Apparatus, method and computer readable medium for monitoring airport congestion

Abstract

The present disclosure relates to apparatuses, methods, and computer-readable media for monitoring airport congestion. An apparatus includes one or more processors configured to generate an operational congestion indicator associated with a particular airport, wherein the operational congestion indicator is based on at least one or more usage indicators of the particular airport. The one or more processors are configured to nonlinearly generate an impact congestion indicator based on at least the operational congestion indicator. The one or more processors are configured to determine a congestion forecast for the particular airport based on the impact congestion indicator. The one or more processors are configured to transmit a congestion alert for the particular airport, wherein the congestion alert is based on at least the congestion forecast.

Description

Technical Field

[0001] This disclosure generally pertains to monitoring airport congestion. Background Technology

[0002] Air traffic networks are highly dependent on airport arrival and departure processes, which are related to capacity constraints and delay propagation. To minimize delays in air traffic networks and achieve an improved balance between demand and capacity, it is crucial to accurately assess and predict potential congestion at airports.

[0003] Traditionally, congestion at airports is measured by comparing scheduled times with the actual times flights depart from or arrive at the airport. For example, a traditional metric for calculating congestion is the average departure delay over a period of time—for instance, the average difference between the scheduled departure time and the actual departure time for each flight. However, besides the difficulty in accessing each specific airport from the outside, flight schedule information is often inaccurate and can change significantly over time.

[0004] Another traditional approach that airports can use is to calculate congestion based on passenger flow and available resources, such as ground staff and air traffic controllers in the tower. This approach works well for generating customized congestion calculations for a specific airport, but because the input data (e.g., passenger flow and resource availability) is not globally available, and the models used may be tailored to a specific airport, the practicality of these techniques is largely limited to local calculations at each particular airport.

[0005] An improved system for predicting potential airport congestion will enable enhanced operation and efficiency of air traffic networks, without relying on timetable information or other specific data available only at each particular airport. Summary of the Invention

[0006] One aspect of the subject matter disclosed in detail below is an apparatus comprising one or more processors configured to generate operational congestion indicators associated with a particular airport, wherein the operational congestion indicators are based at least on one or more usage indicators of the particular airport. The one or more processors are configured to non-linearly generate congestion-influencing indicators based at least on the operational congestion indicators. The one or more processors are configured to determine congestion forecasts for the particular airport based on the congestion-influencing indicators. The one or more processors are configured to transmit congestion alerts for the particular airport, wherein the congestion alerts are based at least on the congestion forecasts.

[0007] Another aspect of the subject matter disclosed below is a method that includes generating, via a processor, operational congestion indicators associated with a specific airport, wherein the operational congestion indicators are based at least on one or more usage indicators of the specific airport. The method includes, via a processor, non-linearly generating congestion-influencing indicators, at least based on the operational congestion indicators. The method includes, via a processor, determining congestion forecasts for the specific airport based on the congestion-influencing indicators. The method includes, via a processor, transmitting congestion alerts for the specific airport, wherein the congestion alerts are based at least on the congestion forecasts.

[0008] Another aspect of the subject matter disclosed in detail below is a non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to generate operational congestion indicators associated with a particular airport, wherein the operational congestion indicators are based at least on one or more usage indicators of the particular airport. These instructions, when executed by one or more processors, cause the one or more processors to non-linearly generate congestion impact indicators based at least on the operational congestion indicators. These instructions, when executed by one or more processors, cause the one or more processors to determine congestion forecasts for the particular airport based on the congestion impact indicators. These instructions, when executed by one or more processors, cause the one or more processors to transmit congestion alerts for the particular airport, wherein the congestion alerts are based at least on the congestion forecasts.

[0009] The features, functions, and advantages described herein can be implemented independently in various ways or combined in other ways. Further details can be found in the following description and figures. Attached Figure Description

[0010] Figure 1 A system is shown that includes components associated with monitoring airport congestion, according to some embodiments of the present disclosure.

[0011] Figure 2 This is a diagram illustrating the calculation of example operating throughput (OTR) over time for multiple aircraft operations according to some embodiments of the present disclosure.

[0012] Figure 3 Example diagrams illustrating the relationship between operational congestion indicators and influencing congestion indicators are shown according to some embodiments of the present disclosure.

[0013] Figure 4 This is a flowchart illustrating a method for monitoring airport congestion according to some embodiments of the present disclosure.

[0014] Figure 5This is a block diagram of a computing environment according to the present disclosure, which includes computing devices configured to support aspects of computer-implemented methods and computer-executable program instructions (or code). Detailed Implementation

[0015] This paper discloses various aspects of systems and methods for monitoring airport congestion. Traditional techniques for monitoring airport congestion often rely on timetable information that may be inaccurate and difficult to access externally for each specific airport, and / or other data such as passenger flow and resource availability that are only available at each specific airport. This makes it difficult for air traffic management to predict potential airport congestion for air traffic between multiple airports.

[0016] This disclosure solves the problem of predicting potential airport congestion using airport data that is often inaccurate or difficult to access by introducing techniques for using globally available data to calculate congestion at any airport in the world where such data is available. For example, according to this disclosure, usage metrics for a particular airport can be calculated based on information that can be extracted from globally available data sources such as surveillance information (e.g., location reports), airport map database (AMDB) data, and weather reports.

[0017] Airport traffic information can be computed in real time based on this globally available data and used to determine the congestion level at each airport of interest. Examples of traffic information that can be used for a specific time interval and at a specific airport include: the number of taxiing operations for arriving aircraft, the number of taxiing operations for departing aircraft, the number of aircraft that have taken off, the number of aircraft that have landed, the number of aircraft about to arrive, the number of aircraft moving on the ground, and the number of aircraft following a waiting pattern. These traffic counts can be determined using a sliding window to measure the results across different time intervals. Furthermore, weather information can be used to differentiate between different types of weather conditions (such as varying visibility conditions) at the airport during each time interval. This information can be grouped by airport and hour of day to obtain historical data distribution of total operational events occurring at a specified airport at that hour. The historical data distribution can be further refined based on the various types of weather conditions present at the specified airport where the operational events occurred.

