A method for optimizing multi-target scheduling of departing flights with consideration of CTOT coincidence rate

Abstract

The embodiment of the application discloses a kind of off airport flight multi-objective scheduling optimization methods giving consideration to CTOT coincidence rate, which comprises: collecting airport operation data, establishing scheduling sample library containing flight plan information, actual push out / withdraw wheel block time and CTOT and other parameters;Build multi-objective optimization model that fuses SOBT constraint, COBT dynamic adjustment mechanism, with off airport normal rate, CTOT coincidence rate and taxiing time as joint optimization target;Determine multi-objective weight using entropy weight method, design hybrid simulated annealing algorithm that fuses elite reservation strategy and adaptive weight mechanism to solve model;According to the optimization result, output adjusted push-out time plan.It is suitable for ground traffic scheduling and collaborative decision system of large hub airport.The application aims to solve the target conflict problem between off airport normal rate and CTOT coincidence rate in current airport off airport scheduling process, by giving consideration to push-out time control and taxiing conflict management, realize multi-objective collaborative optimization of flight off airport scheduling.

Description

Technical Field

[0001] This invention relates to the field of civil aviation air traffic control technology, and in particular to a multi-objective scheduling optimization method for departing flights that takes into account the CTOT (Calculated Take-Off Time) compliance rate. It is applicable to flight pushback scheduling and flight release scheduling in the ground taxi area of ​​civil transport airports, and its main application scenario is the cross-application scenario of ground-air collaborative optimization and airspace capacity management. Background Technology

[0002] As the core hub of the air transport system, the efficiency of airport ground operations directly impacts flight punctuality and the rational allocation of airspace resources. The International Civil Aviation Organization (ICAO), in its Global Air Navigation Plan, explicitly states that airport operational efficiency should be assessed using Key Performance Indicators (KPIs), with "On-Time Departure Rate" (KPI 01), "Extra Taxiout Time" (KPI 02), and "CTOT Compliance Rate" (KPI 03) being core indicators for measuring the efficiency of airport ground scheduling and air-ground coordination. How to improve CTOT compliance while ensuring on-time flight departures has become a crucial issue urgently needing resolution in today's complex airport operating environment, and also a direction for further optimization of civil aviation air traffic control systems.

[0003] On-time departure rate, typically measured by the percentage of flights whose actual departure time (AOBT) deviates from their scheduled departure time (SOBT) by no more than 15 minutes, is a primary indicator of ground scheduling timeliness and operational stability. CTOT compliance rate, on the other hand, measures whether a flight takes off within the time window allowed by its Calculated Take-Off Time (CTOT), and is a crucial standard reflecting whether flights are operating within the predetermined airspace capacity. Clearly, there is a significant conflict between the two objectives: to ensure on-time departure rate, dispatchers must schedule flights to depart according to the original SOBT as much as possible; however, if flights fail to obtain available taxiways or runway windows at this time, it may cause taxiing congestion or conflicts, affecting CTOT execution. Conversely, forcibly adjusting the departure order or delaying taxiing to ensure CTOT compliance rate may lead to irregular flight departures, affecting overall departure timeliness.

[0004] Currently, most airports still rely on fixed timetables in their scheduling systems, experience-based rules from senior dispatchers, or static priorities for pushback scheduling. They lack a systematic optimization mechanism for CTOT (Centralized Toll-Free Operation) coordination, making it difficult to dynamically balance taxiway path conflicts between flights, airspace control time slot execution needs, and ground operational pressure. Furthermore, existing scheduling strategies lack the ability to model the linkage between SOBT (Side-On-Board) and COBT (Cross-On-Board), failing to achieve comprehensive coordination of departure efficiency and airspace compliance during pushback and return taxiing. This results in unstable flight operation outcomes, low levels of ground-air coordination, and negatively impacts overall airport operational efficiency. Summary of the Invention

[0005] The embodiments of the present invention provide a multi-objective scheduling optimization method for departing flights that takes into account CTOT compliance rate, which can solve the objective conflict problem between departure on-time rate and CTOT compliance rate in the current airport departure scheduling process. By taking into account pushback time control and taxiing conflict management, the method achieves multi-objective collaborative optimization of flight departure scheduling.

[0006] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0007] A multi-objective scheduling optimization method for departing flights that takes into account CTOT compliance rate includes:

[0008] S1. Collect airport operation data and establish a scheduling sample database, which includes: flight plan information, actual pushback / wheel chock removal time, and CTOT; specifically, basic flight information: flight number, planned pushback time (SOBT), calculated wheel chock removal time (COBT), actual wheel chock removal time (AOBT), calculated takeoff time (CTOT), and actual takeoff time (ATOT); aircraft type, parking stand number, runway number, departure direction, etc.; environmental status information: parking stand latitude and longitude coordinates, runway latitude and longitude coordinates, taxiway node coordinates, etc.

