CN114492617A - Pipe network partition and trans-regional water quantity allocation method based on clustering - Google Patents
Pipe network partition and trans-regional water quantity allocation method based on clustering Download PDFInfo
- Publication number
- CN114492617A CN114492617A CN202210075924.2A CN202210075924A CN114492617A CN 114492617 A CN114492617 A CN 114492617A CN 202210075924 A CN202210075924 A CN 202210075924A CN 114492617 A CN114492617 A CN 114492617A
- Authority
- CN
- China
- Prior art keywords
- water
- pipeline
- clustering
- pipe network
- flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 199
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005192 partition Methods 0.000 title claims description 65
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 6
- 230000011218 segmentation Effects 0.000 claims description 14
- 230000035945 sensitivity Effects 0.000 claims description 11
- 238000013316 zoning Methods 0.000 claims description 9
- 238000003064 k means clustering Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 4
- 239000002245 particle Substances 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000004931 aggregating effect Effects 0.000 claims 1
- 238000000638 solvent extraction Methods 0.000 description 15
- 230000000694 effects Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Pipeline Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for allocating water quantity of pipe network subareas and cross-areas based on clustering, which comprises the steps of analyzing the water supply influence of water source of water plants, generating the water supply source characteristics of nodes, dividing reasonable subareas by utilizing a clustering algorithm, determining the reasonable subarea number and the subarea range, identifying the cross-area important pipelines according to sensitivity analysis, analyzing the allocation capacity of each water plant, and finally obtaining the water allocation efficiency among the areas under the current subarea scheme; so can carry out the science subregion of large scale and satisfy its water yield allotment demand to the water supply pipe network, realize the pipe network dispatch based on water balance, provide the decision-making basis.
Description
Technical Field
The invention relates to the technical field of water supply, in particular to a method for water quantity allocation of pipe network partitions and cross-partitions based on clustering.
Background
With the rapid development of the economic level of China, particularly the continuous promotion of the urbanization process, the scale and the occupied area of urban population are greatly increased, and the water supply network is gradually enlarged and more complicated; the original pipe network scheduling by artificial experience is greatly influenced by uncertain factors and cannot rapidly meet the requirement of short-term water quantity allocation, so that a more scientific pipe network scheduling technology aiming at a large-scale pipe network is urgently needed.
At present, a hierarchical partitioning technology is adopted, water balance or administrative management partitioning is generally considered on a first-level, partitioning is managed on the basis of pressure and flow on a second-level, and finer management and control needs, such as leakage control and the like, are considered on a third-level. The large-scale primary partition is the basis of multi-level scheduling, but the existing method mainly depends on manual experience and belongs to project trial and error, so that scientific planning is lacked and automatic partition cannot be realized; the application of the existing clustering algorithm in the subarea directly considers the management requirement of small scale, is not suitable for the first-level subarea with larger scale and does not consider the influence of subarea water imbalance caused by multiple water sources, so that an effective pipe network dispatching plan is difficult to make.
Disclosure of Invention
The invention aims to design a method for water distribution of pipe network partitions and cross-regions based on clustering, which can perform large-scale scientific partition on a water supply pipe network, meet the water distribution requirement of the water supply pipe network, realize pipe network scheduling based on water balance and provide decision basis.
In order to achieve the purpose, the invention provides the following technical scheme: a method for allocating water quantity in pipe network partitions and across partitions based on clustering comprises the steps of firstly analyzing water supply ranges of water plants to generate water supply source characteristics of nodes, then dividing reasonable partitions by using a clustering algorithm, determining reasonable partition number and partition ranges, then identifying cross-regional important pipelines according to sensitivity analysis, then analyzing allocation capacity of each water plant, and finally obtaining water allocation efficiency among domains under the current partition scheme, wherein the method specifically comprises the following steps:
the method comprises the following steps: carrying out delay hydraulic simulation on a water source of a water plant in a water supply network by using pipe network simulation software, wherein the pipe network simulation software is epanet and calculates an influenced flow value of a node; particle tracking as a method of performing material tracking, the concentration of the output point is described as a linear function of the input source intensity, which is shown in equation (1):
wherein, c0Is the output point concentration; n is the number of the stroke paths between the input and the output; t is0Is the output time; c. CjInputting the strength of a water quality source; t is tjIs the delay of the travel path j; gamma rayjThe influence coefficient of the travel path j; input intensity of water quality source cjAnd coefficient of influence gammajDepending on the source model used.