[0018] The systems and methods disclosed herein can be used to generate one or more traffic congestion metrics using the exemplary metrics described above. For example, operational congestion metrics may include Operational Throughput (OTR). OTR is the ratio between actual operational events and scheduled operational events. In some implementations, a nominal situation includes an OTR of 1, indicating that a particular airport is handling the expected operational events. An OTR value greater than 1 indicates that a particular airport is experiencing overflow of inbound and / or outbound flights. An OTR value less than 1 indicates that a particular airport cannot handle the expected operational events.

[0019] As another embodiment, the congestion metric can be based on an operational congestion metric. In some implementations, this may include combining OTR data for a specific airport with operational delay data. The delay data may indicate, for example, the average delay of relevant operational events at a specific airport. OTR values ​​and delay values ​​can be calculated over predetermined time periods. Each time period may be the same or different. For example, the time window associated with the OTR-based operational congestion metric may be approximately thirty minutes. To calculate the delay data, the systems and methods disclosed herein can calculate the number of operational events every ten minutes and the associated average delay over the most recent thirty minutes.

[0020] As described in more detail below, congestion metrics can be combined in a non-linear manner. For example, OTR data and delay data can be combined into a single congestion metric to facilitate consumer understanding. Departures and arrivals can each have their own dedicated congestion metrics. Congestion metrics allow users to gain a relatively quick and understandable insight into the current state of traffic flow at the airport.

[0021] Congestion metrics can also be used to generate congestion predictions for specific airports. For example, trained machine learning models can generate congestion predictions. Based on these predictions, the systems and methods disclosed in this paper can also generate congestion alerts. Congestion alerts can notify users of information related to predicted congestion at the airport (e.g., unexpectedly low congestion, unexpectedly high congestion, congestion updates, etc.).

[0022] Systems using the disclosed technology therefore employ data-driven statistical methods to determine or predict congestion at a specific airport at a specific time. The technical advantages of this disclosure include improved automated flight planning. The disclosed systems and methods provide a holistic overview of global airport congestion status through accurate and global calculations using publicly available data sources rather than incomplete datasets or data that is very specific to a single airport and not globally available. Therefore, more accurate flight planning can be achieved using the disclosed systems and methods.

[0023] Another technical advantage of this disclosure is the improved congestion prediction calculation system. Some previous congestion prediction systems do not consider the validity of historical operational data. This leads to inaccurate congestion predictions based on anomalous congestion conditions at different points in the past. The disclosed system and method consider the validity of historical data, thereby improving the automated congestion prediction calculation system. For example, the system and method disclosed herein describe a congestion index that considers the historical validity of a particular airport by periodically calculating the parameters of a logistic function that correlates operational congestion indicators with those influencing congestion indicators, and periodically calculating a nominal point of this relationship.

[0024] Specific embodiments are illustrated in the accompanying drawings and the following description. All drawings are covered by this technical solution, which has common features across the various drawings. The drawings include multiple examples of different types of systems, apparatuses, and operations that may be combined with this technical solution. It should be understood that those skilled in the art will be able to design various arrangements, although not explicitly described or shown herein, that embody the principles described herein and are included within the scope of the claims following this description. Furthermore, any embodiments described herein are intended to aid in understanding the principles of this disclosure and are not intended to be limiting. Therefore, this disclosure is not limited to the specific embodiments or examples described below, but is defined by the claims and their equivalents.

[0025] Specific embodiments are described herein with reference to the accompanying drawings. Throughout the description, common features are indicated by common reference numerals. In some drawings, multiple instances of a particular type of feature are used. Although these features are physically and / or logically different, the same reference numerals are used for each feature, and different instances are distinguished by the addition of letters to the reference numerals. When a feature is referred to herein as a group or type (e.g., when a specific feature within a group of features is not mentioned), reference numerals are used without distinguishing letters. However, when a specific feature among multiple features of the same type is referred to herein, reference numerals are used with distinguishing letters. For example, reference... Figure 2 Multiple aircraft operation events are shown and associated with reference numerals 214A-214I. When referring to a specific operation event among these aircraft operation events, such as aircraft operation event 214A, the distinguishing letter "A" is used. However, when referring to any operation event among these aircraft operation events or when these aircraft operation events are mentioned as a group, reference numeral 214 is used without the distinguishing letter.

[0026] As used herein, various terms are used for the purpose of describing particular embodiments and are not intended to be limiting. For example, unless the context clearly indicates otherwise, the singular forms “an,” “a,” and “the” are intended to also include the plural forms. Furthermore, some features described herein may be singular or plural. For illustration, Figure 5 It describes a system that includes one or more processors ( Figure 5 The device of “processor 520” in the document may include a single processor 520 or may include multiple processors 520. For ease of reference herein, this feature is generally introduced as “one or more” features and is subsequently referred to in the singular unless an aspect relating to multiple features is described.

[0027] The terms “comprise,” “comprises,” and “comprising” are used interchangeably with “include,” “includes,” or “including.” Furthermore, the term “wherein” is used interchangeably with the term “where.” As used herein, “exemplary” indicates an embodiment, implementation, and / or aspect and should not be construed as limiting or indicating a preference or preferred implementation. As used herein, ordinal terms used to modify elements (such as structures, components, operations, etc.) (e.g., “first,” “second,” “third,” etc.) do not themselves indicate any priority or order of that element relative to another element, but merely distinguish that element from another element having the same name (other than the use of ordinal terms). As used herein, the term “set” refers to a grouping of one or more elements, and the term “multiple” refers to multiple elements.

[0028] As used herein, the terms “acquire,” “generate,” “calculate,” “use,” “select,” “access,” and “determine” are interchangeable unless the context otherwise indicates. For example, “acquire,” “generate,” “calculate,” or “determine” a parameter (or signal) can refer to actively generating, calculating, or determining a parameter (or signal), or it can refer to using, selecting, or accessing a parameter (or signal) that has already been generated, such as through another component or device. As used herein, a device “configured to” perform an operation includes dedicated circuitry, hardware, or other components that enable the operation to be performed by the device. As an example, a dedicated processor is obtained by programming a general-purpose processor with instructions that, when executed by the processor, cause the processor to perform that specific operation. A device can be configured to perform multiple operations. A device configured to perform an operation does not necessarily preclude the device from being configured to perform other operations.

