CN116720705A - Regional water resource intelligent configuration method - Google Patents
Regional water resource intelligent configuration method Download PDFInfo
- Publication number
- CN116720705A CN116720705A CN202310748032.9A CN202310748032A CN116720705A CN 116720705 A CN116720705 A CN 116720705A CN 202310748032 A CN202310748032 A CN 202310748032A CN 116720705 A CN116720705 A CN 116720705A
- Authority
- CN
- China
- Prior art keywords
- water
- annual
- index
- water resource
- regional
- 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 364
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000005457 optimization Methods 0.000 claims abstract description 53
- 238000004088 simulation Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000013468 resource allocation Methods 0.000 claims abstract description 31
- 238000011160 research Methods 0.000 claims abstract description 11
- 230000004044 response Effects 0.000 claims abstract description 11
- 238000010276 construction Methods 0.000 claims abstract description 9
- 238000009826 distribution Methods 0.000 claims description 39
- 238000004519 manufacturing process Methods 0.000 claims description 30
- 230000006870 function Effects 0.000 claims description 21
- 239000002352 surface water Substances 0.000 claims description 12
- 244000025254 Cannabis sativa Species 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 9
- 235000013311 vegetables Nutrition 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 241001465754 Metazoa Species 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000003673 groundwater Substances 0.000 claims description 6
- 230000002262 irrigation Effects 0.000 claims description 6
- 238000003973 irrigation Methods 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 230000008602 contraction Effects 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 2
- 230000008901 benefit Effects 0.000 description 5
- 241000282414 Homo sapiens Species 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 description 1
- 230000009466 transformation Effects 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent regional water resource allocation method, and belongs to the field of water resource allocation. The method comprises the following steps: determining configuration indexes of the researched area according to an intelligent configuration index system of the regional water resources; generating a data set based on historical data of the research area according to the state index and the response index; constructing an intelligent regional water resource configuration simulation model, and then generating a plan library by utilizing the data set; constructing an intelligent regional water resource allocation decision model based on the plan library; constructing a subarea optimization model and a secondary optimization model based on the configuration index; solving an optimization model by applying an optimization algorithm to complete the construction of an intelligent regional water resource configuration model of the researched region; and inputting the target state index and the target pressure index of the regional water resource intelligent configuration model to obtain an output regional water resource intelligent configuration scheme. The water resource allocation scheme provided by the invention not only is optimized by model optimization, but also accords with the water supply characteristics of the area, and has actual operability.
Description
Technical Field
The invention belongs to the field of water resource allocation, and particularly relates to an intelligent regional water resource allocation method.
Background
In the water-deficient area, the optimal allocation of water resources can coordinate the water contradiction between the human society and the nature, so that the limited water resources exert the greatest comprehensive benefit; in the area with relatively abundant water resources, from the global aspect, the water resource optimal allocation is not only beneficial to the local water resource protection, but also can directly or indirectly improve the water resource crisis of the water-deficient area through the modes of water regulation engineering and the like. In a word, the water resource optimal allocation can balance the competition relationship between human beings and natural water resources, and promote the harmony and symbiosis of the human beings and the natural.
The conventional water resource optimization configuration research is close to an ideal configuration scheme, can only be used as a target of real water resource configuration, and lacks practicality; most of the simulation configuration of the water resource system is based on dynamic supply and demand balance, and the overall configuration of the water resource is often relatively poor in optimal benefit.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an intelligent regional water resource allocation method. The water resource allocation scheme output by the invention accords with the water supply characteristics of the area besides model optimizing optimization. Namely, the regional water resource intelligent allocation not only macroscopically optimizes the overall benefit of the water resource allocation, but also has actual operability.
The specific technical scheme adopted by the invention is as follows:
the invention provides an intelligent regional water resource allocation method, which comprises the following steps:
s1, determining configuration indexes of a researched area according to an intelligent configuration index system of regional water resources, wherein the configuration indexes comprise state indexes, response indexes and pressure indexes;
s2, generating a data set based on historical data of a research area according to the state index and the response index;
s3, constructing an intelligent regional water resource configuration simulation model, and then generating a plan library by utilizing the data set;
s4, constructing an intelligent regional water resource allocation decision model based on the plan library;
s5, constructing a subarea optimization model and a secondary optimization model based on the configuration indexes in the step S1;
s6, solving the sub-region optimization model and the secondary optimization model by using an optimization algorithm, and then combining the simulation model and the decision model to complete the construction of an intelligent regional water resource configuration model of the researched region;
s7, inputting the planned annual state index and the target pressure index of the regional water resource intelligent configuration model to obtain an output regional water resource intelligent configuration scheme.
