Energy configuration scheme generation method and device of multi-energy system and electronic equipment

Abstract

The application provides an energy configuration scheme generation method and device of a multi-energy system and electronic equipment, relates to the technical field of computers, and comprises the following steps: obtaining papermaking industry system operation parameters; performing comprehensive modeling according to the papermaking industry system operation parameters to obtain an energy system model, wherein the energy system model comprises an energy target function, an economic target function and an environmental target function; based on an improved NSGA-II algorithm, the energy system model is solved to obtain a plurality of initial optimal solutions; and based on a TOPSIS algorithm, all the initial optimal solutions are sorted to obtain a papermaking industry energy configuration scheme. The application realizes the improvement of the efficiency of energy configuration while ensuring accuracy.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method, apparatus, and electronic device for generating energy configuration schemes for multi-energy systems. Background Technology

[0002] The energy systems of the paper industry typically encompass multiple energy inputs and conversion methods, involving various energy forms such as coal-fired boilers, biogas generators, purchased electricity, and purchased steam. This results in a complex, highly coupled, multi-energy complementary system that requires simultaneous multi-level and multi-type decision-making.

[0003] Traditional energy system decision-making methods are prone to slow convergence, getting trapped in local optima, and uneven distribution of frontier solutions when dealing with problems with high-dimensional decision variables and complex nonlinear coupling relationships. As a result, energy allocation schemes in the paper industry cannot meet the comprehensiveness and efficiency required by actual needs. Summary of the Invention

[0004] The problem addressed by this invention is how to improve the efficiency of energy allocation while ensuring accuracy.

[0005] To address the aforementioned problems, this invention provides a method, apparatus, and electronic device for generating energy configuration schemes for multi-energy systems.

[0006] In a first aspect, the present invention provides a method for generating an energy configuration scheme for a multi-energy system, comprising:

[0007] Obtain system operating parameters for the paper industry;

[0008] A comprehensive model is obtained by performing a comprehensive modeling based on the operating parameters of the paper industry system, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function;

[0009] Based on the improved NSGA-II algorithm, multiple initial optimal solutions are obtained by solving the energy system model.

[0010] Based on the TOPSIS algorithm, all the initial optimal solutions are sorted to obtain the energy configuration scheme for the paper industry.

[0011] Optionally, solving the energy system model yields multiple initial optimal solutions, including:

[0012] An initial population is obtained based on the energy system model, wherein the initial population includes multiple individuals;

[0013] The initial population is screened to obtain the initial parent population;

[0014] The initial parent population is subjected to selection, crossover, and mutation operations to obtain a new offspring population;

[0015] Based on the adaptive random walk mechanism, a new parent population is obtained from the initial parent population and the new offspring population. The process of performing selection, crossover, and mutation operations on the initial parent population to obtain a new offspring population is then repeated until a preset condition is met, resulting in multiple initial optimal solutions.

[0016] Optionally, the step of performing selection, crossover, and mutation operations on the initial parent population to obtain a new offspring population includes:

[0017] The selected parent population is obtained by performing non-dominated quicksort and crowding distance calculation on the initial parent population.

[0018] The congestion distance calculation includes:

[0019] ,

[0020] in, For individual i, the crowding distance The maximum value of the k-th target dimension. The minimum value of the k-th target dimension. Let be the function value of individual i in the k-th target dimension. Let i be the function value of individual i-1 in the k-th target dimension. Let be the function value of individual i+1 in the k-th target dimension, and M be the total number of individuals;

[0021] The selected parent population is subjected to crossover and mutation operations to obtain the new offspring population.

[0022] Optionally, obtaining a new parent population based on the initial parent population and the new offspring population includes:

[0023] Perturbation analysis is performed on each individual of the new offspring population to obtain the processed offspring population;

[0024] The disturbance analysis includes:

[0025] ,

[0026] in, This represents the position of the i-th individual in the treated offspring population. Let i be the position of the i-th individual in the new offspring population. Step size factor Let i be the historical direction of the i-th individual in the new offspring population. The disturbance is random, and N is the total population size.

[0027] The initial parent population and the processed offspring population are combined to obtain the new parent population.

[0028] Optionally, the step of sorting all the initial optimal solutions to obtain the energy allocation scheme for the paper industry includes:

[0029] The distances to the positive and negative ideal solutions are obtained based on all the initial optimal solutions.

[0030] The distance to the positive ideal solution includes:

[0031] ,

[0032] in, Let the distance be the positive ideal solution. Let be the normalized value of the i-th scheme on the k-th metric. Let M be the positive ideal solution for the k-th indicator, and M be the number of evaluation indicators.

[0033] The negative ideal solution distance includes:

[0034] ,

[0035] in, The distance to the negative ideal solution. The negative ideal solution for the k-th index;

[0036] A similarity score is obtained by performing a similarity score using the positive ideal solution distance and the negative ideal solution distance;

[0037] The similarity score includes:

[0038] ,

[0039] in, Score the similarity.

[0040] The initial optimal solution is sorted using the corresponding similarity score to obtain the energy allocation scheme for the paper industry.

[0041] Optionally, the step of comprehensively modeling the energy system based on the operating parameters of the paper industry system to obtain the energy system model includes:

[0042] Based on the system operating parameters of the paper industry, a comprehensive model is performed to obtain the energy objective function, which is used to represent the amount of standard coal consumed in papermaking.

[0043] The energy efficiency objective function includes:

[0044] ,

[0045] in, The term "papermaking standard coal consumption" refers to the amount of standard coal consumed per unit of paper. To sum the data for all energy types, Let L be the energy consumption at time t, and L be the quantity of energy types. As the lower heating value of energy, The lower calorific value of standard coal. Annual paper production;

[0046] Based on the system operating parameters of the paper industry, a comprehensive model is performed to obtain the economic objective function, wherein the economic objective function is used to represent the total annual operating cost;

[0047] The economic objective function includes:

[0048] ,

[0049] in, The total annual operating cost, The cost of purchasing energy at time t. The operation and maintenance cost of energy at time t. The carbon trading cost of energy at time t;

[0050] Based on the system operating parameters of the papermaking industry, a comprehensive model is performed to obtain the environmental objective function, which is used to represent the total annual carbon emissions.

