Power supply scheme generation method based on multi-target mixed integer programming large model, medium and program product

Abstract

The invention discloses a power supply scheme generation method based on a multi-objective mixed integer programming large model, a medium and a program product, and the method comprises the steps: generating a personalized portrait function of a customer based on collected customer demand side information; generating a power supply scheme parameter set function based on the power supply scheme related parameters; based on the personalized portrait function of the customer and the power supply scheme parameter set function, generating a multi-objective mixed integer programming large model; and solving the multi-target mixed integer programming large model by adopting a branch and bound method, and determining an optimal power supply scheme suitable for the current customer. According to the method, the optimal power supply scheme suitable for the current customer is quickly determined based on the customer portrait function and the power supply scheme related parameters in combination with the branch and bound method and multi-target mixed integer programming.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence large models, and particularly relates to a power supply scheme generation method, medium and program product based on a multi-objective mixed integer programming large model. Background Art

[0002] With the increasing diversification of customer needs and technological progress, the limitations of traditional power supply scheme formulation methods have gradually emerged, and they cannot efficiently meet the personalized needs of different customers. In addition, some existing solutions have certain limitations in dealing with complex operations research algorithm problems, especially in the case where the demand side needs to comprehensively consider cost sensitivity, reliability requirements, and load change trends, and the grid side needs to take into account multiple variables and parameters such as the number of power sources, operation modes, available power supply capacity, designed connection modes, and transformer capacity selection for optimal configuration problems. Summary of the Invention

[0003] In view of the above problems, the present invention proposes a power supply scheme generation method, medium and program product based on a multi-objective mixed integer programming large model, which quickly determines the best power supply scheme suitable for the current customer based on the customer portrait function and power supply scheme related parameters, combined with the branch and bound method and multi-objective mixed integer programming.

[0004] To achieve the above technical objectives and effects, the present invention is realized through the following technical solutions:

[0005] In a first aspect, the present invention provides a power supply scheme generation method based on a multi-objective mixed integer programming large model, including:

[0006] Generating a personalized portrait function of a customer based on the collected customer demand side information;

[0007] Generating a power supply scheme parameter set function based on the power supply scheme related parameters;

[0008] Generating a multi-objective mixed integer programming large model based on the personalized portrait function of the customer and the power supply scheme parameter set function;

[0009] Solving the multi-objective mixed integer programming large model by using the branch and bound method to determine the best power supply scheme suitable for the current customer.

[0010] In combination with the first aspect, optionally, the method for generating the personalized portrait function of the customer includes:

[0011] Obtaining customer demand side information;

[0012] Based on the obtained customer demand side information, determining the sensitivity of the customer to electricity charges and the reliability requirements of the customer for the stability of power supply;

[0013] Based on the customer's sensitivity to electricity charges and the reliability requirements of the customer for the stability of power supply, a personalized portrait function of the customer is generated as P = f(C s , R r ), where C s is the customer's sensitivity to electricity charges, and R r is the reliability requirement of the customer for the stability of power supply.

[0014] Combined with the first aspect, optionally, the personalized portrait function of the customer is P = w cost ·C s + w reliability ·R r , where C s is the customer's sensitivity to electricity charges, R r is the reliability requirement of the customer for the stability of power supply, w cost is the weight of the customer's sensitivity to electricity charges, and w reliability is the weight of the reliability requirement of the customer for the stability of power supply.

[0015] Combined with the first aspect, optionally, the method for generating the power supply scheme parameter set function includes:

[0016] According to the expected load and geographical location, combined with the power supply scheme knowledge base mounted on the intelligent agent, determine the appropriate number of generating units to obtain the power quantity N g ;

[0017] Based on the power supply scheme knowledge base mounted on the intelligent agent and the relevant information of the user's application for electricity, recommend what type of power generation equipment to adopt to obtain the power operation mode O m ;

[0018] Based on the power supply scheme compilation knowledge base mounted on the intelligent agent and the relevant information of the user's application for electricity, determine the power supply capacity P c of the power source to ensure that the selected power source can meet the maximum load demand and leave a certain margin to cope with emergencies;

[0019] Based on the power supply scheme compilation knowledge base mounted on the intelligent agent and the user's application for electricity information, generate a reasonable power grid connection structure and determine the connection mode C l ;

[0020] Select a transformer with a suitable specification according to the user's needs and determine the transformer capacity T c ;

[0021] Based on the power quantity N g , power operation mode O m , power supply capacity P c , connection mode C l and transformer capacity T c, generate the power supply plan parameter set function S, S = g(N g , O m , P c , C l , T c ).

