Target area counterbalance scene prediction system and method based on system dynamics coupling genetic algorithm

Abstract

The invention discloses a target area counterbalance scene prediction system and method based on a system dynamics coupling genetic algorithm, and relates to the technical field of resource optimization configuration, and the system comprises a data collection module, a data processing module, a scene generation module, a scene prediction module and corresponding functions. According to the method, different future scenes in regional development can be predicted on the basis of target counterbalance.

Description

Technical Field

[0001] The present invention relates to the technical field of resource optimization configuration, and more particularly to a target area balancing scenario prediction system and method based on system dynamics coupled genetic algorithm. Background Art

[0002] At present, the development differences in some regions are quite large. For example, the Yellow River Basin is vast, and the resource endowments and economic development models vary greatly between different regions. Therefore, it is particularly important to seek regional scenario predictions with a certain degree of universality. The above scenario predictions can be achieved through scientific methods.

[0003] However, the existing technologies for scenario prediction are mostly concentrated in the field of water resources. Forecasts of future scenarios are often based on artificially preset scenarios, which fail to provide high-precision predictions applicable to multiple future scenarios. At the same time, there is a lack of checks and balances of relevant constraints, resulting in low prediction accuracy.

[0004] Therefore, how to provide a target area balancing scenario prediction system that can solve the above problems is an issue that those skilled in the art urgently need to solve. Summary of the Invention

[0005] In view of this, the present invention provides a target regional balance scenario prediction system and method based on system dynamics coupled genetic algorithm, which can predict different future scenarios in regional development based on target balance.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A target area balance scenario prediction system based on system dynamics coupled with genetic algorithm, including:

[0008] The data acquisition module is used to obtain basic data in the target area and process the basic data to obtain corresponding multiple regional development variable data;

[0009] A data processing module is used to construct a system dynamics model based on multiple regional development variable data, establish corresponding quantitative functional relationships, and determine corresponding constraint conditions based on the system dynamics model and quantitative functional relationships;

[0010] a scenario generation module, configured to determine a plurality of target balancing scenarios based on the system dynamics model, the basic data of the variables, and the constraint conditions, and select an optimal target balancing scenario from the plurality of target balancing scenarios;

[0011] A scenario prediction module is used to perform scenario prediction based on the optimal target balancing scenario.

[0012] Preferably, the data processing module includes:

[0013] A model building unit is used to extract data of multiple regional development variables into the system dynamics model, build the system dynamics model, and establish corresponding quantitative functional relationships;

[0014] A constraint condition determination unit, configured to determine the constraint conditions of the system dynamics model and the quantitative function relationship according to the expected target scenario variables;

[0015] A scenario generating unit, configured to determine a plurality of target balancing scenarios based on the plurality of regional development variable data and the constraint conditions;

[0016] The selection unit is used to select the best target balancing scenario from multiple target balancing scenarios.

[0017] Preferably, the implementation process of the model building unit specifically further includes:

[0018] The system dynamics model is historically tested.

[0019] Preferably, the implementation process of the model building unit specifically further includes:

[0020] The quantitative function relationship is obtained by fitting the relationship between multiple regional development variable data.

[0021] Preferably, the implementation process of the selection unit further includes:

[0022] A multi-objective optimization genetic algorithm is used to select the best target balancing scenario from multiple target balancing scenarios.

[0023] Preferably, the data acquisition module includes:

[0024] A collection unit is used to obtain basic data of the target area, wherein the basic data includes regional environmental emission data, regional ecological data, regional economic and consumption data, and regional energy use data;

[0025] The pre-processing unit is used to process the basic data to obtain corresponding multiple regional development variable data.

[0026] The present invention also provides a target area balancing scenario prediction method based on system dynamics coupled genetic algorithm, comprising the following steps:

[0027] Acquiring basic data in the target area and processing the basic data to obtain corresponding multiple regional development variable data;

[0028] Extract multiple regional development variable data into the system dynamics model, build the system dynamics model, and establish the corresponding quantitative function relationship;

[0029] Determine the constraints, select several variables from the system dynamics model as scenario variables, reflect the constraints / expected goals of regional policies in the system dynamics model, and generate multiple target scenarios;

[0030] Using a genetic algorithm that uses multi-objective optimization, the best target balancing scenario is selected from multiple target balancing scenarios;

[0031] The optimal target balance scenario is input into the system dynamics model to obtain the predicted values of regional development variables in the model and complete the scenario forecast.

