Regional resource collaborative optimization configuration method, device, equipment and medium
By improving the multi-target gray wolf algorithm and optimizing resource allocation in the water-energy-food link system, the problem of low efficiency of resource collaborative optimization in the existing technology is solved, and a faster and more accurate resource allocation solution is achieved.
Patent Information
- Application Number
- CN202411017169.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-22
AI Technical Summary
When the existing metaheuristic algorithm deals with the multi-objective optimization problem of the water-energy-food link system, there are problems such as slow computing speed and difficult to achieve optimal solution results, which makes it difficult to effectively weigh the convergence and distribution of algorithms, resulting in resource collaborative optimization. Inefficient configuration.
Using the improved multi-objective gray wolf algorithm, the optimal location of straw power plants is determined by dividing the research areas, and a multi-objective multi-factor collaborative optimization configuration model is constructed. The crop planting area and channel lining length of investment and construction are used as decision variables to optimize the area. Resource allocation includes optimizing crop planting structure, channel length and straw power generation.
The calculation speed and solution accuracy of regional resource collaborative optimization configuration are improved, the problems of high time complexity and poor solution effect are solved, and more efficient resource allocation planning is achieved.
Smart Images

Figure CN119005400A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of natural resource management, and in particular to a method, device, equipment and medium for collaborative optimization of regional resource allocation. Background Art
[0002] Water, energy and food are the cornerstones of human survival and well-being. The three are intertwined and affect the sustainable development of the region. However, due to the deterioration of supply and demand, climate change, fragmented planning policies and department-centered resource management methods, the above resources are facing the risk of shortage. A systematic approach is urgently needed to optimize the use of multi-user resources. As a systematic approach, the water-energy-food nexus has gradually become a powerful tool for regional resource system planning and policy making since the 2011 Bonn Conference. With the deepening of research, the water-energy-food nexus system not only involves the "core system" of resources, but also includes "peripheral systems" such as the environment, economy, and society. The traditional nexus approach is difficult to reflect the trade-offs and coordination process of the multi-user resource utilization process of the system, and cannot effectively support the coordinated optimization decision-making of regional resources.
[0003] Metaheuristic algorithms provide an effective method for solving multi-objective optimization problems in link systems due to their simplicity, flexibility, no deduction, and avoidance of local optimality. However, current metaheuristic algorithms have the following problems: 1) They often use the method of calculating crowding distance or density to select populations, which easily leads to high algorithm time complexity and low computing speed when dealing with multi-objective optimization problems; 2) It is difficult to effectively balance the convergence and distribution of the algorithm, and the solution is difficult to achieve the optimal result.
[0004] Therefore, there is an urgent need for a regional resource collaborative optimization configuration method with high computing speed and high solution accuracy. Summary of the invention
[0005] The purpose of this application is to provide a method, device, equipment and medium for collaborative optimization configuration of regional resources, which can improve the calculation speed and solution accuracy of collaborative optimization configuration of regional resources.
[0006] To achieve the above objectives, this application provides the following solutions:
[0007] In a first aspect, the present application provides a method for collaborative optimization configuration of regional resources, including:
[0008] Divide the study area into several sub-areas;
[0009] Determine the optimal location of the straw power plant corresponding to each of the sub-areas;
[0010] Taking the crop planting area and the length of the channel lining invested and constructed as decision variables and the operating years of the straw power plant as the life cycle, a multi-objective and multi-factor collaborative optimization configuration model of the link system is constructed; the multi-objective and multi-factor collaborative optimization configuration model of the link system includes an objective function and constraints; the objective function includes a first objective function with the minimum water consumption as the goal and a second objective function with the maximum benefit of the main crop planting and straw power generation as the goal; the water consumption is composed of the water consumption of the main crops and the water consumption of coal-related energy enterprises and straw power plants;
[0011] The improved multi-objective grey wolf algorithm is used to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system to obtain an optimized regional resource allocation plan; the optimized regional resource allocation plan includes optimizing the crop planting structure of each sub-region, optimizing the canal length, and optimizing the power generation of the planned straw power plant.
[0012] In a second aspect, the present application provides a regional resource collaborative optimization configuration device, comprising:
[0013] The regional division module is used to: divide the research area into several sub-areas;
[0014] A power plant location determination module is used to: determine the optimal location of the straw power plant corresponding to each of the sub-areas;
[0015] The model building module is used to: take the crop planting area and the length of the channel lining invested and constructed as decision variables, and take the operating years of the straw power plant as the life cycle, to build a multi-objective and multi-factor collaborative optimization configuration model of the link system; the multi-objective and multi-factor collaborative optimization configuration model of the link system includes an objective function and constraint conditions; the objective function includes a first objective function with the minimum water consumption as the goal and a second objective function with the maximum benefit of the main crop planting and straw power generation as the goal; the water consumption is composed of the water consumption of the main crops and the water consumption of the coal-related energy enterprises and the straw power plant;
[0016] The model solving module is used to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system using an improved multi-objective grey wolf algorithm to obtain an optimized regional resource allocation plan; the optimized regional resource allocation plan includes optimizing the crop planting structure of each sub-region, optimizing the canal length, and optimizing the power generation of the proposed straw power plant.
[0017] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for collaborative optimization configuration of regional resources.
[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for collaborative optimization configuration of regional resources.