[0022] Combined with the first aspect, optionally, the optimization objective function of the multi-objective mixed-integer programming large model is related to cost, reliability, and flexibility.

[0023] Combined with the first aspect, optionally, the optimization objective function of the multi-objective mixed-integer programming large model is:[[]]

[0024] minimize Z = w1f C (x) + w2f R (x) + w3f F (x);

[0025] Among them, Z is the total objective function, w1, w2, w3 are the weight coefficients corresponding to different objective functions, and x represents the decision variable;

[0026] f C (x) represents the cost objective function, including construction cost and maintenance cost, and its mathematical expression is:[[]]

[0027]

[0028] f R (x) represents the reliability objective function, which is used to evaluate the probability that the power supply system can still operate normally under various fault conditions, and its mathematical expression is:[[]]

[0029]

[0030] f C (x) represents the flexibility objective function, which is used to measure the ability of the power supply system to adapt to future changes, and its mathematical expression is:[[]]

[0031]

[0032] Among them, c i , r j , f k are the coefficients related to cost, reliability, and flexibility respectively; P is the personalized portrait function of the customer, S is the power supply plan parameter set function, n is the number of different cost items involved in the cost objective function f C (x), m is the number of different reliability evaluation scenarios or indicators involved in the reliability objective function f R (x), and p is the number of different flexibility evaluation indicators or future change scenarios involved in the flexibility objective function f F (x).

[0033] In combination with the first aspect, optionally, the constraint conditions of the multi-objective mixed-integer programming large model include:

[0034]

[0035] where t i is the number of the i-th transformer, p i is the power output of the i-th power supply, l i is the demand of the i-th important load, N tr is the maximum value of the number of transformers, C max is the maximum capacity, and L imp is the minimum total load demand that the system needs to meet.

[0036] In combination with the first aspect, optionally, solving the multi-objective mixed-integer programming large model by using the branch and bound method to determine the best power supply plan suitable for the current customer includes:

[0037] Solving the multi-objective mixed-integer programming large model by using the branch and bound method, ignoring the integer constraints to solve the linear programming relaxation problem to obtain the lower bound LB, gradually branching the non-integer solutions, and narrowing the search range by dynamically updating the upper bound UB, and determining the best power supply plan suitable for the current customer within 1 second.

[0038] In the second aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the power supply plan generation method based on the multi-objective mixed-integer programming large model described in any item of the first aspect.

[0039] In the third aspect, the present invention provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, it implements the power supply plan generation method based on the multi-objective mixed-integer programming large model described in any item of the first aspect.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] Based on the customer portrait function and the relevant parameters of the power supply plan, the present invention combines the branch and bound method and multi-objective mixed-integer programming to quickly determine the best power supply plan suitable for the current customer.

[0042] Furthermore, the present invention overcomes the limitations of large models in dealing with such complex operations research algorithm problems, solves the problem of complex power receiving equipment configuration in the process of large models generating power supply plans. In particular, on the demand side, it is necessary to comprehensively consider cost sensitivity and reliability requirements, and on the grid side, it is necessary to balance multiple variables and multi-parameter conditions such as the number of power sources, operation modes, available power supply capacity, design connection modes, and transformer capacity selection to achieve the optimal configuration problem. It can efficiently provide customers with detailed and accurate power supply plan suggestions, significantly improve the intelligent level and service quality in the process of power supply plan compilation, and provide strong technical support for the precise and personalized services in the power industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings, where:

[0044] Figure 1 It is a schematic flow chart of a power supply plan generation method based on a multi-objective mixed integer programming large model according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0046] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0047] Embodiment 1

[0048] An embodiment of the present invention provides a power supply plan generation method based on a multi-objective mixed integer programming large model, as Figure 1 shown, including:

[0049] (1) Generate a personalized portrait function of the customer based on the collected customer demand-side information;

[0050] (2) Generate a power supply plan parameter set function based on the relevant parameters of the power supply plan;

[0051] (3) Generate a multi-objective mixed-integer programming large model based on the customer's personalized portrait function and the power supply plan parameter set function;

[0052] (4) Solve the multi-objective mixed-integer programming large model by the branch and bound method to determine the best power supply plan suitable for the current customer.

[0053] Based on the simulation experiment, it can be known that based on the method in the embodiment of the present invention, the best power supply plan suitable for the current customer can be determined within 1 second at the fastest.

