Air carbon emission reduction planning method and device, electronic equipment and storage medium

Abstract

The application provides an aviation carbon emission reduction planning method and device, electronic equipment and storage medium, and relates to the technical field of aviation carbon emission reduction planning. The method comprises collecting historical data, wherein the historical data comprises historical passenger demand data; based on the historical passenger demand data, a passenger demand prediction interval is generated by combining a prediction model and a Monte Carlo simulation; different decision level models are constructed for different decision levels of aviation carbon emission reduction; based on decision variables and constraint conditions of different decision levels, the different decision levels are independently solved by a genetic algorithm to obtain independent reference values of the different decision levels; a global satisfaction function is constructed based on the independent reference values of the different decision levels, and the global satisfaction function is iteratively optimized by the genetic algorithm to obtain a balanced optimal solution. The application plans aviation carbon emission reduction through different decision levels, and can solve the problems of multi-level decision and multiple uncertainties in aviation carbon emission reduction planning.

Description

Technical Field

[0001] This application relates to the field of aviation carbon emission reduction planning technology, and in particular to an aviation carbon emission reduction planning method, device, electronic device and storage medium. Background Technology

[0002] Aviation carbon emission reduction management is a complex system involving multiple stakeholders, multiple objectives, and inherent uncertainties. Its decision-making process exhibits a significant hierarchical structure and interactive characteristics. In terms of system composition, the air transport chain encompasses multiple stakeholders, including government regulatory bodies, numerous airlines, and a large number of consumers. These parties are closely linked through operations, regulation, and consumption behavior, pursuing their own differentiated goals while simultaneously achieving the overall function of air transport. Secondly, government emission reduction policies, airline operational decisions, and consumer travel choices are all influenced by various internal and external factors, such as external market fluctuations, technological conditions, resource constraints, and individual preferences. Simultaneously, air transport activities themselves have a significant impact on global climate and the environment. Furthermore, key indicators such as passenger demand, emission reduction costs (sustainable aviation fuel or carbon trading), and technical parameters all exhibit objective uncertainties during the decision-making process, while the risk preferences and value judgments of different decision-makers also present subjective uncertainties. Therefore, aviation carbon emission reduction planning simultaneously possesses the characteristics of multi-layered decision-making entities and a highly uncertain decision-making environment; the behavior of one party will influence the strategy choices and goal achievement of another, potentially leading to decision-making imbalances.

[0003] In existing technologies, research on aviation emission reduction pathway optimization employs single-objective or multi-objective programming. These methods typically simplify the problem into a single unified objective, neglecting the interaction mechanisms and conflicts of interest among governments, airlines, and consumers as independent decision-makers. In the management process, traditional methods often focus solely on a single objective, lacking consideration for the overall system benefits and the synergy of satisfaction among all parties. They struggle to achieve an effective balance between ensuring aviation service supply, controlling operating costs, and achieving emission reduction targets. With the advancement of global carbon neutrality and the increasing complexity of the aviation market, the scale and hierarchical structure of emission reduction management issues are expanding, requiring decision-makers at different levels to make independent yet interconnected decisions based on their respective information and constraints. Against this backdrop, traditional single-level optimization or static multi-objective programming techniques are no longer sufficient to effectively address these challenges. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for aviation carbon emission reduction planning, which at least to some extent overcomes the problems of multi-layer decision-making and multiple uncertainties in aviation carbon emission reduction planning due to the limitations of related technologies.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to one aspect of this application, an aviation carbon emission reduction planning method is provided, comprising: collecting historical data, including historical passenger demand data; generating a passenger demand prediction interval based on the historical passenger demand data by combining a prediction model and Monte Carlo simulation, wherein the combined prediction model includes singular spectrum analysis, a seasonal autoregressive integrated moving average model, and a lightweight gradient booster model; constructing different decision-level models for different decision-making levels of aviation carbon emission reduction; each decision-level model includes an objective function, decision variables, and constraints; independently solving the different decision-making levels using a genetic algorithm based on the decision variables and constraints of different decision-making levels to obtain independent reference values ​​for different decision-making levels; constructing an overall satisfaction function based on the independent reference values ​​of different decision-making levels, and using a genetic algorithm to iteratively optimize the overall satisfaction function to obtain an equilibrium optimal solution.

[0007] In some embodiments, generating a passenger demand forecast interval based on historical passenger demand data by combining a forecasting model with Monte Carlo simulation includes: decomposing the historical passenger demand data using singular spectrum analysis to obtain a trend component, a seasonal component, and a residual component; forecasting the seasonal component using a seasonal autoregressive combined with a moving average model to obtain a seasonal component forecast value; forecasting the trend component using a lightweight gradient boosting model to obtain a trend component forecast value; summing the trend component forecast value and the seasonal component forecast value item by item at each time point to obtain a point forecast value for passenger demand; and generating a passenger demand forecast interval based on the historical passenger demand data and the point forecast value using a Monte Carlo random sampling method.

[0008] In some embodiments, the historical data further includes airline operation data, market demand data, policy and market data, techno-economic parameters, and consumer behavior data; the airline operation data includes aircraft type and fleet composition, flight frequency, flight distance, SAF usage and its carbon emission factor, and fixed and variable operating costs; the market demand data includes historical passenger throughput time series, seasonality, and trend characteristics; the policy and market data includes carbon trading market mechanisms, carbon quota allocation rules, and pollutant emission standards; the techno-economic parameters include the upper limit of SAF blending ratio, fuel prices of conventional fuel and SAF, carbon trading prices, cost coefficients, and environmental carrying capacity indicators; and the consumer behavior data includes fare sensitivity coefficients, punctuality sensitivity coefficients, and demand elasticity parameters.

[0009] In some embodiments, constructing an overall satisfaction function based on independent reference values ​​at different decision levels includes: using the independent reference values ​​as a benchmark to set tolerance ranges for different decision levels; constructing satisfaction functions based on the tolerance ranges of different decision levels respectively; and constructing an overall satisfaction function by aggregating the satisfaction functions of different decision levels.

