Maritime vessel communication systems and related methods

Abstract

The marine vessel communication system may include a satellite communication network and a marine communication terminal associated with the marine vessel and operable through the satellite communication network. The system may also include a communication management server to obtain vessel geographic location and heading data associated with the marine vessel, and to obtain historical vessel travel route data associated with the marine vessel. The server may also determine a predicted ship travel route based on the ship geographic location and heading data and historical ship travel route data using machine learning, and obtain historical satellite communication network usage data associated with the offshore communication terminal. The server may also determine a predicted network usage of the terminal based on the historical network usage data and the predicted ship travel route using machine learning, and operate at least one of the satellite communication network and the terminal based on the predicted usage.

Description

Technical Field

[0001] The present invention relates to the field of communications, and in particular to satellite communications of marine vessels and related methods. Background Art

[0002] When ships at sea cross large bodies of water, such as oceans, they rely on satellite communications to maintain contact with shore. Satellites typically operate in multiple frequency bands, such as, for example, the C-band and the Ku-band. The C-band provides a larger coverage area than the Ku-band. Since the Ku-band operates at a higher frequency than the C-band, it uses a shorter wavelength signal.

[0003] Marine vessels typically include a multi-band satellite antenna assembly that operates in both the C-band and the Ku-band. For example, when an oil and gas exploration vessel, drilling platform, ship, or other floating equipment (referred to herein as a marine vessel) is operating in the Gulf of Mexico, the multi-band satellite antenna assembly is typically configured to operate in the Ku-band. The Ku-band may be preferred because the cost of operating in the Ku-band is generally lower than operating in the C-band. For example, when an oil and gas exploration marine vessel is crossing the ocean to the North Sea, the availability of the Ku-band is limited.

[0004] In some embodiments, the multi-band satellite antenna assembly may not support both C-band and Ku-band simultaneously and requires manual configuration for the desired frequency band. This requires the marine vessel to be in port, and reconfiguration can be a time-consuming and expensive process. In other embodiments, the multi-band satellite antenna assembly may support both C-band and Ku-band simultaneously, so manual reconfiguration is not required.

[0005] The continued growth and demand for bandwidth has resulted in new commercial satellite constellations at higher frequencies. The O3b satellite constellation is the next generation of satellites operating in the Ka-band. Ka-band satellites are deployed in medium earth orbits compared to the geosynchronous orbits used by C-band / Ku-band satellite constellations. The advantage of medium earth orbits is that latency is significantly reduced for voice and data communications.

[0006] There are a variety of multi-band satellite antenna assemblies that support Ku-band and Ka-band but not C-band. For example, U.S. Patent No. 8,497,810 to Kits van Heyningen et al. discloses an antenna assembly implemented as a multi-beam, multi-band antenna having a main reflector with multiple feed horns and a sub-reflector, the antenna assembly having a reflective surface that defines an image focus for Ka-band signals and a primary focus for Ku-band frequency signals. U.S. Patent No. 8,334,815 to Monte et al. discloses an antenna assembly implemented as a multi-beam, multi-feed antenna having a main reflector equipped with a dual-mode feed tube and a switchable low noise feed block (LNB) that supports both Ka-band and Ku-band reception.

[0007] U.S. Published Patent Application No. 2013 / 0295841 to Choi et al. discloses a satellite communication system between a source and a destination via multiple satellite communication paths. The satellite communication system first identifies link performance established in multiple spectrums, and then performs link comparisons between multiple spectrums (e.g., C-band, Ku-band, or Ka-band) to determine the spectrum link that provides the highest throughput within an acceptable reliability standard. The satellite communication system switches between the multiple spectrum links to provide the determined spectrum link between the source and the destination.

[0008] When a marine vessel has the potential to access multiple satellite networks, it may be necessary to determine which satellite network to select. Satellite network selection may be based on many factors. In some cases, antennas and associated circuitry are manually changed to reconfigure to a satellite network, typically while the marine vessel is in a desired port. Summary of the invention

[0009] The marine vessel communication system may include a satellite communication network, and a plurality of marine communication terminals associated with a plurality of marine vessels and operable through the satellite communication network. The marine vessel communication system may also include a communication management server configured to obtain ship geographic location and heading data associated with a plurality of marine vessels, and to obtain historical ship route data associated with a plurality of marine vessels. The communication management server may also be configured to use machine learning to determine a predicted ship route based on the ship geographic location and heading data and the historical ship route data, and to obtain historical satellite communication network usage data associated with a plurality of marine communication terminals. The communication management server may also be configured to use machine learning to determine predicted satellite communication network usage of a plurality of marine communication terminals based on historical satellite communication network usage data and predicted ship routes, and to operate at least one of the satellite communication network and a plurality of marine communication terminals based on the predicted satellite communication network usage.