[0009] S2. Establish a multi-objective optimization model for departing flights that takes into account CTOT compliance rate. The constructed multi-objective optimization model integrates SOBT (Scheduled Off-Block Time) constraints and COBT (Calculated Off-Block Time) dynamic adjustment mechanism. The multi-objective optimization model aims to maximize the on-time departure rate, maximize the CTOT compliance rate, and minimize taxiing time. The baseline input of the multi-objective optimization model includes smooth taxiing time.

[0010] S3. Determine and assign the weights of each objective function using the Entropy Weight Method (EWM);

[0011] S4. Run the multi-objective optimization model and adjust the launch time plan.

[0012] In this embodiment, in S1, the collection of airport operation data includes: collecting full flight operation data of the target airport within a specified period from the Airport Collaborative Decision Making System (A-CDM) and the air traffic control automation system. The types of the collected full flight operation data include: basic flight information, taxiway path information, ground resource and restriction information, and environmental status information. Specifically, before flight scheduling modeling, full flight operation data of the target airport within a certain period is collected and preprocessed to form a high-quality scheduling input sample set. The collected data includes, but is not limited to: 1. Basic flight information: flight number, planned pushback time (SOBT), calculated wheel chock removal time (COBT), actual wheel chock removal time (AOBT), calculated takeoff time (CTOT), and actual takeoff time (ATOT); 2. Taxi path information: parking stand number, runway usage number, taxiway structure, and nodes traversed by the taxi path; 3. Ground resources and restrictions: taxiway segment occupancy time, pushback / return interval restrictions, taxiing time, etc.; 4. Environmental status information: aircraft type, airspace flow control classification, and whether it is a CTOT-controlled flight, etc. The raw data undergoes standardized preprocessing, including field format conversion, unit standardization, outlier removal, data completion, and taxi path mapping, ultimately constructing a model-oriented standardized scheduling sample set.

[0013] The airport's surface structure data is collected, and a directed graph model of the airport's taxiway area is constructed. Furthermore, airport surface structure data is collected, and a directed graph model of the airport's taxiway area is constructed based on graph theory methods. Nodes represent parking stands, taxiway intersections, and runway entrances, while edges represent taxiway segments. Operational constraint parameters, such as apron conflict separation, wake separation, departure direction restrictions, and taxiing distance, are integrated into the graph model. For example, the airport surface operation model is constructed using graph theory methods by collecting airport surface operation data, including the latitude and longitude information, connectivity relationships, taxiing directions, and distances of key nodes such as parking stands, runways, and taxiways, and constructing an airport surface taxiway network topology graph. Nodes represent parking stands, taxiway intersections, and runway entrances, while edges represent taxiing paths. A directed graph structure of the airport surface operation model is constructed using graph theory methods. Based on this graph model, relevant operational constraint information is integrated, including: apron pushback conflict: the pushback time between adjacent parking positions must meet the minimum safe interval; wake turbulence interval constraint: the time interval required for takeoff between different aircraft combinations; departure direction interval: the minimum time interval between flights at the same departure point; the above constraints can be used as weights between nodes or attributes of edges in the graph structure for conflict detection and path optimization in subsequent model solving.

[0014] In this embodiment, in S1, the establishment of the scheduling sample library includes: flight operation data extracted from the collected full flight operation data and standardized, and the clear taxiing time corresponding to each runway-parking stand combination. The flight operation data includes: Planned Wheel Shackle Removal Time (SOBT), Calculated Wheel Shackle Removal Time (COBT), Actual Wheel Shackle Removal Time (AOBT), Calculated Takeoff Time (CTOT), Actual Takeoff Time (ATOT), aircraft type, parking stand location, runway used, taxiing time, and taxiing path;

[0015] The raw flight operation data undergoes standardization processing, including: data cleaning: removing unreasonable data such as time logic errors, missing fields, and outliers in taxiing time; unit standardization: converting time fields to a standard format and matching location fields to node numbers in the graph model; feature construction: extracting information such as the graph path corresponding to the flight, CTOT type indicator variables, and whether it is a controlled flight. Finally, a sample library is constructed for model training and scheduling optimization.

