Comprehensive energy system low-carbon operation decision generation method and system

Abstract

The invention discloses a low-carbon operation decision generation method and system for an integrated energy system, and belongs to the technical field of energy system optimization operation. Therefore, the upper-layer strategy generation model can continuously optimize the generated operation strategy in different scenes, economical efficiency and operation stability are considered, operation risks caused by fluctuation of electricity price, output and the like are solved, the situation that the upper-layer decision is averagely optimal but extremely unbalanced due to neglect of uncertainty is avoided, and the method is suitable for large-scale popularization and application. The problem that the actual benefit of the optimized operation strategy is not good due to the fact that the expected optimal effect is difficult to achieve under the condition of actual scene fluctuation change in the generation of the existing integrated energy system optimized operation strategy is solved.

Description

Technical Field

[0001] This invention relates to the field of energy system optimization and operation technology, specifically to a method and system for generating low-carbon operation decisions for integrated energy systems. Background Technology

[0002] An Integrated Energy System (IES) is a multi-energy complementary and synergistically optimized energy management system capable of unified planning and coordinated operation of various energy sources such as electricity, gas, heat, and cooling. Low-carbon operation optimization of IESs has become an important approach to achieving efficient energy utilization and carbon emission reduction. Traditional IES operation optimization often aims for economic optimization, employing deterministic or static stochastic optimization models. In actual operation, energy market prices, carbon emission factors, load demand, and renewable energy output all exhibit significant fluctuations, causing deterministic model operating strategies to easily deviate from the expected optimal solution. Therefore, how to achieve risk perception and robust decision-making under uncertain conditions has become an important research direction.

[0003] Chinese Patent, Publication No. CN118822150A, Publication Date: October 22, 2024, discloses a low-carbon dispatch method for integrated energy systems based on dynamic carbon trading prices. By establishing an IES dynamic carbon trading model, it flexibly captures the fluctuations in supply and demand in the carbon trading market. Under conditions of system uncertainty, it constructs a two-layer optimization model with the goal of minimizing operating costs. The upper-layer model considers the fit to actual conditions, while the lower-layer model considers economic efficiency, thereby effectively providing time-varying carbon trading price signals and fully reflecting the supply and demand relationship of carbon emission allowances. It is quite effective in reducing imbalances such as wind curtailment, improving system efficiency, and reducing carbon emissions. Although it considers the impact of uncertainties in the actual operation of the energy system on decision-making, it does not specifically address this issue, relying only on historical data for fitting, resulting in low reliability. Summary of the Invention

[0004] This invention addresses the problem that existing integrated energy system optimization operation strategies often fail to achieve the expected optimal results due to fluctuations in actual scenarios, resulting in poor actual benefits. It provides a method and system for generating low-carbon operation decisions for integrated energy systems. By first determining the basic scenario and then using a lower-level scenario adjustment model to simulate subsequent operation scenarios, the upper-level strategy generation model can continuously optimize the generated operation strategy under different scenarios. This balances economic efficiency and operational stability, addresses the operational risks caused by fluctuations in electricity prices and power output, and avoids the problem of average optimality but extreme imbalance in upper-level decisions due to neglecting uncertainty.

[0005] In a first aspect, one technical solution provided in the embodiments of the present invention is: a method for generating low-carbon operation decisions for an integrated energy system, comprising the following steps: S1. Collect the configuration parameters of the integrated energy system and determine the basic optimization scenario based on the configuration parameters; S2. Under the basic optimization scenario, an upper-level decision generation model is constructed with the goal of minimizing the net operating cost, carbon emissions, and negative adjustment flexibility of the integrated energy system; a lower-level scenario adjustment model is constructed with the goal of minimizing the fluctuation of operating losses of the integrated energy system when it is dynamically changing under the basic optimization scenario. S3. Based on the data collaborative transmission mechanism, a two-layer stochastic optimization model is constructed by associating the upper-layer decision generation model and the lower-layer scenario adjustment model. S4. Solve the two-level stochastic optimization model based on the collaborative solution mechanism to obtain the optimal decision for low-carbon operation.

