A decision-making method, apparatus, and terminal equipment for power grid construction project investment.

Abstract

This application relates to a decision-making method, apparatus, and terminal equipment for power grid construction project investment. The method includes obtaining the total investment amount, the total number of construction projects, and the project construction parameters for each project; constructing a model based on the total number of construction projects and the project construction parameters for each project to obtain a power grid optimal combination decision-making model with multidimensional objective functions and multidimensional constraints; and using an improved particle swarm optimization algorithm to screen all construction projects based on the total investment amount to obtain the investment decision result. This power grid construction project investment decision-making method, by constructing a power grid optimal combination decision-making model with multidimensional objective functions and multidimensional constraints, combined with an improved particle swarm optimization algorithm, outputs the optimal investment decision result and expected return data based on the total investment amount and the total number of construction projects, thus obtaining the investment decision result of the optimal project combination.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a decision-making method, apparatus and terminal equipment for power grid construction project investment. Background Technology

[0002] Currently, some significant problems remain in investment decision-making research, with the most core and typical issue being the simplification of objective functions and constraints. Specifically, existing technologies generally use only one project revenue indicator as the objective function, and the consideration of constraints is rather one-sided, making it difficult to accurately solve the multi-criteria decision-making problem of combined investment in power grid construction projects. Furthermore, technical methods and data models that incorporate corporate investment capacity as a constraint on investment decisions are very scarce. In other words, the objective functions and constraints in the research are not comprehensive or systematic enough, lacking constraints on investment capacity, resulting in investment schemes that are not reasonable or scientific enough, requiring further research and improvement. Summary of the Invention

[0003] This application provides a decision-making method, apparatus, and terminal equipment for power grid construction project investment, which addresses the technical problem that existing investment decision-making models, due to insufficient comprehensive objective functions and constraints, result in unreasonable and unscientific output decision results.

[0004] To achieve the above objectives, this application provides the following technical solution:

[0005] On the one hand, a decision-making method for power grid construction project investment is provided, including the following steps:

[0006] Obtain the total investment, the total number of construction projects, and the project construction parameters for each construction project;

[0007] Based on the total number of construction projects and the construction parameters of each construction project, a model is constructed to obtain a power grid optimization combined decision model with multidimensional objective functions and multidimensional constraints.

[0008] In the power grid optimization and decision-making model, an improved particle swarm optimization algorithm is used to screen all the construction projects based on the total investment amount to obtain the investment decision results;

[0009] The improved particle swarm optimization algorithm includes adaptive inertia weights based on average granularity and a linearly adjusted learning factor.

[0010] Preferably, the model is constructed based on the total number of construction projects and the construction parameters of each construction project to obtain a power grid optimization combined decision model with multidimensional objective functions and multidimensional constraints, including:

[0011] Based on the total number of construction projects and the construction parameters of each construction project, a multi-dimensional objective function is constructed based on economic benefits, safety benefits, energy-saving benefits, and construction costs.

[0012] Based on the total number of construction projects and the construction parameters of each construction project, multi-dimensional constraints are constructed according to investment capacity constraints, power demand constraints, and investment project relationship constraints.

[0013] Preferably, the expression for the multidimensional objective function is:

[0014]

[0015] In the formula, F(x) is the maximum return function of the investment, E(x) is the economic benefit function of the investment, S(x) is the safety benefit function of the investment, D(x) is the energy-saving benefit function of the investment, and Q(x) is the penalty function for investment capacity.

[0016] Preferably, the economic benefit function is:

[0017]

[0018] The security benefit function is:

[0019]

[0020] The energy-saving benefit function is:

[0021]

[0022] The investment capability penalty function is:

[0023]

[0024] In the formula, N represents the total number of construction projects, T represents the life cycle of a construction project, and S represents the total number of construction projects. it Let C be the sales revenue of the i-th construction project in year t. it Let a be the operating cost of the i-th construction project in year t. i Let Q be the investment variable for the i-th construction project. i Let c1 be the construction cost of the i-th construction project, c2 be the influence coefficient of the remaining capacity of the power grid in the construction project, c2 be the influence coefficient of the insufficient capacity in the construction project, L be the average load of the power grid, and b be the construction cost of the ith construction project. i Let b be the new capacity of the i-th construction project, b be the capacity of the original power grid in the construction project, and W be the new capacity of the i-th construction project. h-i Let Δη be the electricity consumption of the i-th construction project. loss-i Let P be the network loss rate of the i-th construction project. f T represents the rated power of the f-th type of clean energy power generation. fLet f be the maximum utilization hours type coefficient for clean energy power generation, l be the total number of clean energy power generation, and e be the coefficient. i Let m1 be the emission reduction benefit per kilowatt-hour of the i-th construction project, m2, m3, m4 and m5 be the coal price per ton of standard coal, m2, m3, m4 and m5 be the environmental treatment costs per ton of carbon dioxide, sulfur dioxide, nitrogen oxides and dust, respectively, λ1 be the weight of standard coal saved per kilowatt-hour, and λ2, λ3, λ4 and λ5 be the emissions of carbon dioxide, sulfur dioxide, nitrogen oxides and dust.

[0025] Preferably, the multidimensional constraints include investment capacity constraints, electricity demand constraints, and investment project relationship constraints, and the expression for the investment capacity constraints is:

[0026]

[0027] The expression for the electricity demand constraint is:

[0028]

[0029] The expression for the investment project relationship constraint is as follows:

[0030]

[0031] In the formula, N represents the total number of construction projects, and Q... 0i Let Q be the investment amount for the i-th construction project, and let a be the total investment amount. i Let b be the investment variable for the i-th construction project. i Let B be the new capacity added by the i-th construction project, B be the power demand of the power grid, and a be the new capacity added by the i-th construction project. i+1 Let N be the investment variable for the (i+1)th construction project, and let N0 be the total investment variable for the construction project.