According to the formula (1), the water source of the water plant is used as an input source to increase the flow, and each node is used as an output point to calculate the flow increase value as the measurement of the influence degree of the node.
Step two: constructing water supply source characteristics of all nodes according to the node influence values obtained in the first step; the method comprises the steps that influence values of water plant water sources on all nodes are aggregated according to node IDs to obtain water plant influence values corresponding to all the nodes, then the water plant influence values of the nodes are converted into water plant influence ratios of the nodes, and further water supply source characteristics of all the nodes are constructed; note that, when some node IDs are not affected by a certain water plant, the influence value is "0" by default.
Step three: inputting the water supply source characteristics obtained in the step two as a model, and obtaining a partition result based on binary K-means clustering; the method comprises the steps of inputting water supply source structure characteristics of all nodes serving as a training set into a binary K-means clustering model, and outputting node sets of various different clusters after training, so that various partitioning schemes with different K values are obtained.
Determining a final K-type partition scheme by taking the deceleration and slowdown point of a K-SSE curve as an evaluation basis and combining a specific pipe network condition; comparing the distribution positions of the water plants of the pipe network, judging whether the current subareas can ensure that each water plant is distributed to each area more uniformly, and considering the condition that a plurality of water plants are contained in the subareas; comparing whether the boundaries of the partitions are clear or not, whether local nodes are scattered or not and whether the boundaries are not obvious or not are judged; if the partition boundary is clear, the local nodes are not scattered, and the boundary is obvious, the current partition effect is good, and the partition can be directly completed or the increase of the number of clustering partitions is considered; if the boundary is not clear, the local nodes are scattered and the boundary is not obvious, the current partitioning effect is poor, the partitions need to be combined, and the number of clustering partitions is reduced.
It should be noted that the Binary K-means model is an improvement of K-means based on Binary Split; k is preset in the clustering algorithm and represents the number of clustering clusters; SSE (sum of squares error) is the sum of squares of errors, which measures the effect of clustering.
Step four: extracting boundary pipelines from the partition results in the step three, and calculating the sensitivity of the pipelines on the influence of the water plant; the specific node partition is converted into a node information table (node ID, partition number ID), and the partition numbers corresponding to the head node and the tail node of each pipeline are matched by combining the pipeline information table (pipeline ID, head node ID and tail node ID).
Reuse of XOR operations
And judging whether the head and the tail of the pipeline belong to nodes of different regions, so as to judge whether the pipeline is a partitioned pipeline, and further automatically extracting the pipeline information of the boundary.
Finally, sensitivity analysis (sensivityanalysis) is utilized, delay hydraulic simulation is carried out by combining water sources of water plants in the water supply network, the water outlet pressure or the water outlet flow of the water sources of the water plants are changed in sequence, and the extracted response flow of the boundary pipelines is summarized and counted according to the partition boundaries to serve as the sensitivity of the boundary pipelines on the influence of the water plants.
Step five: identifying important pipelines at the boundary according to the sensitivity of the pipelines obtained in the step four to the influence of the water plant; specifically, an optimal segmentation algorithm is used for identifying the trans-regional important pipelines, and the application steps are as follows: arranging boundary pipelines in a descending order of flow change values; determining N-1 dividing points for N pipelines, dividing the pipelines into two groups, and traversing the positions of the dividing points; (iii) determine an optimal slicing strategy based on an objective function, usually based on the minimization of the square error, as shown in equation (2):
wherein Y is the final optimization objective, minimizing it; s is a point of tangency, R1(s) and R2(s) represent the two groups of data after being divided, respectively, c1And c2Each represents the average of two sets of data.
