A fuzzy logic based approach to leakage forecasting in water industry

Lech Birek, Dobrila Petrovic, John Boylan

Research output: Contribution to conferencePaper

Abstract

Leakage and demand forecasting is a crucial part of the resource planning decision making in the UK water industry. OFWAT - the economic regulatory body - sets the annual leakage targets for 5 years in advance. However, the leakage is not constant throughout the year and depends on the leakage control policy applied, external factors and seasonal fluctuations. The leakage for each month of the year is forecasted and later adjusted every quarter as new data become available. In this paper, a new system is developed to help the expert in adjusting the leakage forecast based on the newly available data, as well as other factors used for leakage forecasting, such as Natural Rate of Rise (relates to the rate at which the leakage increases over time), efficiency measures (hours to detect the leakage) and the number of reported and detected leakages. Fuzzy clustering and a fuzzy interpolation method are applied to generate fuzzy if-then rules based on the recorded data. The fuzzy rules represent imprecise knowledge of the relationship between the above mentioned factors and leakages. The leakage forecast is then adjusted using the generated fuzzy rules. The proposed approach is verified using real-life data from one of the leading water supply companies in the UK
Original languageEnglish
Publication statusPublished - 2011
EventThe 31st Annual International Symposium on Forecasting - Prague, Czech Republic
Duration: 26 Jun 201129 Jun 2011

Conference

ConferenceThe 31st Annual International Symposium on Forecasting
CountryCzech Republic
CityPrague
Period26/06/1129/06/11

Fingerprint

Fuzzy rules
Fuzzy logic
Fuzzy clustering
Water supply
Water
Industry
Interpolation
Decision making
Planning
Economics

Bibliographical note

This paper was given at the 31st Annual International Symposium on Forecasting, June 26-29 2011, Prague. The paper is available at: http://www.forecasters.org/submissions/BirekLechISF2011.pdf

Keywords

  • leakage forecasting
  • c-means clustering
  • fuzzy logic
  • water industry

Cite this

Birek, L., Petrovic, D., & Boylan, J. (2011). A fuzzy logic based approach to leakage forecasting in water industry. Paper presented at The 31st Annual International Symposium on Forecasting, Prague, Czech Republic.

A fuzzy logic based approach to leakage forecasting in water industry. / Birek, Lech; Petrovic, Dobrila; Boylan, John.

2011. Paper presented at The 31st Annual International Symposium on Forecasting, Prague, Czech Republic.

Research output: Contribution to conferencePaper

Birek, L, Petrovic, D & Boylan, J 2011, 'A fuzzy logic based approach to leakage forecasting in water industry' Paper presented at The 31st Annual International Symposium on Forecasting, Prague, Czech Republic, 26/06/11 - 29/06/11, .
Birek L, Petrovic D, Boylan J. A fuzzy logic based approach to leakage forecasting in water industry. 2011. Paper presented at The 31st Annual International Symposium on Forecasting, Prague, Czech Republic.
Birek, Lech ; Petrovic, Dobrila ; Boylan, John. / A fuzzy logic based approach to leakage forecasting in water industry. Paper presented at The 31st Annual International Symposium on Forecasting, Prague, Czech Republic.
@conference{a458ba213c594284863c8488ca58c6f6,
title = "A fuzzy logic based approach to leakage forecasting in water industry",
abstract = "Leakage and demand forecasting is a crucial part of the resource planning decision making in the UK water industry. OFWAT - the economic regulatory body - sets the annual leakage targets for 5 years in advance. However, the leakage is not constant throughout the year and depends on the leakage control policy applied, external factors and seasonal fluctuations. The leakage for each month of the year is forecasted and later adjusted every quarter as new data become available. In this paper, a new system is developed to help the expert in adjusting the leakage forecast based on the newly available data, as well as other factors used for leakage forecasting, such as Natural Rate of Rise (relates to the rate at which the leakage increases over time), efficiency measures (hours to detect the leakage) and the number of reported and detected leakages. Fuzzy clustering and a fuzzy interpolation method are applied to generate fuzzy if-then rules based on the recorded data. The fuzzy rules represent imprecise knowledge of the relationship between the above mentioned factors and leakages. The leakage forecast is then adjusted using the generated fuzzy rules. The proposed approach is verified using real-life data from one of the leading water supply companies in the UK",
keywords = "leakage forecasting, c-means clustering, fuzzy logic, water industry",
author = "Lech Birek and Dobrila Petrovic and John Boylan",
note = "This paper was given at the 31st Annual International Symposium on Forecasting, June 26-29 2011, Prague. The paper is available at: http://www.forecasters.org/submissions/BirekLechISF2011.pdf; The 31st Annual International Symposium on Forecasting ; Conference date: 26-06-2011 Through 29-06-2011",
year = "2011",
language = "English",

}

TY - CONF

T1 - A fuzzy logic based approach to leakage forecasting in water industry

AU - Birek, Lech

AU - Petrovic, Dobrila

AU - Boylan, John

N1 - This paper was given at the 31st Annual International Symposium on Forecasting, June 26-29 2011, Prague. The paper is available at: http://www.forecasters.org/submissions/BirekLechISF2011.pdf

PY - 2011

Y1 - 2011

N2 - Leakage and demand forecasting is a crucial part of the resource planning decision making in the UK water industry. OFWAT - the economic regulatory body - sets the annual leakage targets for 5 years in advance. However, the leakage is not constant throughout the year and depends on the leakage control policy applied, external factors and seasonal fluctuations. The leakage for each month of the year is forecasted and later adjusted every quarter as new data become available. In this paper, a new system is developed to help the expert in adjusting the leakage forecast based on the newly available data, as well as other factors used for leakage forecasting, such as Natural Rate of Rise (relates to the rate at which the leakage increases over time), efficiency measures (hours to detect the leakage) and the number of reported and detected leakages. Fuzzy clustering and a fuzzy interpolation method are applied to generate fuzzy if-then rules based on the recorded data. The fuzzy rules represent imprecise knowledge of the relationship between the above mentioned factors and leakages. The leakage forecast is then adjusted using the generated fuzzy rules. The proposed approach is verified using real-life data from one of the leading water supply companies in the UK

AB - Leakage and demand forecasting is a crucial part of the resource planning decision making in the UK water industry. OFWAT - the economic regulatory body - sets the annual leakage targets for 5 years in advance. However, the leakage is not constant throughout the year and depends on the leakage control policy applied, external factors and seasonal fluctuations. The leakage for each month of the year is forecasted and later adjusted every quarter as new data become available. In this paper, a new system is developed to help the expert in adjusting the leakage forecast based on the newly available data, as well as other factors used for leakage forecasting, such as Natural Rate of Rise (relates to the rate at which the leakage increases over time), efficiency measures (hours to detect the leakage) and the number of reported and detected leakages. Fuzzy clustering and a fuzzy interpolation method are applied to generate fuzzy if-then rules based on the recorded data. The fuzzy rules represent imprecise knowledge of the relationship between the above mentioned factors and leakages. The leakage forecast is then adjusted using the generated fuzzy rules. The proposed approach is verified using real-life data from one of the leading water supply companies in the UK

KW - leakage forecasting

KW - c-means clustering

KW - fuzzy logic

KW - water industry

M3 - Paper

ER -