CN107145958A - A kind of intelligent draining dispatching method of municipal drainage pipe network based on improvement particle cluster algorithm - Google Patents
A kind of intelligent draining dispatching method of municipal drainage pipe network based on improvement particle cluster algorithm Download PDFInfo
- Publication number
- CN107145958A CN107145958A CN201710167859.5A CN201710167859A CN107145958A CN 107145958 A CN107145958 A CN 107145958A CN 201710167859 A CN201710167859 A CN 201710167859A CN 107145958 A CN107145958 A CN 107145958A
- Authority
- CN
- China
- Prior art keywords
- pipe network
- particle
- dispatching method
- drainage pipe
- municipal drainage
- 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
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
Manually participated at this stage for municipal drainage pipe network dispatching method computational efficiency is low, the shortcoming that resource cost is big, the degree of accuracy is relatively low, it is proposed that it is a kind of based on the intelligent draining dispatching method of municipal drainage pipe network for improving particle cluster algorithm.This method carries out mathematical modeling to existing drainage pipeline networks model first.Then encoded, then using modified particle swarm optiziation, evolutionary operation is carried out to it for object function so that system operation is least in power-consuming, drainage line optimal under current environment is searched out.By this intelligent dispatch method, system energy consumption can be farthest reduced.
Description
Technical field
The present invention relates to the field of drainage pipeline networks scheduling.
Background technology
The inventive method is related to improvement particle cluster algorithm design, and corresponding model, application enhancements are set up from drainage pipeline networks
The method and process of optimal drainage line under particle cluster algorithm selection current environment.
With the present invention most close method Wei Hong spaces et al.《Set based on the city water-supply pipe network optimization for improving particle cluster algorithm
Meter》For the design of water supply network, it is proposed that a kind of based on the Optimal Design of Water Distribution Network method for improving particle cluster algorithm.
The content of the invention
The scheduling of current municipal drainage pipe network is all to draw optimal drainage line by way of manually participating in calculating,
Such mode can very big defect in efficiency and accuracy.The greatest problem that this method is present is manually to participate in meter
Calculate, because manually participate in calculating easily goes wrong in the case where data volume is huge, while the error of manual calculation
Can be very big, mistake also occurs in the continuous accumulation final result of error, is so difficult to draw optimal drain line.For this
Individual problem, the problem of present invention is directed to the drainage pipeline optimal route selection of drainage pipeline networks is completed from drainage pipeline networks first
In the case of, according to parameters such as being distributed of existing pipe network, real-time ponding situation and pumping drainage efficiency, dynamically build pipe network operation
Model.According to rainfall and distribution situation, suitable drainage strategy is pre-designed, then on the basis of drainage pipeline networks model, knot
The real time data for the pipeline regimen condition that the information such as the coordinate position that generalized information system is provided and drainage pipeline networks SCADA are provided is closed, water is omitted
Power feature, only considers the incidence relation between node and pipeline, figure is reduced to the digraph of a weighting, managed further according to building
Affecting parameters during road calculate the consuming value from a summit to another summit, as the power on side between element in figure, with
This weighted digraph constructed is asked for most saving to represent the power consumption model of drainage pipeline networks, then using modified particle swarm optiziation
Drainage path, the algorithm increases penalty on the basis of conventional particle group's algorithm, precocious for conventional particle group's algorithm
And diversity lose problem, the method for exchanging a certain amount of particle with other populations using current population, come solve precocity with
Diversity loses problem, and perfect algorithm terminates strategy, on the one hand set termination process of the maximum iterations as algorithm,
On the one hand it is termination process according to the convergence situation of colony, optimization aim and target formal similarity is set, acquisition is quickly asked
Solution, draws the optimal result under the situation of presence, solves the optimal draining scheduling problem of existing pipe network.
Brief description of the drawings
Fig. 1 solves the method flow diagram of optimal drainage line.