[0016] The smooth taxiing time corresponding to each runway-parking stand combination includes: after data cleaning, the remaining flights are grouped according to the near departure stage, based on the parking stand and runway usage, to form runway-parking stand combinations; for each combination, the 10th percentile of the actual taxiing time of all flights in the group is taken as the corresponding smooth taxiing time, wherein at least 10 flights in each combination have a smooth taxiing time shorter than that of the group.

[0017] To accurately reflect the normal time consumption during the taxiing phase of a flight and avoid outliers affecting model performance, a representative taxiing time needs to be estimated for each parking stand-runway combination. In this scheme, "open taxiing time" is used as the input indicator for taxiing efficiency evaluation, defined as the time from when the aircraft pushes out of the parking stand to when it arrives at the runway gate and waits in line, excluding the runway gate waiting or release time. The specific steps are as follows: (1) Data cleaning: First, flights with de-icing procedures and helicopter flights are removed. Second, after calculating the actual taxiing time of the aircraft, flights with actual taxiing times less than 0 or greater than 2 hours are removed to ensure the validity of the data. (2) Grouping and clustering: Flights are grouped according to the near departure phase, based on parking stands and runway usage, to form runway-parking stand combinations. For each airport, flights are grouped by combination and have the same runway and parking stand. These runway-parking stand flight combinations follow similar taxiing paths and therefore have similar open taxiing times. (3) Calculate the clear taxiing time: Calculate the clear taxiing time for each runway-stand combination, which is the 10th percentile of the actual taxiing time of all flights within the group. Simultaneously, to ensure the representativeness of the taxiing time for each runway-stand combination, at least 10 flights within each combination must have a clear taxiing time shorter than that group's. This clear taxiing time serves as the baseline input for flight taxiing time estimation in the optimization model, measuring the operational efficiency level between pushback and takeoff times, and providing important references in algorithm path calculation and taxiing conflict detection.

[0018] In this embodiment, the actual pushback time (AOBT) of the flight is used as the main decision variable of the multi-objective optimization model. Specifically, a multi-objective flight pushback scheduling optimization model oriented towards CTOT coordination is constructed, aiming to achieve a dynamic balance among the following three objectives: maximizing the on-time departure rate: that is, pushing back flights within the SOBT ± 15-minute window as much as possible; maximizing the CTOT compliance rate: that is, flights with CTOT restrictions should complete takeoff within the CTOT ± 3-minute range; minimizing taxiing time (unimpeded taxiing time): that is, reducing the ground taxiing time from pushback to takeoff and improving taxiing efficiency.

[0019] The model uses the actual pushback time (AOBT) of flights as the primary decision variable and introduces the following key constraint mechanisms: SOBT reference window constraint: setting boundaries for tolerance of flight pushback deviations from the plan; COBT dynamic adjustment mechanism: allowing COBT adjustment under certain rules to meet CTOT constraints; graph model taxiing path feasibility constraint: ensuring that the selected path is available without conflicts under current resource conditions; CTOT indicator variable: applying CTOT window constraints only to controlled flights; resource occupancy and time interval constraints: controlling key operational constraints such as adjacent pushback / return intervals and release intervals; taxiing network topology modeling: strengthening path connectivity judgment, node resource conflict handling, and timing coordination management. The model's objective function uses entropy weighting fusion, with weights reflecting the relative volatility and scheduling influence of each objective in the sample, achieving multi-objective coordination. The multi-objective optimization model includes: f = max(ω1f1 + ω2f2 - ω3f3), where ω1, ω2, and ω3 are the weights corresponding to f1, f2, and f3, respectively, and f1, f2, and f3 are the objective functions of departure on-time rate, CTOT compliance rate, and taxiing time, respectively.

[0020] In this embodiment of the invention, airport operation data is collected to establish a scheduling sample library containing flight schedule information, actual pushback / wheel chock removal times, and CTOT (Critical Off-Block Time) parameters. A multi-objective optimization model is constructed, integrating SOBT (Scheduled Off-Block Time) constraints and COBT (Calculated Off-Block Time) dynamic adjustment mechanisms, with departure on-time performance, CTOT compliance rate, and taxiing time as joint optimization objectives. The entropy weight method is used to determine the weights of the multiple objectives, and a hybrid simulated annealing (HSA) algorithm integrating an elite retention strategy and an adaptive weighting mechanism is designed to solve the model. Based on the optimization results, an adjusted pushback time schedule is output. This solves the objective conflict problem between departure on-time performance and CTOT compliance rate in the current airport departure scheduling process, achieving multi-objective collaborative optimization of flight departure scheduling by taking into account both pushback time control and taxiing conflict management. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 The flow chart of the smooth coasting time algorithm provided in this embodiment of the invention;

[0023] Figure 2 This invention provides a feasible solution generation method for embodiments of the invention.