[0010] For example, the communication management server can be configured to obtain current weather data associated with a plurality of marine vessels and obtain historical weather data of historical ship travel route data associated with a plurality of marine vessels. The communication management server can also be configured to use machine learning to determine a predicted ship travel route based on the current weather data and the historical weather data.

[0011] The historical ship travel route data may include, for example, day-of-week travel data. The communication management server may be configured to obtain historical satellite communication degradation data associated with a plurality of marine vessels corresponding to the historical ship travel route data, and determine predicted satellite communication degradation of a plurality of marine communication terminals based on the historical satellite communication degradation data and predicted ship travel routes, for example, using machine learning.

[0012] The communication management server may also be configured to operate multiple marine communication terminals based on predicted satellite communication degradation. The historical satellite communication degradation data may include, for example, signal-to-noise ratio data. The historical satellite communication degradation data may include terrain data of terrain adjacent to multiple marine vessels and associated with historical vessel travel route data.

[0013] The historical ship route data may include, for example, Automatic Identification System (AIS) data of a plurality of marine vessels. The historical satellite communication network usage data may include, for example, at least one of vessel Committed Information Rate (CIR) data, vessel bandwidth usage data, and satellite capacity.

[0014] Each of the plurality of maritime terminals may include an antenna including a plurality of antenna feeds operable at respective different frequencies, and a communication circuit system coupled to the plurality of antenna feeds and configurable for a selected antenna feed. For example, the communication management server may be configured to operate the plurality of maritime communication terminals by selecting an antenna feed from the plurality of antenna feeds.

[0015] The satellite communication network may include multiple communication satellites. For example, each of the multiple marine communication terminals may include an antenna and a locator for mounting the antenna to a marine vessel and directing the antenna. The communication management server may be configured to operate the locator to direct the antenna to a selected communication satellite from the multiple communication satellites.

[0016] A method aspect is directed to a method for marine vessel communication. The method may include using a communication management server to obtain ship geographic location and heading data associated with multiple marine vessels, and obtaining historical ship route data associated with multiple marine vessels. The method may also include using the communication management server to use machine learning to determine a predicted ship route based on the ship geographic location and heading data and the historical ship route data, and obtain historical satellite communication network usage data associated with multiple marine communication terminals, the multiple marine communication terminals being associated with multiple marine vessels and operable through a satellite communication network. The method may also include using a communication management server to use machine learning to determine predicted satellite communication network usage of multiple marine communication terminals based on historical satellite communication network usage data and predicted ship routes, and operating at least one of the satellite communication network and multiple marine communication terminals based on the predicted satellite communication network usage.

[0017] A computer-readable medium aspect is directed to a non-transitory computer-readable medium for maritime vessel communications. The non-transitory computer-readable medium includes computer-executable instructions that, when executed by a processor of a communication management server, cause the processor to perform operations. The operations may include obtaining ship geographic location and heading data associated with a plurality of maritime vessels, and obtaining historical ship route data associated with a plurality of maritime vessels. The operations may also include using machine learning to determine predicted ship routes based on the ship geographic location and heading data and historical ship route data, and obtaining historical satellite communication network usage data associated with a plurality of maritime communication terminals, the plurality of maritime communication terminals being associated with a plurality of maritime vessels and operable through a satellite communication network. The operations may also include using machine learning to determine predicted satellite communication network usage of a plurality of maritime communication terminals based on historical satellite communication network usage data and predicted ship routes, and operating a plurality of maritime communication terminals based on predicted satellite communication network usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic diagram of a marine vessel communication system according to an embodiment.

[0019] Figure 2 yes Figure 1 Another schematic diagram of a maritime vessel communication system.

[0020] Figure 3 yes Figure 1 A schematic block diagram of a communication management server of a marine vessel communication system.

[0021] Figure 4 yes Figure 2Schematic diagram of the marine communication terminal of the marine ship communication system.

[0022] Figure 5 It is a graphic Figure 1 Flowchart of the operation of a communication management server of a marine vessel communication system. DETAILED DESCRIPTION

[0023] The present invention will be described more fully below with reference to the accompanying drawings, in which preferred embodiments of the present invention are shown. However, the present invention may be implemented in a variety of different forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make this disclosure comprehensive and complete and to fully convey the scope of the present invention to those skilled in the art. The same numbers throughout the text represent the same elements.