[0032] On the other hand, a decision-making device for power grid construction project investment is provided, including a data acquisition module, a model building module, and a decision output module;

[0033] The data acquisition module is used to acquire the total investment, the total number of construction projects, and the project construction parameters for each construction project;

[0034] The model building module is used to build a model based on the total number of construction projects and the construction parameters of each construction project, so as to obtain a power grid optimization combined decision model with multidimensional objective function and multidimensional constraints.

[0035] The decision output module is used to screen all the construction projects in the power grid optimization combination decision model according to the total investment amount using an improved particle swarm optimization algorithm to obtain investment decision results;

[0036] The improved particle swarm optimization algorithm includes adaptive inertia weights based on average granularity and a linearly adjusted learning factor.

[0037] Preferably, the model building module includes an objective function building submodule and a constraint condition building submodule;

[0038] The objective function construction submodule is used to construct a multi-dimensional objective function based on economic benefits, safety benefits, energy-saving benefits, and construction costs, according to the total number of construction projects and the project construction parameters of each construction project.

[0039] The constraint construction submodule is used to construct multi-dimensional constraint conditions based on the total number of construction projects and the project construction parameters of each construction project, using constraints on investment capacity, electricity demand, and investment project relationships.

[0040] Preferably, the expression for the multidimensional objective function is:

[0041]

[0042] In the formula, F(x) is the maximum return function of the investment, E(x) is the economic benefit function of the investment, S(x) is the safety benefit function of the investment, D(x) is the energy-saving benefit function of the investment, and Q(x) is the penalty function for investment capacity.

[0043] Preferably, the economic benefit function is:

[0044]

[0045] The security benefit function is:

[0046]

[0047] The energy-saving benefit function is:

[0048]

[0049] The investment capability penalty function is:

[0050]

[0051] The multidimensional constraints include investment capacity constraints, electricity demand constraints, and investment project relationship constraints. The expression for the investment capacity constraint is as follows:

[0052]

[0053] The expression for the electricity demand constraint is:

[0054]

[0055] The expression for the investment project relationship constraint is as follows:

[0056]

[0057] In the formula, Q 0i Let Q be the investment amount for the i-th construction project, N0 be the total investment, B be the electricity demand of the power grid, and a be the total investment amount for the construction project. i+1 Let S be the investment variable for the (i+1)th construction project, N be the total number of construction projects, T be the life cycle of the construction project, and S be the investment variable for the (i+1)th construction project. it Let C be the sales revenue of the i-th construction project in year t. it Let a be the operating cost of the i-th construction project in year t. i Let Q be the investment variable for the i-th construction project. i Let c1 be the construction cost of the i-th construction project, c2 be the influence coefficient of the remaining capacity of the power grid in the construction project, c2 be the influence coefficient of the insufficient capacity in the construction project, L be the average load of the power grid, and b be the construction cost of the ith construction project. i Let b be the new capacity of the i-th construction project, b be the capacity of the original power grid in the construction project, and W be the new capacity of the i-th construction project. h-i Let Δη be the electricity consumption of the i-th construction project. loss-i Let P be the network loss rate of the i-th construction project. f T represents the rated power of the f-th type of clean energy power generation. f Let f be the maximum utilization hours type coefficient for clean energy power generation, l be the total number of clean energy power generation, and e be the coefficient. i Let m1 be the emission reduction benefit per kilowatt-hour of the i-th construction project, m2, m3, m4 and m5 be the coal price per ton of standard coal, m2, m3, m4 and m5 be the environmental treatment costs per ton of carbon dioxide, sulfur dioxide, nitrogen oxides and dust, respectively, λ1 be the weight of standard coal saved per kilowatt-hour, and λ2, λ3, λ4 and λ5 be the emissions of carbon dioxide, sulfur dioxide, nitrogen oxides and dust.

[0058] On the other hand, a terminal device is provided, including a processor and a memory;

[0059] The memory is used to store program code and transmit the program code to the processor;

[0060] The processor is used to execute the above-described decision-making method for power grid construction project investment according to the instructions in the program code.

[0061] The decision-making method, apparatus, and terminal equipment for the power grid construction project investment include: obtaining the total investment amount, the total number of construction projects, and the project construction parameters for each construction project; constructing a model based on the total number of construction projects and the project construction parameters for each construction project to obtain a power grid optimization combination decision-making model with multi-dimensional objective functions and multi-dimensional constraints; in the power grid optimization combination decision-making model, using an improved particle swarm optimization algorithm based on the total investment amount to screen all construction projects and obtain the investment decision result; wherein, the improved particle swarm optimization algorithm includes adaptive inertial weights based on average granularity and linearly adjusted learning factors.

[0062] As can be seen from the above technical solutions, this application has the following advantages: The decision-making method for power grid construction project investment, by constructing a power grid optimization combination decision-making model with multidimensional objective functions and multidimensional constraints, combined with an improved particle swarm optimization algorithm, outputs the optimal investment decision-making results and expected return data based on the total investment amount and the total number of construction projects, thus obtaining the investment decision-making results of the optimal combination of construction projects; it solves the technical problem that the existing investment decision-making model outputs unreasonable and unscientific decision-making results due to the lack of comprehensive objective functions and constraints.

