CN107480813A - Basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm - Google Patents
Basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm Download PDFInfo
- Publication number
- CN107480813A CN107480813A CN201710624335.4A CN201710624335A CN107480813A CN 107480813 A CN107480813 A CN 107480813A CN 201710624335 A CN201710624335 A CN 201710624335A CN 107480813 A CN107480813 A CN 107480813A
- Authority
- CN
- China
- Prior art keywords
- water
- genetic algorithm
- chaotic
- mrow
- basin
- 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 161
- 230000000739 chaotic effect Effects 0.000 title claims abstract description 61
- 230000002068 genetic effect Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000005457 optimization Methods 0.000 claims abstract description 41
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000013210 evaluation model Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 42
- 230000007935 neutral effect Effects 0.000 claims description 28
- 238000011156 evaluation Methods 0.000 claims description 23
- 230000008901 benefit Effects 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 239000012141 concentrate Substances 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 6
- 230000033001 locomotion Effects 0.000 claims description 5
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 230000004044 response Effects 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 210000005036 nerve Anatomy 0.000 claims 1
- 230000009467 reduction Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 239000008400 supply water Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000003673 groundwater Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000002352 surface water Substances 0.000 description 2
- 241000372132 Hydrometridae Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000008235 industrial water Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000007261 regionalization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
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"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0418—Architecture, e.g. interconnection topology using chaos or fractal principles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm, belong to water resource optimal allocation technical field.Its step is as follows:Obtain basin water resources essential information;Multiple target water resource optimal allocation mathematical modeling is established, and carries out allocation models parameter calibration;Using multi-Objective Chaotic genetic algorithm, water resource optimal allocation alternative collection is solved;Water resource optimal allocation optimal equalization scheme is determined finally by chaotic neural network comprehensive evaluation model.The present invention has coupled the inverting of the ergodic and genetic algorithm of chaos, improves algorithm speed, and optimal solution is stable, meets the multiple-objection optimization configuration requirement of basin water resources complication system.
Description
Technical field
The invention discloses a kind of water resource optimal allocation method based on multi-Objective Chaotic genetic algorithm, belong to water resource
Distribute technical field rationally.
Background technology
Water resource system is to utilize system, life by the water resource that water resources circulation system, mankind's activity and its influence are formed
The complex large system that state environmental system and material within and outside the region, energy, information interaction are formed.In water resource system
The complicated commutative relation of material, energy and information, the evolution of common moving system between portion, outside be present;In addition, water resource system
The ecological economy element distribution of system, demand, supply and consumption it is uneven, the lack of balance of structure be present, it is multiple between subsystem
The otherness of matter and input, the disequilibrium etc. of output, the fine difference of system action will cause different system results.Cause
This, water resource system is a complication system open, away from nonequilibrium state.The complexity of water resource system determines that water provides
Source sustainable use must use Complex System Theory and method to be analyzed and researched.Chaos is it is determined that one occurred in system
Rule, similar random phenomenon seemingly are planted, is the compound movement form of generally existing in water resources management.Using chaology,
Deterministic parsing single in traditional hydrographic water resource analysis in the past or Stochastic analysis will be broken, and set up both unifications
Chaos analysis method, be advantageous to content that is abundant and developing complicated system analysis of water resources, make water resource study to obtain new development.
Chaotic optimization algorithm is a kind of new algorithm being suggested recently as the development of chaos subject.Its basic thought is
By by mapping of the optimization problem model to Chaos Variable, i.e., the valued space of Chaos Variable Linear Mapping to optimized variable,
Chaos Variable is constructed, makes full use of Chaos Variable possessed ergodic, randomness, regularity during chaotic motion to seek
Look for the optimal solution of the overall situation.Because chaos optimization method belongs to the direct random search of no derivative, the spy of optimization object function is treated
Property require it is less, avoid and require that object function and constraints are continuously differentiable difficulties in gradient search method, carry significantly
The high efficiency of algorithm.For chaotic optimization algorithm with respect to GA, DDDP scheduling algorithms have principle simple, convenience of calculation, result precision height etc.
Advantage.(application [J] the China agriculture of the chaotic optimization algorithms such as Qiu Lin, Tian Jinghuan, Duan Chunqing in optimizing scheduling of reservoir such as Qiu Lin
Village's water conservancy and hydropower, 2005 (7):17~19.) chaotic optimization algorithm is applied in optimizing scheduling of reservoir, using chaos iteration not
Repeatability and ergodic, obtain globally optimal solution.(such as Liang Wei, Chen Shoulun, what spring member is calculated based on chaos optimization by Liang Wei, Chen Shoulun
Step hydroelectric station reservoir Optimized Operation [J] HYDROELECTRIC ENERGY science of method, 2008,26 (1):63~66.) calculated using chaos optimization
Method optimizes calculating to long-term reservoir operation problem in step power station.But chaotic optimization algorithm also has following deficiency:Only
The optimization problem of dividing value is measured suitable for unconstrained optimization and change;It is only applicable to single-object problem;Using initial value as initially
Optimal solution, iteration efficiency have much room for improvement;Ergodic means larger iterations, program runtime length.
The content of the invention
It is an object of the invention to overcome above-mentioned deficiency, there is provided a kind of basin water based on multi-Objective Chaotic genetic algorithm
Resource optimization configuration method, the inverting of the ergodic of chaos and genetic algorithm is coupled together, it is therefore an objective to overcome chaos optimization
Algorithm requires that optimization problem single goal, program runtime are long and genetic algorithm has dependence, optimal solution to problem characteristic
It is unstable, deviate it is larger the problems such as so that water resource best configuration scheme selection process is highly efficient superior.
Multi-Objective Chaotic genetic Optimization Algorithm (Multi-objective Chaotic Genetic Algorithm,
MCGA it is) to be coupled chaos optimization, genetic algorithm and multi-objective decision-making.Realize that the algorithm there are two kinds of approach, it is a kind of
It is that multi-objective optimization question is converted into single-objective problem using multi-objective decision-making, is solved using Chaos Genetic Algorithm;Separately
A kind of is the collective search characteristic using genetic algorithm, using multiple individual methods in processing colony simultaneously, to search space
In multiple solutions assessed.The optimal solution obtained using Chaos Genetic Algorithm keeps stable optimum state, and each run obtains
The achievement arrived is substantially close, is all sufficiently close to optimal solution, and the optimal solution obtained using traditional genetic algorithm have it is unstable
Property, although its solution is all to approach optimal solution, sometimes deviate larger.Therefore, the ergodic and genetic algorithm of chaos are utilized
The Chaos Genetic Algorithm that inverting is coupled together undoubtedly has more superiority in searching process than simple genetic algorithm.