[0010] In some embodiments, the different decision-making level models are upper-level models, middle-level models, and lower-level models; the objective function of the upper-level model is to minimize environmental costs, and the constraints of the upper-level model are total carbon quota limits, SAF environmental carrying capacity constraints, and tradable quota constraints; the objective function of the middle-level model is to maximize airline operating revenue, and the constraints of the middle-level model are quota constraints, carbon trading constraints, airline capacity constraints, supply and demand constraints, and an upper limit on the SAF blending ratio; the objective function of the lower-level model is to maximize consumer utility, and the constraints of the lower-level model are ticket price and punctuality sensitivity constraints, ticket price policy constraints, and demand elasticity constraints; the objective function of the upper-level model is... The objective function of the middle-layer model is: The objective function of the lower-level model is: The constraints are: ;in, Represents a range of values. This represents the maximum value of the upper-level objective function. This represents the maximum value of the mid-level objective function. This represents the maximum value of the lower-level objective function. For model parameters, For decision variables of the upper-level model, For decision variables in the mid-level model, For decision variables in the lower-level model, As a constraint, p i The maximum probability that the constraint is not satisfied, i.e., the probability of default, is given by i, which represents the i-th constraint.

[0011] In some embodiments, the satisfaction function is:

[0012] , where μ i (f i ) is the objective function f i The satisfaction level ranges from 0 to 1; f i This represents the actual calculated value of the i-th objective function. This is the ideal objective value of the objective function. Its corresponding tolerance range; t iIt is the tolerance interval radius, representing the maximum absolute range within which the target value is allowed to deviate from the ideal value. When the actual value deviates from the ideal value by more than t... i At that time, the satisfaction rate dropped to 0.

[0013] According to another aspect of this application, an aviation carbon emission reduction planning device is also provided, comprising a data acquisition module for collecting historical data, including historical passenger demand data; a generation module for acquiring the historical passenger demand data from the data acquisition module, and generating a passenger demand prediction interval based on the historical passenger demand data through a combination of prediction models and Monte Carlo simulation, wherein the combination prediction model includes singular spectrum analysis, a seasonal autoregressive integrated moving average model, and a lightweight gradient booster model; and a model building module for constructing different decision-level models for different decision-making levels of aviation carbon emission reduction. The decision-making hierarchy model includes an objective function, decision variables, and constraints; an independent solution module is used to obtain the decision variables and constraints of different decision levels in the model construction module, and to independently solve the different decision levels using a genetic algorithm based on the decision variables and constraints of different decision levels to obtain independent reference values ​​for different decision levels; and a function construction module is used to obtain the independent reference values ​​of different decision levels in the independent solution module, to construct an overall satisfaction function based on the independent reference values ​​of different decision levels, and to iteratively optimize the overall satisfaction function using a genetic algorithm to obtain the equilibrium optimal solution.

[0014] According to another aspect of this application, an electronic device is also provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute an aviation carbon reduction planning method as described above by executing the executable instructions.

[0015] According to another aspect of this application, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements an aviation carbon emission reduction planning method as described in any of the preceding claims.

[0016] According to another aspect of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements an aviation carbon reduction planning method according to any one of the above.

[0017] The technical solutions provided in the embodiments of this application include at least the following beneficial effects: This application plans aviation carbon emission reduction through different decision-making levels, which can solve the problems of multi-level decision-making and multiple uncertainties in aviation carbon emission reduction planning.

[0018] Furthermore, this method constructs different decision-making levels. By considering the complex relationship between environmental constraints, aviation operating costs, and passenger demand, it constructs a three-level decision-making model that includes the government, airlines, and consumers. The upper-level objective is to minimize environmental costs, the middle-level objective is to maximize airline operating revenue, and the lower-level objective is to maximize consumer utility. This achieves a balance of interests between carbon emission control, economic benefits, and consumer satisfaction, and realizes comprehensive management and regulation of the aviation industry's low-carbon transformation.

[0019] Furthermore, to address uncertainties at each decision-making level (such as demand fluctuations and cost changes), interval opportunity-constrained programming is employed to quantify risks and enhance the model's robustness. To achieve balanced coordination of the goals of decision-makers at each level, a satisfaction index is introduced, transforming the multi-level programming problem into an optimization problem that maximizes satisfaction, thereby obtaining an optimal solution acceptable to all parties. Ultimately, the model can output optimal fleet configuration schemes, sustainable aviation fuel blending ratios, carbon quota allocation schemes, and carbon trading strategies, achieving carbon emission control while ensuring the supply of air services.

[0020] Furthermore, this application employs the interval chance constraint programming method to address the uncertainty of parameters and the risk of constraint violation, and introduces the default probability level (p) to characterize and handle the random uncertainty in the model constraints. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0022] Figure 1 A schematic diagram of an aviation carbon emission reduction planning system is shown in an embodiment of this application.

[0023] Figure 2 A flowchart of an aviation carbon emission reduction planning method according to an embodiment of this application is shown.

[0024] Figure 3 A schematic diagram of an aviation carbon emission reduction planning device is shown in an embodiment of this application.

[0025] Figure 4 A structural block diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0026] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0027] Furthermore, the accompanying drawings are merely illustrative of this application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0028] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. The various types of data, such as personal identity data, operational data, and behavioral data related to individuals, customers, and groups, obtained in the embodiments of this application have all been authorized.

[0029] The specific implementation methods of the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0030] Figure 1 A schematic diagram of an aviation carbon emission reduction planning system according to an embodiment of this application is shown. Figure 1 As shown, the system may include planning equipment 11, a first server 12, and a second server 13.

[0031] The first server 12 may store historical data, and this application does not restrict the source of the historical data or the content thereof.

[0032] In some embodiments, historical data are derived from the China Civil Aviation Statistical Yearbook, official airline reports, OAG analysis, government website bulletins, and academic literature.

[0033] In some embodiments, the historical data includes historical passenger demand data, airline operation data, market demand data, policy and market data, technical and economic parameters, and consumer behavior data; the airline operation data includes aircraft type and fleet composition, flight frequency, flight distance, use of conventional aviation fuel and sustainable aviation fuel (SAF), and its carbon footprint. putThe data includes emission factors, fixed and variable operating costs; market demand data includes historical passenger throughput time series, seasonality and trend characteristics; policy and market data includes carbon trading market mechanisms, carbon quota allocation rules, and pollutant emission standards; technical and economic parameters include the upper limit of SAF blending ratio, fuel prices of traditional fuel and SAF, carbon trading prices, cost coefficients, and environmental carrying capacity indicators; and consumer behavior data includes fare sensitivity coefficient, punctuality sensitivity coefficient, and demand elasticity parameters.

