A multi-objective optimization method for project construction considering life cycle assessment of carbon emissions

Abstract

The present application relates to a kind of project construction multi-objective optimization method considering carbon emission life cycle assessment, comprising the following steps: first, by analyzing the system composition of power grid infrastructure, in combination with the characteristics of power grid infrastructure construction project and low-carbon evaluation content, construct life cycle carbon emission evaluation index system and power grid infrastructure economic benefit evaluation index system;Subjective weight and objective weight of each evaluation index are calculated using entropy weight method and laboratory method respectively.A combination weight optimization model considering subjective weight and objective weight is constructed, and the combination weight optimization model is solved based on QPSO quantum particle swarm algorithm, to calculate the combination weight of each evaluation index.Setting constraint condition and constructing multi-objective optimization model based on optimal economic benefit and low-carbon benefit.The multi-objective optimization model is solved using niche genetic algorithm, to obtain the project construction scheme with optimal comprehensive benefit, to realize project optimization sorting.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of project optimization, and particularly relates to a project construction multi-objective optimization method considering carbon emission life cycle assessment. BACKGROUND

[0002] Under the background of current global energy structure transformation, as a bridge connecting energy production and consumption, the greenization and intelligentization upgrading of power grid infrastructure construction is particularly important. Power grid enterprises are facing the dual challenges of ensuring power supply safety and reliability and significantly reducing carbon emissions. Therefore, from the perspective of the whole life cycle, scientifically assessing the carbon footprint of power grid infrastructure construction projects and optimizing decisions on this basis have become an urgent need for the industry development.

[0003] Technology development trends:

[0004] 1. Digital transformation: The rapid development of digital technologies such as the Internet of Things, big data, artificial intelligence, etc. provides new tools and methods for the intelligent operation and maintenance, energy consumption monitoring and carbon emission management of power grid infrastructure, promoting the improvement of management efficiency and accuracy.

[0005] 2. Low-carbon technology integration: The application of new materials and new energy technologies, as well as the development of smart grids and microgrids, provides technical support for reducing carbon emissions in the construction and operation of power grids.

[0006] 3. Promotion of green finance: With the improvement of the green financial system, green credit, green bonds and other financial products provide financial support for low-carbon power grid construction projects, prompting projects to pay more attention to environmental friendliness in the design and implementation process.

[0007] Challenges:

[0008] 1. Difficulty in data acquisition and processing: The life cycle carbon emissions of power grid construction projects involve a large amount of complex data, including material production, transportation, construction, operation and maintenance, etc. Accurate acquisition and efficient processing of data is a major problem.

[0009] 2. Multi-objective conflict: While pursuing economic benefits, environmental protection, social responsibility and other multiple objectives need to be considered, how to find the best balance point among these objectives is a complex decision-making problem.

[0010] 3. Limitations of evaluation and optimization methods: Traditional evaluation methods and optimization models often fail to fully cope with the complexity, dynamics and uncertainty of power grid construction projects, especially the lack of intelligent optimization algorithms that can effectively integrate multi-source information and handle high-dimensional data.

[0011] Defects of prior art:

[0012] 1. Evaluation system limitations: Existing evaluation methods mostly focus on a single dimension, such as only considering economic benefits or environmental impact, lacking a comprehensive consideration of carbon emissions throughout the life cycle of power grid construction projects.

[0013] 2. Strong subjectivity in weight determination: In constructing a multi-objective optimization model, the determination of index weights often relies on subjective methods such as expert scoring, lacking balance between scientificity and objectivity.

[0014] 3. Efficiency and effectiveness of optimization algorithm: Traditional optimization algorithms are prone to local optimal solutions when dealing with complex, high-dimensional multi-objective optimization problems, and have low search efficiency, making it difficult to fully explore the diversity of the solution space.

[0015] 4. Lack of project optimization and decision support: Existing technologies fail to effectively combine engineering practice in considering economic benefits and low-carbon benefits, especially failing to fully utilize modern intelligent optimization algorithms for efficient processing and optimal ranking of large-scale project data. SUMMARY

[0016] To solve the above technical problems, the present application proposes a project construction multi-objective optimization method considering carbon emission life cycle evaluation.

[0017] The technical solution of the present application is as follows:

[0018] On the one hand, the present application proposes a project construction multi-objective optimization method considering carbon emission life cycle evaluation, comprising the following steps:

[0019] Analyzing the system composition of power grid infrastructure, combining the characteristics of power grid infrastructure construction projects and low-carbon evaluation content, constructing power grid infrastructure low-carbon benefit evaluation index system and power grid infrastructure economic benefit evaluation index system;

[0020] Based on the power grid infrastructure low-carbon benefit evaluation index system and the power grid infrastructure economic benefit evaluation index system, the subjective weight and the objective weight of each evaluation index are calculated by using the entropy weight method and the laboratory method;

[0021] A combined weight optimization model considering subjective weight and objective weight is constructed, and the combined weight optimization model is solved based on QPSO quantum particle swarm algorithm to calculate the combined weight of each evaluation index;

[0022] Set the constraint conditions and construct a multi-objective optimization model based on the optimal economic benefit and low-carbon benefit;

[0023] The multi-objective optimization model is solved by using the niche genetic algorithm to obtain the optimal project construction scheme with comprehensive benefits, realizing the optimal ranking of the project.