[0051] The environmental objective function includes:

[0052] ,

[0053] in, The total annual carbon emissions are [the stated amount]. Carbon emission factors for energy.

[0054] Optionally, before performing comprehensive modeling based on the operating parameters of the paper industry system to obtain the energy system model, the method further includes:

[0055] The steam supply and demand balance constraints, power load constraints, and equipment operation constraints are obtained from the system operating parameters of the paper industry.

[0056] Secondly, the present invention provides an energy configuration scheme generation device for a multi-energy system, comprising: a paper industry system operating parameter acquisition module, used to acquire paper industry system operating parameters;

[0057] The energy system model acquisition module is used to perform comprehensive modeling based on the operating parameters of the paper industry system to obtain an energy system model, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function;

[0058] The initial optimal solution acquisition module is used to solve the energy system model based on the improved NSGA-II algorithm to obtain multiple initial optimal solutions;

[0059] The energy configuration scheme acquisition module for the paper industry is used to sort all the initial optimal solutions based on the TOPSIS algorithm to obtain the energy configuration scheme for the paper industry.

[0060] Thirdly, the present invention provides an electronic device, including a memory and a processor;

[0061] The memory is used to store computer programs;

[0062] The processor is configured to, when executing the computer program, implement the energy configuration scheme generation method for a multi-energy system as described in the first aspect.

[0063] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for generating an energy configuration scheme for a multi-energy system as described in the first aspect.

[0064] The beneficial effects of the energy configuration scheme generation method, device, and electronic equipment for multi-energy systems of the present invention are as follows: Real operating parameters are collected to obtain system operating parameters for the paper industry, and an energy system model including energy objective functions, economic objective functions, and environmental objective functions is constructed, truly realizing green manufacturing and sustainable development. An improved NSGA-II algorithm is introduced to solve the energy system model, obtaining multiple initial optimal solutions, which are more suitable for the decision-making characteristics of the paper industry, with a wide solution set coverage, facilitating subsequent decision selection. Based on the TOPSIS algorithm, the optimal solutions are sorted, automatically identifying the optimal energy configuration scheme for the paper industry, improving the efficiency of energy configuration while ensuring accuracy. Attached Figure Description

[0065] Figure 1 This is a flowchart illustrating a method for generating an energy configuration scheme for a multi-energy system according to an embodiment of the present invention.

[0066] Figure 2 This is a schematic diagram of the structure of an energy configuration scheme generation device for a multi-energy system according to an embodiment of the present invention;

[0067] Figure 3This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0068] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0069] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0070] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to"; the term "based on" means "at least partially based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; and the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first," "second," etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0071] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0072] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0073] In related technologies, paper mills have gradually introduced renewable energy technologies such as sludge incineration and biogas power generation. However, due to the lack of scientific and effective integration and optimization methods, the application potential of these renewable energy sources has not been fully realized, resulting in limited improvement in the energy structure and significant constraints on the overall economic and environmental benefits.

[0074] In recent years, under the pressure of the "dual carbon" strategic goal and increasingly stringent environmental policies, the paper industry urgently needs to optimize and upgrade its energy system to achieve sustainable development while balancing economic benefits, energy efficiency, and environmental benefits. However, traditional single-objective optimization methods, such as those focusing only on cost or emissions, are insufficient to address the highly complex conflicts and coupling relationships between the economy, environment, and energy, and cannot provide enterprises with comprehensive optimal decision-making solutions. Therefore, the academic community has gradually introduced multi-objective optimization techniques in recent years, especially evolutionary algorithms represented by the Non-Dominated Sorting Genetic Algorithm (NSGA-II), which are widely used in industry. However, existing NSGA-II algorithms still exhibit significant shortcomings when dealing with the complex, multi-energy systems of the paper industry, such as slow convergence speed, susceptibility to local optima, and uneven distribution of Pareto front solutions, which restricts their widespread application in practical engineering.

[0075] Furthermore, even with a sufficiently large Pareto solution set, companies still face the challenge of efficiently and accurately selecting the optimal solution when making decisions. Traditional experience-based or manual decision-making methods struggle to quickly and scientifically evaluate the complex trade-offs between multiple objectives, resulting in low decision-making efficiency and insufficient accuracy. Single decision-making methods still cannot effectively solve the complex trade-offs between multiple objectives, and they have failed to demonstrate sufficient comprehensive advantages in the context of the complex energy system optimization in the paper industry.

[0076] To address the problems existing in the aforementioned related technologies, this embodiment provides a method, apparatus, and electronic device for generating energy configuration schemes for multi-energy systems.

[0077] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for generating an energy configuration scheme for a multi-energy system, comprising:

[0078] Step 110: Obtain the system operating parameters for the paper industry.

[0079] Specifically, the system operating parameters for the paper industry include the performance parameters of each piece of equipment in the system, as well as the supply and consumption of various energy sources. Equipment parameters, such as the maximum steam output capacity of boilers, the rated power of generator sets, and the configuration capacity of biogas units, will provide data support for subsequent modeling. Energy resource data includes the supply, procurement costs, and corresponding carbon emission factors of coal, biogas, electricity, and steam.

[0080] Step 120: Based on the operating parameters of the paper industry system, a comprehensive model is performed to obtain an energy system model, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function.

[0081] Specifically, a comprehensive modeling approach is employed to detail the energy consumption, carbon emissions, and interrelationships of each component in the system (such as boilers, biogas generators, electricity purchased from the grid, and steam procurement). Key energy, economic, and environmental objectives are clearly defined. The economic objective is modeled through system operating costs, considering factors such as energy procurement costs, equipment maintenance costs, and carbon emission trading costs, aiming to reduce total costs while meeting system requirements. The environmental objective focuses on minimizing system carbon emissions, particularly carbon dioxide emissions, contributing to environmental protection and carbon reduction. The energy objective aims to improve energy efficiency and reduce unit energy consumption, especially the amount of standard coal consumed per unit of product (such as paper). The energy system model primarily describes the conversion and exchange between various energy forms, ensuring that the simulation process accurately reflects energy usage.