[0034] The planning device 11 can obtain historical data from the first server 12 via the network, and the obtained historical data can be stored locally on the planning device 11.

[0035] The second server 13 is used to host the prediction model. The planning device 11 can send requests to the second server 13 via the network to apply the prediction model. The embodiments of this application do not limit the specific prediction model used. For example, the prediction model includes singular spectrum analysis, seasonal autoregressive integrated moving average model, lightweight gradient booster model, Monte Carlo simulation, etc.

[0036] For example, planning device 11 can send a request to second server 13 to generate a passenger demand forecast interval using the forecast model.

[0037] Then, the planning device 11 can construct different decision-making level models based on the prediction interval. For example, the different decision-making level models are upper-level models, middle-level models, and lower-level models.

[0038] The planning device 11 and the first server 12, and the planning device 11 and the second server 13, are connected via a network. This network can be a wired network or a wireless network. Optionally, the aforementioned wireless or wired network uses standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to a Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats including HyperText Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), and Internet Protocol Security (IPSec) can be used to encrypt all or some of the links. In other embodiments, custom and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0039] The planned device 11 can be various electronic devices, including but not limited to smartphones, tablets, laptops, desktop computers, etc.

[0040] Both the first server 12 and the second server 13 can be servers that provide various services. Optionally, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0041] Under the above system architecture, this application provides an aviation carbon emission reduction planning method, which can be executed by any electronic device with computing power.

[0042] In some embodiments, the aviation carbon emission reduction planning method provided in this application can be executed by the terminal device of the above-described system architecture; in other embodiments, the aviation carbon emission reduction planning method provided in this application can be executed by the server in the above-described system architecture; in still other embodiments, the aviation carbon emission reduction planning method provided in this application can be implemented by the terminal device and the server in the above-described system architecture through interaction.

[0043] Figure 2 This application illustrates a flowchart of an aviation carbon emission reduction planning method according to an embodiment of the present application, such as... Figure 2 As shown, the aviation carbon emission reduction planning method provided in this application embodiment includes the following steps S201 to S205.

[0044] S201. Collect historical data.

[0045] In some embodiments, historical data are derived from the China Civil Aviation Statistical Yearbook, official airline reports, OAG analysis, government website bulletins, and academic literature.

[0046] In some embodiments, the historical data may further include airline operating data, market demand data, policy and market data, technical and economic parameters, and consumer behavior data; the airline operating data includes aircraft type and fleet composition, flight frequency, flight distance, usage of conventional aviation fuel and sustainable aviation fuel (SAF), and its carbon footprint. put The data includes emission factors, fixed and variable operating costs; market demand data includes historical passenger throughput time series, seasonality, and trend characteristics; policy and market data includes carbon trading market mechanisms, carbon quota allocation rules, and pollutant emission standards; techno-economic parameters include the upper limit of SAF blending ratio, fuel prices of conventional fuels and SAF, carbon trading prices, cost coefficients, and environmental carrying capacity indicators; and consumer behavior data includes fare sensitivity coefficient, punctuality sensitivity coefficient, and demand elasticity parameter. The fare sensitivity coefficient characterizes the responsiveness of air passenger demand to changes in fares and can be obtained by constructing a demand function and performing regression analysis using historical fare and passenger volume data. The demand elasticity parameter is calculated from the demand function according to the defined elasticity formula, based on the established demand function form.

[0047] S202. Based on historical passenger demand data, a passenger demand forecast interval is generated by combining a forecast model and Monte Carlo simulation. The combined forecast model includes singular spectrum analysis, seasonal autoregressive integrated moving average model, and lightweight gradient booster model.

[0048] In this embodiment of the application, step S202 includes S2021 to S2025:

[0049] S2021. The historical passenger demand data is decomposed using Singular Spectrum Analysis (SSA) to obtain trend components, seasonal components, and residual components.

[0050] In this embodiment, the window length (L) in Singular Spectral Analysis (SSA) is not limited, but is typically 1 / 3 to 1 / 2 of the sequence length and must be an integer multiple of the seasonal cycle. The grouping strategy for SSA is also not limited; it can be automatically determined based on the singular value spectrum or set based on the inflection points of the singular value spectrum. The window length (L) is used to construct the sliding window width of the trajectory matrix, and the grouping strategy specifies the component assignments corresponding to the first few singular values.

[0051] Example using monthly passenger demand data for a certain air route:

[0052] The input data is: [85.2, 88.5, 90.1, 92.6, 95.4, 98.7, 102.3, 104.8, 107.6, 105.1, 101.3, 97.8, ..., 132.8]

[0053] (Monthly passenger demand data for 48 months, unit: 10,000 passengers);

[0054] Parameter settings: Window length L=24;

[0055] Grouping strategy: Automatically determined based on the singular value spectrum (or specified: trend component is the 1st singular value, seasonal component is the 2nd-5th singular values, and remaining component is the remaining singular values).

[0056] Output three component sequences, each with a length of 48:

[0057] Trend component sequence: [82.0, 82.8, 83.7, 84.6, 85.5, 86.4, 87.3, 88.2, 89.1, 90.0, ..., 124.2];

[0058] Seasonal component sequence: [3.2, 4.5, 6.1, 6.8, 7.9, ..., 3.6];

[0059] The remaining component sequence is: [0.0, 0.2, 0.3, 0.1, -0.1, ..., 0.0];

[0060] Verification: The error between the sum of the components and the original sequence is negligible within the range of numerical precision.

[0061] S2022. The seasonal component is predicted using the seasonal autoregressive integrated moving average model (SARIMA) to obtain the predicted value of the seasonal component.

[0062] In this embodiment of the application, the expression of the SARIMA model is as follows:

[0063] (1)

[0064] in, For non-stationary time series, such as the seasonal components obtained through SSA, It's white noise. and Autoregressive and moving averages representing seasonal components and The difference between the seasonal and trend components is represented by B, which is the shift operator. The autoregressive and moving average processes for the trend components are expressed using polynomials. and express.