Preferably, the state indexes are divided into a water resource index set z1= { Z11, Z12, Z13, Z14, Z15, Z16, Z17}, a water ecological index set z2= { Z21, Z22, Z23, Z24, Z25, Z26, Z27, Z28}, an economic index set z3= { Z31, Z32, Z33, Z34, Z35, Z36, Z37, Z38, Z39, Z310, Z311, Z312}, and a social index set z4= { Z41, Z42, Z43, Z44, Z45, Z46, Z47, Z48, Z49, Z410, Z411, Z412, Z413, Z414, Z415}; wherein: z11 is regional annual surface water resource quantity, z12 is regional annual mineable groundwater resource quantity, z13 is regional annual unconventional water resource utilization quantity, z14 is regional annual coordinated surface water resource quantity, z15 is regional annual coordinated groundwater resource quantity, z16 is regional annual coordinated unconventional water resource quantity, and z17 is regional annual external water regulation resource quantity; wherein z14 to z17 form the coordination of the decision variable by the regional multi-objective optimization algorithm; z21 is the life year water withdrawal amount of urban residents, z22 is the industry year water withdrawal amount, z23 is the building industry year water withdrawal amount, z24 is the service industry year water withdrawal amount, z25 is the life year water withdrawal BOD content of urban residents, z26 is the industry year water withdrawal BOD content, z27 is the building industry year water withdrawal BOD content, and z28 is the service industry year water withdrawal BOD content; z31 is a paddy field annual production total value, z32 is a dry field annual production total value, z33 is a vegetable field annual production total value, z34 is a garden grass annual production total value, z35 is a stock raising annual production total value, z36 is a pond raising annual production total value, z37 is an electric power annual production total value, z38 is a general industrial annual production total value, z39 is a building annual production total value, z310 is a service annual production total value, z311 is a paddy field annual grain yield, and z312 is a dry field annual grain yield; z41 is paddy field annual water demand, z42 is dry land annual water demand, z43 is vegetable field annual water demand, z44 is garden grass irrigation annual water demand, z45 is fishpond water supply annual water demand, z46 is animal husbandry annual water demand, z47 is fire nuclear annual water demand, z48 is general industrial annual water demand, z49 is building industrial annual water demand, z410 is service industrial annual water demand, z411 is urban resident annual living water demand, z412 is rural resident annual living water demand, z413 is river channel external ecological water annual water demand, z414 is urban population total, and z415 is rural population total;
the stress index is divided into a 4-layer water resource allocation scheme comprising surface water resource amount, underground water resource amount, unconventional water resource amount and external water regulation resource amount allocation, each layer of R4= { R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, R12 and R13}, and the regional water use scheme is regulated to regulate the socioeconomic and ecological states of the regional based on the water resource; wherein: r1 is paddy field annual water distribution, r2 is dry land annual water distribution, r3 is vegetable field annual water distribution, r4 is garden grass irrigation annual water distribution, r5 is fishpond water supply annual water distribution, r6 is animal husbandry annual water distribution, r7 is fire nuclear annual water distribution, r8 is general industrial annual water distribution, r9 is building annual water distribution, r10 is service annual water distribution, r11 is urban resident life annual water distribution, r12 is rural resident life annual water distribution, and r13 is river course external ecological water supply annual water distribution;
the pressure index is divided into an external pressure index and an internal pressure index; wherein the external pressure index describes a decision pressure applied by a decision maker; the internal pressure index reflects the pressure of the external pressure index applied to the state index, describes factors influencing the balance of the water ecological system and the socioeconomic system from four aspects of water resource, water ecology, economy and society, and is a quantification index of the external pressure index; the external pressure index includes: p= { P1, P2, P3, P4, P5, P6, P7, P8}, P1 being the residential domestic water guarantee level, P2 being the first industrial development level, P3 being the second industrial development level, P4 being the third industrial development level, P5 being the value-producing importance level, P6 being the social water fairness level, P7 being the ecological environmental protection level, P8 being the water resource system coordination level; the internal pressure indexes comprise water resource index sets p1= { p11, p12, p13}, water ecological index sets p2= { p21, p22, p23}, economic index sets p3= { p31, p32}, social index sets p4= { p41, p42, p43, p44, p45, p46, p47}; wherein, p11 is the surface water consumption proportion, p12 is the underground water consumption proportion, p13 is the unconventional water resource utilization rate, p21 is the unilateral water withdrawal rate, p22 is the ecological water consumption proportion in the river channel, p23 is the water withdrawal Biochemical Oxygen Demand (BOD), p31 is the unilateral water GDP, p32 is the unilateral water grain yield, p41 is the first industry water shortage rate, p42 is the second industry water shortage rate, p43 is the third industry water shortage rate, p44 is the non-industry water shortage rate, p45 is the annual urban average life water consumption, p46 is the rural annual average life water consumption, p47 is the river channel outside average ecological annual average water consumption, and p48 is the water shortage imbalance rate.
Preferably, in the step S3, the intelligent water resource configuration simulation model is constructed by adopting fuzzy logic, including determining the domain of the input and output variables and the membership function of the input and output variables of the simulation model, and automatically determining the rule base of the simulation model by a general rule base according to the selected index; the plan library is generated by the data set generated by the historical data in the step S2 through the intelligent water resource configuration simulation model and is used for training the intelligent water resource configuration decision model.
Preferably, the step S4 specifically includes the following steps:
s41, performing parameter adjustment on the water resource intelligent configuration decision model based on the convolutional neural network by using the plan library, wherein the parameter adjustment comprises the steps of determining the convolutional kernel size, the hidden layer node number, the learning rate and the iteration times of the water resource intelligent configuration decision model;
s42, training the intelligent water resource configuration decision model according to the determined parameters by using the plan library.
Preferably, in the step S5, the sub-region optimizes the general model decision variablesIn the form of r 1 1 ，r 1 2 ，r 1 3 ，…，r 1 13 ，r 2 1 ，…，r 2 13 ，r 3 1 ，…，r 3 13 ，r 4 1 ，…，r 4 13 The method comprises the steps of carrying out a first treatment on the surface of the Its objective function isThe constraint to be satisfied is non-negative constraint +.>Water resource demand constraint->Water supply capacity restriction->The P is i Is the ith external pressure index; p (P) i ' is the ith external pressure index simulated by the simulation model; />The water quantity allocated to the ith user for the water source j; r's' i The water resource demand for the ith user; w (W) j Is the available water supply for water source j in the sub-zone.