[0024] As a preferred embodiment, the project construction multi-objective optimization method considering carbon emission life cycle assessment, the step of constructing the power grid infrastructure low-carbon benefit evaluation index system and the power grid infrastructure economic benefit evaluation index system combines the system composition of the power grid infrastructure, the construction engineering characteristics of the power grid infrastructure, and the low-carbon evaluation content.

[0025] The life cycle of the power grid infrastructure construction project is divided into different stages, including the planning stage, the design stage, the construction stage, the operation stage, and the demolition and recycling stage.

[0026] According to the characteristics of each stage, a plurality of corresponding carbon emission evaluation indexes are set.

[0027] As a preferred embodiment, the project construction multi-objective optimization method considering carbon emission life cycle assessment, the step of calculating the subjective weight and the objective weight of each evaluation index by using the entropy weight method and the laboratory method is as follows:

[0028] The subjective weight of each evaluation index is calculated by using the DEMATEL decision test and evaluation test method, including the following steps:

[0029] The mutual influence degree between each evaluation index is determined by questionnaire / expert scoring, and the initial influence matrix is constructed based on the mutual influence degree between each evaluation index.

[0030] The initial influence matrix O is standardized to obtain the normalized matrix WN, and the formula is as follows:

[0031]

[0032] In the formula, r is the number of normalized indexes, O bh is the element in the bth row and hth column;

[0033] The comprehensive influence matrix T is calculated, and the formula is as follows:

[0034]

[0035] In the formula, I is the unit matrix, WN p is the pth normalized matrix;

[0036] The values of various parameters of each index are calculated by using the comprehensive influence matrix, including the influence value D, the affected value C, the center value D+C, and the reason value D-C, wherein the calculation formulas of the influence value D and the affected value C are as follows:

[0037]

[0038] In the formula, e and f represent two interacting evaluation indexes.

[0039] The centralization value D+C or the reason value D-C is normalized so that the sum of the centralization value D+C or the reason value D-C of each evaluation index is 1, and the normalized centralization value D+C or reason value D-C is used as the subjective weight vector of each evaluation index;

[0040] The objective weight of each evaluation index is calculated using the entropy weight method, including the following steps:

[0041] The data of each evaluation index is normalized to ensure that the data values of each evaluation index are on the same order of magnitude;

[0042] For each evaluation index, the proportion of each sample data value to the total data value of the evaluation index is calculated to obtain the probability distribution of each evaluation index;

[0043] The information entropy of each evaluation index is calculated based on the probability distribution of each evaluation index, the information utility value is calculated through the information entropy of each evaluation index, and the normalized information utility value is obtained by normalizing each information utility value, and the sum of the normalized information utility values of each evaluation index is 1, and the normalized information utility value is used as the objective weight of the corresponding evaluation index.

[0044] As a preferred embodiment, the project construction multi-objective optimization method considering the whole life cycle evaluation of carbon emissions, the step of solving the combination weight optimization model based on the QPSO quantum particle swarm algorithm is specifically:

[0045] The initial parameters are set, including population size, learning factor, maximum iteration number, initial speed, index number, and inertia weight;

[0046] An initial population is generated, each particle in the initial population represents a combination weight configuration of an evaluation index, and the combination weight configuration is adjusted and generated based on the subjective weight and objective weight of the corresponding evaluation index, and the initial position and initial speed of each particle are randomly generated;

[0047] The fitness of each particle in the initial population is calculated, and the global optimal particle and individual optimal particle are found, wherein the fitness function is configured as an error function between the actual carbon emission evaluation value and the carbon emission prediction value calculated based on each evaluation index and the corresponding combination weight;

[0048] The global optimal position and historical optimal position of each particle are updated based on the fitness value of each particle;

[0049] The particle with the lowest fitness is eliminated, and the speed and position of the particle are updated based on the fitness value;

[0050] The global optimal particle and individual optimal particle are updated;

[0051] Repeat the above steps until the maximum number of iterations is reached or the convergence condition is met, and the optimization ends, and the current combination weight configuration of each particle is output as the combination weight of the corresponding evaluation index.

[0052] As a preferred embodiment, in the step of setting constraints and constructing a multi-objective optimization model based on economic benefits and low-carbon benefits, the multi-objective optimization model is constructed based on the following formula:

[0053] The multi-objective optimization method for project construction considering the life cycle assessment of carbon emissions includes two parts: economic investment benefit score and low-carbon benefit score of a single project, and the total economic investment benefit score and low-carbon benefit score of all selected power grid infrastructure projects can be obtained.

[0054] The power grid investment scale constraint set is constructed, and the specific formula is as follows:

[0055]

[0056] Where M o is the economic benefit score of the oth item, and N o is the low-carbon benefit score of the oth item; maxQM is the maximum sum of economic benefit scores of all projects, and maxQN is the maximum sum of low-carbon benefit scores of all projects.

[0057]

[0058] In the formula, C rn is the construction investment of the rnth investment project of the power grid, C max is the maximum investment of the power grid, a rn = 0 or 1 represents whether the project is selected or not, and SN is the number of evaluation samples.

