Energy Flow - Carbon Flow Joint Optimal Scheduling Method for New Energy Power Systems

Abstract

The present invention discloses an energy flow-carbon flow joint optimization scheduling method for a new energy power system, which relates to the technical field of new energy scheduling. The method includes: connecting the new energy power system to establish scenarios for peak load periods, low-carbon emission periods, and energy storage efficient periods; establishing priority weights for energy flow, carbon flow, and energy storage indicators and configuring an iteration scheme; configuring a fitness function; performing population initialization; performing probabilistic selection of individuals in the population; generating cross-constraint factors and mutation-constraint factors based on the iteration scheme, reconstructing the crossover rate and mutation rate, performing mutation operations, and generating mutation results; generating a joint optimization scheduling scheme. The present invention solves the technical problems existing in the prior art, such as low scheduling accuracy and energy storage efficiency of the new energy power system under different scenarios and insufficient carbon emission control, and achieves the technical effects of improving the scheduling accuracy, carbon emission control, and energy storage efficiency of the new energy power system under different scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy scheduling, and particularly to an energy flow-carbon flow joint optimization scheduling method for a new energy power system. Background Art

[0002] In a new energy power system, due to the volatility and uncontrollability of renewable energy sources such as wind energy and solar energy, the scheduling optimization of the system faces many challenges. Traditional power scheduling methods often struggle to balance multiple objectives among energy flow, carbon emissions, and energy storage, resulting in low system operation efficiency, unsatisfactory carbon emission control effects, and insufficient utilization of energy storage devices. In addition, the complexity and real-time nature of the new energy power system require flexible adjustment of the scheduling plan in different scenarios such as peak load periods, low carbon emission periods, and high energy storage efficiency periods, which poses higher requirements on existing scheduling algorithms.

[0003] The prior art has technical problems of low scheduling accuracy and energy storage efficiency, and insufficient carbon emission control in different scenarios of the new energy power system. Summary of the Invention

[0004] The present application provides an energy flow-carbon flow joint optimization scheduling method for a new energy power system, which is used to solve the technical problems of low scheduling accuracy and energy storage efficiency, and insufficient carbon emission control in different scenarios of the new energy power system in the prior art.

[0005] In view of the above problems, the present application provides an energy flow-carbon flow joint optimization scheduling method for a new energy power system. The method includes: connecting the new energy power system, dividing system scenarios according to the historical working data of the new energy power system, and establishing a peak load period scenario, a low carbon emission period scenario, and an energy storage high efficiency period scenario; establishing priority weights for energy flow, carbon flow, and energy storage indicators based on the system scenario division results, and configuring an iterative scheme mapped to the system scenario division results; configuring a fitness function, which is constructed according to the priority weights; performing population initialization, where the population includes N individuals, and each individual represents a candidate solution; activating the fitness function through the scenario attribution of the current task to calculate the individual fitness values in the population, configuring individual selection probabilities based on the individual fitness values, and performing probabilistic selection of individuals in the population; generating a crossover constraint factor and a mutation constraint factor based on the iterative scheme, reconstructing the crossover rate and mutation rate according to the iterative stage, performing data crossover of population individuals through the reconstructed crossover rate, and performing a mutation operation on the offspring individuals generated by the crossover at the mutation rate to generate a mutation result, performing individual fitness elimination on the mutation result and the initialized population, and performing iterative update; generating a joint optimization scheduling plan according to the iterative update result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Connect to the new energy power system, establish scenarios for peak load periods, low-carbon emission periods, and efficient energy storage periods; based on the results of the system scenario division, establish the priority weights of energy flow, carbon flow, and energy storage indicators, and configure an iterative scheme mapped to the results of the system scenario division; configure a fitness function, which is constructed according to the priority weights; perform population initialization; activate the fitness function through the scenario attribution of the current task to calculate the individual fitness values in the population, and perform probabilistic selection of individuals in the population; generate crossover constraint factors and mutation constraint factors based on the iterative scheme, perform data crossover of population individuals through the reconstructed crossover rate to generate mutation results, perform individual fitness elimination of the mutation results and the initialized population, and perform iterative update; generate a joint optimization scheduling scheme. It achieves the technical effect of improving the scheduling accuracy, carbon emission control, and energy storage efficiency of the new energy power system under different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0009] Figure 1 It is a flowchart of the energy flow-carbon flow joint optimization scheduling method for the new energy power system provided in the embodiments of this application;

[0010] Figure 2 It is a flowchart of reconstructing the crossover rate and mutation rate in the energy flow-carbon flow joint optimization scheduling method for the new energy power system provided in the embodiments of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] This application provides an energy flow-carbon flow joint optimization scheduling method for a new energy power system, which is used to solve the technical problems of low scheduling accuracy and energy storage efficiency, and insufficient carbon emission control in the new energy power system in the prior art.

[0012] The following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0013] Embodiment, such as Figure 1 As shown, the present application provides an energy flow - carbon flow joint optimization scheduling method for a new energy power system, and the method includes:

[0014] Step S100: Connect the new energy power system, divide the system scenarios according to the historical working data of the new energy power system, and establish a peak load period scenario, a low - carbon emission period scenario, and a storage - efficient period scenario.

[0015] Specifically, first, it is necessary to connect the new energy power system and establish an effective connection with the new energy power system so as to be able to obtain its relevant data and status information.

[0016] Divide the system scenarios according to the historical working data of the new energy power system. The historical working data includes the operation conditions of the system at different time periods, such as power load, energy supply, carbon emission level, and the use of energy storage devices, etc. By analyzing these data, different operation modes and characteristics are identified.

[0017] For the establishment of the peak load period scenario, it is mainly based on the time periods with higher power demand in the historical data. During these time periods, there is a greater power supply pressure, and it is necessary to focus on how to meet the peak load demand while minimizing the operation cost and ensuring the stability of the system.

[0018] The determination of the low - carbon emission period scenario is based on the time periods with lower carbon emission levels in the historical data. In this scenario, the environmental protection requirements are high, and it is necessary to focus on reducing the total carbon emissions and the carbon emission cost, which involves preferentially using clean energy for power generation, improving energy utilization efficiency, and taking effective carbon emission reduction measures, etc.

