CN111767677A - GA algorithm-based cascade pump station group lift optimal distribution method - Google Patents
GA algorithm-based cascade pump station group lift optimal distribution method Download PDFInfo
- Publication number
- CN111767677A CN111767677A CN202010620977.9A CN202010620977A CN111767677A CN 111767677 A CN111767677 A CN 111767677A CN 202010620977 A CN202010620977 A CN 202010620977A CN 111767677 A CN111767677 A CN 111767677A
- Authority
- CN
- China
- Prior art keywords
- pump station
- water
- group
- lift
- water level
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 153
- 230000035772 mutation Effects 0.000 claims description 22
- 238000005086 pumping Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 4
- 238000011144 upstream manufacturing Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 3
- 238000013461 design Methods 0.000 description 21
- 238000004364 calculation method Methods 0.000 description 17
- 238000011160 research Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 230000009194 climbing Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Water Supply & Treatment (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a GA algorithm-based method for optimally distributing the lift of a cascade pump station group, which comprises the following steps of S1, determining a target function, a decision variable and a constraint condition; s2, performing preprocessing on the pump stations in the step pump station group; and S3, solving the objective function by adopting a GA algorithm to obtain the optimal distribution result of the lift of the cascade pump station group. The advantages are that: the pump station group system carries out optimization scheduling under to full operating mode, compares in current mode, and the practicality is higher.
Description
Technical Field
The invention relates to the field of water conservancy system optimization, in particular to a cascade pump station group lift optimization distribution method based on a GA (genetic algorithm).
Background
In order to realize reasonable allocation of water resources, a plurality of large-scale river basin-crossing and series-parallel ladder-level pump station water transfer projects are built at home and abroad. In the projects, the step pump station system plays a great role, but the system has high operation energy consumption and great energy-saving potential due to large installed capacity and high energy consumption.
The optimized dispatching of the lift of the cascade pump station group is always an important problem in the field of water conservancy system optimization. The domestic and foreign scholars do a lot of research and application on the optimized scheduling aspect of the cascade pumping station group, and research and application of a genetic algorithm to carry out optimized research on the design of a plurality of large-scale water distribution systems, and the result shows that the operation cost of the optimized scheme can be reduced by 30-40%. Research provides an optimization algorithm framework based on dynamic programming, and the optimization algorithm framework is applied to a programmable logic controller to improve automatic control of parallel water pumps and achieve the purpose of energy conservation. An optimization model is established by taking the minimum daily water lifting cost of a parallel pump station group as an objective function. In the research, a pump station, power transmission and transformation equipment and a water delivery river channel are taken into consideration as the whole large-scale step pump station system, and an optimized mathematical model is established by taking the minimum total input power of the system as a target. In the current research, economic indicators such as energy consumption, operating cost, pump station efficiency and the like are often selected as scheduling targets of an optimization model. In recent years, the quality of water, evaporation leakage, maintenance cost and the like of water delivery are gradually brought into consideration of optimized scheduling of a step pump station system. In a pump station system, the existence of various decision variables such as pump lift, blade angle, rotating speed, switch state and the like enables the optimized distribution of the pump lift of the cascade pump station group to be a complex nonlinear problem.
At present, for the problem of optimized distribution of the head of the cascade pump station group, the traditional optimization algorithms such as linear programming, nonlinear programming and dynamic programming are generally adopted, so that the problem of dimension disaster is easily caused, the calculation amount is huge, and the generation of results is not facilitated. The existing optimized distribution of the lift of the cascade pump station group is mainly researched aiming at design working conditions and specific working conditions, and the optimized operation of the pump station group system under the non-design working conditions is rarely concerned. Under the influence of factors such as water load change, water supply process fluctuation, pump station unit adjustment and the like, the water delivery system of the cascade pump station group is always operated under a non-designed working condition in an operation stage. The existing research cannot completely meet the actual requirements of engineering. Therefore, the actual operation requirement of the water delivery system of the step pump station is solved, the optimized operation mode of the step pump station group under the non-design working condition needs to be further deeply researched, the lift optimized distribution process under different working conditions is systematically analyzed, and basic data support is provided for the scientific and reasonable scheduling of the water delivery system of the step pump station group.