When the concrete division is carried out, two strategies are fused at the same time, one strategy utilizes an optimal division algorithm to search for a so-called optimal division point, the other strategy judges whether the current divided pipeline flow accounts for 85% of the original flow, and if not, the current divided pipeline flow is moved to the next division point until the current divided pipeline flow reaches 85% of the original flow; it should be noted that by restricting the flow rate of the cross-regional important pipeline to be more than 85%, the excessive data caused by the extreme distribution of the pipeline flow rate is avoided being screened out.
And obtaining an important pipeline set of each boundary according to an optimal segmentation point determined by an optimal segmentation algorithm and the current segmented pipeline flow ratio.
Step six: and calculating the dispatching capacity of the water source of the water plant and the cross-regional water quantity allocation efficiency, namely respectively testing the response flow influenced by each water plant according to the important pipeline set of each boundary, thereby obtaining the dispatching capacity of the water source of the water plant and the cross-regional water quantity allocation efficiency. Specifically, the application steps are as follows: the water outlet flow of 1000 square/hour is respectively increased for each water plant; counting the total water supply flow of important pipelines on the boundary of a subarea adjacent to the subarea where the water plant is located, obtaining the flow scheduling capacity of a water source of the water plant on the boundary, and summarizing the flow ratio of each boundary to obtain the transfer efficiency of the flow; and respectively drawing a boundary water supply efficiency map for each water plant.
Compared with the prior art, the invention has the beneficial effects that: by using the method for pipe network partition and cross-regional water quantity allocation based on clustering, the water supply range of a water plant is analyzed, then the partition is divided by using a clustering algorithm, important pipelines are identified and the allocation capacity of each water plant is analyzed after the partition, so that the water allocation efficiency between areas under the current partition scheme can be obtained, the large-scale scientific partition can be performed on the water supply pipe network, the water allocation requirement of the water supply pipe network can be met, the pipe network scheduling based on water quantity balance is realized, and a decision basis is provided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the steps of the present invention;
FIG. 2 is an input/output diagram of a binary K-means clustering partitioning scheme according to the present invention;
FIG. 3 is a flow chart of the calculation of important pipe identification of the present invention;
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and obviously, the description is only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example (b): referring to fig. 1, a method for pipe network zoning and trans-regional water quantity allocation based on clustering includes the steps of firstly analyzing water supply ranges of water plants to generate water supply source characteristics of nodes, then dividing reasonable zones by using a clustering algorithm, determining reasonable number of zones and zone ranges, then identifying trans-regional important pipelines according to sensitivity analysis, then analyzing allocation capacity of each water plant, and finally obtaining water allocation efficiency between zones under a current zoning scheme, which specifically includes the following steps:
the method comprises the following steps: carrying out delay hydraulic simulation on a water source of a water plant in a water supply network by using pipe network simulation software, wherein the pipe network simulation software is epanet and calculates an influenced flow value of a node; particle tracking as a method of performing material tracking, the concentration of the output point is described as a linear function of the input source intensity, which is shown in equation (1):
wherein, c0Is the output point concentration; n is the number of the stroke paths between input and output; t is0Is the output time; c. CjInputting the strength of a water quality source; t is tjIs the delay of the travel path j; gamma rayjIs the influence coefficient of the travel path j; input intensity of water quality source cjAnd coefficient of influence γjDepending on the source model used.
According to the formula (1), the water source of the water plant is used as an input source to increase the flow, and each node is used as an output point to calculate the flow increase value as the measurement of the influence degree of the node.
Step two: constructing water supply source characteristics of all nodes according to the node influence values obtained in the step one; the method comprises the steps that influence values of water plant water sources on all nodes are aggregated according to node IDs to obtain water plant influence values corresponding to all the nodes, then the water plant influence values of the nodes are converted into water plant influence ratios of the nodes, and further water supply source characteristics of all the nodes are constructed; note that, when some node IDs are not affected by a certain water plant, the influence value is "0" by default.