Embodiment
Embodiment is as shown in figure 1, set up pipe net leakage rate:First according to rainfall and distribution situation, area is preselected
Domain drainage direction, is shp, shx, dbf texts by suffix derived from GIS-Geographic Information System (GIS) then on selected region
Geographical position coordinates information is read out naive model of painting out by part, then sets up corresponding undirected graph model, in combination with
Remove some from real system than minor facility, after some of drainage pipeline networks partial simplified, keep its function, and
Relation between each element is constant, with the principle of macro equivalent, omits its and constructs hydraulic characteristic, only consider node and pipeline section it
Between incidence relation, construct pipe network graph model.Pipe network figure representation after simplification is the Directed Graph Model of a weighting, can be used
G (V, E) represent, wherein V be pipeline node set, i.e. V={ v1, v2 ..., vn }, E is line set, i.e. E=e1, e2 ...,
Em }, Wij is the side eij existed weights (i.e. the consuming of the conveying water of pipeline), and P (i, k) is point i to a k paths (k ∈
V).Theoretically analyze, the optimal topological structure of pipe network should be tree, then the last optimization knot of the graph model of pipe network
Fruit should also be tree.If pipeline starting point and terminal give, give n pipe point and two-by-two between pipe point pipeline section flower
Take, ask each pipe point of a process and total consuming only once.Then the optimization of pipe network figure is to find a directed tree so as to V
In each node i, it is minimum that P (i, t) meets weights from i to t in figure G.Directed tree T is pipe network Optimized Operation scheme.For
The optimization of pipe network figure, need to only estimate total consuming of pipe network, shown in the object function that can be used such as formula (1):
In formula (1):
WLAlways expended for tree pipe network;Li, j be the i-th pipe point between jth pipe point whether connection;V is pipe network connection figure
Side set.
It is the cost that the interrelated constraint of the multiple parameters in drainage pipeline networks pipeline is calculated for above-mentioned consuming,
Specific constrained parameters have pipe flow speed, conduit slope, pipe full degree, pipe range etc..Specific constrained parameters are described as follows:
(1) conduit slope & pipe flow speeds:China's outdoor water supply and sewerage design specification provides the minimal design slope of various calibers
Degree.Due to pipeline the gradient influence pipeline flow velocity, if the gradient is different, flow velocity is also different, when need increase flow velocity when it is necessary to
By setting up, pump machine etc. is outer to be located at current hill grade and gets off to gather way, and whenever using ancillary equipment, consuming can also increase accordingly
Plus, so this is also to participate in calculating one of parameter of influence.Constrained again by the processing speed of pumping plant below for flow velocity.Flow velocity has
Minimax is limited:
Vmin≤V≤Vmax
(2) duct length:Duct length between different nodes is also different from Practical Project.The length of pipeline
Consuming during for carrying out riser tubing flow velocity using peripheral hardware is also one of key factor, and different conduit slopes causes pipeline different
Flow velocity, pipeline it is different in flow rate to reach constraints minimum value when, it is just different in the consuming of unit duct length, so pipe
The length in road is also to calculate the key parameter that this pipeline expends.
(3) pipe full degree:Pipe full degree and pipe flow speed and outlet pipe can be calculated according to the other specification of pipeline
The flow in road, because the cistern of node pumping plant has certain limitation size, so pipe full degree is mutual in this multiple parameters
Mutually constrain.This parameter is also to calculate one of affecting parameters that pipeline expends.
Improve particle cluster algorithm design:Each particulate in population is considered as to the undirected graph model connection figure of pipe network after simplifying
A random generation, in order to distinguish this random spanning tree, using binary coding mode.The mould generated after simplifying to pipe network
It is 0 or 1 that all sides to be selected in type figure G (V, E), which carry out binary coding, i.e. value, then with two that length is m (number on side)
System character string can represent figure G subgraph.When the character value in character string certain is 1, represent that the side corresponding to it is
Constitute subgraph side, when character value be 0 when, represent corresponding to it while be not constitute subgraph while.The binary string of this m
Referred to as one of external channeling optimization problem solves.Because tree pipe network has n-1 bars side and with connectedness, if the tree of generation has small
For 1 individual must not be tree pipe network in or more than n-1 character value.Therefore, in order to avoid producing during evolution not
Feasible program, it is necessary to which only n-1 character value of each individual produced by controlling is 1, the necessary condition for making it meet feasible solution.