Disclosure of Invention
The invention aims to provide a GA (genetic algorithm) -based method for optimally distributing the head of a cascade pump station group, so that the problems in the prior art are solved.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a GA algorithm-based lift optimization distribution method for a cascade pump station group comprises the following steps,
s1, determining an objective function, a decision variable and a constraint condition;
s2, performing preprocessing on the pump stations in the step pump station group;
and S3, solving the objective function by adopting a GA algorithm to obtain the optimal distribution result of the lift of the cascade pump station group.
Preferably, the objective function of the m-step pumping station is,
wherein the content of the first and second substances,
for the kth period step pumping station at the flow rate of
Total head of HtotalOverall efficiency under the circumstances; htotalThe total lift of the step pump station;
is the maximum efficiency of the j-th stage pumping station.
Preferably, the decision variables are the water level of the water inlet side and the water level of the water outlet side of each stage of pump station.
Preferably, the constraint conditions are total pump lift constraint of a step pump station, pump lift constraint of a single pump station, water level control interval constraint of water inlet sides of all stages of pump stations and water level control interval constraint of water outlet sides of all stages of pump stations, which are respectively expressed as follows,
wherein h isj,j+1Finding the water head loss of the channel for the j-th pump station and the j + 1-th pump station;
the water level of the water outlet pool of the last stage pump station and the water level of the water inlet pool of the first stage pump station are respectively;
are respectively asThe minimum and maximum lift of the j-th pump station;
respectively setting the minimum and maximum water levels of a water inlet pool of a j-stage pump station;
the minimum and maximum water levels of the outlet pool of the j-th stage pump station are respectively.
Preferably, step S2 is to determine the lowest and highest operating water level intervals of the water inlet and the water outlet of each pump station, and determine the single-machine flow operating interval of the pump station; and acquiring a series of upstream flow and downstream water level values according to the selected water level interval and the selected dispersion step length of the flow interval, and simulating head loss among stages under various feasible flow and water levels.
Preferably, step S3 includes the following,
s31, determining a group of operable working conditions in the pump station, coding the group, and randomly generating a series of flow individuals;
s32, processing the decision variables and the constraint conditions, and calculating the fitness of each individual in the population through an objective function;
s33, judging whether the fitness of the optimal individual reaches a set threshold, or whether the fitness of the optimal individual and the fitness of the group do not rise any more, or whether the iteration times reach preset times, if so, terminating the GA algorithm, and obtaining the optimal distribution result of the lift of the cascade pump station group; if not, sorting the individuals in the group according to the fitness and executing the step S34;
s34, acting a selection operator on the population so as to enable the optimized individuals to be directly inherited to the next generation or generate new individuals through pairing and crossing and then be inherited to the next generation;
s35, acting a crossover operator on the population to replace and recombine partial structures of the two parent individuals to generate a new individual;
s36, acting the mutation operator on the population, judging whether each individual in the population needs to be mutated according to the preset mutation probability, randomly selecting a mutation position for mutation of the individual needing to be mutated to obtain the next generation population, and returning to the step S32.
The invention has the beneficial effects that: 1. the danger of dimension disaster is avoided, and the practical and effective data is generated. 2. The global optimal solution can be directly found by jumping out of the local solution, and the problem of large calculation amount is effectively solved. 3. Has self-organization, self-adaptation and self-learning. When the GA algorithm utilizes the information obtained in the evolution process to self-organize and search, individuals with high fitness have higher survival probability, and a gene structure more suitable for the environment is obtained. 4. The prior optimal scheduling of the cascade pump station group is mainly researched aiming at design working conditions and specific working conditions, and the optimal operation of the pump station group system under the non-design working conditions is rarely concerned.