Preferably, in the step S5, the general form of the second-level optimization model decision variable of the second-level optimization model is S14 1 、s15 1 、s16 1 、s17 1 、…、s14 N 、s15 N 、s16 N 、s17 N The method comprises the steps of carrying out a first treatment on the surface of the Its objective function isThe constraint to be met is the water balance constraint +.> Said->An ith external pressure index for subregion n; p'. i n An ith external pressure index simulated for the simulation model for subregion n; n is the number of subareas; v (V) w The water resource amount is regulated outside the area.
Preferably, in the step S6, a ripple algorithm is adopted as the optimization algorithm;
the implementation flow of the ripple algorithm is as follows: a, determining the dimension of an optimized variable, a fitness function and constraint conditions; b, determining algorithm parameters and initializing ripple center point groups; c, calculating the fitness value of the center group; d calculating the ripple radius of each center point according to the global optimal fitness; e, carrying out multi-layer ripple random point searching by taking each central point as a unit, and calculating the fitness value of all random points; f, comparing each center point with the corresponding ripple layer random points, and reserving the point with the maximum fitness value to form a new center point group; g, judging whether the maximum iteration times or the minimum precision error requirement is met, if so, outputting a solution with the optimal fitness value, and if not, returning to the step c to continue the iterative computation;
the ripple structure of the ripple algorithm is formed by three layers of ripples diffused from each center point, and the radius from inside to outside is R in sequence 1 、R 2 、R 3 The calculation method is thatThe sigma i For the fitness value, sigma, of the ith center point opt The global optimal fitness value; the coefficient u is greater than 0 when solving the maximum problem and less than 0 when solving the minimum problem; the coefficient v is smaller than 0 when solving the maximum problem and larger than 0 when solving the minimum problem; />First layer radius for the ith center point, < > x->Second layer radius for the ith center point, < > x->A third radius that is the ith center point; beta is a contraction function whose mathematical expression is +.>T is the current iteration number, T is the total iteration number, and c is the function number; f (f) r (x) In order to achieve the purpose of adjusting the ripple searching region based on the fitness gap information, the ripple radius function has the following characteristics: f (f) r (x) Passing points (1, 0); f (f) r (x) Continuously monotonically decreasing over the definition field (0, 1);
the ripple searching mode of the ripple algorithm is to take each central point as a unit, perform multi-layer ripple random point searching, and calculate the fitness value of all random points; the multi-layer ripple random point-taking calculation method is thatThe saidMth random search point of kth layer representing ith center point, +.>Represents the i-th center point,/->The kth layer radius, which represents the ith center point,/->Is an n-dimensional random unit vector;
the central point group updating formula of the ripple algorithm is as followsThe saidThe ith center point of the t+1st generation center point group,/th center point>The ith center point of the t-th generation center point group,/and (I)>The M search points are the M search points of the k layers corresponding to the ith center point of the ith generation of center point group, and M is the number of ripple random sampling points of each layer.
Preferably, in the step S7, the planned year status index is a predicted planned year status index value, and the target pressure index is an external pressure index value formed by decision-making by a decision maker.
Compared with the prior art, the invention has the following beneficial effects:
the intelligent water resource allocation scheme output by the invention accords with the water supply characteristics of the area besides model optimizing optimization. Namely, the regional water resource intelligent allocation not only macroscopically optimizes the overall benefit of the water resource allocation, but also has actual operability.
Drawings
FIG. 1 is a flow chart of a method for intelligently configuring regional water resources according to the present invention;
fig. 2 is a diagram of an intelligent regional water resource allocation pattern based on a water informatics model, which is obtained by the intelligent regional water resource allocation method of the invention.
Detailed Description
The invention is further illustrated and described below with reference to the drawings and detailed description. The technical features of the embodiments of the invention can be combined correspondingly on the premise of no mutual conflict.
As shown in fig. 1, the method for intelligently configuring regional water resources provided by the invention mainly comprises the following steps:
s1, determining configuration indexes of the researched area according to an intelligent configuration index system of the regional water resource, wherein the configuration indexes comprise state indexes, response indexes and pressure indexes.
S2, generating a data set based on historical data of the research area according to the state index and the response index in the step S1.
S3, constructing an intelligent regional water resource configuration simulation model, and then generating a plan library by utilizing the data set in the step S2.
S4, constructing an intelligent regional water resource allocation decision model based on the plan library in the step S3.
S5, constructing a subarea optimization model and a secondary optimization model based on the configuration indexes in the step S1.
And S6, solving the sub-region optimization model and the secondary optimization model in the step S5 by applying an optimization algorithm, and then combining the simulation model in the step S3 and the decision model in the step S4 to complete the construction of the intelligent regional water resource configuration model of the researched region.
S7, inputting the planned annual state index and the target pressure index of the regional water resource intelligent configuration model to obtain an output regional water resource intelligent configuration scheme.
It can be seen that the regional water resource intelligent configuration method provided by the invention mainly comprises seven parts of contents, namely: determining research area indexes, generating a data set of a research area, constructing an area water resource intelligent configuration simulation model and a plan library, constructing an area water resource intelligent configuration decision model, constructing a subarea optimization model and a secondary optimization model, solving the optimization model by applying an optimization algorithm, and inputting state indexes and pressure indexes of the research area water resource intelligent configuration model according to an area water resource intelligent configuration index system, wherein the seven parts of contents are explained below.
