Water resource allocation scheme decision-making method and system based on multi-agent game

Abstract

The invention discloses a water resource allocation scheme decision-making method and system based on a multi-agent game, and relates to the field of water resource management technologies and methods. Comprising the steps of obtaining a research area water resource configuration scheme set; calculating the water income of multiple subjects; calculating the water utilization fairness of multiple subjects; determining a configuration scheme preference matrix of multiple subjects; analyzing a configuration scheme negotiation space of multiple subjects; carrying out multi-subject negotiation based on a group decision game; and determining a water resource allocation scheme under game equilibrium. According to the invention, reasonable utilization appeals of all subjects are considered in decision making, and fairness of benefit distribution and water resource allocation efficiency are taken into consideration.

Description

Technical Field

[0001] The present invention relates to the field of water resource management technology and methods, and in particular to a water resource allocation plan decision-making method and system based on multi-agent game. Background Art

[0002] Water resource allocation is a complex system involving multiple regions, multiple industries, and multiple users. Current research on multi-objective optimization of water resource allocation focuses on how to achieve the solution under the overall Pareto optimality. The research on the impact of competition and cooperation between different regions and different water users on the optimal allocation of water resources still needs to be deepened, and the difference between the theoretical optimal solution of water resource allocation and the actual allocation situation needs to be bridged. Therefore, solving the problem of water resource allocation requires full respect and attention to all interests and strategic interaction characteristics, avoiding water-related conflicts through scientific and reasonable institutional arrangements, and achieving sustainable development of water resources.

[0003] This patent introduces group decision-making game methods into water resource allocation decision-making, and proposes a water resource allocation plan decision-making method and system based on multi-agent game. From the perspective of game equilibrium among all parties, it seeks a water resource allocation plan that meets the greatest common divisor of the interests of all parties, thereby increasing the practicality and feasibility of the final decision plan.

[0004] The ultimate goal of optimizing water resources allocation is to achieve regional sustainable development, and game theory provides tools and means for this. Studying the decision-making process of each game player can reveal the laws of stability and dynamic evolution, which is crucial to achieving the sustainability of allocation results and maximizing benefits. However, each game player has different goals and interest preferences, and other external factors (corporate strategy, political factors, public welfare demands, etc.) also affect the game pattern and final decision.

[0005] Therefore, it is an urgent problem for technical personnel in this field to propose a water resources allocation plan decision-making method and system based on multi-agent game, which takes into account the reasonable utilization demands of various subjects in decision-making and takes into account the fair distribution of interests and the efficiency of water resources allocation. Summary of the invention

[0006] In view of this, the present invention provides a water resource allocation plan decision-making method and system based on multi-agent game, which helps to balance the fairness of interest distribution and the efficiency of water resource allocation.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A water resources allocation scheme decision-making method based on multi-agent game includes the following steps:

[0009] S1. Obtain the water resources allocation plan set of the study area and obtain the allocation plan matrix of the study area;

[0010] S2. Based on the maximization of water use benefits as one of the conditions for making allocation plan decisions, the water use benefits of multiple entities under different allocation plans are calculated, and then the total water use benefit target is obtained;

[0011] S3, based on the optimal fairness of water use as one of the conditions for making configuration plan decisions, using the minimum water shortage rate within multiple subjects, calculate the fairness of water use of multiple subjects under different configuration plans, and then obtain the optimal goal of total water use fairness;

[0012] S4. Construct a preference matrix of water resource allocation schemes among multiple agents;

[0013] S5. Determine the negotiation space for water use benefits of each entity;

[0014] S6. Multi-agent water use benefit negotiation based on group decision-making game;

[0015] S7. Determine the water resources allocation plan under game equilibrium.

[0016] The above method is optional. The specific content of S1 is: calling the water resource allocation model of the study area to form different allocation scheme sets. The allocation scheme matrix of the study area is:

[0017]

[0018] Among them, D N×K is the water resources allocation scheme matrix of the calculation area; d i,k is the water consumption of subject i under water resource allocation scheme k, where: i = 1, 2, ... N, k = 1, 2, ... K, N is the total number of subjects, and K is the total number of schemes.