[0063] The decision-making device for power grid construction project investment constructs a power grid optimization combination decision-making model with multidimensional objective functions and multidimensional constraints, combined with an improved particle swarm optimization algorithm, to output the optimal investment decision results and expected return data based on the total investment amount and the total number of construction projects, thus obtaining the investment decision results of the optimal combination of construction projects. This solves the technical problem that existing investment decision-making models, due to insufficient comprehensive objective functions and constraints, result in unreasonable and unscientific output decision results. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart illustrating the steps of the decision-making method for power grid construction project investment as described in the embodiments of this application;

[0066] Figure 2 A line graph showing the selection of the power grid optimal combination decision model in the decision-making method for power grid construction project investment described in the embodiments of this application;

[0067] Figure 3This is a schematic diagram of the framework of the decision-making device for power grid construction project investment described in the embodiments of this application;

[0068] Figure 4 This is a schematic diagram of the terminal device described in an embodiment of this application. Detailed Implementation

[0069] To make the inventive objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0070] In the description of the embodiments of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0071] In the embodiments of this application, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this application according to the specific circumstances.

[0072] Investment decisions are a crucial step in the rational allocation of corporate funds. Correct and reasonable investment decisions are essential for improving economic efficiency and accelerating capital turnover. Power grid investment decisions involve phased project construction based on power grid planning, investment capacity, project importance, and construction schedule requirements. Therefore, decisions regarding power grid investment projects are particularly important.

[0073] Research on investment decision-making in power grid construction projects is still in its developmental stage. Traditional methods for solving the goal-planning problem of power grid investment decision-making typically include discrete approximation iterative methods and backward induction. Among these, the backward induction method generally uses empirical simulation studies to provide the optimal combination strategy, investment scale, and investment timing for power grid companies from a micro-level perspective of project investment decision-making. Existing intelligent optimization algorithms, such as genetic algorithms and ant colony algorithms, are also widely used to solve optimization problems. For example, genetic algorithms can be used to find the best matching combination to achieve the optimal goal of the overall investment plan, or to consider factors such as investment amount and construction period from the perspective of overall project optimization, and establish a cost-minimizing model for the overall project decision-making scheme.

[0074] In existing technologies, methods such as technology maturity theory, Markowitz models, and the eigenvalue method for expert group decisions have been applied to related research and to power grid investment decision optimization. However, these existing technologies still have some significant problems in investment decision research, the most core and typical being the simplification of objective functions and constraints. These technical shortcomings are key points restricting investment optimization decisions in power grid construction projects. Specifically, using only one project revenue indicator as the objective function and considering constraints in a one-sided manner makes it difficult to accurately solve the multi-criteria decision-making problem of combined investment in power grid construction projects. Therefore, in existing technologies, the objective functions and constraints are not comprehensive and systematic enough, lack constraints on investment capabilities, and the resulting investment schemes are not reasonable and scientific enough, requiring further research and improvement.

[0075] This application provides a decision-making method, apparatus, and terminal equipment for power grid construction project investment, solving the technical problem that existing investment decision-making models suffer from incomplete objective functions and constraints, leading to unreasonable and unscientific output decisions. In this embodiment, the decision-making method, apparatus, and terminal equipment for power grid construction project investment are illustrated using a power grid construction project as an example. The purpose of this method, apparatus, and terminal equipment is to select the optimal combination of investment projects from all power grid construction projects under limited capital constraints (investment capacity, such as total investment amount) to meet the regional power grid's electricity demand. In current power grid construction, multiple projects are typically invested in and constructed simultaneously. Under the premise of meeting electricity demand, capital and other constraints are introduced to optimize the combination of projects requiring investment, thereby obtaining the investment decision result.

[0076] Example 1:

[0077] Figure 1 This is a flowchart illustrating the steps of the decision-making method for power grid construction project investment as described in the embodiments of this application.

[0078] like Figure 1As shown in the embodiment of this application, a decision-making method for power grid construction project investment is provided, including the following steps:

[0079] S1. Obtain the total investment amount, the total number of construction projects, and the project construction parameters for each construction project.

[0080] It should be noted that step S1 involves obtaining the data needed for investment decisions in power grid construction projects. This data includes the total investment Q, the total number of construction projects N, and the project construction parameters for each project. In this embodiment, the project construction parameters for each construction project include the project's lifecycle T and the project's sales revenue S. it Operating costs of the construction project C it Investment variables of the construction project a i Construction cost Q of the construction project i The influence coefficients of the remaining capacity of the power grid in the construction project (c1), the influence coefficients of insufficient capacity in the construction project (c2), the average load of the power grid (L), and the new production capacity of the construction project (b). i a) The capacity of the original power grid in the construction project; b) The electricity consumption of the construction project (W). h-i Network loss rate Δη of the construction project loss-i Rated power P of clean energy power generation f Maximum utilization hours of clean energy power generation type coefficient T f Total amount of clean energy power generation (l), emission reduction benefit per kilowatt-hour of project emissions (e) i The following are the environmental treatment costs for each ton of standard coal (m1), each ton of carbon dioxide (m2), each ton of sulfur dioxide (m3), each ton of nitrogen oxides (m4), each ton of dust (m5), λ1 (weight of standard coal saved per kilowatt-hour), carbon dioxide emissions (λ2), sulfur dioxide emissions (λ3), nitrogen oxide emissions (λ4), dust emissions (λ5), and the project investment amount (Q). 0i The new production capacity of the construction project b i The variables include the power demand of the power grid (B) and the total investment of the construction project (N0). A value of 1 for the investment variable indicates that the construction project is feasible; a value of 0 indicates that the construction project is not feasible.