1. Determining the index of the research area according to the intelligent allocation index system of the regional water resource
The core content of the part is as follows: according to a general regional water resource intelligent allocation index system, the state index, the pressure index and the response index of the researched region are determined by combining the water resource and the socioeconomic state of the researched region.
The part of the content corresponds to the first step, and the first step comprises the following contents:
s1, determining configuration indexes of the researched area according to an intelligent configuration index system of the regional water resource.
In this embodiment, the regional water resource intelligent configuration index system includes status indexes, divided into water resource index sets z1= { Z11, Z12, Z13, Z14, Z15, Z16, Z17}, water ecological index sets z2= { Z21, Z22, Z23, Z24, Z25, Z26, Z27, Z28}, economic index sets z3= { Z31, Z32, Z33, Z34, Z35, Z36, Z37, Z38, Z39, Z310, Z311, Z312}, and social index sets z4= { Z41, Z42, Z43, Z44, Z45, Z46, Z47, Z48, Z49, Z410, Z411, Z412, Z413, Z414, Z415}. Wherein: z11 is regional annual surface water resource quantity, z12 is regional annual producible groundwater resource quantity, z13 is regional annual unconventional water resource utilization quantity, z14 is regional annual coordinated surface water resource quantity, z15 is regional annual coordinated groundwater resource quantity, z16 is regional annual coordinated unconventional water resource quantity, and z17 is regional annual external water regulation resource quantity. Wherein z 14-z 17 constitute the decision variables coordinated by the regional multi-objective optimization algorithm. z21 is the annual water withdrawal of urban residents, z22 is the annual water withdrawal of industry, z23 is the annual water withdrawal of construction industry, z24 is the annual water withdrawal of service industry, z25 is the annual water withdrawal BOD of urban residents, z26 is the annual water withdrawal BOD of industry, z27 is the annual water withdrawal BOD of construction industry, and z28 is the annual water withdrawal BOD of service industry. z31 is a paddy field annual production total value, z32 is a dry field annual production total value, z33 is a vegetable field annual production total value, z34 is a garden grass annual production total value, z35 is a stock raising annual production total value, z36 is a pond raising annual production total value, z37 is an electric power annual production total value, z38 is a general industrial annual production total value, z39 is a building annual production total value, z310 is a service annual production total value, z311 is a paddy field annual grain yield, and z312 is a dry field annual grain yield. z41 is paddy field annual water demand, z42 is dry land annual water demand, z43 is vegetable field annual water demand, z44 is garden grass irrigation annual water demand, z45 is fishpond water supply annual water demand, z46 is animal husbandry annual water demand, z47 is fire nuclear annual water demand, z48 is general industrial annual water demand, z49 is building industrial annual water demand, z410 is service industrial annual water demand, z411 is urban resident annual living water demand, z412 is rural resident annual living water demand, z413 is river channel external ecological water annual water demand, z414 is urban population total number, and z415 is rural population total number.
In this embodiment, the regional water resource intelligent allocation index system includes response indexes, and is correspondingly divided into 4 layers of water resource allocation schemes including surface water resource allocation, underground water resource allocation, unconventional water resource allocation and external water resource allocation, each layer of r4= { R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, R12 and R13}, and the regional water use scheme is adjusted to adjust the socioeconomic and ecological states of the regional based on water resources. Wherein: r1 is paddy field annual water distribution, r2 is dry land annual water distribution, r3 is vegetable annual water distribution, r4 is garden grass irrigation annual water distribution, r5 is fishpond water supply annual water distribution, r6 is animal husbandry annual water distribution, r7 is fire nuclear annual water distribution, r8 is general industrial annual water distribution, r9 is building annual water distribution, r10 is service annual water distribution, r11 is urban resident life annual water distribution, r12 is rural resident life annual water distribution, and r13 is river course external ecological water supply annual water distribution.
In this embodiment, the regional water resource intelligent allocation index system includes pressure indexes, and the pressure indexes are divided into an external pressure index and an internal pressure index. Wherein the external pressure index describes a decision pressure applied by a decision maker; the internal pressure index reflects the pressure applied by the external pressure index to the state index, describes factors influencing the balance of the water ecological system and the socioeconomic system from four aspects of water resource, water ecology, economy and society, and is a quantification index of the external pressure index. The external pressure index includes: p= { P1, P2, P3, P4, P5, P6, P7, P8}, P1 is the residential domestic water guarantee level, P2 is the first industry development level, P3 is the second industry development level, P4 is the third industry development level, P5 is the value-producing importance level, P6 is the social water fairness level, P7 is the ecological environment protection level, and P8 is the water resource system coordination level. The internal pressure indexes comprise water resource index sets p1= { p11, p12, p13}, water ecological index sets p2= { p21, p22, p23}, economic index sets p3= { p31, p32}, social index sets p4= { p41, p42, p43, p44, p45, p46, p47}. Wherein, p11 is the surface water consumption proportion, p12 is the underground water consumption proportion, p13 is the unconventional water resource utilization rate, p21 is the unilateral water withdrawal rate, p22 is the ecological water consumption proportion in the river channel, p23 is the water withdrawal Biochemical Oxygen Demand (BOD), p31 is the unilateral water GDP, p32 is the unilateral water grain yield, p41 is the first industry water shortage rate, p42 is the second industry water shortage rate, p43 is the third industry water shortage rate, p44 is the non-industry water shortage rate, p45 is the annual urban average life water consumption, p46 is the rural annual average life water consumption, p47 is the river channel outside average ecological annual average water consumption, and p48 is the water shortage imbalance rate.