[0006] This solution ensures that the basic scenario accurately reflects the system's hardware conditions and operating environment by collecting configuration parameters, providing a data foundation for subsequent multi-scenario adjustments and strategy modifications. By discussing losses at the upper level and strategy stability at the lower level, it focuses on the long-term economic efficiency and low-carbon operation of the system, thus preventing the upper-level decision from deviating from the expected situation due to ignoring uncertainties. This also resolves the problem of solution complexity and optimization imbalance caused by the multi-objective mixture in traditional single-layer models. Through a data collaborative transmission mechanism, the upper-level and lower-level models are linked, allowing the decision to not only meet the requirement of minimizing static losses but also adapt to dynamic fluctuations, thereby significantly improving the reliability of the decision. Through collaborative solving, the final decision takes into account economy, low carbon emissions, and flexibility, adapting to the economic incentive logic of the carbon market and achieving a triple balance of economic feasibility, low-carbon compliance, and operational safety.

[0007] Preferably, in S1, the configuration parameters of the integrated energy system include basic timing parameters, equipment parameters, and economic market parameters; The basic timing parameters include system operating cycle, load sequence, and renewable power; The equipment parameters include system equipment capacity, equipment output, carbon capture capacity, product generation capacity, and equipment consumption. The economic market parameters include electricity prices, gas prices, system product prices, carbon prices, and equipment maintenance prices.

[0008] In this solution, basic time-series parameters provide data support for dynamic changes in the scenario, adapting to renewable power output and load fluctuations; equipment parameters are directly linked to emission and flexibility targets, ensuring accurate accounting for key aspects such as carbon capture and product generation; economic market parameters connect tiered carbon pricing and cost accounting. These three parameters provide accurate data input for subsequent upper-level decision-making and lower-level risk assessment, making the two-level optimization more targeted, thereby improving the adaptability and feasibility of the final decision.

[0009] As a preferred option, in S2, a higher-level decision generation model is constructed with the objective of minimizing the net operating cost, carbon emissions, and negative adjustment flexibility of the integrated energy system, including the following steps: The net operating cost of the system is calculated based on electricity price, gas price, system product price, product output, equipment consumption, and carbon price. Carbon emissions are determined based on carbon capture volume and equipment consumption. The system's adjustment flexibility is calculated based on the equipment output under different load sequences. A high-level decision generation model is constructed with the goal of achieving the optimal overall benefits in terms of net system operating costs, carbon emissions, and system adjustment flexibility.

[0010] In this scheme, net cost calculation can integrate multiple economic market parameters, thereby connecting tiered carbon pricing with product revenue accounting and truly reflecting the commercial operating efficiency of the system; carbon emissions are linked to carbon capture volume to ensure that emission reduction effects can be quantified; adjustment flexibility is based on equipment output and load sequence calculation, which can specifically address the problem of renewable energy fluctuations. The three factors are discussed in a coordinated manner, with the goal of achieving the best overall benefit, i.e., minimizing system operating losses. This provides a precise optimization direction for the upper-level model, ensuring the scientific nature and feasibility of the final decision.

[0011] As a preferred option, in S2, a lower-level scenario adjustment model is constructed with the objective of minimizing the fluctuation of operational losses of the integrated energy system under dynamic changes in the basic optimization scenario. This includes the following steps: Using the configuration parameters of the integrated energy system as scenario variables, historical configuration parameters of the integrated energy system are collected, and the standard deviation of each scenario variable is calculated. A covariance matrix is ​​constructed using the standard deviation of each scenario variable as the diagonal, and the covariance matrix is ​​randomly perturbed using a multivariate normal distribution to obtain the time-by-time variable values ​​of each variable as different scenario arrays; Calculate the system operating loss under different scenario arrays, and construct a lower-level scenario adjustment model with the goal of minimizing the fluctuation range of the system operating loss under different scenarios.

[0012] In this scheme, the covariance matrix is ​​constructed to reflect the correlation of various variables, avoiding the one-sidedness of traditional independent scenarios. The covariance matrix is ​​randomly perturbed by a multivariate normal distribution, thus comprehensively covering parameter fluctuations and making the generated scenario array realistic and comprehensive. By aiming to minimize loss fluctuations, the risk control logic during scenario fluctuations is reflected, thereby accurately suppressing losses in extreme scenarios. This provides objective risk feedback for upper-level decision-making, avoiding the occurrence of average optimality but extreme imbalance. At the same time, it reduces the solution complexity of the model, making the risk assessment of the two-layer optimization more accurate and the decision more robust, and significantly improving the feasibility of engineering implementation.