[0082] Step 130: Based on the improved NSGA-II algorithm, solve the energy system model to obtain multiple initial optimal solutions.

[0083] Specifically, a multi-objective optimization based on the improved NSGA-II algorithm and the adaptive random walk (RWDE) mechanism is performed. In this step, the NSGA-II algorithm effectively balances multiple objectives through non-dominated sorting and crowding distance mechanisms, generating multiple Pareto optimal solutions. The improved NSGA-II algorithm introduces the RWDE mechanism to enhance global search capabilities and avoid getting trapped in local optima. The RWDE mechanism increases the diversity of the solution space by locally perturbing the current optimal solution, improving the algorithm's search efficiency and ensuring the globality and reliability of the optimization results.

[0084] Step 140: Based on the TOPSIS algorithm, sort all the initial optimal solutions to obtain the energy configuration scheme for the paper industry.

[0085] Specifically, the multiple Pareto initial optimal solutions (i.e., the best set of plant energy configuration schemes) generated during the optimization process will enter the TOPSIS scheme evaluation stage. In this stage, the decision-making method assigns weights to each objective, comprehensively considering the priorities of multiple objectives such as economy, environment, and energy efficiency. Using the TOPSIS method, the system calculates the distance of each scheme to the ideal solution and the negative ideal solution, thereby ranking all solutions. The TOPSIS method can effectively evaluate the merits of each solution, helping decision-makers select the optimal scheme. Ultimately, through TOPSIS evaluation, the system can provide decision-makers with energy configuration schemes for the paper industry.

[0086] In this embodiment, real-world operating parameters are collected to obtain the system operating parameters of the paper industry. An energy system model is constructed, including energy-related, economic, and environmental objective functions, truly realizing green manufacturing and sustainable development. An improved NSGA-II algorithm is introduced to solve the energy system model, obtaining multiple initial optimal solutions. This is more suitable for the decision-making characteristics of the paper industry, with a wide solution set coverage, facilitating subsequent decision selection. The TOPSIS algorithm is used to sort the optimal solutions, automatically identifying the optimal energy allocation scheme for the paper industry, improving energy allocation efficiency while ensuring accuracy.

[0087] Optionally, solving the energy system model yields multiple initial optimal solutions, including:

[0088] An initial population is obtained based on the energy system model, wherein the initial population includes multiple individuals;

[0089] The initial population is screened to obtain the initial parent population;

[0090] The initial parent population is subjected to selection, crossover, and mutation operations to obtain a new offspring population;

[0091] Based on the adaptive random walk mechanism, a new parent population is obtained from the initial parent population and the new offspring population. The process of performing selection, crossover, and mutation operations on the initial parent population to obtain a new offspring population is then repeated until a preset condition is met, resulting in multiple initial optimal solutions.

[0092] Specifically, an initial population is obtained based on the energy system model, comprising multiple individuals. Each individual contains multiple decision variables (i.e., coal consumption, biogas usage, etc.). For a multi-objective optimization problem, N individuals are first randomly generated. Each individual (i.e., each objective function represents an energy configuration scheme for the plant) consists of D decision variables, each ranging between a specified minimum and maximum value. The decision variables in the model include boiler steam supply, purchased electricity load, and the number of biogas generator units. The number of randomly generated individuals represents the number of objective functions (3E objectives, i.e., the plant's energy operation schemes).

[0093] In this optional embodiment, an improved multi-objective evolutionary algorithm framework incorporating an adaptive random walk mechanism is provided for solving the multi-objective optimization problem of an energy system model in the paper industry. This method introduces a dynamic search strategy on top of the standard evolutionary algorithm, significantly improving optimization performance.

[0094] Optionally, the step of performing selection, crossover, and mutation operations on the initial parent population to obtain a new offspring population includes:

[0095] The selected parent population is obtained by performing non-dominated quicksort and crowding distance calculation on the initial parent population.

[0096] The congestion distance calculation includes:

[0097] ,

[0098] in, For individual i, the crowding distance The maximum value of the k-th target dimension. The minimum value of the k-th target dimension. Let be the function value of individual i in the k-th target dimension. Let i be the function value of individual i-1 in the k-th target dimension. Let be the function value of individual i+1 in the k-th target dimension, and M be the total number of individuals;

[0099] The selected parent population is subjected to crossover and mutation operations to obtain the new offspring population.

[0100] Specifically, the population is first initialized, and each individual is set... Where D is the number of decision variables (e.g., boiler steam output, purchased electricity, etc.). The range of values ​​for each decision variable is:

[0101] ,

[0102] in, To randomly generate each decision variable, To minimize the decision variable, The maximum value of the decision variable is:

[0103] ,

[0104] in, For the individual minimum value, The maximum value is denoted by , and rand is a random number within the interval [0, 1].

[0105] Input the decision variables in the model (boiler steam supply, purchased electricity load, number of biogas generator units). Randomly generate N individuals (i.e., each objective function represents an energy configuration scheme for the factory), with each individual representing one energy configuration scheme for the factory. Output the initial population, where each individual takes values ​​between the upper and lower limits of the variables.

[0106] Secondly, non-dominated sorting is performed. The purpose of non-dominated sorting is to rank each individual in the initial population, i.e., each objective function (3E), to determine its position in the Pareto front. The core of this step is to determine the dominance relationship of each individual. Among them, individuals with dominance relationships... Dominant Individual If and only if:

[0107] ,

[0108] in, Individual The k-th objective function value. In determining dominance relationships, the dominance number for each individual is first calculated. , representing an individual The number of dominated individuals, while also calculating the number of individuals. The set of individuals under control The output of a non-dominated sort is a series of rank fronts F1, F2, ..., which are the sets of initial optimal solutions in the Pareto front, F2 is the set of suboptimal solutions, and so on.