2. Data set generation for a study area
The part of the content corresponds to a second step, and the second step comprises the following contents:
s2, generating a data set based on historical data of the research area according to the state index and the response index in the step S1.
In this embodiment, the data set includes the status indicators and response indicators in the determined study area indicator system.
3. Construction of regional water resource intelligent configuration simulation model and generation of plan library
The core content of the part is as follows: and constructing an area water resource intelligent configuration simulation model, which is used for simulating and simulating the water resource configuration scheme output by the water resource intelligent configuration decision model and generating a plan library for training the water resource intelligent configuration decision model.
The part of the content corresponds to the third step, and the third step comprises the following contents:
s3, constructing an intelligent regional water resource configuration simulation model, and then generating a plan library by utilizing the data set in the step S2.
In this embodiment, the intelligent water resource configuration simulation model may be constructed by using fuzzy logic, including determining the domain of the input/output variables and the membership function of the input/output variables of the simulation model, where the rule base of the simulation model is automatically determined by the general rule base according to the selected index. The plan library is generated by a data set generated by historical data through the established intelligent water resource configuration simulation model and is used for training the intelligent water resource configuration decision model.
4. Construction of regional water resource intelligent configuration decision model
The core content of the part is as follows: and constructing an intelligent configuration decision model of the regional water resources, and outputting an intelligent configuration scheme of the water resources by the decision model according to the input state indexes and the pressure indexes.
The part of the content corresponds to a step four, which comprises the following contents:
s4, constructing an intelligent regional water resource allocation decision model based on the plan library in the step S3.
In this embodiment, the water resource intelligent configuration decision model may be constructed by adopting a convolutional neural network, and specifically includes the following steps:
step 41, performing parameter adjustment on the water resource intelligent configuration decision model based on the convolutional neural network by using a plan library, wherein the parameter adjustment comprises the steps of determining the convolutional kernel size, the hidden layer node number, the learning rate and the iteration times of the water resource intelligent configuration decision model;
and 42, training the intelligent water resource configuration decision model according to the determined parameters by using a plan library.
5. Establishing a sub-region optimization model and a secondary optimization model
The core content of the part is as follows: constructing a subarea optimization model, wherein the intelligent water resource allocation scheme output by the intelligent water resource allocation decision model is subjected to simulation by a simulation model, and optimizing and coordinating the water resource allocation scheme which does not meet the requirements by the subarea optimization model; and constructing a secondary optimization model, and optimizing the water resource allocation benefit of the regional level by coordinating the water resource quantity of the subintervals.
The part of the content corresponds to a step five, which comprises the following contents:
s5, constructing a subarea optimization model and a secondary optimization model based on the configuration indexes in the step S1.
In this embodiment, the general form of the decision variables in the subregion optimization model is r 1 1 ，r 1 2 ，r 1 3 ，…，r 1 13 ，r 2 1 ，…，r 2 13 ，r 3 1 ，…，r 3 13 ，r 4 1 ，…，r 4 13 . Its objective function isThe constraint to be satisfied is non-negative constraint +.>Water resource demand constraint->Water supply capacity restriction->Wherein P is i Is the ith external pressure index; p (P) i ' is the ith external pressure index simulated by the simulation model; />The water quantity allocated to the ith user for the water source j; r's' i The water resource demand for the ith user; w (W) j Is the available water supply for water source j in the sub-zone.
In this embodiment, the general form of the two-level optimization model decision variable is s14 1 、s15 1 、s16 1 、s17 1 、…、s14 N 、s15 N 、s16 N 、s17 N . Its objective function isThe constraint to be met is the water balance constraint +.>Wherein (1)>An ith external pressure index for subregion n; p'. i n An ith external pressure index simulated for the simulation model of subregion n; n is the number of subareas; v (V) w The water resource amount is regulated outside the area.
6. Solving optimization model by applying optimization algorithm
The part of the content corresponds to the step six, and the step six comprises the following contents:
and S6, solving the sub-region optimization model and the secondary optimization model in the step S5 by applying an optimization algorithm, and then combining the simulation model in the step S3 and the decision model in the step S4 as shown in the attached figure 2 to complete the construction of the intelligent regional water resource configuration model of the researched region.
In this embodiment, the optimization algorithm may be a ripple algorithm.
Specifically, the implementation flow of the ripple algorithm is as follows: a, determining the dimension of an optimized variable, a fitness function and constraint conditions; b, determining algorithm parameters and initializing ripple center point groups; c, calculating the fitness value of the center group; d calculating the ripple radius of each center point according to the global optimal fitness; e, carrying out multi-layer ripple random point searching by taking each central point as a unit, and calculating the fitness value of all random points; f, comparing each center point with the corresponding ripple layer random points, and reserving the point with the maximum fitness value to form a new center point group; and g, judging whether the maximum iteration times or the minimum precision error requirement is met, if so, outputting a solution with the optimal fitness value, and if not, returning to the step c to continue the iterative computation.