[0013] Preferably, in S3, the data collaborative transmission mechanism specifically includes: The upper-level decision generation model sends the generated upper-level decisions down to the lower-level scenario adjustment model. The lower-level scenario adjustment model adjusts the basic optimized scenario at each time and calculates the actual operating loss of the integrated energy system under the upper-level decision after adjustment. The upper-level decision generation model optimizes the upper-level decisions based on the actual operating losses of the integrated energy system, and then distributes the optimized upper-level decisions to the lower-level scenario adjustment model.

[0014] In this solution, a data collaborative transmission mechanism is used to send upper-level decisions to the lower level in real time, ensuring that the lower-level scenario adjustments closely follow the actual decisions. Meanwhile, the actual operational losses reported by the lower level provide the upper level with accurate risk and performance feedback, avoiding the shortcomings of traditional model decisions being out of touch with reality. This achieves two-way dynamic iteration, allowing decisions to adapt to scenario fluctuations and ensuring the overall optimal balance between net cost, carbon emissions, and flexibility. It enables efficient linkage between the two-layer models, significantly improving the accuracy, robustness, and engineering feasibility of decisions.

[0015] As a preferred option, in S4, the optimal decision for low-carbon operation is obtained by solving the two-level stochastic optimization model based on a collaborative solution mechanism, including the following steps: Under preset constraints, N system operation strategies are randomly generated as initial populations, and the operating loss of each initial population is calculated as the fitness value based on the upper objective function. For the i populations with the smallest fitness values, the model is adjusted in the lower-level scene to generate the corresponding dynamic scene and the fluctuation of fitness values ​​over time is recorded. The n populations with the smallest fluctuation amplitude are used as the parent populations. The upper-level decision generation model performs crossover and mutation operations on the parent population to obtain N offspring solutions as the offspring population, and repeats the above steps until the change in the stress value fluctuation amplitude in the lower-level scenario adjustment model is less than or equal to the change threshold for a consecutive iterations. The system operation strategy corresponding to the parent population at the last iteration is taken as the optimal decision for low-carbon operation.

[0016] In this scheme, an initial population can be randomly generated to cover multiple operating schemes. The initially generated schemes are initially screened by fitness values, and the better-performing populations are sent down to the lower-level model for risk analysis. The risk analysis results are then returned to the upper-level model, where these populations are cross-crossed and mutated to retain the best variable parameters. Through continuous iteration, the optimal operating strategy is finally obtained at both the upper and lower levels. This makes the decision-making process economical, low-carbon, and robust, significantly improving the reliability and adaptability of engineering implementation.

[0017] Preferably, the crossover and mutation operations performed on the parent population specifically include: The parent populations are randomly paired up, and the policy variables in the system operation strategy of each pair of parent populations are randomly swapped to complete the crossover operation. A random number is introduced for each policy variable, and the values ​​of each policy variable are adjusted based on the random number to complete the mutation operation.

[0018] In this scheme, random pairwise crossover not only integrates the superior strategy characteristics of the parent generation but also retains the file decision genes. By introducing random number mutation, the limitations of a single strategy are broken, new optimization spaces are explored, and the algorithm is prevented from getting trapped in local optima. The combination of the two allows the offspring population to inherit the risk resistance of the parent generation while also possessing new optimization potential, which helps to search for more comprehensive Pareto solutions. This meets the collaborative needs of upper-level multi-objectives and lower-level risk control, and improves the optimality and adaptability of the final decision.

[0019] Secondly, one technical solution provided in this embodiment of the invention is: a low-carbon operation decision generation system for integrated energy systems, comprising a data acquisition and processing module, an upper-level decision module, a lower-level scenario adjustment module, a data collaborative transmission module, and a decision generation module; The data acquisition and processing module collects the configuration parameters of the integrated energy system and determines the basic optimization scenario based on the configuration parameters; The upper-level decision-making process, under the basic optimization scenario, is equipped with an upper-level decision-making generation model that aims to minimize the net operating cost, carbon emissions, and negative adjustment flexibility of the integrated energy system. The lower-level scenario adjustment module is equipped with a lower-level scenario adjustment model that aims to minimize the overall risk of the integrated energy system operating under dynamic changes in the basic optimized scenario. The data collaborative transmission module, based on the data collaborative transmission mechanism, associates the upper-level decision generation model and the lower-level scenario adjustment model to construct a two-layer stochastic optimization system. The decision generation module uses a collaborative solution mechanism to collaboratively solve the two-layer stochastic optimization system to obtain the optimal decision for low-carbon operation.