[0109] In the selection step, a tournament selection method is used to select parent individuals from the current population. Tournament selection selects the individual with a stronger dominance relationship by comparing two randomly selected individuals. Two individuals are randomly selected from the population, and their non-dominance levels are compared. If the two individuals have different non-dominance levels, the individual with the lower level (i.e., the individual with a stronger dominance relationship) is selected; if the levels are the same, selection is made using crowding distance, with the individual having a larger crowding distance being selected. For a given frontier set, the crowding distance for each individual is calculated in each target dimension. Crowding distance measures the "crowding degree" of an individual in the target space, i.e., its distance from other individuals. The calculation of crowding distance includes:

[0110] ,

[0111] in, For individual i, the crowding distance The maximum value of the k-th target dimension. The minimum value of the k-th target dimension. Let be the function value of individual i in the k-th target dimension. Let i be the function value of individual i-1 in the k-th target dimension. Let be the function value of individual i+1 in the k-th target dimension, and M be the total number of individuals.

[0112] The aim is to recombine and perturb the energy allocation of the current parent solution through simulated binary crossover (SBX) and polynomial mutation operations to generate a new generation of individuals. The decision variables of each individual include boiler steam supply, purchased electricity load, and the number of biogas generator units in operation. Each individual represents a specific energy dispatch scheme for a paper mill. The crossover operation recombines the continuous variables (such as boiler and grid load) using the SBX method. For example, crossing the two parent solutions "boiler steam supply 280 t / h" and "300 t / h" generates a offspring with 290 t / h. The mutation operation uses polynomial perturbation to slightly perturb the individual variables. For example, changing the purchased electricity load from 125,000 kWh / h to 118,000 kWh / h expands the search space. While respecting the upper and lower limits of industrial parameters, this continuously generates more diverse energy allocation candidate schemes, effectively enhancing the breadth of the multi-objective search. The simulated binary crossover (SBX) method is used to cross continuous variables.

[0113] ,

[0114] ,

[0115] in, The cross-mixing factor controls the degree of cross-mixing. and It is the parent generation individual. and This is the result after crossover.

[0116] Multinomial mutation is used to perturb the decision variables, thereby updating the individual's decision variables:

[0117] ,

[0118] in, To update the individual's decision variables, This is the scaling factor calculated based on the probability of variation and the range of decision variables.

[0119] In this optional embodiment, a closed-loop iterative mechanism is constructed to achieve efficient and high-quality multi-objective optimization solutions for complex multi-energy complementary energy systems in the papermaking industry. Compared to traditional NSGA-II or other fixed-strategy evolutionary algorithms, it significantly improves the quality of the initial population and enhances the representativeness and diversity of the convergence starting point. By selecting the initial parent population from the initial population, the problem of too many inferior individuals that may be caused by traditional random initialization is avoided, significantly accelerating the convergence speed.

[0120] Optionally, obtaining a new parent population based on the initial parent population and the new offspring population includes:

[0121] Perturbation analysis is performed on each individual of the new offspring population to obtain the processed offspring population;

[0122] The disturbance analysis includes:

[0123] ,

[0124] in, This represents the position of the i-th individual in the treated offspring population. Let i be the position of the i-th individual in the new offspring population. Step size factor Let i be the historical direction of the i-th individual in the new offspring population. The disturbance is random, and N is the total population size.

[0125] The initial parent population and the processed offspring population are combined to obtain the new parent population.

[0126] Specifically, the RWDE mechanism updates the solution by adding a certain degree of random perturbation based on the historical performance of previous generations of excellent solutions in dimensions such as "lowest operating cost" or "lowest carbon emissions." For example, if a solution shows a convergence trend in the "cost-optimal" direction, the algorithm can further perturb the number of biogas generators or the proportion of purchased steam to explore its optimization potential in the "carbon emissions" dimension. For each individual, the new position is calculated based on the direction of historical solutions and random perturbation. Furthermore, the perturbation analysis includes:

[0127] ,

[0128] in, This represents the position of the i-th individual in the treated offspring population. Let i be the position of the i-th individual in the new offspring population. Step size factor Let i be the historical direction of the i-th individual in the new offspring population. The disturbance is random, and N is the total population size.

[0129] The objective assessment utilizes an energy system model to calculate the objective function results. The objective function value for each individual needs to be evaluated; here, the system model is used to calculate the objective values ​​for each individual, such as total cost and carbon emissions. This is used to assess the performance of newly generated individuals on the three main objective functions: annual total cost, energy consumption per unit of paper, and annual carbon emissions, and to provide a basis for non-dominated ranking. The evaluation of all individuals is based on a mathematical model of the paper mill's energy system, with inputs including variables such as boiler output, grid electricity purchases, and biogas operation, and outputs being quantitative indicators.

[0130] Energy consumption per unit of paper (kg standard coal / t paper): This is derived by converting different energy consumption amounts into standard coal equivalent based on the lower heating value.

[0131] Annual operating costs (RMB 100 million): Taking into account the procurement costs of coal, electricity, and steam, operation and maintenance expenses, and carbon emission trading fees;

[0132] Annual carbon emissions (10,000 tons) ): Calculated using various energy carbon emission factor methods.

[0133] By evaluating the objective function, the "energy configuration scheme" was quantified into "three performance indicators", providing a unified evaluation basis for subsequent ranking and selection.

[0134] The parent and offspring populations are merged, and a non-dominated ranking is performed based on the evaluation results of the three objectives to ensure that the optimal solution set is retained in each generation. The Pareto front (F1) output by the ranking includes the optimal solution that is not completely dominated among cost, emissions, and energy efficiency, covering typical strategies such as "lowest cost operation", "lowest energy consumption operation", and "comprehensive equilibrium operation". An elite strategy is used to replace the original population, prioritizing the retention of configurations with higher feasibility and economic efficiency in the actual operation of the paper mill, such as the typical energy-saving scheme of "300t / h boiler steam + 60,000kWh / h purchased electricity + 2 biogas digesters". This effectively prevents excellent operating condition solutions from being eliminated during the evolution process and ensures that the solution set quality is continuously optimized during the algorithm's convergence process. The termination condition is used to determine whether to end the process. If the termination condition is met, the final optimal solution is output. The optimization process terminates when the preset maximum number of iterations is reached or the Pareto front converges between consecutive generations. In actual operation in the paper industry, this output set provides enterprises with a database of operating conditions covering different strategic objectives, enabling the formulation of flexible energy dispatch strategies.

