A resource optimization configuration method, system, device and medium based on a non-dominated sorting genetic algorithm

Abstract

This invention discloses a resource optimization allocation method, system, device, and medium based on a non-dominated sorting genetic algorithm, belonging to the field of power resource allocation. The method comprises: resource optimization allocation based on an improved genetic algorithm, obtaining resource characteristic parameters of source-grid-load-storage resources and basic power system operation data; constructing an optimization allocation model based on the resource characteristic parameters and the basic power system operation data; performing fast non-dominated sorting and crowding calculation on the initial population using a non-dominated sorting genetic algorithm based on the optimization allocation model, and iteratively calculating using an adaptive crossover and mutation operator and an elite retention strategy to obtain an optimal solution set containing resource allocation schemes; and performing resource optimization allocation on the source-grid-load-storage resources based on the optimal solution set. Therefore, by implementing this invention, using an improved genetic algorithm for multi-objective optimization, efficient and balanced decision-making on resource allocation is achieved.

Description

Technical Field

[0001] This invention relates to the field of power resource allocation, and in particular to a resource optimization allocation method, system, device and medium based on a non-dominated sorting genetic algorithm. Background Technology

[0002] The integrated source-grid-load-storage system is the core carrier of energy transformation. Its configuration needs to balance multiple objectives such as new energy consumption, investment costs, and power supply reliability, and it faces the complex characteristics of distributed energy output fluctuations, load randomness, and high variable dimensionality.

[0003] Existing configuration algorithms often employ a weighted summation method to transform multi-objective problems into single-objective problems, followed by solution using traditional genetic algorithms. However, the weighting coefficients in the weighted summation method are highly subjective, making it difficult to objectively reflect the complex trade-offs between objectives. In high-dimensional scenarios, this can easily lead to convergence directions deviating from the global optimum. Some techniques use non-dominated sorting genetic algorithms, but when dealing with high-dimensional, multi-constraint optimization problems, their crowding calculation mechanism gradually becomes ineffective in the high-dimensional objective space, leading to a rapid decline in population diversity. The algorithm is prone to getting trapped in local optima, resulting in slow convergence and difficulty in adapting to the precise configuration requirements of real-world systems. Therefore, there is an urgent need to design optimization algorithms adapted to high-dimensional, multi-constraint scenarios to improve solution accuracy and efficiency, and ensure the optimal synergistic effect of system economic, environmental, and safety objectives. Summary of the Invention

[0004] This invention provides a resource optimization allocation method, system, device, and medium based on a non-dominated sorting genetic algorithm. By implementing this invention, the problem of local optima easily arising in multi-objective optimization of source-grid-load-storage systems under high-dimensional and multi-constraint environments can be solved by using a non-dominated sorting genetic algorithm, thereby achieving efficient and balanced decision-making for resource allocation.

[0005] This invention provides a resource optimization allocation method based on a non-dominated sorting genetic algorithm, comprising: Based on the equipment load parameters, energy revenue data, and preset cost data of the source-grid-load-storage resources, an optimal configuration model is constructed. The optimal configuration model takes the maximization of comprehensive benefits as the objective function and power balance constraints, resource and technology constraints, grid security constraints, and investment constraints as constraints. According to the optimization configuration model, the initial population is quickly sorted and crowded by a non-dominated sorting genetic algorithm, and an adaptive crossover mutation operator and an elite retention strategy are used for iterative calculation to obtain the optimal solution set containing resource configuration schemes. Then, resource optimization configuration is performed based on the optimal solution set.

[0006] This invention constructs a resource optimization model for source-grid-load-storage, encompassing comprehensive power balance constraints, resource and technology constraints, grid security constraints, and investment constraints. The objective function transforms multiple objectives into a single-objective optimization problem, with the core objective of maximizing the overall benefit of the virtual power plant while considering technical feasibility, economic rationality, and environmental friendliness. Based on a non-dominated sorting genetic algorithm, an adaptive crossover and mutation operator is used for dynamic adjustment to maintain the population's exploration breadth in the high-dimensional objective space. An elite retention strategy is employed to select high-quality individuals, effectively compensating for the insufficient distinguishing ability of crowding distance in high-dimensional spaces. Compared to existing non-dominated sorting genetic algorithms, which are prone to failure in crowding calculations under high-dimensional multi-constraint environments and suffer from decreased population diversity and local optima, this invention enhances the algorithm's global search capability and convergence performance in complex solution spaces. It effectively handles trade-offs between multiple objectives, avoids getting trapped in local optima, and thus improves solution efficiency and accuracy. Furthermore, resource optimization is performed based on the optimal solution set, effectively balancing and optimizing the resource allocation of source-grid-load-storage while ensuring that constraints are met, achieving efficient and balanced decision-making.

[0007] Furthermore, based on the aforementioned optimized configuration model, a fast non-dominated sorting and crowding calculation are performed on the initial population using a non-dominated sorting genetic algorithm, specifically as follows: An initial population is generated using real-number encoding; each individual in the initial population corresponds to a resource allocation scheme. Based on the objective function of the optimization configuration model, the fitness of the initial population is calculated and fast non-dominated sorting is performed to obtain the fitness value and non-dominated sorting level of the initial population. Based on the non-dominated sorting levels, the fitness values ​​of non-dominated individuals at each level of the initial population are ranked, and the crowding value of each level's non-dominated individuals is calculated. This initial population is generated using real-number encoding, with each individual directly corresponding to a resource allocation scheme. The encoding is intuitive and easy to operate, facilitating search and evaluation in a continuous variable space. By calculating the fitness of the initial population, the comprehensive benefits of each resource allocation scheme can be quickly and directly quantified based on the objective function of the optimal allocation model, providing an objective basis for comparing the merits of individuals. Implementing rapid non-dominated sorting efficiently identifies and classifies dominant individuals in the population, clarifying the quality distribution of solutions at different levels, thereby guiding the search process towards a better direction and improving the directionality of the optimization process. By calculating the crowding value of each level's non-dominated individuals, the distribution density of solutions in the target space can be effectively measured, prioritizing the retention of individuals in sparsely distributed regions. This proactively maintains population diversity during iteration, avoids premature convergence, and ensures that the final optimal solution set broadly covers the trade-off regions between different objectives.