[0029] As used herein, “coupling” can include “communication coupling,” “electrical coupling,” or “physical coupling,” and may also (or alternatively) include any combination thereof. Two devices (or components) may be coupled directly or indirectly (e.g., communication coupling, electrical coupling, or physical coupling) via one or more other devices, components, wires, buses, networks (e.g., wired networks, wireless networks, or combinations thereof). Two electrically coupled devices (or components) may be in the same or different devices and, as an illustrative, non-limiting embodiment, may be connected via electronics, one or more connectors, or inductive coupling. In some implementations, two communication-coupled (e.g., communicating electrically) devices (or components) may transmit and receive electrical signals (digital or analog signals) directly or indirectly, for example, via one or more wires, buses, networks, etc. As used herein, “direct coupling” is used to describe two devices coupled (e.g., communication coupling, electrical coupling, or physical coupling) without intermediate components.

[0030] refer to Figure 1 According to some embodiments of this disclosure, system 100 is shown to include components associated with monitoring airport congestion. System 100 includes a computing device 102 coupled to one or more devices 104 and one or more globally available data sources 136. Device 104 may include one or more electronic devices, including one or more processors 132 coupled to memory 134. Device 104 may be configured to transmit data to computing device 102 (e.g., one or more usage indicators 122), receive data from computing device 102 (e.g., one or more congestion alerts 138), or some combination thereof.

[0031] Globally available data source 136 includes one or more sources of global data associated with aircraft traffic. For example, globally available data source 136 may include: an airport map database that provides map data on runways, taxiways, etc. of various airports; an aircraft tracking data source that provides location data (e.g., radar surveillance data) of aircraft near the airport; and a weather data source that provides current weather data, weather forecasts, or both for the airport.

[0032] Globally available data sources 136 may include Airport Map Databases (AMDBs), aircraft tracking data sources, weather data sources, or some combination thereof. An Airport Map Database may include or correspond to one or more AMTBs that store data associated with one or more airports subject to congestion detection by System 100. For illustration, an AMTB may include a dataset representing the spatial layout of an airport based on features that can be described as points, lines, polygons, etc. (e.g., runways, taxiways, parking stands), as well as other information such as surface types. In an embodiment, an AMTB includes data in a format conforming to Geographic Information System (GIS) types.

[0033] Aircraft tracking data sources may include or correspond to sources or collections of location reports. For illustration, aircraft tracking data sources may include internet-based services that provide real-time commercial aircraft flight tracking information from one or more aggregated sources: departure and destination, flight number, aircraft type, location, altitude, heading, and speed, such as services like FLIGHTRADAR24 (FLIGHTRADAR24 is a trademark of Flightradar24 AB, based in Stockholm, Sweden).

[0034] Weather data sources may include or correspond to a collection of current weather reports. For example, a weather report may correspond to a Meteorological Terminal Aviation Routine Weather Report (METAR) type report from an airport, a weather observation station, one or more sources, or any combination thereof. Alternatively or additionally, a weather report may correspond to a Terminal Airport Weather Forecast (TAF) type forecast report.

[0035] The computing device 102 includes one or more processors 106 coupled to memory 108. Processor 106 may include various components such as a congestion indicator generator 110, a congestion predictor 112, or combinations thereof. In some implementations, the congestion indicator generator 110 may be configured to generate an operational congestion indicator 114 associated with a specific airport. In some aspects, the congestion indicator generator 110 may be configured to generate a plurality of operational congestion indicators 114, wherein each of the plurality of operational congestion indicators 114 is associated with a different specific airport. In the same or alternative aspects, the operational congestion indicator 114 may include a plurality of congestion indicators. For example, the congestion indicator generator 110 may be configured to generate operational congestion indicators 114 including generating a first takeoff congestion indicator associated with takeoffs at a specific airport and a first landing congestion indicator associated with landings at a specific airport.

[0036] Operational congestion metric 114 is based at least on one or more usage metrics 122 for a specific airport. As described above, usage metrics 122 may include operational data associated with a specific airport. For example, usage metrics 122 may include flight event data, flight schedule data, weather data, or a combination thereof. As another embodiment, usage metrics 122 may include planned flight event data, planned flight operation data, actual flight event data, actual flight operation data, or a combination thereof. Each usage metric 122 may each include data associated with a time frame. The time frames for each usage metric 122 do not need to be the same. For example, flight event data, flight schedule data, and weather data may be received by a computing device in real-time or near real-time, hourly, daily, etc., or a combination thereof. In some aspects, usage metrics 122 may be stored at memory 108. In a particular aspect, processor 106 may be configured to acquire usage metrics 122. For example, processor 106 may be configured to acquire usage metrics 122 from a globally available data source 136.

[0037] In some respects, the operational congestion metric 114 may include Operational Turnover (OTR). As mentioned above, OTR is the ratio between actual operational events and scheduled operational events. See the following reference... Figure 2 As described, the OTR can be associated with a first time window for an operational event at a specific airport. For example, the first time window may include a thirty-minute time window. In other embodiments, the first time window may include other values ​​for the OTR time window (e.g., ten minutes, one hour, etc.). Smaller time windows typically provide enhanced temporal resolution and relatively less congestion attenuation compared to larger time windows, while larger time windows are generally less susceptible to noise compared to smaller time windows. Different implementations utilize corresponding time windows that balance these adversarial factors, such as those tailored to different specific performance criteria.

[0038] In some implementations, the congestion indicator generator 110 may be configured to non-linearly generate impact congestion indicators 116 based at least on operational congestion indicators 114. In some aspects, the congestion indicator generator 110 may be configured to generate a plurality of impact congestion indicators 116, wherein each of the plurality of impact congestion indicators 116 is associated with a different specific airport. In the same or alternative aspects, impact congestion indicators 116 may include multiple congestion indicators. For example, the congestion indicator generator 110 may be configured to generate impact congestion indicators 116 including generating a second takeoff congestion indicator associated with takeoffs at a specific airport and a second landing congestion indicator associated with landings at a specific airport.