[0019] In the above method, the total water use benefit target in S2 is optionally:

[0020]

[0021] in,

[0022] v i,j =w i,j ×p i,j

[0023] Among them, v i is the water use benefit target of subject i; w i,j is the water supply of the j sector / industry of entity i; p i,j is the unilateral benefit of water use by the jth department / industry of subject i; j = 1, 2, ... M, where M is the total number of departments / industries within the subject;

[0024] The water use benefit matrix of the water resources allocation plan is:

[0025]

[0026] Among them, V N×K is the benefit matrix of the water resources allocation scheme for the calculation area; i,k is the water use benefit of subject i under water resource allocation plan k.

[0027] In the above method, optionally, the optimal objective of total water use fairness in S3 is expressed as:

[0028]

[0029] in,

[0030]

[0031] Among them, s i is the water equity goal of subject i; s i,j is the water shortage rate of subject i under water resource allocation scheme j; are the water demand of the jth sector / industry of entity i;

[0032] Then the water use fairness matrix of the water resources allocation plan is:

[0033]

[0034] Among them, S N×K To calculate the water use equity matrix of the water resources allocation scheme in the region; i,k is the water use fairness indicator of subject i under water resource allocation plan k.

[0035] The above method is optional. In S4, water use benefits and water use fairness demands are standardized. The specific method is as follows:

[0036]

[0037] Among them, n i,k is the value of the water use evaluation index of subject i for the kth scheme; N i,k is the standardized attribute value;

[0038] A weighted indicator evaluation matrix is ​​constructed according to the preferences of each subject, and the weighting method is:

[0039] wn i,k =N i,k 0ω i,j

[0040] Among them, wn i,k is the weighted attribute value, ω i,j is the weight value of entity i for industry j;

[0041] Further determine the positive understanding and negative ideal solution of each subject and The method is:

[0042]

[0043] in:

[0044]

[0045] in, and are the positive ideal solution and negative ideal solution of subject i for the kth solution respectively;

[0046] Calculate the distance of each configuration scheme from the positive ideal solution and the negative ideal solution as follows:

[0047]

[0048] in: is the Euclidean distance between solution k and the positive ideal solution under subject i’s preference; is the Euclidean distance between solution k and the negative ideal solution under subject i’s preference;

[0049] The degree of conformity between each configuration scheme and the ideal method is expressed by the following formula:

[0050]

[0051] in, is the degree of conformity between plan k and the ideal plan under the preference of subject i;

[0052] The larger the value, the higher the preference of subject i for scheme k. By sorting the schemes from large to small, we can obtain the preference matrix of subject i for each scheme as follows:

[0053]

[0054] Among them, r i,k For the subject i The values ​​of rank the preferences for solution j.

[0055] The above method, optionally, the set of all solutions for the cooperative game in S5 that can keep the cooperation stable is expressed as:

[0056]

[0057] in, is the comprehensive benefit obtained by subject i in the cooperation, i is a positive integer greater than 1; u iis the comprehensive benefit obtained by subject i in non-cooperation; S and N represent the set of local cooperation and the set of global cooperation respectively. v(s) represents the benefit of local cooperation at s; v(N) is the benefit of global cooperation.

[0058] In the above method, optionally, the negotiation decision method adopted in S6 includes the plurality voting method PV, the Haar system method HS, the Borda voting method BC, the paired comparison method PC and the approval voting method AV.

[0059] In the above method, optionally, the final decision solution in S7 is expressed as:

[0060] BEST=Max{PV,HS,BC,PC,AV}

[0061] Among them, BEST is the optimal solution of the lower-level group decision-making game model.

[0062] A water resource allocation scheme decision system based on multi-agent game, which executes any of the above-mentioned water resource allocation scheme decision methods based on multi-agent game, comprising: a memory, a processor, a calling interface and an output interface;

[0063] The memory is communicatively connected to the processor, and the processor is communicatively connected to the calling interface and the output interface respectively;

[0064] Memory, used to store and call the data required by the model;

[0065] Processor, used to realize the functions of calling data, running model programs, and inputting and outputting calculation results;

[0066] The calling interface is used to call the water resource allocation model and obtain a set of water resource allocation solutions under different scenarios;

[0067] Output interface, used to output standardized decision result data.