[0008] Furthermore, an adaptive crossover and mutation operator and an elite retention strategy are used for iterative calculations to obtain the optimal solution set containing resource allocation schemes, specifically: Based on the objective function of the optimization configuration model, the initial population is subjected to iterative crossover and mutation calculations using an adaptive crossover and mutation operator. The initial population is then screened and retained using an elite retention strategy to select high-quality and sub-high-quality individuals until the iteration termination condition is met, thereby obtaining an optimal solution set containing resource allocation schemes.

[0009] By introducing an adaptive crossover and mutation operator combined with an elite retention strategy, the algorithm significantly improves its convergence speed, solution stability, and the quality of the final solution set when dealing with multi-objective and multi-constraint optimization problems. This reliably generates the optimal solution set that reflects the trade-offs between different objectives, providing a comprehensive and high-quality decision-making basis for subsequent scheme selection.

[0010] Furthermore, the adaptive crossover and mutation operator includes an adaptive crossover operator and an adaptive mutation operator; the initial population is subjected to iterative crossover and mutation calculations using the adaptive crossover and mutation operator, specifically as follows: The initial population is subjected to iterative crossover calculations using an adaptive crossover operator, and the initial population is subjected to iterative mutation calculations using an adaptive mutation operator. The adaptive crossover operator is used to simulate binary crossover for adjustment, adjusting the crossover step size according to the convergence state of the population, and adjusting the crossover probability according to the diversity coefficient of the population. The adaptive mutation operator is used to perform polynomial mutation, while adjusting the mutation amplitude according to the ratio of the number of iterations and adjusting the mutation probability according to the crowding value of individuals in the population.

[0011] This approach achieves an adaptive balance between global and local search capabilities by introducing an adaptive crossover operator that simulates binary crossover and dynamically adjusts the crossover step size based on the population's convergence status. When convergence is slow, the step size is increased to enhance global exploration capabilities; when convergence is near, the step size is decreased to strengthen local fine-tuning. Furthermore, the crossover probability is dynamically adjusted based on the population diversity coefficient. When diversity is insufficient, the crossover probability is increased to promote information exchange and increase population diversity; when diversity is sufficient, the probability is appropriately decreased to maintain optimal patterns, thus effectively maintaining the population's evolutionary vitality and search breadth. An adaptive mutation operator using polynomial mutation is introduced, causing the mutation amplitude to gradually decrease with increasing iterations, achieving a natural transition from extensive exploration in the early stages to fine-tuning in the later stages, improving convergence accuracy. Finally, the mutation probability is dynamically adjusted based on individual crowding levels, increasing the mutation probability for individuals with low crowding levels to promote exploration of sparse regions and optimize distribution uniformity.

[0012] Furthermore, the elite retention strategy includes an elite pool selection strategy and a candidate pool replenishment strategy; the selection and retention of high-quality and sub-high-quality individuals in the initial population through the elite retention strategy specifically involves: The elite pool screening strategy selects individuals from the highest non-dominant ranking individuals in each generation based on their crowding value for storage, in order to screen high-quality individuals in the population. By employing a candidate pool replenishment strategy, individuals with the second and third highest non-dominated ranking levels are weighted by their crowding and fitness values, and then selected as the next best individuals for storage based on these weights.

[0013] This two-tiered screening mechanism, consisting of an elite pool and a candidate pool, enables precise identification and hierarchical management of outstanding individuals. The elite pool selection process prioritizes top-ranked individuals from the highest non-dominated tier based on crowding levels, ensuring the retention of elite individuals with optimal overall performance and relatively sparse distribution in each generation. This guarantees the stable inheritance of core superior genes and maintains the overall quality of the population. The candidate pool replenishment process uses a weighted selection process combining crowding and fitness from the second-best non-dominated tier, absorbing individuals with development potential or located in sparse areas. This effectively enriches the genetic diversity of the population while retaining elites, avoiding population homogenization and premature convergence caused by over-selection. At the end of each generation iteration, by retaining most of the core individuals in the elite pool and introducing some of the best individuals from the candidate pool for updating, moderate flow and dynamic optimization of the elite population are achieved. This maintains the stability of the evolutionary process while injecting new superior genes into the population.

[0014] Furthermore, the resource characteristic parameters include the rated capacity of distributed energy, the ramp-up capability parameters of distributed energy, the capacity of the energy storage system, the charging and discharging power parameters of the energy storage system, the adjustment capacity of the adjustable load, and the rate parameters of the adjustable load; the system operation basic data includes new energy output forecast data, load demand data, electricity market price data, carbon trading price data, fossil energy consumption data, equipment investment unit price, and operation and maintenance cost unit price data. The objective function construction of the optimized configuration model includes: The renewable energy absorption rate is calculated based on the renewable energy output forecast data and the load demand data; the renewable energy absorption rate is used to quantify the actual renewable energy absorption and potential power generation. The comprehensive revenue is calculated based on the electricity market price data, the new energy output forecast data, the adjustable load regulation capacity, the adjustable load rate parameters, and the continuous regulation duration data; the comprehensive revenue includes on-grid electricity price revenue, ancillary service revenue, and demand response revenue. Based on the carbon trading price data and fossil energy consumption data, energy conservation and emission reduction benefits are calculated. The investment cost is calculated based on the unit price of the equipment investment and the resource characteristic parameters. The operating cost is calculated based on the unit price data of the operation and maintenance cost and the resource characteristic parameters; Based on the new energy absorption rate, the comprehensive benefits, the energy conservation and emission reduction benefits, the investment costs, and the operating costs, an objective function is constructed with the goal of maximizing comprehensive benefits.