[0039] The congestion index 116 is non-linearly based on the operational congestion index 114. For example, see the reference below. Figure 3 As shown, the congestion impact index 116 is correlated with the operational congestion index 114 via a logical function. In a specific embodiment, the congestion impact index 116 is correlated with the operational congestion index 114 according to the following formula, wherein, This affects the congestion index of 116. It is the growth rate associated with the impact on the congestion index 116, and It is the midpoint affecting the congestion index 116 (i.e., obtaining) (value)

[0040] In some aspects, the magnitude of the impact on the congestion index 116 can be determined in advance. This is to make it easy for users to understand the factors affecting congestion index 116. For example, the magnitude... The value can be 10, to achieve a scale from one to ten for the impact of the congestion index 116.

[0041] In some implementations, the congestion indicator generator 110 can be configured to further modify the congestion indicator 116. For example, the congestion indicator generator 110 can be configured to determine the congestion indicator 116, including modifying the congestion indicator 116 based at least on its value during a second time window. The second time window is earlier than the first time window. For example, as referenced below... Figure 3 As shown, the congestion index generator 110 can classify the factors affecting congestion index 116 into one of a number of congestion levels. For illustration, the multiple congestion levels can include a number of classification levels, such as "very low", "moderate", and "very high". Each classification level can have a corresponding color for reporting purposes (e.g., green, yellow, and red, respectively).

[0042] The initial classification in the congestion level can be based on the value of the influencing congestion index 116 during a first time window. In some implementations, the change in the influencing congestion index 116 from one time window to another may be drastic. To make congestion predictions more useful or informative for users, the congestion index generator 110 can be configured to impose constraints on the change in the value of the influencing congestion index 116 from one time window to subsequent time windows. For example, if the influencing congestion index 116 indicates a “very high” level of traffic congestion in an earlier time window (e.g., ten on a scale of one to ten), but indicates a “very low” level of traffic congestion in a subsequent time window (e.g., two on a scale of one to ten), the congestion index generator 110 can be configured to impose constraints on the value of the influencing congestion index 116 to more closely approximate the user experience of changing traffic congestion. The congestion index generator 110 can be configured to change the influencing congestion index 116 by only one congestion level each time from one reporting time window to the next. Therefore, even if the congestion index 116 has a "very low" value in the above embodiments, the congestion index 116 can be transmitted to the user as a "moderate" level of traffic congestion (e.g., via congestion alert 138).

[0043] In another configuration, the congestion indicator generator 110 can be configured to impose a constraint on the value of the congestion indicator 116 by limiting the variation in the value of the congestion indicator 116 between consecutive time windows. In an illustrative embodiment, the congestion indicator generator 110 can limit the amount of change allowed in the congestion indicator 116 on a scale of one to ten from one reporting time window to the next. For example, if the value of the congestion indicator 116 is ten in an earlier time window (i.e., the second time window) and zero in a later time window (i.e., the first time window), the congestion indicator generator 110 can be configured to allow the congestion indicator 116 to change by only one unit on a scale of one to ten, thereby reporting a value of nine for the congestion indicator 116 in the later time window. This constraint can be continued to be imposed through subsequent time windows. For example, if the value of congestion index 116 in the third time window following the first time window is five, then congestion index generator 110 can be configured to report a value of eight on a scale of one to ten (i.e., based on the fact that the value is actually lower than the previously reported value, but is constrained to decrease by only one). If the value of congestion index 116 returns to ten in the fourth time window following the third time window, then congestion index generator 110 can be configured to report a value of nine on a scale of one to ten (i.e., based on the fact that the value is actually higher than the previously reported value, but is constrained to increase by only one).

[0044] In some implementations, processor 106 may also include congestion predictor 112. Congestion predictor 112 may be configured to determine congestion prediction 118 for a specific airport based on congestion metric 116. For example, congestion predictor 112 may consider historical congestion metric data, operational data, environmental data, etc., to determine congestion prediction 118.

[0045] In some aspects, the congestion predictor 112 can be configured to determine a congestion prediction 118, including by using a trained machine learning model 120. The trained machine learning model 120 can be trained on specific training data. Training data may include historical congestion index data 124, flight event data 126, flight schedule data 128, weather data 130, one or more other datasets, or some combination thereof. In some configurations, this data may be stored at memory 108. Once trained, the trained machine learning model 120 can be configured to determine the congestion prediction 118 based on influencing congestion index 116. In some configurations, once trained, the machine learning model 120 can also (or alternatively) receive other data as input to congestion prediction operations. This other data includes hours of the day, days of the year, departure and / or arrival data from actual operational events, departure and / or arrival data from planned operational events, the number of waiting, turning, circling, taxiing operations of arriving aircraft and their average duration, the number of taxiing operations of departing aircraft and their average duration, the number of aircraft that have arrived and / or departed in the most recent time window, or some combination thereof.

[0046] In some implementations, processor 106 may also be configured to transmit congestion alerts 138 for a specific airport. Congestion alert 138 is based at least on congestion prediction 118. For example, congestion alert 138 may include warning alerts (e.g., “abnormally high traffic congestion,” “abnormally low traffic congestion,” etc.), information alerts (e.g., reports of current values ​​affecting congestion metric 116), other appropriate alerts, or some combination thereof. Congestion alert 138 may include data associated with different types of alerts, including text, visual indicators, audio indicators, other appropriate indicators, or some combination thereof. Furthermore, congestion alert 138 may include data associated with multiple airports affecting congestion metric 116. For example, congestion alert 138 may include data associated with a map of an area including multiple airports, where each airport is associated with a color indicating its current level of traffic congestion (e.g., green for “low,” yellow for “medium,” and red for “high”).