Step three: taking the water supply source characteristics obtained in the second step as model input, and obtaining a partitioning result based on binary K-means clustering, wherein the related partitioning scheme based on binary K-means clustering refers to FIG. 2; the method comprises the steps of inputting water supply source structure characteristics of all nodes serving as a training set into a binary K-means clustering model, outputting node sets of various clusters after training, and in specific implementation, optimizing a clustering process by using a PAM algorithm during specific implementation to improve a partitioning effect. In addition, a K value is selected according to the speed reduction and slow change point of a K-SSE curve and the actual condition of a pipe network to obtain the most appropriate partitioning scheme, namely comparing the distribution positions of the water plants of the pipe network, judging whether the current partitioning can ensure that each water plant is uniformly distributed to each partition or not, and considering the condition that a plurality of water plants are contained in the partitioning; comparing whether the boundaries of the partitions are clear or not, whether local nodes are scattered or not and whether the boundaries are not obvious or not are judged; if the partition boundary is clear, the local nodes are not scattered, and the boundary is obvious, the current partition effect is good, and the partition can be directly completed or the increase of the number of clustering partitions is considered; if the boundary is not clear, the local nodes are scattered and the boundary is not obvious, the current partitioning effect is poor, the partitions need to be combined, and the number of clustering partitions is reduced.
It should be noted that the Binary K-means model is an improvement of K-means based on Binary Split; k is preset in the clustering algorithm and represents the number of clustering clusters; SSE (sum of squares error) is the sum of squares of errors, which measures the effect of clustering.
Step four: extracting boundary pipelines from the partition results in the step three, and calculating the sensitivity of the pipelines on the influence of the water plant; the specific node partition is converted into a node information table (node ID, partition number ID), and the partition numbers corresponding to the head node and the tail node of each pipeline are matched by combining the pipeline information table (pipeline ID, head node ID and tail node ID).
Reuse of XOR operations
And judging whether the head and the tail of the pipeline belong to nodes of different regions, so as to judge whether the pipeline is a partitioned pipeline, and further automatically extracting the pipeline information of the boundary.
Finally, by utilizing sensitivity analysis (sensivityanalysis) and combining pipe network hydraulic simulation, the outlet water pressure or the outlet water flow of each water plant water source is changed in sequence, and the extracted response flow of the boundary pipelines is summarized and counted according to the partition boundaries to serve as the influence sensitivity of each boundary pipeline on the water plant.
Step five: identifying the important pipelines at the boundary according to the sensitivity of each boundary pipeline to the water plant obtained in the step four, wherein the related cross-region important pipeline identification calculation flow is shown in FIG. 3; specifically, an optimal segmentation algorithm is used for identifying the trans-regional important pipelines, and the application steps are as follows: arranging the boundary pipelines in a descending order of flow change values; determining N-1 dividing points for N pipelines, dividing the pipelines into two groups, and traversing the positions of the dividing points; (iii) determine an optimal slicing strategy based on an objective function, usually based on the minimization of the square error, as shown in equation (2):
wherein Y is the final optimization objective, minimizing it; s is a point of tangency, R1(s) and R2(s) represent the two groups of data after being segmented, respectively, c1And c2Each represents the average of two sets of data.
When the concrete division is carried out, two strategies are fused at the same time, one strategy utilizes an optimal division algorithm to search for a so-called optimal division point, the other strategy judges whether the current divided pipeline flow accounts for 85% of the original flow, and if not, the current divided pipeline flow is moved to the next division point until the current divided pipeline flow reaches 85% of the original flow; it should be noted that by restricting the flow rate of the cross-regional important pipeline to be more than 85%, the excessive data caused by the extreme distribution of the pipeline flow rate is avoided being screened out.
And obtaining the important pipeline set of each boundary according to the optimal segmentation point determined by the optimal segmentation algorithm and the current segmented pipeline flow ratio.
Step six: and calculating the dispatching capacity of the water source of the water plant and the cross-regional water quantity allocation efficiency, namely respectively testing the response flow influenced by each water plant according to the important pipeline set of each boundary, thereby obtaining the dispatching capacity of the water source of the water plant and the cross-regional water quantity allocation efficiency. Specifically, the application steps are as follows: the water outlet flow of 1000 square/hour is respectively increased for each water plant; counting the total water supply flow of important pipelines on the boundary of a subarea adjacent to the subarea where the water plant is located, obtaining the flow scheduling capacity of a water source of the water plant on the boundary, and summarizing the flow ratio of each boundary to obtain the transfer efficiency of the flow; and respectively drawing a boundary water supply efficiency map for each water plant.