The object of the present invention is achieved like this:
The present invention is achieved by the following technical solutions:A kind of basin water resources optimization based on multi-Objective Chaotic genetic algorithm
Collocation method, comprise the following steps:
Step 1:Basin water resources system essential information is obtained, including:Basin basic condition and water resources characteristic, basin subregion
Generalization, basin gross water requirement, basin total supply;
Step 2:Establish and Optimality Criteria, water balance constraint, water are up to society, economic and ecological environment comprehensive benefit
Reservoir filling capacity consistency, the constraint of reservoir letdown flow, the constraint of water source available water, the constraint of water source conveyance power of water, user need water energy
Force constraint, variable nonnegativity restrictions are the multiple target water resource optimal allocation mathematical modeling of constraints, and carry out allocation models ginseng
Digit rate is determined;
Step 3:Multi-Objective Chaotic genetic algorithm is applied to above-mentioned water resource optimal allocation mathematical modeling, generation Pareto is most
Excellent disaggregation, i.e. water resource optimal allocation alternative collection;
Step 4:On the basis of water resource optimal allocation alternative collection, determined using chaotic neural network comprehensive evaluation model
Water resource optimal allocation optimal equalization scheme.
Further, the step 3 specifically includes:
Step 3-1:Restriction condition treat, using non-differentiability Exact Penalty Function Method, certain penalty factor is selected, constructs penalty term,
Restricted problem is converted into unconstrained optimization problem, now obtains the optimization problem of continuous object:
min f(x1,x2,L,xN)xi∈[ai,bi] i=1,2, L, N (3)
In formula, xiFor decision variable, ai、biFor decision variable value bound;
Step 3-2:Parameter setting, determine the number N of the decision variable and span [a of variablei,bi], determine genetic algorithm
Initial population scale M, termination iterations T, the crossover probability P of genetic algorithmcWith mutation probability Pm;
Step 3-3:Population is initialized, chooses n different initial values, it is different to can obtain n track by Logistic mappings
Chaos Variable sequence εi,j, i=1,2, L, N, j=1,2, L, M, Logistic mapping:
εi,k+1=μ εi,k(1-εi,k) (4)
In formula, μ is controling parameter, if 0≤εI, 1During≤1, μ=4, system is completely in chaos state, has the institute of chaotic motion
There is feature;Again by Logistic map caused by chaos sequence be amplified to by formula (3) span of optimized variable, in this, as
Initial population:
xi,j=ai+(bi-ai)εi,j(i=1,2, L, N, j=1,2, L, M) (5)
In formula, εi,jFor Chaos Variable sequence;
Step 3-4:External storage archives are constructed, determine the maximum-norm of archives, the external storage archives, for advancing for
Fitness value is preferably individual, avoids it from being destroyed because of the strong randomness of genetic algorithm, finally therefrom obtains Noninferior Solution Set;
Step 3-5:According to target the number of function is split to population, distributes a sub- object function to each sub-group, respectively
Individual sub- object function independently carries out selection operation in corresponding sub-group;
Step 3-6:Appropriate fitness function is selected, calculates the fitness value of specific item scalar functions corresponding to each sub-group;
Step 3-7:Select the high individual of fitness value to form new sub-group, by the colony of all new compositions be merged into one it is complete
Whole colony, is intersected and mutation operation, forms population of future generation;
Step 3-8:Calculate new fitness value and be adjusted, then colony is ranked up by fitness value, will wherein fit
Response is worst 10% to be replaced, and carries out File Maintenance;
Step 3-9:If meeting to terminate iterated conditional, Pareto optimal solution sets are exported, otherwise gives and works as fitness in former generation colony
Corresponding optimized variable adds a chaotic disturbance, and is mapped as optimized variable by carrier method, is transferred to step 3-6.
Further, in above-mentioned steps 3-1, the non-differentiability Exact Penalty Function Method, restricted problem is converted into without about
Beam optimization problem, avoid calculate on sequential property, directly make constrained optimization solution and penalty function some minimal point accurately
Unanimously, conversion formula is:
P (x)=f (x)+σ (c (x)) (2)
In formula, f (x) is the object function of former problem, and σ (c (x)) is penalty term, and c (x) is the constraints of former problem.
Further, in above-mentioned steps 3-8, the File Maintenance is specially:When the number solved in archives reaches regulation
During value, archives are safeguarded, to determine that can new explanation be added in archives, and if new explanation is added in archives after, from it
For middle which solution of removal to ensure that archives size is no more than setting all the time, external storage File Maintenance mainly passes through external storage
Collection increase rule and external storage collection reduce rule and determine that can new explanation be added in archives.
Wherein, external storage collection increase rule be approximation theory non-domination solution precision index be advantageous to reality
One of both existing population diversity indexs just have an opportunity to be added into external storage collection better than his father's individual;
It is to concentrate each individual to assign age attribute to external storage that the external storage collection, which reduces rule, is assigned to when adding first
0, circulate and remain in the set if completing one and developing, the age increases by 1, if certain individual age exceedes max age
Limitation, or certain individual adaptive value are minimum, then reduce rule and concentrate the deletion individual from external storage.
Further, in above-mentioned steps 3-9, the termination iterated conditional is:The average value of fitness and maximum it
Difference is less than allowable error, reaches termination iterations, until the difference of the front and rear fitness average value calculated twice is less than in advance
The small positive number of some given.