Drawings
FIG. 1 is a schematic flow chart of a method in an embodiment of the invention;
FIG. 2 shows that the flow of the cascade pump station group after optimization is 72.8m in the embodiment of the invention3Inlet level-outlet level-efficiency curve at/s.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Example one
In the embodiment, as shown in fig. 1, a GA algorithm based method for optimizing head allocation of a cascade pump station group is provided, which includes the following steps,
s1, determining an objective function, a decision variable and a constraint condition;
s2, performing preprocessing on the pump stations in the step pump station group;
and S3, solving the objective function by adopting a GA algorithm to obtain the optimal distribution result of the lift of the cascade pump station group.
In the embodiment, the method firstly researches the hydraulic optimization combination problem among stages of the pump stations forming the step pump station water delivery system on the basis of single-stage optimization operation inside the pump station, and seeks an optimal lift distribution scheme.
In this embodiment, the objective function is to realize the optimal distribution of the lift among the cascade pump stations while satisfying various equality and inequality constraints, so as to maximize the total efficiency of the cascade pump stations. Then, the target function of the m-level cascade pump station is,
wherein the content of the first and second substances,
for the kth period step pumping station at the flow rate of
Total head of HtotalOverall efficiency under the circumstances; htotalThe total lift of the step pump station;
is the maximum efficiency of the j-th stage pumping station.
In this embodiment, the decision variables are the water level on the water inlet side and the water level on the water outlet side of each stage of the pump station. And (3) adopting the water levels of the water inlet side and the water outlet side of each stage of pump station as decision variables, and discretizing the decision variables, wherein the smaller the discrete step length is, the higher the calculation precision is.
In this embodiment, the constraint conditions are total pump head constraint of a step pump station, pump head constraint of a single pump station, water level control interval constraint of the water inlet side of each stage of pump station, and water level control interval constraint of the water outlet side of each stage of pump station, which are respectively expressed as follows,
wherein h isj,j+1Finding the water head loss of the channel for the j-th pump station and the j + 1-th pump station;
the water level of the water outlet pool of the last stage pump station and the water level of the water inlet pool of the first stage pump station are respectively;
the minimum and maximum lift of the j-th pump station are respectively;
respectively setting the minimum and maximum water levels of a water inlet pool of a j-stage pump station;
the minimum and maximum water levels of the outlet pool of the j-th stage pump station are respectively.
In this embodiment, step S2 is specifically to determine the lowest and highest operating water level intervals of the water inlet and the water outlet of each pump station, and determine the single-machine flow operating interval of the pump station; and acquiring a series of upstream flow and downstream water level values according to the selected discrete step length of the water level interval and the flow interval, and simulating head loss among stages under various feasible flow and water levels. The discrete step length is determined according to engineering requirements and requirements, and a specific discrete process is carried out in early preparation.
In the embodiment, the method adopts the GA algorithm to solve, and compared with the traditional hill climbing algorithm, the GA algorithm can jump out the local optimum to find the global optimum point. Furthermore GA algorithms allow the use of very complex fitness functions (i.e. objective functions) and may impose limits on the range of variation of the variables. The GA algorithm corresponds to the content of step S3, specifically including,
s31, determining a set (group P (t)) of operable working conditions in the pump station, coding the set, and randomly generating a series of flow combinations (individuals);
s32, individual evaluation: firstly, processing decision variables and constraint conditions, and then calculating the fitness of each individual in a group through an objective function;
s33, end condition: judging whether the fitness of the optimal individual reaches a set threshold value or not, or whether the fitness of the optimal individual and the fitness of the group are not increased any more or whether the iteration times reach a preset number or not, if so, terminating the GA algorithm, and obtaining an optimal distribution result of the lift of the cascade pump station group; if not, sorting the individuals in the group according to the fitness, and executing the step S34;
s34, selection operation: acting a selection operator on the population, wherein the selection is to directly inherit the optimized individuals to the next generation or generate new individuals through pairing and crossing and then inherit the new individuals to the next generation; the selection operation is established on the basis of fitness evaluation of individuals in a group;
s35, intersection operation: acting a crossover operator (single-point crossover operator) on the population, and replacing and recombining partial structures of two parent individuals to generate a new individual;
s36, mutation operation: and (4) acting the mutation operator on the population, judging whether each individual in the population needs to be mutated according to a preset mutation probability, randomly selecting a mutation position for mutation of the individual needing to be mutated, obtaining a next generation population, and returning to the step (S32). And (t) obtaining a next generation group P (t +1) after selection, crossing and mutation operations of the group P (t).