[0059] As a preferred embodiment, in the step of using a niche genetic algorithm to solve the multi-objective optimization model to obtain a project construction scheme with optimal comprehensive benefits and realize project optimization ranking, the following steps are performed:

[0060] Initialization: randomly generate an initial population, and each individual contains the values of multiple objective functions, which represent different optimization objectives of the multi-objective optimization problem;

[0061] Evaluation: use the evaluation function or objective function of the multi-objective optimization problem to calculate the fitness of each individual;

[0062] Niche division: according to the characteristics of individuals, including the closeness of solutions and objective function values, the population is divided into multiple niches;

[0063] Selection and crossover, variation: perform competitive selection operation in each niche, preferably select the best individual in each niche; cross and mutate the selected best individual to generate new individuals, increase population diversity;

[0064] Update population: add the newly generated individuals to the population, replace part of the old population;

[0065] Check termination condition: check whether the result meets the iteration termination condition, including reaching the preset number of iterations, the quality of the solution no longer improves;

[0066] Result output: select representative solutions from the non-dominated solution set in the evolution process as the Pareto front solution output, as the project preferred ranking.

[0067] On the other hand, the present application also provides a project construction multi-objective optimization system considering carbon emission life cycle assessment, comprising:

[0068] An index system construction module analyzes the system composition of power grid infrastructure, combines the characteristics of power grid infrastructure construction projects and low-carbon evaluation content, and constructs a power grid infrastructure low-carbon benefit evaluation index system and a power grid infrastructure economic benefit evaluation index system;

[0069] A weight calculation module calculates the subjective weight and objective weight of each evaluation index based on the power grid infrastructure low-carbon benefit evaluation index system and the power grid infrastructure economic benefit evaluation index system using the entropy weight method and the laboratory method;

[0070] A weight optimization module is used to construct a combined weight optimization model considering subjective weight and objective weight, and to solve the combined weight optimization model based on the QPSO quantum particle swarm algorithm to calculate the combined weight of each evaluation index;

[0071] An optimization model construction module is used to set constraints and construct a multi-objective optimization model based on economic benefit and low-carbon benefit optimization;

[0072] A decision module uses a niche genetic algorithm to solve the multi-objective optimization model to obtain a project construction scheme with optimal comprehensive benefit, and realizes project optimization ranking.

[0073] As a preferred embodiment, the decision module uses a niche genetic algorithm to solve the multi-objective optimization model to obtain a project construction scheme with optimal comprehensive benefit, and realizes project optimization ranking. The steps of the preferred embodiment are as follows:

[0074] Initialization: randomly generate an initial population, each individual contains the numerical value of multiple objective functions, which represent different optimization objectives of the multi-objective optimization problem;

[0075] Evaluation: Calculate the fitness of each individual using the evaluation function or objective function of the multi-objective optimization problem;

[0076] Niche division: Divide the population into multiple niches according to the characteristics of the individuals, including the closeness of the solution and the objective function value;

[0077] Selection and crossover, mutation: Perform competitive selection operations within each niche, and select the best individual in each niche; Perform crossover and mutation operations on the selected best individuals to generate new individuals and increase population diversity;

[0078] Update population: Add the newly generated individuals to the population and replace part of the old population;

[0079] Check termination condition: Check if the result meets the iteration termination condition, including reaching the preset number of iterations and the quality of the solution no longer improving;

[0080] Result output: Select representative solutions from the non-dominated solution set in the evolution process as Pareto front solutions and output them as project preferred ranking.

[0081] In another aspect, the present application also provides an electronic device having a computer program stored thereon, wherein the computer program is executed by a processor to implement the project construction multi-objective optimization method considering carbon emission life cycle assessment according to any one of the embodiments of the present application.

[0082] In another aspect, the present application also provides a computer readable medium for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the project construction multi-objective optimization method considering carbon emission life cycle assessment according to any one of the embodiments of the present application.

[0083] The present application has the following beneficial effects:

[0084] 1. Life cycle perspective: The constructed carbon emission evaluation index system comprehensively covers each stage from planning, design, construction, operation to decommissioning of power grid infrastructure construction, ensuring the systematization and integrity of the evaluation.

[0085] 2. Scientific weight allocation: Through the combination of entropy weight method and laboratory method, both the objective importance of the indicators and the expert experience are considered, the scientific integration of subjective and objective weights is realized, and the accuracy of the evaluation is improved.

[0086] 3. Quantum heuristic optimization algorithm innovation: The introduction of QPSO algorithm enhances the global search ability and diversity of particle swarm optimization algorithm by using the concept of quantum bit, effectively solves the local optimal problem in multi-objective optimization, and improves the solving efficiency and quality.

[0087] 4. Maximization of comprehensive benefits: The multi-objective optimization model constructed not only considers economic benefits, but also takes into account low-carbon benefits, and is solved by a niche genetic algorithm, ensuring the comprehensive optimality of the project optimization scheme, while considering practical constraint conditions such as investment scale, thereby enhancing the practicality and feasibility of the decision.