[0015] This approach simplifies the problem structure by transforming a multi-objective optimization problem into a single-objective optimization problem focused on maximizing comprehensive benefits, facilitating model solving and result interpretation. It accurately quantifies the efficiency of new energy utilization through the new energy absorption rate, objectively reflecting the system's capacity to absorb distributed energy. By comprehensively incorporating grid-connected electricity price revenue, ancillary service revenue, and demand response revenue into the overall revenue, it systematically assesses the economic potential of virtual power plants. Furthermore, it scientifically measures the effects of fossil energy conservation and carbon emission reduction through energy conservation and emission reduction benefits, aligning with green and low-carbon development goals. Finally, by detailing the composition of investment and operating costs, it precisely controls the full-cycle costs of resource allocation, enhancing the financial feasibility of the solution.

[0016] Furthermore, the constraints of the optimized configuration model include power balance constraints, resource and technology constraints, grid security constraints, and investment constraints, specifically: Based on the capacity of the energy storage system, the charging and discharging power parameters of the energy storage system, the adjustment capacity of the adjustable load, and the rate parameters of the adjustable load, combined with the grid exchange power, a power balance constraint is constructed. Distributed energy constraints are constructed based on the rated capacity and ramping capability parameters of the distributed energy source; energy storage constraints are constructed based on the capacity and charging / discharging power parameters of the energy storage system; adjustable load constraints are constructed based on the adjustment capacity and rate parameters of the adjustable load, combined with continuous adjustment duration data limits; resource and technology constraints are obtained by combining the distributed energy constraints, the energy storage constraints, and the adjustable load constraints. Voltage constraints are constructed based on system node voltages and rated voltages; frequency constraints are constructed based on system operating frequencies and frequency limits; line transmission constraints are constructed based on system line transmission power and rated transmission power; and power grid security constraints are obtained by combining the voltage constraints, frequency constraints, and line transmission constraints. Investment constraints are established based on the initial total investment in distributed energy, energy storage, adjustable loads, and terminal equipment, as well as the project's preset total investment ceiling. Based on the power balance constraint, the resource technology constraint, the power grid security constraint, and the investment constraint, the constraints of the optimal configuration model are constructed.

[0017] By constructing a comprehensive constraint system encompassing power balance, resource technology, grid security, and investment constraints, the optimized configuration model can closely align with the actual physical system and engineering conditions, effectively ensuring the feasibility and reliability of the resulting solution. Power balance constraints ensure real-time power supply and demand equilibrium at any given time, maintaining operational stability. Resource technology constraints, by incorporating distributed energy output and ramp-up limits, energy storage state of charge and charging / discharging power limits, and the power and regulation characteristics of adjustable loads, accurately characterize the operational boundaries of various resources, preventing equipment overload or abnormal operation. Grid security constraints, by setting safe ranges for voltage, frequency, and line transmission power, ensure that the optimized system meets grid standards, preventing over-limit risks and improving grid connection security. Investment constraints, by limiting the total investment in equipment, incorporate economic feasibility into the model, preventing the solution from exceeding the budget.

[0018] Another embodiment of the present invention provides a resource optimization allocation system based on a non-dominated sorting genetic algorithm, including: a model building module and a resource allocation module; The model building module is used to acquire resource characteristic parameters of source-grid-load-storage resources and basic power system operation data; and to construct an optimization configuration model based on the resource characteristic parameters and the basic power system operation data; the optimization configuration model takes maximizing comprehensive benefits as the objective function and power balance constraints, resource technology constraints, grid security constraints, and investment constraints as constraints. The resource allocation module is used to perform iterative calculations using a non-dominated sorting genetic algorithm based on the optimized allocation model, combined with an adaptive crossover and mutation operator and an elite retention strategy, to obtain an optimal solution set containing resource allocation schemes; and to perform resource optimization allocation on the source-grid-load-storage resources based on the optimal solution set.

[0019] This invention constructs a resource optimization model for source-grid-load-storage, encompassing comprehensive power balance constraints, resource and technology constraints, grid security constraints, and investment constraints. By transforming multiple objectives into a single-objective optimization problem through an objective function, the core objective is to maximize the overall benefit of the virtual power plant, while also considering technical feasibility, economic rationality, and environmental friendliness. A non-dominated sorting genetic algorithm is used to solve the high-dimensional, multi-constraint optimization model, enhancing the algorithm's global search capability and convergence performance in complex solution spaces. This effectively handles the trade-offs between multiple objectives, avoiding getting trapped in local optima, thereby improving solution efficiency and accuracy. Furthermore, resource optimization is performed based on the optimal solution set, effectively balancing and optimizing the resource allocation of source-grid-load-storage while ensuring that constraints are met, achieving efficient and balanced decision-making.

[0020] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the resource optimization allocation method based on the non-dominated sorting genetic algorithm of the present invention.

[0021] Another embodiment of the present invention provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform steps of the resource optimization allocation method based on the non-dominated sorting genetic algorithm of the present invention. Attached Figure Description

[0022] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments 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 from these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating an embodiment of the resource optimization allocation method based on a non-dominated sorting genetic algorithm provided by the present invention. Figure 2 This is a schematic diagram of another embodiment of the resource optimization and allocation system based on the non-dominated sorting genetic algorithm provided by the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0026] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0029] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0030] See Figure 1 To address the problem of optimal allocation of power resources in existing technologies, an embodiment of the present invention provides a resource optimization allocation method based on a non-dominated sorting genetic algorithm, comprising steps S1 to S4, the specific steps of which are as follows: S1. Obtain resource characteristic parameters of power source, grid, load and storage resources and basic data on power system operation; S2. Based on the resource characteristic parameters and the power system operation data, construct an optimal configuration model; the optimal configuration model takes the maximization of comprehensive benefits as the objective function and power balance constraints, resource and technology constraints, power grid security constraints, and investment constraints as constraints. S3. Based on the optimization configuration model, the initial population is quickly sorted and crowding is calculated using a non-dominated sorting genetic algorithm, and an adaptive crossover mutation operator and an elite retention strategy are used for iterative calculation to obtain the optimal solution set containing resource allocation schemes. S4. Based on the optimal solution set, optimize the resource allocation of the source-grid-load-storage resources.