[0019] The storage - efficient period scenario is established according to the periods in the historical data when the energy storage devices can play the maximum benefit. During these time periods, the charge - discharge efficiency of the energy storage devices is high, which can effectively balance the power supply and demand and improve the reliability and flexibility of the system. For example, when the power supply is sufficient, the excess electric energy can be stored, and the stored energy can be released during the peak load period, thus realizing the optimal utilization of energy.

[0020] By analyzing and dividing the system scenarios according to the historical working data of the new energy power system, the operation rules and characteristics of the system can be better understood, providing a more accurate and targeted basis for subsequent optimization scheduling.

[0021] Step S200: Based on the system scenario division results, establish the priority weights of the energy flow, carbon flow, and energy storage indicators, and configure an iterative scheme mapped to the system scenario division results.

[0022] Specifically, based on the previously divided system scenario results, the priority weights of the energy flow, carbon flow, and energy storage indicators are established. First of all, for different scenarios, the importance of these indicators will vary. In the peak load period scenario, since the power demand is high at this time, ensuring the stable supply of energy is crucial, so the energy flow indicator will be given a higher priority weight. At the same time, in order to avoid excessive costs and carbon emissions when meeting the peak load, the carbon flow and energy storage indicators also need to be considered to some extent, but their weights may be slightly lower than that of the energy flow.

[0023] In the low-carbon emission period scenario, reducing carbon emissions becomes the primary goal, and the priority weight of the carbon flow indicator will increase significantly. At this time, the system will pay more attention to selecting clean energy and taking carbon emission reduction measures to reduce the total carbon emissions and costs. The energy flow and energy storage indicators are still important, but will be optimized on the premise of meeting low-carbon emissions.

[0024] In the energy storage high-efficiency period scenario, the priority weight of the energy storage indicator will increase, making full use of the high-efficiency charge and discharge characteristics of the energy storage device to balance the power supply and demand and improve the flexibility and reliability of the system. The energy flow and carbon flow indicators will also be coordinated based on the energy storage to achieve the optimal operation of the overall system.

[0025] At the same time, an iterative scheme mapped to the system scenario division results needs to be configured. For different scenarios, the iterative scheme will be adjusted according to their characteristics and goals. For example, in the peak load period scenario, the iterative scheme will pay more attention to quickly finding feasible solutions to meet the immediate power demand. A larger step size and a higher mutation rate will be adopted to increase the breadth and speed of the search. In the low-carbon emission period scenario, the iterative process will be more refined to ensure finding the optimal carbon emission reduction strategy. The mutation rate will be reduced and the frequency of crossover operations will be increased to make full use of the existing excellent solutions for optimization. In the energy storage high-efficiency period scenario, the iterative scheme will focus on exploring the best use strategy of the energy storage device and adjust the parameters according to the characteristics of the energy storage device to achieve the efficient storage and release of energy.

[0026] By establishing the priority weights and configuring the iterative scheme, the optimization scheduling process can be made more targeted and efficient, and better adapt to the needs of different system scenarios.

[0027] Step S300: Configure a fitness function, and the fitness function is constructed according to the priority weights.

[0028] Specifically, the fitness function is configured to evaluate the pros and cons of various possible scheduling schemes in the new energy power system. This fitness function is constructed based on the priority weights of energy flow, carbon flow, and energy storage indicators under different scenarios. For example, in the peak load period scenario, the energy flow indicator has a higher priority weight, and the fitness function will focus more on evaluating the performance of the scheme in meeting power demand and ensuring system stability. In the low-carbon emission period scenario, the weight of the carbon flow indicator will increase, and the fitness function will mainly examine the contribution of the scheme to reducing carbon emissions. In the energy storage high-efficiency period scenario, the energy storage indicator becomes crucial, and the fitness function will measure the effect of the scheme in improving the utilization efficiency of energy storage devices. By comprehensively considering the priority weights of these different indicators, the constructed fitness function can accurately reflect the adaptability of the scheduling scheme under a specific scenario, providing a powerful evaluation tool for finding the optimal joint optimization scheduling scheme.

[0029] Step S400: Perform population initialization. The population contains N individuals, and each individual represents a candidate solution.

[0030] Specifically, perform the population initialization operation. First, determine the size of the population as N, which means creating a set containing N individuals. In the joint optimization scheduling problem of the new energy power system, each individual represents a candidate solution. These candidate solutions are a specific arrangement of aspects such as energy allocation, equipment operating status, and energy storage strategies. For example, an individual represents the output power allocation scheme of each power generation device, the charge and discharge strategy of the energy storage facility, and the load distribution of the energy transmission line during a specific time period. To initialize the population, a random generation method is used to randomly generate N different individuals within the given problem space. This can ensure that the population has a certain degree of diversity in the initial stage, providing a broader search space for the subsequent evolution process. For example, for a new energy power system including multiple wind turbines, solar panels, energy storage devices, and electrical loads, an individual is a set of specific wind turbine output power values, the tilt angle of the solar panels, the charge and discharge power of the energy storage device, and the energy allocation ratio of each electrical load. By randomly generating N such individuals, the initial population is established, providing a basis for the subsequent iteration of optimization methods such as genetic algorithms. Population initialization is an important step in the joint optimization scheduling process of the new energy power system, laying the foundation for finding the optimal solution.

[0031] Step S500: Activate the fitness function through the scenario attribution of the current task to calculate the individual fitness values in the population, configure the individual selection probabilities based on the individual fitness values, and perform probabilistic selection of individuals in the population.

[0032] Specifically, the fitness function is activated according to the scenario attribution of the current task. If the current scenario is the peak load period, the fitness function will be calculated with specific priority weights for the energy flow, carbon flow, and energy storage indicators in this scenario. If it is the low-carbon emission period scenario or the energy storage high-efficiency period scenario, the fitness function will also be activated according to the respective scenario weights.