[0088] 5. Project optimization ranking and decision support: The proposed framework not only obtains the optimal construction scheme, but also provides intuitive comparative analysis for decision-makers through ranking, thereby assisting in scientific decision-making and sustainable development of green power grid construction projects. BRIEF DESCRIPTION OF DRAWINGS

[0089] Figure 1 is a method flowchart of the embodiment one of the present application; DETAILED DESCRIPTION

[0090] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0091] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0092] It should be understood that the terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clear from the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0093] The terms "include" and "contain" indicate the presence of the described features, whole, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0094] The term "and / or" means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0095] Embodiment one:

[0096] In order to make the purposes, technical solutions and advantages of the present application clearer, the following will combine specific embodiments of the present application, and refer to the accompanying drawings Figure 1 The technical solutions of the present application are clearly and completely described.

[0097] To solve the problems in the prior art, the project construction multi-target optimization method considering the whole life cycle evaluation of carbon emissions is provided, which comprises the following steps:

[0098] Step S101: analyze the system composition of the power grid infrastructure, combine the characteristics of the power grid infrastructure construction project and the low-carbon evaluation content, and construct a low-carbon benefit evaluation index system of the power grid infrastructure and an economic benefit evaluation index system of the power grid infrastructure.

[0099] The following is the construction of the project whole life cycle low-carbon benefit evaluation index system:

[0100] The power grid infrastructure construction project is an important part of the national energy system, and its construction and operation not only relate to the safe and stable supply of energy, but also is a key field of national carbon emission management. From project planning to final demolition and recycling, each stage is accompanied by the generation of carbon footprint, and the sources and intensity of carbon emissions at different stages are different.

[0101] Planning stage: Although the direct carbon emissions in this stage are small, the decisions such as project scale, site selection, and energy supply mode have a huge impact on the carbon emissions throughout the life cycle. Reasonable planning can avoid unnecessary modification and repeated construction in the future, and reduce long-term carbon emissions.

[0102] Design stage: The selection of low-carbon materials, optimization of design scheme, consideration of energy efficiency and integration of renewable energy in the design stage are crucial for reducing carbon emissions in the construction and operation stages. The decisions made in the design stage have a decisive influence on the overall carbon emissions.

[0103] Construction stage: The carbon emissions in this stage mainly come from material production and transportation, construction machinery operation, and on-site energy consumption. Optimizing construction processes, using low-carbon building materials, and improving construction efficiency can effectively reduce carbon emissions in this stage.

[0104] Operation stage: Energy consumption in power grid operation is a continuous source of carbon emissions, including the loss of substations and transmission lines as well as maintenance activities. Improving energy efficiency, adopting smart grid technology, and optimizing scheduling strategies can significantly reduce carbon emissions during the operation period.

[0105] Demolition and recycling stage: The demolition and material recycling of retired power grid facilities will also produce carbon emissions, but through efficient recycling strategies, this part of carbon emissions can be minimized and resource recycling can be achieved.

[0106] Based on the above analysis, a comprehensive evaluation index system is constructed, covering the forward-looking of planning, the low-carbon of design, the green degree of construction, the energy efficiency ratio of operation and the recycling economy of demolition and recycling, etc. Key indicators aim to guide and measure the low-carbon process of power grid infrastructure construction project. The indicators of each stage are independent and interrelated, which together constitute a life cycle low-carbon benefit evaluation index system.

[0107]

[0108] The economic benefit evaluation index system of power grid infrastructure refers to the existing evaluation index system of power grid, including the following first-level indicators: investment benefit, operation benefit, and social benefit. Investment benefit includes the following second-level indicators: investment recovery period, capital net present value, internal rate of return, and investment yield. Operation benefit includes the following second-level indicators: operation cost, operation reliability index, load service capacity, and power supply quality. Social benefit includes the following second-level indicators: job creation, local tax contribution, electricity price preferential policy, and social stability contribution.

[0109] Step S102: Based on the low-carbon benefit evaluation index system of power grid infrastructure and the economic benefit evaluation index system of power grid infrastructure, the subjective weight and objective weight of each evaluation index are calculated using the entropy weight method and the laboratory method.

[0110] DEMATEL decision-making and evaluation test method is used to calculate the subjective weight of each evaluation index; including the following steps:

[0111] The mutual influence degree between each evaluation index is determined by questionnaire / expert scoring, and the initial influence matrix is constructed based on the mutual influence degree between each evaluation index.

[0112] The initial influence matrix O is standardized to obtain the normalized matrix WN, and the formula is as follows:

[0113]

[0114] In the formula, r is the number of normalized indicators, O bh is the element in the bth row and hth column;

[0115] The comprehensive influence matrix T is calculated, and the formula is as follows:

[0116]

[0117] In the formula, I is the unit matrix, WN p is the pth normalized matrix;

[0118] The comprehensive influence matrix is used to calculate the parameter values of each index, including influence value D, affected value C, center value D+C, and cause value D-C. The calculation formulas of influence value D and affected value C are as follows:

[0119]

[0120]

[0121] wherein e and f represent two interacting evaluation indexes;

[0122] The center value D+C or the cause value D-C is normalized so that the sum of the center value D+C or the cause value D-C of each evaluation index is 1, and the normalized center value D+C or the cause value D-C is used as the subjective weight vector of each evaluation index;

[0123] The entropy weight method is used to calculate the objective weight of each evaluation index, including the following steps:

[0124] The evaluation model is as follows: let h evaluation indexes be used to evaluate f to-be-selected schemes. ul : the estimated value of evaluation index u of to-be-selected scheme l. ul * : the ideal value of evaluation index u. ul * The value size is different due to the different characteristics of evaluation indexes. For a benefit index, the larger the value is, the better the performance is. ul * For a loss index (inverse index), the smaller the value is, the better the performance is (it can also be converted into a positive index first). ul * For a loss index (inverse index), the smaller the value is, the better the performance is (it can also be converted into a positive index first).