[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0020] The present application provides a method, device, equipment and medium for collaborative optimization configuration of regional resources, divides the study area into several sub-areas, determines the optimal position of the straw power plant corresponding to each of the sub-areas, takes the crop planting area and the length of the channel lining invested and constructed as decision variables, takes the operating years of the straw power plant as the life cycle, constructs a multi-objective and multi-factor collaborative optimization configuration model of the link system, uses the improved multi-objective gray wolf algorithm to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system, and obtains an optimized regional resource allocation plan, which solves the problems of high time complexity and poor solution effect of the existing metaheuristic algorithm, and improves the calculation speed and solution accuracy of the collaborative optimization configuration of resources in the study area. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0022] Figure 1 This is an application environment diagram of a method for collaborative optimization configuration of regional resources in one embodiment of the present application;
[0023] Figure 2 A flowchart of a method for collaborative optimization configuration of regional resources provided in one embodiment of the present application;
[0024] Figure 3 A schematic diagram of a process for solving the optimal location of a planned straw power plant in a region provided in an embodiment of the present application;
[0025] Figure 4 A schematic diagram of the improved multi-objective grey wolf algorithm flow chart provided in one embodiment of the present application;
[0026] Figure 5 A schematic diagram of the theoretical principle of polygon interior point determination provided by an embodiment of the present application; Figure 5 (a) is a schematic diagram showing the situation where the coordinate point is outside the polygon; Figure 5 (b) is a schematic diagram showing the situation where the coordinate point is not outside the polygon;
[0027] Figure 6A schematic diagram of a simulated PF of each algorithm in a ZDT test problem provided in an embodiment of the present application; Figure 6 (a), (b), and (c) are schematic diagrams of PF simulation of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in the ZDT1 test problem; Figure 6 (d), (e), and (f) are schematic diagrams of PF simulation of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in ZDT3 test problem, respectively; Figure 6 (g), (h), and (i) are schematic diagrams of simulating PF of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in the ZDT6 test problem, respectively;
[0028] Figure 7 A schematic diagram of a simulated PF of each algorithm in an IMOP test problem provided in an embodiment of the present application; Figure 7 (a), (b), and (c) are schematic diagrams of simulating PF of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in the IMOP5 test problem; Figure 7 (d), (e), and (f) are schematic diagrams of simulating PF of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in the IMOP6 test problem; Figure 7 (g), (h), and (i) are schematic diagrams of simulating PF of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in the IMOP8 test problem, respectively;
[0029] Figure 8 A schematic diagram of a simulated PF for a CF test problem of each algorithm provided in an embodiment of the present application; Figure 8 (a), (b), and (c) are schematic diagrams of simulating PF of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in the CF1 test problem; Figure 8 (d), (e), and (f) are schematic diagrams of simulating PF of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in CF2 test problem, respectively; Figure 8 (g), (h), and (i) are schematic diagrams of PF simulation of ENS-MOGWO algorithm, MO-GWO algorithm, and MO-PSO algorithm in CF8 test problem, respectively;
[0030] Fig. 9 A schematic diagram of functional modules of a regional resource collaborative optimization configuration device provided in one embodiment of the present application.
[0031] Fig.10 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0033] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0034] The regional resource collaborative optimization configuration method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on the cloud or other servers. The terminal can send the model of the study area to the server. After the server receives the model of the study area, it divides the study area to obtain several sub-areas, determines the optimal position of the straw power plant corresponding to each of the sub-areas, takes the crop planting area and the length of the channel lining invested and constructed as decision variables, and takes the operating years of the straw power plant as the life cycle to construct a multi-objective and multi-factor collaborative optimization configuration model of the link system. The multi-objective and multi-factor collaborative optimization configuration model of the link system is solved by using the improved multi-objective gray wolf algorithm to obtain an optimized regional resource allocation plan. The server can feedback the obtained optimized regional resource allocation plan for the study area to the terminal. In addition, in some embodiments, the regional resource collaborative optimization configuration method can also be implemented by a server or a terminal alone, such as the terminal can directly perform resource collaborative optimization configuration for the study area, or the server can obtain the model of the study area from the data storage system and perform resource collaborative optimization configuration for the study area.
[0035] The terminal may be, but is not limited to, various desktop computers, laptop computers, smart phones, and tablet computers. The server may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.
[0036] In an exemplary embodiment, Figure 2 As shown, a method for collaborative optimization configuration of regional resources is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1The server in the example is used to illustrate, including the following steps 101 to 104. Among them:
[0037] Step 101: Divide the study area into several sub-areas.
[0038] Step 102: Determine the optimal location of the straw power plant corresponding to each of the sub-areas.
[0039] Step 103: Taking the crop planting area and the length of the channel lining invested and constructed as decision variables and the operating years of the straw power plant as the life cycle, a multi-objective and multi-factor collaborative optimization configuration model of the link system is constructed; the multi-objective and multi-factor collaborative optimization configuration model of the link system includes an objective function and constraints; the objective function includes a first objective function with the minimum water consumption as the goal and a second objective function with the maximum benefit of main crop planting and straw power generation as the goal; the water consumption is composed of the water consumption of main crops and the water consumption of coal-related energy enterprises and straw power plants.
[0040] Step 104: using the improved multi-objective grey wolf algorithm, the multi-objective multi-factor collaborative optimization configuration model of the link system is solved to obtain an optimized regional resource allocation plan; the optimized regional resource allocation plan includes optimizing the crop planting structure of each sub-region, optimizing the canal length, and optimizing the power generation of the proposed straw power plant.
[0041] Implement the above-mentioned steps 101 to 104, use the improved multi-objective gray wolf algorithm to solve the multi-objective and multi-element collaborative optimization configuration model of the link system, and obtain the optimized regional resource allocation plan, which solves the problem of high time complexity of the existing metaheuristic algorithm and improves the calculation speed of the collaborative optimization configuration of regional resources. In addition, it is difficult for existing algorithms to balance the convergence and distribution of the solution results. In addition, the constraints of various complex conditions of the link system greatly limit the application of metaheuristic optimization algorithms in the multi-objective optimization problems of realistic link systems. The present application can clarify the feedback relationship between complex system elements, simulate the resource allocation planning process of agriculture, water resources and energy departments, and can efficiently solve the problem of conflict of interests in the system planning process, avoid unreasonable decision-making in the resource allocation of the link system, and solve the problems of low efficiency in solving high-dimensional constraint problems and difficulty in balancing the convergence and distribution of solution results in the existing link system optimization methods.
[0042] First, the boundaries, ties and core stakeholders of the water-energy-food linkage system are determined. The determination of the boundaries, ties and core stakeholders of the linkage system is based on the current situation of the study area and the proposed energy planning and construction. Among them, the proposed energy planning and construction plan is to carry out water rights replacement in the irrigation area, that is, in addition to the water rights replacement between regions, the water rights replacement plan of "taking water from the food system by coal-related energy enterprises and the planned straw power plant to ensure the water use of coal-related enterprises and develop crop straw power generation; the food system obtains the water cost of the energy system, which is used to invest in the construction of agricultural water-saving equipment and projects" is implemented in the Hetao Irrigation District.