[0081] S2. Based on the total number of construction projects and the construction parameters of each project, a model is constructed to obtain a power grid optimization combined decision model with multidimensional objective functions and multidimensional constraints.

[0082] It should be noted that in step S2, a power grid optimization combined decision-making model is constructed based on the total number of construction projects and the project construction parameters of each construction project obtained in step S1. In this embodiment, the power grid optimization combined decision-making model includes a multi-dimensional objective function and multi-dimensional constraints. Specifically, constructing the power grid optimization combined decision-making model not only includes a data module for a multi-dimensional objective function that is compatible with many factors of power grid project investment, but also embeds a data module on top of the multi-dimensional objective function data module that incorporates various data processes such as independent, correlated, dependent, and mutually exclusive data, and is also compatible with subsequently expanded combined multi-dimensional constraints.

[0083] S3. In the power grid optimization and decision-making model, an improved particle swarm optimization algorithm is used to screen all construction projects based on the total investment amount to obtain the investment decision results.

[0084] It should be noted that in step S3, based on the total investment Q, an improved particle swarm optimization algorithm is used in the power grid optimization combination decision model to optimize and filter all construction projects, obtaining investment decision results and expected investment return data. In this embodiment, the existing particle swarm optimization algorithm is introduced into the power grid optimization combination decision model, and adaptation improvements are made so that the power grid optimization combination decision model outputs the optimal investment decision results and expected return data.

[0085] In this embodiment, the power grid construction project investment decision-making method constructs a power grid optimization combination decision model with the objective of maximizing investment utility, taking into account the constraints of electricity demand and investment capacity. Addressing the shortcomings of existing particle swarm optimization algorithms, such as slow convergence speed and long computation time, this power grid optimization combination decision model employs an improved particle swarm optimization algorithm to output better investment decision results and expected return data, thereby improving the convergence speed of optimization screening and enabling the power grid optimization combination decision model to output the investment decision result of the optimal project combination.

[0086] In the embodiments of this application, the improved particle swarm optimization algorithm includes adaptive inertia weights based on average granularity and a linearly adjusted learning factor.

[0087] It should be noted that existing particle swarm optimization (PSO) algorithms are intelligent evolutionary algorithms that simulate the behavior of biological groups such as flocks. Through collective cooperation among flocks of birds, the entire group can reach the optimal value. Existing PSO algorithms iteratively update the position and velocity of particles by analyzing their velocity and displacement. This PSO algorithm possesses excellent search performance characteristics, such as: clear concept, simple formula, few parameters, ease of programming, no special requirements for initial values, efficient hidden parallelism, and suitability for handling non-differentiable and non-convex functions.

[0088] In this embodiment, the main parameters of the existing particle swarm optimization algorithm include inertia weight w, learning factors (such as c1, c2), maximum velocity vmax, population size N, and maximum number of iterations Itera. This improved particle swarm optimization algorithm is derived based on improvements to the inertia weight and learning factor.

[0089] It should be noted that the inertia weight *w* has a significant impact on the convergence performance of the particle swarm optimization algorithm. A larger inertia weight *w* results in stronger global optimization and exploration capabilities; otherwise, stronger local optimization and exploration capabilities. Learning factors *c1* and *c2* reflect the strength of the particles' own thinking and the information exchange between particles. The maximum velocity *vmax* can balance global and local search capabilities, effectively control the search range, and be set to anticipate the problem to be optimized. The population size *N* (also representing the total number of power grid construction projects) represents the number of particles searching simultaneously and determines the minimum number of updates required in each iteration. The maximum number of iterations *Itera* determines the computational cost, thus indirectly affecting the convergence accuracy, because when the number of iterations is small, the population will not have enough time to find the global optimum.

[0090] In the embodiments of this application, the improvement of the inertia weight in the improved particle swarm optimization algorithm is achieved based on an adaptive inertia weight adjustment strategy of average granularity. The adaptive inertia weight adjustment strategy includes: adaptive adjustment of average particle size and inertia weight; average particle size: it reflects the degree of dispersion among particles in the swarm. The formula for calculating the "average particle size" of the swarm in the k-th iteration is as follows:

[0091]

[0092] In the formula, L0 is the diagonal length of the search space; N is the total number of projects; D is the dimension of the solution space; x ij k x represents the coordinates of the i-th particle relative to the j-th dimension in the k-th iteration; j k x is the average value of the k-th iteration relative to the j-th dimension coordinates; j,max and x j，min Let $\mathbf{j}$ be the upper and lower bounds of the j-th dimension of the feasible region space, respectively. The expression for the adaptive adjustment of the inertia weight is:

[0093]

[0094] In the formula, Dis(k) is the average particle distance; w(k) is the inertia weight in the k-th iteration. In this embodiment, upper and lower limits can be set to prevent the inertia weight from exceeding the boundaries. When the average particle distance is large, the inertia weight is large, achieving global search. When the average particle distance is small, the inertia weight is small, achieving fine-grained regional search.

[0095] In the embodiments of this application, the improvement of the inertia weight in the improved particle swarm optimization algorithm is achieved based on the improvement of the learning factor, and the expression for linearly adjusting the learning factor is:

[0096]

[0097] In the formula, c 1，max c 1，min c 2，max c 2，min Let c1 and c2 be the upper and lower bounds, respectively. At the start of the iteration, c1 is large and c2 is small. The iterative updates of particles in the population are mainly based on the particles' own experience. Then c1 decreases and c2 increases. Cooperation among particles is strengthened, thus enabling the population to move towards the global optimum.

