نوع مقاله : مقاله پژوهشی
نویسندگان
1 استادیار مهندسی کامپیوتر، دانشکده مهندسی کامپیوتر، دانشگاه یزد، یزد، ایران
2 دانشآموخته دکترا مهندسی کامپیوتر، دانشکده مهندسی کامپیوتر، دانشگاه یزد، یزد، ایران
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
Smart water resource management is the best short-time solution for water resource shortage around
the world. Predicting water demand is the major prerequisite to be aware of the required water within a
short time. The proposed prediction framework uses the billing records of water consumers in Yazd city
to extract consumption history. In addition, external data resources such as business calendar data, urban
water production, meteorological parameters, the financial value of buildings, and in-stream pressure
are collected and employed in the prediction model. The proposed framework tracks the changes in
consumption behaviors of consumers, which are grouped according to their volume of water usage to
remove consumers with anomalous consumption behaviors. The cleaned grouped records of
consumption are utilized in the fitting of a quantile regressor with three breakpoints to forecast the water
demand of the consumers for the next month. Results of the experiments showed that the proposed
model’s prediction percentage error is less than 10%. Besides, the model is able to recognize consumers
with anomalous consumption behaviors.
کلیدواژهها [English]