[0054] In the embodiment of the present invention, based on the customer portrait function and the relevant parameters of the power supply plan, combined with the branch and bound method and multi-objective mixed-integer programming, the best power supply plan suitable for the current customer is quickly determined.

[0055] In a specific implementation manner of the embodiment of the present invention, the generation method of the personalized portrait function of the customer includes:

[0056] Obtain customer demand-side information;

[0057] Based on the obtained customer demand-side information, determine the sensitivity of the customer to electricity charges and the reliability requirements of the customer for the stability of power supply;

[0058] Based on the sensitivity of the customer to electricity charges and the reliability requirements of the customer for the stability of power supply, generate the personalized portrait function of the customer P = f(C s , R r ), where C s is the sensitivity of the customer to electricity charges, and R r is the reliability requirement of the customer for the stability of power supply.

[0059] In a specific implementation manner of the embodiment of the present invention, the personalized portrait function of the customer P = w cost ·C s + w reliability ·R r , where C s is the sensitivity of the customer to electricity charges, R r is the reliability requirement of the customer for the stability of power supply, w cost is the weight of the sensitivity of the customer to electricity charges, and w reliability is the weight of the reliability requirement of the customer for the stability of power supply.

[0060] In the specific implementation process, the method for generating the personalized portrait function of the customer specifically includes:

[0061] Determine the sensitivity degree C of the customer to electricity charges by analyzing historical bills or communicating with the customer through intelligent customer service s . For example, if a certain factory indicates that it is willing to pay a higher initial investment in exchange for long-term energy-saving benefits, its cost sensitivity is relatively low;

[0062] Evaluate the degree of emphasis on the stability of power supply, that is, the reliability requirement R, according to the industry characteristics of the customer (such as medical facilities, data centers, etc.) and operation requirements r .

[0063] Construct a personalized portrait function P = f(C s , R r ). The personalized portrait function can be a comprehensive scoring system, which quantifies the above two factors into values between 0 and 1 and obtains the total score by adding them according to weights. For example: P = w cost ·C s + w reliability ·R r . Here, w cost , w reliability are the weight coefficients of cost sensitivity and reliability respectively, and these weights can be adjusted according to the actual application situation.

[0064] In a specific implementation manner of the embodiment of the present invention, the method for generating the power supply scheme parameter set function includes:

[0065] Determine the appropriate number of generator sets according to the expected load and geographical location, in combination with the power supply scheme knowledge base mounted on the intelligent agent, to obtain the power quantity N g ;

[0066] Recommend what type of power generation equipment (such as diesel generators, gas turbines and their operation modes, such as standing by, standby) to adopt based on the power supply scheme knowledge base mounted on the intelligent agent and the relevant information of the user's application for power connection, to obtain the power operation mode O m ;

[0067] Determine the power supply capacity P of the power source based on the power supply scheme compilation knowledge base mounted on the intelligent agent and the relevant information of the user's application for power connection c , ensure that the selected power source can meet the maximum load demand, and at the same time leave a certain margin to cope with emergencies;

[0068] Generate a reasonable power grid connection structure based on the power supply scheme compilation knowledge base mounted on the intelligent agent and the user's application for power connection information, and determine the connection mode C l; for example, according to the focus of the connection structure with the best cost, the best reliability, and the best flexibility, different weights are assigned to connection methods such as without standby and with standby to ensure the safety and efficiency of power transmission;

[0069] Select a transformer with a suitable specification according to user requirements, and determine the transformer capacity T c , neither overloading nor wasting resources;

[0070] Based on the number of power supplies N g , the power supply operation mode O m , the power supply capacity P that the power supply can provide c , the connection method C l and the transformer capacity T c , generate a power supply plan parameter set function S, S = g(N g , O m , P c , C l , T c ).

[0071] In a specific implementation manner of the embodiment of the present invention, the optimization objective function of the multi-objective mixed integer programming large model is related to cost, reliability, and flexibility.