[0033] Next, the fitness value of each individual in the population is calculated using the activated fitness function. This fitness value reflects the quality of the individual as a new energy power system scheduling scheme in the current scenario. For example, during the peak load period, if an individual can effectively meet the high load demand while maintaining a low cost and reasonable carbon emissions, its fitness value will be relatively high. Based on the calculated individual fitness values, the individual selection probabilities are configured. The higher the fitness value of an individual, the greater the probability of being selected. This is because individuals with high fitness are more likely to represent better scheduling schemes and should have a greater chance of being retained and further optimized in the subsequent evolution process. Finally, the probabilistic selection of individuals in the population is performed. It is done through random selection, but the selection probability is determined according to the individual selection probability. This can ensure that individuals with high fitness are more likely to be selected, while individuals with low fitness also have a certain chance of being retained to maintain the diversity of the population. Through such steps, more potential individuals can be selected according to the scenario of the current task, providing a better basis for subsequent evolutionary operations and gradually approaching the optimal joint optimization scheduling scheme.

[0034] Step S600: Generate the crossover constraint factor and mutation constraint factor based on the iterative scheme, reconstruct the crossover rate and mutation rate according to the iterative stage, perform data crossover of the population individuals through the reconstructed crossover rate, and perform mutation operations on the offspring individuals generated by crossover at the mutation rate to generate mutation results. Eliminate the individual fitness of the mutation results and the initialized population, and execute iterative update.

[0035] Specifically, the generation of the crossover constraint factor and mutation constraint factor is to ensure that during the crossover and mutation operations of the genetic algorithm, the newly generated individuals still meet the various constraint conditions of the new energy power system. For example, in the new energy power system, there are output power limits of power generation equipment, capacity limits of energy storage equipment, load limits of energy transmission lines, etc. The crossover constraint factor adjusts the new individuals that exceed the constraint range during the crossover operation. For instance, if the output power of a certain power generation equipment in the offspring individual exceeds its allowed maximum value after the crossover of two parent individuals, the crossover constraint factor can adjust this power value to the maximum value. Similarly, the mutation constraint factor also plays a similar role in the mutation operation to ensure that the mutated individuals do not violate the system's constraint conditions.

[0036] As the genetic algorithm iterates, the crossover rate and mutation rate need to be dynamically adjusted according to the iteration stage. In the initial stage of the genetic algorithm, to increase the diversity of the population, a relatively high mutation rate and an appropriate crossover rate are usually set. This allows the genetic algorithm to explore the search space more extensively. As the iteration progresses, the mutation rate is gradually decreased and the crossover rate is increased. Because at this time, the population already has a certain degree of diversity, and more local search and optimization of excellent individuals are needed.

[0037] The crossover operation is an important way to generate new individuals in the genetic algorithm. Common crossover methods include single-point crossover, two-point crossover, uniform crossover, etc. Taking single-point crossover as an example, two individuals are randomly selected from the population as parent individuals, and then a crossover point is randomly selected. The parts of the two parent individuals after the crossover point are exchanged to generate two offspring individuals. The reconstructed crossover rate is used to determine whether to perform the crossover operation. A random number between 0 and 1 is generated. If this random number is less than the crossover rate, the crossover operation is performed; otherwise, it is not.

[0038] After generating offspring individuals through crossover, these offspring individuals are mutated at the mutation rate. The mutation operation can introduce new gene combinations and increase the diversity of the population. For example, a random perturbation is applied to a certain gene value in the offspring individual, or a gene position is randomly selected for change. Similarly, a random number between 0 and 1 is generated. If this random number is less than the mutation rate, the offspring individual is mutated; otherwise, it is not.

[0039] The mutation results generated by the mutation operation are combined with the initialized population. Then, the fitness value of each individual is calculated according to the fitness function. The fitness function is usually constructed based on the optimization objectives of the new energy power system, such as minimizing energy costs, minimizing carbon emissions, maximizing energy supply reliability, etc. Elimination operations are performed according to the individual fitness values. A part of the individuals with higher fitness values can be selected and retained to form a new population and enter the next round of iteration. This can ensure that the population continuously evolves towards a better direction. By continuously repeating the above steps, the genetic algorithm gradually searches for a better solution in the joint optimal scheduling problem of the new energy power system. As the iteration progresses, the individuals in the population become more and more adapted to the requirements of the problem, and finally, it is expected to find a joint optimal scheduling scheme that satisfies various constraint conditions and has the optimal optimization objective.

[0040] Step S700: Generate a joint optimal scheduling scheme according to the iteration update result.

[0041] Specifically, a joint optimal scheduling scheme is generated according to the results of the iteration update. After a series of previous steps, the population gradually evolves during the continuous iteration process, and the candidate solutions represented by each individual are also continuously optimized.

[0042] First, analyze the population after iterative update. The individuals in this population have undergone operations such as crossover, mutation, and fitness elimination, and have had a significant improvement in fitness. At this time, select the individual with the highest fitness or multiple individuals with relatively high fitness from the population for further analysis. The candidate solutions represented by these individuals with relatively high fitness contain combinations of various parameters in the new energy power system, such as the power generation ratios of different energy sources, the charge-discharge strategies of energy storage devices, and the operating parameters of the power grid. According to these parameters, a specific combined optimal scheduling plan can be constructed. For example, if an individual has a relatively high fitness in the peak load period scenario, the corresponding scheduling plan is to preferentially call efficient power generation resources to meet the load demand, and at the same time reasonably arrange the energy storage device to discharge during the load peak. In the low-carbon emission period scenario, the plan represented by an individual with high fitness is to preferentially use clean energy for power generation to reduce the total carbon emissions and costs. In the energy storage high-efficiency period scenario, the scheduling plan focuses on making full use of the high-efficiency charge-discharge characteristics of the energy storage device to balance power supply and demand.

[0043] Comprehensively consider the optimization results in different scenarios, integrate these results, and form a comprehensive combined optimal scheduling plan. This plan can achieve the goals of efficient operation of the new energy power system, reduction of carbon emissions, and improvement of the utilization efficiency of energy storage devices in different scenarios, thus providing a scientific and reasonable decision-making basis for the optimal scheduling of the new energy power system.