[0065] Furthermore, this application does not impose restrictions on how the p, d, q, P, D, Q, and s data in the SARIMA model are set, and they can be set according to the actual data characteristics. For example, SARIMA(2,1,1)(1,1,1) 12 .

[0066] S2023. The trend component is predicted using the Lightweight Gradient Boosting Model (LightGBM) to obtain the predicted value of the trend component.

[0067] In this embodiment, the LightGBM model is used to capture and predict the passenger demand trend component obtained from singular spectral analysis decomposition. This trend component is typically influenced by various complex, nonlinear economic and operational factors, such as macroeconomic indicators, aviation industry policies, and long-term market growth. The LightGBM model fits these nonlinear relationships by integrating multiple weak learners (decision trees), and its optimization process is described as follows:

[0068] (2)

[0069] Where F(x) is the prediction function of the final ensemble. It is the optimal prediction function. F(x) is the loss function used to measure the difference between the predicted value F(x) and the true value y. For example, the loss function is the mean squared error. E represents the expectation on the distribution of the training data.

[0070] The prediction function F(x) is a linear combination of multiple weak classifiers.

[0071] (3)

[0072] Where F(x) is the prediction function for the trend component, and f(x) is the weak classifier. These are the parameters of the weak classifier.

[0073] x is a series of features, such as [time sequence, historical GDP, fuel price index, trend value of the previous 12 periods, etc.].

[0074] y is the known true trend component value obtained from historical data through SSA decomposition.

[0075] S2024. Add the trend component forecast and the seasonal component forecast values ​​one by one according to the time point to obtain the point forecast value of passenger demand.

[0076] S2025. Based on historical passenger demand and point forecast values, the passenger demand forecast interval is obtained using the Monte Carlo random sampling method.

[0077] In this embodiment, the key parameters that need to be set include:

[0078] (1) The number of Monte Carlo simulations is used to characterize the sampling accuracy of demand uncertainty. In this embodiment, it is taken as 1000 simulations.

[0079] (2) The form and parameters of random disturbance distribution. In this embodiment, it is assumed that the disturbance follows a normal distribution and its mean is set as the predicted value of demand at that time point to reflect the historical demand fluctuation range.

[0080] (3) Confidence level: In this embodiment, prediction intervals with three confidence levels of 85%, 90% and 95% are constructed respectively, and the corresponding upper and lower bounds are determined by the corresponding quantiles of the simulation results.

[0081] Example: Taking a certain point in time as an example, the predicted value of the trend component is 2.10 and the predicted value of the seasonal component is 0.29. Then the predicted value of the passenger demand at that point in time is: y = 2.10 + 0.29 = 2.39.

[0082] In the Monte Carlo simulation, y=2.39 was used as the mean of a normal distribution, and the standard deviation was set to 0.2. 1000 demand samples were randomly generated. Based on the simulation results, the prediction interval was obtained by taking the quantiles at different confidence levels. For example, at a 95% confidence level, the corresponding prediction interval was determined by the 2.5% and 97.5% quantiles.

[0083] S203. Construct different decision-making level models for different decision-making levels of aviation carbon emission reduction.

[0084] In some embodiments, the different decision-making level models are upper-level models, middle-level models, and lower-level models. The decision-making level model includes an objective function, decision variables, and constraints.

[0085] In some embodiments, the objective function of the upper-level model aims to minimize environmental costs, and the constraints of the upper-level model are total carbon quota limits, SAF environmental carrying capacity constraints, and tradable quota constraints; the objective function of the middle-level model aims to maximize airline operating revenue, and the constraints of the middle-level model are quota constraints, carbon trading constraints, airline capacity constraints, supply and demand constraints, and an upper limit on the SAF blending ratio; the objective function of the lower-level model aims to maximize consumer utility, and the constraints of the lower-level model are ticket price and punctuality sensitivity constraints, airfare pricing policy constraints, and demand elasticity constraints.

[0086] In some embodiments, the decision variables of the upper-level model are carbon quota allocation schemes, SAF blending ratio policies, and environmental carrying capacity standards; the decision variables of the middle-level model are fleet configuration schemes, flight schedules, carbon trading strategies, and airfare pricing; and the decision variables of the lower-level model are travel choices.

[0087] Furthermore, the decision variables for the upper-level model are the amount of free carbon allowances allocated to an airline, the amount of tradable carbon allowances allocated to an airline, the lower limit of SAF blending ratio, the maximum permissible water consumption, the environmental carrying capacity of solid waste, and wastewater discharge standards. The decision variables for the middle-level model are the frequency of flights operated by an airline using a certain type of aircraft during the period, the actual SAF blending ratio of the airline on that type of aircraft, the amount of carbon allowances purchased or sold by the airline, the airline's ticket pricing for that type of aircraft, and the number of that type of aircraft deployed by the airline. The decision variables for the lower-level model are the passenger demand for a particular type of aircraft operated by an airline, consumers' on-time performance requirements for the airline, and the combination of consumer choices among ticket price, on-time performance, and route.

[0088] The specific framework is as follows:

[0089] Upper-level model: (4) Middle-level model: (5)

[0090] Lower-level model: (6)

[0091] Constraints:

[0092] (7)

[0093] in, This represents the maximum value of the upper-level objective function. This represents the maximum value of the mid-level objective function. This represents the maximum value of the lower-level objective function. For model parameters, For decision variables of the upper-level model, For decision variables in the mid-level model, For decision variables in the lower-level model, Let pi be the constraint condition, pi be the maximum probability that the constraint is not satisfied, i.e., the probability of default, and i be the i-th constraint condition.

[0094] In this embodiment, These are symbolic parameters, and in practical applications, they need to be assigned values ​​based on the specific problem, data, or random process.

[0095] In this embodiment, p i The value of p is set in conjunction with the uncertainty characteristics of air passenger demand: by analyzing the random fluctuation range of demand forecasts under different scenarios, scenario assessments are performed on the probability of constraint satisfaction, thereby selecting a representative level of default probability, for example, p. i =0.05, 0.10, 0.15.