[0068] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a water resources allocation solution decision-making method and system based on multi-agent game, which has the following beneficial effects:

[0069] This method proposes a multi-agent decision preference identification method based on TOPSIS and a multi-agent negotiation and decision-making method based on group decision-making game, thereby obtaining a water resources allocation plan decision-making method system considering multi-agent game, and proposes a corresponding system; this method can provide a scientific basis for resolving water use conflicts among regions and water users and realizing a water resources allocation plan that takes into account both water use efficiency and fairness. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0071] Figure 1 A flow chart of a water resources allocation plan decision-making method based on multi-agent game disclosed in the present invention;

[0072] Figure 2 It is a calculation flow chart of the water resources allocation scheme decision method based on multi-agent game disclosed in the present invention;

[0073] Figure 3 This is a structural diagram of a water resources allocation plan decision-making system based on multi-agent game disclosed by the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0076] The purpose of the present invention is to provide a multi-scheme decision-making method for water resource allocation based on multi-agent group decision-making game, and to form a practical system to solve the water use conflicts among different regions and water users, and to achieve water resource allocation that takes into account water use fairness, water use efficiency and the economic demands of all parties. The calculation flow chart of the technology involved in the present invention is as follows: Figure 2 Based on Figure 2 The present invention discloses a specific solution for the process, which is as follows:

[0077] See also Figure 1 As shown, the present invention discloses a water resources allocation scheme decision-making method based on multi-agent game, comprising the following steps:

[0078] S1. Obtain the water resources allocation plan set of the study area and obtain the allocation plan matrix of the study area;

[0079] S2. Based on the maximization of water use benefits as one of the conditions for making allocation plan decisions, the water use benefits of multiple entities under different allocation plans are calculated, and then the total water use benefit target is obtained;

[0080] S3, based on the optimal fairness of water use as one of the conditions for making configuration plan decisions, using the minimum water shortage rate within multiple subjects, calculate the fairness of water use of multiple subjects under different configuration plans, and then obtain the optimal goal of total water use fairness;

[0081] S4. Construct a preference matrix of water resource allocation schemes among multiple agents;

[0082] S5. Determine the negotiation space for water use benefits of each entity;

[0083] S6. Multi-agent water use benefit negotiation based on group decision-making game;

[0084] S7. Determine the water resources allocation plan under game equilibrium.

[0085] Further, see Figure 3 As shown in Figure 1, the specific content of S1 is: calling the water resources allocation model of the study area to form different allocation scheme sets. The allocation scheme matrix of the study area is:

[0086]

[0087] Among them, D N×K is the water resources allocation scheme matrix of the calculation area; d i,k is the water consumption of subject i under water resource allocation scheme k (10,000 m 3 ), where: i = 1, 2, ... N, k = 1, 2, ... K, N is the total number of entities, K is the total number of solutions.

[0088] Specifically, under different allocation schemes, each entity will further carry out water resource allocation among different departments / industries within the entity after obtaining the corresponding allocated water volume, in order to maximize the water use effect that takes into account both benefits and fairness. Therefore, it is necessary to establish corresponding objective functions from the two dimensions of water use benefits and water use fairness.

[0089] Furthermore, the total water use benefit target in S2 is:

[0090]

[0091] in,

[0092] v i,j =w i,j ×p i,j

[0093] Among them, v i is the water use benefit target of subject i; w i,j is the water supply of the j sector / industry of entity i; p i,j is the unilateral benefit of water use by the jth department / industry of subject i; j = 1, 2, ... M, where M is the total number of departments / industries within the subject;

[0094] The water use benefit matrix of the water resources allocation plan is:

[0095]

[0096] Among them, V N×K is the benefit matrix of the water resources allocation scheme for the calculation area; i,k is the water use benefit of subject i under water resource allocation plan k.

[0097] Specifically, the water use benefits of multiple entities under different configuration schemes are evaluated, and the maximization of water use benefits is used as one of the basic bases for making configuration scheme decisions. For water users, there may be multiple water use departments / industries (for example, agriculture, industry, life, etc.), and each department / industry has different water demand. Maximizing the overall water use benefits is one of the configuration goals of the subject.

[0098] Furthermore, the optimal objective of total water fairness in S3 can be expressed as:

[0099]

[0100] in,

[0101]

[0102] Among them, s i is the water equity goal of subject i; s i,j is the water shortage rate of subject i under water resource allocation scheme j; are the water demand of the jth sector / industry of entity i;

[0103] Then the water use fairness matrix of the water resources allocation plan is:

[0104]

[0105] Among them, S N×K To calculate the water use equity matrix of the water resources allocation scheme in the region;i,k is the water use fairness indicator of subject i under water resource allocation plan k.