[0044] In one possible way, step S300 further includes:

[0045] The objective function of the fitness function includes an operating cost function, an energy utilization efficiency function, a total carbon emissions function, a carbon emission cost function, and an energy storage device utilization efficiency function. The fitness function is as follows:

[0046] Among them, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of the operating cost, energy utilization efficiency, total carbon emissions, carbon emission cost, and energy storage device utilization efficiency respectively, and ω i = λ i ·W i , ω i is the i-th weight coefficient, λ i represents the priority weight in the current scenario, W i is the basic weight of the corresponding target, C run (x) is the operating cost function, η energy (x) is the energy utilization efficiency function, C carbon (x) is the total carbon emissions function, is the carbon emission cost function, η storage (x) is the energy storage device utilization efficiency function.

[0047] Specifically, the fitness function of the present invention is mainly used to measure the advantages and disadvantages of the scheduling scheme of the new energy power system and is calculated by combining multiple key factors. This fitness function consists of the following five objective functions: 1. Operating cost function C run (x): The operating cost function C run (x) is used to represent the total cost during the operation of the system, including power generation cost, transmission and distribution cost, maintenance cost, etc. The specific form is: Among them, x i represents the operating state of the i-th device in the system, C gen (x i ) is the power generation cost, C trans (x i ) is the transmission and distribution cost, C maint (x i ) is the maintenance cost. 2. Energy utilization efficiency function η energy (x): The energy utilization efficiency function η energy (x) is used to represent the energy utilization efficiency of the system, which is usually related to the power generation efficiency and transmission efficiency of the system. The calculation method is: Among them, E use (x i ) is the actual power consumption of the i-th device, E gen (x i ) is the power generation of the i-th device. 3. Total carbon emission function C carbon (x): The total carbon emission function C carbon (x) is used to measure the total carbon emissions of the system, mainly considering the product of the carbon emission factor and the output power of each power source. The formula is: Among them, α i represents the carbon emission factor of the i-th power generation device, P gen (x i ) is its output power. 4. Carbon emission cost function C curboncost (x): The carbon emission cost function C curboncost (x) is used to represent the cost of the system within and outside the carbon emission quota. The formula is: Among them, C permit is the cost within the carbon emission quota, C exceed is the fine cost for the part exceeding the quota, and P quota is the carbon emission quota. 5. Energy storage device utilization efficiency function η storage (x): The energy storage device utilization efficiency function η storage (x) is used to represent the utilization efficiency of the energy storage device, which is usually related to the charge and discharge efficiency and loss rate of the energy storage. The calculation formula is: Among them, E charge (x i ) and E discharge (x i ) respectively represent the charging amount and discharging amount of the energy storage device.

[0048] Each objective function has a corresponding weight coefficient ω i , and these weight coefficients are jointly determined by the scenario priority weight λ i and the base weight W i . The formula is: ω i = λ i ·W i . Among them, λ i reflects the priority weight in the current scenario, and W i is the base weight of the corresponding objective. The adjustment of the weight coefficients enables the system to flexibly adjust the focus of the optimization objective according to different scenarios (such as peak load periods, low-carbon emission periods, etc.), so as to achieve the optimal scheduling scheme.

[0049] Through this fitness function, the system can balance the operating cost, energy utilization efficiency, total carbon emissions, carbon emission cost, and energy storage device utilization efficiency, so as to achieve the joint optimization scheduling of energy flow and carbon flow.

[0050] In a possible way, as Figure 2 shown, step S600 further includes:

[0051] Step S610: Divide the iteration process into stages, and configure the early iteration stage, the middle iteration stage, and the late iteration stage.

[0052] Step S620: Establish the initial crossover rate and the initial mutation rate corresponding to the stage division result.

[0053] Step S630: Complete the crossover rate reconstruction through the crossover constraint factor and the initial crossover rate, and complete the mutation rate reconstruction according to the mutation constraint factor and the initial mutation rate.

[0054] Specifically, dividing the iteration process into stages is a very important step, which clearly divides the iteration process into the early iteration stage, the middle iteration stage, and the late iteration stage. Such a division helps to adopt appropriate strategies to optimize the performance of the genetic algorithm according to the characteristics and requirements of different stages.

[0055] Establish the initial crossover rate and the initial mutation rate corresponding to the stage division result. The settings of the initial crossover rate and the initial mutation rate will affect the search ability and diversity of the genetic algorithm in different stages. In the early iteration, higher initial crossover rate and mutation rate are required to promote the diversity of the population and widely search the solution space. While in the late iteration, lower initial crossover rate and mutation rate are required to more finely search the area near the optimal solution.

[0056] The reconstruction of the crossover rate is completed through the crossover constraint factor and the initial crossover rate. The crossover constraint factor adjusts the intensity and manner of the crossover operation according to specific problems and the requirements of the genetic algorithm. Combined with the initial crossover rate, the crossover rate can be adapted to the search requirements of the genetic algorithm at different stages. At the same time, the reconstruction of the mutation rate is completed according to the mutation constraint factor and the initial mutation rate. The mutation constraint factor can control the degree and direction of the mutation operation. Acting together with the initial mutation rate, it ensures that the mutation rate can effectively introduce new genes at different stages and prevent the genetic algorithm from falling into a local optimum.

[0057] Through such steps, the crossover rate and the mutation rate can be reasonably reconstructed according to the stage division of the iterative process, thereby improving the search efficiency of the genetic algorithm at different stages and its ability to find the optimal solution.

[0058] In a possible way, step S630 further includes:

[0059] Step S631: Establish an adaptive update network for self-update. When reconstructing the crossover rate and the mutation rate, activate the adaptive update network to perform an update self-check. The update self-check includes:

[0060] Step S632: Read the current iteration stage, perform an end-approximation analysis for the current stage according to the current iteration stage, and generate a stage-approximation self-check result.