In this embodiment, in step S32, the higher the fitness, the more suitable the corresponding individual is for the model (target function), the closer the obtained result is to the optimal distribution result, and the more optimal result is selected one time through continuous cyclic sorting to screen out other results, so that the target function can converge quickly to reach the optimal value, and the corresponding optimal distribution result is obtained. The fitness is determined by an efficiency coefficient, and the larger the coefficient is, the larger the fitness is, and the smaller the fitness is, otherwise, the smaller the fitness is.
In this embodiment, the optimal individual is a representative, and the model automatically determines whether the optimal individual is reached through calculation according to the above-mentioned conditions, such as the objective function, the decision variable, the constraint condition, and the discrete range. Namely, the optimal individual is determined by comparing the fitness.
Example two
In this embodiment, the method of the present invention is specifically described in the north water conveying section of the project of qi Huai river.
1. Determining an objective function
The objective function is to realize the optimal distribution of the lift between the cascade pump stations while satisfying various equality and inequality constraints so as to maximize the total efficiency of the cascade pump stations. The objective function of the 5-step cascade pump station is as follows:
in the formula:
for the kth period step pumping station at the flow rate of
Total head of HtotalOverall efficiency under the circumstances; htotalThe total lift of the step pump station;
is the maximum efficiency of the j-th stage pumping station.
2. Determining decision variables
And adopting the water levels of the water inlet side and the water outlet side of each stage of pump station as decision variables. For discretization of the decision variable, the smaller the discrete step length is, the higher the calculation accuracy is.
3. Determining constraints
The constraint conditions comprise step total lift constraint, single pump station lift constraint and water level control interval constraint of water inlet and outlet sides of each stage of pump station, and mathematical expressions are respectively shown as the following formulas.
In the formula: h isj,j+1Finding the water head loss of the channel for the j-th pump station and the j + 1-th pump station;
the water level of the water outlet pool of the last stage pump station and the water level of the water inlet pool of the first stage pump station are respectively;
the minimum and maximum lifts of the j-th pump station are respectively;
respectively the minimum water level and the maximum water level of a water inlet pool of a j-stage pump station;
the minimum and maximum water levels of the outlet pool of the j-th stage pump station are respectively.
4. Pretreatment of
Firstly, selecting design working conditions, wherein the water level of the water inlet side of a first-stage (west- (28125;) river) pump station is 17.4m, the water level of the water outlet side of a last-stage (Longde) pump station is 32.3m, the water level of the water outlet side of a last-stage pump station-the water level of the water inlet side of a first-stage pump station obtain the net lift of a step, the west- (28125;) river pump station designs the water delivery flow rate to be 85m3(s) leather village south Pumping station design Water transfer flow of 80m3Water delivery flow rate of 80m designed for northriver pump station3The design water delivery flow of the Zhuji pump station is 55m3The designed water delivery flow of the Longde pump station is 45m3/s。
Secondly, selecting an off-design working condition, wherein the off-design working condition operation of the water conveying system of the step pump station at the north conveying section of river water takes the whole step net lift (namely, west 28125; water inlet side control water level of the river pump station and water outlet side control water level difference value of the Longde pump station) as a constraint condition, six water inlets are arranged in the water conveying system, and the total water inlet amount is 61m3And/s, respectively binding each water intake to a corresponding river section in calculation, calculating the water loss of the river channel and the head loss, and simultaneously calculating the water loss caused by the water intake, and respectively optimizing west 28125and the lift distribution of a river, a river village south, a west name of a river in Anhui Province north river, a Zhu set and a Longde pump station on the basis of the water loss and the head loss, wherein west 28125is firstly dispersed by taking 0.1m as a step length for a water level WS0(16.4-19.9m) at the water inlet side of the river pump station, and then the WS5(31.8-32.4m) at the water outlet side of the Longde pump station is dispersed by taking 0.1m as a step length to form 37 × 23 851 step net lift working condition points, and then the 5106 working condition points are calculated by combining 6 working condition points of different unit distribution flow.