In step 4, water resource optimal allocation optimal equalization side is determined using chaotic neural network comprehensive evaluation model
Case, specifically include following steps:
Step 4-1:Each parameter of neutral net is set:Input layer, hidden layer and output layer neuron node number N1、N2And N3;
Step 4-2:Water resource optimal allocation Effect Evaluation Index System is established, standardization is done to each index, by each scheme
Input value R=[r of the quantized value of evaluation index property value as neutral netp], and determine neutral net desired output B=
[b1,b2,L,bp]T, i.e. input pattern (R, B), wherein, p is scheme number;
Step 4-3:By neutral net and each scheme input value and desired output of determination, the neutral net overall situation is determined most
Excellent weights, i.e., each most reasonable weights of evaluation index;
Step 4-4:With the most reasonable weights of each evaluation index, chaotic neural network comprehensive evaluation model is built, then each scheme is referred to
Evaluations matrix R=[r after mark standardizationp] input chaotic neural network comprehensive evaluation model calculated, obtain each scheme
Value of utility { PVk(k=1,2, L, p), then on this basis, according to Preference Theory, synthesis is ranked up to scheme preferably, i.e.,
PV*=max { PVkCorresponding to scheme be preferred plan.
In step 4-2, the determination of the neutral net desired output:Respect former evaluation expertise and evaluation is tied
Fruit, or determined using the evaluation method of multi-attribute-utility theories of value and Preference Theory method.
In step 4-3, the determination of neutral net global optimum weights:Mapped using Logistic and produce chaos change
Amount, obtain network weight vectorInput (R, B) and network weight coefficientAccording to the Mechanics in Chaotic Neural Networks calculating network phase
Hope output bpWith network reality output op;The correction error of output layer is calculated by error function method, and it is reverse using network error
Propagate, constantly modification adjustment weight parameter, to obtain neutral net global optimum weights, error function E:
In formula, EpFor scheme p error;bpFor scheme p desired output, opFor neutral net network output valve;X is sample,
W is weighted value;F (x, W) is the nonlinear function of neutral net description, in the case where network structure determines, error letter in formula
Number E is the energy function using weight as primary variables.
Beneficial effect
Compared with prior art, advantageous effects of the invention are:
(1) the multiple-objection optimization configuration requirement of basin water resources complication system is met;
(2) take full advantage of the ergodic of chaotic optimization algorithm, randomness, it is regular find the optimal solution of the overall situation, chaos is excellent
Change method belongs to the direct random search of no derivative, and it is less to treat the characteristic requirements of optimization object function, avoids gradient search
Require that object function and constraints are continuously differentiable difficulties in method, substantially increase the efficiency of algorithm;
(3) multi-Objective Chaotic genetic algorithm is proposed, has coupled inverting and the multiple target of the ergodic, genetic algorithm of chaos optimization
Decision-making technic, solves chaotic optimization algorithm requirement optimization problem single goal without constraint and iterations multiprogram long operational time
And genetic algorithm has the problems such as dependence, optimal solution are unstable, deviation is larger to problem characteristic;
(4) noninferior solution of algorithm acquisition is retained using the external archive of Dynamic Updating Mechanism, passing through external storage collection increases rule
Reduce rule with external storage collection and determine that can new explanation be added in archives, and if new explanation is added to archives after, which is therefrom removed
A little solutions ensure that archives size is no more than setting all the time, ensure that noninferior solution individual is evenly distributed with this, have good diversity,
Accelerate global convergence;
(5) propose that chaotic neural network comprehensive evaluation model concentrates selection preferred plan from water resource optimal allocation alternative,
Enhance the ability of making decisions on one's own of Programming for Multiobjective Water Resources configuration system.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention;
Fig. 2 is multi-Objective Chaotic genetic algorithm calculation flow chart of the present invention;
Fig. 3 is chaotic neural network overall merit flow chart of the present invention;
Fig. 4 lifts current domain water resource system subregion schematic diagram for the present invention;
Fig. 5 lifts current domain water resource system sketch network figure for the present invention.
Embodiment
With reference to specific embodiment, clear, complete description is carried out to technical solution of the present invention.
The present invention requires optimization problem single goal without constraint and iterations multiprogram for traditional chaotic optimization algorithm
Long operational time and traditional genetic algorithm have the problems such as dependence, optimal solution are unstable, deviation is larger to problem characteristic, carry
For a kind of basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm, this method has fully coupled chaos optimization
Ergodic, genetic algorithm inverting and multi-objective decision-making so that optimal solution keeps stable optimum state, realizes and calculates
Method ability of searching optimum, and on the basis of water resource optimal allocation alternative collection, using chaotic neural network overall merit mould
Type independently selects water resource optimal equalization allocation plan, realizes that basin water resources multiple-objection optimization configures, referring to Fig. 1 to Fig. 3, its
In, Fig. 1 is flow chart of the method for the present invention;Fig. 2 is multi-Objective Chaotic genetic algorithm calculation flow chart of the present invention;Fig. 3 is this hair
Bright chaotic neural network overall merit flow chart.
A kind of basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm of the present invention, including following step
Suddenly:
Step 1:Basin water resources system essential information data are obtained, including:Basin basic condition and water resources characteristic, basin
Subregion is generally changed, basin gross water requirement, basin total supply.
Wherein, basin basic condition includes physical geography, social economy, hydrometeorology, trunk river reservoir etc.;Water resource
Feature includes distribution of water resources feature, situation of water resource use;Basin gross water requirement is divided into economic society water requirement and ecological ring
Border water requirement, economic society water requirement includes life again needs water, agricultural to need water, industrial water demand, construction industry and the tertiary industry to need water,
Ecological environment water demand includes ecology narration and water demand for natural service outside river course in river course, and water demand for natural service includes ecological water demand of rivers outside river course
With urban ecological demand water;Basin total supply is divided into earth's surface water supply and groundwater supply, and terrestrial reference output includes water storage project and supplied water
Measure and draw water lift engineering water supply amount.
