AWWA ACE59835

This paper discusses how Artificial Neural Network (ANN) technology servedas a valuable tool in making conservation program choices in an ongoing residential waterconservation program for Edmonton, Alberta, Canada. The focus of this study was toidentify significant influencing factors for residential water consumption and use thisinformation to adopt public education programs that would best influence the behavior ofresidential water users. Artificial Intelligence (AI) was used in-house to create an ANN model that forecasts residential waterconsumption levels. One of the most important steps in creating the model was determiningthe statistically significant factors that have affected residential water consumption inEdmonton over the last 30 years. Now complete, the model can be used to predictconsumption forecasts based on various combinations of these factors. The ANN modelprovided the list of the main factors that influence water consumption as well as a means forrunning multiple scenarios based on a range of values for the various factors. Eachscenario produced a consumption prediction. The degree of variability of theseconsumption predictions was analyzed to determine which factors have the greatest impact on consumption. The order of significance of impact of these factors on residentialconsumption proved to be:base consumption index (a measure of the lowest year-round minimum usage);weather (summer and winter months); and,customer count (can be most or least significant, depending on the span of yearsstudied). Determining theorder of significance of the main residential consumption drivers helped identify whichfactors could be targeted through public water conservation initiatives. ANN technology provided the information necessary to eliminate options and to focusresources on the most effective and cost efficient programs for the community. In order to create a targeted residential water conservation program, the study researchedthese 5 questions:is the ANN model predicting consumption with a reasonable degree of accuracy;what is the range of possible residential water consumption (these values were usedas a check on later calculations);what factors drive residential water consumption (these factors were determinedduring development of an ANN residential water consumption forecasting model);how much can the changes in each consumption driver affect total residential waterconsumption (the degree of variability was assessed by running scenarios with theANN model); and,which factors can be influenced by water conservation campaigns? Includes 6 references, figures.

Product Details

Edition:

Vol. - No.

Published:

06/17/2004

Number of Pages:

13

File Size:

1 file , 310 KB