5. Model solution
And solving by adopting a GA algorithm. Compared with the traditional hill climbing algorithm, the GA algorithm can jump out of local optima and find out a global optima. Furthermore, the legacy GA algorithm allows the use of very complex fitness functions (otherwise known as target functions) and may impose limits on the range of variation of the variables. The concrete steps of model solution are as follows:
a) a set of operable conditions (group P (t)) of the pump station is determined and encoded, and a series of flow combinations (individuals) are randomly generated.
b) Individual evaluation: firstly, processing constraint conditions and decision variables, and then calculating the fitness of each individual in the population through the objective function, namely the fitness function.
c) Selecting and operating: the selection operator is applied to the population. The purpose of selection is to inherit optimized individuals directly into the next generation or to create new individuals by pairwise crossing before inheriting into the next generation. The selection operation is based on fitness evaluation of the individuals in the population.
d) And (3) cross operation: applying a crossover operator (single point crossover operator) to the population; and replacing and recombining partial structures of the two parent individuals to generate a new individual.
e) And (3) mutation operation: and (4) acting mutation operators on the population. Judging whether to perform mutation or not for all individuals in the group according to a preset mutation probability, and randomly selecting a mutation site for the individuals performing mutation to perform mutation. And (t) obtaining a next generation group P (t +1) after selection, crossing and mutation operations of the group P (t).
f) Termination conditions were as follows: and judging whether a termination condition is reached, and terminating the algorithm when the fitness of the optimal individual reaches a given threshold value, or the fitness and the group fitness of the optimal individual do not rise any more, or the iteration times reach a preset algebra.
6. Step pump station section lift optimization distribution calculation result display
(1) Efficient operation scheme under design working condition
The calculation results of the original scheme are shown in Table 1, and the calculation results of the optimized scheme are shown in Table 2, and the calculation results of the design scheme are shown in Table 1
TABLE 2 optimization scheme calculation results
According to calculation, under the condition that the water level of a water inlet tank of a west (28125) river pump station and the water level of a water outlet tank of a Longde pump station are both designed water levels (namely the water level of the west (28125), the total lift of a water delivery system of the river pump station-Longde pump station section is constant), the efficiency of the optimization scheme is 4.96% higher than that of the design scheme under the current situation, the change is very obvious, the optimized scheme plays a role in efficient energy saving and saves a huge economic expenditure.
(2) High-efficiency operation scheme under non-design working condition
The flow rate Q is 72.8m only3And explaining the calculation results of the non-design working conditions when the WS0 is 16.4-19.9m and the WS5 is 31.8-32.4m, wherein the optimized efficiency of the step pumping station system and the optimized lift distribution of each stage of pumping station are respectively shown in tables 3 and 4. At the same time select 72.8m3The results of the calculation of the non-design conditions when the WS0 is 16.4-19.9m and the WS5 is 31.8-32.4m are plotted and shown in fig. 2.