Step 2:Establish and Optimality Criteria is up to society, economic and ecological environment comprehensive benefit, water balance is about
Beam, reservoir filling capacity consistency, the constraint of reservoir letdown flow, the constraint of water source available water, the constraint of water source conveyance power of water, Yong Huxu
Outlet capacity constraint, the multiple target water resource optimal allocation mathematical modeling that variable nonnegativity restrictions is constraints:
In formula, opt represents that optimization direction, including minimax direction, n represent the number of targets of water resource optimal allocation, F (x) tables
Society, the object function of economic and ecological environment comprehensive benefit maximum are shown as, i, k, j are respectively independent water source, basin
Region and user's ordinal number, xijFor user's output;Vt、Vt+1Respectively at the beginning of the reservoir t periods and period Mo pondage;
QintFor reservoir t periods average Incoming water quantity;QouttFor the average outbound water of t periods reservoir, including supply water, irrigate, generating electricity and
Abandon water;QstWater, including evaporation and seepage are lost for the reservoir t periods;Respectively the reservoir t periods allow most
Small and maximum water-storage;qminFor the minimum vent flow (such as shipping, ecology water) of mining under reservoir requirement;For independent water source
I available waters;For the maximum conveyance power of water at k sub-district i water sources;Represent minimum, the maximum of k sub-district j users
Water requirement.
Then allocation models parameter calibration is carried out, specifically depending on the situation of basin.
Step 3:Water resource optimal allocation mathematical modeling is solved using multi-Objective Chaotic genetic algorithm, generation Pareto is most
Excellent disaggregation, i.e. water resource optimal allocation alternative collection.Specifically include (see Fig. 2):
Step 3-1:The constraints that multiple target water resource optimal allocation mathematical modeling is established in step 2 is handled.Utilize
Non-differentiability Exact Penalty Function Method, certain penalty factor is selected, construct penalty term, restricted problem is converted into unconstrained optimization and asked
Topic, conversion formula are:
P (x)=f (x)+σ (c (x)) (2)
In formula, f (x) is the object function of former problem, and σ (c (x)) is penalty term, and c (x) is the constraints of former problem.
Now obtain the optimization problem of continuous object:
min f(x1,x2,L,xN)xi∈[ai,bi] i=1,2, L, N (3)
In formula, xiFor decision variable, ai、biFor decision variable value bound.
Step 3-2:Setup parameter.Determine the number N of the decision variable and span [a of variablei,bi], it is determined that heredity is calculated
The initial population scale M of method, termination iterations T, the crossover probability P of genetic algorithmcWith mutation probability Pm。
Step 3-3:Population is initialized, chooses n different initial values, n track can obtain not by Logistic mappings
Same Chaos Variable sequence εi,j, i=1,2, L, N, j=1,2, L, M, Logistic mapping:
εi,k+1=μ εi,k(1-εi,k) (4)
In formula, μ is controling parameter, if 0≤εI, 1During≤1, μ=4, system is completely in chaos state, has the institute of chaotic motion
There is feature, therefore can be as the Chaos Variable iterative equation in optimized algorithm.
Again by Logistic map caused by chaos sequence be amplified to by formula (5) span of optimized variable, made with this
For initial population:
xi,j=ai+(bi-ai)εi,j(i=1,2, L, N, j=1,2, L, M) (5)
In formula, εi,jFor Chaos Variable sequence.
Step 3-4:External storage archives are constructed, determine the maximum-norm of archives, external storage archives are used to advance for
Fitness value is preferably individual, avoids it from being destroyed because of the strong randomness of genetic algorithm, finally therefrom obtains Noninferior Solution Set.
Step 3-5:According to target the number of function is split to population, and a sub-goal letter is distributed to each sub-group
Number, each specific item scalar functions independently carry out selection operation in corresponding sub-group.
Step 3-6:Appropriate fitness function is selected, calculates the fitness value of specific item scalar functions corresponding to each sub-group.
Step 3-7:Select the high individual of fitness value to form new sub-group, the colony of all new compositions is merged into one
Individual complete colony, is intersected and mutation operation, forms population of future generation.
Step 3-8:Calculate new fitness value and carry out File Maintenance.Specifically include:Calculate new fitness value and progress
Adjustment, is then ranked up by fitness value to colony, 10% is replaced wherein fitness is worst, and carry out archives dimension
Shield.Wherein File Maintenance is specially:When the number solved in archives reaches setting, archives are safeguarded, it is new to determine
Can solution be added in archives, and if new explanation is added in archives after, remove which solution therefrom to ensure archives size all the time
No more than setting.External storage File Maintenance mainly reduces rule by external storage collection increase rule and external storage collection
Determine that can new explanation be added in archives;
Wherein, external storage collection increase rule be approximation theory non-domination solution precision index with to be advantageously implemented population various
Property one of both indexs better than his father's individual, just have an opportunity to be added into external storage collection;
It is to concentrate each individual to assign age attribute to external storage that external storage collection, which reduces rule, and 0 is assigned to when adding first,
Circulate and remain in the set if completing one and developing, age increase by 1, if certain individual age is more than max age limit
System, or certain individual adaptive value are minimum, then are concentrated from external storage and delete the individual.
Step 3-9:If meet to terminate iterated conditional:The average value of fitness and the difference of maximum are less than allowable error,
Reach termination iterations, until the difference of the front and rear fitness average value calculated twice is small just less than some previously given
Number, then Pareto optimal solution sets are exported, otherwise give and work as fitness in former generation colony and correspond to optimized variable and add a chaotic disturbance, and lead to
Cross carrier method and be mapped as optimized variable, be transferred to step 3-6.
Step 4:On the basis of water resource optimal allocation alternative collection, using chaotic neural network comprehensive evaluation model
Determine water resource optimal allocation optimal equalization scheme.Specifically include following steps (see Fig. 3):
Step 4-1:Each parameter of neutral net is set:Input layer, hidden layer and output layer neuron node number N1、N2And N3。
Step 4-2:Water resource optimal allocation Effect Evaluation Index System is established, standardization is done to each index, will be each
Input value of the quantized value of evaluating indexesto scheme property value as neutral netAnd determine neutral net desired output
Value B=[b1,b2,L,bp]T, i.e. input pattern (R, B), wherein, p is scheme number.Neutral net desired output is usually to respect
Original evaluation expertise and evaluation result, it can also use the evaluation method of multi-attribute-utility theories of value and Preference Theory method true
It is fixed.
