An empirical investigation of Water Consumption Forecasting methods

Panagiotis I. Karamaziotis; Achilleas  Raptis; Konstantinos Nikolopoulos; Konstantina Litsiou; Vassilis Assimakopoulos

doi:10.1016/j.ijforecast.2019.07.009

An empirical investigation of Water Consumption Forecasting methods

Panagiotis I. Karamaziotis, Achilleas Raptis, Konstantinos Nikolopoulos, Konstantina Litsiou, Vassilis Assimakopoulos

Bangor Business School

Research output: Contribution to journal › Article › peer-review

282 Downloads (Pure)

Abstract

Many regions on earth everyday face limitations in the quantity and quality of available water resources. To that end, it is necessary to implement reliable methodologies for water consumption forecasting, that will lead to better management and planning of water resources. In this research, we analyse a first-time used large database containing data from 2 million water meters in 274 unique postal codes, in one of the most densely populated areas in Europe, which faces instances of droughts and overconsumption in hot summer
months. With the assistance of R programming language, we built and tested three alternative forecasting methodologies, employing univariate forecasting techniques including a machine-learning algorithm, with very promising results

Original language	English
Pages (from-to)	588-606
Journal	International Journal of Forecasting
Volume	36
Issue number	2
Early online date	21 Nov 2019
DOIs	https://doi.org/10.1016/j.ijforecast.2019.07.009
Publication status	Published - Jun 2020

Access to Document

10.1016/j.ijforecast.2019.07.009

2019 Water ConsumptionAccepted author manuscript, 1.25 MBLicence: CC BY-NC-ND

Cite this

@article{c0521ebbd026447b8de32a9d406e1204,

title = "An empirical investigation of Water Consumption Forecasting methods",

abstract = "Many regions on earth everyday face limitations in the quantity and quality of available water resources. To that end, it is necessary to implement reliable methodologies for water consumption forecasting, that will lead to better management and planning of water resources. In this research, we analyse a first-time used large database containing data from 2 million water meters in 274 unique postal codes, in one of the most densely populated areas in Europe, which faces instances of droughts and overconsumption in hot summer months. With the assistance of R programming language, we built and tested three alternative forecasting methodologies, employing univariate forecasting techniques including a machine-learning algorithm, with very promising results",

author = "Karamaziotis, {Panagiotis I.} and Achilleas Raptis and Konstantinos Nikolopoulos and Konstantina Litsiou and Vassilis Assimakopoulos",

year = "2020",

month = jun,

doi = "10.1016/j.ijforecast.2019.07.009",

language = "English",

volume = "36",

pages = "588--606",

journal = "International Journal of Forecasting",

issn = "0169-2070",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - An empirical investigation of Water Consumption Forecasting methods

AU - Karamaziotis, Panagiotis I.

AU - Raptis, Achilleas

AU - Nikolopoulos, Konstantinos

AU - Litsiou, Konstantina

AU - Assimakopoulos, Vassilis

PY - 2020/6

Y1 - 2020/6

N2 - Many regions on earth everyday face limitations in the quantity and quality of available water resources. To that end, it is necessary to implement reliable methodologies for water consumption forecasting, that will lead to better management and planning of water resources. In this research, we analyse a first-time used large database containing data from 2 million water meters in 274 unique postal codes, in one of the most densely populated areas in Europe, which faces instances of droughts and overconsumption in hot summer months. With the assistance of R programming language, we built and tested three alternative forecasting methodologies, employing univariate forecasting techniques including a machine-learning algorithm, with very promising results

AB - Many regions on earth everyday face limitations in the quantity and quality of available water resources. To that end, it is necessary to implement reliable methodologies for water consumption forecasting, that will lead to better management and planning of water resources. In this research, we analyse a first-time used large database containing data from 2 million water meters in 274 unique postal codes, in one of the most densely populated areas in Europe, which faces instances of droughts and overconsumption in hot summer months. With the assistance of R programming language, we built and tested three alternative forecasting methodologies, employing univariate forecasting techniques including a machine-learning algorithm, with very promising results

U2 - 10.1016/j.ijforecast.2019.07.009

DO - 10.1016/j.ijforecast.2019.07.009

M3 - Article

SN - 0169-2070

VL - 36

SP - 588

EP - 606

JO - International Journal of Forecasting

JF - International Journal of Forecasting

IS - 2

ER -

An empirical investigation of Water Consumption Forecasting methods

Abstract

Access to Document

Fingerprint

Cite this