By using the method for pipe network partition and cross-regional water quantity allocation based on clustering, the water supply range of a water plant is analyzed, then the partition is divided by using a clustering algorithm, important pipelines are identified and the allocation capacity of each water plant is analyzed after the partition, so that the water allocation efficiency between areas under the current partition scheme can be obtained, the large-scale scientific partition can be performed on the water supply pipe network, the water allocation requirement of the water supply pipe network can be met, the pipe network scheduling based on water quantity balance is realized, and a decision basis is provided; the decision is based on two main aspects, namely, on one hand, the decision is used for helping a pipe network manager to perform proper water supply partition; on the other hand, reliable information is provided for scheduling personnel, and when some areas lack water and have water-transfer requirements of adjacent areas, the pipeline valve at which position should be started or stopped can be judged according to the scheduling capability of the pipeline;
the clustering method is simple in principle, clear in calculation logic and clear in meaning of related parameters, and after water affair personnel collect a water source flow data set of the nodes, the method can be directly applied to partitioning.
The large pipe network partitioning method based on clustering meets the requirement of water balance, and the clustering algorithm and the simulation technology are comprehensively utilized, so that the water affair informatization degree can be effectively improved.
The related cross-regional important pipeline identification method is very simple in calculation formula and very strong in practicability, and facilitates management of a subsequent water quantity scheduling plan.
Claims (9)
1. A method for water quantity allocation of pipe network partitions and cross-regions based on clustering is characterized in that: analyzing the water supply influence of water sources of water plants, generating water supply source characteristics of nodes, dividing reasonable partitions by using a clustering algorithm, determining the number and the range of the reasonable partitions, identifying cross-regional important pipelines according to sensitivity analysis, analyzing the allocation capacity of each water plant, and finally obtaining the inter-regional water allocation efficiency of the current partition scheme.
2. The method for pipe network partition and trans-partition water volume allocation based on clustering according to claim 1, wherein: the method comprises the following steps:
the method comprises the following steps: performing delay hydraulic simulation on a water source of a water plant in a water supply network by using pipe network simulation software, and calculating a node influence value;
step two: constructing water supply source characteristics of all nodes according to the node influence values obtained in the step one;
step three: inputting the water supply source characteristics obtained in the step two as a model, and obtaining a partition result based on binary K-means clustering;
step four: extracting boundary pipelines from the partition results in the step three, and calculating the sensitivity of the pipelines on the influence of the water plant;
step five: identifying important pipelines on the boundary according to the sensitivity of the pipelines obtained in the step four on the influence of the water plant;
step six: and calculating the dispatching capacity of the water source of the water plant and the cross-region water quantity allocation efficiency.
3. The method for pipe network zoning and trans-regional water volume allocation based on clustering of claim 2, wherein: and calculating the node influence value comprises the steps of increasing the flow by using a water source of a water plant as an input source and calculating the flow increase value by using the node as an output point by using a particle tracking algorithm to obtain the node influence value.
4. The method for pipe network zoning and trans-regional water volume allocation based on clustering of claim 2, wherein: constructing the source characteristics of the water supply comprises the following steps:
(4.1): aggregating the influence value data of the water plant water source to the nodes according to the node ID to obtain the water plant influence value corresponding to each node;
(4.2): and converting the water plant influence value corresponding to the node into the water plant influence ratio of the node, and taking the ratio as the water supply source characteristic of the node.
5. The method for pipe network zoning and trans-regional water volume allocation based on clustering of claim 2, wherein: the third step specifically comprises the following steps:
(5.1) inputting the water supply source characteristics of the nodes into a binary K-means clustering model as a training set, and outputting node sets of various different clusters after training so as to obtain partition schemes with various different K values;
and (5.2) determining a final K-type partition scheme by taking the deceleration and slowdown point of the K-SSE curve as an evaluation basis and combining the specific pipe network condition.