[0125] The definition is as follows: ul For the value of, the value of is as follows: u * The closeness D ul :

[0126]

[0127] D ul Normalization processing:

[0128]

[0129] The overall entropy of h evaluation indexes for evaluating f to-be-selected schemes is as follows:

[0130]

[0131] The overall entropy when the index is irrelevant to the scheme is as follows:

[0132] If the relative importance of the evaluation index is irrelevant to the selected scheme, the entropy is calculated by the following formula:

[0133]

[0134] In the formula:

[0135] Thus, the uncertainty of the relative importance of the evaluation index u to the selected scheme decision evaluation can be determined by the following conditional entropy.

[0136] Conditional entropy of evaluation index u

[0137]

[0138] From the extremum of the entropy, it can be seen that That is, du1≈du2≈…dul, the closer to equal, the greater the conditional entropy, and the greater the uncertainty of the evaluation index to the selected scheme evaluation decision.

[0139] By normalizing the above formula, the entropy value representing the evaluation decision importance of the evaluation index u is obtained.

[0140]

[0141] Step S103: Construct a combination weight optimization model considering subjective weight and objective weight, solve the combination weight optimization model based on QPSO quantum particle swarm algorithm, and calculate the combination weight of each evaluation index.

[0142] The PSO algorithm is a random search algorithm based on group cooperation. In the process of each iteration search, the random particles in the group find the optimal solution by tracking two "extremes". Let the size of a certain population be N, the position of particle i in the D-dimensional search space in the t-th generation is The velocity is The individual historical optimal position is The global optimal position in the t-th generation Then the optimal solution formula is:

[0143]

[0144] In the formula: c1, c2 are learning factors; r1, r2 are random numbers uniformly distributed between [0, 1]; k is the current iteration number, I tera is the maximum iteration number, ω is the inertia weight, which is linearly reduced from the maximum ω max to ω min with the calculation of iteration.

[0145] Particle swarm optimization algorithm has been applied in many fields, but when dealing with complex models, the algorithm is easy to fall into local optimum problem, that is, "premature problem". In view of the obvious shortage of particle swarm optimization algorithm in dealing with complex problems, to avoid the algorithm falling into local optimum in the iteration process, the quadratic interpolation factor is introduced to improve it, and QPSO algorithm is proposed. This improvement improves the optimization speed of the algorithm, and makes the operation efficiency of the algorithm improved and the global optimization ability enhanced, so as to improve the practicability of the algorithm in the application of power grid reserve project library optimization. QPSO algorithm is essentially to introduce quadratic interpolation operator into particle swarm optimization algorithm, so as to improve the convergence speed and calculation efficiency of the algorithm, and then find the global optimal position of the model, that is:

[0146]

[0147] The point generated by the above formula is the minimum point of the quadratic surface passing through p l , p j and p g in D-dimensional space, so the global optimal position generated in the above formula is always selected. The global optimal position of the t-th generation is p g = (p g1 , p g2 ,..., p gD ), and two positions p l , p j are randomly selected from the individual historical optimal position, and l,j≠g. Wherein, e is a very small positive number, so that d is not 0.

[0148] Let Q i = (q i1 , q i2 ,..., q iD ), i = 1, 2,..., N, then:

[0149]

[0150] The flow chart of QPSO algorithm is as follows.

[0151] 1. Set the parameters such as population size n, learning factor c1, c2, maximum iteration number I tera , initial speed v, index number D, inertia weight, etc.

[0152] 2. Generate initial population, randomly generate initial position and initial speed

[0153] 3. Calculate the fitness of the initial particles, find the global optimal particle g best and individual optimal particle P best ;

[0154] 4. Update the historical optimal position P of the particle i and the global optimal position P g ;

[0155] 5. Eliminate the particle with the lowest fitness and update the velocity v of the particle and the position x of the particle;

[0156] 6. Update the global optimal particle and the individual optimal particle;

[0157] 7. Repeat steps 3-6, if the maximum number of iterations I tera is reached and the convergence condition is met, the optimization algorithm ends, and the combined weighting weight is output.