[0047] In some implementations, congestion alert 138 may be received by device 104. Device 104 may include electronic devices associated with airport personnel (e.g., smartphones, tablets, etc.), electronic devices associated with air traffic management systems, etc. Each device 104 may be configured to further transmit and / or modify the data of congestion alert 138 before presenting it to the user of device 104. For example, in the embodiment described above that includes a map indicating traffic congestion levels at multiple airports, the processor 132 of device 104 may be configured to generate map data that can be used to display the data of congestion alert 138 to improve the user experience for the user of device 104.

[0048] In some embodiments, by issuing a congestion alert 138, airport personnel and / or the air traffic management system can take proactive measures to reduce or mitigate predicted congestion or the potential impact of congestion at the airport. As an example, additional personnel may be notified that they may be called up to services to help mitigate predicted congestion.

[0049] In some embodiments, by issuing a congestion alert 138, airport personnel and / or the air traffic management system can take remedial measures to reduce or alleviate congestion at the airport. As an example, additional personnel may be deployed to the service to help alleviate congestion.

[0050] By implementing mitigation actions in response to updates to one or more congestion forecasts 118, timetable adjustments can be made to reflect anticipated delays due to increased airport congestion, and the adjusted flight forecasts can be disseminated at the airport via arrival and departure flight timetables to provide a more accurate timetable of flight operation events for use by airport staff, crew, and passengers.

[0051] By implementing mitigation actions, including the reallocation of one or more resources at a specific airport, resources such as gate allocation, crew members, ground staff, and other resources associated with aircraft turnaround can be reallocated to reduce the inefficiencies anticipated due to delays caused by airport congestion. For example, when airport congestion is expected to delay the arrival of a particular aircraft (which in turn will lead to anticipated delays in the departure of that particular aircraft on subsequent flights), resource allocation may include performing a tail swap, in which a different aircraft is assigned to a subsequent flight to reduce or eliminate the anticipated delay in the departure of that flight.

[0052] Aircraft efficiency can be improved by implementing mitigation measures, which include adjusting the flight plan of an aircraft en route to a specific airport, to enhance fuel efficiency. For example, when anticipated congestion at the expected arrival airport causes an aircraft to enter a holding mode upon arrival, the flight plan can be adjusted to reduce the aircraft's speed. Compared to following the initial flight plan, this not only reduces the amount of time the aircraft spends in holding mode, but also improves the aircraft's fuel efficiency for the remaining flight distance.

[0053] While computing devices 102 and 104 can be implemented in separate devices, alternatively, components associated with computing devices 102 and 104 can be included in a single device. For example, a single device may include one or more processors, including (or otherwise configured to perform operations associated with) a congestion metric generator 110, a congestion predictor 112, or a combination thereof. Alternatively, one or more of the components (e.g., a trained machine learning model 120) may be implemented in another subsystem (e.g., a machine learning subsystem communicating with the congestion predictor 112). Furthermore, one or more of the globally available data sources 136 may be integrated with each other, integrated with the computing device, or different from computing device 102, etc.

[0054] Although the congestion indicator generator 110 and the congestion predictor 112 are shown as different components, the functionality of the congestion indicator generator 110 and the congestion predictor 112 can optionally be combined into a single component.

[0055] Although the above embodiments describe the congestion index 116 on a scale of one to ten, such embodiments are provided for illustrative purposes and should not be considered limiting. For example, the congestion index 116 may be based on a scale of one to one hundred, a scale of zero to fifty, etc. Furthermore, although the above embodiments describe the congestion index 116 as being related to the operational congestion index 114 according to a logical function, other nonlinear relationships between the operational congestion index 114 and the congestion index 116 may be included without departing from the scope of this disclosure.

[0056] Figure 2 This is a graphical representation of an example OTR calculation 200 depicting multiple aircraft operation events 214 over time according to some embodiments of the present disclosure. The example OTR calculation 200 includes multiple aircraft operation events 214 plotted against a first axis 212 associated with time. The further to the left of the example OTR calculation 200, the earlier the aircraft operation event 214, and the further to the right, the later the time.

[0057] Example OTR calculation 200 includes two sets of aircraft operating events 214. The first set 202 includes data indicating actual aircraft operating events (e.g., aircraft operating events 214A through 214D). The second set 204 includes data indicating planned aircraft operating events (e.g., aircraft operating events 214E through 214I). OTR is calculated as the ratio of aircraft operating events 214 in the first set 202 to those in the second set 204 within a specific time window. Example OTR calculation 200 includes three exemplary time windows 206, 208, and 210. Exemplary time windows 206, 208, and 210 have the same duration, but their start times are staggered. Figure 2 In the example, each of the exemplary time windows 206, 208, and 210 represents a thirty-minute time window, wherein each subsequent time window begins ten minutes after the beginning of the previous time window. Other configurations are possible without departing from the scope of this disclosure.

[0058] The first time window 206 indicates an OTR of 0.5 (or 1 / 2). Within the first time window 206, there are two planned aircraft operation events 214E and 214F, and one actual aircraft operation event 214A. The second time window 208 also indicates an OTR of 0.5 (or 1 / 2). Within the second time window 208, there are two planned aircraft operation events 214F and 214G, and one actual aircraft operation event 214B. The second time window 210 indicates an OTR of 1 (or 3 / 3). Within the third time window 210, there are three planned aircraft operation events 214G, 214H, and 214I, and three actual aircraft operation events 214B, 214C, and 214D.

[0059] Figure 3 Example graph 300 illustrating the relationship between operational congestion indicators and influencing congestion indicators according to some embodiments of this disclosure is shown. Graph 300 includes two relationship lines 306 and 308. The first relationship line 306 is associated with airports having a first rated condition. The second relationship line 308 is associated with airports having a second rated condition. For example, the first relationship line 306 is associated with airports with a rated OTR of 1. The second relationship line 308 is associated with airports with a rated OTR other than 1. Each airport may have a specific set of data characteristics associated with the airport, which may result in a particular airport having a different OTR rating. For example, general aviation airports, airports with insufficient surveillance data (e.g., unavailable, reporting at insufficient frequency, etc.), airports that do not provide timetable data, etc., may have different rated OTR values.