[0031] The resource optimization allocation method based on a non-dominated sorting genetic algorithm provided in this invention constructs a resource optimization allocation model for source-grid-load-storage resources that integrates power balance constraints, resource and technology constraints, grid security constraints, and investment constraints. The objective function transforms multiple objectives into a single-objective optimization problem, with the core objective of maximizing the overall benefits of the virtual power plant while considering technical feasibility, economic rationality, and environmental friendliness. The non-dominated sorting genetic algorithm is used to solve the high-dimensional, multi-constraint optimization allocation model, enhancing the algorithm's global search capability and convergence performance in complex solution spaces. This effectively handles the trade-offs between multiple objectives, avoiding getting trapped in local optima, thereby improving solution efficiency and accuracy. Finally, resource optimization allocation is performed based on the optimal solution set, effectively balancing and optimizing the resource allocation of source-grid-load-storage resources while ensuring that the constraints are met, achieving efficient and balanced decision-making.

[0032] In practical applications, this invention has achieved remarkable results in optimizing the allocation of power generation, grid, load, and storage resources: technically, it can improve the absorption capacity of new energy sources, reduce power curtailment, and ensure power supply reliability and grid operation stability; economically, it can optimize the investment scale of various resources, control investment and operating costs, and improve the overall benefits of virtual power plants participating in market transactions and demand response; environmentally, it can reduce fossil energy consumption, lower carbon emission intensity, and improve energy utilization efficiency, meeting the needs of green and low-carbon development.

[0033] In one embodiment, according to the optimized configuration model, a non-dominated sorting genetic algorithm is used to perform fast non-dominated sorting and crowding calculation on the initial population, including steps S201 to S203, each of which is as follows: S201. An initial population is generated using real number encoding; each individual in the initial population corresponds to a resource allocation scheme. The encoding method using real numbers is employed, with each individual being a vector of length 4. , , , These correspond to the total capacity of distributed energy resources, the rated capacity of energy storage, the maximum adjustable load capacity, and the number of terminal devices, respectively; the range of variable constraints is determined based on resource and technology constraints and investment budgets, for example... ∈[100, 5000]kW, ∈[50, 2000]kWh, ∈[10, 200] units; Set the population size to 100, randomly generate initial individuals, and ensure that the variable values ​​are evenly distributed within the constraints; S202. Based on the objective function of the optimization configuration model, the fitness of the initial population is calculated and fast non-dominated sorting is performed to obtain the fitness value and non-dominated sorting level of the initial population. Among them, based on the objective function The multi-objective fitness value is converted into a single-objective fitness value. Before the calculation, it is checked whether the individual meets the constraints (power balance, grid security, etc.). The fitness value of the individual that does not meet the constraints is reduced by 30%, and it is forced to be eliminated. The initial population is subjected to a fast non-dominated sort: 1. For each individual, calculate its dominance count (the number of times it is dominated by other individuals) and dominance set (all individuals dominated by this individual); 2. Individuals with a dominance count of 0 are assigned to the first level of the non-dominated sort (the optimal level); 3. Individuals at each level are processed sequentially, and individuals whose dominance count in their dominance set is reduced by 1 and becomes 0 are assigned to the next level, until all individuals are sorted. S302. According to the non-dominated sorting level, the fitness values ​​of each level of non-dominated individuals in the initial population are sorted, and the crowding value of each level of non-dominated individuals is calculated.

[0034] For each level of non-dominant individuals, they are arranged in ascending order of fitness value; The formula for calculating congestion is as follows: Where M is the number of objective functions; Let m be the objective function value for the i-th individual; , This represents the maximum / minimum value of the objective function. The crowding of the first and last individuals in the sorting is set to infinity to ensure that the optimal individual at the boundary is not eliminated. This invention, through fitness calculation of the initial population, can quickly and directly quantify and evaluate the comprehensive benefits of each resource allocation scheme based on the objective function of the optimization model, providing an objective basis for comparing the merits of individuals. By implementing fast non-dominated sorting, it can efficiently identify and classify dominant individuals in the population, clarify the quality distribution of solutions at different levels, thereby guiding the search process towards a better direction and improving the directionality of the optimization process. By calculating the crowding degree of non-dominated individuals at each level, it can effectively measure the distribution density of solutions in the target space, prioritizing the retention of individuals in sparsely distributed regions, thereby actively maintaining population diversity during the iteration process, avoiding premature convergence, and ensuring that the final set of optimal solutions can broadly cover the trade-off regions between different objectives.

[0035] In one embodiment, an adaptive crossover mutation operator and an elite retention strategy are used for iterative calculation to obtain the optimal solution set containing resource allocation schemes, including step S301, as follows: S301. Based on the objective function of the optimized configuration model, the initial population is subjected to iterative crossover and mutation calculations using an adaptive crossover and mutation operator. The initial population is then screened and retained using an elite retention strategy to select high-quality and sub-high-quality individuals until the iteration termination condition is met, thereby obtaining an optimal solution set containing resource configuration schemes.

[0036] The selection process employs a combination of roulette wheel selection and direct retention of elite individuals. All individuals in the elite pool directly enter the next generation population. The selection probability of individuals in the candidate pool is calculated based on their fitness percentage. Roulette wheel selection is used to supplement the population size (e.g., 100 individuals) to ensure a balance between selection fairness and excellence. Crossover and mutation operations are performed on the individuals in the population. Candidate pool individuals are randomly paired, and simulated binary crossover is performed according to adaptive crossover probability and step size to generate offspring individuals. Polynomial mutation is then performed on the offspring individuals according to adaptive mutation probability and amplitude to avoid population homogenization. Simultaneously, constraint verification is performed. If, after crossover and mutation, offspring individuals exceed the variable constraint range, boundary truncation is used for correction (e.g., ...). When the power is greater than 5000kW, it is adjusted to 5000kW); iteration stops when any of the following iteration termination conditions are met: 1. The number of iterations reaches the preset maximum value (1000 times); 2. The fitness change rate of the Pareto optimal solution set for 50 consecutive generations is ≤0.1%; 3. The objective function value of the optimal individual meets the preset threshold (e.g., new energy absorption rate ≥95%, comprehensive benefit ≥ preset peak value); after the iteration terminates, the optimal resource allocation scheme is selected from the Pareto optimal solution set according to the weight coefficients determined by the analytic hierarchy process, and the optimal solution set containing the resource allocation scheme is obtained.

