Modelling on Non-Revenue water / Mohamad Hafizi Zakaria, Muhammad Luqman Zulkifli and Nur Farahin Roslan
Non-Revenue Water (NON-REVENUE WATER RATIO) refers to the treated water that has produced from water plant which did not reach to the customer. It becomes one the challenges for commercial water system management. It is because the water company have to fulfill the demand from the society which keep...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Student Project |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/50418/1/50418.pdf https://ir.uitm.edu.my/id/eprint/50418/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Non-Revenue Water (NON-REVENUE WATER RATIO) refers to the treated water that has produced from water plant which did not reach to the customer. It becomes one the challenges for commercial water system management. It is because the water company have to fulfill the demand from the society which keep increasing day by day. This wasted water could cause the company face losses and hence, burdens the people with increasing water tariff. This study focused on identifying the significant factors that influencing the Non-Revenue Water and modelling the data using Multiple Linear Regression Model and Artificial Neural Network. The sample size used in this study were 234 observations and the variables involved were Length of Connection, Number of Connection, Production Quantity, Consumption Quantity and Non-Revenue Water Ratio. The result of Multiple Linear Regression imply that Consumption Quantity and Production Quantity were significant to Non-Revenue Water Ratio whereas the variables of Length of Connection and Number of Connection were not significant. Apart from that, Artificial Neural Network also had been used to analyze the data in order to build the best model for predicting Non¬ Revenue Water Ratio. In comparison of Multiple Linear Regression and Artificial Neural Network, higher value of R-square (R2 = 0.99) and lower of Mean Square Error (MSE = 2.09) of Artificial Neural Network concluded that Artificial Neural Network model more accurate and better to predict Non-Revenue Water Ratio as compared to Multiple Linear Regression. It is hoped that the result from this study can be used by the water authority company in improving the water distribution and thus reduce water losses and cost. |
|---|