[0135] In this optional embodiment, to overcome the premature convergence and local optima dilemmas commonly encountered in multi-objective optimization, this invention introduces an adaptive random walk (RWDE) mechanism based on the traditional NSGA-II. This mechanism perturbs the current best solution to further explore the local solution domain. In the context of an energy system, this mechanism applies a small perturbation to the boiler-biogas-grid combination scheme represented by the current best solution, enabling continuous exploration of the surrounding neighborhood. The RWDE mechanism, through historical guidance and random perturbation, improves the quality and distribution balance of solutions, laying the foundation for the subsequent formation of a continuous and complete Pareto front.

[0136] Optionally, the step of sorting all the initial optimal solutions to obtain the energy allocation scheme for the paper industry includes:

[0137] The distances to the positive and negative ideal solutions are obtained based on all the initial optimal solutions.

[0138] The distance to the positive ideal solution includes:

[0139] ,

[0140] in, Let the distance be the positive ideal solution. Let be the normalized value of the i-th scheme on the k-th metric. Let M be the positive ideal solution for the k-th indicator, and M be the number of evaluation indicators.

[0141] The negative ideal solution distance includes:

[0142] ,

[0143] in, The distance to the negative ideal solution. The negative ideal solution for the k-th index;

[0144] A similarity score is obtained by performing a similarity score using the positive ideal solution distance and the negative ideal solution distance;

[0145] The similarity score includes:

[0146] ,

[0147] in, Score the similarity.

[0148] The initial optimal solution is sorted using the corresponding similarity score to obtain the energy allocation scheme for the paper industry.

[0149] Specifically, in multi-objective optimization, the decision matrix needs to be normalized because the objective functions have different dimensions. The purpose of normalization is to unify the values ​​of different objectives to the same order of magnitude, facilitating subsequent comparisons and calculations. In TOPSIS, the relative importance (i.e., weight) of each objective function reflects the differences in importance between different objectives.

[0150] Suppose there are M objective functions, and the weights, determined by expert evaluation or based on the decision-maker's knowledge, reflect the relative importance of each objective. The weights can be expressed as:

[0151] ,

[0152] To ensure that the sum of the weights of all objectives is 1, the weights need to be normalized:

[0153] ,

[0154] in, It is the weight of the k-th objective, and satisfies... Calculate the weighted normalized decision matrix: By multiplying the normalized decision matrix by the weights, we obtain the weighted normalized matrix for each individual, reflecting each individual's weighted performance on each objective.

[0155] ,

[0156] in, It is the weighted normalized value of the i-th individual on the k-th objective. It is the normalized value. These are the weights of the objective function k. The distance between the positive and negative ideal solutions for each solution is determined and calculated: In the TOPSIS method, the positive and negative ideal solutions are benchmarks used to measure the performance of individuals. The positive ideal solution is the best solution among all objectives, while the negative ideal solution is the worst solution among all objectives. The distance between the positive ideal solutions includes:

[0157] ,

[0158] in, Let be the distance to the positive ideal solution, that is, the distance between the i-th individual and the positive ideal solution. Let be the normalized value of the i-th scheme on the k-th metric. Let M be the positive ideal solution for the k-th indicator, and M be the number of evaluation indicators.

[0159] The negative ideal solution distance includes:

[0160] ,

[0161] in, Let be the distance to the negative ideal solution, that is, the distance between the i-th individual and the negative ideal solution. The negative ideal solution is the k-th indicator. The TOPSIS similarity score is calculated based on the distances of each individual to both the ideal and negative ideal solutions. The TOPSIS score is obtained by calculating the ratio of the distance to the negative ideal solution to the distance to the ideal solution. The similarity score includes:

[0162] ,

[0163] in, For the similarity score, the larger the score, the better. This indicates that the individual is closer to the ideal solution and smaller. This indicates that the individual is far from the ideal solution. Based on the TOPSIS score, all individuals are ranked, and the individual with the highest TOPSIS score is selected as the optimal solution. The TOPSIS method helps decision-makers make optimal choices in this way, especially when there are conflicting objectives.

[0164] ,

[0165] in, For the i-th individual, the non-dominant rank is... The ranking function assigns a ranking to individuals, with higher-ranked solutions considered superior. Based on the TOPSIS evaluation results, the system outputs the optimal solution. This optimal solution includes specific values ​​for key optimization variables, such as boiler steam supply, purchased electricity load, and the number of biogas generator units, for decision-makers' reference. This optimal solution provides theoretical support for practical applications, effectively improving the economic efficiency of energy systems, reducing carbon emissions, and increasing energy utilization efficiency.

[0166] In this optional embodiment, the multiple Pareto optimal solutions (i.e., the best set of plant energy configuration schemes) generated during the optimization process will enter the TOPSIS scheme evaluation stage. In this stage, weights are assigned to each objective, comprehensively considering the priorities of multiple objectives such as economy, environment, and energy efficiency. Using the TOPSIS method, the system calculates the distance of each scheme to the ideal solution and the negative ideal solution, thereby ranking all solutions. The TOPSIS method can effectively evaluate the merits of each solution, helping decision-makers select the optimal scheme. Finally, through TOPSIS evaluation, the system can provide decision-makers with a preferred scheme that comprehensively considers the balance of multiple objectives.

[0167] Optionally, the step of comprehensively modeling the energy system based on the operating parameters of the paper industry system to obtain the energy system model includes:

[0168] Based on the system operating parameters of the paper industry, a comprehensive model is performed to obtain the energy objective function, which is used to represent the amount of standard coal consumed in papermaking.