[0032] Through the above technical solutions, it can be seen that compared with the prior art, the present invention discloses a target area balance scenario prediction system and method based on system dynamics coupled genetic algorithm, which has the following features:

[0033] Beneficial effects:

[0034] 1. The present invention obtains and processes the basic data of the target area to generate regional development variable data, providing more accurate and comprehensive input for the model and improving the accuracy of subsequent predictions.

[0035] 2. This invention uses a system dynamics model to simulate long-term trends and structural changes in regional development. By constructing quantitative functional relationships and clarifying the mathematical logic between variables, the model predictions are made more interpretable and credible.

[0036] 3. This invention generates multiple target scenarios by setting constraints and scenario variables, helping decision makers explore the possibilities of regional development under different policy paths and improving the scientific nature of decision-making.

[0037] 4. The present invention utilizes the advantages of genetic algorithms in multi-objective optimization problems to select the best scenario from multiple objective balance scenarios, obtain more accurate prediction values, and improve prediction efficiency and practicality.

[0038] In summary, the present invention couples the genetic algorithm of multi-objective optimization with the traditional system dynamics method to seek a more scientific and objective optimal solution, thereby avoiding the problems of the traditional system dynamics method in the process of goal setting and scenario prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0040] Figure 1 This is a structural principle block diagram of a target area balancing scenario prediction system based on system dynamics coupled genetic algorithm provided by the present invention;

[0041] Figure 2 A cause-and-effect diagram of a system dynamics model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0043] See also Figure 1-2 As shown, the embodiment of the present invention discloses a target area balancing scenario prediction system based on system dynamics coupled genetic algorithm, including:

[0044] Data acquisition module 1 is used to obtain basic data in the target area and process the basic data to obtain corresponding multiple regional development variable data;

[0045] Data processing module 2 is used to construct a system dynamics model based on multiple regional development variable data, establish corresponding quantitative functional relationships, and determine corresponding constraint conditions based on the system dynamics model and the quantitative functional relationships;

[0046] Scenario generation module 3, used to determine multiple target balancing scenarios based on the system dynamics model, basic data of variables, and constraints, and select the best target balancing scenario from the multiple target balancing scenarios;

[0047] The scenario prediction module 4 is used to perform scenario prediction based on the optimal target balance scenario, including but not limited to the predicted values of the variables included in the system dynamics model and the values calculated from the variables included in the system dynamics model.

[0048] In a specific embodiment, the data acquisition module 1 includes:

[0049] The acquisition unit 11 is used to obtain basic data of the target area, wherein the basic data includes regional environmental emission data, regional ecological data, regional economic and consumption data, and regional energy use data;

[0050] The pre-processing unit 12 is used to process the basic data to obtain corresponding multiple regional development variable data.

[0051] Specifically, regional environmental emission data may include environmental emission data such as particulate matter emission concentration, sulfur dioxide emissions, nitrogen oxide emissions, domestic sewage emissions, carbon emissions, etc. Regional ecological data may include forest area, cultivated land area and other data. Regional economic and consumption data may include GDP, permanent population, urbanization rate, fiscal expenditure, the proportion of primary / secondary / tertiary industries and other data. Regional energy use data may include fossil energy, electric energy, new energy, total water resources, water consumption of key industries and other data.

[0052] In the process of processing the basic data through the preprocessing unit 12, the basic data may be abstracted, and the obtained multiple regional development variable data may include regional GDP total, R&D funding investment intensity, primary / secondary / tertiary industry GDP, primary / secondary / tertiary industry proportion, industrial added value, total population, per capita GDP, urbanization rate, total water consumption, industrial water consumption, domestic water consumption, agricultural water consumption, ecological water consumption, total energy consumption, production energy consumption, domestic energy consumption, coal / oil / natural gas consumption proportion, new energy consumption proportion, unit GDP production energy consumption, carbon emissions, coal / oil / natural gas carbon emission factor, domestic sewage treatment volume, industrial wastewater treatment volume, total wastewater discharge, wastewater COD emissions, forest coverage, effective irrigation area and other variable data.

[0053] In addition, multiple regional development variable data include but are not limited to four types of variables: level variables, which are variables that accumulate values over time; rate variables, which affect the accumulation speed of state variables; auxiliary variables, which assist in establishing connections between variables; and constants.