[0072] In a specific implementation manner of the embodiment of the present invention, the optimization objective function of the multi-objective mixed integer programming large model is:

[0073] minimize Z = w1f C (x) + w2f R (x) + w3f F ;

[0074] Among them, Z is the total objective function, w1, w2, and w3 are the weight coefficients corresponding to different objective functions, and x represents the decision variable;

[0075] f C (x) represents the cost objective function, including construction cost and maintenance cost, and its mathematical expression is:

[0076]

[0077] f R (x) represents the reliability objective function, which is used to evaluate the probability that the power supply system can still operate normally under various fault conditions, and its mathematical expression is:

[0078]

[0079] f C(x) represents the flexibility objective function, which is used to measure the ability of the power supply system to adapt to future changes, such as expanding new loads or responding to market price fluctuations. Its mathematical expression is:

[0080]

[0081] Among them, c i , r j , f k are coefficients related to cost, reliability, and flexibility respectively; P is the personalized portrait function of customers, and S is the set function of power supply plan parameters; n is the number of different cost items involved in the cost objective function. Specifically, n corresponds to the total number of various devices or components in the power supply plan, and each device or component has its specific cost coefficient c i . By summing these cost items multiplied by the corresponding coefficients and function values, the total cost objective function value is calculated. m is the number of different reliability evaluation scenarios or indicators involved in the reliability objective function f R (x). m corresponds to the reliability situations that the power supply system needs to consider under various possible fault conditions, and each reliability situation has its corresponding coefficient r j . By summing these reliability items multiplied by the corresponding coefficients and function values, the overall reliability of the power supply system is evaluated. p is the number of different flexibility evaluation indicators or future change scenarios involved in the flexibility objective function f F (x). p corresponds to the future possible change situations that the power supply system needs to adapt to, such as load growth, new energy access, etc. Each flexibility situation has its corresponding coefficient f k . By summing these flexibility items multiplied by the corresponding coefficients and function values, the flexibility of the power supply system is measured.

[0082] Determine and quantify various constraint conditions of the multi-objective mixed-integer programming large model, such as transformer number limit, capacity limit, important load limit, etc., to ensure that the generated plan meets both customer needs and grid specifications and technical standards. The transformer number limit N tr limits the maximum number of transformers installed, the capacity limit C max ensures that the total power supply capacity does not exceed the allowed maximum value, and the important load limit L imp ensures that critical equipment always has sufficient power support. For this reason, in a specific implementation manner of the embodiment of the present invention, the constraint conditions of the multi-objective mixed-integer programming large model include:

[0083]

[0084] Among them, t i is the number of the i-th transformer, p i is the power output of the i-th power source, l iis the demand of the i-th important load, N tr is the maximum number of transformers, C max is the maximum capacity, L imp is the minimum total load demand that the system needs to meet.

[0085] In a specific implementation manner of the embodiment of the present invention, the method for solving the multi-objective mixed-integer programming large model by using the branch and bound method to determine the best power supply plan suitable for the current customer includes:

[0086] Use the branch and bound method to solve the multi-objective mixed-integer programming large model, ignore the integer constraints to solve the linear programming relaxation problem to obtain the lower bound LB, gradually branch the non-integer solutions, and narrow the search range by dynamically updating the upper bound UB, and determine the best power supply plan suitable for the current customer within 1 second. Each step of the branch and bound method is closely related to the elements of the mixed-integer programming model

[0087] The elements of the mixed-integer programming model corresponding to the branch and bound steps

[0088] 1. Solving the relaxation problem Finding the minimum value (lower bound LB) of the objective function for continuous variables 2. Selecting branching variables Preferentially selecting integer variables that have the greatest impact on the objective function 3. Updating constraint conditions When adding branch constraints, update the power supply parameter constraints 4. Updating upper and lower bounds The UB / LB calculation includes dynamic adjustment of customer profile weights

[0089] The process can be expressed by the formula:

[0090] while UB - LB > ∈;

[0091] if

[0092] branch on x i ;

[0093] update UB, LB;

[0094] end while;

[0095] where ∈ is a small positive number used to control the accuracy. The core of the branch and bound method lies in effectively managing the branch tree to quickly converge to the global optimal solution. x i is a decision variable, which can be an integer variable or a continuous variable, representing a parameter or value that needs to be determined during the power supply plan generation process. is an integer.

[0096] The following will describe in detail the power supply plan generation method based on the multi-objective mixed-integer programming large model in the embodiment of the present invention in combination with a specific implementation manner.

[0097] The power supply plan generation method based on the multi-objective mixed-integer programming large model in the embodiment of the present invention specifically includes the following steps:

[0098] Step A: Collect and analyze the information on the customer demand side, and construct the personalized portrait function of the customer.

[0099] Cost sensitivity C s : This factory is willing to pay a higher initial investment in exchange for long-term energy-saving benefits. Therefore, its cost sensitivity is low. Let C s = 0.2.