[0061] Step S633: Obtain the search state of the previous iteration, perform a state self-check according to the search state, and establish a state self-check result.

[0062] Step S634: Perform an adaptation analysis on the stage-approximation self-check result and the state self-check result, complete the self-check update with the adaptation analysis result, and adjust the reconstructed crossover rate and mutation rate according to the self-check update result.

[0063] Specifically, an adaptive update network for self-update is established. When it is necessary to reconstruct the crossover rate and the mutation rate, this network will be activated to perform an update self-check, and this update self-check process includes various aspects of checks.

[0064] The system will first read the specific information of the current iteration stage, including the number of iterations that have been carried out, the current time point, and the position in the entire iteration process, etc. These information are crucial for judging the progress of the current stage. Then, the system will conduct an end-approximation analysis of the current stage based on the read information of the current iteration stage. This analysis process aims to evaluate the closeness between the current stage and the preset end conditions. The system will check the diversity of the current population, the distribution of individual fitness, and the optimization degree of the objective function, etc. When conducting the end-approximation analysis, the system calculates the average value and standard deviation of the individual fitness in the population to evaluate the diversity of the population; compares the value of the current objective function with the historical optimal value to judge the progress of the optimization degree. Based on these analyses and calculations, the system will generate a stage-approximation self-check result. This result is a specific numerical value indicating the closeness between the current stage and the end conditions. For example, if the diversity of the population has reached a relatively high level, the individual fitness is generally good, and the optimization degree of the objective function is close to the expected goal, then the stage-approximation self-check result will show "close to the end". On the contrary, if the diversity of the population is low, the difference in individual fitness is large, or the optimization progress of the objective function is slow, then the result may show "further iteration is still needed". By reading the current iteration stage and conducting the end-approximation analysis, it provides important feedback on the iteration process for the system, which helps the system make reasonable decisions, such as whether to adjust parameters such as the crossover rate and mutation rate to ensure that the iteration can proceed smoothly towards the optimal solution.

[0065] Obtain the search status information of the previous iteration. These search status information include the distribution of the population, the change trend of individual fitness, the effects of crossover and mutation operations, etc. in the previous round or several rounds of iterations. By obtaining this information, the system can comprehensively understand the previous search process and results. The system will conduct a status self-check based on these search statuses. During the self-check process, the system will analyze whether the distribution of the population is reasonable and whether there are traps of local optimal solutions; whether the change trend of individual fitness is stable and whether there are obvious improvements or stagnations; whether the crossover and mutation operations effectively promote the evolution of the population and whether relevant parameters need to be adjusted, etc. Through the comprehensive analysis of these factors, the system can establish a status self-check result. This result is an evaluation of the current search status, judging whether the search is in the correct direction and whether adjustments or improvements are needed. By obtaining the search status of the previous iteration and conducting the status self-check, it can provide important feedback on the search process for the system, helping the system adjust strategies in a timely manner, improve the search efficiency, and increase the possibility of finding the optimal solution.

[0066] Conduct a comprehensive adaptation analysis on the stage approximation self-check result and the status self-check result. This analysis process aims to deeply understand the progress and potential problems of the current iteration process, and optimize the subsequent iteration strategy based on this information. The system will carefully compare the stage approximation self-check result and the status self-check result to find the correlations and mutual influences between them. For example, if the stage approximation self-check result shows that the current stage is approaching the end, but the status self-check result indicates that the population may have fallen into a local optimal solution, then the system needs to consider how to avoid falling into the local optimum while approaching the end. Based on the results of the adaptation analysis, the system will complete the self-check update. This includes adjusting the parameters of the adaptive update network, updating the search strategy, or re-evaluating the priorities, etc. The purpose of the self-check update is to enable the system to better adapt to the current iteration state and provide more effective guidance for subsequent iterations. According to the results of the self-check update, the system will make corresponding adjustments to the reconstructed crossover rate and mutation rate. If the self-check update result indicates that it is necessary to increase the diversity of the population, then the system will increase the mutation rate to introduce more new individuals and new features. On the contrary, if the system believes that the current population is already diverse enough and needs to focus more on optimizing the existing solutions, then it will decrease the mutation rate and appropriately adjust the crossover rate to promote the gene exchange and combination between excellent individuals. For example, if the adaptation analysis result shows that the diversity of the current population is insufficient and the stage approximation self-check result indicates that further iteration is still required, then the system will significantly increase the mutation rate and moderately increase the crossover rate to encourage more exploration and innovation. If the stage approximation self-check result shows that it is approaching the end and the status self-check result indicates that the population is already relatively stable, then the system will fine-tune the crossover rate and mutation rate to ensure that while converging to the optimal solution, the progress already made will not be destroyed due to excessive mutation. Through the adaptation analysis of the stage approximation self-check result and the status self-check result and the corresponding adjustments, the crossover rate and mutation rate can be made more suitable for the needs of the current iteration, thereby improving the efficiency and accuracy of the genetic algorithm and making it more likely to find the optimal joint optimization scheduling solution.

[0067] In a possible way, step S600 further includes:

[0068] Step S640: Establish a taboo retention set, where the taboo retention set is a set of individuals whose taboo values meet a preset threshold, and the taboo value is calculated from the individual fitness value and the individual offspring fitness value.

[0069] Step S650: Perform a screening of the taboo values in the taboo retention set in order, update the order sorting result to the population, and mark it as the single-round iteration retention data.

[0070] Step S660: Continue the iterative update according to the updated population.