[0106] Specifically, the fairness of water use among multiple entities under different allocation schemes is evaluated, and the optimal fairness of water use is used as one of the basic bases for making allocation scheme decisions. The minimum water shortage rate of each water-using department / industry within the water-using entity is used as an assessment indicator of fairness.

[0107] Furthermore, in S4, water use benefits and water use fairness demands are standardized, and the specific method is as follows:

[0108]

[0109] Among them, n i,k is the value of the water use evaluation index of subject i for the kth scheme; N i,k is the standardized attribute value;

[0110] Taking into account the differences in preferences of different subjects, a weighted indicator evaluation matrix is ​​constructed according to the preferences of each subject. The weighting method is:

[0111] wn i,k =N i,k ·ω i,j

[0112] Among them, wn i,k is the weighted attribute value, ω i,j is the weight value of entity i for industry j;

[0113] Further determine the positive understanding and negative ideal solution of each subject and The method is:

[0114]

[0115] in:

[0116]

[0117] in, and are the positive ideal solution and negative ideal solution of subject i for the kth solution respectively;

[0118] Calculate the distance of each configuration scheme from the positive ideal solution and the negative ideal solution as follows:

[0119]

[0120] in: is the Euclidean distance between solution k and the positive ideal solution under subject i’s preference; is the Euclidean distance between solution k and the negative ideal solution under subject i’s preference;

[0121] The degree of conformity between each configuration scheme and the ideal method is expressed by the following formula:

[0122]

[0123] in, is the degree of conformity between plan k and the ideal plan under the preference of subject i;

[0124] The larger the value, the higher the preference of subject i for scheme k. By sorting the schemes from large to small, we can obtain the preference matrix of subject i for each scheme as follows:

[0125]

[0126] Among them, r i,k For the subject i The values ​​of rank the preferences for solution j.

[0127] Specifically, since each participant has different interests in different allocation plans, and the differences in different regions (hydrological conditions, cultural factors, political factors, historical factors, etc.) will also affect the game pattern and the final decision. Therefore, it is necessary to first clarify the preference matrix of each participant. In group decision-making, the subject will rank the alternative water resource allocation plans according to its own preferences, and give priority to the plan with the highest ranking.

[0128] Furthermore, the set of all solutions for the cooperative game in S5 that can keep the cooperation stable is expressed as:

[0129]

[0130] in, is the comprehensive benefit obtained by subject i in the cooperation, i is a positive integer greater than 1; u i is the comprehensive benefit obtained by subject i in non-cooperation; S and N represent the set of local cooperation and the set of global cooperation respectively. v(s) represents the benefit of local cooperation at s; v(N) is the benefit of global cooperation.

[0131] Specifically, in order to achieve the reasonable allocation of regional water resources and find an equilibrium solution that meets the interests of all parties, this patent introduces the cooperative game method into the decision-making of water resource allocation plans. Cooperation Game Theory (CGT) is an important branch of game theory, which is mainly used to solve the problem of reasonable distribution of interests among different game players. Its biggest feature is that the participating subjects participate in multi-party cooperation based on the principle of individual rationality, and on the premise of maximizing the total benefits of win-win cooperation, they satisfy their own interests according to certain strategies, thereby achieving a balance of interests among all parties. The cooperative game focuses on the fair and effective distribution of the benefits obtained from cooperation, and evaluates the acceptability of different allocation plans to each participant, which plays a good supporting role in forming a win-win cooperation pattern.

[0132] In order to realize the cooperative game of all parties, we first need to find the "core" of the cooperative game, that is, the outer boundary of all allocation methods that all participants may accept, that is, the set of all solutions that can keep the cooperation stable. The solutions within the core must satisfy that all game players will not benefit from leaving the cooperative body (adopting a non-cooperative approach). The "core" of the cooperative game is used as the negotiation space for all water resource allocation participants. That is, if the water resource allocation plan is within the "core", it is considered to have feasible conditions.

[0133] Furthermore, the negotiation decision-making methods used in S6 include the plurality voting method PV, the Haar system method HS, the Borda voting method BC, the paired comparison method PC and the approval voting method AV.

[0134] PV is one of the most widely used decision-making methods. The "winning" solution of this method is the one that is most favored by all parties:

[0135]

[0136] Then the number of votes for alternative j is:

[0137]

[0138] Under the PV method, the solution with the most total votes wins.

[0139] The Haar system method HS designs a multi-round elimination mechanism, in which the worst alternatives are eliminated in each round of voting, and the remaining options are the "winning" options. For a decision scenario with m alternatives, the Haar system method requires at most m-1 rounds of voting.

