Keywords

biofilm; drinking water distribution system; data mining; multi-agent systems

Location

Session G2: Data Mining for Environmental Sciences (s-DMTES IV)

Start Date

17-6-2014 2:00 PM

End Date

17-6-2014 3:20 PM

Abstract

Biofilm leads to various undesirable problems in drinking water distribution systems (DWDSs), representing a critical paradigm in the management of these systems. Biofilm depends on a complex interaction of water quality, operational factors, and infrastructure associated to DWDSs. Although, it is known that all these factors do influence biofilm development, they have not been studied to the same extent. Those associated with the design and operation of DWDSs have been the most unconsidered. Besides, the joint influence of these factors has been scarcely investigated due to the complexity of the community and the environment under study. In order to bridge this gap, we focus on the joint analysis of the hydraulic (operation) and physical (design) characteristics of DWDSs to evaluate the susceptibility of the different areas of a DWDS to favour biofilm development. In addition, we also take into account the daily variability of the hydraulic conditions. Since hydraulic conditions are associated with demand, and demand varies depending on the moment of the day, we evaluate how biofilm susceptibility of a DWDS varies regarding a 24 hours demand curve. To achieve this objective we use (i) a meta-analysis process by applying Data Mining techniques, (ii) a label negotiation process by multi-agent systems and (iii) hydraulic simulation of DWDSs by using EPANET. As a result, a multiple time series study of the demand is approached to finally develop a decision making support tool useful for water utility managers. This will provide useful extra information to decide suitable actions addressing maintenance operations to mitigate problems associated to biofilm.

COinS
 
Jun 17th, 2:00 PM Jun 17th, 3:20 PM

Biofilm Susceptibility in a Drinking Water Distribution System Regarding 24 Hours Demand Curve

Session G2: Data Mining for Environmental Sciences (s-DMTES IV)

Biofilm leads to various undesirable problems in drinking water distribution systems (DWDSs), representing a critical paradigm in the management of these systems. Biofilm depends on a complex interaction of water quality, operational factors, and infrastructure associated to DWDSs. Although, it is known that all these factors do influence biofilm development, they have not been studied to the same extent. Those associated with the design and operation of DWDSs have been the most unconsidered. Besides, the joint influence of these factors has been scarcely investigated due to the complexity of the community and the environment under study. In order to bridge this gap, we focus on the joint analysis of the hydraulic (operation) and physical (design) characteristics of DWDSs to evaluate the susceptibility of the different areas of a DWDS to favour biofilm development. In addition, we also take into account the daily variability of the hydraulic conditions. Since hydraulic conditions are associated with demand, and demand varies depending on the moment of the day, we evaluate how biofilm susceptibility of a DWDS varies regarding a 24 hours demand curve. To achieve this objective we use (i) a meta-analysis process by applying Data Mining techniques, (ii) a label negotiation process by multi-agent systems and (iii) hydraulic simulation of DWDSs by using EPANET. As a result, a multiple time series study of the demand is approached to finally develop a decision making support tool useful for water utility managers. This will provide useful extra information to decide suitable actions addressing maintenance operations to mitigate problems associated to biofilm.