[0071] Specifically, establishing a taboo retention set is an important operation. The taboo retention set is a special set that contains those individuals whose taboo values meet a preset threshold. These individuals are considered to have a certain degree of particularity or importance and thus need to be specially retained. The calculation of the taboo value is based on the individual fitness value and the fitness value of the individual's offspring. The individual fitness value reflects the survival ability and advantages of the individual in the current environment, while the fitness value of the individual's offspring takes into account the genetic potential of the individual and its impact on the offspring. By comprehensively considering these two factors, the value of the individual can be evaluated more comprehensively. The weighted summation method is used to calculate the taboo value and establish the taboo retention set. The weights of the individual fitness value and the fitness value of the individual's offspring are determined. These weights are set according to the requirements and experience of the specific problem and are used to represent the relative importance of the individual fitness value and the fitness value of the individual's offspring when calculating the taboo value. Then, for each individual, its taboo value is calculated. The taboo value is obtained by multiplying the individual fitness value by its corresponding weight, adding the product of the fitness value of the individual's offspring and its corresponding weight, and finally summing them up. Next, a preset threshold is set. This preset threshold is used to determine whether an individual should be included in the taboo retention set. Finally, the individuals whose taboo values meet the preset threshold are selected into the taboo retention set. These individuals are considered to have higher value or particularity and need to be specially processed or retained in subsequent iterations. In this way, the weighted summation method can comprehensively consider the individual fitness value and the fitness value of the individual's offspring to determine the taboo value of the individual, thereby establishing the taboo retention set.

[0072] Further processing is carried out on the individuals in the taboo retention set. First, these individuals are sorted and screened according to the size of the taboo value, which means that the individuals in the taboo retention set are sorted from largest to smallest according to their taboo values. After the sorting is completed, the result of the sequential sorting is updated to the population. Specifically, these screened and sorted individuals are replaced or added to the original population to update the composition of the population. At the same time, these updated individuals are marked as single-round iteration retention data. The role of this marking is to clearly know in the subsequent iteration process that these individuals are retained in the current round of iteration, which helps to track and analyze the operation and results of the genetic algorithm. Through such steps, the population can be continuously optimized, retaining individuals with high potential and increasing the possibility of the genetic algorithm finding the optimal solution.

[0073] Continue the iterative update process based on the updated population. The system uses the updated population as the basis and re-executes the previous iterative steps, including calculating individual fitness values, performing probabilistic selection, generating crossover constraint factors and mutation constraint factors, and performing data crossover and mutation operations. In this process, the individuals in the updated population have different characteristics and fitness values, which will affect the subsequent iterative results. The system will evaluate the advantages and disadvantages of individuals based on their fitness values, select individuals with higher fitness values for reproduction and crossover to produce new offspring individuals. At the same time, a certain degree of randomness is introduced through mutation operations to increase the diversity of the population and prevent the genetic algorithm from falling into local optimal solutions. As the iteration progresses, the population will continuously evolve and optimize, gradually approaching the optimal solution. The system will continuously monitor the changes in the population and judge whether to end the iteration according to the preset termination conditions. If the termination conditions have not been reached, the system will continue to repeat the above steps, continuously update the population, until the required optimal solution is found or the maximum number of iterations is reached. By continuously iterating and updating the population, the system can gradually increase the possibility of finding the optimal solution and achieve the joint optimal scheduling of the energy flow-carbon flow of the new energy power system.

[0074] In a possible way, step S700 further includes:

[0075] Step S710: Obtain the prediction task data of the new energy power system, perform scenario transition analysis based on the prediction task data and the current task, and establish a scenario transition interval.

[0076] Step S720: Perform linear variation update on the priority weights based on the scenario transition interval.

[0077] Step S730: Reconstruct the fitness function using the updated priority weights, and establish a buffer strategy mapped to the scenario transition interval with the reconstructed fitness function.

[0078] Step S740: Perform joint optimal scheduling management according to the buffer strategy.

[0079] Specifically, first, obtain the prediction task data of the new energy power system. These prediction task data include the prediction of energy production in the future for a period of time, such as the expected power generation of renewable energy sources like solar energy and wind energy, the prediction of energy demand, such as the electricity demand in different regions during different time periods. At the same time, it also involves the prediction of the operating status of equipment, such as the failure probability of certain key equipment. After obtaining these prediction task data, compare and analyze them with the tasks currently in progress. Consider the progress of the current task, the completed part and the uncompleted part, and combine the future trends presented by the prediction task data to conduct scenario transition analysis. For example, if the energy supply in the current task is relatively stable, but the prediction data shows that the energy demand may increase significantly in the future for a period of time, or the output of renewable energy may decrease due to weather changes, then it is necessary to conduct in-depth analysis on the transition from the current relatively stable scenario to the future scenario with supply-demand imbalance. Through the comprehensive analysis of the prediction task data and the current task, determine a scenario transition interval. This interval covers the time period from the current state to the future predicted state, as well as various intermediate states that may occur during this time period. It can help the system better understand and grasp the process of scenario change, providing an important basis for subsequent optimal scheduling decisions.

[0080] Understanding the scenario transition interval means realizing the process of changing from the current task scenario to the future predicted task scenario. During this process, the importance of different factors and goals changes, and the priority weights determine the relative importance of each goal in the joint optimal scheduling. As the scenario gradually transitions from the current state to the future state, some goals may be more important at the beginning, but their importance gradually decreases as the transition progresses; conversely, some other goals may not be crucial in the initial stage, but become extremely important when approaching the future scenario. To adapt to this change, the priority weights are updated in a linear change manner. This is like on a time axis, smoothly adjusting the weights of each goal according to the progress of the scenario transition. Set a starting weight and a final weight, and then gradually adjust the weight values according to the linear ratio according to the progress of the scenario transition interval. If at the beginning of the scenario transition interval, the stability of energy supply is the primary goal, then the corresponding priority weight is higher. But as the transition progresses, the goal of controlling energy costs or environmental sustainability becomes more important. At this time, the priority weights of these goals will gradually increase, while the weight of energy supply stability will linearly decrease accordingly. By updating the priority weights in this linear change way, the new energy power system can more flexibly respond to the changes of different goals during the scenario transition process, achieving more efficient and reasonable joint optimal scheduling management.