[0043] This application uses the Hetao Irrigation District as the research area. The system boundaries, ties and core stakeholders include surface water and groundwater consumption during regional crop planting, water consumption during the growth cycle of major crops (including spring and summer irrigation, autumn irrigation, and autumn pouring), and water ecological replenishment during the intervals between agricultural irrigation; irrigation electricity consumption during agricultural production, water consumption during the production process of major energy companies; and diesel and other energy consumption during the planting of major crops. Under the system boundaries determined here, the core stakeholders mainly include farmers, coal-related energy companies, power plants, water resources management departments, and regional management departments. Among them, the main crop types in the irrigation area include wheat, corn, sunflower, melons, and tomatoes; the irrigation area sub-areas are divided according to administrative units, including Dengkou County, Hangjinhou Banner, Linhe District, Wuyuan County, and Urad Front Banner.
[0044] Simulate the spatial distribution of regional water resources, energy and crop planting structure: The spatial distribution of system resources includes the distribution of major crop planting areas in each sub-region, the distribution of crop planting and energy production and consumption under different water source types, and the distribution of energy sector production capacity. Among them, it is necessary to simulate and optimize the proposed location and scale of the straw power plant, and obtain the optimal location and construction scale of the straw power plant through the differential evolution algorithm and polygon interior point judgment theory.
[0045] In another exemplary embodiment of the present application, Figure 3 As shown, step 102 may include the following steps 201 to 204:
[0046] Step 201: for each sub-region, using a path planning algorithm, determine a path length according to the high-definition remote sensing data of the sub-region; the path length includes the distance from all straw collection and storage stations in the sub-region to the straw power plant;
[0047] Step 202: constructing a regional straw power plant cluster optimization distribution model;
[0048] Step 203: Solve the optimal distribution model of the straw power plant cluster in the region by using the differential evolution algorithm and the polygon interior point judgment theory to obtain the optimal location of the straw power plant corresponding to each of the sub-regions. Solve the optimal distribution model of the straw power plant cluster in the region, specifically including: solve the optimal distribution model of the straw power plant cluster in the region by using the differential evolution algorithm and the polygon interior point judgment theory.
[0049] Step 204: construct the construction scale of the straw power plant according to the optimal location of the straw power plant corresponding to the sub-region, specifically: obtain the optimal plant group location distribution, that is, the optimal location of the straw power plant in each sub-region j, and calculate the construction scale of the proposed straw power plant in each sub-region based on the different crop planting structures of each sub-region over the years.
[0050] In order to obtain the location and construction scale of the straw power plant in the study area, this application takes the Hetao Irrigation District as the study area and divides the Hetao Irrigation District into five sub-areas (j=1 for Wuyuan, j=2 for Linhe, j=3 for Urad Front Banner, j=4 for Hangjin Hou Banner, and j=5 for Dengkou County) and calculates the straw quantity of five main crops (c=1: wheat, c=2: corn, c=3: sunflower, c=4: melon, and c=5: tomato), and makes the following settings: (1) Only one straw power plant is built in each sub-area, and in order to avoid competition for straw among straw power plants, it is stipulated that the straw in each sub-area is only allowed to be sent to the straw power plant in the sub-area; (2) The coordinate point of the straw storage station in each sub-area is the geographical coordinate of the town government, denoted as p jk (x jk ,y jk ), the coordinates of the proposed straw power plant in each sub-area are P(X j ,Y j ); (3) The unit transportation cost of each sub-region is the same, and the straw is transported by fully loaded vehicles of the same model; (4) The construction period of each straw power plant is 1 year, and the average daily power generation hours must not be less than 12 hours. The construction location of the straw power plant can be determined by calculating the minimum transportation cost TS in each sub-region. j The expression of the regional straw power plant cluster optimization distribution model is as follows:
[0051]
[0052] Among them, DIS j is the distance between the straw storage station in sub-region j and the regional straw power plant; and are the fuel consumption of the vehicle in a single round trip between sub-areas j in a fully loaded and unloaded mode; PFUEL is the average annual unit price of fuel; Q load is the amount of straw fully loaded on the carrier (kg); represents the average annual amount of straw in area k of sub-region j; c represents the grass-to-grain ratio of crop c; c = 1, 2, 3...C, C represents the number of crop types planted in area k of sub-region j; k c is the collection coefficient of crop c; ARE jck is the average annual planting area of crop c in region k of subregion j, k = 1, 2, 3...K, K represents the number of town governments in subregion j; YIELD jck is the average annual yield of crop c in region k in region j; is the average annual rate of straw conversion into fuel.
[0053] The constraints of the regional straw power plant cluster optimization distribution model meet the following conditions: (X j ,Y j )∈(x j ,y j ); where (x j ,y j ) are the longitude and latitude coordinates of the points in the j sub-region. The above constraints can be implemented by the inpolygon algorithm.
[0054] The polygon interior point determination theory calls the inpolygon method that comes with MATLAB, which requires four parameters to be determined: the longitude and latitude of the determination point and the longitude and latitude of the boundary point of the polygon corresponding to the sub-region. [in, ~] = inpolygon (xq, yq, xv, yv) returns in to indicate whether the query point specified by xq and yq is inside the edge of the polygon sub-region defined by xv and yv.
[0055] A ray is made with the coordinate point, and whether the coordinate point is within the sub-region is determined according to the intersection of the ray and the boundary of the sub-region.
[0056] like Figure 5 As shown in (a), when the number of times the ray crosses the polygon boundary is even, all even-numbered crossings (including the last intersection) are outgoing crossings, and therefore all odd-numbered crossings (including the first intersection) are incoming crossings, and this coordinate point is outside the polygon.
[0057] like Figure 5 As shown in (b), when the number of times the ray crosses the polygon boundary is odd, all odd-numbered crossings (including the first intersection and the last intersection) are out-crossings, from which it can be inferred that the coordinate point is inside the polygon.
[0058] Build the linkage system database: The basic data of the linkage system database include the operating parameters of the planned power plant, reasonable construction location and scale, investment, operation, maintenance, labor and other costs of the power plant, calorific value of combustion of different crops, emission coefficients of greenhouse gases such as CO2, water consumption and planting area of different crops in each region, crop planting, irrigation, labor and harvesting costs under different irrigation methods, construction costs of water-saving projects, agricultural and energy water prices, sales prices of different crops, power generation prices, and benchmark discount rates.
