Water leakage forecasting: The application of a modified fuzzy evolving algorithm

Lech Birek, Dobrila Petrovic, J. Boylan

Research output: Contribution to journalArticle

8 Citations (Scopus)
22 Downloads (Pure)

Abstract

This paper investigates the use of evolving fuzzy algorithms in forecasting. An evolving Takagi-Sugeno (eTS) algorithm, which is based on a recursive version of the subtractive algorithm is considered. It groups data into several clusters based on Euclidean distance between the relevant independent variables. The Mod eTS algorithm, which incorporates a modified dynamic update of cluster radii while accommodating new available data is proposed. The created clusters serve as a base for fuzzy If-Then rules with Gaussian membership functions which are defined using the cluster centres and have linear functions in the consequent i.e., Then parts of rules. The parameters of the linear functions are calculated using a weighted version of the Recursive Least Squares algorithm. The proposed algorithm is applied to a leakage forecasting problem faced by one of the leading UK water supplying companies. Using the real world data provided by the company the forecasting results obtained from the proposed modified eTS algorithm, Mod eTS, are compared to the standard eTS algorithm, exTS, eTS+ and fuzzy C-means clustering algorithm and some standard statistical forecasting methods. Different measures of forecasting accuracy are used. The results show higher accuracy achieved by applying the algorithm proposed compared to other fuzzy clustering algorithms and statistical methods. Similar results are obtained when comparing with other fuzzy evolving algorithms with dynamic cluster radii. Furthermore the algorithm generates typically a smaller number of clusters than standard fuzzy forecasting methods which leads to more transparent forecasting models.
Original languageEnglish
Pages (from-to)305-315
JournalApplied Soft Computing Journal
Volume14
Issue numberPART B
Early online date10 Jun 2013
DOIs
Publication statusPublished - Jan 2014

Fingerprint

Water
Clustering algorithms
Fuzzy clustering
Membership functions
Industry
Statistical methods

Bibliographical note

The full text of this item is not available from the repository.

Keywords

  • fuzzy algorithms
  • forecasting

Cite this

Water leakage forecasting: The application of a modified fuzzy evolving algorithm. / Birek, Lech; Petrovic, Dobrila; Boylan, J.

In: Applied Soft Computing Journal, Vol. 14, No. PART B, 01.2014, p. 305-315.

Research output: Contribution to journalArticle

@article{1b80ec5d9d2447909f9788d3197e847e,
title = "Water leakage forecasting: The application of a modified fuzzy evolving algorithm",
abstract = "This paper investigates the use of evolving fuzzy algorithms in forecasting. An evolving Takagi-Sugeno (eTS) algorithm, which is based on a recursive version of the subtractive algorithm is considered. It groups data into several clusters based on Euclidean distance between the relevant independent variables. The Mod eTS algorithm, which incorporates a modified dynamic update of cluster radii while accommodating new available data is proposed. The created clusters serve as a base for fuzzy If-Then rules with Gaussian membership functions which are defined using the cluster centres and have linear functions in the consequent i.e., Then parts of rules. The parameters of the linear functions are calculated using a weighted version of the Recursive Least Squares algorithm. The proposed algorithm is applied to a leakage forecasting problem faced by one of the leading UK water supplying companies. Using the real world data provided by the company the forecasting results obtained from the proposed modified eTS algorithm, Mod eTS, are compared to the standard eTS algorithm, exTS, eTS+ and fuzzy C-means clustering algorithm and some standard statistical forecasting methods. Different measures of forecasting accuracy are used. The results show higher accuracy achieved by applying the algorithm proposed compared to other fuzzy clustering algorithms and statistical methods. Similar results are obtained when comparing with other fuzzy evolving algorithms with dynamic cluster radii. Furthermore the algorithm generates typically a smaller number of clusters than standard fuzzy forecasting methods which leads to more transparent forecasting models.",
keywords = "fuzzy algorithms, forecasting",
author = "Lech Birek and Dobrila Petrovic and J. Boylan",
note = "The full text of this item is not available from the repository.",
year = "2014",
month = "1",
doi = "10.1016/j.asoc.2013.05.021",
language = "English",
volume = "14",
pages = "305--315",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier",
number = "PART B",

}

TY - JOUR

T1 - Water leakage forecasting: The application of a modified fuzzy evolving algorithm

AU - Birek, Lech

AU - Petrovic, Dobrila

AU - Boylan, J.

N1 - The full text of this item is not available from the repository.

PY - 2014/1

Y1 - 2014/1

N2 - This paper investigates the use of evolving fuzzy algorithms in forecasting. An evolving Takagi-Sugeno (eTS) algorithm, which is based on a recursive version of the subtractive algorithm is considered. It groups data into several clusters based on Euclidean distance between the relevant independent variables. The Mod eTS algorithm, which incorporates a modified dynamic update of cluster radii while accommodating new available data is proposed. The created clusters serve as a base for fuzzy If-Then rules with Gaussian membership functions which are defined using the cluster centres and have linear functions in the consequent i.e., Then parts of rules. The parameters of the linear functions are calculated using a weighted version of the Recursive Least Squares algorithm. The proposed algorithm is applied to a leakage forecasting problem faced by one of the leading UK water supplying companies. Using the real world data provided by the company the forecasting results obtained from the proposed modified eTS algorithm, Mod eTS, are compared to the standard eTS algorithm, exTS, eTS+ and fuzzy C-means clustering algorithm and some standard statistical forecasting methods. Different measures of forecasting accuracy are used. The results show higher accuracy achieved by applying the algorithm proposed compared to other fuzzy clustering algorithms and statistical methods. Similar results are obtained when comparing with other fuzzy evolving algorithms with dynamic cluster radii. Furthermore the algorithm generates typically a smaller number of clusters than standard fuzzy forecasting methods which leads to more transparent forecasting models.

AB - This paper investigates the use of evolving fuzzy algorithms in forecasting. An evolving Takagi-Sugeno (eTS) algorithm, which is based on a recursive version of the subtractive algorithm is considered. It groups data into several clusters based on Euclidean distance between the relevant independent variables. The Mod eTS algorithm, which incorporates a modified dynamic update of cluster radii while accommodating new available data is proposed. The created clusters serve as a base for fuzzy If-Then rules with Gaussian membership functions which are defined using the cluster centres and have linear functions in the consequent i.e., Then parts of rules. The parameters of the linear functions are calculated using a weighted version of the Recursive Least Squares algorithm. The proposed algorithm is applied to a leakage forecasting problem faced by one of the leading UK water supplying companies. Using the real world data provided by the company the forecasting results obtained from the proposed modified eTS algorithm, Mod eTS, are compared to the standard eTS algorithm, exTS, eTS+ and fuzzy C-means clustering algorithm and some standard statistical forecasting methods. Different measures of forecasting accuracy are used. The results show higher accuracy achieved by applying the algorithm proposed compared to other fuzzy clustering algorithms and statistical methods. Similar results are obtained when comparing with other fuzzy evolving algorithms with dynamic cluster radii. Furthermore the algorithm generates typically a smaller number of clusters than standard fuzzy forecasting methods which leads to more transparent forecasting models.

KW - fuzzy algorithms

KW - forecasting

U2 - 10.1016/j.asoc.2013.05.021

DO - 10.1016/j.asoc.2013.05.021

M3 - Article

VL - 14

SP - 305

EP - 315

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

IS - PART B

ER -