6. The method for pipe network zoning and trans-regional water volume allocation based on clustering of claim 2, wherein: the method for calculating the sensitivity of the pipeline to the influence of the water plant comprises the following steps:
(6.1): matching the partition results with the partition numbers corresponding to the head and tail nodes of each pipeline by combining the pipeline information;
(6.2): using XOR operations
Judging whether the head and the tail of the pipeline belong to nodes of different areas or not, thereby judging whether the pipeline is a partitioned pipeline or not;
(6.3): and changing the water outlet pressure or the water outlet flow of the water source of the water plant, summarizing and counting the response flow of the boundary pipeline extracted in the step according to the partition boundary, and taking the response flow as the sensitivity of the boundary pipeline on the influence of the water plant.
7. The method for pipe network zoning and trans-regional water volume allocation based on clustering of claim 2, wherein: identifying the critical pipe of the boundary comprises the following steps:
(7.1) arranging the pipeline sets of each boundary in a descending order according to the sensitivity of the pipelines to the influence of the water plant;
(7.2) determining an optimal segmentation point by using an optimal segmentation algorithm, and dividing the pipeline set into an upper group and a lower group, wherein the upper group is used as a theoretical important pipeline;
(7.3) verifying whether the flow of the theoretically important pipeline is more than 85% of the total flow of the boundary, if so, moving the dividing point downwards to enable the dividing point to contain more pipelines until the flow is more than 85%;
and (7.4) taking the pipeline set divided by the pipeline set (7.3) as an important pipeline set of the cross-region.
8. The method for pipe network zoning and trans-regional water volume allocation based on clustering of claim 7, wherein: the optimal segmentation algorithm comprises the steps of dividing N pieces of flow data into two parts according to N-1 segmentation points, and traversing the N-1 segmentation points in sequence; and calculating the square sum of the variances of all the segmentation points to obtain the minimum segmentation point X, namely the optimal segmentation point.
9. The method for pipe network zoning and trans-regional water volume allocation based on clustering of claim 2, wherein: the method for calculating the dispatching capacity of the water source of the water plant and the cross-regional water quantity allocation efficiency comprises the following steps:
(9.1) increasing the water outlet flow rate of 1000 square/hour for the water plant;
(9.2) counting the total water supply flow of important pipelines on the boundary of the subarea adjacent to the subarea where the water plant is located;
(9.3) calculating the flow ratio of each boundary pipeline, namely the transfer efficiency of the flow;
and (9.4) respectively drawing a boundary water supply efficiency map for each water plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210075924.2A CN114492617A (en) | 2022-01-23 | 2022-01-23 | Pipe network partition and trans-regional water quantity allocation method based on clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210075924.2A CN114492617A (en) | 2022-01-23 | 2022-01-23 | Pipe network partition and trans-regional water quantity allocation method based on clustering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114492617A true CN114492617A (en) | 2022-05-13 |
Family
ID=81472672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210075924.2A Pending CN114492617A (en) | 2022-01-23 | 2022-01-23 | Pipe network partition and trans-regional water quantity allocation method based on clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114492617A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115370973A (en) * | 2022-10-25 | 2022-11-22 | 山东辰智电子科技有限公司 | Water supply leakage monitoring method and device, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391856A (en) * | 2017-07-27 | 2017-11-24 | 燕山大学 | Optimize the method for water meter and valve location in a kind of water supply network subregion |
| KR101875885B1 (en) * | 2018-02-06 | 2018-07-06 | 주식회사 코비 | Water supply integrated management operating system using water network analysis |
| CN108876016A (en) * | 2018-05-30 | 2018-11-23 | 燕山大学 | A kind of multistage multiple target water supply network optimization partition method |
| CN110056781A (en) * | 2019-03-12 | 2019-07-26 | 天津大学 | Water supply network flow monitoring point optimization placement method |