[0020] In this solution, a corresponding system is built to integrate the low-carbon operation decision generation method, thereby enabling human-computer interaction and improving the user experience.

[0021] Thirdly, one technical solution provided in this embodiment of the invention is: a computer device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store computer programs; the processor is used to execute the program stored in the memory to implement the steps of a method for generating low-carbon operation decisions for an integrated energy system.

[0022] Fourthly, one technical solution provided in this embodiment of the invention is: a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of a method for generating low-carbon operation decisions for an integrated energy system.

[0023] The beneficial effects of this invention are as follows: This invention first determines the basic scenario and then uses the lower-level scenario adjustment model to simulate the subsequent operation scenario, so that the upper-level strategy generation model can continuously optimize the generated operation strategy under different scenarios, thereby taking into account both economy and operation stability, solving the operation risks caused by fluctuations in electricity prices and power output, and avoiding the problem of average optimality but extreme imbalance in upper-level decision-making due to ignoring uncertainty.

[0024] The above description of the invention is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0025] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0026] Figure 1 This is a flowchart of a method for generating low-carbon operation decisions for an integrated energy system according to the present invention. Figure 2 This is a schematic diagram of a low-carbon operation decision generation system for an integrated energy system according to the present invention; Figure 3 A schematic diagram of the structure of the computer device provided by the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only one preferred embodiment of this invention and are only used to explain this invention. They do not limit the scope of protection of this invention. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0028] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations (or steps) can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it may also have additional steps not included in the figures; the process may correspond to a method, function, procedure, subroutine, subroutine, etc.

[0029] Example 1: As Figure 1 As shown, in order to address the problem that existing integrated energy system optimization operation strategies often fail to achieve the expected optimal results due to fluctuations in actual scenarios, resulting in poor actual benefits, this embodiment provides a method for generating low-carbon operation decisions for integrated energy systems, including the following steps: S1: Collect configuration parameters of the integrated energy system and determine the basic optimization scenario based on the configuration parameters.

[0030] In this embodiment, the configuration parameters of the integrated energy system include basic timing parameters, equipment parameters, and economic market parameters; The basic timing parameters include system operating cycle, load sequence, and renewable power; The equipment parameters include system equipment capacity, equipment output, carbon capture capacity, product generation capacity, and equipment consumption. The economic market parameters include electricity prices, gas prices, system product prices, carbon prices, and equipment maintenance prices.

[0031] The basic time-series parameters in this embodiment provide data support for dynamic changes in the scenario, adapting to fluctuations in renewable power output and load; equipment parameters are directly related to emission and flexibility targets, ensuring accurate calculations for key aspects such as carbon capture and product generation; economic market parameters connect tiered carbon pricing and cost accounting. These three parameters provide accurate data input for subsequent upper-level decision-making and lower-level risk assessment, making the two-level optimization more targeted, thereby improving the adaptability and feasibility of the final decision.

[0032] S2: Under the basic optimization scenario, an upper-level decision generation model is constructed with the goal of minimizing the net operating cost, carbon emissions, and negative adjustment flexibility of the integrated energy system; a lower-level scenario adjustment model is constructed with the goal of minimizing the fluctuation of operating losses of the integrated energy system when it is dynamically changing under the basic optimization scenario.

[0033] In this embodiment, an upper-level decision generation model is constructed with the goal of minimizing the net operating cost, carbon emissions, and negative adjustment flexibility of the integrated energy system, including the following steps: The net operating cost of the system is calculated based on electricity price, gas price, system product price, product output, equipment consumption, and carbon price. Carbon emissions are determined based on carbon capture volume and equipment consumption. The system's adjustment flexibility is calculated based on the equipment output under different load sequences. A high-level decision generation model is constructed with the goal of achieving the optimal overall benefits in terms of net system operating costs, carbon emissions, and system adjustment flexibility.

[0034] Specifically, the decision vector is first defined based on the configuration parameters of the energy system. In this embodiment, eight main parameters are selected as the decision vector, as follows: in, Renewable energy installed capacity (kW); Electrolyzer capacity (kW); Hydrogen storage capacity (kg); Carbon capture rate; The capacity of the electro-gas conversion device (kW); The blending ratio of natural gas; For ammonia synthesis efficiency; For oxygen concentration fraction in oxygen-enriched combustion, all of the above data can be directly collected and calculated by macros based on the configured parameters. The upper-level objective function is: in The net operating cost of the system, For carbon emissions, To ensure system flexibility, since the objective function takes a minimum value, the flexibility is taken as a negative number.