TABLE 3 Cascade Pump station System optimization efficiency (data Unit:%)
| Outlet water level/m inlet water level/m | 16.4 | 16.5 | 16.6 | 16.7 | 16.8 | 16.9 | 17 | 17.1 | 17.2 |
| 31.8 | 90.29 | 90.15 | 89.7 | 88.71 | 89.98 | 87.72 | 87.3 | 87.36 | 84.5 |
| 31.9 | 90.29 | 90.29 | 90.24 | 90.31 | 90.36 | 87.72 | 86.97 | 87.14 | 82.52 |
| 32.0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 32.1 | 90.57 | 90.6 | 90.08 | 90.36 | 89.89 | 87.99 | 87.06 | 87.32 | 84.46 |
| 32.2 | 90.84 | 90.31 | 88.85 | 90.62 | 90.48 | 88.01 | 87.99 | 87.72 | 84.77 |
| 32.3 | 90.72 | 90.5 | 90.84 | 90.57 | 89.56 | 87.9 | 88.06 | 87.79 | 84.81 |
| 32.4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Outlet water level/m inlet water level/m | 17.3 | 17.4 | 17.5 | 17.6 | 17.7 | 17.8 | 17.9 | 18 | 18.1 |
| 31.8 | 83.8 | 84.25 | 80.27 | 80.25 | 74.37 | 75.26 | 75.31 | 74.85 | 68.51 |
| 31.9 | 84.46 | 83.76 | 80.44 | 79.94 | 80.23 | 75.31 | 74.95 | 75.26 | 68.48 |
| 32.0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 32.1 | 84.62 | 84.15 | 75.23 | 80.42 | 79.71 | 75.48 | 75.23 | 75.31 | 68.45 |
| 32.2 | 84.56 | 84.56 | 80.49 | 80.49 | 80.49 | 75.39 | 75.48 | 68.45 | 68.45 |
| 32.3 | 84.33 | 75.64 | 80.57 | 80.21 | 80.7 | 75.43 | 75.28 | 75.28 | 68.6 |
| 32.4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
TABLE 4 optimized distribution of pump station lift at each stage (data unit in TABLE: m)
And the calculation results are comprehensively analyzed and optimized, so that the result after model optimization can further improve the water delivery efficiency of the water delivery system of the cascade pump station, and further reduce the water delivery cost. Along with the increase of the operation time of the pump stations, in the actual operation process of a project, the upstream water flow of the water delivery system of the cascade pump station, the water level of the water inlet side and the water outlet side of each stage of the pump station in the system and the water level line between each channel section are likely to change, so that the performance of the water pump is actually changed greatly, the water delivery system is enabled to operate under the condition of non-design working conditions, and under the condition, the optimized scheduling can be carried out by referring to the result obtained by the specific calculation of the lift optimized distribution model of the water delivery system of the cascade pump station.
By adopting the technical scheme disclosed by the invention, the following beneficial effects are obtained:
the invention provides a GA algorithm-based cascade pump station group lift optimization allocation method, which avoids the danger of dimension disaster and is beneficial to generating actual and effective data. The local solution can be skipped to directly find the global optimal solution, and the problem of large calculation amount is effectively solved. Has self-organization, self-adaptation and self-learning. When the GA algorithm utilizes the information obtained in the evolution process to self-organize and search, individuals with high fitness have higher survival probability, and a gene structure more suitable for the environment is obtained. The prior optimal scheduling of the cascade pump station group is mainly researched aiming at design working conditions and specific working conditions, and the optimal operation of the pump station group system under the non-design working conditions is rarely concerned.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that it is obvious to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and such modifications and improvements should be considered within the scope of the present invention.
Claims (6)
1. A GA algorithm-based cascade pump station group lift optimization distribution method is characterized by comprising the following steps: including the following aspects in that,
s1, determining an objective function, a decision variable and a constraint condition;
s2, performing preprocessing on the pump stations in the step pump station group;
and S3, solving the objective function by adopting a GA algorithm to obtain the optimal distribution result of the lift of the cascade pump station group.
2. A GA algorithm based step pump station group head optimized distribution method according to claim 1, wherein: the objective function of the m-step pumping station is,
wherein the content of the first and second substances,
for the kth period step pumping station at the flow rate of
Total head of HtotalOverall efficiency under the circumstances; htotalThe total lift of the step pump station;
is the maximum efficiency of the j-th stage pumping station.