[0059] After obtaining the optimal location and scale of straw power plants in each region, the multi-user economic benefit objectives and resource utilization benefit objectives were comprehensively considered, with the goal of maximizing economic benefits and minimizing water resource consumption, and the crop planting area ARE jcmt and investment in channel lining length ICL t As the decision variable, the operating life of the straw power plant is taken as the life cycle (T = 20), and two irrigation methods, flood irrigation (m = 1) and well-channel combined drip irrigation (m = 2), are considered to construct a multi-objective and multi-factor collaborative optimization configuration model of the link system. The multi-objective and multi-factor collaborative optimization configuration model of the link system is constructed as follows:
[0060] The water resource consumption target f1 is the minimum water consumption of major crops, coal-related enterprises, and straw power generation during the planning period. The economic target f2 is the maximum income from major crop planting and straw power generation during the entire planning period. The income from crop planting can be expressed by multiplying the discount coefficient β by the difference between income and cost; the income from straw power generation can be expressed by the extended net present value of straw power generation with the help of real option theory, which includes two parts: net present value NPV and real option OV.
[0061]
[0062] Among them, min f1 is the first objective function, min f2 is the second objective function; W F Indicates the water consumption of main crops, W E represents the water consumption of coal-related energy enterprises and straw power plants; β is the discount factor, which can be calculated by the average annual interest rate and the average annual inflation rate l to calculate, I F and C F I represents the crop benefits and costs of the food system respectively; F The income from the sale of crops and their straw is included; F It is the cost of crop planting, including the cost of seeds per unit area of crops, the cost of using film, the cost of using fertilizers and pesticides, water and electricity fees, and the cost of building well-channel combined drip irrigation, etc. Among them, the cost of well-channel combined drip irrigation includes the cost of water source wells and the head hub, the cost of drip irrigation belts, and the cost of facilities such as ground and underground pipelines; NPV is the net present value of straw power generation; OV is the option value of the straw power plant.
[0063]
[0064] Among them, PCROP ct represents the sales price of crop c in period t; PS t is the price of unit straw in period t; YIELD jcmt is the yield per unit area of crop c planted in sub-area j under irrigation method m during period t; SED ct is the seed cost per unit area of crop c in period t; TF t is the cost of thin film per unit area during period t; FET cmt and PES cmt They represent the fertilizer cost and pesticide cost per unit planting area of crop c under irrigation method m in period t; WE cmt represents the water and electricity costs per unit area of crop c under irrigation method m during period t; LAB t MEC is the labor cost per unit planting area of crops in period t; t FWS is the management cost per unit area of crops in period t, which includes the management costs during tillage, sowing, fertilization, irrigation and harvesting; jct CWC represents the drip irrigation area of crop c in sub-area j adjusted to well-canal combined drip irrigation in period t; t The cost required to build a well-channel combined drip irrigation system includes: water source well and head hub costs, drip irrigation tape costs, ground and underground pipelines and other facilities costs.
[0065] Based on the whole life cycle process, considering the cost-benefit of biomass power generation straw collection, straw transportation and power plant operation, the net present value is calculated as follows:
[0066]
[0067] Among them, GEN jt is the income from electricity sales of straw power generation in sub-region j during period t; CO jt represents the potential benefit of CO2 emission reduction from straw power generation in sub-region j during period t; O&M jt TAX is the operation and maintenance cost of straw power generation in sub-region j during period t; jt represents the tax revenue during the straw power generation process in sub-region j during period t; CS jt is the cost of collecting straw in sub-area j during period t; TS jt is the cost of transporting straw to sub-region j during period t; WRT jt INV is the cost of replacing water in sub-area j during period t; j The investment cost of building a straw power plant in sub-region j; ASH jt It is represented by the revenue from selling plant ash in sub-region j during period t; STOR jtis the cost of storing straw in sub-region j during period t, including labor costs, etc.; r0 represents the base discount rate; t1 is the time when the straw power plant starts to invest.
[0068] Among them, the income from electricity sales from straw power generation is expressed as follows:
[0069]
[0070] GE jt =GE j(t-1) (1-dr) (9);
[0071] Where EH jt is the effective power generation time of sub-region j during period t; GE j is the power generation efficiency of sub-region j; IC j is the installed capacity of straw power plant in sub-region j; CONSUMP is the self-consumption rate of straw power plant; dr is the system power efficiency reduction rate; FIT t is the on-grid electricity price in period t. With the advancement of market-oriented electricity prices, the change of electricity prices will be a random process, satisfying the geometric Brownian motion:
[0072] dFIT t =μ E FIT t dt+σ E FIT t dW t E (10);
[0073] Where μ E and σ E Respectively represent the drift rate and volatility of the on-grid electricity price; dW t E is an increment of the standard Wiener process, Conforms to the standard normal distribution, FIT t It can be obtained by using Ito's lemma.
[0074] The potential income from CO2 emission reduction during straw power generation can be expressed as:
[0075]
[0076] Where ξ represents the CO2 emission coefficient; PCO t represents the CO2 transaction price (yuan / ton). According to previous studies, PCO t It is described as a random process that conforms to the geometric Brownian motion, which can be described as follows:
[0077] dPCO t =μ C PCO tdt+σ C PCO t dW t C (12);
[0078] Where μ C and σ C Respectively represent the drift rate and volatility of CO2 price; dW t is an increment of the standard Wiener process, Conforms to the standard normal distribution, PCO t The solution process is the same as the on-grid electricity price.
[0079] The operation and maintenance costs during straw power generation are shown in the following formula:
[0080]
[0081] Where OMC t It is the unit operation and maintenance cost of the straw power plant.
[0082] The straw collection cost is expressed as follows:
[0083]
[0084] in, represents the amount of straw of crop c in region j during period t, The relationship between it and the calorific value efficiency of straw power generation is as follows:
[0085]
[0086] Among them, GCV c is the lower calorific value of the crop (kJ / kg).
[0087] The cost of straw transportation is:
[0088]
[0089] Among them, PFUEL t is the fuel price in period t (yuan / L).