[0037] This invention generates an initial population using real-number encoding, where each individual directly corresponds to a resource allocation scheme. The encoding is intuitive and easy to operate, facilitating search and evaluation in a continuous variable space. By introducing an adaptive crossover and mutation operator combined with an elite retention strategy, the algorithm significantly improves its convergence speed, solution stability, and the quality of the final solution set when dealing with multi-objective and multi-constraint optimization problems. This reliably generates an optimal solution set that reflects the trade-offs between different objectives, providing a comprehensive and high-quality decision-making basis for subsequent scheme selection.

[0038] In one embodiment, the adaptive crossover and mutation operator includes an adaptive crossover operator and an adaptive mutation operator. The adaptive crossover and mutation operator is used to perform iterative crossover and mutation calculations on the initial population, including steps S401 to S403, each of which is as follows: S401. Perform iterative crossover calculations on the initial population using an adaptive crossover operator, and perform iterative mutation calculations on the initial population using an adaptive mutation operator. S402. The adaptive crossover operator is used to simulate binary crossover for adjustment, adjusting the crossover step size according to the convergence state of the population, and adjusting the crossover probability according to the diversity coefficient of the population. The crossover operator uses simulated binary crossover (SBX), with the crossover step size σ adaptively adjusted: when the population convergence speed is slow (fitness change rate > 1% over 20 consecutive generations), σ ∈ [1.2, 1.5], expanding the search range; when the population tends to converge (fitness change rate ≤ 1% over 20 consecutive generations), σ ∈ [0.6, 0.9], focusing on local optimization; the base value of the crossover probability is set to 0.8, dynamically adjusted according to the population diversity coefficient (probability increases to 0.9 when diversity coefficient < 0.3; decreases to 0.7 when diversity coefficient > 0.7). S403. The adaptive mutation operator is used to perform polynomial mutation, while adjusting the mutation amplitude according to the proportional relationship of the number of iterations, and adjusting the mutation probability according to the crowding value of individuals in the population.

[0039] The mutation operator employs polynomial mutation, and the specific formula for adaptively adjusting the mutation magnitude η is as follows: in, =20; =5; This represents the current iteration number; =1000; The base value of the mutation probability is 0.05. When the individual crowding degree is <0.1 (local population density), the probability increases to 0.08 to avoid local optima.

[0040] This invention introduces an adaptive crossover operator using simulated binary crossover. By sensing the population's convergence state, the crossover step size is dynamically adjusted: increasing the step size when convergence is slow to enhance global exploration capabilities, and decreasing it when convergence is near to strengthen local fine-tuning, thus achieving an adaptive balance between global and local search capabilities. The crossover probability is dynamically adjusted based on the population diversity coefficient: increasing the crossover probability when diversity is insufficient to promote information exchange and increase population diversity, and appropriately decreasing the probability when diversity is sufficient to maintain optimal patterns, thereby effectively maintaining the population's evolutionary vitality and search breadth. An adaptive mutation operator using polynomial mutation is introduced, causing the mutation amplitude to gradually decrease with increasing iterations, achieving a natural transition from extensive exploration in the early stages to fine-tuning in the later stages, improving convergence accuracy. Finally, the mutation probability is dynamically adjusted based on individual crowding levels, increasing the mutation probability for individuals with low crowding levels to promote exploration of sparse regions and optimize distribution uniformity.

[0041] In one embodiment, the elite retention strategy includes an elite pool screening strategy and a candidate pool replenishment strategy. The elite retention strategy is used to screen and retain high-quality and sub-high-quality individuals in the initial population, including steps S501 to S502, each of which is as follows: S501. Using an elite pool screening strategy, individuals with the highest non-dominant ranking level in each generation are selected and stored based on their crowding value to screen for high-quality individuals in the population. Among them, a "dual-repository screening mechanism" is constructed, setting up an elite repository (with a capacity of 20% of the population size) and a candidate repository (with a capacity of 80% of the population size); through the elite repository screening strategy, the top 20% of individuals in each generation's non-dominant ranking level 1 are selected in descending order of crowding to ensure that the optimal individuals are stably inherited. S502. Using a candidate pool replenishment strategy, the crowding and fitness values ​​of individuals with the second and third highest non-dominated ranking levels are weighted and calculated, and the second-highest quality individuals are selected for storage based on the weight values.

[0042] Among them, a candidate pool replenishment strategy is used to select individuals from the non-dominated ranking level 2 and 3 individuals by weighting "crowding degree + fitness" (weight 0.5 each) to maintain population diversity; continuous iterative updates are carried out, and after each generation, 80% of the core individuals are retained in the elite pool, and 20% of the slots are replaced with the best individuals in the candidate pool to avoid elite degeneration.

[0043] This invention employs a two-tiered screening mechanism—an elite pool and a candidate pool—to achieve precise identification and hierarchical management of outstanding individuals. The elite pool screening process selects top-ranked individuals from the highest non-dominated level based on crowding values, ensuring that the best-performing and relatively sparsely distributed elite individuals are retained in each generation. This guarantees the stable inheritance of core superior genes and maintains the overall quality of the population. The candidate pool replenishment process uses a weighted selection process combining crowding and fitness from the second-best non-dominated level, absorbing individuals with development potential or located in sparse areas. This effectively enriches the genetic diversity of the population while retaining elites, avoiding population homogenization and premature convergence caused by over-selection. At the end of each generation iteration, by retaining most of the core individuals in the elite pool and introducing some of the best individuals from the candidate pool for updating, moderate flow and dynamic optimization of the elite population are achieved. This maintains the stability of the evolutionary process while injecting new superior genes into the population.