[0054] In a specific embodiment, the data processing module 2 includes:

[0055] A model building unit 21 is used to extract multiple regional development variable data into the system dynamics model, build the system dynamics model, and establish corresponding quantitative function relationships;

[0056] A constraint condition determination unit 22 is used to determine the constraint conditions of the system dynamics model and the quantitative function relationship based on the expected target scenario variables;

[0057] A scenario generating unit 23 is used to determine multiple target balancing scenarios based on multiple regional development variable data and constraint conditions;

[0058] The selection unit 24 is configured to select an optimal target balancing scenario from a plurality of target balancing scenarios.

[0059] Specifically, the establishment of quantitative functional relationships is categorized as direct or indirect, depending on the relationship between variables. For variables with direct relationships, the relationship is established using arithmetic operations. For variables with indirect relationships, mathematical functions are fitted based on historical data between the two variables. Functional equations include, but are not limited to, integral equations, linear equations, exponential equations, polynomial equations, power equations, and table functions.

[0060] The constraints determined in the constraint determination unit 22 include environmental constraints, resource constraints, and ecological constraints. They may also include regional policy constraints and economic constraints such as information released on the official website of the regional government, data / descriptive indicators in the planning documents released by the regional government, and the government's strategic positioning of the region.

[0061] The scenario generation unit 23 outputs a number of target balancing scenarios based on a multi-objective optimization algorithm. Each target balancing scenario may include scenario variable values, which may also include key policy target balancing result values corresponding to the scenario variable values.

[0062] In a specific embodiment, the implementation process of the model building unit 21 specifically further includes:

[0063] Conducting a historical test of system dynamics models.

[0064] Specifically, the historical test is performed by inputting historical data into the model to obtain simulated values, and then calculating the error rate between the simulated values and the historical values. When the error rate is low enough, it can be considered that the model has a good simulation effect on the area. The specific expression is:

[0065]

[0066] Where, ε i is the average error rate of variable i; N is the total number of years of historical testing; L i,t(模拟)为 The value of variable i in year t simulated by the system dynamics model; L i,t(历史) is the historical data value of variable i in year t.

[0067] In a specific embodiment, the implementation process of the model building unit 21 specifically further includes:

[0068] The quantitative functional relationship is obtained by fitting the relationship between multiple regional development variable data.

[0069] In a specific embodiment, the implementation process of the selection unit 24 further includes:

[0070] A multi-objective optimization genetic algorithm is used to select the best target balancing scenario from multiple target balancing scenarios.

[0071] Specifically, the above processes can be implemented through relevant algorithm software, computers and corresponding hardware.

[0072] The present invention further provides a method for implementing a target area balancing scenario prediction system based on a system dynamics coupled genetic algorithm according to any one of the above embodiments, comprising the following steps:

[0073] Obtain basic data in the target area and process the basic data to obtain corresponding multiple regional development variable data;

[0074] Extract multiple regional development variable data into the system dynamics model, build the system dynamics model, and establish the corresponding quantitative function relationship;

[0075] Determine the constraints, select several variables from the system dynamics model as scenario variables, reflect the constraints / expected goals of regional policies in the system dynamics model, and generate multiple target scenarios;

[0076] Using a genetic algorithm that uses multi-objective optimization, the best target balancing scenario is selected from multiple target balancing scenarios;

[0077] The optimal target balance scenario is input into the system dynamics model to obtain the predicted values of regional development variables in the model and complete the scenario forecast.

[0078] The method provided in the embodiment of the present invention is described in detail below, including the following steps:

[0079] 1. Collect basic data in the target area.

[0080] The regional scope includes but is not limited to river basins, provinces, and cities.

[0081] Social / economic data include but are not limited to: GDP, permanent population, urbanization rate, fiscal expenditure, proportion of primary / secondary / tertiary industries, and industrial added value.

[0082] Resource production / consumption data include but are not limited to: fossil energy consumption, electricity energy consumption, new energy power growth rate, total water resources, and water consumption of key industries.

[0083] Environmental emission data include but are not limited to: particulate matter emission concentration, sulfur dioxide emissions, nitrogen oxide emissions, domestic sewage emissions, and carbon emissions.

[0084] Ecological protection data include but are not limited to: forest area and cultivated land area.

[0085] Combined with basic information, variables related to regional development are extracted into the system dynamics model to establish quantitative functional relationships.