Step 4-3:By neutral net and each scheme input value and desired output of determination, determine that neutral net is complete
Office's best initial weights, i.e., each most reasonable weights of evaluation index;Further comprise:Mapped using Logistic and produce Chaos Variable, obtained
To network weight vectorInput (R, B) and network weight coefficientAccording to neural computing network desired output bpAnd network
Reality output op;The correction error of output layer is calculated by error function method, and utilizes network error backpropagation, constantly modification
Weight parameter is adjusted, to obtain neutral net global optimum weights, error function E:
In formula, EpFor scheme p error;bpFor scheme p desired output, opFor neutral net network output valve;X is sample,
W is weighted value;F (x, W) is the nonlinear function of neutral net description, in the case where network structure determines, error letter in formula
Number E is the energy function using weight as primary variables.
Step 4-4:With the most reasonable weights of each evaluation index, chaotic neural network comprehensive evaluation model is built, then by each side
Evaluations matrix after case criterionInput chaotic neural network collective model is calculated, and obtains the effect of each scheme
With value { PVk, then on this basis, according to Preference Theory, comprehensive preferred, i.e. PV is ranked up to scheme*=max { PVkRight
The scheme answered is preferred plan.
Embodiment
Now lifted by Hubei Province exemplified by current domains Programming for Multiobjective Water Resources distributes rationally, illustrate the validity and rationally of inventive method
Property.It is the tributary of the Changjiang river one to lift current domains, mainstream total length 170.4km, drainage area 4367.6km2.It is existing large, medium and small to lift current domain
293, all kinds of reservoirs of type, the m of aggregate storage capacity 15.25 hundred million3, the m of effective storage 8.64 hundred million3, including small reservoir, output account for storage draw carry it is total
The 74.2% of output.Current domain will be lifted in this research and is generalized as 9 intake areas (see Fig. 4), current domain water resource of mutually attending an imperial examination
System sketch network figure (see Fig. 5).According to current domain water source supply area situation is lifted, across the basin water source in this area is public
Water mainstream is is lifted in water source, and independent water source can be divided into two kinds of surface water and groundwater, and water user is urban life, life in the countryside, agriculture
Industry water, industry, construction industry and the tertiary industry and the class of Eco-environmental Water Consumption six.
The present invention is using each user's output of normal flow year (fraction P=90%) as decision variable, economic, social, ecological ring
Border comprehensive benefit is up to target, constrained with water balance, reservoir filling capacity consistency, reservoir letdown flow constraint, water source can
Output constraint, water source conveyance power of water constraint, user need outlet capacity constraint, variable nonnegativity restrictions be constraints, using more mesh
Mark Chaos Genetic Algorithm carries out lifting current domain water resource optimal allocation.
Objectives function is as follows:
(1) economic benefit target:Water resource is maximum using the net contribution value of GDP in watershed in basin,
In formula, GDPw(k) the net contribution value for water resource optimal allocation to kth sub-district GDP, using between GDP and water consumption
Linear relationship represents;
(2) social benefit target:Water supply fairness degrees of coordination is maximum in basin,
In formula, f2' it is department's water supply Gini coefficient, reflect the interdepartmental fairness of water resource optimal allocation;f2" be
Basin water supply Gini coefficient, reflect the fairness between each sub-district of water resource optimal allocation;
(3) ecological environment benefit target:Each sub-district BOD discharge capacitys sum in region is minimum,
In formula,For the content of k sub-district j Subscriber Unit wastewater discharge mesophytization oxygen demands (BOD), mg/L;For k sub-districts j
User's sewage discharge coefficient.
Parameter rating of the model is carried out, calculates and lifts current domain gross water requirement and total available water.In Matlab software programming rings
Solved under border.Four Water Resources Allocation sides corresponding to finally being randomly selected from the water resource optimal allocation scheme noninferior set of generation
Case V1、V2、V3、V4Optionally, composition lifts current domain water resource optimal allocation alternative collection (being shown in Table 1).
Table 1 lifts current domain water resource optimal allocation alternative collection (P=90%) unit:Hundred million m3
On the basis of above-mentioned water resource optimal allocation alternative collection, determined using chaotic neural network comprehensive evaluation model
Water Resources Allocation preferred plan, specific achievement of evaluating are shown in Table 2.
The Mechanics in Chaotic Neural Networks of table 2 is to allocation plan overall merit achievement
To each scheme, water supply of each water source to each user can be sub-divided into water resources regionalization.Detained among total supply water
Except ecological environment supplies water in river course, obtain under the conditions of lifting current domain P=90%, act current domain water resource optimal allocation achievement (see
Table 3).
Table 3 lifts current domain water resource optimal allocation achievement (P=90%-V1 schemes) unit:Ten thousand m3
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that not taking off
In the case of principle and objective from the present invention a variety of change, modification, replacement and modification, this hair can be carried out to these embodiments
Bright scope is limited by claim and its equivalent.
Claims (9)
1. a kind of basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm, it is characterised in that including following
Step:
Step 1:Basin water resources system essential information is obtained, including:Basin basic condition and water resources characteristic, basin subregion
Generalization, basin gross water requirement, basin total supply;
Step 2:Establish and Optimality Criteria, water balance constraint, water are up to society, economic and ecological environment comprehensive benefit
Reservoir filling capacity consistency, the constraint of reservoir letdown flow, the constraint of water source available water, the constraint of water source conveyance power of water, user need water energy
Force constraint, variable nonnegativity restrictions are the multiple target water resource optimal allocation mathematical modeling of constraints, and carry out allocation models ginseng
Digit rate is determined;
Step 3:Multi-Objective Chaotic genetic algorithm is applied to above-mentioned water resource optimal allocation mathematical modeling, generation Pareto is most
Excellent disaggregation, i.e. water resource optimal allocation alternative collection;
Step 4:On the basis of water resource optimal allocation alternative collection, determined using chaotic neural network comprehensive evaluation model
Water resource optimal allocation optimal equalization scheme.
2. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 1, it is special
Sign is that the step 3 specifically includes:
Step 3-1:Restriction condition treat, using non-differentiability Exact Penalty Function Method, certain penalty factor is selected, constructs penalty term,
Restricted problem is converted into unconstrained optimization problem, now obtains the optimization problem of continuous object:
minf(x1,x2,L,xN)xi∈[ai,bi] i=1,2, L, N (3)
In formula, xiFor decision variable, ai、biFor decision variable value bound;
Step 3-2:Parameter setting, determine the number N of the decision variable and span [a of variablei,bi], determine genetic algorithm
Initial population scale M, genetic algorithm termination iterations T, crossover probability PcWith mutation probability Pm;
Step 3-3:Population is initialized, chooses n different initial values, it is different to can obtain n track by Logistic mappings
Chaos Variable sequence εi,j, i=1,2, L, N, j=1,2, L, M, Logistic mapping:
εi,k+1=μ εi,k(1-εi,k) (4)
In formula, μ is controling parameter, if 0≤εI, 1During≤1, μ=4, system is completely in chaos state, has the institute of chaotic motion
There is feature;Again by Logistic map caused by chaos sequence be amplified to by formula (5) span of optimized variable, in this, as
Initial population:
xi,j=ai+(bi-ai)εi,j(i=1,2, L, N, j=1,2, L, M) (5)
In formula, εi,jFor Chaos Variable sequence;
Step 3-4:External storage archives are constructed, determine the maximum-norm of archives, the external storage archives, for advancing for
Fitness value is preferably individual, avoids it from being destroyed because of the strong randomness of genetic algorithm, finally therefrom obtains Noninferior Solution Set;
Step 3-5:According to target the number of function is split to population, distributes a sub- object function to each sub-group, respectively
Individual sub- object function independently carries out selection operation in corresponding sub-group;
Step 3-6:Appropriate fitness function is selected, calculates the fitness value of specific item scalar functions corresponding to each sub-group;
Step 3-7:Select the high individual of fitness value to form new sub-group, by the colony of all new compositions be merged into one it is complete
Whole colony, is intersected and mutation operation, forms population of future generation;
Step 3-8:Calculate new fitness value and be adjusted, then colony is ranked up by fitness value, will wherein fit
Response is worst 10% to be replaced, and carries out File Maintenance;
Step 3-9:If meeting to terminate iterated conditional, Pareto optimal solution sets are exported, otherwise gives and works as fitness in former generation colony
Corresponding optimized variable adds a chaotic disturbance, and is mapped as optimized variable by carrier method, is transferred to step 3-6.
3. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 2, its feature
It is, in step 3-1, the non-differentiability Exact Penalty Function Method, restricted problem is converted into unconstrained optimization problem, avoids counting
The sequential property counted in, directly make constrained optimization solution and penalty function some minimal point it is accurately consistent, conversion formula is:
P (x)=f (x)+σ (c (x)) (2)
In formula, f (x) is the object function of former problem, and σ (c (x)) is penalty term, and c (x) is the constraints of former problem.
4. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 2, its feature
It is, in step 3-8, the File Maintenance is specially:When the number solved in archives reaches setting, archives are carried out
Safeguard, to determine that can new explanation be added in archives, and if new explanation is added in archives after, remove which solution therefrom to ensure
Archives size is no more than setting all the time, and external storage File Maintenance mainly increases rule by external storage collection and outside is deposited
Preserve reduction rule and determine that can new explanation be added in archives.
5. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 4, its feature
Be, external storage collection increase rule be approximation theory non-domination solution precision index with to be advantageously implemented population more
One of both sample indexs just have an opportunity to be added into external storage collection better than his father's individual;
It is to concentrate each individual to assign age attribute to external storage that the external storage collection, which reduces rule, is assigned to when adding first
0, circulate and remain in the set if completing one and developing, the age increases by 1, if certain individual age exceedes max age
Limitation, or certain individual adaptive value are minimum, then reduce rule and concentrate the deletion individual from external storage.
6. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 2, its feature
It is, in step 3-9, the termination iterated conditional is:The average value of fitness and the difference of maximum are less than allowable error, reach
To iterations is terminated, until the difference of the front and rear fitness average value calculated twice is less than the small positive number of some previously given.
7. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 1, its feature
It is, in step 4, water resource optimal allocation optimal equalization scheme is determined using chaotic neural network comprehensive evaluation model, has
Body comprises the following steps:
Step 4-1:Each parameter of neutral net is set:Input layer, hidden layer and output layer neuron node number N1、N2And N3;
Step 4-2:Water resource optimal allocation Effect Evaluation Index System is established, standardization is done to each index, by each scheme
Input value R=[r of the quantized value of evaluation index property value as neutral netp], and determine neutral net desired output B=
[b1,b2,L,bp]T, i.e. input pattern (R, B), wherein, p is scheme number;
Step 4-3:By nerve network system and each scheme input value and desired output of determination, determine that neutral net is complete
Office's best initial weights, i.e., each most reasonable weights of evaluation index;
Step 4-4:With the most reasonable weights of each evaluation index, chaotic neural network comprehensive evaluation model is built, then each scheme is referred to
Evaluations matrix R=[r after mark standardizationp] input chaotic neural network comprehensive evaluation model calculated, obtain each scheme
Value of utility { PVk(k=1,2, L, p), then on this basis, according to Preference Theory, synthesis is ranked up to scheme preferably, i.e.,
PV*=max { PVkCorresponding to scheme be preferred plan.
8. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 7, its feature
It is, in step 4-2, the determination of the neutral net desired output:Respect former evaluation expertise and evaluation result, or
Determined using the evaluation method of multi-attribute-utility theories of value and Preference Theory method.