[0044] In one embodiment, the resource characteristic parameters include the rated capacity of distributed energy, the ramp-up capability parameters of distributed energy, the capacity of the energy storage system, the charging and discharging power parameters of the energy storage system, the adjustment capacity of the adjustable load, and the rate parameters of the adjustable load; the system operation basic data includes new energy output forecast data, load demand data, electricity market price data, carbon trading price data, fossil energy consumption data, equipment investment unit price, and operation and maintenance cost unit price data. The objective function construction of the optimization configuration model includes steps S601 to S606, each step of which is as follows: S601. Calculate the renewable energy absorption rate based on the renewable energy output forecast data and the load demand data; the renewable energy absorption rate is used to quantify the actual renewable energy absorption and potential power generation. The specific formula for calculating the renewable energy absorption rate is as follows: Where F1 is the renewable energy absorption rate; E DG,util This represents the actual consumption of renewable energy power; EDG and pot represent potential renewable energy power generation. S602. Based on the electricity market price data, the new energy output forecast data, the adjustable load adjustment capacity, the adjustable load rate parameters, and the continuous adjustment duration data, calculate the comprehensive revenue; the comprehensive revenue includes on-grid electricity price revenue, ancillary service revenue, and demand response revenue. The specific formula for calculating comprehensive income is as follows: F2=F energy +F aux +F dr Wherein, F2 represents total revenue; Fenergy represents feed-in tariff revenue; Faux represents ancillary service revenue; and Fdr represents demand response revenue. S603. Calculate the energy conservation and emission reduction benefits based on the carbon trading price data and fossil energy consumption data; The specific formula for calculating energy conservation and emission reduction benefits is as follows: F3=(E fossil,ref -E fossil,opt )×C CO2 Among them, F3 represents energy conservation and emission reduction benefits; E fossil,ref E is the baseline fossil fuel consumption. fossil,opt To optimize fossil fuel consumption; C CO2 For carbon trading prices; S604. Calculate the investment cost based on the unit price of the equipment investment and the resource characteristic parameters; The specific formula for calculating investment costs is as follows: C1=C DG +C ESS +C load +C term Where C1 is the investment cost; C DG For distributed energy investment costs; C ESS C represents the investment cost of energy storage. load For adjustable load investment costs; C term Investment cost for terminal equipment; S605. Calculate the operating cost based on the unit price data of the operation and maintenance cost and the resource characteristic parameters; The specific formula for calculating operating costs is as follows: C2=C loss +C om +C dr Where C2 represents operating costs; C loss Cost of charging and discharging losses; C om For operation and maintenance costs; C dr For load adjustment costs; S606. Based on the new energy absorption rate, the comprehensive benefits, the energy conservation and emission reduction benefits, the investment costs, and the operating costs, construct an objective function with the goal of maximizing comprehensive benefits.

[0045] Among them, by integrating the three positive objectives of new energy consumption, economic benefits, and energy conservation and emission reduction through weighted coefficients, and deducting the two negative objectives of investment costs and operating costs, the objective function expression is as follows: Where F is the comprehensive objective function value, the larger the value, the better the comprehensive benefits of the configuration scheme; F1 is the new energy absorption rate; F2 is the comprehensive benefit; F3 is the energy conservation and emission reduction benefit; C1 is the investment cost; C2 is the operating cost; The weighting coefficients are determined using the Analytic Hierarchy Process (AHP) and satisfy the following conditions: .

[0046] This invention simplifies the problem structure by transforming a multi-objective optimization problem into a single-objective optimization problem focused on maximizing comprehensive benefits, thus facilitating model solving and result interpretation. It accurately quantifies the efficiency of new energy utilization through the new energy absorption rate, objectively reflecting the system's capacity to absorb distributed energy. By comprehensively incorporating grid-connected electricity price revenue, ancillary service revenue, and demand response revenue into the overall revenue, the system systematically assesses the economic potential of virtual power plants. It scientifically measures the effects of fossil energy conservation and carbon emission reduction through energy conservation and emission reduction benefits, aligning with green and low-carbon development goals. Furthermore, by detailing the composition of investment and operating costs, it precisely controls the full-cycle costs of resource allocation, enhancing the financial feasibility of the solution.

[0047] In one embodiment, the constraints of the optimization configuration model include power balance constraints, resource and technology constraints, grid security constraints, and investment constraints, including steps S701 to S705, each step as follows: S701. Based on the capacity of the energy storage system, the charging and discharging power parameters of the energy storage system, the adjustment capacity of the adjustable load, and the rate parameters of the adjustable load, combined with the grid exchange power, a power balance constraint is constructed. The specific formula for the power balance constraint is as follows: , Where t is a time variable, defined as any moment within the optimization time scale, usually divided into optimization periods on an hourly basis; The actual output of distributed power sources such as photovoltaic and wind power at time t shall not exceed the rated capacity of distributed energy. Let t be the charging / discharging power of the energy storage system at time t, which is limited by the energy storage charging / discharging power and the charging and discharging do not occur simultaneously; The total load demand of the system at time t, including the actual values ​​of fixed load and adjustable load; In order to exchange power with the power grid; The maximum power that the power grid allows the system to connect to is determined by the power grid planning department; S702. Construct distributed energy constraints based on the rated capacity and ramping capability parameters of the distributed energy source; construct energy storage constraints based on the capacity and charging / discharging power parameters of the energy storage system; construct adjustable load constraints based on the adjustment capacity and rate parameters of the load adjustment, combined with the continuous adjustment duration limit; and obtain resource and technology constraints by combining the distributed energy constraints, the energy storage constraints, and the adjustable load constraints. The specific formula for the distributed energy constraint is as follows: , The specific formula for energy storage constraints is as follows: , , The formula for the adjustable load constraint is as follows: , , in, , The minimum / maximum output of distributed energy sources represents the output range within which distributed power sources can operate safely. Let be the ramp rate of the distributed energy source at time t; , Minimum / maximum ramp rate for distributed energy; Let t be the energy storage state of charge at time t; , These represent the maximum and minimum states of charge for energy storage. Minimum / maximum charging power for energy storage; , Minimum / maximum discharge power for energy storage; Let be the operating power of the adjustable load at time t; , Minimum / maximum operating power for adjustable load; The adjustable load regulation rate at time t; , The minimum / maximum adjustment rate for adjustable load; The duration for the adjustable load to maintain its current adjustment state at time t; , Minimum / maximum continuous adjustment duration; S703. Construct voltage constraints based on system node voltages and rated voltages; construct frequency constraints based on system operating frequencies and frequency limits; construct line transmission constraints based on system line transmission power and rated transmission power; and obtain power grid security constraints by combining the voltage constraints, frequency constraints, and line transmission constraints. The specific formula for voltage constraint is as follows: The formula for the frequency constraint is as follows: The specific formula for the line transmission constraint is as follows: in, Let be the system node voltage at time t; = , = , This is the system's rated voltage; Let t be the system operating frequency at time t; , For the minimum and maximum operating frequencies of the system, ; Let t be the line transmission power at time t; A 10% margin is reserved for the rated transmission power (kW) of the line to ensure safety; S704. Construct investment constraints based on the initial total investment in distributed energy, energy storage, adjustable load, and terminal equipment, and the project's preset total investment ceiling. The specific formula for investment constraints is as follows: in, This represents the total initial investment in distributed energy resources. This represents the total initial investment in energy storage. This represents the total initial investment for adjustable loads. This represents the total initial investment in the terminal equipment. The project's total investment limit is preset; S705. Based on the power balance constraint, the resource technology constraint, the power grid security constraint, and the investment constraint, construct the constraint conditions for the optimal configuration model.