[0096] It should be noted that, in the specific implementation of this application, for the sake of unified solution, the objective functions of the upper-level model, middle-level model, and lower-level model are all processed in a maximization form during computation. For an objective function that is semantically minimization, it is equivalently transformed into a maximization optimization problem by taking the inverse of the objective function. That is, the upper-level model semantically aims to minimize environmental costs, but in the computational implementation, it is equivalently transformed into a maximization problem by taking the inverse of the objective function. For example, when the original objective function value is 10, the corresponding objective value in the maximization form is −10, and this transformation does not affect the optimal solution.

[0097] S204. Based on the decision variables and constraints of different decision levels, the genetic algorithm is used to solve the different decision levels independently to obtain independent reference values ​​for different decision levels.

[0098] In some embodiments, a genetic algorithm (GA) is used to independently optimize and solve the upper-level model, middle-level model, and lower-level model to obtain the target reference values ​​for each level of decision-makers when only their own interests are considered. Solving the upper-level model, middle-level model, and lower-level model separately yields the following results: , where i=1, 2, 3 represent the upper, middle, and lower layers, respectively.

[0099] S205. Construct an overall satisfaction function based on independent reference values ​​at different decision levels, and use a genetic algorithm to iteratively optimize the overall satisfaction function to obtain the equilibrium optimal solution.

[0100] In some embodiments, the following steps S2051~S2053 are included:

[0101] S2051. Using the independent reference value as a benchmark, set tolerance ranges for different decision-making levels;

[0102] In some embodiments, the objective function of each layer sets a tolerance range, ( , , ) and the acceptable minimum value ( , , This tolerance range can be based on... The values ​​are determined to reflect the preferences of decision-makers at different levels for different objectives and the acceptable range of compromises.

[0103] For example, in mid-level decision-making, if the model calculates the objective function to have an interval of FM=[8, 10], then the tolerable interval of this objective function can be set to [8, 10], where 8 represents the worst acceptable level and 10 represents the ideal satisfactory level. Based on this, a satisfaction function of the objective function can be constructed to characterize the decision-maker's preference for different outcomes.

[0104] S2052. Construct satisfaction functions based on the tolerance intervals of different decision-making levels;

[0105] Based on the set tolerance intervals for each objective, the preference membership functions (satisfaction functions) of upper-level, middle-level, and lower-level decision-makers regarding their objective functions are solved respectively. , , This method quantifies the degree to which each objective is achieved during the interaction process. Based on fuzzy set theory, a membership function (satisfaction function) is established for each objective function, thereby transforming the multi-objective optimization problem into a unified framework for maximizing satisfaction. For each objective function fᵢ, its satisfaction μᵢ∈[0,1] is defined through a linear membership function. This value is calculated based on the degree to which the objective function deviates from the ideal value within a preset tolerance interval. The specific expression is as follows:

[0106] (8)

[0107] Where, μ i (f i ): Objective function f i The satisfaction level ranges from 0 to 1; f i This represents the actual calculated value of the i-th objective function. This is the ideal objective value of the objective function. Its corresponding tolerance range; t i It is the tolerance interval radius, representing the maximum absolute range within which the target value is allowed to deviate from the ideal value. When the actual value deviates from the ideal value by more than t... i At that time, the satisfaction rate dropped to 0.

[0108] The specific expression is as follows:

[0109] Upper-level decision-makers in solving ( The optimal solution is found at point (), and the objective function value corresponding to this solution is (). Its membership function is constructed as follows:

[0110] (9)

[0111] in, This represents the actual calculated value of the upper-level objective function under the decision variable x, which is the function value that changes with the decision variable. This represents the optimal objective value obtained by optimizing the upper-level model separately, and is a constant. This represents the maximum acceptable value after coordination across the three layers, with the optimization process proceeding sequentially level by level. Since the semantics of the upper-level objective function are a minimization problem, the optimal objective value obtained through individual optimization is... This is the theoretical minimum value, and the target value allowed in the three-layer coordination process should not be better than this optimal value. Therefore, the two satisfy: .

[0112] The membership functions established by middle-level decision-makers for the objective function are as follows:

[0113] (10)

[0114] in, This represents the actual calculated value of the objective function of middle-level decision-makers. This represents the optimal objective value obtained by optimizing the middle-level model separately. The minimum acceptable value after coordination among the three levels is the middle level. The optimization process proceeds sequentially, ensuring that each decision level meets the corresponding constraints.

[0115] The membership functions established by lower-level decision-makers for the objective function are as follows:

[0116] (11)

[0117] in, This represents the actual calculated value of the objective function of the lower-level decision-makers. This represents the optimal objective value obtained by optimizing the lower-level model separately. The minimum acceptable value after coordination at the three levels is determined by the lower level. The optimization process proceeds sequentially, ensuring that each decision level meets the corresponding constraints.

[0118] S2053. By aggregating the satisfaction functions of different decision-making levels, an overall satisfaction function is constructed.

[0119] In some embodiments, the original multi-level programming problem is transformed into solving for the maximum overall satisfaction (max) through a designed interactive solution process based on genetic algorithms. The goal is to find the optimal solution of the model that achieves a balance between the objectives of the government, airlines, and consumers.

[0120] After determining the multi-level satisfaction function, the satisfaction level is calculated as follows:

[0121] (12)

[0122] Constraints:

[0123] (13)

[0124] (14)

[0125] (15) (16)

[0126] (17)

[0127] (18)

[0128] in, The overall satisfaction level of the model is represented by Equation (14). Equation (14) is a constraint on the satisfaction level of the decision variables to ensure that their values ​​are not lower than the overall satisfaction level.

[0129] By solving the maximum satisfaction model in this embodiment, the optimal decision variables are finally obtained. This value is then incorporated into the upper, middle, and lower layer models to obtain the optimal target value. Furthermore, considering the random fluctuations in transportation volume, multiple default probabilities can be set, such as pi=0.01, 0.05, 0.1. By repeating the above steps, decision results under multiple default probabilities can be obtained.

[0130] The following is a specific case study, demonstrating how the method of this invention can be used to solve the comprehensive decision-making problem in aviation carbon reduction planning:

[0131] 1) Aviation carbon emission reduction planning involves multiple decision-making entities, including governments, airlines, and consumers. Each entity has different decision-making objectives and faces multiple uncertainties such as passenger demand, fuel prices, and carbon trading costs during the multi-level decision-making process. Through research and analysis of actual data from specific routes, uncertain parameters are represented using interval numbers. Based on route operation characteristics and decision-making hierarchy, a multi-level planning model for aviation carbon emission reduction uncertainty is established as follows:

[0132] Upper-level objective function: Select the option that minimizes the environmental costs of emission reduction measures (including sustainable aviation fuel and carbon trading mechanisms).

