Leak Localization In Water Distribution Networks

CLIAMS:1. A method for locating a leak in a water distribution network, the method comprising: detecting, by a processor (102), a leak situation in the water distribution network based on a flow difference value between an actual flow value and a predicted flow value of an inlet flow meter of the water distribution network at at least one time interval being more than a predefined leak threshold; determining, by the processor (102), leak signature values of demand nodes in the water distribution network at the at least one time interval, wherein a leak signature value of a respective demand node at a respective time interval is indicative of a total flow increment due to the leak at the respective demand node and is determined based on centrality metrics, the predicted flow value at the respective time interval, and static physical properties related to the water distribution network; and identifying, by the processor (102), at least one possible leak node, from amongst the demand nodes, based on the flow difference value and the leak signature values of the demand nodes at the at least one time interval. 2. The method as claimed in claim 1 further comprising: obtaining, by the processor (102), historic flow values of the inlet flow meter when the water distribution network is leak-free; and determining, by the processor (102), the predicted flow value of the inlet flow meter at the at least one time interval based on the historic flow values. 3. The method as claimed in claim 1, wherein the determining the leak signature value of the respective demand node comprises: computing the total flow increment for which a pressure head at the respective demand node due to a water flow from an inlet node is about a predefined burst pressure head due to the leak at the respective demand node. 4. The method as claimed in claim 1, wherein the determining the leak signature value of the respective demand node at the respective time interval comprises: generating an adjacency matrix for a network topology of the water distribution network having pipes and nodes, wherein the adjacency matrix is generated based on the static physical properties related to the water distribution network; computing current-flow centrality metrics for pipes in the water distribution network that are in a water path from an inlet node to the respective demand node, wherein a current-flow centrality metric for a respective pipe is indicative of an amount of water passing through the respective pipe in the water path, and wherein the computing the current-flow centrality metrics is based on the adjacency matrix and a water supply at each of the demand nodes equal to the predicted flow value at the respective time interval divided by a number of the demand nodes. 5. The method as claimed in claim 4 further comprises: iteratively determining a pressure head at the respective demand node due to a water flow from the inlet node, wherein the determining the pressure head in each iteration is based on the current-flow centrality metrics computed based on incrementing the water supply at the respective demand node by a predefined flow increment value; and determining the leak signature value of the respective node equal to an integer multiple of the predefined flow increment value, wherein the integer multiple is based on a number of iterations till the pressure head at the respective node is within a first predefined tolerance limit of a predefined burst pressure head due to the leak at the respective demand node. 6. The method as claimed in claim 5, wherein identifying the at least one possible leak node comprises: identifying the respective demand node as one of the at least one possible leak node when the flow difference value at the respective time interval is within a second predefined tolerance limit of the leak signature value of the respective demand node at the respective time interval. 7. The method as claimed in claim 4, wherein for a pair of nodes connected directly to each other through a single pipe, an element of the adjacency matrix has a value of diameter of the single pipe raised to power five divided by length of the single pipe; and for a pair of nodes not connected directly to each other, an element of the adjacency matrix has a value of zero. 8. The method as claimed in claim 1, wherein the static physical properties comprise lengths and diameters of pipes in the water distribution network. 9. A system (100) for locating a leak in a water distribution network, the system (100) comprising: a processor (102); and a leak detection module (112) coupled to, and executable by, the processor (102) to: obtain an actual flow value and a predicted flow value of an inlet flow meter of the water distribution network at at least one time interval; and compute a flow difference value between the actual flow value and the predicted flow value at the at least one time interval to detect a leak situation in the water distribution network based on the flow difference value being more than a predefined leak threshold; a leak signature computation module (114) coupled to, and executable by, the processor (102) to determine leak signature values of demand nodes in the water distribution network at the at least one time interval, wherein a leak signature value of a respective demand node at a respective time interval is indicative of a total flow increment due to the leak at the respective demand node and is determined based on centrality metrics, the predicted flow value at the respective time interval, and static physical properties related to the water distribution network; and a leak location module (116) coupled to, and executable by, the processor (102) to identify at least one possible leak node, from amongst the demand nodes, based on the flow difference value and the leak signature values of the demand nodes at the at least one time interval. 10. The system (100) as claimed in claim 9, wherein the leak detection module (112) obtains historic flow values of the inlet flow meter when the water distribution network is leak-free, wherein the predicted flow value of the inlet flow meter at the at least one time interval is obtained based on the historic flow values. 11. The system (100) as claimed in claim 9, wherein the leak signature computation module (114) computes the total flow increment, as the leak signature value of the respective demand node, for which a pressure head at the respective demand node due to a water flow from an inlet node is about a predefined burst pressure head due to the leak at the respective demand node. 12. The system (100) as claimed in claim 9, wherein, to determine the leak signature value of the respective demand node at the respective time interval, the leak signature computation module (114) generates an adjacency matrix for a network topology of the water distribution network having pipes and nodes, wherein the adjacency matrix is generated based on the static physical properties related to the water distribution network; computes current-flow centrality metrics for pipes in the water distribution network that are in a water path from an inlet node to the respective demand node, wherein a current-flow centrality metric for a respective pipe is indicative of an amount of water passing through the respective pipe in the water path, and wherein the current-flow centrality metrics are based on the adjacency matrix and based on a water supply at each of the demand nodes equal to the predicted flow value at the respective time interval divided by a number of the demand nodes. 13. The system (100) as claimed in claim 12, wherein the leak signature computation module (114) iteratively determines a pressure head at the respective demand node due to a water flow from the inlet node, wherein the pressure head in each iteration is determined based on the current-flow centrality metrics computed based on incrementing the water supply at the respective demand node by a predefined flow increment value; and determines the leak signature value of the respective node equal to an integer multiple of the predefined flow increment value, wherein the integer multiple is based on a number of iterations till the pressure head at the respective node is within a first predefined tolerance limit of a predefined burst pressure head due to the leak at the respective demand node. 14. The system (100) as claimed in claim 13, wherein the leak location module (116) identifies the respective demand node as one of the at least one possible leak node when the flow difference value at the respective time interval is within a second predefined tolerance limit of the leak signature value of the respective demand node at the respective time interval. 15. The system (100) as claimed in claim 12, wherein, in the adjacency matrix, for a pair of nodes connected directly to each other through a single pipe, an element of the adjacency matrix has a value of diameter of the single pipe raised to power five divided by length of the single pipe; and for a pair of nodes not connected directly to each other, an element of the adjacency matrix has a value of zero. 16. A non-transitory computer-readable medium comprising instructions executable by a processor to: detect a leak situation in the water distribution network based on a flow difference value between an actual flow value and a predicted flow value of an inlet flow meter of the water distribution network at at least one time interval being more than a predefined leak threshold; determine leak signature values of demand nodes in the water distribution network at the at least one time interval, wherein a leak signature value of a respective demand node at a respective time interval is indicative of a total flow increment due to a leak at the respective demand node and is based on centrality metrics, the predicted flow value at the respective time interval, and static physical properties related to the water distribution network; and identify at least one possible leak node, from amongst the demand nodes, based on the flow difference value and the leak signature values of the demand nodes at the at least one time interval. ,TagSPECI:As Attached