[0169] The energy efficiency objective function includes:

[0170] ,

[0171] in, The term "papermaking standard coal consumption" refers to the amount of standard coal consumed per unit of paper. To sum the data for all energy types, Let L be the energy consumption at time t, and L be the quantity of energy types. As the lower heating value of energy, The lower calorific value of standard coal. Annual paper production;

[0172] Based on the system operating parameters of the paper industry, a comprehensive model is performed to obtain the economic objective function, wherein the economic objective function is used to represent the total annual operating cost;

[0173] The economic objective function includes:

[0174] ,

[0175] in, The total annual operating cost, The cost of purchasing energy at time t. The operation and maintenance cost of energy at time t. The carbon trading cost of energy at time t;

[0176] Based on the system operating parameters of the papermaking industry, a comprehensive model is performed to obtain the environmental objective function, which is used to represent the total annual carbon emissions.

[0177] The environmental objective function includes:

[0178] ,

[0179] in, The total annual carbon emissions are [the stated amount]. Carbon emission factors for energy.

[0180] Specifically, the energy performance target (energy consumption per unit of paper (kg standard coal / t of paper)): Energy consumption per unit of paper is a key indicator for measuring the energy efficiency of a paper mill, widely used to evaluate the energy utilization efficiency of a paper mill during production. It is typically expressed as the amount of standard coal consumed per ton of paper produced (unit: kg standard coal / ton of paper). This indicator converts the consumption of different energy forms (such as coal, biogas, electricity, steam, etc.) into standard coal equivalents, thus providing a unified standard for comparison and evaluation of the consumption of various energy sources. The energy performance objective function includes:

[0181] ,

[0182] in, The standard coal consumption for papermaking is used to express the amount of standard coal consumed per unit of paper (unit: kg standard coal / ton of paper). To sum the data for all energy types, such as coal, biogas, and electricity, This represents the consumption of a certain energy source at time t. For example, for coal, its hourly consumption (tons), etc., where L is the quantity of the energy type. The lower heating value (unit: kJ / unit of energy) is given for each energy source, and the specific value varies depending on the type of energy. The lower heating value of standard coal (unit: kJ / kg) serves as a conversion standard, used to unify the conversion of all energy forms into standard coal units. This refers to the annual paper production (in tons per year), used to normalize total energy consumption calculations. This value can be set based on the specific factory's annual paper production.

[0183] The primary objective of the economic objective is to minimize the system's total annual operating cost, thereby improving the energy system's economic efficiency. To this end, all relevant costs incurred during system operation are calculated, including but not limited to equipment maintenance costs, energy procurement costs, and carbon emissions trading costs. The economic objective function includes:

[0184] ,

[0185] in, Let $\frac{ ... Let be the purchase cost of each energy source at time t, such as the purchase cost of coal, biogas, electricity, etc. The operational and maintenance costs for each energy source at time t, including equipment maintenance, energy conversion, and other related expenses. The carbon trading cost for each type of energy at time t, i.e. the carbon trading fee paid when carbon emissions exceed the allowance.

[0186] The environmental objective function of this invention aims to minimize the total carbon emissions of the energy system, particularly carbon dioxide emissions. By optimizing the energy consumption structure and configuration of the energy system, greenhouse gas emissions are reduced, thereby promoting the green and low-carbon transformation of the energy system and complying with global requirements for addressing climate change and environmental protection. To achieve this goal, this invention employs the carbon emission factor method, which accurately calculates the carbon emissions generated by each energy form based on the relationship between its consumption and its carbon emission factor. Through this method, the system can accurately quantify the environmental impact of energy consumption and ultimately minimize carbon emissions. The environmental objective function includes:

[0187] ,

[0188] in, The system's total annual carbon emissions (unit: tons) ), Carbon emission factor for each energy type (unit: kg) / unit energy), which represents the amount of carbon dioxide emissions generated per unit of energy consumption.

[0189] In this optional embodiment, the three objective functions correspond to three types of ultimately acquired data indicators, forming a direct basis for optimization evaluation: the energy objective function calculates the energy consumption per unit of paper by converting it to standard coal equivalent for different energy consumption levels; the economic objective function calculates the total annual operating cost by comprehensively considering costs such as energy procurement, equipment operation and maintenance, and carbon emission trading; and the environmental objective function calculates the carbon dioxide emissions generated by energy consumption based on the carbon emission factor method, obtaining the total annual carbon emissions. These three data results serve as evaluation indicators during the optimization algorithm iteration process and also as the final quantitative basis for providing decision support to enterprises.

[0190] Optionally, before performing comprehensive modeling based on the operating parameters of the paper industry system to obtain the energy system model, the method further includes:

[0191] The steam supply and demand balance constraints, power load constraints, and equipment operation constraints are obtained from the system operating parameters of the paper industry.

[0192] Specifically, the constraints include steam supply and demand balance conditions (e.g., steam output greater than or equal to 300 t / h), power load constraints (e.g., purchased power not less than 125,000 kWh per hour), and equipment operation constraints, namely the upper and lower limits of equipment operation. By combining these constraints with the objective function, it is ensured that the optimization process is carried out within the feasible solution space, and that the final optimized solution meets the constraints required in actual operation.

[0193] In some more specific embodiments, a paper mill in Dongguan with an annual output of 1.45 million tons is used as the research object. A multi-energy complementary energy system model is constructed based on the coordinated supply of multiple energy sources, including coal-fired boilers, biogas generator sets, purchased electricity, and purchased steam. The system modeling phase considers in detail the actual steam and electricity demands during the enterprise's production process and integrates key parameters such as the operating characteristics, economic indicators, and carbon emission factors of each energy device. Equipment parameters are provided by the enterprise or calculated based on its actual operating conditions. The coal-fired boiler has an operating efficiency of 94%, with some sludge co-firing; the effect of this co-firing is assessed using empirical formulas to reduce boiler efficiency. The unit lower heating value of coal is 18819 kJ / kg, the coal price is 846 yuan / t, and the carbon emission coefficient is 2.493 kg. / kg standard coal; the rated power generation capacity of a single biogas generator set is approximately 7000 kWh / h, with a maximum installed capacity of 3 units, a power generation efficiency of 42.7%, and an internal loss of 4%; the carbon emission coefficient of purchased electricity is 0.455 kg / kWh, electricity price is 0.75 yuan / kWh; the enthalpy of heat of purchased steam is 2847 kJ / kg, the price is 185.8 yuan / t, and the carbon emission coefficient is equivalent to 0.2 t. / t steam.