9. the basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm as claimed in claim 7, its feature
It is, in step 4-3, the determination of neutral net global optimum weights:Mapped using Logistic and produce Chaos Variable,
Obtain network weight vectorInput (R, B) and network weight coefficientIt is expected according to Mechanics in Chaotic Neural Networks calculating network defeated
Go out bpWith network reality output op;The correction error of output layer is calculated by error function method, and is reversely passed using network error
Broadcast, constantly modification adjustment weight parameter, to obtain neutral net global optimum weights, error function E:
<mrow>
<mi>E</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>P</mi>
</munderover>
<msub>
<mi>E</mi>
<mi>p</mi>
</msub>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>P</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>b</mi>
<mi>p</mi>
</msub>
<mo>-</mo>
<msub>
<mi>o</mi>
<mi>p</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>P</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>b</mi>
<mi>p</mi>
</msub>
<mo>-</mo>
<mi>f</mi>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>W</mi>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>6</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula, EpFor scheme p error;bpFor scheme p desired output, opFor neutral net network output valve;X is sample,
W is weighted value;F (x, W) is the nonlinear function of neutral net description, in the case where network structure determines, error letter in formula
Number E is the energy function using weight as primary variables.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710624335.4A CN107480813A (en) | 2017-07-27 | 2017-07-27 | Basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710624335.4A CN107480813A (en) | 2017-07-27 | 2017-07-27 | Basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107480813A true CN107480813A (en) | 2017-12-15 |
Family
ID=60597797
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710624335.4A Pending CN107480813A (en) | 2017-07-27 | 2017-07-27 | Basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107480813A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108171413A (en) * | 2017-12-26 | 2018-06-15 | 杭州电子科技大学 | A kind of chemical industrial park emergency resources method for optimizing configuration |
CN108681844A (en) * | 2018-08-01 | 2018-10-19 | 河海大学 | A kind of water diversion project flood water resources utilization risk evaluating method |
CN108681974A (en) * | 2018-05-29 | 2018-10-19 | 中国水利水电科学研究院 | A kind of water resource multidimensional equilibrium allocation method towards Arid Region |
CN108830419A (en) * | 2018-06-15 | 2018-11-16 | 武汉大学 | A kind of Cascade Reservoirs reservoir inflow joint forecasting procedure based on ECC post-processing |
CN109086469A (en) * | 2018-03-09 | 2018-12-25 | 重庆科技学院 | Aluminium electroloysis modeling and optimization method based on recurrent neural network and preference information |
CN109446630A (en) * | 2018-10-23 | 2019-03-08 | 宁夏大学 | Multiple target water resource optimal allocation method based on Hybrid Particle Swarm |
CN109919485A (en) * | 2019-03-06 | 2019-06-21 | 桂林理工大学 | A kind of Multipurpose Optimal Method of the Water Resources Allocation based on NSGA-II |
CN110739045A (en) * | 2019-10-14 | 2020-01-31 | 郑州航空工业管理学院 | Interactive evolution optimization method for personalized recipe design |
CN111210157A (en) * | 2020-01-13 | 2020-05-29 | 上海威派格智慧水务股份有限公司 | Dynamic storage adjusting method for water tank |
CN111932083A (en) * | 2020-07-14 | 2020-11-13 | 黄河勘测规划设计研究院有限公司 | Water resource configuration method and system based on cooperative genetic algorithm |
CN112668909A (en) * | 2020-12-31 | 2021-04-16 | 齐鲁工业大学 | Water resource optimal configuration method and system based on genetic algorithm |
CN112906952A (en) * | 2021-02-04 | 2021-06-04 | 交通银行股份有限公司 | Intelligent scheduling system for bank process tasks |
CN113449935A (en) * | 2021-08-31 | 2021-09-28 | 中国水利水电科学研究院 | Ecological-oriented water resource optimal allocation method |
CN113780768A (en) * | 2021-08-26 | 2021-12-10 | 浙江大学常州工业技术研究院 | Chaotic variation inheritance high-dimensional multi-index comprehensive energy system planning method and system |
CN114154421A (en) * | 2021-12-08 | 2022-03-08 | 中国科学院地理科学与资源研究所 | Regional water resource control management method, device and system |
CN115130791A (en) * | 2022-08-30 | 2022-09-30 | 广东翼景信息科技有限公司 | Unmanned aerial vehicle and vehicle cooperative scheduling method and device for vehicle-mounted intelligent airport |
CN115271437A (en) * | 2022-07-27 | 2022-11-01 | 中国水利水电科学研究院 | Water resource configuration method and system based on multi-decision-making main body |
CN115409387A (en) * | 2022-08-30 | 2022-11-29 | 华中科技大学 | Reservoir optimal scheduling method and system based on improved differential evolution |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529166A (en) * | 2016-11-04 | 2017-03-22 | 河海大学 | Method for regional water-source optimized configuration based on MAEPSO algorithm |
-
2017
- 2017-07-27 CN CN201710624335.4A patent/CN107480813A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529166A (en) * | 2016-11-04 | 2017-03-22 | 河海大学 | Method for regional water-source optimized configuration based on MAEPSO algorithm |
Non-Patent Citations (2)
Title |
---|
赵小强等: "基于混沌遗传算法的多目标决策水资源优化调度", 《第27届中国控制与决策会议》 * |
黄显峰等: "基于混沌神经网络的水资源配置效果综合评价研究", 《变化环境下的水资源响应与可持续利用——中国水利学会水资源专业委员会2009学术年会》 * |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108171413A (en) * | 2017-12-26 | 2018-06-15 | 杭州电子科技大学 | A kind of chemical industrial park emergency resources method for optimizing configuration |
CN108171413B (en) * | 2017-12-26 | 2021-08-10 | 杭州电子科技大学 | Chemical industry park emergency resource allocation optimization method |
CN109086469A (en) * | 2018-03-09 | 2018-12-25 | 重庆科技学院 | Aluminium electroloysis modeling and optimization method based on recurrent neural network and preference information |
CN109086469B (en) * | 2018-03-09 | 2022-11-11 | 重庆科技学院 | Aluminum electrolysis modeling and optimizing method based on recurrent neural network and preference information |
CN108681974A (en) * | 2018-05-29 | 2018-10-19 | 中国水利水电科学研究院 | A kind of water resource multidimensional equilibrium allocation method towards Arid Region |
CN108681974B (en) * | 2018-05-29 | 2021-11-02 | 中国水利水电科学研究院 | Inland arid region oriented multidimensional equilibrium configuration method for water resources |
CN108830419A (en) * | 2018-06-15 | 2018-11-16 | 武汉大学 | A kind of Cascade Reservoirs reservoir inflow joint forecasting procedure based on ECC post-processing |