[0098] Figure 2 This is a line graph used to screen the power grid optimization combination decision-making model in the power grid construction project investment decision-making method described in the embodiments of this application.

[0099] In this embodiment, N=7 power grid construction projects to be invested in are used as a case study to analyze the practicality of the decision-making method for power grid construction project investment. Relevant data for the N=7 power grid construction projects to be invested in are shown in Table 1. It is assumed that the expected lifespan of each power grid construction project is T=30 years, and the annual net income and operating costs of each project will never change in the next 30 years. The parameter values ​​of learning factors c1 and c2 are 0.1 and 0.2, respectively, and the total investment Q is 180 million yuan. The sum of the selected project capacities represents the new capacity of the power grid system. The selected seven construction projects are optimized using the constructed power grid optimization combination decision model, and the improved adaptive particle swarm optimization algorithm is used to solve the power grid optimization combination decision model. In the power grid optimization combination decision model, the parameter settings include: population size N = 50; maximum number of iterations k = 150; maximum speed vmax = 10; and learning factor c... 1，max c 1，min c 2，max c 2，min The values ​​are 2.75, 1.25, 2.25, and 1.05 respectively; the initial value of the inertia weight, wmax, is 0.8; and the final value of the inertia weight, wmin, is 0.3. The optimization process of this improved adaptive particle swarm optimization algorithm is as follows: Figure 2 As shown in Table 2, this power grid optimization decision-making model transforms investment capacity constraints into objective functions based on the economic, social, and reliability considerations of power grid construction projects. An improved particle swarm optimization algorithm is then used to optimize the power grid optimization decision-making model, resulting in the final optimization results, including investment decision outcomes and expected return data.

[0100] Table 1 shows the relevant data for each construction project.

[0101]

[0102] Table 2 shows the main indicators of the regional 220 kV power grid construction scale.

[0103]

[0104] As shown in Table 2, the power grid optimization combined decision model based on the improved particle swarm optimization algorithm outputs the final investment decision results for the power grid construction project as project names B, D, E, and f, with an expected return of 56.8 million yuan.

[0105] This application provides a decision-making method for power grid construction project investment, including obtaining the total investment amount, the total number of construction projects, and the project construction parameters for each construction project; constructing a model based on the total number of construction projects and the project construction parameters for each construction project to obtain a power grid optimal combination decision-making model with multidimensional objective functions and multidimensional constraints; in the power grid optimal combination decision-making model, using an improved particle swarm optimization algorithm based on the total investment amount to screen all construction projects and obtain the investment decision result; wherein, the improved particle swarm optimization algorithm includes adaptive inertia weights based on average granularity and a linearly adjusted learning factor. This decision-making method for power grid construction project investment, by constructing a power grid optimal combination decision-making model with multidimensional objective functions and multidimensional constraints and combining it with the improved particle swarm optimization algorithm, outputs the optimal investment decision result and expected return data based on the total investment amount and the total number of construction projects, thus obtaining the optimal project combination investment decision result; it solves the technical problem that existing investment decision-making models, due to insufficient comprehensiveness of objective functions and constraints, result in unreasonable and unscientific output decision results.

[0106] In one embodiment of this application, a model is constructed based on the total number of construction projects and the project construction parameters of each construction project to obtain a power grid optimization combined decision model with multidimensional objective functions and multidimensional constraints, including:

[0107] Based on the total number of construction projects and the project construction parameters of each project, a multi-dimensional objective function is constructed based on economic benefits, safety benefits, energy-saving benefits, and construction costs.

[0108] Based on the total number of construction projects and the construction parameters of each project, multi-dimensional constraints are constructed according to investment capacity constraints, power demand constraints, and investment project relationship constraints.

[0109] It should be noted that the expression for the multidimensional objective function is:

[0110]

[0111] In the formula, F(x) is the maximum return function of the investment, E(x) is the economic benefit function of the investment, S(x) is the safety benefit function of the investment, D(x) is the energy-saving benefit function of the investment, and Q(x) is the investment capacity penalty function. The multidimensional objective function is an objective function that comprehensively considers the economic, safety, and energy-saving benefits after power grid optimization investment.

[0112] In the embodiments of this application, the economic benefit function is:

[0113]

[0114] The safety benefit function is:

[0115]

[0116] The energy-saving benefit function is:

[0117]

[0118] The investment capability penalty function is:

[0119]

[0120] In the formula, N represents the total number of construction projects, T represents the life cycle of a construction project, and S represents the total number of construction projects. it Let C be the sales revenue of the i-th construction project in year t. it Let a be the operating cost of the i-th construction project in year t. i Let Q be the investment variable for the i-th construction project. i Let c1 be the construction cost of the i-th construction project, c2 be the influence coefficient of the remaining capacity of the power grid in the construction project, c2 be the influence coefficient of the insufficient capacity in the construction project, L be the average load of the power grid, and b be the construction cost of the ith construction project. i Let b be the new capacity of the i-th construction project, b be the capacity of the original power grid in the construction project, and W be the new capacity of the i-th construction project. h-i Let Δη be the electricity consumption of the i-th construction project. loss-i Let P be the network loss rate of the i-th construction project. f T represents the rated power of the f-th type of clean energy power generation. f Let f be the maximum utilization hours type coefficient for clean energy power generation, l be the total number of clean energy power generation, and e be the coefficient. i Let m1 be the emission reduction benefit per kilowatt-hour of the i-th construction project, m2, m3, m4 and m5 be the coal price per ton of standard coal, m2, m3, m4 and m5 be the environmental treatment costs per ton of carbon dioxide, sulfur dioxide, nitrogen oxides and dust, respectively, λ1 be the weight of standard coal saved per kilowatt-hour, and λ2, λ3, λ4 and λ5 be the emissions of carbon dioxide, sulfur dioxide, nitrogen oxides and dust.