[0140] In each round of voting, the eliminated solutions are:

[0141] P j* =Min{P j

[0142] Where: P j The definition of is the same as in PV.

[0143] The final "winning" solution is:

[0144]

[0145] Where: m' is the number of alternatives remaining in the last round of voting.

[0146] In the Borda voting method (BC), each participant ranks and scores the alternative options according to their preferences, and the scores of each alternative option are counted. The one with the highest score is the "winning" option.

[0147] The score of alternative j can be expressed as:

[0148]

[0149] Where n is the number of participants and m is the number of alternatives.

[0150] In the end, the plan with the highest score wins.

[0151] The participants in the paired comparison method PC match the alternatives with each other and compare them one by one. The winning solution gets 1 point, the tie gets 0.5 points each, and the failure gets 0 points:

[0152]

[0153] Where: g≠h and g,h∈{1,2,...m}

[0154] Where: b g,h is the score of the comparison between alternative g and alternative h; N(j g ,j h ) is the sum of the scores given by all participants when comparing alternatives g and h based on their own preferences.

[0155] In the PC scenario with m alternatives, P can be constructed m×m Pairwise comparison matrix of

[0156]

[0157] For any b g,h +b h,g =1

[0158] The final score for alternative j is:

[0159]

[0160] In the end, the solution with the highest score wins.

[0161] In the AV method, participants can vote for multiple solutions at the same time, and the solution with the most votes is the "winning" solution:

[0162]

[0163] Where: ρ is the number of votes each participant can cast, 1<ρ <m;

[0164] The final score for alternative j is:

[0165] Furthermore, the final decision solution in S7 is expressed as:

[0166] BEST=Max{PV,HS,BC,PC,AV}

[0167] Among them, BEST is the optimal solution of the lower-level group decision-making game model.

[0168] and Figure 1 Corresponding to the method, the present invention also discloses a water resource allocation scheme decision system based on multi-agent game, which executes any of the above-mentioned water resource allocation scheme decision methods based on multi-agent game. The specific structure is referenced to Figure 3 As shown, it includes: a memory, a processor, a calling interface and an output interface;

[0169] The memory is communicatively connected to the processor, and the processor is communicatively connected to the calling interface and the output interface respectively;

[0170] Memory, used to store and call the data required by the model;

[0171] Processor, used to realize the functions of calling data, running model programs, and inputting and outputting calculation results;

[0172] The calling interface is used to call the water resource allocation model and obtain a set of water resource allocation solutions under different scenarios;

[0173] Output interface, used to output standardized decision result data.

[0174] Specifically, the memory mainly serves as the database of the model, and is responsible for storing and calling the required data. The memory contains a variety of data types such as local water source data, water demand data of various industries, economic and social data, reservoir information data, engineering node topology data, etc. The storage file can be a callable database format such as .db, .sqlite, .dmp, or a readable file format such as .scv. The processor provides a computing platform for the model, and is responsible for calling data, running model programs, inputting and outputting calculation results, etc. The professional model in the processor is developed in FORTRAN or Python, mainly including generalization module, water use efficiency analysis module, negotiation space analysis module, subject preference calculation module, group decision game module, etc. Different functional modules are called according to different computing needs.

[0175] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0176] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A water resources allocation decision-making method based on multi-agent game, It is characterized in that The following steps are involved: S1. Obtain the water resources allocation plan set of the study area and obtain the allocation plan matrix of the study area; S2. Based on the maximization of water use benefits as one of the conditions for making allocation plan decisions, the water use benefits of multiple entities under different allocation plans are calculated, and then the total water use benefit target is obtained; S3, based on the optimal fairness of water use as one of the conditions for making configuration plan decisions, using the minimum water shortage rate within multiple subjects, calculate the fairness of water use of multiple subjects under different configuration plans, and then obtain the optimal goal of total water use fairness; S4. Construct a preference matrix of water resource allocation schemes among multiple agents; S5. Determine the negotiation space for water use benefits of each entity; S6. Multi-agent water use benefit negotiation based on group decision-making game; S7. Determine the water resources allocation plan under game equilibrium.