[0024] Figure 3 The following is the solution process for the simulated annealing algorithm provided in the embodiments of the present invention;

[0025] Figure 4 The following are before and after optimization results of the on-time departure rate of Lukou Airport throughout the day, provided in an embodiment of the present invention;

[0026] Figure 5 The following are before and after optimization figures for CTOT compliance rate at Lukou Airport during different time periods throughout the day, provided in an embodiment of the present invention;

[0027] Figure 6 Density diagram of monthly taxiing time before and after optimization provided in an embodiment of the present invention at Lukou Airport;

[0028] Figure 7 This is a schematic diagram of the airport departure point direction provided in an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Embodiments of the present invention will be described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in the specification of the present invention means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or couplings. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items. It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as herein.

[0030] The design concept of this embodiment is to collaboratively consider multiple objectives of outbound scheduling optimization, including flight departure on-time rate, CTOT compliance rate, and taxiing time, in order to resolve the objective conflict problem in airport ground scheduling. It is applicable to hub airport operating environments equipped with a Cooperative Departure Management (CDM) system and taxiing scheduling module, and is particularly suitable for medium and large airports with high operational density, strong CTOT restrictions, and intense competition for taxiing area resources.

[0031] The design objectives of this embodiment are: to improve the compliance of flight CTOT instructions while ensuring the on-time departure rate; to effectively control the extra taxiing time of flights and improve airport taxiing efficiency; to achieve intelligent optimization of the collaborative scheduling mechanism between flight SOBT, AOBT and COBT; and to build a multi-objective scheduling model for complex airport operating environments to provide decision support for airport operation management.

[0032] This invention provides a multi-objective scheduling optimization method for departing flights that takes into account CTOT compliance rate, such as... Figure 1-3 As shown, it includes:

[0033] S1. Collect airport operation data and establish a scheduling sample library, which includes: flight plan information, actual pushback / removal wheel chock times and CTOT;

[0034] S2. Establish a multi-objective optimization model for departing flights that takes into account CTOT compliance rate. The multi-objective optimization model aims to maximize the on-time departure rate, maximize the CTOT compliance rate, and minimize taxiing time. The baseline input of the multi-objective optimization model includes smooth taxiing time.

[0035] S3. Determine and assign the weights of each objective function using the Entropy Weight Method (EWM);

[0036] S4. Run the multi-objective optimization model and adjust the launch time plan.

[0037] In S1, the collection of airport operation data includes: collecting full flight operation data of the target airport within a specified period, wherein the types of the collected full flight operation data include: basic flight information, taxiway information, ground resource and restriction information, and environmental status information; collecting surface structure data of the target airport, and constructing a directed graph model of the airport taxiway area.

[0038] The established scheduling sample library includes: flight operation data extracted from the collected full flight operation data and standardized, including: planned wheel chock removal time (SOBT), calculated wheel chock removal time (COBT), actual wheel chock removal time (AOBT), calculated takeoff time (CTOT), actual takeoff time (ATOT), aircraft type, parking position, runway used, taxiing time and taxiing path; and the clear taxiing time corresponding to each runway-parking position combination.

[0039] Among them, such as Figure 1 The method for calculating the smooth taxiing time shown includes the following steps: After data cleaning, the remaining flights are grouped according to their approach and departure stages, based on the number of parking stands and the status of runway usage, to form runway-parking stand combinations. For each combination, the 10th percentile of the actual taxiing time of all flights within the group is taken as the corresponding smooth taxiing time. At least 10 flights within each combination have a smooth taxiing time shorter than that of the group.

[0040] The actual launch time (AOBT) of the flight is used as the main decision variable in the multi-objective optimization model.

[0041] The multi-objective optimization model includes: f = max(ω1f1 + ω2f2 - ω3f3), where ω1, ω2, and ω3 are the weights corresponding to f1, f2, and f3, respectively, and f1, f2, and f3 are the objective functions of departure on-time rate, CTOT compliance rate, and taxiing time, respectively.

[0042] Specifically, the joint optimization objectives are departure on-time performance rate, CTOT compliance rate, and taxiing time. The objective function for departure on-time performance rate is based on:

[0043] |AOBT-SOBT| ≤15 minutes definition;

[0044] CTOT compliance rate is defined based on a window of |ATOT-CTOT| ≤ 3 minutes; coasting time is ATOT-AOBT.