[0048] This invention constructs a comprehensive constraint system encompassing power balance, resource technology, grid security, and investment constraints. This ensures that the optimized configuration model closely matches the actual physical system and engineering conditions, effectively guaranteeing the feasibility and reliability of the resulting solution. Power balance constraints ensure real-time power supply and demand equilibrium at any given time, maintaining operational stability. Resource technology constraints, by incorporating distributed energy output and ramp-up limits, energy storage state of charge and charging / discharging power limits, and the power and regulation characteristics of adjustable loads, accurately characterize the operational boundaries of various resources, preventing equipment overload or abnormal operation. Grid security constraints, by setting safe ranges for voltage, frequency, and line transmission power, ensure that the optimized system meets grid standards, preventing over-limit risks and improving grid connection security. Investment constraints, by limiting the total investment in equipment, incorporate economic feasibility into the model, preventing the solution from exceeding the budget.

[0049] like Figure 2 As shown in the resource optimization allocation based on the non-dominated sorting genetic algorithm, a corresponding system implementation is provided based on the above method implementation. This invention provides a resource optimization allocation system based on a non-dominated sorting genetic algorithm, comprising: a model building module 801 and a resource allocation module 802; The model building module 801 is used to acquire resource characteristic parameters of source-grid-load-storage resources and basic power system operation data; and to build an optimization configuration model based on the resource characteristic parameters and the basic power system operation data; the optimization configuration model takes the maximization of comprehensive benefits as the objective function and power balance constraints, resource technology constraints, grid security constraints and investment constraints as constraints. The resource allocation module 802 is used to perform iterative calculations using a non-dominated sorting genetic algorithm based on the optimized allocation model, combined with an adaptive crossover mutation operator and an elite retention strategy, to obtain an optimal solution set containing resource allocation schemes; and to perform resource optimization allocation on the source-grid-load-storage resources based on the optimal solution set.

[0050] This invention constructs a resource optimization model for source-grid-load-storage, encompassing comprehensive power balance constraints, resource and technology constraints, grid security constraints, and investment constraints. By transforming multiple objectives into a single-objective optimization problem through an objective function, the core objective is to maximize the overall benefit of the virtual power plant, while also considering technical feasibility, economic rationality, and environmental friendliness. A non-dominated sorting genetic algorithm is used to solve the high-dimensional, multi-constraint optimization model, enhancing the algorithm's global search capability and convergence performance in complex solution spaces. This effectively handles the trade-offs between multiple objectives, avoiding getting trapped in local optima, thereby improving solution efficiency and accuracy. Furthermore, resource optimization is performed based on the optimal solution set, effectively balancing and optimizing the resource allocation of source-grid-load-storage while ensuring that constraints are met, achieving efficient and balanced decision-making.

[0051] It is understood that the above system item embodiments correspond to the method item embodiments of the present invention, and can implement the resource optimization allocation method based on non-dominated sorting genetic algorithm provided by any of the above method item embodiments of the present invention.

[0052] It should be noted that the system embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0053] For ease of description and brevity, the system embodiments of the present invention include all the implementation methods described in the above embodiments of the resource optimization allocation method based on non-dominated sorting genetic algorithm, and will not be repeated here.

[0054] Based on the above embodiments of the resource optimization allocation method based on non-dominated sorting genetic algorithm, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the resource optimization allocation method based on non-dominated sorting genetic algorithm of any embodiment of the present invention.

[0055] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0056] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0057] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-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. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0058] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the resource optimization allocation method based on the non-dominated sorting genetic algorithm described in any of the above-described method embodiments of the present invention.

[0059] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0060] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A resource optimization allocation method based on a non-dominated sorting genetic algorithm, characterized in that, include: Obtain resource characteristic parameters of power source, grid, load and storage resources and basic data on power system operation; Based on the resource characteristic parameters and the power system operation data, an optimal configuration model is constructed. The optimal configuration model takes the maximization of comprehensive benefits as the objective function and power balance constraints, resource and technology constraints, power grid security constraints, and investment constraints as constraints. Based on the optimization configuration model, the initial population is quickly sorted and crowded by a non-dominated sorting genetic algorithm, and an adaptive crossover mutation operator and an elite retention strategy are used for iterative calculation to obtain the optimal solution set containing resource allocation schemes. Based on the optimal solution set, the source-grid-load-storage resources are optimized and allocated.

2. The resource optimization allocation method based on non-dominated sorting genetic algorithm as described in claim 1, characterized in that, The step of performing fast non-dominated sorting and crowding calculation on the initial population based on the optimized configuration model is as follows: An initial population is generated using real-number encoding; each individual in the initial population corresponds to a resource allocation scheme. Based on the objective function of the optimization configuration model, the fitness of the initial population is calculated and fast non-dominated sorting is performed to obtain the fitness value and non-dominated sorting level of the initial population. According to the non-dominated sorting level, the fitness values ​​of each level of non-dominated individuals in the initial population are sorted, and the crowding value of each level of non-dominated individuals is calculated.