[0121] It should be noted that economic benefits can be obtained through the economic benefit function by calculating investment costs, annual returns, investment expenses, and investment costs. The safety benefit function uses the capacity-to-load ratio to measure the reliability of a construction project's investment. When the capacity-to-load ratio is too high, more electrical equipment will be idle, leading to lower investment efficiency. Conversely, if it is too low, it will suppress electricity consumption, which is detrimental to economic development. Therefore, under the premise of meeting demand and ensuring reliability, the value of the capacity-to-load ratio should be gradually reduced and controlled within a certain range. Energy-saving benefits are obtained through the energy-saving benefit function, which calculates the benefits constructed after considering the electricity generated by distributed power sources and the network losses of the construction project. Construction costs are calculated through the investment capacity penalty function, which calculates the total investment of all construction projects.

[0122] In one embodiment of this application, the multidimensional constraints include investment capacity constraints, electricity demand constraints, and investment project relationship constraints. The expression for the investment capacity constraint is as follows:

[0123]

[0124] The expression for the electricity demand constraint is:

[0125]

[0126] The expression for the investment project relationship constraint is:

[0127]

[0128] In the formula, N represents the total number of construction projects, and Q... 0i Let Q be the investment amount for the i-th construction project, and let a be the total investment amount. i Let b be the investment variable for the i-th construction project. i Let B be the new capacity added by the i-th construction project, B be the power demand of the power grid, and a be the new capacity added by the i-th construction project. i+1 Let N be the investment variable for the (i+1)th construction project, and let N0 be the total investment variable for the construction project.

[0129] It should be noted that the investment capacity constraint indicates that the total investment amount after optimization should not exceed the investment capacity of the power grid company. The electricity demand constraint indicates that, subject to investment capacity constraints, the newly added power grid capacity must meet the social electricity demand. The investment project relationship constraint can be defined by the existence of several relationships between N construction projects.

[0130] In this embodiment of the application, if all construction projects are independent of each other, the investment project relationship constraint is as follows:

[0131]

[0132] If all construction projects are mutually exclusive, then the investment project relationship constraints are as follows:

[0133]

[0134] If the construction projects are interdependent, it can be understood that: only if construction project i is selected can construction project i+1 be selected; otherwise, if construction project i is not selected, construction project i+1 may not be selected. Therefore, the investment project relationship constraint is: ;

[0135] If the construction projects are closely related, it can be understood that the two construction projects must be selected simultaneously or not simultaneously. Therefore, the investment project relationship constraints are as follows: .

[0136] Example 2:

[0137] Figure 3 This is a schematic diagram of the framework of the decision-making device for power grid construction project investment as described in the embodiments of this application.

[0138] like Figure 3 As shown in the figure, this application provides a decision-making device for power grid construction project investment, including a data acquisition module 10, a model building module 20 and a decision output module 30;

[0139] Data acquisition module 10 is used to acquire the total investment, the total number of construction projects, and the project construction parameters of each construction project;

[0140] The model building module 20 is used to build a model based on the total number of construction projects and the project construction parameters of each construction project, so as to obtain a power grid optimization combined decision model with multidimensional objective function and multidimensional constraints.

[0141] The decision output module 30 is used to screen all construction projects in the power grid optimization combined decision model based on the total investment using an improved particle swarm optimization algorithm to obtain investment decision results.

[0142] Among them, the improved particle swarm optimization algorithm includes adaptive inertia weights based on average granularity and linearly adjusted learning factors.

[0143] It should be noted that the modules in the decision-making device for power grid construction project investment in Example 2 correspond to the steps in the decision-making method for power grid construction project investment. The steps in the decision-making method for power grid construction project investment have already been described in Example 1, and will not be elaborated further in this example. This decision-making device for power grid construction project investment, by constructing a power grid optimization combination decision-making model with multi-dimensional objective functions and multi-dimensional constraints, combined with an improved particle swarm optimization algorithm, outputs the optimal investment decision-making result and expected return data based on the total investment amount and the total number of construction projects, thus obtaining the optimal investment decision-making result for the optimal combination of construction projects. This solves the technical problem that existing investment decision-making models, due to insufficient comprehensive objective functions and constraints, result in unreasonable and unscientific output decision-making results.

[0144] In this embodiment, the model building module 20 includes an objective function building submodule and a constraint condition building submodule;

[0145] The objective function construction submodule is used to construct a multi-dimensional objective function based on economic benefits, safety benefits, energy-saving benefits, and construction costs, according to the total number of construction projects and the project construction parameters of each construction project.

[0146] The constraint construction submodule is used to construct multi-dimensional constraint conditions based on the total number of construction projects and the project construction parameters of each construction project, including investment capacity constraints, power demand constraints, and investment project relationship constraints.

[0147] In this embodiment of the application, the expression for the multidimensional objective function is:

[0148]

[0149] In the formula, F(x) is the maximum return function of the investment, E(x) is the economic benefit function of the investment, S(x) is the safety benefit function of the investment, D(x) is the energy-saving benefit function of the investment, and Q(x) is the penalty function for investment capacity.