Specifically, the ripple structure of the ripple algorithm is composed of three layers of ripples diffused from each center point, and the radii of the three layers of ripples are R from inside to outside 1 、R 2 、R 3 The calculation method is that Wherein sigma i For the fitness value, sigma, of the ith center point opt For the global optimal fitness value, the coefficient u is greater than 0 when solving the maximum problem, the coefficient v is less than 0 when solving the maximum problem, the coefficient v is greater than 0 when solving the minimum problem, and the coefficient u is greater than 0 when solving the minimum problem,>first layer radius for the ith center point, < > x->Second layer radius for the ith center point, < > x->The third radius of the ith center point, beta is a contraction function, and the mathematical expression is +.>T is the current iteration number, T is the total iteration number, and c is the function number. f (f) r (x) In order to achieve the purpose of adjusting the ripple searching region based on the fitness gap information, the ripple radius function has the following characteristics: f (f) r (x) Passing points (1, 0); f (f) r (x) Continuously monotonically decreasing over the definition field (0, 1).
Specifically, the ripple searching mode of the ripple algorithm is to perform multi-layer random ripple point searching by taking each center point as a unit, and calculate the fitness value of all random points. The multi-layer ripple random point-taking calculation method is thatWherein (1)>Mth random search point of kth layer representing ith center point, +.>Represents the i-th center point,/->The kth layer radius, which represents the ith center point,/->Is an n-dimensional random unit vector.
Specifically, the center point group update formula of the ripple algorithm is as followsWherein said->The ith center point of the t+1st generation center point group,/th center point>An ith center point of the ith generation of center point group,the M search points are the M search points of the k layers corresponding to the ith center point of the ith generation of center point group, and M is the number of ripple random sampling points of each layer.
7. Input of state index and pressure index of intelligent water resource configuration model of research area
The part of the content corresponds to a step seven, and the step seven comprises the following contents:
s7, inputting the planned annual state index and the target pressure index of the regional water resource intelligent configuration model to obtain an output regional water resource intelligent configuration scheme.
In this embodiment, the target state index is a predicted state index value of a planned year, and the target pressure index is an external pressure index value formed by decision-making by a decision maker.
The water resource allocation scheme provided by the invention not only is optimized by model optimization, but also accords with the water supply characteristics of the area, and has actual operability.
The above embodiment is only a preferred embodiment of the present invention, but it is not intended to limit the present invention. Various changes and modifications may be made by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present invention. Therefore, all the technical schemes obtained by adopting the equivalent substitution or equivalent transformation are within the protection scope of the invention.
Claims (8)
1. The regional water resource intelligent configuration method is characterized by comprising the following steps of:
s1, determining configuration indexes of a researched area according to an intelligent configuration index system of regional water resources, wherein the configuration indexes comprise state indexes, response indexes and pressure indexes;
s2, generating a data set based on historical data of a research area according to the state index and the response index;
s3, constructing an intelligent regional water resource configuration simulation model, and then generating a plan library by utilizing the data set;
s4, constructing an intelligent regional water resource allocation decision model based on the plan library;
s5, constructing a subarea optimization model and a secondary optimization model based on the configuration indexes in the step S1;
s6, solving the sub-region optimization model and the secondary optimization model by using an optimization algorithm, and then combining the simulation model and the decision model to complete the construction of an intelligent regional water resource configuration model of the researched region;
s7, inputting the planned annual state index and the target pressure index of the regional water resource intelligent configuration model to obtain an output regional water resource intelligent configuration scheme.
2. The regional water resource intelligent allocation method according to claim 1, wherein the state indexes are divided into a water resource index set z1= { Z11, Z12, Z13, Z14, Z15, Z16, Z17}, a water ecological index set z2= { Z21, Z22, Z23, Z24, Z25, Z26, Z27, Z28}, an economic index set z3= { Z31, Z32, Z33, Z34, Z35, Z36, Z37, Z38, Z39, Z310, Z311, Z312} and a social index set z4= { Z41, Z42, Z43, Z44, Z45, Z46, Z47, Z48, Z49, Z410, Z411, Z412, Z413, Z414, Z415}; wherein: z11 is regional annual surface water resource quantity, z12 is regional annual mineable groundwater resource quantity, z13 is regional annual unconventional water resource utilization quantity, z14 is regional annual coordinated surface water resource quantity, z15 is regional annual coordinated groundwater resource quantity, z16 is regional annual coordinated unconventional water resource quantity, and z17 is regional annual external water regulation resource quantity; wherein z14 to z17 form the coordination of the decision variable by the regional multi-objective optimization algorithm; z21 is the life year water withdrawal amount of urban residents, z22 is the industry year water withdrawal amount, z23 is the building industry year water withdrawal amount, z24 is the service industry year water withdrawal amount, z25 is the life year water withdrawal BOD content of urban residents, z26 is the industry year water withdrawal BOD content, z27 is the building industry year water withdrawal BOD content, and z28 is the service industry year water withdrawal BOD content; z31 is a paddy field annual production total value, z32 is a dry field annual production total value, z33 is a vegetable field annual production total value, z34 is a garden grass annual production total value, z35 is a stock raising annual production total value, z36 is a pond raising annual production total value, z37 is an electric power annual production total value, z38 is a general industrial annual production total value, z39 is a building annual production total value, z310 is a service annual production total value, z311 is a paddy field annual grain yield, and z312 is a dry field annual grain yield; z41 is paddy field annual water demand, z42 is dry land annual water demand, z43 is vegetable field annual water demand, z44 is garden grass irrigation annual water demand, z45 is fishpond water supply annual water demand, z46 is animal husbandry annual water demand, z47 is fire nuclear annual water demand, z48 is general industrial annual water demand, z49 is building industrial annual water demand, z410 is service industrial annual water demand, z411 is urban resident annual living water demand, z412 is rural resident annual living water demand, z413 is river channel external ecological water annual water demand, z414 is urban population total, and z415 is rural population total;