[0194] Constraints include the maximum allowable values ​​of the equipment, steam supply constraints (the actual steam output of the boiler must be ≥300t / h), and power load constraints (purchased electricity per hour must be no less than 125,000 kW). In the optimization analysis phase, three key objective functions were clearly defined: minimizing the standard coal consumption per unit of paper (kg standard coal / t paper); minimizing the annual total carbon emissions (ten thousand tons); and minimizing the annual operating costs (hundred million yuan). These objective functions are directly based on energy consumption, energy prices, carbon emission coefficients, and the actual production conditions of the enterprise. The optimization process adopted an improved RWDE-NSGA-II multi-objective evolutionary algorithm, using non-dominated sorting and adaptive random walk mechanisms to improve search efficiency and accuracy, effectively avoiding local convergence problems. Simultaneously, to further achieve comprehensive decision-making among multiple objectives, the TOPSIS comprehensive evaluation method was introduced. By calculating the distance between each solution and the ideal solution and the negative ideal solution, the optimal operating conditions were evaluated and ranked.

[0195] Table 1

[0196]

[0197] As shown in Table 1, three representative weights were set for the actual decision-making scenarios of enterprises: (1) economy-oriented (energy consumption-emission-cost = 0.2-0.2-0.5); (2) economic and environmental protection-oriented (0.25-0.25-0.5); (3) energy efficiency and environmental protection-oriented (0.3-0.3-0.4). The optimization results were compared with the actual operating conditions of the enterprise (boiler steam 260 t / h, purchased steam 40 t / h, self-generated electricity 38,000 kWh / h, purchased electricity 87,000 kWh / h). The optimal solutions under different weights showed significant differences in energy consumption, carbon emissions, and cost, reflecting the effectiveness of the RWDE-NSGA-II algorithm and the sensitive response capability of the TOPSIS method to decision preferences. For example, the economic weighting optimization scheme significantly reduced annual costs by 22.8% to RMB 790 million, and reduced the demand for purchased electricity to 14,541 kWh / h; the energy efficiency and environmental protection orientation scheme significantly reduced energy consumption and carbon emissions per unit of product, with annual carbon emissions reduced to 1.0771 million tons and energy consumption per unit of paper at 259.56 kg of standard coal / t of paper, demonstrating the best energy conservation and emission reduction effect.

[0198] like Figure 2 As shown in the figure, an energy configuration scheme generation device for a multi-energy system provided in an embodiment of the present invention includes:

[0199] The paper industry system operation parameter acquisition module 10 is used to acquire the paper industry system operation parameters.

[0200] The energy system model acquisition module 20 is used to perform comprehensive modeling based on the operating parameters of the paper industry system to obtain an energy system model, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function;

[0201] The initial optimal solution acquisition module 30 is used to solve the energy system model based on the improved NSGA-II algorithm to obtain multiple initial optimal solutions;

[0202] The energy configuration scheme acquisition module 40 for the paper industry is used to sort all the initial optimal solutions based on the TOPSIS algorithm to obtain the energy configuration scheme for the paper industry.

[0203] The energy configuration scheme generation device for multi-energy systems in this embodiment is used to implement the energy configuration scheme generation method for multi-energy systems as described above. Its advantages over the prior art are the same as the advantages of the energy configuration scheme generation method for multi-energy systems over the prior art, and will not be repeated here.

[0204] like Figure 3 As shown, an electronic device 300 provided in this embodiment of the invention includes a memory 310 and a processor 320; the memory 310 is used to store a computer program; the processor 320 is used to implement the energy configuration scheme generation method of the multi-energy system as described above when the computer program is executed.

[0205] Alternatively, an electronic device 300 includes a memory 310 and a processor 320 coupled to the memory 310; the memory 310 is configured to store a computer program; and the processor 320 is configured to perform the following operations when the computer program is executed:

[0206] Obtain system operating parameters for the paper industry;

[0207] A comprehensive model is obtained by performing a comprehensive modeling based on the operating parameters of the paper industry system, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function;

[0208] Based on the improved NSGA-II algorithm, multiple initial optimal solutions are obtained by solving the energy system model.

[0209] Based on the TOPSIS algorithm, all the initial optimal solutions are sorted to obtain the energy configuration scheme for the paper industry.

[0210] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the energy configuration scheme generation method for a multi-energy system as described above.

[0211] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations:

[0212] Obtain system operating parameters for the paper industry;

[0213] A comprehensive model is obtained by performing a comprehensive modeling based on the operating parameters of the paper industry system, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function;

[0214] Based on the improved NSGA-II algorithm, multiple initial optimal solutions are obtained by solving the energy system model.

[0215] Based on the TOPSIS algorithm, all the initial optimal solutions are sorted to obtain the energy configuration scheme for the paper industry.

[0216] The present invention will now be described an electronic device 300 that can serve as a server or client of the present invention, which is an example of a hardware device that can be applied to various aspects of the present invention. Electronic device 300 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0217] Electronic device 300 includes a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or a computer program loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0218] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, 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 the embodiments of the present invention according to actual needs. Furthermore, the functional units in the various embodiments of the present invention 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 units can be implemented in hardware or as software functional units.

