Optimizing Time Series Models for Water Demand Forecasting

This study focuses on optimizing time series forecasting models for water demand in a North Italian city as part of the Battle of the Water Demand Forecast (BWDF) challenge. It aims to accurately predict water demands across ten district-metered areas (DMAs) using historical data and weather informa...

Full description

Saved in:
Bibliographic Details
Main Authors: Gal Perelman, Yaniv Romano, Avi Ostfeld
Format: Article
Language:English
Published: MDPI AG 2024-08-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/69/1/9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850089705760096256
author Gal Perelman
Yaniv Romano
Avi Ostfeld
author_facet Gal Perelman
Yaniv Romano
Avi Ostfeld
author_sort Gal Perelman
collection DOAJ
description This study focuses on optimizing time series forecasting models for water demand in a North Italian city as part of the Battle of the Water Demand Forecast (BWDF) challenge. It aims to accurately predict water demands across ten district-metered areas (DMAs) using historical data and weather information over a one-week horizon. The methodology encompasses data preprocessing, including missing data imputation, feature engineering, and novel normalization techniques, followed by the development and hyperparameter optimization of various data-driven models such as random forest, XGB, LSTM, and Prophet. Extensive cross-validation tests assess each model’s performance, revealing that our refined approach markedly enhances forecast accuracy, demonstrating the importance of model and parameter selection for effective water demand forecasting.
format Article
id doaj-art-4e99328d5ea74375953d1b9afadfc3ad
institution DOAJ
issn 2673-4591
language English
publishDate 2024-08-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-4e99328d5ea74375953d1b9afadfc3ad2025-08-20T02:42:42ZengMDPI AGEngineering Proceedings2673-45912024-08-01691910.3390/engproc2024069009Optimizing Time Series Models for Water Demand ForecastingGal Perelman0Yaniv Romano1Avi Ostfeld2Faculty of Civil and Environmental Engineering, Technion—Israel Institute of Technology, Haifa 32000, IsraelFaculty of Electrical Engineering and Computer Science, Technion—Israel Institute of Technology, Haifa 32000, IsraelFaculty of Civil and Environmental Engineering, Technion—Israel Institute of Technology, Haifa 32000, IsraelThis study focuses on optimizing time series forecasting models for water demand in a North Italian city as part of the Battle of the Water Demand Forecast (BWDF) challenge. It aims to accurately predict water demands across ten district-metered areas (DMAs) using historical data and weather information over a one-week horizon. The methodology encompasses data preprocessing, including missing data imputation, feature engineering, and novel normalization techniques, followed by the development and hyperparameter optimization of various data-driven models such as random forest, XGB, LSTM, and Prophet. Extensive cross-validation tests assess each model’s performance, revealing that our refined approach markedly enhances forecast accuracy, demonstrating the importance of model and parameter selection for effective water demand forecasting.https://www.mdpi.com/2673-4591/69/1/9time series forecastingwater demanddata-driven modelsdata normalization
spellingShingle Gal Perelman
Yaniv Romano
Avi Ostfeld
Optimizing Time Series Models for Water Demand Forecasting
Engineering Proceedings
time series forecasting
water demand
data-driven models
data normalization
title Optimizing Time Series Models for Water Demand Forecasting
title_full Optimizing Time Series Models for Water Demand Forecasting
title_fullStr Optimizing Time Series Models for Water Demand Forecasting
title_full_unstemmed Optimizing Time Series Models for Water Demand Forecasting
title_short Optimizing Time Series Models for Water Demand Forecasting
title_sort optimizing time series models for water demand forecasting
topic time series forecasting
water demand
data-driven models
data normalization
url https://www.mdpi.com/2673-4591/69/1/9
work_keys_str_mv AT galperelman optimizingtimeseriesmodelsforwaterdemandforecasting
AT yanivromano optimizingtimeseriesmodelsforwaterdemandforecasting
AT aviostfeld optimizingtimeseriesmodelsforwaterdemandforecasting