the stress index is divided into a 4-layer water resource allocation scheme comprising surface water resource amount, underground water resource amount, unconventional water resource amount and external water regulation resource amount allocation, each layer of R4= { R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, R12 and R13}, and the regional water use scheme is regulated to regulate the socioeconomic and ecological states of the regional based on the water resource; wherein: r1 is paddy field annual water distribution, r2 is dry land annual water distribution, r3 is vegetable field annual water distribution, r4 is garden grass irrigation annual water distribution, r5 is fishpond water supply annual water distribution, r6 is animal husbandry annual water distribution, r7 is fire nuclear annual water distribution, r8 is general industrial annual water distribution, r9 is building annual water distribution, r10 is service annual water distribution, r11 is urban resident life annual water distribution, r12 is rural resident life annual water distribution, and r13 is river course external ecological water supply annual water distribution;
the pressure index is divided into an external pressure index and an internal pressure index; wherein the external pressure index describes a decision pressure applied by a decision maker; the internal pressure index reflects the pressure of the external pressure index applied to the state index, describes factors influencing the balance of the water ecological system and the socioeconomic system from four aspects of water resource, water ecology, economy and society, and is a quantification index of the external pressure index; the external pressure index includes: p= { P1, P2, P3, P4, P5, P6, P7, P8}, P1 being the residential domestic water guarantee level, P2 being the first industrial development level, P3 being the second industrial development level, P4 being the third industrial development level, P5 being the value-producing importance level, P6 being the social water fairness level, P7 being the ecological environmental protection level, P8 being the water resource system coordination level; the internal pressure indexes comprise water resource index sets p1= { p11, p12, p13}, water ecological index sets p2= { p21, p22, p23}, economic index sets p3= { p31, p32}, social index sets p4= { p41, p42, p43, p44, p45, p46, p47}; wherein, p11 is the surface water consumption proportion, p12 is the underground water consumption proportion, p13 is the unconventional water resource quantity utilization rate, p21 is the unilateral water withdrawal rate, p22 is the ecological water consumption proportion in the river channel, p23 is the water withdrawal biochemical oxygen demand, p31 is unilateral water GDP, p32 is the unilateral water grain yield, p41 is the first industry water shortage rate, p42 is the second industry water shortage rate, p43 is the third industry water shortage rate, p44 is the non-industry water shortage rate, p45 is the annual urban people average life water consumption, p46 is the annual rural people average life water consumption, p47 is the river channel outside people average ecological water consumption, and p48 is the water shortage imbalance rate.
3. The intelligent configuration method of regional water resources according to claim 1, wherein in the step S3, the intelligent configuration simulation model of water resources is constructed by adopting fuzzy logic, including determining the domain of the input and output variables of the simulation model and the membership function of the input and output variables, and automatically determining the rule base of the simulation model by a general rule base according to the selected index; the plan library is generated by the data set generated by the historical data in the step S2 through the intelligent water resource configuration simulation model and is used for training the intelligent water resource configuration decision model.
4. The method for intelligently configuring regional water resources according to claim 1, wherein the step S4 is specifically as follows:
s41, performing parameter adjustment on the water resource intelligent configuration decision model based on the convolutional neural network by using the plan library, wherein the parameter adjustment comprises the steps of determining the convolutional kernel size, the hidden layer node number, the learning rate and the iteration times of the water resource intelligent configuration decision model;
s42, training the intelligent water resource configuration decision model according to the determined parameters by using the plan library.
5. The method for intelligent configuration of regional water resources according to claim 1, wherein in step S5, the general form of the sub-region optimization model decision variable is r 1 1 ，r 1 2 ，r 1 3 ，…，r 1 13 ，r 2 1 ，…，r 2 13 ，r 3 1 ，…，r 3 13 ，r 4 1 ，…，r 4 13 The method comprises the steps of carrying out a first treatment on the surface of the Its objective function isThe constraint condition to be satisfied is that non-negative constraint 0 is less than or equal to r i j Water resource demand constraint->Water supply capacity restriction->The P is i Is the ith external pressure index; p (P) i ' is the ith external pressure index simulated by the simulation model; r is (r) i j The water quantity allocated to the ith user for the water source j; r's' i The water resource demand for the ith user; w (W) j Is the available water supply for water source j in the sub-zone.
6. The method for intelligent configuration of regional water resources according to claim 1, wherein in step S5, the general form of the secondary optimization model decision variable of the secondary optimization model is S14 1 、s15 1 、s16 1 、s17 1 、…、s14 N 、s15 N 、s16 N 、s17 N The method comprises the steps of carrying out a first treatment on the surface of the Its objective function isThe constraint to be satisfied is a water balance constraint Said->An ith external pressure index for subregion n; />An ith external pressure index simulated for the simulation model for subregion n; n is the number of subareas; v (V) w The water resource amount is regulated outside the area.