[0035] This embodiment integrates multiple economic market parameters through net cost calculation, thereby connecting tiered carbon pricing with product revenue accounting and truly reflecting the system's commercial operating efficiency. Carbon emissions are tied to carbon capture volume, ensuring that emission reduction effects are quantifiable. Adjustment flexibility is based on equipment output and load sequence calculations, which can specifically address the issue of renewable energy fluctuations. The three factors are discussed in synergy, with the goal of achieving optimal overall benefits, i.e., minimizing system operating losses. This provides a precise optimization direction for the upper-level model, ensuring the scientific nature and feasibility of the final decision.

[0036] In this embodiment, a lower-level scenario adjustment model is constructed with the objective of minimizing the fluctuation of operational losses of the integrated energy system when the basic optimization scenario dynamically changes. The model includes the following steps: Using the configuration parameters of the integrated energy system as scenario variables, historical configuration parameters of the integrated energy system are collected, and the standard deviation of each scenario variable is calculated. A covariance matrix is ​​constructed using the standard deviation of each scenario variable as the diagonal, and the covariance matrix is ​​randomly perturbed using a multivariate normal distribution to obtain the time-by-time variable values ​​of each variable as different scenario arrays; Calculate the system operating loss under different scenario arrays, and construct a lower-level scenario adjustment model with the goal of minimizing the fluctuation range of the system operating loss under different scenarios.

[0037] Specifically, the formula for the covariance matrix is ​​as follows: in, Let be the standard deviation of the scene variables. Each scene variable can be represented by a covariance matrix. This is the empirical correlation coefficient matrix between variables, which can be selected according to the actual situation.

[0038] Random perturbations are generated based on a multivariate normal distribution, and then the perturbations are mapped to the actual distributions of each variable through distribution transformation (e.g., converting a normal perturbation into a log-normal distribution of electricity prices), ultimately resulting in an array of N scenarios: Each scene Each of them contains the value of each variable at each moment of every hour.

[0039] For each scenario Based on the equipment parameters determined by the upper-level decision vector, the net operating cost, carbon emissions, and system adjustment flexibility of the system are calculated at each time step.

[0040] The net operating cost of the system = basic cost - revenue + carbon cost; carbon emissions = fossil fuel emissions + emissions implied by purchased energy - CCS capture; system regulation flexibility = (energy storage regulation contribution + equipment ramp-up contribution) / load fluctuation range; all the above calculation parameters are based on the basic system parameters.

[0041] To further reflect the overall risk of the decision-making process, it is necessary to statistically analyze the net operating cost, carbon emissions, and system adjustment flexibility across N scenarios to assess the average performance of the decision. This requires quantifying the tail risk of the net cost using dynamic CVaR to obtain the target value for feedback to the upper layers. First, a sample set is obtained by statistically analyzing various indicators across the N scenarios: Where C is the net cost sample, E is the carbon emission sample, and F is the flexibility sample; The formula for calculating the sample mean of net cost is as follows: Then, calculate the CvaR of the net cost sample according to the CVaR calculation principle. Finally, the target net cost is obtained by dynamically weighting the samples: in The risk coefficient is determined by time, with a larger value used during peak periods and a smaller value used during off-peak periods.

[0042] The target carbon emissions and target flexibility are obtained by simply averaging the average carbon emissions and the average flexibility. The target net cost, target carbon emissions, and target flexibility are then fed back to the upper-level strategy generation model to complete the closed-loop feedback of the data.

[0043] This embodiment constructs a covariance matrix to reflect the correlation of various variables, avoiding the one-sidedness of traditional independent scenarios. It also uses a multivariate normal distribution to randomly perturb the covariance matrix, thereby comprehensively covering parameter fluctuations and making the generated scenario array realistic and comprehensive. By aiming to minimize loss fluctuations, it reflects the risk control logic when scenarios fluctuate, thus accurately suppressing losses in extreme scenarios. This provides objective risk feedback for upper-level decision-making, avoiding the occurrence of average optimality but extreme imbalance. It also reduces the solution complexity of the model, making the risk assessment of the two-layer optimization more accurate and the decision more robust, significantly improving the feasibility of engineering implementation.

[0044] S3: Based on the data collaborative transmission mechanism, a two-layer stochastic optimization model is constructed by associating the upper-layer decision generation model and the lower-layer scenario adjustment model.