Then it could be examined connective, spanning tree is determined whether.Improve the optimal drainage line of PSO Algorithm drainage pipeline networks
Algorithm it is as follows:
Step1:Initialize Particle Swarm.Population size M is given, a random sequence is assigned to each particulate in colony
Row, setting particle cluster algorithm parameter ω, c1, c2 initial value takes the position vector p and speed v of each particle at random, and will be each
The adaptive value of the desired positions of particulate is set to ∞, wherein initialization p=1-2*rand ();V=1-2*rand ()-p/2;Its
Middle rand () is random function;
Step2:Evaluate the fitness of each particle respectively according to formula (1);
Step3:Punishment does not meet the particulate of constraints, and the fitness for resetting this particulate is 0.Due to c1, c2 parameters
Randomness, necessarily occurs that the new position of generation does not meet constraints when built pipe network pipeline is designed, therefore we are right
The new position for not meeting constraints sets it to punish that fitness is 0, is constantly oriented with to ensure particle populations to optimal location winged
OK;
Step4:Renewal speed v and position x is obtained by formula (2) to each particulate, and the new speed of each particle is carried out
Amplitude limiting processing:
Vid(t+1)=ω × Vid(t)+(δ-Xid(t))×β+C2×φ2×(Pgd-Xid(t))
Tri=Xi(t)+Vi(t+1) (2)
X in formula (2)idIt is individual i bit string position d current state;T is current time step;Vid(t) individual is represented
Do the tendency of a selection;PgdIt is the best condition in field;δ is represented for each particle i, is randomly selected two and is different from i
And the particle that three differs, the difference between this two particle randomly selected represents with δ;β is the random number on [0,1];
ω is Inertia Weight;C2For enchancement factor, purpose is in order to increase particles position diversity;TriRepresent particle i position next time;
φ2For the random number of amplitude limit, value is in [0,1] scope.
Step5:If population meets give-and-take conditions, carry out exchange of particles operation and (press ranking fitness, randomly choose population
Exchange particle);
Step6:When the condition of reinitializing is met, reinitialized according to fitness in domain of definition a number of
Compared with population;
Step7:The optimal particle position of each population is updated, will desired positions that each fitness of particulate is lived through with it
Pbest fitness is compared, if the fitness better than Pbest, regard the position of the particle as current best position
Put Pbest;To each particulate, the fitness value for the desired positions gbest that its adaptive value is lived through with colony is compared,
If the fitness better than gbest, using its particle position as colony's optimal location, and gbest call number is reset;
Step8:End condition is such as not up to, then Step2 is returned to, untill meeting end condition.Wherein on the one hand refer to
Fixed maximum iteration as particle swarm optimization termination process;On the other hand, according to the convergence feelings of colony in evolutionary process
Condition terminate process, if during evolution colony's average fitness continue 50 generations keep it is constant, it is believed that particle swarm optimization receive
Hold back, you can jump out circulation, terminate evolutionary process, shorten Riming time of algorithm, improve efficiency.
Step9:Output result value.
Above-described embodiment is preferably embodiment, but embodiments of the present invention are not by above-described embodiment of the invention
Limitation, other any Spirit Essences without departing from the present invention and the change made under principle, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (5)
1. it is a kind of based on the intelligent draining dispatching method of municipal drainage pipe network for improving particle cluster algorithm, comprise the following steps:Build
Standpipe pessimistic concurrency control;Initialization of population, inputs initial data;According to the feasible program of existing model run of designing;Calculate punishment letter
Number;Judge whether to meet population give-and-take conditions, such as meet, then update the certain poor population of initialization, and then update Particle Swarm
Speed and position;Such as it is unsatisfactory for, then directly updates particulate group velocity and position;Judge whether to meet end condition, if meeting
Terminate.