[0090] The tax expenses in the process of straw power generation are as follows
[0091]
[0092] in, represents value added tax, represents corporate income tax, and Represent the tax rates of value added tax and corporate income tax respectively.
[0093] The water cost of straw power plant replacement is calculated as follows:
[0094] WRT jt =EH jt ·IC j GE jt ·ω t WRTP (18);
[0095] Where WRTP is the unit price of replacement water; ω t It is the water consumption per unit of power generation in straw power plant.
[0096] The income from the ash produced by straw power generation is calculated as follows:
[0097] ASH jt =EH jt ·IC j GE jt PASH (19);
[0098] Where PASH is the income of wood ash per unit of electricity generation.
[0099] The cost of storing straw is calculated as follows:
[0100]
[0101] Where USTOR is the unit cost required to store straw.
[0102] The investment and construction cost of a straw power plant can be calculated by the following formula: UINV represents the unit construction cost of straw power plant.
[0103] The option value of the straw power plant can be solved by the Black-Scholes differential equation and the BS option pricing model is obtained. This model is a European call option value evaluation model based on interest-free payment, which is expressed as follows:
[0104] OV=S0N(d1)-e -r(T-t) KN(d2) (21);
[0105] in,
[0106]
[0107] In the formula, S0 represents the present value of the straw power generation underlying asset; K represents the present value of the option exercise price; N(·) represents the cumulative normal distribution function; Tt represents the option validity period; r represents the risk-free rate of return, which can be replaced by selecting the treasury bond interest rate closest to the expiration date and the option validity period; d1 and d2 are intermediate variables, which are functions of the asset present value, the present value of the exercise price, the option validity period, the risk-return rate and the asset volatility; σ represents the volatility of the underlying asset, which can be calculated by the standard deviation of the continuous compounding rate of return of the underlying asset:
[0108] r=ln(F / P) / t country (twenty two);
[0109]
[0110] Among them, F represents the final value of the national debt; P represents the present value of the national debt; t country The duration of the bond maturity (a); S is the value of the underlying asset; is the mean of the continuous compound interest rate of the underlying asset
[0111]
[0112] Among them, IWQ cmt AWQ represents the irrigation quota of crop c under irrigation method m during period t; j It represents the autumn watering amount per unit area in region j.
[0113] Considering the basic requirements of water, energy and food production and the cost limit of investing in water-saving irrigation projects, the constraints of the multi-objective and multi-factor collaborative optimization configuration model of the link system in this application include agricultural and energy water consumption constraints, drip irrigation area constraints, channel lining length constraints, planting area constraints, food production constraints, power generation time constraints and non-negative constraints of decision variables. The details are as follows:
[0114] 1) Constraints on agricultural and energy water consumption: Under water-saving irrigation conditions, the sum of water consumption and energy water consumption during the planting of major crops is less than the total water available for agriculture:
[0115]
[0116] Among them, TCL is the length of the main canal lined with lining; ULW is the water leakage per unit length of the canal system; ε is the proportion of lining that has been constructed; UWS is the water saving per unit length of the canal system after lining; WDQ represents the annual average ecological water replenishment between irrigation intervals; t is the total amount of water available for the five main crops during period t.
[0117] 2) Drip irrigation area constraint: The area that can be adjusted to well-channel combined drip irrigation in each planning year FWS jct The maximum adjustment area not exceeding Among them, TWSF j It represents the maximum drip irrigation area that can be adjusted to well-channel dual irrigation in the j sub-region in any planning year, and c is the main crop type.
[0118] 3) Invest in the construction of channel lining length ICL in each planning year t Not exceeding the maximum annual construction length specified, i.e. MCL is the annual planned maximum lining length.
[0119] 4) Planting area constraints: To ensure food security, the planting area of major crops in each region must be limited to a certain range within a certain period of time, that is, in, and are the minimum and maximum planting areas of the j-th sub-region respectively.
[0120] 5) Grain production constraints: The total production of major crops in the region must not be less than the minimum demand:
[0121]
[0122] in, It represents the minimum demand (kg) of crop c in sub-region j during period t.
[0123] 6) Power generation duration constraints: The effective duration of power generation in each region within a year must not be less than the minimum effective operation duration: EH min Indicates the minimum effective operating time of a power plant.
[0124] 7) Non-negative constraints on decision variables:
[0125] like Figure 4 As shown, the above step 104 can be replaced by the following steps 301 to 305:
[0126] Step 301: Initialize algorithm parameters and population decision variables, and set the optimal archive set to empty; the algorithm parameters include the maximum number of iterations, population individuals, and reference points; the reference points are used to establish a mapping relationship between the solution set and the reference points;
[0127] Step 302: using a non-dominated sorting method, sorting the individuals in the population according to the objective function values corresponding to the individuals in the population; the objective function values corresponding to the individuals in the population are obtained by calculating the objective function of the multi-objective and multi-factor collaborative optimization configuration model of the linkage system;
[0128] Step 303: using the microhabitat retention strategy, performing environmental selection on the population according to the reference point to obtain the population after environmental selection;
[0129] Step 304: Using the binary tournament selection method, the improved multi-stage evolutionary algorithm and the hunting strategy to update the population after environmental selection, obtain the population individuals with the highest non-dominated level and save them into the optimal archive set, specifically including:
[0130] The binary tournament method is used to select the population after environmental selection to obtain the first population;
[0131] Determine the group with the highest non-dominance rank from the first population to obtain the second population;
[0132] The improved multi-stage evolutionary algorithm was used to identify three leading wolves from the second population;
[0133] According to the results of the three leading wolves, all population individuals after environmental selection are updated with the help of hunting strategies, and the population individuals with the highest non-dominant level are obtained and saved in the optimal archive set.
[0134] Step 305: Determine whether the number of iterations reaches the maximum number of iterations. If so, determine the population individuals in the optimal archive set as the optimized regional resource allocation plan; if not, loop through steps 302-305.