[0045] In this embodiment, the data collaborative transmission mechanism specifically includes: The upper-level decision generation model sends the generated upper-level decisions down to the lower-level scenario adjustment model. The lower-level scenario adjustment model adjusts the basic optimized scenario at each time and calculates the actual operating loss of the integrated energy system under the upper-level decision after adjustment. The upper-level decision generation model optimizes the upper-level decisions based on the actual operating losses of the integrated energy system, and then distributes the optimized upper-level decisions to the lower-level scenario adjustment model.

[0046] This embodiment uses a data collaborative transmission mechanism to send upper-level decisions to the lower level in real time, ensuring that the lower-level scenario adjustments closely follow the actual decisions. Meanwhile, the actual operational losses reported by the lower level provide the upper level with accurate risk and performance feedback, avoiding the shortcomings of traditional model decisions being out of touch with reality. This achieves bidirectional dynamic iteration, allowing decisions to adapt to scenario fluctuations and ensuring the overall optimal balance between net cost, carbon emissions, and flexibility. It enables efficient linkage between the two-layer models, significantly improving the accuracy, robustness, and engineering feasibility of decisions.

[0047] S4: Solve the two-level stochastic optimization model based on the collaborative solution mechanism to obtain the optimal decision for low-carbon operation.

[0048] In this embodiment, the optimal decision for low-carbon operation is obtained by solving the two-level stochastic optimization model based on a collaborative solution mechanism, including the following steps: Under preset constraints, N system operation strategies are randomly generated as initial populations, and the operating loss of each initial population is calculated as the fitness value based on the upper objective function. For the i populations with the smallest fitness values, the model is adjusted in the lower-level scene to generate the corresponding dynamic scene and the fluctuation of fitness values ​​over time is recorded. The n populations with the smallest fluctuation amplitude are used as the parent populations. The upper-level decision generation model performs crossover and mutation operations on the parent population to obtain N offspring solutions as the offspring population, and repeats the above steps until the change in the stress value fluctuation amplitude in the lower-level scenario adjustment model is less than or equal to the change threshold for a consecutive iterations. The system operation strategy corresponding to the parent population at the last iteration is taken as the optimal decision for low-carbon operation.

[0049] This embodiment can cover multiple operational schemes by randomly generating an initial population. The initial generated schemes are initially screened by fitness values, and the better-performing populations are sent down to the lower-level model for risk analysis. The risk analysis results are then returned to the upper-level model, where these populations are cross-crossed and mutated to retain excellent variable parameters. Through continuous iteration, the optimal operational strategy is finally obtained at both the upper and lower levels, making the decision-making process economical, low-carbon, and robust, and significantly improving the reliability and adaptability of engineering implementation.

[0050] In this embodiment, the crossover and mutation operations performed on the parent population specifically include: The parent populations are randomly paired up, and the policy variables in the system operation strategy of each pair of parent populations are randomly swapped to complete the crossover operation. A random number is introduced for each policy variable, and the values ​​of each policy variable are adjusted based on the random number to complete the mutation operation.

[0051] Specifically, the formula for crossover is expressed as follows: for a pair of parent populations Perform cross-validation on each of the eight decision variables to generate random numbers. If the random number is less than or equal to 0.5, then the crossover factor is... If the random number is greater than 0.5, then the crossover factor is... The resulting offspring solution is: Then, for each decision variable in each sub-solution, generate random numbers. If random number If the mutation rate is less than or equal to the preset mutation rate, then mutation is performed, and the mutated offspring are represented as follows: in For a given crossover, the child solution is... and These represent the upper and lower bounds of the values ​​of each decision variable in the sub-solution. As a variable factor, it is preset according to the actual situation.

[0052] This embodiment, through random pairwise crossover, not only integrates the superior strategy characteristics of the parent generation but also retains the file decision genes. By introducing random number mutation, it breaks the limitations of a single strategy, explores new optimization spaces, and avoids the algorithm getting trapped in local optima. The combination of the two allows the offspring population to inherit the risk resistance capabilities of the parent generation while possessing new optimization potential, helping to search for more comprehensive Pareto solutions. This aligns with the collaborative needs of upper-level multi-objectives and lower-level risk control, improving the optimality and adaptability of the final decision.