[0150] In this embodiment of the application, the economic benefit function is:

[0151]

[0152] The safety benefit function is:

[0153]

[0154] The energy-saving benefit function is:

[0155]

[0156] The investment capability penalty function is:

[0157]

[0158] The multidimensional constraints include investment capacity constraints, electricity demand constraints, and investment project relationship constraints. The expression for the investment capacity constraint is as follows:

[0159]

[0160] The expression for the electricity demand constraint is:

[0161]

[0162] The expression for the investment project relationship constraint is:

[0163]

[0164] In the formula, Q 0i Let Q be the investment amount for the i-th construction project, N0 be the total investment, B be the electricity demand of the power grid, and a be the total investment amount for the construction project. i+1 Let S be the investment variable for the (i+1)th construction project, N be the total number of construction projects, T be the life cycle of the construction project, and S be the investment variable for the (i+1)th construction project. it Let C be the sales revenue of the i-th construction project in year t. it Let a be the operating cost of the i-th construction project in year t. i Let Q be the investment variable for the i-th construction project. i Let c1 be the construction cost of the i-th construction project, c2 be the influence coefficient of the remaining capacity of the power grid in the construction project, c2 be the influence coefficient of the insufficient capacity in the construction project, L be the average load of the power grid, and b be the construction cost of the ith construction project. i Let b be the new capacity of the i-th construction project, b be the capacity of the original power grid in the construction project, and W be the new capacity of the i-th construction project. h-i Let Δη be the electricity consumption of the i-th construction project. loss-i Let P be the network loss rate of the i-th construction project. f T represents the rated power of the f-th type of clean energy power generation. f Let f be the maximum utilization hours type coefficient for clean energy power generation, l be the total number of clean energy power generation, and e be the coefficient. i Let m1 be the emission reduction benefit per kilowatt-hour of the i-th construction project, m2, m3, m4 and m5 be the coal price per ton of standard coal, m2, m3, m4 and m5 be the environmental treatment costs per ton of carbon dioxide, sulfur dioxide, nitrogen oxides and dust, respectively, λ1 be the weight of standard coal saved per kilowatt-hour, and λ2, λ3, λ4 and λ5 be the emissions of carbon dioxide, sulfur dioxide, nitrogen oxides and dust.

[0165] Example 3:

[0166] Figure 4This is a schematic diagram of the terminal device described in an embodiment of this application.

[0167] like Figure 4 As shown, this application provides a terminal device, including a processor and a memory;

[0168] Memory is used to store program code and transfer the program code to the processor;

[0169] The processor is used to execute the aforementioned decision-making method for power grid construction project investment based on instructions in the program code.

[0170] It should be noted that the processor is used to execute the steps in the above-described embodiment of a decision-making method for power grid construction project investment according to the instructions in the program code. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described system / device embodiments.

[0171] For example, a computer program can be divided into one or more modules / units, one or more of which are stored in memory and executed by a processor to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0172] Terminal devices can be computing devices such as desktop computers, laptops, handheld computers, and cloud servers. Terminal devices may include, but are not limited to, processors and memory. Those skilled in the art will understand that this does not constitute a limitation on the terminal device, which may include more or fewer components than illustrated, or combinations of certain components, or different components. For example, a terminal device may also include input / output devices, network access devices, buses, etc.

[0173] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor, etc.

[0174] Memory can be an internal storage unit of a terminal device, such as a hard drive or RAM. Memory can also be an external storage device, such as a plug-in hard drive, smart memory card (SMC), secure digital card (SD) card, or flash card. Furthermore, memory can include both internal and external storage units. Memory is used to store computer programs and other programs and data required by the terminal device. Memory can also be used to temporarily store data that has been output or will be output.

[0175] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0176] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0177] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0178] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0179] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0180] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method of decision making for investment in a power grid construction project, characterized by, The method comprises the following steps: acquiring a total investment amount, a total number of construction projects, and project construction parameters of each construction project; model construction is performed according to the total number of construction projects and the project construction parameters of each construction project, to obtain a power grid optimization combination decision model with a multi-dimensional objective function and a multi-dimensional constraint condition; all the construction projects are screened in the power grid optimization combination decision model according to the total investment amount by using an improved particle swarm optimization algorithm, to obtain an investment decision result; the improved particle swarm optimization algorithm comprises an adaptive inertia weight based on average particle size and a linear adjustment learning factor; the multi-dimensional objective function comprises an economic benefit function, a safety benefit function, an energy-saving benefit function, and an investment capacity penalty function; the economic benefit function is: ； the safety benefit function is: ； the energy-saving benefit function is: ； the investment capacity penalty function is: ； Where N is the total number of construction projects, T is the life cycle of the construction project, S it is the sales revenue of the ith construction project in the tth year, C it is the operating cost of the ith construction project in the tth year, a i is the investment variable of the ith construction project, Q i is the construction cost of the ith construction project, c1 is the influence coefficient of the remaining capacity of the power grid in the construction project, c2 is the influence coefficient of the insufficient capacity in the construction project, L is the average load of the power grid, b i is the new capacity of the ith construction project, b is the capacity of the original power grid in the construction project, W h-i is the electricity consumption of the ith construction project, Δη loss-i is the network loss rate of the ith construction project, P f is the rated power of the fth clean energy power generation, T f is the maximum utilization hour type coefficient of the fth clean energy power generation, l is the total number of clean energy power generations, e i is the emission reduction benefit of the ith construction project per kilowatt hour, m1 is the price of coal per ton of standard coal, m2, m3, m4 and m5 are the environmental treatment costs of carbon dioxide, sulfur dioxide, nitrogen oxides and dust per ton, λ1 is the weight of standard coal saved per kilowatt hour, λ2, λ3, λ4 and λ5 are the emission amounts of carbon dioxide, sulfur dioxide, nitrogen oxides and dust, E(x) is the economic benefit function of investment, S(x) is the safety benefit function of investment, D(x) is the energy saving benefit function of investment, and Q(x) is the investment capacity penalty function.