3. A GA algorithm based step pump station group head optimized distribution method according to claim 1, wherein: and the decision variables are the water level of the water inlet side and the water level of the water outlet side of each stage of pump station.
4. A GA algorithm based step pump station group head optimized distribution method according to claim 3, wherein: the constraint conditions are total pump station lift constraint, single pump station lift constraint, water level control interval constraint of the water inlet side of each stage of pump station and water level control interval constraint of the water outlet side of each stage of pump station, which are respectively expressed as follows,
wherein h isj,j+1Finding the water head loss of the channel for the j-th pump station and the j + 1-th pump station;
the water level of the water outlet pool of the last stage pump station and the water level of the water inlet pool of the first stage pump station are respectively;
the minimum and maximum lift of the j-th pump station are respectively;
respectively setting the minimum and maximum water levels of a water inlet pool of a j-stage pump station;
the minimum and maximum water levels of the outlet pool of the j-th stage pump station are respectively.
5. A GA algorithm based step pump station group head optimized distribution method according to claim 1, wherein: step S2 is specifically that the lowest and highest operation water level intervals of the water inlet and the water outlet of each pump station are determined, and the single machine flow operation interval of the pump station is determined; and acquiring a series of upstream flow and downstream water level values according to the selected water level interval and discrete step length of the flow interval, and simulating head loss among stages under various feasible flows and water levels.
6. A GA algorithm based step pump station group head optimized distribution method according to claim 1, wherein: the step S3 includes the following contents,
s31, determining a group of operable working conditions in the pump station, coding the group, and randomly generating a series of flow individuals;
s32, processing the decision variables and the constraint conditions, and calculating the fitness of each individual in the group through an objective function;
s33, judging whether the fitness of the optimal individual reaches a set threshold, or whether the fitness of the optimal individual and the fitness of the group do not rise any more, or whether the iteration times reach preset times, if so, terminating the GA algorithm, and obtaining the optimal distribution result of the lift of the cascade pump station group; if not, sorting the individuals in the group according to the fitness, and executing the step S34;
s34, acting a selection operator on the population so as to enable the optimized individuals to be directly inherited to the next generation or generate new individuals through pairing and crossing and then be inherited to the next generation;
s35, acting a crossover operator on the population to replace and recombine partial structures of the two parent individuals to generate a new individual;
s36, acting the mutation operator on the population, judging whether each individual in the population needs to be mutated according to the preset mutation probability, randomly selecting a mutation position for mutation of the individual needing to be mutated to obtain the next generation population, and returning to the step S32.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010620977.9A CN111767677A (en) | 2020-07-01 | 2020-07-01 | GA algorithm-based cascade pump station group lift optimal distribution method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010620977.9A CN111767677A (en) | 2020-07-01 | 2020-07-01 | GA algorithm-based cascade pump station group lift optimal distribution method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111767677A true CN111767677A (en) | 2020-10-13 |
Family
ID=72723267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010620977.9A Pending CN111767677A (en) | 2020-07-01 | 2020-07-01 | GA algorithm-based cascade pump station group lift optimal distribution method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111767677A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392506A (en) * | 2021-05-21 | 2021-09-14 | 苏州市排水有限公司 | Optimal configuration method for regional sewage pump station joint scheduling based on flow |
| CN113422365A (en) * | 2021-05-06 | 2021-09-21 | 华翔翔能科技股份有限公司 | Layered distributed cooperative scheduling optimization method for small watershed intelligent pump station group |