[0045] To achieve coordinated optimization of the three objectives, the variables are defined as shown in Table 1 below:

[0046] Table 1

[0047]

[0048]

[0049] The objective function is as follows:

[0050] ① Maximize the on-time departure rate

[0051] On-time departure rate is the percentage of on-time departure flights to the total number of departing flights at the airport. The standard for judging on-time departure is if the difference between the actual off-block time (AOBT) and the scheduled off-block time (SOBT) is within the allowable time range (|AOBT-SOBT|≤15 minutes).

[0052] The normal departure rate is:

[0053] Where f1 represents the on-time departure rate, and the objective function for the on-time departure rate is: P i g : The pushback time of the i-th aircraft at the g-th parking position (actual wheel chock removal time AOBT). The planned time for the i-th aircraft to remove its wheel chocks at parking position g (SOBT) δ(*) is an indicator function that takes the value 1 when the condition is true and 0 otherwise.

[0054] ② Maximize CTOT compliance rate

[0055] Since not all departing flights include CTOT, a CTOT indicator variable is set to identify which flights have CTOT constraints.

[0056]

[0057] If the flight has a CTOT, then If the flight does not have a CTOT, then

[0058] CTOT compliance rate measures whether the actual take-off time (ATOT) of a flight complies with CTOT constraints, i.e., whether the aircraft can complete take-off within the specified time window. Specifically, CTOT time slot tolerance is divided into Category I tolerance and Category II tolerance. Traffic management measures based on capacity management are Category I tolerances, with a tolerance range of (-5, +10) minutes; traffic management measures based on interval management are Category II tolerances, with a tolerance range of (-3, +3) minutes. Therefore, this paper selects the (-3, +3) tolerance range.

[0059] The maximum CTOT compliance rate is defined as:

[0060]

[0061] Where δ(*) is the indicator function, when The value is 1 when the minute is reached, and 0 otherwise.

[0062] in, This represents the actual takeoff time of the i-th aircraft on runway r. This indicates that the takeoff time of the i-th aircraft is calculated on runway r. This indicates an indicator variable used to identify flights that include CTOT;

[0063] ③ Minimize gliding time

[0064] The taxiing time in this paper is the aircraft's actual takeoff time minus the aircraft's pushback time. Since the taxiing path time in this paper is replaced by the unobstructed taxiing time, minimizing the taxiing time is equivalent to minimizing the extra taxiing time.

[0065]

[0066] A multi-objective function was established:

[0067]

[0068] Among them, ω1, ω2, and ω3 are calculated using the Entropy Weight Method (EWM) to calculate the weights of each objective function.

[0069] S3 includes: determining the weights of each objective function using the entropy weight method based on the constraints, wherein the constraints include: parking stand conflict constraints, runway clearance interval constraints, and CTOT time window constraints;

[0070] The parking position conflict constraint is a minimum rollout time requirement: the minimum rollout time for adjacent affected parking positions must be limited to a certain duration.

[0071]

[0072] To ensure that departing flights meet the departure direction and aircraft type separation requirements when entering the runway, we define the runway entry time of aircraft i on runway r as follows: Release interval is The runway clearance interval constraint is as follows:

[0073] Aircraft entry time on the runway:

[0074] The release interval is determined by both the departure direction interval and the aircraft type interval, and the final release interval constraint is:

[0075] The actual takeoff time is the sum of the runway entry time and the runway occupancy time.

[0076]

[0077] The CTOT time window constraint is as follows:

[0078]

[0079] in, Let i and j represent the set of aircraft IDs, where i and j represent the aircraft IDs in the set. Let g represent the set of parking positions, and g represent the parking position number. P represents the time when the i-th aircraft enters the runway. i g U represents the launch time of the i-th aircraft. gr This represents the clear taxiing time from parking position g to runway r. This indicates that the takeoff time of the i-th aircraft is calculated on runway r. This represents the actual takeoff time of the i-th aircraft on runway r. This represents the indicator variable used to identify flights that include CTOT. A combination of factors indicating runway occupancy time. This indicates the runway clearance interval.

[0080] Specifically, Runway occupancy time is determined by a combination of factors, such as wind direction and speed, runway slipperiness, load, and aircraft operation. Values ​​are differentiated by aircraft type, which must include at least light, medium, and heavy aircraft. For example, runway occupancy time requirements for different aircraft types are shown in Table 2.