[0158] Step S104: Set the constraint condition and construct a multi-objective optimization model based on economic benefit and low-carbon benefit optimization; wherein:

[0159] The multi-objective optimization model considering the life cycle assessment of carbon emissions of project construction includes two parts of economic investment benefit score and low-carbon benefit score of a single project, and the total economic investment benefit score and low-carbon benefit score of all selected power grid infrastructure projects can be obtained;

[0160] And the power grid investment scale constraint set is constructed, and the specific formula is as follows:

[0161]

[0162] Wherein M o is the oth economic benefit score, N o is the oth low-carbon benefit score; maxQM is the highest sum of economic benefit scores of each project, and maxQN is the highest sum of low-carbon benefit scores of each project;

[0163]

[0164] In the formula, C rn is the construction investment of the nth investment project of the power grid; C max is the maximum investment of the power grid; in the formula, a rn = 0 or 1 represents whether the project is selected; SN is the number of evaluation samples.

[0165] Step S105: Based on the niche genetic algorithm, the model is solved to obtain a project construction scheme considering the optimal comprehensive benefit, and the project optimization ranking is realized.

[0166] Niche Genetic Algorithm (NGA) is an improved algorithm based on traditional genetic algorithm, which is especially suitable for solving multi-objective optimization problem. It introduces the concept of "niche", simulates the mechanism of survival and competition of biological population in different ecological environment, maintains the diversity of population, avoids premature convergence, and thus more effectively searches the Pareto frontier solution of multi-objective optimization problem.

[0167] The specific solution process is as follows:

[0168] (1) Input system data, parameter values and variable values. The input niche genetic algorithm parameters include individual population size, individual gene number, crossover rate, mutation rate and maximum genetic generation number, etc.

[0169] (2) Chromosome coding is carried out by binary.

[0170] (3) Randomly generate initial population.

[0171] (4) Check the constraint condition.

[0172] (5) Calculate the fitness function value of each chromosome in the population. In order to minimize the total risk of the described objective function, the fitness function is:

[0173]

[0174] F = R + μW

[0175] Wherein,

[0176] GF—fitness function;

[0177] F—modified value of objective function;

[0178] F max —Given a large constant, which can be selected as the maximum value of the objective function F obtained so far or obtained according to the test data.

[0179] W—network overload capacity (MW).

[0180] (6) Arrange the chromosomes in descending order according to their fitness function values, and remember the first LK chromosomes (M < LK).

[0181] (7) Perform proportional selection operation on the population P(tv) to obtain P'(tv). The fitness function value proportional method is used as the selection strategy to realize the selection operation.

[0182] (8) Perform one-point crossover operation on P'(tv) to obtain P"(tv). The crossover operation can change the topology of two networks to obtain a new structure. The basic steps of the crossover operation are:

[0183] 1) Select parent chromosomes: The process is as follows: repeat the following process from ai = 1 to LK: generate a random number r from [0, 1] ai If r ai ≤ P C , select the chromosome ai as a parent for crossover. Where P C is the crossover rate, usually between 0.6 and 0.9, embodying the idea of information exchange in nature.

[0184] 2) Select a crossover point: One-point crossover is used. The specific operation is to randomly select a crossover point in a chromosome, and the two chromosomes are partially exchanged before or after the point to generate new chromosomes.

[0185] (9) Perform two-point mutation operation on P"(tv) to obtain P'"(tv).

[0186] (10) Calculate the fitness of P'"(tv).

[0187] (11) Perform niche elimination algorithm. Combine the LK chromosomes obtained in step (9) and the M chromosomes memorized in step (6) to obtain a new population containing (LK+M) chromosomes. For the (LK+M) chromosomes, the Hamming distance between two chromosomes X ai and X aj is calculated as follows:

[0188]

[0189] When ||X ai -X aj || < DL (L is a specified distance), compare the fitness of chromosomes X ai and X aj , and impose a penalty function on the chromosome with lower fitness: F min(X ai , X aj ) = Penalty.

[0190] (12) Sort the new fitness of (N+M) chromosomes in descending order, and memorize the first M chromosomes.

[0191] (13) Implement the optimal preservation strategy.

[0192] (14) judging whether the termination condition is met. If the termination condition is met, go to step (15), otherwise update the evolution generation counter Gen = Gen + 1, take the first N chromosomes in the arrangement in step (11) as the new next generation population, and then go to step (7).

[0193] (15) decoding and outputting the optimization calculation result. Output the chromosomes with the highest or second highest fitness function value, and decode and restore to the power grid project optimization scheme.

[0194] Embodiment Two:

[0195] The embodiment provides a project construction multi-objective optimization system considering carbon emission life cycle assessment, comprising:

[0196] An index system construction module is configured to analyze the system composition of power grid infrastructure, construct a power grid infrastructure low-carbon benefit evaluation index system and a power grid infrastructure economic benefit evaluation index system in combination with the characteristics of power grid infrastructure construction projects and low-carbon evaluation content; the module is configured to realize the function of step S101 in Embodiment One, and will not be described here again.

[0197] A weight calculation module is configured to calculate the subjective weight and the objective weight of each evaluation index by using an entropy weight method and a laboratory method based on the power grid infrastructure low-carbon benefit evaluation index system and the power grid infrastructure economic benefit evaluation index system; the module is configured to realize the function of step S102 in Embodiment One, and will not be described here again.

[0198] A weight optimization module is configured to construct a combined weight optimization model considering the subjective weight and the objective weight, and calculate the combined weight of each evaluation index by solving the combined weight optimization model based on a QPSO quantum particle swarm algorithm; the module is configured to realize the function of step S103 in Embodiment One, and will not be described here again.