[0133] (19)

[0134] The objective function of the middle level is to maximize economic benefits, which include both fixed and variable costs.

[0135] (20)

[0136] The lower-level objective function maximizes consumer utility, taking into account both ticket utility and flight punctuality. The study uses a utility function to quantify the degree of consumer preference.

[0137] (twenty one)

[0138] The constraints include:

[0139] Environmental constraints: SAF’s environmental impacts include exceeding government-mandated standards for water use, solid waste and wastewater discharge.

[0140] (twenty two)

[0141] (twenty three)

[0142] (twenty four)

[0143] Carbon trading constraints: Airlines must comply with national policy requirements to conduct carbon trading.

[0144] (25) (26) (27) (28)

[0145] Airline capacity constraints: Airline fleet allocation follows operational capacity constraints.

[0146] (29)

[0147] (30)

[0148] Supply and demand constraints: the balance between supply and demand for air passenger transport among different airlines, while opportunity constraints are used to represent the random fluctuations in transport demand.

[0149] (31)

[0150] SAF blending ratio constraint: Current technical requirements stipulate that the blending ratio of SAF with conventional aviation fuel shall not exceed 50%.

[0151] (32)

[0152] Sensitivity constraints: Sensitivity coefficients μ1 and μ2 determine the impact of ticket price and punctuality rate on passenger utility.

[0153] (33)

[0154] (34)

[0155] Airfare price constraints: Airfare prices should meet the airline's revenue management requirements and should not be lower than the minimum level stipulated by the market.

[0156] (35)

[0157] (36)

[0158] (37)

[0159] (38)

[0160] Elasticity constraint: The price elasticity of demand for air transport can be divided into business travel and tourism based on different groups. When the ticket price changes, the demand rate will also change to some extent according to the price elasticity.

[0161] (39)

[0162] (40)

[0163] in, Let y represent the integer variables used to determine how many type k aircraft airline i will select within a certain period. These variables are determined by the airline itself; i represents the airline; k represents different aircraft types; and y represents different species types. This indicates the blending ratio of sustainable aviation fuel in various types of aircraft; This indicates the ticket price for airline i's k-type aircraft; The CO2 emission factor for traditional aviation fuel; The carbon dioxide emission factor for mixing different proportions of SAF; The price of conventional aviation fuel; It is the price of SAF; Carbon dioxide emissions from aircraft that use conventional aviation fuel; Carbon dioxide emitted by aircraft using specific fuel blends; It represents the number of seats for a specific aircraft model; SWD represents the wastewater discharge per unit of biofuel. For wastewater treatment costs; The output of the biorefinery SAF; BSW represents the wastewater pretreatment rate; BR represents the area occupied by the biorefinery. This refers to the amount of air pollutants emitted; The cost of treating pollutants; Pretreatment rate for air pollutants; SOW represents solid waste emissions; RUR represents solid waste recycling rate; Cost of solid waste disposal; Density of biofuel (kg / L); Represents the feedstock-to-biofuel conversion ratio (kg / kg); ET represents seasonal evaporation. The price of water resources; The proportion of species y in all individuals; Indicates the unit price for maintaining biodiversity; This refers to the allowance provided free of charge domestically. Represents the amount of carbon allowances that can be traded; The maximum water consumption is indicated by: TES (Environmental Carrying Capacity for Solid Waste in the Region); SV (Wastewater Treatment Capacity per Unit Area); SEDI (Wastewater Discharge Standard); and PLF (Airline Passenger Load Factor). This represents the operating cost per ton-kilometer for an airline's K-type aircraft; APT represents the airport's passenger throughput. The target is for carbon dioxide emissions per ton-kilometer. The total amount of carbon allowances available to airlines; The amount of carbon emission allowances that airlines need to buy or sell; If airlines do not have enough carbon credits, they will need to purchase additional carbon credits. The cost of carbon dioxide that airlines need to sell to offset the surplus of carbon allowances; For the carbon trading price in the aviation market; This represents the number of aircraft owned (operational capacity) of airline i. This indicates the airport's future air passenger traffic volume; This represents the maximum number of available flights for airline i; Refers to the on-time performance rate of airline i; and These represent the sensitivity coefficients of airlines' on-time performance and ticket prices, respectively. The basic airfare is determined by standards set by the government. This indicates the aircraft's carbon dioxide emissions during the LTO (Low-Temperature Toll Collection) phase. Indicates changes in airfare prices; The change in ticket price is derived from changes in demand; This represents the revenue elasticity coefficient of airlines; This represents the price elasticity coefficient of airfares; This indicates the minimum demand in the aviation market; The minimum revenue required for an airline to break even is the sum of its fixed and variable costs.

[0164] 2) An interactive solution method based on genetic algorithms is used to coordinate and optimize the coupled three-layer model. First, the three-layer model is temporarily decoupled, and the genetic algorithm is used to independently optimize the upper, middle, and lower layers, initially obtaining the decision variables for each layer (such as the carbon quota allocated by the government and the SAF blending ratio, the airline's fleet configuration and flight frequency, and the route services chosen by consumers) and their corresponding target reference values. There are trade-offs and contradictions among minimizing environmental costs, maximizing airline profits, and maximizing consumer utility; the solutions obtained independently at each layer are not directly compatible and require system coordination. Therefore, an acceptable tolerance range needs to be set for the objective functions of the upper, middle, and lower layer decision-makers, and a linear preference membership function is constructed based on this to quantify the degree of achievement and satisfaction of each objective during the interaction process.

[0165] 3) To balance the conflicts between environmental constraints, operational efficiency, and consumer satisfaction, while simultaneously meeting the objectives of decision-makers at all levels, an overall satisfaction index is introduced. An overall satisfaction function is constructed by aggregating the preference membership functions of objectives at each level. Therefore, the original multi-level programming problem is transformed into an optimization problem aimed at maximizing overall satisfaction. Through iterative search using a genetic algorithm, an equilibrium optimal solution that satisfies the government, airlines, and consumers is ultimately obtained.