[0060] Example graph 300 shows relationship lines 306 and 308 plotted against two axes. The first axis 302 is related to the values ​​affecting congestion indicators (e.g., Figure 1 The impact of the congestion index 116 is related to the second axis 304, which is associated with the OTR value (e.g., Figure 1 The operational congestion index (114) is correlated with this. Relationship lines 306 and 308 illustrate the non-linear relationship between the OTR value on the second axis 304 and the value of the impact congestion index on the first axis 302. This non-linear relationship can, for example, be used to mitigate the impact congestion index value around a nominal point of the OTR value.

[0061] Example graph 300 shows relationship lines 306 and 308, which reflect the asymmetry around the corresponding nominal points. For example, relationship line 306 has a corresponding nominal point at OTR=1, while relationship line 308 has a corresponding nominal point at OTR<1. At the nominal points, congestion may be relatively low (e.g., zero). The value along the first axis 302 increases non-linearly from either side of the nominal point, but at different rates.

[0062] Example graph 300 also shows the values ​​of congestion indicators highlighted according to multiple congestion levels 310, 312, and 314. Congestion levels 310, 312, and 314 can indicate, for example, "low," "medium," and "high" levels of traffic congestion. The first congestion level 314 is associated with a low traffic congestion level, the second congestion level 312 with a medium traffic congestion level, and the third congestion level 310 with a high traffic congestion level. Although... Figure 3 Three traffic congestion levels are shown, but more, fewer and / or different traffic congestion levels may exist without departing from the scope of this disclosure.

[0063] Figure 4 This is a flowchart illustrating a method 400 for monitoring airport congestion according to some embodiments of the present disclosure. In a particular implementation, method 400 is performed by a congestion index generator 110, a congestion predictor 112, a processor 106, or a combination thereof.

[0064] Method 400 includes: at box 402, by a processor, generating an operational congestion metric associated with a specific airport, wherein the operational congestion metric is based at least on one or more usage metrics for the specific airport. For example, Figure 1 The congestion index generator 110 can be configured to generate operational congestion index 114. The operational congestion index 114 is based at least on the usage index 122 of a specific airport.

[0065] Method 400 includes: at box 404, by a processor, non-linearly generating congestion-affecting indicators, at least based on operational congestion indicators. For example, Figure 1 The congestion index generator 110 can be configured to nonlinearly generate an impact congestion index 116 based at least on the operational congestion index 114.

[0066] Method 400 includes: at box 406, using a processor, determining congestion forecasts for a specific airport based on indicators affecting congestion. For example, Figure 1 The congestion predictor 112 can be configured to determine congestion predictions 118 for a specific airport based on congestion indices 116.

[0067] Method 400 includes: at box 408, transmitting a congestion alert for a specific airport via a processor, wherein the congestion alert is based at least on congestion prediction. For example, Figure 1 The processor 106 can be configured to transmit congestion alerts 138 for a specific airport. The congestion alerts 138 are based at least on congestion predictions 118.

[0068] Method 400 may optionally include methods that can be derived from... Figure 1 The processor 106 performs one or more actions. For example, the congestion index generator 110 may generate operational congestion index 114, including generating a first takeoff congestion index associated with takeoffs at a specific airport and a first landing congestion index associated with landings at a specific airport. Similarly, the congestion index generator 110 may generate impact congestion index 116, including generating a second takeoff congestion index associated with takeoffs at a specific airport and a second landing congestion index associated with landings at a specific airport.

[0069] Method 400 thus enables the determination of congestion levels at a specific airport using globally available public data. Therefore, as an illustrative and non-limiting embodiment, method 400 enables mitigation actions to reduce the impact of congestion at individual airports, targeting individual flights, fleets operated by one or more airlines, or air traffic management systems.

[0070] Figure 5 This is a block diagram of a computing environment 500, which includes computing device 510 configured to support aspects of computer-implemented methods and computer-executable program instructions (or code) according to this disclosure. For example, computing device 510 or a portion thereof is configured to execute instructions to initiate, execute, or control references. Figures 1 to 4 One or more operations are described. In some implementations, computing device 510 corresponds to computing device 102, device 104, globally available data source 136, or a combination thereof.

[0071] Computing device 510 includes one or more processors 520. The one or more processors 520 are configured to communicate with system memory 530, one or more storage devices 550, one or more input / output interfaces 540, one or more communication interfaces 560, or any combination thereof. System memory 530 includes volatile memory devices (e.g., random access memory (RAM) devices), non-volatile memory devices (e.g., read-only memory (ROM) devices, programmable read-only memory, and flash memory), or both. System memory 530 stores operating system 532, which may include a basic input / output system for booting computing device 510 and a complete operating system enabling computing device 510 to interact with users, other programs, and other devices. System memory 530 stores program data 538 (system data), such as usage metrics 122 from globally available data sources 136.

[0072] System memory 530 includes one or more application programs 534 (e.g., instruction sets) that can be executed by one or more processors 520. As an example, one or more application programs 534 include those that can be executed by one or more processors 520 to initiate, control, or execute references. Figures 1 to 4 Instructions for one or more operations described. For illustration, one or more applications 534 include instructions 536 that can be executed by one or more processors 520 to initiate, control, or perform one or more operations described by the reference congestion indicator generator 110, the congestion predictor 112, or a combination thereof.

[0073] System memory 530 includes a non-transitory computer-readable medium storing instructions that, when executed by one or more processors 520, cause the one or more processors 520 to: generate operational congestion indicators associated with a particular airport, wherein the operational congestion indicators are based at least on one or more usage indicators of the particular airport; non-linearly generate congestion impact indicators based at least on the operational congestion indicators; determine congestion forecasts for the particular airport based on the congestion impact indicators; and transmit congestion alerts for the particular airport, wherein the congestion alerts are based at least on the congestion forecasts.