2. According to the water resources allocation plan decision-making method based on multi-agent game in claim 1, It is characterized in that The specific content of S1 is: calling the water resources allocation model of the study area to form different allocation scheme sets. The allocation scheme matrix of the study area is: Among them, D N×K is the water resources allocation matrix of the calculation area; d i,k is the water consumption of subject i under water resource allocation scheme k, where: i = 1, 2, ... N, k = 1, 2, ... K, N is the total number of subjects, and K is the total number of schemes.

3. According to the water resources allocation plan decision-making method based on multi-agent game in claim 1, It is characterized in that The total water use benefit target in S2 is: in, v i,j =w i,j ×p i,j Among them, v i is the water use benefit target of subject i; w i,j is the water supply of the jth sector / industry of entity i; p i,j is the unilateral benefit of water use by the jth department / industry of subject i; j = 1, 2, ... M, where M is the total number of departments / industries within the subject; The water use benefit matrix of the water resources allocation plan is: Among them, V N×K is the benefit matrix of the water resources allocation scheme for the calculation area; i,k is the water use benefit of subject i under water resource allocation plan k.

4. According to claim 1, a water resources allocation plan decision-making method based on multi-agent game, It is characterized in that The optimal objective of total water use fairness in S3 is expressed as: in, Among them, s i is the water equity goal of subject i; s i,j is the water shortage rate of subject i under water resource allocation scheme j; are the water demand of the jth sector / industry of entity i; Then the water use fairness matrix of the water resources allocation plan is: Among them, S N×K To calculate the water use equity matrix of the water resources allocation scheme in the region; i,k is the water use fairness indicator of subject i under water resource allocation plan k.

5. According to claim 1, a water resources allocation plan decision-making method based on multi-agent game, It is characterized in that S4 standardizes water use benefits and water use equity claims in the following ways: Among them, n i,k is the value of the water use evaluation index of subject i for the kth scheme; N i,k is the standardized attribute value; A weighted indicator evaluation matrix is ​​constructed according to the preferences of each subject, and the weighting method is: wn i,k =N i,k ·oh i,j Among them, wn i,k is the weighted attribute value, ω i,j is the weight value of entity i for industry j; Further determine the positive understanding and negative ideal solution of each subject and The method is: in: in, and are the positive ideal solution and negative ideal solution of subject i for the kth solution respectively; Calculate the distance of each configuration scheme from the positive ideal solution and the negative ideal solution as follows: in: is the Euclidean distance between solution k and the positive ideal solution under subject i’s preference; is the Euclidean distance between solution k and the negative ideal solution under subject i’s preference; The degree of conformity between each configuration scheme and the ideal method is expressed by the following formula: in, is the degree of conformity between plan k and the ideal plan under the preference of subject i; The larger the value, the higher the preference of subject i for scheme k. By sorting the schemes from large to small, we can obtain the preference matrix of subject i for each scheme as follows: Among them, r i,k For the subject i The values ​​of rank the preferences for solution j.

6. According to claim 1, a water resources allocation plan decision-making method based on multi-agent game, It is characterized in that The set of all solutions for the cooperative game in S5 that can keep the cooperation stable is expressed as: in, is the comprehensive benefit obtained by subject i in the cooperation, i is a positive integer greater than 1; u i is the comprehensive benefit obtained by subject i in non-cooperation; S and N represent the set of local cooperation and the set of global cooperation respectively. v(s) represents the benefit of local cooperation at s; v(N) is the benefit of global cooperation.

7. A water resources allocation plan decision-making method based on multi-agent game according to claim 6, It is characterized in that The negotiation decision-making methods used in S6 include the plurality voting method PV, the Haar system method HS, the Borda voting method BC, the paired comparison method PC and the approval voting method AV.

8. According to claim 7, a water resources allocation plan decision-making method based on multi-agent game, It is characterized in that The final decision solution in S7 is expressed as: BEST=Max{PV,HS,BC,PC,AV} Among them, BEST is the optimal solution of the lower-level group decision-making game model.

9. A water resources allocation decision-making system based on multi-agent game, It is characterized in that A method for deciding a water resource allocation scheme based on multi-agent game according to any one of claims 1 to 8, comprising: a memory, a processor, a calling interface and an output interface; The memory is communicatively connected to the processor, and the processor is communicatively connected to the calling interface and the output interface respectively; Memory, used to store and call the data required by the model; Processor, used to realize the functions of calling data, running model programs, and inputting and outputting calculation results; The calling interface is used to call the water resource allocation model and obtain a set of water resource allocation solutions under different scenarios; Output interface, used to output standardized decision result data.

Images