[0053] Example 2: As Figure 2 As shown, this embodiment also provides a low-carbon operation decision generation system for integrated energy systems, including a data acquisition and processing module, an upper-level decision module, a lower-level scenario adjustment module, a data collaborative transmission module, and a decision generation module; The data acquisition and processing module collects the configuration parameters of the integrated energy system and determines the basic optimization scenario based on the configuration parameters; The upper-level decision-making process, under the basic optimization scenario, is equipped with an upper-level decision-making generation model that aims to minimize the operational losses of the integrated energy system. The lower-level scenario adjustment module is equipped with an upper-level decision generation model that aims to minimize the net operating cost, carbon emissions, and negative adjustment flexibility of the integrated energy system. The data collaborative transmission module, based on the data collaborative transmission mechanism, associates the upper-level decision generation model and the lower-level scenario adjustment model to construct a two-layer stochastic optimization system. The decision generation module uses a collaborative solution mechanism to collaboratively solve the two-layer stochastic optimization system to obtain the optimal decision for low-carbon operation.

[0054] By constructing a corresponding system to integrate the low-carbon operation decision generation method in this solution, human-computer interaction is achieved, improving the user experience.

[0055] The embodiments also provide a computer device, such as Figure 3 As shown, it includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory is used to store computer programs; When the processor executes the program stored in memory, it implements a method for generating low-carbon operation decisions for an integrated energy system.

[0056] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0057] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0058] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0059] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be 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, or discrete hardware components.

[0060] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a method for generating low-carbon operation decisions for an integrated energy system.

[0061] As can be seen from the above embodiments, it has at least the following substantial effects: (1) By collecting configuration parameters, this invention ensures that the basic scenario can truly reflect the system hardware conditions and operating environment, providing a data foundation for subsequent multi-scenario adjustment and strategy adjustment; (2) This invention focuses on the economic efficiency and low carbon emissions of the system’s long-term operation by discussing loss at the upper level and strategy stability at the lower level, thereby avoiding the deviation of the upper-level decision from the expected situation due to ignoring uncertainty, and resolving the problem of solution complexity and optimization imbalance caused by the multi-objective mixture of traditional single-level models. (3) This invention associates the upper-level model and the lower-level model through a data collaborative transmission mechanism, so that the decision can not only meet the requirement of minimum static loss, but also adapt to dynamic fluctuations, thereby significantly improving the reliability of the decision. (4) Through collaborative solution, the present invention makes the final decision take into account economy, low carbon and flexibility, adapts to the economic incentive logic of carbon market, and achieves a triple balance of economic feasibility, low carbon compliance and safe operation.

[0062] The specific embodiments described above are preferred embodiments of the integrated energy system low-carbon operation decision generation method and system of the present invention, and are not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to the specific embodiments described above. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A method for generating low-carbon operation decisions for an integrated energy system, characterized in that: Includes the following steps: S1. Collect the configuration parameters of the integrated energy system and determine the basic optimization scenario based on the configuration parameters; S2. Under the basic optimization scenario, construct an upper-level decision generation model with the goal of minimizing the net operating cost of the integrated energy system, carbon emissions, and negative adjustment flexibility. A lower-level scenario regulation model is constructed with the goal of minimizing the fluctuation of operating losses of the integrated energy system when the basic optimization scenario changes dynamically. S3. Based on the data collaborative transmission mechanism, a two-layer stochastic optimization model is constructed by associating the upper-layer decision generation model and the lower-layer scenario adjustment model. S4. Solve the two-level stochastic optimization model based on the collaborative solution mechanism to obtain the optimal decision for low-carbon operation.

2. The method for generating low-carbon operation decisions for an integrated energy system according to claim 1, characterized in that: In S1, the configuration parameters of the integrated energy system include basic timing parameters, equipment parameters, and economic market parameters; The basic timing parameters include system operating cycle, load sequence, and renewable power; The equipment parameters include system equipment capacity, equipment output, carbon capture capacity, product generation capacity, and equipment consumption. The economic market parameters include electricity prices, gas prices, system product prices, carbon prices, and equipment maintenance prices.

3. The method for generating low-carbon operation decisions for an integrated energy system according to claim 2, characterized in that: In S2, an upper-level decision generation model is constructed with the goal of minimizing the net operating cost, carbon emissions, and negative adjustment flexibility of the integrated energy system. This includes the following steps: The net operating cost of the system is calculated based on electricity price, gas price, system product price, product output, equipment consumption, and carbon price. Carbon emissions are determined based on carbon capture volume and equipment consumption. The system's adjustment flexibility is calculated based on the equipment output under different load sequences. A high-level decision generation model is constructed with the goal of achieving the optimal overall benefits in terms of net system operating costs, carbon emissions, and system adjustment flexibility.