[0166] Based on the same inventive concept, this application also provides an aviation carbon emission reduction planning device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to that of the above-described method embodiments, the implementation of this device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0167] Figure 3 A schematic diagram of an aviation carbon emission reduction planning device according to an embodiment of this application is shown, such as... Figure 3As shown, the device includes: a data acquisition module 301 for acquiring historical data; a generation module 302 for generating passenger demand prediction intervals based on historical passenger demand data by combining prediction models and Monte Carlo simulations; a model building module 303 for building different decision-making level models for different decision-making levels of aviation carbon emission reduction; an independent solution module 304 for independently solving the different decision-making levels based on decision variables and constraints of different decision-making levels using a genetic algorithm to obtain independent reference values ​​for different decision-making levels; and a function construction module 305 for constructing an overall satisfaction function based on the independent reference values ​​of different decision-making levels, and using a genetic algorithm to iteratively optimize the overall satisfaction function to obtain the equilibrium optimal solution.

[0168] In some embodiments, generating a passenger demand forecast interval based on historical passenger demand data by combining a forecasting model with Monte Carlo simulation includes: decomposing the historical passenger demand data using singular spectrum analysis to obtain a trend component, a seasonal component, and a residual component; forecasting the seasonal component using a seasonal autoregressive combined with a moving average model to obtain a seasonal component forecast value; forecasting the trend component using a lightweight gradient boosting model to obtain a trend component forecast value; summing the trend component forecast value and the seasonal component forecast value item by item at each time point to obtain a point forecast value for passenger demand; and generating a passenger demand forecast interval based on the historical passenger demand data and the point forecast value using a Monte Carlo random sampling method.

[0169] In some embodiments, the historical data further includes airline operation data, market demand data, policy and market data, techno-economic parameters, and consumer behavior data; the airline operation data includes aircraft type and fleet composition, flight frequency, flight distance, SAF usage and its carbon emission factor, and fixed and variable operating costs; the market demand data includes historical passenger throughput time series, seasonality, and trend characteristics; the policy and market data includes carbon trading market mechanisms, carbon quota allocation rules, and pollutant emission standards; the techno-economic parameters include the upper limit of SAF blending ratio, fuel prices of conventional fuel and SAF, carbon trading prices, cost coefficients, and environmental carrying capacity indicators; and the consumer behavior data includes fare sensitivity coefficients, punctuality sensitivity coefficients, and demand elasticity parameters.

[0170] In some embodiments, constructing an overall satisfaction function based on independent reference values ​​at different decision levels includes: using the independent reference values ​​as a benchmark to set tolerance ranges for different decision levels; constructing satisfaction functions based on the tolerance ranges of different decision levels respectively; and constructing an overall satisfaction function by aggregating the satisfaction functions of different decision levels.

[0171] In some embodiments, the different decision-making level models are upper-level models, middle-level models, and lower-level models; the objective function of the upper-level model is to minimize environmental costs, and the constraints of the upper-level model are total carbon quota limits, SAF environmental carrying capacity constraints, and tradable quota constraints; the objective function of the middle-level model is to maximize airline operating revenue, and the constraints of the middle-level model are quota constraints, carbon trading constraints, airline capacity constraints, supply and demand constraints, and an upper limit on the SAF blending ratio; the objective function of the lower-level model is to maximize consumer utility, and the constraints of the lower-level model are ticket price and punctuality sensitivity constraints, ticket price policy constraints, and demand elasticity constraints; the objective function of the upper-level model is... The objective function of the middle-layer model is: The objective function of the lower-level model is: The constraints are: ;in, Represents a range of values. This represents the maximum value of the upper-level objective function. This represents the maximum value of the mid-level objective function. This represents the maximum value of the lower-level objective function. For model parameters, For decision variables of the upper-level model, For decision variables in the mid-level model, For decision variables in the lower-level model, As a constraint, p i The maximum probability that the constraint will not be satisfied, i.e., the probability of default.

[0172] In some embodiments, the satisfaction function is:

[0173] , where μ i (f i ) is the objective function f i The satisfaction level ranges from 0 to 1; f i This represents the actual calculated value of the i-th objective function. This is the ideal objective value of the objective function. Its corresponding tolerance range; t i It is the tolerance interval radius, representing the maximum absolute range within which the target value is allowed to deviate from the ideal value. When the actual value deviates from the ideal value by more than t... i At that time, the satisfaction rate dropped to 0.

[0174] It should be noted that the above-mentioned configuration data acquisition module 301, generation module 302, model building module 303, independent solution module 304, and function building module 305 correspond to S201~S205 in the method embodiment. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above method embodiment. It should be noted that the above modules, as part of the device, can be executed in a computer system such as a set of computer-executable instructions.

[0175] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0176] The following reference Figure 4 To describe an electronic device 400 according to this embodiment of the present application. Figure 4 The electronic device 400 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0177] like Figure 4 As shown, the electronic device 400 is manifested in the form of a general-purpose computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including storage unit 420 and processing unit 410).

[0178] The storage unit stores program code that can be executed by the processing unit 410, causing the processing unit 410 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this application. For example, the processing unit 410 can perform steps S201 to S205 of the above method embodiments.

[0179] Storage unit 420 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 4201 and / or cache memory 4202, and may further include a read-only memory (ROM) 4203.

[0180] Storage unit 420 may also include a program / utility 4204 having a set (at least one) program module 4205, such program module 4205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0181] Bus 430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0182] Electronic device 400 can also communicate with one or more external devices 440 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 400, and / or with any device that enables electronic device 400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 450. Furthermore, electronic device 400 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 460. As shown, network adapter 460 communicates with other modules of electronic device 400 via bus 430. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0183] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this application.

[0184] In particular, according to embodiments of this application, the process described in the above-mentioned flowchart can be implemented as a computer program product, which includes a computer program that, when executed by a processor, implements the above-described aviation carbon emission reduction planning method.

[0185] In an exemplary embodiment of this application, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. The computer-readable storage medium stores a program product capable of implementing the methods described above in this application.

[0186] In some possible implementations, various aspects of this application may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this application.