2. The method of decision making for grid development project investments according to claim 1, characterized in that, the model construction comprises the following steps: a multi-dimensional objective function is constructed based on economic benefit, safety benefit, energy-saving benefit, and construction cost according to the total number of construction projects and the project construction parameters of each construction project; a multi-dimensional constraint condition is constructed based on investment capacity constraint, power demand constraint, and investment project relationship constraint according to the total number of construction projects and the project construction parameters of each construction project.

3. The method for decision making of grid development project investment according to claim 2, characterized in that, The expression of the multi-dimensional objective function is: ； in the formula, F(x) is a maximum benefit function of investment.

4. The method of decision making for grid development project investment according to claim 2, characterized in that, The multi-dimensional constraint condition comprises an investment capacity constraint condition, a power demand constraint condition, and an investment project relationship constraint condition, the expression of the investment capacity constraint condition is: ； the expression of the power demand constraint condition is: ； the expression of the investment project relationship constraint condition is: ; or ; or ; or ； where N is the total number of construction projects, Q 0i is the investment amount of the i-th construction project, Q is the total investment, a i is the investment variable of the i-th construction project, b i is the new capacity of the i-th construction project, B is the power demand of the power grid, a i+1 is the investment variable of the i+1-th construction project, N0 is the total variable value of the investment of the construction projects.

5. A decision device for grid construction project investment, characterized by, The method comprises the following steps: a data acquisition module, a model construction module, and a decision output module; the data acquisition module is used to acquire a total investment amount, a total number of construction projects, and project construction parameters of each construction project; the model construction module is used to perform model construction according to the total number of construction projects and the project construction parameters of each construction project, to obtain a power grid optimization combination decision model with a multi-dimensional objective function and a multi-dimensional constraint condition; the decision output module is used to screen all the construction projects in the power grid optimization combination decision model according to the total investment amount by using an improved particle swarm optimization algorithm, to obtain an investment decision result; the improved particle swarm optimization algorithm comprises an adaptive inertia weight based on average particle size and a linear adjustment learning factor; the multi-dimensional objective function comprises an economic benefit function, a safety benefit function, an energy-saving benefit function, and an investment capacity penalty function; ； the economic benefit function is: ； the safety benefit function is: ； the energy-saving benefit function is: ； Where N is the total number of construction projects, T is the life cycle of the construction project, S it is the sales revenue of the ith construction project in the tth year, C it is the operating cost of the ith construction project in the tth year, a i is the investment variable of the ith construction project, Q i is the construction cost of the ith construction project, c1 is the influence coefficient of the remaining capacity of the power grid in the construction project, c2 is the influence coefficient of the insufficient capacity in the construction project, L is the average load of the power grid, b i is the added capacity of the ith construction project, b is the capacity of the original power grid in the construction project, W h-i is the electricity consumption of the ith construction project, Δη loss-i is the network loss rate of the ith construction project, P f is the rated power of the fth clean energy power generation, T f is the maximum utilization hour type coefficient of the fth clean energy power generation, l is the total number of clean energy power generations, e i is the emission reduction benefit of the ith construction project per kilowatt hour, m1 is the price of coal per ton of standard coal, m2, m3, m4 and m5 are the environmental treatment costs of carbon dioxide, sulfur dioxide, nitrogen oxides and dust per ton, λ1 is the weight of standard coal saved per kilowatt hour, λ2, λ3, λ4 and λ5 are the emission amounts of carbon dioxide, sulfur dioxide, nitrogen oxides and dust, E(x) is the economic benefit function of investment, S(x) is the safety benefit function of investment, D(x) is the energy saving benefit function of investment, and Q(x) is the investment capacity penalty function.

6. The grid development project investment decision apparatus according to claim 5, wherein, the investment capacity penalty function is: the model construction module comprises an objective function construction sub-module and a constraint condition construction sub-module; The target function construction submodule is configured to construct a multi-dimensional target function based on economic benefits, safety benefits, energy-saving benefits and construction costs according to the total number of construction projects and the project construction parameters of each construction project. The constraint condition construction submodule is configured to construct a multi-dimensional constraint condition based on investment capacity constraints, power demand constraints and investment project relationship constraints according to the total number of construction projects and the project construction parameters of each construction project.

7. The apparatus for decision making of grid development project investment according to claim 6, characterized in that, The expression of the multi-dimensional target function is as follows: ； In the formula, F(x) is a maximum income function of investment.

8. The apparatus for decision making of investment in a grid construction project according to claim 6, wherein, The multi-dimensional constraint condition includes investment capacity constraints, power demand constraints and investment project relationship constraints. ； The expression of the power demand constraint condition is as follows: ； The expression of the investment project relationship constraint condition is as follows: ; or ; or ; or ； wherein Q 0i Qi is the investment amount of the ith construction project, Q is the total investment, No is the total variable number of the investment of the construction project, B is the power demand of the power grid, a i+1 Qi+1 is the investment variable of the i+1th construction project, N is the total number of the construction projects, a i Qi is the investment variable of the ith construction project, b i Qi is the added capacity of the ith construction project.

9. A terminal device, comprising: The power grid construction project investment decision method comprises a processor and a memory. The memory is configured to store program code and transmit the program code to the processor. The processor is configured to execute the power grid construction project investment decision method according to instructions in the program code.

Images