[0100] Reliability requirement R r : As part of the manufacturing industry, the stability of power supply is crucial. Let R r = 0.9.

[0101] Step A01: Construct the personalized portrait function P = f(C s , R r ), assuming the weight coefficients are w cost = 0.3 and w reliability = 0.4. Then the personalized portrait function can be expressed as: P = w cost ·C s + w reliability ·R r . Substitute the specific values: P = 0.3×0.2 + 0.4×0.9 = 0.42.

[0102] Step B: Integrate the relevant parameters of the power supply plan and define the power supply plan parameter set function S = g(N g , O m , P c , C l , T c ).

[0103] Number of power sources N g : Assume that two generators are required to ensure redundancy and reliability.

[0104] Power source operation mode O m : Select the standby operation mode to ensure sufficient power supply at any time.

[0105] Power supply capacity of the power source P c : The maximum output power of each generator is 600 kW, and the total capacity is 1200 kW.

[0106] Designed connection method C l : Design a ring power grid connection to enhance the flexibility and fault resistance of the system.

[0107] Market-available transformer capacity T c : Select a 1000 kVA transformer according to the maximum expected load, which can meet the current demand and also has a certain expansion space.

[0108] Step C: Establish a multi-objective mixed-integer programming large model based on the obtained personalized portrait function of the customer and the power supply plan parameter set function.

[0109] Cost objective function f C : Calculate the construction and maintenance costs of the entire power supply system.

[0110] Reliability objective function f R : Evaluate the probability that the system can still operate normally under various fault conditions.

[0111] Flexibility objective function f F : Measure the system's ability to adapt to future changes, such as expanding new loads or responding to market price fluctuations. Assume the weight coefficients are w1 = 0.4, w2 = 0.3, and w3 = 0.3. The combined objective function is as follows

[0112] Z = w1f C (x) + w2f R (x) + w3f F (x);

[0113] Now, specify each objective function:

[0114] Cost objective function f C : Assume the installation cost per kilowatt is 100 yuan, and the annual maintenance cost is 10 yuan / kilowatt. If the total installed capacity is 1200 kW, then the initial investment is 1200×100 = 120,000, and the annual maintenance cost is 1200×10 = 12,000. Therefore, f C (x) = 120,000 + 12,000.

[0115] Reliability objective function f R : Assume that after adopting redundant design, the improvement of system reliability reduces the power outage probability by 90%, that is, f R (x) = 0.9.

[0116] Flexibility objective function f F : The system design allows for easy addition of extra loads in the future, which results in a high flexibility score. Let f F (x) = 0.8. Substitute the specific values:

[0117] Z = 0.4×(120,000 + 12,000) + 0.3×0.9 + 0.3×0.8 = 52,800.51;

[0118] Step D: Solve the above mixed-integer programming problem using the branch and bound method. Ignore the integer constraints to solve the linear programming relaxation problem to obtain the lower bound LB. Gradually branch the non-integer solutions and narrow the search range by dynamically updating the upper bound UB, and determine the best power supply plan suitable for the current customer within 1 second. The following is a code example:

[0119] Step D01: Define the personalized portrait function P based on the information obtained above

[0120]

[0121] Step D02: Define the power supply plan parameter set function S based on the information obtained above

[0122]

[0123] Step D03: Define the power supply plan parameter set function Z based on the information obtained above

[0124]

[0125] Step D04: Construct and solve the linear programming relaxation problem

[0126]

[0127]

[0128] Step D05: Main loop of the branch and bound method

[0129]

[0130]

[0131] Example 2

[0132] In the embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, it implements the power supply plan generation method based on the multi-objective mixed-integer programming large model described in any one of Embodiment 1.

[0133] Example 3

[0134] In the embodiment of the present invention, a computer program product is provided, including a computer program / instructions. When the computer program / instructions are executed by a processor, it implements the power supply plan generation method based on the multi-objective mixed-integer programming large model described in any one of Embodiment 1.

[0135] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0136] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0137] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realizes the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0139] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those of ordinary skill in the art, under the inspiration of the present invention and without departing from the spirit and scope protected by the present invention's claims, can also make many forms, and all of these fall within the protection scope of the present invention.

[0140] The above has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for generating a power supply scheme based on a multi-objective mixed integer programming large model, characterized in that: include: Generate a personalized customer portrait function based on the collected customer demand information; Based on the power supply scheme related parameters, generate a power supply scheme parameter set function; Generate a multi-objective mixed integer programming large model based on the customer's personalized portrait function and power supply plan parameter set function; The branch and bound method is used to solve the multi-objective mixed integer programming large model to determine the best power supply solution suitable for the current customer.