3. The resource optimization allocation method based on a non-dominated sorting genetic algorithm as described in claim 2, characterized in that, The process involves iterative calculations using an adaptive crossover and mutation operator and an elite retention strategy to obtain the optimal solution set containing resource allocation schemes. Specifically: Based on the objective function of the optimization configuration model, the initial population is subjected to iterative crossover and mutation calculations using an adaptive crossover and mutation operator. The initial population is then screened and retained using an elite retention strategy to select high-quality and sub-high-quality individuals until the iteration termination condition is met, thereby obtaining an optimal solution set containing resource allocation schemes.

4. The resource optimization allocation method based on non-dominated sorting genetic algorithm as described in claim 3, characterized in that, The adaptive crossover and mutation operator includes an adaptive crossover operator and an adaptive mutation operator; The iterative crossover and mutation calculation of the initial population using the adaptive crossover and mutation operator specifically involves: The initial population is subjected to iterative crossover calculations using an adaptive crossover operator and iterative mutation calculations using an adaptive mutation operator. The adaptive crossover operator is used to simulate binary crossover for adjustment, adjusting the crossover step size according to the convergence state of the population and the crossover probability according to the diversity coefficient of the population. The adaptive mutation operator is used to perform polynomial mutation, adjusting the mutation amplitude according to the ratio of the number of iterations and the mutation probability according to the crowding value of individuals in the population.

5. The resource optimization allocation method based on non-dominated sorting genetic algorithm as described in claim 3, characterized in that, The elite retention strategy includes an elite pool screening strategy and a candidate pool replenishment strategy. The process of selecting and retaining high-quality and sub-high-quality individuals in the initial population using an elite retention strategy specifically involves: The elite pool screening strategy selects individuals from the highest non-dominant ranking individuals in each generation based on their crowding value for storage, in order to screen high-quality individuals in the population. By employing a candidate pool replenishment strategy, individuals with the second and third highest non-dominated ranking levels are weighted by their crowding and fitness values, and then selected as the next best individuals for storage based on these weights.

6. The resource optimization allocation method based on non-dominated sorting genetic algorithm as described in claim 1, characterized in that, The resource characteristic parameters include the rated capacity of distributed energy, the ramp-up capability parameters of distributed energy, the capacity of energy storage system, the charging and discharging power parameters of energy storage system, the adjustment capacity of adjustable load, and the rate parameters of adjustable load; the system operation basic data include new energy output forecast data, load demand data, electricity market price data, carbon trading price data, fossil energy consumption data, equipment investment unit price, and operation and maintenance cost unit price data. The objective function construction of the optimized configuration model includes: The renewable energy absorption rate is calculated based on the renewable energy output forecast data and the load demand data; the renewable energy absorption rate is used to quantify the actual renewable energy absorption and potential power generation. The comprehensive revenue is calculated based on the electricity market price data, the new energy output forecast data, the adjustable load regulation capacity, the adjustable load rate parameters, and the continuous regulation duration data; the comprehensive revenue includes on-grid electricity price revenue, ancillary service revenue, and demand response revenue. Based on the carbon trading price data and fossil energy consumption data, energy conservation and emission reduction benefits are calculated. The investment cost is calculated based on the unit price of the equipment investment and the resource characteristic parameters. The operating cost is calculated based on the unit price data of the operation and maintenance cost and the resource characteristic parameters; Based on the new energy absorption rate, the comprehensive benefits, the energy conservation and emission reduction benefits, the investment costs, and the operating costs, an objective function is constructed with the goal of maximizing comprehensive benefits.

7. The resource optimization allocation method based on non-dominated sorting genetic algorithm as described in claim 6, characterized in that, The constraints of the optimized configuration model include power balance constraints, resource and technology constraints, grid security constraints, and investment constraints, specifically: Based on the capacity of the energy storage system, the charging and discharging power parameters of the energy storage system, the adjustment capacity of the adjustable load, and the rate parameters of the adjustable load, combined with the grid exchange power, a power balance constraint is constructed. Distributed energy constraints are constructed based on the rated capacity and ramping capability parameters of the distributed energy source; energy storage constraints are constructed based on the capacity and charging / discharging power parameters of the energy storage system; adjustable load constraints are constructed based on the adjustment capacity and rate parameters of the adjustable load, combined with continuous adjustment duration data limits; resource and technology constraints are obtained by combining the distributed energy constraints, the energy storage constraints, and the adjustable load constraints. Voltage constraints are constructed based on system node voltages and rated voltages; frequency constraints are constructed based on system operating frequencies and frequency limits; line transmission constraints are constructed based on system line transmission power and rated transmission power; and power grid security constraints are obtained by combining the voltage constraints, frequency constraints, and line transmission constraints. Investment constraints are established based on the initial total investment in distributed energy, energy storage, adjustable loads, and terminal equipment, as well as the project's preset total investment ceiling. Based on the power balance constraint, the resource technology constraint, the power grid security constraint, and the investment constraint, the constraints of the optimal configuration model are constructed.

8. A resource optimization allocation system based on a non-dominated sorting genetic algorithm, characterized in that, include: Model building module and resource configuration module; The model building module is used to obtain resource characteristic parameters of source-grid-load-storage resources and basic data of power system operation; Based on the resource characteristic parameters and the power system operation data, an optimal configuration model is constructed. The optimal configuration model takes the maximization of comprehensive benefits as the objective function and power balance constraints, resource and technology constraints, power grid security constraints, and investment constraints as constraints. The resource allocation module is used to perform iterative calculations using a non-dominated sorting genetic algorithm based on the optimized allocation model, combined with an adaptive crossover and mutation operator and an elite retention strategy, to obtain an optimal solution set containing resource allocation schemes; and to perform resource optimization allocation on the source-grid-load-storage resources based on the optimal solution set.

9. A terminal device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the resource optimization allocation method based on a non-dominated sorting genetic algorithm as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the resource optimization allocation method based on a non-dominated sorting genetic algorithm as described in any one of claims 1-7.

Images