2. the intelligent draining dispatching method of municipal drainage pipe network according to claim 1, it is characterised in that:Initialization of population
Specially:Given population size M, a random sequence is assigned to each particulate in colony, setting particle cluster algorithm parameter ω,
C1, c2 initial value, take the position vector p and speed v of each particle at random, and the adaptive value of the desired positions of each particulate is set
∞ is set to, wherein initialization p=1-2*rand ();V=1-2*rand ()-p/2, wherein rand () are random functions.
3. the intelligent draining dispatching method of municipal drainage pipe network according to claim 2, it is characterised in that:
In formula (1):
WLAlways expended for tree pipe network;Li, j be the i-th pipe point between jth pipe point whether connection;V is the side of pipe network connection figure
Set, evaluate the fitness of each particle respectively according to formula (1).
4. the intelligent draining dispatching method of municipal drainage pipe network according to claim 3, it is characterised in that:Also include as follows
Step:Punishment does not meet the particulate of constraints, and the fitness for resetting this particulate is 0;Due to c1, the randomness of c2 parameters, one
Surely occur that the new position of generation does not meet constraints when built pipe network pipeline is designed, therefore we are not to meeting constraint
The new position of condition sets it to punish that fitness is 0, to ensure that particle populations constantly orient flight to optimal location.
5. the intelligent draining dispatching method of municipal drainage pipe network according to claim 4, it is characterised in that:It is described to update micro-
Particle swarm speed and position are specially:Renewal speed v and position x is obtained by formula (2) to each particulate, and to the new speed of each particle
Spend into
Row amplitude limiting processing:
Vid(t+1)=ω × Vid(t)+(δ-Xid(t))×β+C2×φ2×(Pgd-Xid(t))
Tri=Xi(t)+Vi(t+1) (2)
X in formula (2)idIt is individual i bit string position d current state;T is current time step;Vid(t) represent individual and do one
The tendency of selection;PgdIt is the best condition in field;δ is represented for each particle i, is randomly selected two and is different from i and three
Difference between the particle differed, this two particle randomly selected is represented with δ;β is the random number on [0,1];ω is used
Property weights;C2For enchancement factor, purpose is in order to increase particles position diversity;TriRepresent particle i position next time;φ2For
The random number of amplitude limit, value is in [0,1] scope.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710167859.5A CN107145958A (en) | 2017-03-20 | 2017-03-20 | A kind of intelligent draining dispatching method of municipal drainage pipe network based on improvement particle cluster algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710167859.5A CN107145958A (en) | 2017-03-20 | 2017-03-20 | A kind of intelligent draining dispatching method of municipal drainage pipe network based on improvement particle cluster algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107145958A true CN107145958A (en) | 2017-09-08 |
Family
ID=59783483
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710167859.5A Pending CN107145958A (en) | 2017-03-20 | 2017-03-20 | A kind of intelligent draining dispatching method of municipal drainage pipe network based on improvement particle cluster algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107145958A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110795810A (en) * | 2019-11-08 | 2020-02-14 | 苏州智品信息科技有限公司 | Online hydraulic model generation method |
CN111476700A (en) * | 2020-04-28 | 2020-07-31 | 广州地理研究所 | Flood prevention and control method, device, medium and equipment based on river and lake water system communication |
CN112836321A (en) * | 2020-12-31 | 2021-05-25 | 郑州力通水务有限公司 | Method for establishing drainage pipe network data model |
CN112950096A (en) * | 2021-04-27 | 2021-06-11 | 中国电建集团成都勘测设计研究院有限公司 | Integrated classification intelligent scheduling method for network and river |
CN113190944A (en) * | 2021-04-30 | 2021-07-30 | 西安理工大学 | Urban rainwater drainage system automatic optimization method based on SWMM and MATLAB |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101673369A (en) * | 2009-09-28 | 2010-03-17 | 北京工业大学 | Projection pursuit-based method for evaluating flooding risk of drainage pipe network |
CN105976052A (en) * | 2016-04-28 | 2016-09-28 | 广东工业大学 | Improved quantum-behaved particle swarm optimization algorithm-based multi-region economic dispatch method |