[0074] One or more storage devices 550 include non-volatile storage devices, such as disks, optical disks, or flash memory devices. In a particular embodiment, storage device 550 includes both removable and non-removable memory devices. Storage device 550 is configured to store an operating system, images of the operating system, applications (e.g., one or more of applications 534), and program data (e.g., program data 538). In a particular aspect, system memory 530, storage device 550, or both include tangible computer-readable media. In a particular aspect, one or more of storage devices 550 are external to computing device 510.

[0075] One or more input / output interfaces 540 enable computing device 510 to communicate with one or more input / output devices 570 to facilitate user interaction. For example, one or more input / output interfaces 540 may include a display interface, an input interface, or both. For example, input / output interface 540 is adapted to receive input from a user, input from another computing device, or a combination thereof. Input / output interface 540 may conform to one or more standard interface protocols, including serial interfaces (e.g., Universal Serial Bus (USB) interfaces or Institute of Electrical and Electronics Engineers (IEEE) interface standards), parallel interfaces, display adapters, audio adapters, or custom interfaces (“IEEE” is a registered trademark of the Institute of Electrical and Electronics Engineers of Piscataway, New Jersey). Input / output devices 570 may include one or more user interface devices and displays, including some combination of buttons, keyboards, pointing devices, displays, speakers, microphones, touchscreens, and other devices.

[0076] One or more processors 520 are configured to communicate with one or more devices or controllers 580 via one or more communication interfaces 560. For example, the one or more communication interfaces 560 may include a network interface. The one or more devices or controllers 580 may include, for example, a globally available data source 136, device 104, or a combination thereof.

[0077] In conjunction with the described system and method, an apparatus is disclosed comprising components for generating operational congestion indicators associated with a specific airport, wherein the operational congestion indicators are based at least on one or more usage indicators for the specific airport. The components for generating the operational congestion indicators correspond to system 100, computing device 102, congestion indicator generator 110, device or controller 580, input / output device 570, processor 520, one or more other circuits or devices configured to generate operational congestion indicators, or combinations thereof.

[0078] The device includes components for nonlinearly generating congestion indicators based at least on operational congestion indicators. The components for generating congestion indicators correspond to system 100, computing device 102, congestion indicator generator 110, device or controller 580, input / output device 570, processor 520, one or more other circuits or devices configured to generate congestion indicators, or combinations thereof.

[0079] The device includes components for determining congestion forecasts for a specific airport based on indicators affecting congestion. The components for determining the congestion forecasts correspond to system 100, computing device 102, congestion forecaster 112, device or controller 580, input / output device 570, processor 520, one or more other circuits or devices configured to determine the congestion forecasts, or combinations thereof.

[0080] The device includes components for transmitting congestion alerts for a specific airport, wherein the congestion alerts are based at least on congestion predictions. The components for transmitting the congestion alerts correspond to system 100, computing device 102, device 104, device or controller 580, input / output device 570, processor 520, one or more other circuits or devices configured to transmit congestion alerts, or combinations thereof.

[0081] Non-transitory computer-readable media may store instructions that, when executed by one or more processors, cause those processors to initiate, execute, or control operations to perform some or all of the functions described above. For example, these instructions may be executed to implement... Figures 1 to 5 One or more of the operations or methods. Figures 1 to 5 One or more of the operations or methods may be implemented by one or more processors executing instructions (e.g., one or more central processing units (CPUs), one or more graphics processing units (GPUs), one or more neural processing units (NPUs), one or more digital signal processors (DSPs)), by dedicated hardware circuitry, or any combination thereof.

[0082] Specific aspects of this disclosure are described in the following first set of interconnected embodiments: According to Embodiment 1, an apparatus includes one or more processors configured to: generate operational congestion indicators associated with a specific airport, wherein the operational congestion indicators are based at least on one or more usage indicators of the specific airport; nonlinearly generate congestion impact indicators based at least on the operational congestion indicators; determine congestion forecasts for the specific airport based on the congestion impact indicators; and transmit congestion alerts for the specific airport, wherein the congestion alerts are based at least on the congestion forecasts.

[0083] Example 2 includes the apparatus of Example 1, wherein the congestion index is correlated with the operational congestion index through a logic function.

[0084] Example 3 includes the apparatus of Example 1 or Example 2, wherein one or more processors are configured to generate operational congestion indicators, including generating a first takeoff congestion indicator associated with takeoffs at a specific airport and a first landing congestion indicator associated with landings at a specific airport.

[0085] Example 4 includes the apparatus of any one of Examples 1 to 3, wherein one or more processors are configured to generate congestion indices, including generating a second takeoff congestion index associated with takeoffs at a particular airport and a second landing congestion index associated with landings at a particular airport.

[0086] Example 5 includes the apparatus of any one of Examples 1 to 4, wherein one or more processors are configured to determine congestion predictions, including determining congestion predictions via a trained machine learning model.

[0087] Example 6 includes the apparatus of Example 5, wherein the training data for the trained machine learning model includes historical congestion index data, flight event data, flight schedule data, weather data, or a combination thereof.

[0088] Example 7 includes the apparatus of any one of Examples 1 to 6, wherein one or more processors are further configured to acquire one or more usage metrics.

[0089] Example 8 includes the apparatus of Example 7, wherein at least one of one or more usage metrics is obtained from a globally available data source.

[0090] Example 9 includes the apparatus of any one of Examples 1 to 8, wherein one or more indicators of use include flight event data, flight schedule data, weather data, or a combination thereof.

[0091] Example 10 includes the apparatus of any one of Examples 1 to 9, wherein one or more usage metrics include planned flight event data, planned flight operation data, actual flight event data, actual flight operation data, or a combination thereof.

[0092] Example 11 includes the apparatus of any one of Examples 1 to 10, wherein the operational congestion metric includes operational throughput.

[0093] Example 12 includes the apparatus of Example 11, wherein the operational throughput is associated with a first time window for an operational event at a particular airport.

[0094] Example 13 includes the apparatus of Example 12, wherein the first time window includes a thirty-minute time window.

[0095] Example 14 includes the apparatus of Example 12 or Example 13, wherein the congestion index is associated with a first time window.

[0096] Example 15 includes the apparatus of Example 14, wherein one or more processors are configured to determine an impact congestion metric, including modifying the impact congestion metric based at least on its value during a second time window, wherein the second time window is earlier than a first time window.