[0081] Table 2

[0082] medium-sized machine 50s 50s Heavy machinery 60s 60s

[0083] Then the time when the aircraft enters the runway:

[0084]

[0085] The departure interval is determined by both the departure direction interval and the aircraft type interval. For example, due to differences between different airports, This can be directly interpreted as runway clearance requirements. The following example (departure direction clearance and aircraft type clearance) uses Lukou Airport in a provincial capital city as an example, where:

[0086] (1) Departure direction interval

[0087] like Figure 7 As shown, departing aircraft passing through the same reporting point (HFE, ESBAG, OF, CJ) are considered to be in the same direction, with a 3-minute interval for those in the same direction; however, for those heading consecutively towards Zhengzhou, Wuhan, and Nanchang after HFE, the interval is 6 minutes; for different directions, if the wake turbulence interval requirement is met (the minimum is generally assumed to be 2 minutes), such as... Figure 7 As shown.

[0088]

[0089] (2) Model interval Its value depends on the combination of aircraft types on the preceding and following flights.

[0090] The aircraft release interval requirements are shown in Table 3:

[0091] Table 3

[0092]

[0093] The release interval is then:

[0094]

[0095] The final release interval constraint is:

[0096]

[0097] To reasonably allocate the weights of each optimization objective, this embodiment uses the Entropy Weight Method to determine the weight coefficients of each objective function. The Entropy Weight Method is an objective weighting method that assigns weights based on the degree of variation of each indicator in the sample data. The steps are as follows:

[0098] (1) Standardize the objective function values ​​and normalize each objective function value to avoid the influence of dimensional differences on the calculation results;

[0099] (2) Calculate the proportion of each objective function in each sample;

[0100] (3) Calculate the entropy value of each objective function according to the information entropy formula. The smaller the entropy value, the greater the variability of the objective.

[0101] (4) The redundancy (i.e., information gain) is deduced from the entropy value, and the weight of each objective is calculated accordingly. The greater the redundancy, the more information the objective provides, and the higher its optimization priority should be assigned.

[0102] The above method ensures the objectivity of weight allocation, giving higher weights to targets that have a greater impact on airport operations, thereby enhancing the model's adaptability and fairness. Example weights: ω1 = 0.31 (departure on-time rate), ω2 = 0.44 (CTOT compliance rate), ω3 = 0.25 (taxiing time).

[0103] To efficiently solve the aforementioned multi-objective scheduling optimization problem, this invention employs a multi-objective optimization algorithm framework based on heuristic search, including:

[0104] Multi-objective evolutionary algorithms (such as NSGA-II or MOEA / D): obtain a set of non-dominated solutions in the solution space through a multi-objective Pareto optimization strategy;

[0105] Hybrid Improved Algorithm: It can combine local search strategies such as Particle Swarm Optimization (MOPSO) and Simulated Annealing (HSA) to improve the convergence and diversity of solutions;

[0106] Fitness function construction: combining standardized scores of the three objectives with dynamic crowding penalty factor;

[0107] Population initialization mechanism: The initial population is constructed using the SOBT priority rule to ensure the feasibility of the initial solution;

[0108] Elite retention and crowding control mechanisms: Improve the stability of local search in high-density scheduling intervals;

[0109] Adaptive target weight adjustment mechanism: Automatically adjust the bias strategy according to the target convergence trend during the evolution process.

[0110] This optimization framework can ultimately output a set of optimal or suboptimal scheduling schemes that satisfy multi-objective coordination, which can be used for selection in actual deployment systems or as a reference for multi-scenario analysis.

[0111] A hybrid metaheuristic framework combining simulated annealing (SA) and local search strategies is used to solve the multi-objective flight pushback scheduling problem. By balancing global exploration and local exploitation capabilities, the algorithm efficiently converges to a high-quality Pareto optimal solution under complex operational constraints. The algorithm design mainly includes data preprocessing, feasible solution generation, and conflict resolution. S4 includes:

[0112] (1) Preprocessing: The parameter set input to the multi-objective optimization model is:

[0113]

[0114] The preprocessing stage includes data cleaning and feature extraction: outlier removal: deleting glide time.

[0115] Flights in minutes; Grouping and clustering: Divide flights into sets based on parking stand-runway combinations, and calculate the clear taxiing time U for each group. gr .

[0116] (2) This embodiment proposes a scheduling strategy based on a combination of SOBT anchoring and COBT window flexible adjustment, which enhances the adaptability and execution flexibility of flight pushback scheduling, thereby completing the establishment of a dynamic time slot adjustment mechanism. This is specifically reflected in the generation of feasible solutions, for example:

[0117] For flight i, its feasible departure time interval Defined as:

[0118]

[0119] For flights including CTOT: the time window is strictly limited to 10 minutes before and after COBT.

[0120] For flights without CTOT: the time window is extended to 15 minutes after the scheduled departure time.