[0187] More specific examples of computer-readable storage media in this application may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0188] In this application, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0189] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0190] In practical implementation, program code for performing the operations of this application can be written using any combination of one or more programming languages. These programming languages ​​include object-oriented programming languages—such as Java and C++—and conventional procedural programming languages—such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0191] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0192] Furthermore, although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0193] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0194] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

Claims

1. A method for planning carbon emission reduction in aviation, characterized in that, include: Collect historical data, including historical passenger demand data; Based on historical passenger demand data, a passenger demand forecast interval is generated by combining a forecast model and Monte Carlo simulation. The combined forecast model includes singular spectrum analysis, seasonal autoregressive integrated moving average model and lightweight gradient booster model. Different decision-making level models are constructed for different decision-making levels of aviation carbon emission reduction; each decision-making level model includes an objective function, decision variables, and constraints. Based on the decision variables and constraints at different decision levels, a genetic algorithm is used to solve the different decision levels independently, thereby obtaining independent reference values ​​for each decision level. An overall satisfaction function is constructed based on independent reference values ​​at different decision levels, and a genetic algorithm is used to iteratively optimize the overall satisfaction function to obtain the equilibrium optimal solution.

2. The aviation carbon emission reduction planning method according to claim 1, characterized in that, The process, based on historical passenger demand data, generates a passenger demand forecast interval by combining a prediction model with Monte Carlo simulation, including: The historical passenger demand data was decomposed using singular spectrum analysis, resulting in trend components, seasonal components, and residual components. The seasonal component is predicted using a seasonal autoregressive integrated moving average model to obtain the predicted value of the seasonal component. A lightweight gradient boosting model is used to predict the trend components, and the predicted values ​​of the trend components are obtained. The predicted values ​​of the trend component and the predicted values ​​of the seasonal component are added together item by item at each time point to obtain the point prediction value of passenger demand. Based on the historical passenger demand data and the point prediction values, a passenger demand prediction interval is generated using the Monte Carlo random sampling method.

3. The aviation carbon emission reduction planning method according to claim 1, characterized in that, The historical data also includes airline operation data, market demand data, policy and market data, technical and economic parameters, and consumer behavior data; The airline's operational data includes aircraft type and fleet composition, flight frequency, flight distance, SAF usage and its carbon emission factor, and fixed and variable operating costs; The market demand data includes historical passenger throughput time series, seasonality, and trend characteristics; The policy and market data mentioned include carbon trading market mechanisms, carbon quota allocation rules, and pollutant emission standards. The technical and economic parameters include the upper limit of SAF blending ratio, fuel prices of conventional fuel oil and SAF, carbon trading price, cost coefficient, and environmental carrying capacity index. The consumer behavior data includes the price sensitivity coefficient, punctuality sensitivity coefficient, and demand elasticity parameter.

4. The aviation carbon emission reduction planning method according to claim 1, characterized in that, The construction of the overall satisfaction function based on independent reference values ​​at different decision-making levels includes: Using the aforementioned independent reference value as a benchmark, tolerance ranges are set for different decision-making levels; Satisfaction functions are constructed based on the tolerance intervals of different decision-making levels; By aggregating the satisfaction functions of different decision-making levels, an overall satisfaction function is constructed.

5. The aviation carbon emission reduction planning method according to claim 4, characterized in that, The different decision-making level models are upper-level models, middle-level models, and lower-level models; The objective function of the upper-level model is to minimize environmental costs, and the constraints of the upper-level model are total carbon quota limits, SAF environmental carrying capacity constraints, and tradable quota constraints. The objective function of the intermediate-level model is to maximize the operating revenue of airlines. The constraints of the intermediate-level model are quota constraints, carbon trading constraints, airline capacity constraints, supply and demand constraints, and the upper limit of SAF blending ratio. The objective function of the lower-level model is to maximize consumer utility, and the constraints of the lower-level model are the sensitivity constraints of ticket price and punctuality rate, the constraints of airfare pricing policy, and the constraints of demand elasticity. The objective function of the upper-level model is: The objective function of the middle-layer model is: The objective function of the lower-level model is: The constraints are: ;in, This represents the maximum value of the upper-level objective function. This represents the maximum value of the mid-level objective function. This represents the maximum value of the lower-level objective function. For model parameters, For decision variables of the upper-level model, For decision variables in the mid-level model, For decision variables in the lower-level model, Let pi be the constraint condition, pi be the maximum probability that the constraint is not satisfied, i.e., the probability of default, and i be the i-th constraint condition.

6. The aviation carbon emission reduction planning method according to claim 5, characterized in that, The satisfaction function is: , where μ i (f i ) is the objective function f i The satisfaction level ranges from 0 to 1; f i This represents the actual calculated value of the i-th objective function. This is the ideal objective value of the objective function. Its corresponding tolerance range; t i It is the tolerance interval radius, representing the maximum absolute range within which the target value is allowed to deviate from the ideal value. When the actual value deviates from the ideal value by more than t... i At that time, the satisfaction rate dropped to 0.

7. An aviation carbon emission reduction planning device, characterized in that, include: The data acquisition module is used to collect historical data, including historical passenger demand data. The generation module is used to acquire historical passenger demand data from the data acquisition module. Based on the historical passenger demand data, it generates a passenger demand forecast interval by combining a prediction model and Monte Carlo simulation. The combined prediction model includes singular spectrum analysis, seasonal autoregressive integrated moving average model and lightweight gradient booster model. The model building module is used to build different decision-level models for different decision-making levels of aviation carbon emission reduction. The decision-level models include objective functions, decision variables and constraints. An independent solution module is used to obtain decision variables and constraints at different decision levels in the model construction module. Based on the decision variables and constraints at different decision levels, a genetic algorithm is used to independently solve the different decision levels to obtain independent reference values ​​for each decision level. The function construction module is used to obtain independent reference values ​​at different decision levels in the independent solution module, construct an overall satisfaction function based on the independent reference values ​​at different decision levels, and use a genetic algorithm to iteratively optimize the overall satisfaction function to obtain the equilibrium optimal solution.

8. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the aviation carbon emission reduction planning method according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the aviation carbon emission reduction planning method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program that, when executed by a processor, implements an aviation carbon emission reduction planning method according to any one of claims 1 to 6.

Images