[0086] The established system dynamics model needs to be historically tested, and the error rate of the historical test should be controlled within 10%.

[0087] Regional development variables include but are not limited to four types of variables: level variables, which accumulate values over time; rate variables, which influence the accumulation speed of state variables; auxiliary variables, which help establish connections between variables; and constants.

[0088] Functional equations between variables in system dynamics models include but are not limited to integral equations, linear equations, exponential equations, polynomial equations, power equations and table functions between variables.

[0089] 2. Select several scenario variables and reflect the binding / expected goals of regional policies in the system dynamics model to ensure that regional policies can have an impact on other regional development variables in the system dynamics model.

[0090] 3. Based on regional development variables and regional policy constraints, key policy objectives are selected for checks and balances to obtain several combinations of scenario variables. Among the several checks and balances, the result that is considered most suitable for the future development of the region is selected.

[0091] 4. Based on basic data and the regional development variable system dynamics model, the prediction results of the future scenario of the Yellow River Basin are digitized and visualized.

[0092] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0093] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily 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 is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A target area balance scenario prediction system based on system dynamics coupled genetic algorithm, characterized by: include: The data acquisition module (1) is used to obtain basic data in the target area and process the basic data to obtain corresponding multiple regional development variable data; A data processing module (2) is used to construct a system dynamics model based on a plurality of regional development variable data, establish corresponding quantitative functional relationships, and determine corresponding constraint conditions based on the system dynamics model and the quantitative functional relationships; A scenario generation module (3) is used to determine a plurality of target balancing scenarios based on the system dynamics model, the basic data of the variables, and the constraint conditions, and select the best target balancing scenario from the plurality of target balancing scenarios; A scenario prediction module (4) is used to perform scenario prediction based on the optimal target balancing scenario.

2. The target area balance scenario prediction system based on system dynamics coupled genetic algorithm according to claim 1 is characterized in that: The data processing module (2) comprises: A model building unit (21) is used to extract multiple regional development variable data into the system dynamics model, build the system dynamics model, and establish corresponding quantitative function relationships; A constraint condition determination unit (22) is used to determine the constraint conditions of the system dynamics model and the quantitative function relationship according to the expected target scenario variables; A scenario generating unit (23) is used to determine a plurality of target balancing scenarios based on the plurality of regional development variable data and the constraint conditions; The selection unit (24) is used to select the best target balancing scenario from multiple target balancing scenarios.

3. The target area balance scenario prediction system based on system dynamics coupled genetic algorithm according to claim 2 is characterized in that: The implementation process of the model building unit (21) specifically includes: The system dynamics model is historically tested.

4. The target area balance scenario prediction system based on system dynamics coupled genetic algorithm according to claim 2 is characterized in that: The implementation process of the model building unit (21) specifically includes: The quantitative function relationship is obtained by fitting the relationship between multiple regional development variable data.

5. The target area balance scenario prediction system based on system dynamics coupled genetic algorithm according to claim 2 is characterized in that: The implementation process of the selection unit (24) specifically includes: A multi-objective optimization genetic algorithm is used to select the best target balancing scenario from multiple target balancing scenarios.

6. The target area balance scenario prediction system based on system dynamics coupled genetic algorithm according to claim 1 is characterized in that: The data acquisition module (1) comprises: A collection unit (11) is used to obtain basic data of the target area, wherein the basic data includes regional environmental emission data, regional ecological data, regional economic and consumption data, and regional energy use data; The pre-processing unit (12) is used to process the basic data to obtain corresponding multiple regional development variable data.

7. A method for implementing a target area balancing scenario prediction system based on a system dynamics coupled genetic algorithm according to any one of claims 1 to 6, characterized in that: The following steps are involved: Acquiring basic data in the target area and processing the basic data to obtain corresponding multiple regional development variable data; Extract multiple regional development variable data into the system dynamics model, build the system dynamics model, and establish the corresponding quantitative function relationship; Determine the constraints, select several variables from the system dynamics model as scenario variables, reflect the constraints / expected goals of regional policies in the system dynamics model, and generate multiple target scenarios; Using a genetic algorithm that uses multi-objective optimization, the best target balancing scenario is selected from multiple target balancing scenarios; The optimal target balance scenario is input into the system dynamics model to obtain the predicted values of regional development variables in the model and complete the scenario forecast.

Images