[0121] Further details regarding the parking space occupancy schedule D g Perform conflict detection: remove unavailable time periods.

[0122]

[0123] D g This represents the time interval for occupancy of parking positions, specifically the occupancy period for parking position g.

[0124] The initial arrival time interval is obtained by adding the feasible departure time of the parking position to the unobstructed taxiing time.

[0125] For runway gate r, conflict-free time slots are generated according to the following rules: (1) Time window division: based on runway clearance intervals Will Discretize into time slots. (2) Conflict detection: Eliminate time and space overlap intervals with already scheduled flights. (3) Priority allocation: Reassign time windows to prioritize flights within conflict time slots. Time slots are formed when some intervals cause otherwise continuous time to be occupied due to required intervals. It can only be used as the initial arrival time interval in other times, that is, in the time slot.

[0126] Determine the actual departure time of the flight at the parking stand: Reverse calculation: Calculate the departure time of the flight at the parking stand back from the actual arrival time at the runway gate. Constraint verification: Ensure that the departure time is still within the initial feasible time window.

[0127] Update parking stand occupancy schedule: Primary parking stand: Records actual departure time for subsequent flight conflict detection. No-push-out stands: Adds parking stand time interval constraints to the schedules of adjacent parking stands. Update parking stand occupancy table. The specific algorithm for solving this problem is as follows:

[0128] a) Initialization

[0129] The initial solution X is generated using a greedy heuristic, with an initial temperature T0 = 1000, a cooling rate α = 0.95, a maximum number of iterations of 500, and stop positions allocated according to SOBT sorting. Feasible time windows are then greedily filled.

[0130] b) Annealing cycle

[0131] For each iteration,

[0132] (1) Neighborhood generation: Generate neighborhood solutions X′ of the current solution;

[0133] (2) Target evaluation: F(X′) = ω1·f1 + ω2·f2 - ω3·f3;

[0134] (3) Acceptance criterion: If F(X′) > F(X) t ), accept X t+1 =X′; otherwise, by probability accept;

[0135] (4) Elite archive update: retain the top 10% of optimal solutions to accelerate convergence;

[0136] Temperature update: T t+1 =α·T t Based on the above design, a three-level coordination optimization strategy is implemented in practical applications. Besides the SOBT-based baseline anchoring, it also includes flexible correction of AOBT (Actual Off-Block Time) and fine-tuning of COBT. For example, AOBT is the actual wheel chock removal time, which can be flexibly adjusted based on + to 15 minutes of SOBT or 10 minutes before and after COBT (i.e., flexible correction of AOBT). For flights including CTOT, the time window is strictly limited to 10 minutes before and after COBT (i.e., fine-tuning of COBT), and AOBT (actual wheel chock removal time) is executed within this time window.

[0137] Empirical Verification and Application Output Phase: This embodiment conducted a large-scale verification test based on real flight data from Lukou International Airport in a provincial capital city, constructing a scheduling simulation environment based on 7,658 departing flights throughout June 2023. By comparing scheduling indicators before and after optimization, the applicability and superiority of the method of this invention in practical application were verified: such as... Figure 4-6 As shown, taxiing efficiency has improved: average taxiing time has decreased by 6.4%, extreme long-tail taxiing time has decreased by 58%, and additional taxiing time for key combination flights has decreased by more than 82%; dispatching coordination capabilities have improved: departure on-time rate has increased by 12.1%, CTOT compliance rate has increased by 33.7%, and coordination and dispatching consistency has been enhanced; the system deployment feasibility is high: dispatching results can be used to build a human-assisted decision-making system or an intelligent dispatching platform to support collaborative operations among airports, air traffic control and airlines.

[0138] Compared with existing technologies, this embodiment has the following significant advantages and beneficial effects: Multi-objective coordinated optimization: Unlike traditional single-objective or static rule-based scheduling methods, this invention establishes a joint optimization objective function with departure on-time rate, CTOT compliance rate, and taxiing efficiency as the core, realizing coordinated control of multiple indicators in airport ground scheduling. Dynamic time slot adjustment mechanism: This invention proposes a scheduling strategy based on a combination of SOBT anchoring and COBT window elastic adjustment, enhancing the adaptability and execution flexibility of flight pushback scheduling. Strong applicability and high promotion value: This invention is applicable to hub airports under various operating environments, especially suitable for deployment in the context of high-density flight operations. It can be widely applied to ground taxiing scheduling systems, intelligent tower decision support systems, and air-ground collaborative release platforms, possessing good engineering implementation potential and practical application value.