[0199] A preferred model construction module is configured to set a constraint condition and construct a multi-objective optimization model based on the optimal economic benefit and low-carbon benefit; the module is configured to realize the function of step S104 in Embodiment One, and will not be described here again.

[0200] A decision module is configured to solve the multi-objective optimization model by using a niche genetic algorithm, obtain a project construction scheme with the optimal comprehensive benefit, and realize project optimization sorting; the module is configured to realize the function of step S105 in Embodiment One, and will not be described here again.

[0201] Embodiment Three:

[0202] The embodiment provides an electronic device having a computer program stored thereon, and the computer program is executed by a processor to realize a project construction multi-objective optimization method considering carbon emission life cycle assessment according to any one of the embodiments of the present application.

[0203] Embodiment Four

[0204] The embodiment provides a computer readable medium for storing one or more programs, when the one or more programs are executed by one or more processors, the one or more processors implement a project construction multi-objective optimization method considering carbon emission life cycle assessment according to any embodiment of the application.

[0205] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the cases of A alone, A and B together, and B alone. Wherein A and B can be singular or plural. The character " / " generally represents that the associated objects before and after it are in an "or" relationship. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, and c can be single or multiple.

[0206] Those skilled in the art can realize that the units and algorithm steps described in the embodiments disclosed in the present application can be realized by electronic hardware, computer software and combination of electronic hardware and computer software. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0207] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0208] In several embodiments provided in the present application, any function, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0209] The above description is only some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A multi-objective optimization method for project construction considering life cycle assessment of carbon emissions, characterized in that, Includes the following steps: This paper analyzes the system composition of power grid infrastructure, and, in conjunction with the characteristics of power grid infrastructure construction projects and low-carbon evaluation content, constructs a low-carbon benefit evaluation index system and an economic benefit evaluation index system for power grid infrastructure. Specifically: The evaluation index system for the low-carbon benefits of power grid infrastructure is divided into different stages, including the planning stage, design stage, construction stage, operation stage, and dismantling and recycling stage. The planning phase includes: the frequency of adverse geological disasters, farmland occupancy rate, distribution of pollution sources, and renovation and expansion of transportation infrastructure; the design phase includes: unbalanced earthwork occupancy rate, natural ventilation opening area ratio, window-to-wall area ratio for each orientation, and shape coefficient; the construction phase includes: steel loss rate, cement loss rate, glass loss rate, and water consumption loss rate; the operation phase includes: rainwater harvesting and reuse rate, replacement ratio of clean air GIS equipment with sulfur hexafluoride gas GIS equipment, air conditioning system scheme and energy supply form, condensate recovery rate, and photovoltaic power generation ratio; the demolition and recycling phase includes: glass recycling rate, concrete recycling rate, timber recycling rate, and transformer equipment recycling rate. The economic benefit evaluation index system for power grid infrastructure includes primary indicators: investment benefits, operational benefits, and social benefits; investment benefits include the following secondary indicators: investment payback period, net present value of capital, internal rate of return, and rate of return on investment; operational benefits include the following secondary indicators: operating costs, operational reliability indicators, load service capacity, and power supply quality; social benefits include the following secondary indicators: job creation, local tax revenue contribution, electricity price preferential policies, and contribution to social stability. Based on the evaluation index system for low-carbon benefits of power grid infrastructure and the evaluation index system for economic benefits of power grid infrastructure, the subjective weight and objective weight of each evaluation index are calculated using the entropy weight method and the laboratory method. A combined weight optimization model considering subjective and objective weights is constructed. The combined weight optimization model is solved based on the QPSO quantum particle swarm optimization algorithm, and the combined weights of each evaluation index are calculated. Set constraints and construct a multi-objective optimization model based on optimal economic and low-carbon benefits; By using a niche genetic algorithm to solve a multi-objective optimization model, the optimal project construction scheme with the best overall benefits is obtained, thus achieving project optimization and ranking. 2.The method of claim 1, wherein, The specific steps for calculating the subjective and objective weights of each evaluation index using the entropy weight method and the laboratory method are as follows: The subjective weights of each evaluation index were calculated using the DEMATEL decision and evaluation experiment method, including the following steps: The degree of mutual influence between each evaluation indicator is determined by questionnaires / expert scoring, and an initial influence matrix is ​​constructed based on the degree of mutual influence between each evaluation indicator; The initial influence matrix O is normalized to obtain the normalized matrix WN, as shown in the following formula: where r is the normalized number of indicators, is the element in the bth row and hth column. The formula for calculating the comprehensive influence matrix T is as follows: where I is the identity matrix, is the p-th normalized matrix; The comprehensive influence matrix is ​​used to calculate various parameter values ​​for each indicator, including influence value D, affected value C, centrality value D+C, and causality value DC. The formulas for calculating influence value D and affected value C are as follows: In the formula, e and f represent two interacting evaluation indicators; The centrality value D+C or causal value DC is normalized so that the sum of the centrality value D+C or causal value DC of each evaluation indicator is 1, and the normalized centrality value D+C or causal value DC is used as the subjective weight vector of each evaluation indicator. The objective weights of each evaluation index are calculated using the entropy weight method, including the following steps: Perform data normalization on each evaluation indicator to ensure that the data values ​​of each evaluation indicator are on the same order of magnitude. For each evaluation indicator, calculate the proportion of each sample data value to the total number of data values ​​for that evaluation indicator to obtain the probability distribution of each evaluation indicator. The information entropy of each evaluation indicator is calculated based on the probability distribution of each evaluation indicator. The information utility value is calculated through the information entropy of each evaluation indicator. The information utility values ​​are normalized so that the sum of the normalized information utility values ​​of each evaluation indicator is 1. The normalized information utility value is used as the objective weight of the corresponding evaluation indicator. 3.The method of claim 1, wherein, The specific steps for solving the combined weight optimization model based on the QPSO quantum particle swarm optimization algorithm are as follows: The initial parameters are set, including population size, learning factor, maximum number of iterations, initial velocity, number of indicators, and inertia weight. An initial population is generated, in which each particle represents a combination weight configuration of an evaluation index. The combination weight configuration is generated by adjusting the subjective and objective weights of the evaluation index, and the initial position and initial velocity of each particle are randomly generated. The fitness of each particle in the initial population is calculated to find the globally optimal particle and the individual optimal particle. The fitness function is configured as the error function between the actual carbon emission evaluation value and the carbon emission prediction value calculated based on each evaluation index and the corresponding combined weight. The global best position and historical best position of each particle are updated based on its fitness value. Eliminate the particle with the lowest fitness and update the particle's velocity and position based on the fitness value; Update the global best particle and the individual best particle; Repeat the above steps until the maximum number of iterations is reached or the convergence condition is met. The optimization ends, and the current combination weights of each particle are output as the combination weights of the corresponding evaluation index. 4.The method of claim 1, wherein, In the step of setting constraints and constructing a multi-objective optimization model based on optimal economic and low-carbon benefits: A multi-objective optimization model for project construction that considers the full life cycle evaluation of carbon emissions is constructed, which includes two parts: the economic investment benefit score and the low-carbon benefit score of a single project. This model can be used to derive the total economic investment benefit score and the low-carbon benefit score of investing in all selected power grid infrastructure projects. It is constructed using a set constrained by power grid investment scale, and the specific formula is as follows: wherein is the score of the oth economic benefit, is the score of the oth low-carbon benefit; is the sum of the scores of the economic benefits of the respective projects highest, is the sum of the scores of the low-carbon benefits of the respective projects highest; In the formula: is the construction investment of the nth investment project of the power grid; is the maximum investment of the power grid; in the formula: =0 or 1 represents whether the project is selected or not; SN is the number of evaluation samples.