2. The method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to claim 1, characterized in that: The method for generating the personalized portrait function of the customer includes: Obtain information on customer demand; Based on the customer demand side information obtained, determine the customer's sensitivity to electricity charges and the customer's reliability requirements for power supply stability; Based on the customer's sensitivity to electricity charges and the customer's reliability requirements for power supply stability, a personalized customer profile function P = f(C s ,R r ), where C s is the customer’s sensitivity to electricity charges, R r To meet customers' reliability requirements for stable power supply.

3. The method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to claim 2, characterized in that: The customer's personalized portrait function P = w cost ·C s +w reliability ·R r , where C s is the customer’s sensitivity to electricity charges, R r To meet customers’ reliability requirements for power supply stability, cost is the weight of the customer’s sensitivity to electricity charges, w reliability The weight given to customers’ reliability requirements for electricity supply stability.

4. The method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to claim 1, characterized in that: The method for generating the power supply scheme parameter set function includes: According to the expected load and geographical location, the appropriate number of generator sets is determined in combination with the power supply scheme knowledge base mounted by the intelligent agent, and the number of power sources N is obtained. g ; Based on the power supply solution knowledge base mounted by the intelligent agent and the relevant information of the user's power application, it is recommended to use what type of power generation equipment to obtain the power supply operation mode O m ; Based on the knowledge base of power supply plan preparation mounted by the intelligent agent and the relevant information of the user's power application, the power supply capacity P is determined. c , ensure that the selected power supply can meet the maximum load demand, while leaving a certain margin to deal with emergencies; Based on the power supply plan compilation knowledge base mounted on the intelligent agent and the user's power application information, a reasonable grid connection structure is generated and the contact method C is determined. l ; Select a transformer of appropriate specifications according to user needs and determine the transformer capacity T c ; Based on the power supply number N g , Power supply operation mode O m 、Power supply capacity P c 、Contact information C l and transformer capacity T c , generate the power supply scheme parameter set function S, S = g(N g ,O m ,P c ,C l ,T c ).

5. The method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to claim 1, characterized in that: The optimization objective function of the multi-objective mixed integer programming large model is related to cost, reliability and flexibility.

6. The method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to claim 5, characterized in that: The optimization objective function of the multi-objective mixed integer programming large model is: minimize Z=w1f C (x)+w2f R (x)+w3f F (x); Among them, Z is the overall objective function, w1, w2, w3 correspond to the weight coefficients of different objective functions, and x represents the decision variable; f C (x) represents the cost objective function, including construction cost and maintenance cost, and its mathematical expression is: f R (x) represents the reliability objective function, which is used to evaluate the probability that the power supply system can still operate normally under various fault conditions. Its mathematical expression is: f C (x) represents the flexibility objective function, which is used to measure the ability of the power supply system to adapt to future changes. Its mathematical expression is: Among them, c i 、r j 、f k The coefficients related to cost, reliability and flexibility respectively; P is the customer's personalized portrait function, S is the power supply scheme parameter set function, and n is the cost objective function f C The number of different cost items involved in (x), m is the reliability objective function f R The number of different reliability assessment scenarios or indicators involved in (x), p is the flexibility objective function f F (x) The number of different flexibility assessment indicators or future change scenarios involved.

7. The method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to claim 6, characterized in that: The constraints of the multi-objective mixed integer programming large model include: Among them, t i is the number of the i-th transformer, p i is the power output of the ith power supply, l i is the demand of the ith important load, N tr is the maximum number of transformers, C max is the maximum capacity, L imp is the minimum total load demand that the system needs to meet.

8. The method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to claim 1, characterized in that: The branch and bound method is used to solve the multi-objective mixed integer programming large model to determine the best power supply solution suitable for the current customer, including: The branch and bound method is used to solve the multi-objective mixed integer programming large model. The integer constraints are ignored to solve the linear programming relaxation problem to obtain the lower bound LB. The non-integer solutions are gradually branched, and the search range is narrowed by dynamically updating the upper bound UB. The best power supply plan suitable for the current customer is determined within 1 second.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the power supply scheme generation method based on a multi-objective mixed integer programming large model described in any one of claims 1 to 8 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the method for generating a power supply scheme based on a multi-objective mixed integer programming large model according to any one of claims 1 to 8 is implemented.

Images