7. The intelligent regional water resource allocation method according to claim 1, wherein in the step S6, a ripple algorithm is adopted as an optimization algorithm;
the implementation flow of the ripple algorithm is as follows: a, determining the dimension of an optimized variable, a fitness function and constraint conditions; b, determining algorithm parameters and initializing ripple center point groups; c, calculating the fitness value of the center group; d calculating the ripple radius of each center point according to the global optimal fitness; e, carrying out multi-layer ripple random point searching by taking each central point as a unit, and calculating the fitness value of all random points; f, comparing each center point with the corresponding ripple layer random points, and reserving the point with the maximum fitness value to form a new center point group; g, judging whether the maximum iteration times or the minimum precision error requirement is met, if so, outputting a solution with the optimal fitness value, and if not, returning to the step c to continue the iterative computation;
the ripple structure of the ripple algorithm is formed by three layers of ripples diffused from each center point, and the radius from inside to outside is R in sequence 1 、R 2 、R 3 The calculation method is thatThe sigma i For the fitness value, sigma, of the ith center point opt The global optimal fitness value; the coefficient u is greater than 0 when solving the maximum problem and less than 0 when solving the minimum problem; the coefficient v is smaller than 0 when solving the maximum problem and larger than 0 when solving the minimum problem; />First layer radius for the ith center point, < > x->Second layer radius for the ith center point, < > x->A third radius that is the ith center point; beta is a contraction function whose mathematical expression is +.>T is the current iteration number, T is the total iteration number, and c is the function number; f (f) r (x) In order to achieve the purpose of adjusting the ripple searching region based on the fitness gap information, the ripple radius function has the following characteristics: f (f) r (x) Passing points (1, 0); f (f) r (x) Continuously monotonically decreasing over the definition field (0, 1);
the ripple searching mode of the ripple algorithm is to take each central point as a unit, perform multi-layer ripple random point searching, and calculate the fitness value of all random points; the multi-layer ripple random point-taking calculation method is thatSaid->Mth random search of kth layer representing ith center pointPoint (S)>Represents the i-th center point,/->The kth layer radius, which represents the ith center point,/->Is an n-dimensional random unit vector;
the central point group updating formula of the ripple algorithm is as followsSaid->The ith center point of the t+1st generation center point group,/th center point>The ith center point of the t-th generation center point group,/and (I)>The M search points are the M search points of the k layers corresponding to the ith center point of the ith generation of center point group, and M is the number of ripple random sampling points of each layer.
8. The method according to claim 1, wherein in the step S7, the planned year status index is a predicted planned year status index value, and the target pressure index is an external pressure index value formed by decision maker decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310748032.9A CN116720705A (en) | 2023-06-25 | 2023-06-25 | Regional water resource intelligent configuration method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310748032.9A CN116720705A (en) | 2023-06-25 | 2023-06-25 | Regional water resource intelligent configuration method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116720705A true CN116720705A (en) | 2023-09-08 |
Family
ID=87871312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310748032.9A Pending CN116720705A (en) | 2023-06-25 | 2023-06-25 | Regional water resource intelligent configuration method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116720705A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118014326A (en) * | 2024-04-09 | 2024-05-10 | 水利部水利水电规划设计总院 | Method and system for planning river basin water resource scheduling in water network system |
-
2023
- 2023-06-25 CN CN202310748032.9A patent/CN116720705A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118014326A (en) * | 2024-04-09 | 2024-05-10 | 水利部水利水电规划设计总院 | Method and system for planning river basin water resource scheduling in water network system |
| CN118014326B (en) * | 2024-04-09 | 2024-05-31 | 水利部水利水电规划设计总院 | Method and system for planning river basin water resource scheduling in water network system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu | Optimization of power system operation | |
| Sözen et al. | Prediction of net energy consumption based on economic indicators (GNP and GDP) in Turkey | |
| CN107480813A (en) | Basin water resources Optimal Configuration Method based on multi-Objective Chaotic genetic algorithm | |
| CN116720705A (en) | Regional water resource intelligent configuration method | |
| CN107706932B (en) | A kind of energy method for optimizing scheduling based on dynamic self-adapting fuzzy logic controller | |
| Wu et al. | Prediction and analysis of water resources demand in Taiyuan City based on principal component analysis and BP neural network | |
| CN113033917B (en) | Sewage treatment plant prediction planning operation management method based on peripheral data | |
| CN115544899B (en) | Water plant water intake pump station energy-saving scheduling method based on multi-agent deep reinforcement learning | |
| CN112668909B (en) | Water resource optimal configuration method and system based on genetic algorithm | |
| CN116484647B (en) | Distributed water resource allocation method and system for overall coordination | |
| CN112182951A (en) | Land utilization planning method considering multiple uncertainties | |
| CN114676941A (en) | Electric-thermal load combined self-adaptive prediction method and device for park comprehensive energy system | |
| Sun et al. | Research on prediction of housing prices based on GA-PSO-BP neural network model: evidence from Chongqing, China | |
| CN112966902B (en) | Water pollution load distribution method considering region fairness and pollution source treatment difference | |
| Zhang et al. | A multi-objective optimization prediction approach for water resources based on swarm intelligence | |
| CN113885324A (en) | Intelligent building power utilization control method and system | |
| CN109117998A (en) | A kind of multiple agent configuration method | |
| Li et al. | Water Resources Balanced Scheduling Method Using Particle Swarm Optimization for Future Smart Cities | |
| Mei et al. | Evaluation system of rural sustainable tourism land based on ecosystem service value | |
| CN113111583B (en) | Multi-water-source multi-user dual-quality-based water supply optimal configuration method considering reclaimed water | |
| CN114372645A (en) | Energy supply system optimization method and system based on multi-agent reinforcement learning | |
| Pei et al. | Demand estimation of water resources via bat algorithm | |
| Li et al. | Optimal Deep Belief Networks for Energy Demand Forecasting Using a Developed Version of the Gorilla Troops Optimization Method | |
| Liu et al. | Research on forecasting method of urban water demand based on fuzzy theory | |
| Bowen et al. | Energy Consumption Prediction Model of Wastewater Treatment Plant Based on Stochastic Configuration Networks |
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 |