[0219] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for generating an energy configuration scheme for a multi-energy system, characterized in that, include: Obtain system operating parameters for the paper industry; A comprehensive model is obtained by performing a comprehensive modeling based on the operating parameters of the paper industry system, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function; Based on the improved NSGA-II algorithm, the energy system model is solved to obtain multiple initial optimal solutions, including: An initial population is obtained based on the energy system model, wherein the initial population includes multiple individuals; The initial population is screened to obtain the initial parent population; The initial parent population is subjected to selection, crossover, and mutation operations to obtain a new offspring population; Based on the adaptive random walk mechanism, a new parent population is obtained according to the initial parent population and the new offspring population. The process of performing selection, crossover and mutation operations on the initial parent population to obtain a new offspring population is repeated until the preset conditions are met, resulting in multiple initial optimal solutions. The step of obtaining a new parent population based on the initial parent population and the new offspring population includes: Perturbation analysis is performed on each individual of the new offspring population to obtain the processed offspring population; The disturbance analysis includes: ， in, Let i be the position of individual i in the treated offspring population. Let i be the position of individual i in the new offspring population. Step size factor The historical direction of individual i in the new offspring population. The disturbance is random, and N is the total population size. The initial parent population and the processed offspring population are combined to obtain the new parent population; Based on the TOPSIS algorithm, all the initial optimal solutions are sorted to obtain the energy configuration scheme for the paper industry.

2. The method for generating energy configuration schemes for a multi-energy system according to claim 1, characterized in that, The process of performing selection, crossover, and mutation operations on the initial parent population to obtain a new offspring population includes: The selected parent population is obtained by performing non-dominated quicksort and crowding distance calculation on the initial parent population. The congestion distance calculation includes: ， in, For individual i, the crowding distance The maximum value of the k-th target dimension. Let be the minimum value of the k-th target dimension. Let be the function value of individual i in the k-th target dimension. Let i be the function value of individual i-1 in the k-th target dimension. Let be the function value of individual i+1 in the k-th target dimension, and M be the total number of individuals; The selected parent population is subjected to crossover and mutation operations to obtain the new offspring population.

3. The method for generating energy configuration schemes for a multi-energy system according to claim 1, characterized in that, The process of sorting all the initial optimal solutions to obtain the energy allocation scheme for the paper industry includes: The distances to the positive and negative ideal solutions are obtained based on all the initial optimal solutions. The distance to the positive ideal solution includes: ， in, Let the distance be the positive ideal solution. Normalized value For the positive ideal solution, The number of evaluation indicators; The negative ideal solution distance includes: ， in, The distance to the negative ideal solution. It is a negative ideal solution; A similarity score is obtained by performing a similarity score using the positive ideal solution distance and the negative ideal solution distance; The similarity score includes: ， in, Score the similarity. The initial optimal solution is sorted using the corresponding similarity score to obtain the energy allocation scheme for the paper industry.

4. The method for generating energy configuration schemes for a multi-energy system according to claim 1, characterized in that, The energy system model is obtained by comprehensively modeling the operating parameters of the paper industry system, including: Based on the system operating parameters of the paper industry, a comprehensive model is performed to obtain the energy objective function, which represents the amount of standard coal consumed in papermaking. The energy efficiency objective function includes: ， in, The term "papermaking standard coal consumption" refers to the amount of standard coal consumed per unit of paper. To sum the data for all energy types, Let L be the energy consumption at time t, and L be the quantity of energy types. As the lower heating value of energy, The lower calorific value of standard coal. Annual paper production; Based on the system operating parameters of the paper industry, a comprehensive model is performed to obtain the economic objective function, wherein the economic objective function is used to represent the total annual operating cost; The economic objective function includes: ， in, The total annual operating cost, The cost of purchasing energy at time t. The operation and maintenance cost of energy at time t. The carbon trading cost of energy at time t; Based on the system operating parameters of the papermaking industry, a comprehensive model is performed to obtain the environmental objective function, which is used to represent the total annual carbon emissions. The environmental objective function includes: ， in, The total annual carbon emissions are [the stated amount]. Carbon emission factors for energy.

5. The method for generating energy configuration schemes for a multi-energy system according to claim 1, characterized in that, Before obtaining the energy system model by comprehensively modeling based on the operating parameters of the paper industry system, the following steps are also included: The steam supply and demand balance constraints, power load constraints, and equipment operation constraints are obtained from the system operating parameters of the paper industry.

6. An energy configuration scheme generation device for a multi-energy system, characterized in that, include: The paper industry system operation parameter acquisition module is used to acquire the system operation parameters of the paper industry. The energy system model acquisition module is used to perform comprehensive modeling based on the operating parameters of the paper industry system to obtain an energy system model, wherein the energy system model includes an energy objective function, an economic objective function, and an environmental objective function; The initial optimal solution acquisition module is used to solve the energy system model based on the improved NSGA-II algorithm to obtain multiple initial optimal solutions, including: An initial population is obtained based on the energy system model, wherein the initial population includes multiple individuals; The initial population is screened to obtain the initial parent population; The initial parent population is subjected to selection, crossover, and mutation operations to obtain a new offspring population; Based on the adaptive random walk mechanism, a new parent population is obtained according to the initial parent population and the new offspring population. The process of performing selection, crossover and mutation operations on the initial parent population to obtain a new offspring population is repeated until the preset conditions are met, resulting in multiple initial optimal solutions. The step of obtaining a new parent population based on the initial parent population and the new offspring population includes: Perturbation analysis is performed on each individual of the new offspring population to obtain the processed offspring population; The disturbance analysis includes: ， in, Let i be the position of individual i in the treated offspring population. Let i be the position of individual i in the new offspring population. Step size factor The historical direction of individual i in the new offspring population. The disturbance is random, and N is the total population size. The initial parent population and the processed offspring population are combined to obtain the new parent population; The energy configuration scheme acquisition module for the paper industry is used to sort all the initial optimal solutions based on the TOPSIS algorithm to obtain the energy configuration scheme for the paper industry.

7. An electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to, when executing the computer program, implement the method for generating energy configuration schemes for a multi-energy system as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method for generating energy configuration schemes for a multi-energy system as described in any one of claims 1 to 5.

Images