4. The method for generating low-carbon operation decisions for an integrated energy system according to claim 1, characterized in that: In S2, a lower-level scenario adjustment model is constructed with the objective of minimizing the fluctuation of operational losses of the integrated energy system under dynamic changes in the basic optimization scenario. This includes the following steps: Using the configuration parameters of the integrated energy system as scenario variables, historical configuration parameters of the integrated energy system are collected, and the standard deviation of each scenario variable is calculated. A covariance matrix is ​​constructed using the standard deviation of each scenario variable as the diagonal, and the covariance matrix is ​​randomly perturbed using a multivariate normal distribution to obtain the time-by-time variable values ​​of each variable as different scenario arrays; Calculate the system operating loss under different scenario arrays, and construct a lower-level scenario adjustment model with the goal of minimizing the fluctuation range of the system operating loss under different scenarios.

5. The method for generating low-carbon operation decisions for an integrated energy system according to claim 1, characterized in that: In S3, the data collaborative transmission mechanism specifically includes: The upper-level decision generation model sends the generated upper-level decisions down to the lower-level scenario adjustment model. The lower-level scenario adjustment model adjusts the basic optimized scenario at each time and calculates the actual operating loss of the integrated energy system under the upper-level decision after adjustment. The upper-level decision generation model optimizes the upper-level decisions based on the actual operating losses of the integrated energy system, and then distributes the optimized upper-level decisions to the lower-level scenario adjustment model.

6. The method for generating low-carbon operation decisions for an integrated energy system according to claim 3, characterized in that: In S4, the optimal decision for low-carbon operation is obtained by solving the two-level stochastic optimization model based on the collaborative solution mechanism, including the following steps: Under preset constraints, N system operation strategies are randomly generated as initial populations, and the operating loss of each initial population is calculated as the fitness value based on the upper objective function. For the i populations with the smallest fitness values, the model is adjusted in the lower-level scene to generate the corresponding dynamic scene and the fluctuation of fitness values ​​over time is recorded. The n populations with the smallest fluctuation amplitude are used as the parent populations. The upper-level decision generation model performs crossover and mutation operations on the parent population to obtain N offspring solutions as the offspring population, and repeats the above steps until the change in the stress value fluctuation amplitude in the lower-level scenario adjustment model is less than or equal to the change threshold for a consecutive iterations. The system operation strategy corresponding to the parent population at the last iteration is taken as the optimal decision for low-carbon operation.

7. The method for generating low-carbon operation decisions for an integrated energy system according to claim 6, characterized in that: The specific steps of performing crossover and mutation operations on the parent population include: The parent populations are randomly paired up, and the policy variables in the system operation strategy of each pair of parent populations are randomly swapped to complete the crossover operation. A random number is introduced for each policy variable, and the values ​​of each policy variable are adjusted based on the random number to complete the mutation operation.

8. A low-carbon operation decision generation system for an integrated energy system, applicable to the low-carbon operation decision generation method for an integrated energy system as described in any one of claims 1-7, characterized in that: It includes a data acquisition and processing module, an upper-level decision-making module, a lower-level scene adjustment module, a data collaborative transmission module, and a decision generation module; The data acquisition and processing module collects the configuration parameters of the integrated energy system and determines the basic optimization scenario based on the configuration parameters; The upper-level decision-making process, under the basic optimization scenario, is equipped with an upper-level decision-making generation model that aims to minimize the operational losses of the integrated energy system. The lower-level scenario adjustment module is equipped with a lower-level scenario adjustment model that aims to minimize the overall risk of the integrated energy system operating under dynamic changes in the basic optimized scenario. The data collaborative transmission module, based on the data collaborative transmission mechanism, associates the upper-level decision generation model and the lower-level scenario adjustment model to construct a two-layer stochastic optimization system. The decision generation module uses a collaborative solution mechanism to collaboratively solve the two-layer stochastic optimization system to obtain the optimal decision for low-carbon operation.

9. A computer device, characterized in that: The system includes a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer programs. When the processor executes the program stored in the memory, it implements the steps of the integrated energy system low-carbon operation decision generation method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for generating low-carbon operation decisions for an integrated energy system as described in any one of claims 1-7.

Images