| WO2021000581A1 (en) * | 2019-06-30 | 2021-01-07 | 浙江大学 | Node flow optimization and distribution method for improving transient hydraulic simulation precision of water supply serial pipeline |
| WO2022012093A1 (en) * | 2020-07-13 | 2022-01-20 | 浙江大学 | Complex water resource system optimal configuration method based on "partitioning-rating" theory |
-
2022
- 2022-01-23 CN CN202210075924.2A patent/CN114492617A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391856A (en) * | 2017-07-27 | 2017-11-24 | 燕山大学 | Optimize the method for water meter and valve location in a kind of water supply network subregion |
| KR101875885B1 (en) * | 2018-02-06 | 2018-07-06 | 주식회사 코비 | Water supply integrated management operating system using water network analysis |
| CN108876016A (en) * | 2018-05-30 | 2018-11-23 | 燕山大学 | A kind of multistage multiple target water supply network optimization partition method |
| CN110056781A (en) * | 2019-03-12 | 2019-07-26 | 天津大学 | Water supply network flow monitoring point optimization placement method |
| WO2021000581A1 (en) * | 2019-06-30 | 2021-01-07 | 浙江大学 | Node flow optimization and distribution method for improving transient hydraulic simulation precision of water supply serial pipeline |
| WO2022012093A1 (en) * | 2020-07-13 | 2022-01-20 | 浙江大学 | Complex water resource system optimal configuration method based on "partitioning-rating" theory |
Non-Patent Citations (1)
| Title |
|---|
| 王艳;潘兴忠;郑;洪德松;: "应用管网水力模型辅助制定供水调度方案", 城镇供水, no. 05, 30 September 2015 (2015-09-30), pages 37 - 41 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115370973A (en) * | 2022-10-25 | 2022-11-22 | 山东辰智电子科技有限公司 | Water supply leakage monitoring method and device, storage medium and electronic equipment |
| CN115370973B (en) * | 2022-10-25 | 2023-02-28 | 山东辰智电子科技有限公司 | Water supply leakage monitoring method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492950B (en) | Prediction method capable of meeting space saturation load of large area range based on GIS technology | |
| CN111160430A (en) | Water resource optimization configuration method based on artificial intelligence algorithm | |
| CN109670650A (en) | The method for solving of Cascade Reservoirs scheduling model based on multi-objective optimization algorithm | |
| CN105404944A (en) | Big data analysis method for warning of heavy-load and overload of electric power system | |
| CN105205052B (en) | A kind of data digging method and device | |
| CN107909208A (en) | Damage method drops in a kind of taiwan area distribution | |
| CN109697566A (en) | Electronic product processing technology evaluation system and its evaluation method | |
| CN102088709A (en) | Method for predicting telephone traffic based on clustering and autoregressive integrated moving average (ARIMA) model | |
| CN101808339A (en) | Telephone traffic subdistrict self-adaptive classification method applying K-MEANS and prior knowledge | |
| CN110378510B (en) | Distribution network material demand prediction method based on time sequence and hierarchical aggregation | |
| CN109255384A (en) | A kind of traffic flow pattern recognition methods based on density peaks clustering algorithm | |
| CN109903554A (en) | A kind of road grid traffic operating analysis method based on Spark | |
| CN109285219B (en) | A kind of grid type hydrological model grid calculation order encoding method based on DEM | |
| CN108388726A (en) | A kind of mechanical structure Robust Optimal Design method considering multiple target multiple constraint balancing performance | |
| CN108717584B (en) | Multi-target partition method for water supply pipe network | |
| CN114492617A (en) | Pipe network partition and trans-regional water quantity allocation method based on clustering | |
| CN106845696B (en) | Intelligent optimization water resource configuration method | |
| CN114429053A (en) | Basin scale WEFE system adaptability simulation optimization method | |
| CN112613720A (en) | Reservoir irrigation optimal scheduling method considering multiple uncertainties | |
| CN108664995A (en) | More granularity city public bicycle dispatching methods based on DBScan and system | |
| CN109711727A (en) | Electronic product processing technology combination evaluation system and its evaluation method | |
| Von Lucken et al. | Pump scheduling optimization using asynchronous parallel evolutionary algorithms | |
| CN105590141A (en) | Genetic algorithm initial population construction method applied to optimized design of complex products | |
| CN116542001B (en) | Water supply network independent metering partitioning method based on improved spectral clustering and genetic algorithm | |
| CN113850346B (en) | Edge service secondary clustering method and system for multi-dimensional attribute perception in MEC environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |