Article: "Real-time water demand forecasting system through an agent-based architecture" Journal: Int. J. of Bio-Inspired Computation, 2015 Vol.7 No.3 pp.147 - 156 Abstract: Water policies have evolved enormously since the Rio Earth Summit (1992). These changes have led to the strategic importance of water demand management. The aim is to provide water where and when it is required using the fewest resources. A key variable in this process is the demand forecasting. It is not sufficient to have long term forecasts, as the current context requires the continuous availability of reliable hourly predictions. This paper incorporates artificial intelligence to the subject, through an agent-based system, whose basis are complex forecasting methods (Box-Jenkins, Holt-Winters, multi-layer perceptron networks and radial basis function networks). The prediction system also includes data mining, oriented to the pre and post processing of data and to the knowledge discovery, and other agents. Thereby, the system is capable of choosing at every moment the most appropriate forecast, reaching very low errors. It significantly improves the results of the different methods separately. - Inderscience Publishers - linking academia, business and industry through research

Int. J. of Bio-Inspired Computation » 2015 Vol.7, No.3

Title: Real-time water demand forecasting system through an agent-based architecture

Authors: Borja Ponte; David De la Fuente; Raúl Pino; Rafael Rosillo

Addresses:
Polytechnic School of Engineering, University of Oviedo, Campus de Viesques, s/n, 33204, Gijón, Spain
Polytechnic School of Engineering, University of Oviedo, Campus de Viesques, s/n, 33204, Gijón, Spain
Polytechnic School of Engineering, University of Oviedo, Campus de Viesques, s/n, 33204, Gijón, Spain
Faculty of Economics and Business, University of León, Campus de Vegazana, s/n, 24071, León, Spain

Abstract: Water policies have evolved enormously since the Rio Earth Summit (1992). These changes have led to the strategic importance of water demand management. The aim is to provide water where and when it is required using the fewest resources. A key variable in this process is the demand forecasting. It is not sufficient to have long term forecasts, as the current context requires the continuous availability of reliable hourly predictions. This paper incorporates artificial intelligence to the subject, through an agent-based system, whose basis are complex forecasting methods (Box-Jenkins, Holt-Winters, multi-layer perceptron networks and radial basis function networks). The prediction system also includes data mining, oriented to the pre and post processing of data and to the knowledge discovery, and other agents. Thereby, the system is capable of choosing at every moment the most appropriate forecast, reaching very low errors. It significantly improves the results of the different methods separately.

Keywords: agent-based systems; multi-agent systems; MAS; artificial neural networks; ANNs; Box-Jenkins; data mining; demand forecasting; Holt-Winters; hourly forecasting; multi-layer perceptron; MLP; radial basis function; RBF; water demand management; WDM; knowledge discovery; water supply; water management.

DOI: 10.1504/IJBIC.2015.069559

Int. J. of Bio-Inspired Computation, 2015 Vol.7, No.3, pp.147 - 156

Submission date: 15 Sep 2014
Date of acceptance: 07 Jan 2015
Available online: 25 May 2015