| CN114718645A (en) * | 2022-03-11 | 2022-07-08 | 西南交通大学 | Operation optimization method for tunnel pump station unit |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446789A (en) * | 2018-02-09 | 2018-08-24 | 中国水利水电科学研究院 | A kind of intelligent optimization method towards cascade pumping station group's daily optimal dispatch |
| CN109636051A (en) * | 2018-12-19 | 2019-04-16 | 中建八局第三建设有限公司 | Primary pump variable flow system optimization of operating parameters method based on GA |
-
2020
- 2020-07-01 CN CN202010620977.9A patent/CN111767677A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446789A (en) * | 2018-02-09 | 2018-08-24 | 中国水利水电科学研究院 | A kind of intelligent optimization method towards cascade pumping station group's daily optimal dispatch |
| CN109636051A (en) * | 2018-12-19 | 2019-04-16 | 中建八局第三建设有限公司 | Primary pump variable flow system optimization of operating parameters method based on GA |
Non-Patent Citations (1)
| Title |
|---|
| 吴辉明 等: "多级串联梯级泵站扬程优化分配研究", 《水利水电技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113422365A (en) * | 2021-05-06 | 2021-09-21 | 华翔翔能科技股份有限公司 | Layered distributed cooperative scheduling optimization method for small watershed intelligent pump station group |
| CN113392506A (en) * | 2021-05-21 | 2021-09-14 | 苏州市排水有限公司 | Optimal configuration method for regional sewage pump station joint scheduling based on flow |
| CN114718645A (en) * | 2022-03-11 | 2022-07-08 | 西南交通大学 | Operation optimization method for tunnel pump station unit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111767677A (en) | GA algorithm-based cascade pump station group lift optimal distribution method | |
| Li et al. | Improved decomposition–coordination and discrete differential dynamic programming for optimization of large-scale hydropower system | |
| CN106295878B (en) | A kind of flexible job shop scheduling system based on Petri network and improved adaptive GA-IAGA | |
| CN104636821B (en) | Fired power generating unit load optimal distribution method based on dynamic inertia weight population | |
| CN111723456A (en) | Central air-conditioning system energy efficiency optimization method based on NSGA-II algorithm | |
| CN113156817B (en) | Intelligent pump allocation method for pump station | |
| CN103277291A (en) | Optimal scheduling method for single-stage pump station | |
| CN103020345A (en) | Centrifugal pump design method based on matrix laboratory (MATLAB) genetic algorithm | |
| CN104268712A (en) | Energy balancing and scheduling method based on improved mixed multi-population evolutionary algorithm | |
| CN114722709B (en) | Cascade reservoir group optimal scheduling method and system considering generated energy and minimum output | |
| CN101989743B (en) | Energy-saving power generation dispatching optimization method based on direct current power flow | |
| CN103617455A (en) | Power network and plant two-stage optimal load scheduling method based on virtual machine set subgroup | |
| CN105868867A (en) | Method and system for optimized operation of heating boiler cluster | |
| Shang et al. | Production scheduling optimization method based on hybrid particle swarm optimization algorithm | |
| CN103761385A (en) | Optimized design method for mult-heat-source annular pipe network | |
| CN109214709B (en) | Method for optimizing distribution of oxygen generation system of iron and steel enterprise | |
| CN115860205A (en) | Two-stage distribution robust hydrogen storage equipment optimal configuration method considering cross-season scheduling | |
| CN106055525B (en) | A kind of big data processing method based on stepwise regression analysis | |
| CN111598348A (en) | Power transmission network uniformity planning optimization method, system, medium and electronic equipment | |
| CN108734419A (en) | A kind of blast furnace gas Modeling of Scheduling method of knowledge based migration | |
| Coelho et al. | Analysis of diverse optimisation algorithms for pump scheduling in water supply systems | |
| CN116415824A (en) | Multi-level cascade reservoir simulation scheduling system and method considering different requirements | |
| CN105183940A (en) | Hydraulic design data management system of large-sized low-lift pumping station | |
| CN114880944A (en) | Desulfurization system operation optimization method and system based on Lasso algorithm | |
| CN108364071A (en) | A kind of adaptive modeling wind power prediction method based on genetic programming algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201013 |
|
| RJ01 | Rejection of invention patent application after publication |