CN108830419B (en) * | 2018-06-15 | 2023-10-20 | 武汉大学 | Cascade reservoir group-entering flow joint prediction method based on ECC post-processing |
CN108681844B (en) * | 2018-08-01 | 2021-07-02 | 河海大学 | Flood resource utilization risk evaluation method for water diversion project |
CN108681844A (en) * | 2018-08-01 | 2018-10-19 | 河海大学 | A kind of water diversion project flood water resources utilization risk evaluating method |
CN109446630A (en) * | 2018-10-23 | 2019-03-08 | 宁夏大学 | Multiple target water resource optimal allocation method based on Hybrid Particle Swarm |
CN109919485A (en) * | 2019-03-06 | 2019-06-21 | 桂林理工大学 | A kind of Multipurpose Optimal Method of the Water Resources Allocation based on NSGA-II |
CN110739045A (en) * | 2019-10-14 | 2020-01-31 | 郑州航空工业管理学院 | Interactive evolution optimization method for personalized recipe design |
CN110739045B (en) * | 2019-10-14 | 2023-05-30 | 郑州航空工业管理学院 | Interactive evolution optimization method for personalized recipe design |
CN111210157B (en) * | 2020-01-13 | 2023-05-12 | 上海威派格智慧水务股份有限公司 | Dynamic water tank regulating and accumulating method |
CN111210157A (en) * | 2020-01-13 | 2020-05-29 | 上海威派格智慧水务股份有限公司 | Dynamic storage adjusting method for water tank |
CN111932083A (en) * | 2020-07-14 | 2020-11-13 | 黄河勘测规划设计研究院有限公司 | Water resource configuration method and system based on cooperative genetic algorithm |
CN112668909B (en) * | 2020-12-31 | 2022-04-01 | 齐鲁工业大学 | Water resource optimal configuration method and system based on genetic algorithm |
CN112668909A (en) * | 2020-12-31 | 2021-04-16 | 齐鲁工业大学 | Water resource optimal configuration method and system based on genetic algorithm |
CN112906952A (en) * | 2021-02-04 | 2021-06-04 | 交通银行股份有限公司 | Intelligent scheduling system for bank process tasks |
CN113780768A (en) * | 2021-08-26 | 2021-12-10 | 浙江大学常州工业技术研究院 | Chaotic variation inheritance high-dimensional multi-index comprehensive energy system planning method and system |
CN113780768B (en) * | 2021-08-26 | 2024-07-19 | 浙江大学常州工业技术研究院 | Chaotic variation genetic high-dimensionality multi-index comprehensive energy system planning method and system |
CN113449935A (en) * | 2021-08-31 | 2021-09-28 | 中国水利水电科学研究院 | Ecological-oriented water resource optimal allocation method |
CN114154421A (en) * | 2021-12-08 | 2022-03-08 | 中国科学院地理科学与资源研究所 | Regional water resource control management method, device and system |
CN115271437A (en) * | 2022-07-27 | 2022-11-01 | 中国水利水电科学研究院 | Water resource configuration method and system based on multi-decision-making main body |
CN115130791A (en) * | 2022-08-30 | 2022-09-30 | 广东翼景信息科技有限公司 | Unmanned aerial vehicle and vehicle cooperative scheduling method and device for vehicle-mounted intelligent airport |
CN115409387A (en) * | 2022-08-30 | 2022-11-29 | 华中科技大学 | Reservoir optimal scheduling method and system based on improved differential evolution |
CN115130791B (en) * | 2022-08-30 | 2023-01-03 | 广东翼景信息科技有限公司 | Unmanned aerial vehicle and vehicle cooperative scheduling method and device for vehicle-mounted intelligent airport |
CN115409387B (en) * | 2022-08-30 | 2023-04-18 | 华中科技大学 | Reservoir optimal scheduling method and system based on improved differential evolution |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107480813A (en) | Basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm | |
Zolfaghari et al. | Modeling and predicting the electricity production in hydropower using conjunction of wavelet transform, long short-term memory and random forest models | |
Chen et al. | Genetic aided scheduling of hydraulically coupled plants in hydro-thermal coordination | |
Nguyen et al. | An improved slime mold algorithm and its application for optimal operation of cascade hydropower stations | |
Kucukmehmetoglu et al. | International water resources allocation and conflicts: the case of the Euphrates and Tigris | |
Li et al. | Study of optimal allocation of water resources in Dujiangyan irrigation district of China based on an improved genetic algorithm | |
CN114663254B (en) | Water resource-grain-energy-ecological cooperative regulation and control method | |
Wu et al. | Prediction and analysis of water resources demand in Taiyuan City based on principal component analysis and BP neural network | |
Tospornsampan et al. | Optimization of a multiple reservoir system operation using a combination of genetic algorithm and discrete differential dynamic programming: a case study in Mae Klong system, Thailand | |
Rani et al. | Genetic algorithms and their applications to water resources systems | |
Zhou et al. | Integrated optimal allocation model for complex adaptive system of water resources management (II): Case study | |
Li et al. | An improved shuffled frog leaping algorithm and its application in the optimization of cascade reservoir operation | |
Chen et al. | Cascade hydropower system operation considering ecological flow based on different multi-objective genetic algorithms | |
Zou et al. | Quantitative assessment of adaptive measures on optimal water resources allocation by using reliability, resilience, vulnerability indicators | |
Dariane et al. | Comparative analysis of evolving artificial neural network and reinforcement learning in stochastic optimization of multireservoir systems | |
Leela Krishna et al. | Optimal multipurpose reservoir operation planning using Genetic Algorithm and Non Linear Programming (GA-NLP) hybrid approach | |
CN109117998B (en) | Multi-agent configuration method | |
Li et al. | Research on water resources pricing model under the water resources–economic high-quality development coupling system: A case study of Hubei Province, China | |
Kong et al. | Ecological multi-objective joint optimized scheduling of cascade hydropower plants based on improved marine predators algorithm | |
Zhuo et al. | Optimal water allocation method based on the genetic algorithm for a system of a reservoir and two pumping stations | |
Gao et al. | The structure and development of regional ecological water conservancy economic system | |
Li et al. | [Retracted] An Algorithm for Optimal Allocation of Water Resources in Receiving Areas Based on Adaptive Decreasing Inertia Weights | |
Qin et al. | Water Demand Forecast in the Baiyangdian Basin with the Extensive and Low‐Carbon Economic Modes | |
Fang et al. | Multi-objective optimal allocation for regional water and land resources | |
Yang et al. | Optimization of water allocation system at the river basins |
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: 20171215 |
|
WD01 | Invention patent application deemed withdrawn after publication |