[0081] Reconstruct the fitness function using the updated priority weights. The fitness function plays a crucial role in the joint optimal scheduling of new energy power systems and is used to evaluate the pros and cons of different scheduling schemes. The updated priority weights reflect the changes in the importance of different objectives within the scenario transition interval. Incorporating these new weights into the fitness function enables the fitness function to more accurately measure the adaptability of the scheduling scheme under different scenarios. For example, if the reliability weight of energy supply increases during the scenario transition interval, the reconstructed fitness function will place more emphasis on the performance of the scheduling scheme in ensuring stable energy supply. Then, based on the reconstructed fitness function, establish a buffer policy that maps to the scenario transition interval. The purpose of this buffer policy is to provide a mechanism for the system to achieve a smooth transition during the scenario transition. It takes into account that the change of scenarios does not occur instantaneously but gradually evolves within a certain time interval. The buffer policy includes multiple aspects. For example, at the initial stage of the scenario transition, a more conservative scheduling scheme is adopted to ensure the stability of the system. As the transition progresses, more innovative schemes are gradually introduced to meet the new scenario requirements. At the same time, the buffer policy can also dynamically adjust the scheduling scheme according to the evaluation results of the fitness function to achieve the optimal joint optimal scheduling.

[0082] The buffer policy provides a clear guiding direction for the system during the scenario transition. It takes into account various factors and changing trends during the transition from the current task scenario to the future predicted task scenario. In the joint optimal scheduling management, the system comprehensively considers multiple factors, including energy production, transmission, distribution, and storage. According to the buffer policy, the system dynamically adjusts the operations of each link to achieve the optimal resource allocation and efficiency improvement. For example, in terms of energy production, the system adjusts the operating parameters of renewable energy generation equipment according to the buffer policy to adapt to the changing energy demand under different scenarios. If it is predicted that the future energy demand will increase, the system will increase the blade angle of wind turbines or the tilt angle of solar panels in advance to increase energy production. In the energy transmission and distribution links, the buffer policy can guide the system to optimize the operation mode of the power grid to ensure that energy can be efficiently delivered to the demand locations. This may include adjusting the voltage level of transformers, optimizing the load distribution of lines, etc. At the same time, in terms of energy storage, the buffer policy can determine when to store excess energy and when to release the stored energy to balance the supply and demand relationship. For example, when the energy supply is sufficient, the excess energy is stored for use during future energy demand peaks. By following the buffer policy for joint optimal scheduling management, the new energy power system can more smoothly cope with the challenges brought by the scenario transition, improve the reliability, stability, and efficiency of the system, and achieve the rational utilization and sustainable development of energy.

[0083] In one possible way, step S740 further includes:

[0084] Step S741: Conduct joint optimization scheduling according to the joint optimization scheduling scheme, perform consistency monitoring of scheduling responses, and establish monitoring and early warning.

[0085] Step S742: Use the monitoring and early warning to report optimization feedback, dynamically adjust the fitness function based on the optimization feedback, and regenerate the joint optimization scheduling scheme with the dynamically adjusted fitness function.

[0086] Specifically, the system will actually carry out the joint optimization scheduling of the new energy power system according to the previously determined joint optimization scheduling scheme, aiming to achieve efficient production, transmission, distribution, and storage of energy to meet the energy needs in different scenarios. Once the joint optimization scheduling starts, the system will simultaneously initiate the consistency monitoring of scheduling responses, collecting data from various links, including the actual output of energy production equipment, the load conditions of transmission lines, the energy flow at distribution nodes, and the status of storage facilities, etc. By analyzing these actual operation data, the system can determine whether the actual scheduling is consistent with the expected scheme. If a large deviation is found between the actual scheduling and the expected scheme, the system will immediately establish monitoring and early warning, which can be presented in various forms, such as sounding an alarm, displaying a warning message on the display screen, or sending a notice to relevant personnel. The purpose of the early warning is to timely remind the system management and operation personnel of potential problems so that they can quickly take corresponding measures for adjustment. After receiving the early warning, relevant personnel can quickly conduct fault troubleshooting, adjust the equipment operation parameters, or take other remedial measures to ensure that the joint optimization scheduling can return to normal as soon as possible. By performing the consistency monitoring of scheduling responses and establishing monitoring and early warning, an effective guarantee mechanism is provided for the joint optimization scheduling of the new energy power system, ensuring the stable and efficient operation of the system.

[0087] Monitoring and early warning plays an important role and provides crucial optimization feedback for the system. When the monitoring and early warning is triggered, it reports detailed information about the differences between the current scheduling situation and the expectations. These feedbacks include issues such as the deviation between the actual energy production and the expected production, abnormal losses during the energy transmission process, and uneven energy distribution. Based on these optimization feedbacks, the system starts to dynamically adjust the fitness function. The fitness function plays a core role in the joint optimization scheduling. It is used to evaluate the advantages and disadvantages of different scheduling schemes. According to the feedback information, the system will adjust various parameters and weights in the fitness function to better reflect the actual demands and problems. For example, if it is detected that the energy demand in a certain area suddenly increases and the current scheduling scheme cannot meet it, then the weight of the energy supply for this area in the fitness function will be increased to prompt the new scheduling scheme to pay more attention to the energy distribution in this area. Once the fitness function is dynamically adjusted, the system will, based on this adjusted fitness function, regenerate the joint optimization scheduling scheme. This new scheme will more specifically address the current problems and also take into account possible future changes. By continuously receiving the feedback of the monitoring and early warning and dynamically adjusting the fitness function, the system can continuously optimize the joint optimization scheduling scheme to ensure that the new energy power system always operates in an efficient and stable manner.

[0088] In a possible way, step S740 further includes:

[0089] Step S743: Establish a digital twin model of the new energy power system, and perform a visual presentation of the joint scheduling based on the digital twin model and the joint optimization scheduling scheme.