-
2017
- 2017-03-20 CN CN201710167859.5A patent/CN107145958A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101673369A (en) * | 2009-09-28 | 2010-03-17 | 北京工业大学 | Projection pursuit-based method for evaluating flooding risk of drainage pipe network |
CN105976052A (en) * | 2016-04-28 | 2016-09-28 | 广东工业大学 | Improved quantum-behaved particle swarm optimization algorithm-based multi-region economic dispatch method |
Non-Patent Citations (1)
Title |
---|
李明华: "基于微粒群算法的污水管道优化系统研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110795810A (en) * | 2019-11-08 | 2020-02-14 | 苏州智品信息科技有限公司 | Online hydraulic model generation method |
CN111476700A (en) * | 2020-04-28 | 2020-07-31 | 广州地理研究所 | Flood prevention and control method, device, medium and equipment based on river and lake water system communication |
CN112836321A (en) * | 2020-12-31 | 2021-05-25 | 郑州力通水务有限公司 | Method for establishing drainage pipe network data model |
CN112950096A (en) * | 2021-04-27 | 2021-06-11 | 中国电建集团成都勘测设计研究院有限公司 | Integrated classification intelligent scheduling method for network and river |
CN112950096B (en) * | 2021-04-27 | 2022-06-07 | 中国电建集团成都勘测设计研究院有限公司 | Integrated classification intelligent scheduling method for network and river |
CN113190944A (en) * | 2021-04-30 | 2021-07-30 | 西安理工大学 | Urban rainwater drainage system automatic optimization method based on SWMM and MATLAB |
CN113190944B (en) * | 2021-04-30 | 2022-04-22 | 西安理工大学 | Urban rainwater drainage system automatic optimization method based on SWMM and MATLAB |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107145958A (en) | A kind of intelligent draining dispatching method of municipal drainage pipe network based on improvement particle cluster algorithm | |
CN108764573B (en) | Inland arid region-oriented multidimensional equilibrium configuration system for water resources | |
Fallah-Mehdipour et al. | Developing reservoir operational decision rule by genetic programming | |
Chen et al. | An improved NSGA-III algorithm for reservoir flood control operation | |
CN105243458A (en) | Reservoir dispatching method based on multi-target shuffled frog leaping and differential algorithms | |
CN102629106A (en) | Water supply control method and water supply control system | |
CN109980700A (en) | A kind of distributed generation resource multi-objection optimization planning method, apparatus and equipment | |
CN104537178B (en) | A kind of power system associative simulation modeling method based on Matlab and Netlogo | |
CN108614915B (en) | Hydrological model free construction strategy method based on scene driving | |
CN106355292A (en) | Method and system for optimally dispatching cascade reservoirs on basis of quantum-behaved particle swarm algorithms | |
CN106651628A (en) | Regional cool and thermal power comprehensive energy optimizing configuration method and apparatus based on graph theory | |
CN106934497A (en) | Wisdom cell power consumption real-time predicting method and device based on deep learning | |
CN108155649A (en) | A kind of consideration probabilistic distribution network structure Fuzzy Programmings of DG | |
CN102802163B (en) | A kind of wireless sense network topological construction method based on mixed integer programming | |
CN107808200B (en) | Short-time maintenance plan optimization method and device for power distribution network | |
CN109921420A (en) | Elastic distribution network restoration power method for improving, device and terminal device | |
CN109063388A (en) | The micro climate architecture design addressing design method of wind environment simulation | |
Niu et al. | Cooperation search algorithm for power generation production operation optimization of cascade hydropower reservoirs | |
CN108667077A (en) | A kind of wind storage association system Optimization Scheduling | |
CN113379117B (en) | Gate dam group joint scheduling method and system based on improved elite retention strategy genetic algorithm | |
CN111881626B (en) | Distribution network planning method for promoting DG (distributed generation) digestion | |
CN109426901A (en) | Long-term power consumption prediction method and device in one kind | |
Pringles et al. | Optimal transmission expansion planning using mean-variance mapping optimization | |
CN106550387B (en) | A kind of wireless sensor network routing layer QoS evaluating method | |
CN109274117A (en) | A kind of Unit Combination method of robust a few days ago of data-driven |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170908 |
|
WD01 | Invention patent application deemed withdrawn after publication |