrei3Joaquin Izquierdo4Andrea Menapace5Hydraulic Engineering and Water Resources Department, School of Engineering, Universidade Federal de Minas Gerais, Belo Horizonte 31270-901, BrazilAIAQUA S.r.l., Via Volta 13/A, Bolzano 39100, ItalyDepartment of Infrastructure Engineering, Universität Innsbruck, 6020 Innsbruck, AustriaDepartment of Infrastructure Engineering, Universität Innsbruck, 6020 Innsbruck, AustriaInstitute for Multidisciplinary Mathematics, Universitat Politécnica de Valéncia, Valencia 46022, SpainFaculty of Agricultural, Environmental and Food Sciences, Free University of Bozen-Bolzano, Bozen-Bolzano 39100, ItalyThis work proposes a cascade model incorporating Long–Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP), which offers a more reliable model to forecast short-term (hourly) and medium horizon (week) water demand. The MLP model integrates the previously forecasted demand with exogenous variables, functioning as a filter to enhance the accuracy of the LSTM estimation. The LSTM model estimates, utilizing a univariate approach, the hourly forecasting of water demand for the entire available dataset and the minimum night flow. The algorithm considers various time series sizes for each DMA and predicts the water demand values for each hour throughout the week. Having forecasted all timesteps with the LSTM, a virtual online process can be implemented to enhance forecasting quality.https://www.mdpi.com/2673-4591/69/1/42battle of water demand forecastinglong–short-term memorymulti-layer perceptron
spellingShingle Bruno Brentan
Ariele Zanfei
Martin Oberascher
Robert Sitzenfrei
Joaquin Izquierdo
Andrea Menapace
Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand Forecasting
Engineering Proceedings
battle of water demand forecasting
long–short-term memory
multi-layer perceptron
title Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand Forecasting
title_full Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand Forecasting
title_fullStr Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand Forecasting
title_full_unstemmed Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand Forecasting
title_short Cascade Machine Learning Approach Applied to Short-Term Medium Horizon Demand Forecasting
title_sort cascade machine learning approach applied to short term medium horizon demand forecasting
topic battle of water demand forecasting
long–short-term memory
multi-layer perceptron
url https://www.mdpi.com/2673-4591/69/1/42
work_keys_str_mv AT brunobrentan cascademachinelearningapproachappliedtoshorttermmediumhorizondemandforecasting
AT arielezanfei cascademachinelearningapproachappliedtoshorttermmediumhorizondemandforecasting
AT martinoberascher cascademachinelearningapproachappliedtoshorttermmediumhorizondemandforecasting
AT robertsitzenfrei cascademachinelearningapproachappliedtoshorttermmediumhorizondemandforecasting
AT joaquinizquierdo cascademachinelearningapproachappliedtoshorttermmediumhorizondemandforecasting
AT andreamenapace cascademachinelearningapproachappliedtoshorttermmediumhorizondemandforecasting