[0135] Step 301: Initialize algorithm parameters and population decision variables, and set the optimal archive set to zero, and initialize the number of iterations iter to 0. It should be noted that the improved multi-objective gray wolf algorithm only needs to preset three parameters: the maximum number of iterations maxIter, the population individuals, and the reference points. Among them, the reference points are used to establish a mapping relationship between the solution set and the reference points in step 303, and to achieve the diversity of the solution set distribution by generating uniformly distributed reference points. For a multi-objective problem with an M-dimensional target space and each target divided by H points, the number of reference points generated by the boundary layer is Where C represents a combinatorial operation. Let the reference point set in the M-1-dimensional unit simplex boundary layer be r1 = (r1, r2, ..., r M ), and satisfies r j ={0 / H,1 / H,...,H / H}, The steps to generate reference points are as follows:
[0136] (1) Let x be an (M-1)-dimensional combination, x = {0 / H, 1 / H, ..., (H+M-2) / H};
[0137] (2) For each x ij ∈x,x ij =x ij -(j-1) / H, where i∈[1,N] represents the combined position of the reference point in the j dimension;
[0138] (3) For each r ij ∈r1, which can be connected with x ij The following relation for ∈x is obtained:
[0139]
[0140] (4) Based on the above reference point set r1, an internal reference point set r2 is constructed, which can be obtained through the relationship with r1. The relationship between the two is as follows:
[0141] r' ij =1 / 2(r ij +M) (27);
[0142] Among them, r ij ∈r1,r' ij ∈r2;
[0143] (5) Finally, the boundary and internal reference points are merged to construct the standard hyperplane reference point set r = r1∪r2.
[0144] Step 302: Calculate the objective function and constraint violation values, and classify the population according to the efficient non-dominated sorting method. The efficient non-dominated sorting method sorts the population by the objective function value, and only needs to compare the population in front of the current individual to achieve the non-dominated level division; the objective function value and the constraint violation value are used to represent the "virtual target cost", and finally the dominance relationship between the individuals in the population is determined with the help of the level division and the "virtual target cost". Among them, the "virtual target cost" is calculated as follows (assuming that the solutions of the two individuals are x1 and x2 respectively):
[0145] (1) If x1 and x2 are both feasible solutions, the dominance relationship is determined by calculating the objective function values of the two solutions;
[0146] (2) If x1 is a feasible solution and x2 is an infeasible solution, then
[0147] (3) If both x1 and x2 are infeasible solutions, the solution with the smaller constraint violation dominates the other solution. The constraint violation value is calculated as follows:
[0148]
[0149] g i (x)≥b i ;h j (x) = 0;
[0150] In the formula, g i (x) and h j (x) represents two types of constraints: inequality and equality; and They are the standardized forms of the two constraints respectively; is the transposition operator, which returns the negative of a. When <0, it returns 0, otherwise it returns 。 Make becomes Obviously, the solution obtained by this transformation is a feasible solution that satisfies the constraints, and the value that violates the constraints returns 0; on the contrary, if The obtained solution is an infeasible solution, and its constraint violation value returns a number greater than 0. When both solutions are infeasible solutions, the dominant selection relationship can be obtained by comparing the sum of the constraint violation values of all constraints of the two solutions.
[0151] Step 303: Adopt the strategy of mapping reference points and solution sets and retaining small habitats to select the environment of the population. The idea of this environment selection method is to create a ray starting from an ideal point (a point constructed by satisfying the constraints and with the minimum value of each objective function in the population) and passing through the reference point of the unit simplex surface, calculate the vertical distance between the solution set and the reference ray, and select the individuals in the last level corresponding to the reference point with the least number of occurrences (retaining the small habitat) among the reference points associated with the population except the last level, until the number of selected populations meets the initial population number. The specific implementation process is as follows:
[0152] (1) Population standardization. In order to compare individuals from different populations, the multi-dimensional target values need to be dimensionless. Assume that the ideal point P t The coordinate value of where z min is the minimum value of each objective function of the population; f i is the i-th objective function value of the individual, i∈[1,2,...,M], then the population objective function value is standardized as follows:
[0153]
[0154] Among them, x represents a decision variable of the population; a i It represents the point where the unit simplex surface intersects the objective function of the i-th dimension, that is, the intercept. The intercept of each dimension can be obtained by introducing the extreme value point E i To calculate, the relationship between the two is as follows:
[0155] f(E i )·(1 / a i )=1(30);
[0156] The extreme value E i It means that the function value in dimension i is very large, while the function value in other dimensions is very small. The extreme value of each dimension can be calculated as follows:
[0157]
[0158] where w i is the weight vector; in order to reflect the extreme value characteristics, w i The weight in the i-th dimension is 1, and the weights in other dimensions can be set small enough; N represents the number of populations.
[0159] (2) Establishment of mapping relationship. The mapping relationship between the reference point and the solution set is represented by the vertical distance from the solution set to the reference ray. This application uses the method of calculating the Cosine distance to represent the mapping relationship between the two. The calculation formula is as follows:
[0160]
[0161] Among them, r k Indicates the reference point, and are the transpose of the solution set and the reference point, respectively.
[0162] (3) Microhabitat retention. In order to select the individuals to be retained from the last microhabitat population, the reference point passed by the reference ray closest to each population individual is obtained through the mapping relationship, and then the number of occurrences of each reference point in the 1st to last-1st level population is counted, and then the individual corresponding to the reference point with the least number of occurrences in the last level is selected. If there is no mapping relationship with this reference point in the individuals of the last level population, this reference point will be deleted when the next individual is selected and will no longer be counted. According to the above steps, the last microhabitat population is selected until the number of populations is met.
[0163] Step 304: Update the population according to the binary tournament random selection, improved multi-stage evolution and hunting strategy. In the population update stage, the update strategy of the multi-objective gray wolf algorithm is adopted, that is, when the gray wolf population finds prey and surrounds the prey, the leadership level wolves will always command the wolf pack to continuously update the hunting position to achieve the hunting of prey. Among them, α is the most important guide, and β and δ level wolves will also randomly participate in the command. Because the position of the prey is unknown, the gray wolf algorithm plus the assumption that the positions of α, β and δ can be more conducive to capturing prey, and are saved as the three current optimal solutions. Other gray wolves need to continuously update their positions according to the positions of these three leading wolves. The calculation process is as follows:
[0164]
[0165] in, It represents the position of the gray wolf in the next iteration, and its position change depends on the position of the leading wolf α, β and δ.