5. The project construction multi-objective optimization method considering carbon emission life cycle assessment according to claim 1, characterized in that, The steps for using a niche genetic algorithm to solve a multi-objective optimization model and obtain the project construction scheme with the best overall benefits, and to achieve project optimization and ranking, are as follows: Initialization: Randomly generate an initial population, each individual containing the values ​​of multiple objective functions, which represent different optimization objectives of a multi-objective optimization problem; Evaluation: Calculate the fitness of each individual using the evaluation function or objective function of the multi-objective optimization problem; Niche division: Based on individual characteristics, including the proximity of solutions and objective function values, the population is divided into multiple niches; Selection, crossover, and mutation: Competitive selection is performed within each microhabitat to select the best individuals in each microhabitat; crossover and mutation operations are then performed on the selected best individuals to generate a new generation of individuals, increasing population diversity; Update the population: Add newly generated individuals to the population, replacing some individuals in the old population; Check termination conditions: Check whether the results meet the iteration termination conditions, including reaching the preset number of iterations and the solution quality no longer improving; Output results: Representative solutions are selected from the non-dominated solution set in the evolution process as Pareto front solutions and output as the preferred ranking of projects.

6. A multi-objective optimization system for project construction that considers the entire life cycle assessment of carbon emissions, used to implement the method described in any one of claims 1-5, characterized in that, include: The indicator system construction module analyzes the system composition of power grid infrastructure, and combines the characteristics of power grid infrastructure construction projects and low-carbon evaluation content to construct a low-carbon benefit evaluation indicator system and an economic benefit evaluation indicator system for power grid infrastructure. The weight calculation module, based on the low-carbon benefit evaluation index system and the economic benefit evaluation index system of power grid infrastructure, uses the entropy weight method and the laboratory method to calculate the subjective and objective weights of each evaluation index respectively. The weight optimization module is used to construct a combined weight optimization model that considers subjective and objective weights. The combined weight optimization model is solved based on the QPSO quantum particle swarm optimization algorithm to calculate the combined weights of each evaluation index. The optimal model construction module is used to set constraints and construct a multi-objective optimal model based on the best economic and low-carbon benefits. The decision-making module uses a niche genetic algorithm to solve a multi-objective optimization model, obtaining the project construction plan with the best overall benefits, and achieving project optimization and ranking.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements a multi-objective optimization method for project construction that considers the full life cycle evaluation of carbon emissions, as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements a multi-objective optimization method for project construction that considers the full life cycle evaluation of carbon emissions, as described in any one of claims 1 to 5.

Images