[0097] Example 16 includes the apparatus of any one of Examples 1 to 15, wherein one or more processors are configured to determine an influencing congestion metric, including classifying the influencing congestion metric into one of a plurality of congestion levels.

[0098] According to Example 17, a method includes: generating, via a processor, an operational congestion index associated with a specific airport, wherein the operational congestion index is based at least on one or more usage indicators of the specific airport; non-linearly generating an influencing congestion index based at least on the operational congestion index; determining a congestion forecast for the specific airport based on the influencing congestion index; and transmitting a congestion alert for the specific airport via the processor, wherein the congestion alert is based at least on the congestion forecast.

[0099] Example 18 includes the method of Example 17, wherein the congestion index is correlated with the operational congestion index via a logic function.

[0100] Example 19 includes the method of Example 17 or Example 18, wherein determining the congestion prediction includes determining the congestion prediction by means of a trained machine learning model.

[0101] According to embodiment 20, a non-transitory computer-readable medium includes instructions that, when executed by one or more processors, cause the one or more processors to: generate an operational congestion index associated with a particular airport, wherein the operational congestion index is based at least on one or more usage indicators of the particular airport; generate an influencing congestion index nonlinearly based at least on the operational congestion index; determine a congestion forecast for the particular airport based on the influencing congestion index; and transmit a congestion alert for the particular airport, wherein the congestion alert is based at least on the congestion forecast.

[0102] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of different implementations. These illustrations are not intended to serve as a complete description of all elements and features of devices and systems utilizing the structures or methods described herein. Many other implementations will be apparent to those skilled in the art after reviewing this invention. Other implementations can be utilized and derived from this disclosure, allowing structural and logical substitutions and changes to be made without departing from the scope of this disclosure. For example, method operations may be performed in a different order than those shown in the figures, or one or more method operations may be omitted. Therefore, this disclosure and the accompanying drawings are to be considered illustrative rather than restrictive.

[0103] Furthermore, although specific embodiments have been shown and described herein, it should be understood that any subsequent arrangements designed to achieve the same or similar results may replace the specific implementations shown. This disclosure is intended to cover any and all subsequent adaptations or variations of different implementations. After reviewing this description, combinations of the above implementations, as well as other implementations not specifically described herein, will be apparent to those skilled in the art.

[0104] The abstract of this disclosure is provided to clarify that it is not intended to interpret or limit the scope or meaning of the claims. Furthermore, in the foregoing detailed embodiments, different features may be combined together or described in a single implementation for the purpose of simplification. The above embodiments illustrate but do not limit this disclosure. It should also be understood that many modifications and variations are possible based on the principles of this disclosure. As reflected in the following claims, the claimed subject matter may involve fewer features than all features of any of the disclosed embodiments. Therefore, the scope of this disclosure is defined by the appended claims and their equivalents.

Claims

1. A device for monitoring airport congestion, comprising: One or more processors are configured as follows: Generate operational congestion metrics associated with a specific airport, wherein the operational congestion metrics are based at least on one or more usage metrics for the specific airport; At least based on the aforementioned operational congestion indicators, non-linearly generated congestion-affecting indicators are used to generate congestion-affecting indicators; Congestion forecasts for the specific airport are determined based on the aforementioned congestion impact indicators; and Congestion alerts are transmitted for the specific airport, wherein the congestion alerts are based at least on the congestion predictions.

2. The apparatus according to claim 1, wherein, The congestion impact index is correlated with the operational congestion index through a logic function.

3. The apparatus according to claim 1 or 2, wherein, The one or more processors are configured to generate the operational congestion metrics, including generating a first takeoff congestion metric associated with takeoffs at the specific airport and a first landing congestion metric associated with landings at the specific airport.

4. The apparatus according to claim 1 or 2, wherein, The one or more processors are configured to generate the congestion impact indicators, including generating a second takeoff congestion indicator associated with takeoffs at the specific airport and a second landing congestion indicator associated with landings at the specific airport.

5. The apparatus according to claim 1 or 2, wherein, The one or more processors are configured to determine the congestion prediction, including by using a trained machine learning model.

6. The apparatus according to claim 5, wherein, Training data for the trained machine learning model includes historical congestion index data, flight event data, flight schedule data, weather data, or a combination thereof.

7. The apparatus according to claim 1 or 2, wherein, The one or more processors are also configured to acquire the one or more usage metrics.

8. The apparatus according to claim 7, wherein, At least one of the one or more usage metrics is obtained from a globally available data source.

9. The apparatus according to claim 1 or 2, wherein, The one or more metrics used include flight event data, flight schedule data, weather data, or a combination thereof.

10. The apparatus according to claim 1 or 2, wherein, The one or more metrics used include planned flight event data, planned flight operation data, actual flight event data, actual flight operation data, or a combination thereof.

11. The apparatus according to claim 1 or 2, wherein, The operational congestion metric includes operational throughput.

12. The apparatus according to claim 11, wherein, The operational throughput is associated with the first time window for operational events at a specific airport.

13. The apparatus according to claim 12, wherein, The first time window includes a 30-minute time window.

14. A method for monitoring airport congestion, comprising: The processor generates operational congestion metrics associated with a specific airport, wherein the operational congestion metrics are based at least on one or more usage metrics of the specific airport. The processor generates congestion-affecting indicators non-linearly, based at least on the operational congestion indicators. The processor determines a congestion forecast for the specific airport based on the congestion impact indicators; and The processor transmits congestion alerts for the specific airport, wherein the congestion alerts are based at least on the congestion predictions.

15. A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to: The processor generates operational congestion metrics associated with specific airports, among which... The operational congestion indicators are based at least on one or more usage indicators for the specific airport; The processor generates congestion-affecting indicators non-linearly, based at least on the operational congestion indicators. The processor determines a congestion forecast for the specific airport based on the congestion impact indicators. as well as The processor transmits congestion alerts for the specific airport, wherein the congestion alerts are based at least on the congestion predictions.

Images