[0166] When selecting α, β and δ wolves, this application makes the following improvements to the multi-objective grey wolf algorithm:
[0167] (1) The binary tournament method (Tournament Selection) is used to select population A after environmental selection, with the aim of increasing the chances of excellent individuals being selected by α, β and δ wolves, and obtaining the first population (new population B).
[0168] (2) With the help of the multi-stage evolutionary idea, the group with the highest non-dominated level (the second population L1) (Rank = 1) is obtained from the first population, and the improved multi-stage evolutionary algorithm is used to select α, β and δ wolves from the second population L1. The pseudo code of the algorithm is shown in Table 1 below.
[0169] Table 1 Pseudo code of the improved multi-stage evolutionary algorithm
[0170]
[0171]
[0172] Among them, Div is calculated as follows:
[0173] Div(x)=||f'(x)-f'1(x)||+η||f'(x)-f'2(x)|| (36);
[0174] In the formula, f i '(x) represents the i-th standard target value of solution x; ||f'(x)-f'1(x)|| and ||f'(x)-f'2(x)|| represent the Euclidean distances to the nearest and second nearest solutions to x, respectively; η is the influence weakening factor, which aims to weaken the influence of ||f'(x)-f'2(x)|| on ||f'(x)-f'1(x)||.
[0175] Step 305: The number of iterations iter is increased by 1. If the number of iterations meets the maximum number of iterations, execute step 306; otherwise, execute steps 302 to 305 in a loop.
[0176] Then the optimal archive set is output (the optimal archive set is the optimized regional resource allocation plan) to obtain the optimal crop planting structure, canal length and power generation of the planned straw power plant in each sub-region in each planning year.
[0177] In an example of the present application, after obtaining the optimized regional resource configuration scheme, the regional resource collaborative optimization configuration method further includes:
[0178] Using the cone dominance inflection point theory, the final regional resource allocation plan is determined based on the optimized regional resource allocation plan. That is, the cone dominance inflection point theory is used to perform post-optimization processing of the optimization plan. The implementation process is as follows:
[0179] (1) Definition of objective weight function.
[0180]
[0181] Among them, Ω i () represents the target weight function, m is the number of target functions, a ij It is the gain in the j-dimensional target space due to the loss of one unit in the i-dimensional target space.
[0182] (2) Quantification of dominance relationship. The dominance of one decision variable x over another decision variable y can be expressed as:
[0183]
[0184] Right now where a 12 and a 21 It can be calculated by the following formula:
[0185]
[0186] Through the cone-dominated post-optimization method, the final regional resource allocation plan was obtained, including a reasonable crop planting structure, canal length, and a power generation decision plan for the proposed straw power plant.
[0187] In order to verify the effectiveness of this application in dealing with multi-objective problems, this application selected the inverse generation distance (IGD) indicator to judge the convergence and distribution of the solution.
[0188] In order to better reflect the performance of the algorithm and eliminate random effects, this application sets the number of each algorithm population to 200, the number of iterations to 1000, and repeats the run 5 times. In addition, in order to better verify the performance of the algorithm in solving convex, concave, discontinuous and multimodal problems, this application selected 2 sets of unconstrained benchmark test problem sets (ZDT, IMOP) and 1 set of constrained benchmark test problem sets (CF), each set of problems has 3 test functions. The results of various indicators of the ZDT test problem, IMOP test problem and CF test problem are shown in Table 2, Table 3 and Table 4 respectively. The simulated PF of each algorithm in the ZDT test problem, IMOP test problem and CF test problem are shown in Table 2, Table 3 and Table 4 respectively. Figure 6 , Figure 7 , Figure 8 shown.
[0189] Table 2 Results of various indicators of ZDT test problems
[0190]
[0191] Table 3 Results of various indicators of IMOP test problems
[0192]
[0193] Table 4 Results of various indicators of CF test problems
[0194]
[0195] The present application also provides an application scenario, which applies the above-mentioned regional resource collaborative optimization configuration method. Specifically: The regional resource collaborative optimization configuration method provided in this embodiment can be applied in the regional resource management scenario. The regional resource management scenario includes a regional determination link, a regional resource collaborative optimization configuration link and a regional resource management link; the model of the study area enters the regional resource collaborative optimization configuration link from the regional determination link, obtains the corresponding optimized regional resource configuration plan, and enters the downstream regional resource management link. The regional resource collaborative optimization configuration method provided in this embodiment belongs to the regional resource collaborative optimization configuration link. Specifically, in the process of the regional resource collaborative optimization configuration link for the study area, the study area can be divided to obtain several sub-areas, and the optimal position of the straw power plant corresponding to each of the sub-areas is determined. The crop planting area and the length of the channel lining invested and constructed are used as decision variables, and the operating years of the straw power plant are used as the life cycle. A multi-objective and multi-factor collaborative optimization configuration model of the link system is constructed, and the improved multi-objective gray wolf algorithm is used to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system to obtain an optimized regional resource configuration plan.
[0196] Based on the same inventive concept, the embodiment of the present application also provides a regional resource collaborative optimization configuration device for implementing the regional resource collaborative optimization configuration method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more regional resource collaborative optimization configuration devices provided below can refer to the limitations of the regional resource collaborative optimization configuration method above, and will not be repeated here.
[0197] In an exemplary embodiment, Fig. 9As shown, a regional resource collaborative optimization configuration device is provided, comprising:
[0198] The area division module T1 is used to: divide the research area into several sub-areas;
[0199] The power plant location determination module T2 is used to: determine the optimal location of the straw power plant corresponding to each of the sub-areas;
[0200] Model building module T3 is used to: take the crop planting area and the length of the channel lining invested and constructed as decision variables, and take the operating years of the straw power plant as the life cycle, to build a multi-objective and multi-factor collaborative optimization configuration model of the link system; the multi-objective and multi-factor collaborative optimization configuration model of the link system includes an objective function and constraints; the objective function includes a first objective function with the minimum water consumption as the goal and a second objective function with the maximum benefit of the main crop planting and straw power generation as the goal; the water consumption is composed of the water consumption of the main crops and the water consumption of coal-related energy enterprises and straw power plants;
[0201] The model solving module T4 is used to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system using the improved multi-objective grey wolf algorithm to obtain an optimized regional resource allocation plan; the optimized regional resource allocation plan includes optimizing the crop planting structure of each sub-region, optimizing the canal length, and optimizing the power generation of the proposed straw power plant.