[0090] Specifically, it is of great significance to establish a digital twin model of a new energy power system. The digital twin model is a virtual mapping of the actual new energy power system, which can accurately simulate various operating states and parameters of the system. By establishing a digital twin model, data in the actual system can be obtained in real time and transmitted to the digital twin model for synchronous update, so that the digital twin model can accurately reflect the current state of the actual system. Based on the digital twin model and the joint optimization scheduling scheme, a visual presentation of the joint scheduling can be carried out. This visual presentation can be shown in various forms, such as through a three-dimensional graphic interface, a data dashboard, or virtual reality technology, etc. In the visual presentation, each component of the new energy power system can be intuitively seen, such as power generation equipment, transmission lines, distribution nodes, and storage facilities, etc. At the same time, the flow path of energy, the operating parameters of each link, and the implementation of the joint optimization scheduling scheme can also be shown. For example, through the visual presentation, the real-time power generation of different power generation equipment, the load conditions of transmission lines, and the satisfaction degree of energy demand in each region can be clearly seen. If the joint optimization scheduling scheme involves adjusting the output power of a certain power generation equipment, the visual interface can dynamically display the power change of the equipment and its impact on the entire system. This visual presentation not only helps system managers better understand and monitor the process of joint optimization scheduling, but also provides an intuitive basis for decision-making. By observing the visual interface, managers can timely discover problems, adjust scheduling strategies, and optimize future scheduling schemes.

[0091] It should be noted that the above-mentioned sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification is made. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0093] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, changes, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An energy flow-carbon flow combined optimal scheduling method for a new energy power system, characterized in that, The method includes: Connecting a new energy power system, dividing system scenarios according to the historical working data of the new energy power system, and establishing peak load period scenarios, low carbon emission period scenarios, and energy storage high efficiency period scenarios; Based on the system scenario division results, establishing the priority weights of energy flow, carbon flow, and energy storage indicators, and configuring an iterative scheme mapped to the system scenario division results; Configuring a fitness function, where the fitness function is constructed according to the priority weights; Performing population initialization, where the population includes N individuals, and each individual represents a candidate solution; Activating the fitness function through the scenario attribution of the current task to calculate the individual fitness values in the population, configuring the individual selection probabilities based on the individual fitness values, and performing the probabilistic selection of individuals in the population; Generating a crossover constraint factor and a mutation constraint factor based on the iterative scheme, reconstructing the crossover rate and mutation rate according to the iterative stage, performing data crossover of population individuals through the reconstructed crossover rate, and performing mutation operations on the offspring individuals generated by the crossover at the mutation rate to generate mutation results, and performing individual fitness elimination on the mutation results and the initialized population, and performing iterative update; Generating a combined optimal scheduling scheme according to the iterative update results; The objective functions of the fitness function include an operating cost function, an energy utilization efficiency function, a total carbon emission function, a carbon emission cost function, and an energy storage device utilization efficiency function. The fitness function is as follows: Among them, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of operating cost, energy utilization efficiency, total carbon emissions, carbon emission cost, and energy storage device utilization efficiency, respectively, and ω i = λ i ·W i , ω i is the i-th weight coefficient, λ i represents the priority weight under the current scenario, W i is the basic weight of the corresponding target, C run (x) is the operating cost function, η energy (x) is the energy utilization efficiency function, C carbon (x) is the total carbon emissions function, is the carbon emission cost function, η storage (x) is the energy storage device utilization efficiency function.

2. The energy flow-carbon flow joint optimal scheduling method for new energy power systems according to claim 1, characterized in that Reconstructing the crossover rate and mutation rate according to the iterative stage further includes: Dividing the iterative process into stages, and configuring the early iteration stage, the middle iteration stage, and the late iteration stage; Establishing an initial crossover rate and an initial mutation rate corresponding to the stage division results; Completing the reconstruction of the crossover rate through the crossover constraint factor and the initial crossover rate, and completing the reconstruction of the mutation rate according to the mutation constraint factor and the initial mutation rate.

3. The energy flow-carbon flow joint optimal scheduling method for a new energy power system according to claim 2, characterized in that, Completing the reconstruction of the crossover rate through the crossover constraint factor and the initial crossover rate, and completing the reconstruction of the mutation rate according to the mutation constraint factor and the initial mutation rate further includes: Establishing an adaptive update network for self-update. When reconstructing the crossover rate and mutation rate, activating the adaptive update network for update self-check. The update self-check includes: Reading the current iteration stage, performing an end-approximation analysis of the current stage according to the current iteration stage, and generating a stage approximation self-check result; Obtaining the search state of the previous iteration, performing a state self-check according to the search state, and establishing a state self-check result; Performing an adaptation analysis on the stage approximation self-check result and the state self-check result, completing self-check update with the adaptation analysis result, and adjusting the reconstructed crossover rate and mutation rate according to the self-check update result.

4. The energy flow-carbon flow joint optimal scheduling method for new energy power systems according to claim 1, characterized in that Performing individual fitness elimination on the mutation results and the initialized population further includes: Establishing a taboo retention set, where the taboo retention set is a set of individuals whose taboo values meet a preset threshold, and the taboo values are calculated through individual fitness values and individual offspring fitness values; Performing a sorting and screening of taboo values on the individuals in the taboo retention set, updating the sorting result to the population, and marking it as single-round iteration retention data; Continuing iterative update according to the updated population.

5. The energy flow-carbon flow joint optimal scheduling method for new energy power systems according to claim 1, characterized in that, The method further includes: Obtain the prediction task data of the new energy power system, conduct scenario transition analysis according to the prediction task data and the current task, and establish a scenario transition interval; Based on the scenario transition interval, linearly update the priority weight; Use the updated priority weight to reconstruct the fitness function, and establish a buffer strategy mapped to the scenario transition interval with the reconstructed fitness function; Conduct joint optimization scheduling management according to the buffer strategy.

6. The energy flow-carbon flow joint optimal scheduling method for a new energy power system according to claim 1, wherein The method further includes: Perform joint optimization scheduling with the joint optimization scheduling scheme, and execute the consistency monitoring of the scheduling response to establish a monitoring and early warning; Use the monitoring and early warning to report optimization feedback, and dynamically adjust the fitness function based on the optimization feedback, and regenerate the joint optimization scheduling scheme with the dynamically adjusted fitness function.

7. The energy flow-carbon flow joint optimal scheduling method for new energy power systems according to claim 1, characterized in that The method further includes: Establish a digital twin model of the new energy power system, and conduct visual presentation of joint scheduling based on the digital twin model and the joint optimization scheduling scheme.

Images