[0139] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The above descriptions are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A multi-objective scheduling optimization method for departing flights that takes into account CTOT compliance rate, characterized in that, include: S1. Collect airport operation data and establish a scheduling sample library, which includes: flight plan information, actual pushback / removal wheel chock times and CTOT; S2. Establish a multi-objective optimization model for departing flights that takes into account CTOT compliance rate. The multi-objective optimization model aims to maximize the on-time departure rate, maximize the CTOT compliance rate, and minimize taxiing time. The baseline input of the multi-objective optimization model includes smooth taxiing time. S3. Determine and allocate the weights of each objective function using the entropy weight method; S4. Run the multi-objective optimization model and adjust the launch time plan; The smooth taxiing time for each runway-parking stand combination includes: After data cleaning, the remaining flights are grouped according to arrival and departure stages, based on parking positions and runway usage, forming runway-parking position combinations. For each combination, the 10th percentile of the actual taxiing time of all flights in the combination is taken as the corresponding smooth taxiing time. Among them, at least 10 flights in each combination have a smooth taxiing time of less than that of the combination. S3 includes: The weights of each objective function are determined by the entropy weight method based on the constraints, wherein the constraints include: parking stand conflict constraints, runway clearance interval constraints, and CTOT time window constraints. The parking position conflict constraint is as follows: The runway release interval constraint is as follows: , The CTOT time window constraint is as follows: ,in, Let i and j represent the set of aircraft IDs, where i and j represent the aircraft IDs in the set. This represents the set of parking positions. Indicates the parking position number. Indicates the first Aircraft enters the runway time, Indicates the first The launch time of the aircraft. Indicates the parking position to the runway Smooth gliding time, Indicates the first The aircraft in Runway calculation of takeoff time Indicates the first The aircraft in The actual takeoff time of the runway This represents the indicator variable used to identify flights that include CTOT. Comprehensive factors indicating runway occupancy time , This indicates the runway clearance interval.

2. The method according to claim 1, characterized in that, In S1, the collection of airport operation data includes: Collect all flight operation data of the target airport within a specified period. The types of all flight operation data collected include: basic flight information, taxiway information, ground resource and restriction information, and environmental status information. Collect surface structure data of the target airport and construct a directed graph model of the airport taxiing area.

3. The method according to claim 2, characterized in that, In S1, the establishment of the scheduling sample library includes: Flight operation data is extracted from and standardized from the collected full flight operation data, including: planned wheel chock removal time, calculated wheel chock removal time, actual wheel chock removal time, calculated takeoff time, actual takeoff time, aircraft type, parking position, runway used, taxiing time and taxiing path, and the clear taxiing time corresponding to each runway-parking position combination.

4. The method according to claim 1, characterized in that, The actual launch time of the flight is used as the main decision variable in the multi-objective optimization model. The multi-objective optimization model includes: ,in, , , They are respectively the corresponding The weight, The objective functions for departure regularity rate are respectively: Objective functions for CTOT compliance rate and objective functions for coasting time.

5. The method according to claim 4, characterized in that, The objective function for the departure regularity rate is: Where N represents the total number of flights. Indicates the first The aircraft in the first Release date Indicates the first The aircraft is parked at the parking position. The planned time for removing the wheel chocks, It is an indicator function that takes the value 1 when the condition is true, and 0 otherwise; The objective function for CTOT compliance rate is: ,in, Indicates the first The aircraft in The actual takeoff time of the runway Indicates the first The aircraft in Runway calculation of takeoff time , This indicates an indicator variable used to identify flights that include CTOT; The objective function for the gliding time is: .

6. The method according to claim 1, characterized in that, S4 includes: The parameter set for the multi-objective optimization model is as follows: ; Represents the set of aircraft numbers. This represents the set of parking positions. This indicates the set of runways that an aircraft may occupy. Indicates the first The aircraft is parked at the parking position. The planned time for removing the wheel chocks, Indicates the first The aircraft in Runway calculation of takeoff time Indicates the first The aircraft in Runway calculation of wheel chock removal time Indicates the first Aircraft on the runway The time the runway occupies; Calculate the feasible departure time from the parking position and add it to the unobstructed taxiing time to obtain the initial arrival time interval. ; For each runway gate, generate conflict-free time slots and determine the actual departure time of flights occupying parking positions; Update the parking space occupancy schedule.

7. The method according to claim 6, characterized in that, The generation of conflict-free time slots for each runway entrance includes: According to runway release intervals Will Discretize into time slots; Eliminate time and space overlap with already scheduled flights; Prioritize the reallocation of time windows for CTOT flights within conflict time slots.

Images