[0202] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store regional resource collaborative optimization configuration processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for collaborative optimization configuration of regional resources is implemented.
[0203] Those skilled in the art will understand that Fig.10The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0204] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0205] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0206] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0207] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0208] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0209] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0210] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for collaborative optimization of regional resource allocation, It is characterized in that The method for collaborative optimization configuration of regional resources includes: Divide the study area into several sub-areas; Determine the optimal location of the straw power plant corresponding to each of the sub-areas; Taking the crop planting area and the length of the channel lining invested and constructed as decision variables and the operating years of the straw power plant as the life cycle, a multi-objective and multi-factor collaborative optimization configuration model of the link system is constructed; the multi-objective and multi-factor collaborative optimization configuration model of the link system includes an objective function and constraints; the objective function includes a first objective function with the minimum water consumption as the goal and a second objective function with the maximum benefit of the main crop planting and straw power generation as the goal; the water consumption is composed of the water consumption of the main crops and the water consumption of coal-related energy enterprises and straw power plants; The improved multi-objective grey wolf algorithm is used to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system to obtain an optimized regional resource allocation plan; the optimized regional resource allocation plan includes optimizing the crop planting structure of each sub-region, optimizing the canal length, and optimizing the power generation of the planned straw power plant.
2. The method for collaborative optimization of regional resource allocation according to claim 1, It is characterized in that The improved multi-objective grey wolf algorithm is used to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system to obtain an optimized regional resource allocation plan, which specifically includes: Step 301: Initialize algorithm parameters and population decision variables, and set the optimal archive set to empty; the algorithm parameters include the maximum number of iterations, population individuals, and reference points; the reference points are used to establish a mapping relationship between the solution set and the reference points; Step 302: using a non-dominated sorting method, sorting the individuals in the population according to the objective function values corresponding to the individuals in the population; the objective function values corresponding to the individuals in the population are obtained by calculating the objective function of the multi-objective and multi-factor collaborative optimization configuration model of the linkage system; Step 303: using the microhabitat retention strategy, performing environmental selection on the population according to the reference point to obtain the population after environmental selection; Step 304: using the binary tournament method, the improved multi-stage evolutionary algorithm and the hunting strategy to update the population after environmental selection, obtaining the population individuals with the highest non-dominated level and saving them into the optimal archive set; Step 305: Determine whether the number of iterations reaches the maximum number of iterations. If so, determine the population individuals in the optimal archive set as the optimized regional resource allocation plan; if not, loop through steps 302-305.
3. The method for collaborative optimization of regional resource allocation according to claim 2, It is characterized in that The binary tournament method, the improved multi-stage evolutionary algorithm and the hunting strategy are used to update the population after environmental selection, obtain the population individuals with the highest non-dominated level and save them in the optimal archive set, including: The binary tournament method is used to select the population after environmental selection to obtain the first population; Determine the group with the highest non-dominance rank from the first population to obtain the second population; The improved multi-stage evolutionary algorithm was used to identify three leading wolves from the second population; According to the results of the three leading wolves, all population individuals after environmental selection are updated with the help of hunting strategies, and the population individuals with the highest non-dominant level are obtained and saved in the optimal archive set.
4. The method for collaborative optimization of regional resource allocation according to claim 1, It is characterized in that Determining the optimal location of the straw power plant corresponding to each of the sub-areas specifically includes: For each sub-area, a path planning algorithm is used to determine the path length according to the high-definition remote sensing data of the sub-area; the path length includes the distance from all straw collection and storage stations in the sub-area to the straw power plant; Construct an optimal distribution model for regional straw power plant clusters; Solving the optimization distribution model of the straw power plant group in the region to obtain the optimal location of the straw power plant corresponding to each sub-region; The construction scale of the straw power plant is constructed according to the optimal location of the straw power plant corresponding to the sub-region.
5. The method for collaborative optimization of regional resource allocation according to claim 4, It is characterized in that Solving the optimal distribution model of the straw power plant cluster in the region includes: The differential evolution algorithm and polygon interior point judgment theory are used to solve the optimal distribution model of the straw power plant cluster in the region.
6. The method for collaborative optimization of regional resource allocation according to claim 1, It is characterized in that After obtaining the optimized regional resource allocation scheme, the regional resource collaborative optimization allocation method further includes: The cone dominance inflection point theory is used to determine the final regional resource allocation plan based on the optimized regional resource allocation plan.
7. The method for collaborative optimization of regional resource allocation according to claim 1, It is characterized in that The constraints include agricultural and energy water consumption constraints, drip irrigation area constraints, channel lining length constraints, planting area constraints, grain production constraints, power generation duration constraints and non-negative constraints on decision variables.
8. A regional resource collaborative optimization configuration device, It is characterized in that The regional resource collaborative optimization configuration device comprises: The regional division module is used to: divide the research area into several sub-areas; A power plant location determination module is used to: determine the optimal location of the straw power plant corresponding to each of the sub-areas; The model building module is used to: take the crop planting area and the length of the channel lining invested and constructed as decision variables, and take the operating years of the straw power plant as the life cycle, to build a multi-objective and multi-factor collaborative optimization configuration model of the link system; the multi-objective and multi-factor collaborative optimization configuration model of the link system includes an objective function and constraint conditions; the objective function includes a first objective function with the minimum water consumption as the goal and a second objective function with the maximum benefit of the main crop planting and straw power generation as the goal; the water consumption is composed of the water consumption of the main crops and the water consumption of the coal-related energy enterprises and the straw power plant; The model solving module is used to solve the multi-objective and multi-factor collaborative optimization configuration model of the link system using an improved multi-objective grey wolf algorithm to obtain an optimized regional resource allocation plan; the optimized regional resource allocation plan includes optimizing the crop planting structure of each sub-region, optimizing the canal length, and optimizing the power generation of the proposed straw power plant.
9. A computer device, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for collaborative optimization configuration of regional resources according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for collaborative optimization configuration of regional resources described in any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Photovoltaic grid-connected flexible direct current power transmission and energy storage cooperative control system and method
CN121150334A
Photovoltaic grid-connected flexible direct current power transmission and energy storage collaborative control system and method
CN121150334B