[0024] First reference Figure 1-4 , the marine vessel communication system 20 includes a satellite communication network 21. The satellite communication network 21 includes one or more satellites 22a-22n for providing communications to, for example, marine vessels 23a-23n. The satellites 22a-22n may be any type of satellite, including geostationary and non-geostationary satellites operating in different frequency bands, such as, for example, Ka-band, Ku-band, and C-band.

[0025] The marine vessel communication system 20 also includes marine communication terminals 30a-30n, which are associated with the marine vessels 23a-23n and can be operated through the satellite communication network 21. Each terminal 30a-30n includes an antenna 31a, which includes antenna feeds 32a, 33a, 34a (operable at different frequencies) Figure 4 Although three antenna feeds 32a, 33a, 34a are shown, those skilled in the art will recognize that there may be any number of antenna feeds ( Figure 4 ). The communication circuit system 35a is coupled to the antenna feeds 32a, 33a, 34a. The communication circuit system 35a can be configured for the selected antenna feeds 32a, 33a, 34a. Each marine communication terminal 30a-30n may also include a positioner 35a for mounting the antenna 31a to the marine vessel and directing the antenna ( Figure 4 ). More details of the marine communication terminals 30a-30n may be found in U.S. Patent No. 9,893,417, the entire contents of which are incorporated herein by reference.

[0026] The marine vessel communication system 20 also includes a communication management server 40. The communication management server 40 includes a processor 41 and an associated memory 42. Although multiple operations of the communication management server 40 are described herein, those skilled in the art will recognize that these operations are performed through cooperation between the processor 41 and the memory 42.

[0027] Reference now Figure 5 Referring to the flowchart 60 in FIG. 6A , starting at block 62, the operation of the communication management server 40 will now be described. At block 64, the communication management server obtains vessel geographic location data 24 and heading data 25 associated with the marine vessels 23a-23n. For example, each marine vessel 23a-23n may transmit its current location 24 and its current heading 25 to the communication management server 40. The location data 24 may be, for example, a geographic location represented by latitude and longitude. The heading data 25 may be, for example, a magnetic compass heading. The location data 24 and heading data 25 may be included as part of the automatic identification system (AIS) data transmitted from the marine vessels 23a-23n.

[0028] At block 66, the communication management server 40 obtains historical vessel route data 26 associated with the marine vessels 23a-23n. The historical vessel route data 26 may be stored in the memory 42. The historical vessel route data 26 may include historical AIS data and travel data for days of the week (i.e., Monday, Tuesday, etc.) for the marine vessels 23a-23n. For example, the historical vessel route data 26 may include trip data for the marine vessels 23a-23n. The historical vessel route data 26 may include other and / or additional data or parameters, such as travel data for times of the year (i.e., season, month) and travel data for times of the month associated with the marine vessels 23a-23n.

[0029] The communication management server 40 may optionally obtain current weather data 27 associated with the marine vessels 23a-23n (block 68). The current weather data 27 may include, for example, precipitation, cloud cover, fronts, temperature, wind, humidity, tides, and wave information. The current weather data 27 may be obtained from reports from each marine vessel 23a-23n and / or from weather radar / satellite based on the corresponding geographic location.

[0030] At block 70, the communication management server 40 obtains historical weather data 28 for the historical ship route data 26 associated with the marine vessels 23a-23n. The historical weather data 28 may be obtained in a manner similar to the historical route data 26, for example, by storing the historical weather data in the memory 42 as it is obtained, so that when new current weather data is obtained, the current weather data becomes the historical weather data.

[0031] At block 72, the communication management server 40 uses machine learning to determine, for example, a predicted ship travel route 43 for each marine vessel 23a-23n based on the vessel geographic location data 24 and heading data 25 and the historical ship travel route data 26, and optionally based on the historical weather data 28. More specifically, the communication management server 40 operates a machine learning algorithm that is initially trained on the stored historical ship travel route data 26 and historical weather data. The communication management server 40 may continuously receive the vessel geographic location data 24 and heading data 25, as well as the current weather data 27, from each marine vessel 23a-23n, for example, at predetermined intervals and / or while the marine vessel is traveling. When the communication management server 40 obtains the vessel geographic location data 24 and heading data 25 and the current weather data, the machine learning algorithm is updated so that the predicted ship travel route 43 is updated to be more accurate. The machine learning algorithm may accept additional parameters or inputs as its input to further improve the accuracy of the predicted ship travel route 43. For example, vessel itinerary data (e.g., origin, destination, waypoints, stops, stopovers or refueling points, etc.), maritime vessel type, maritime vessel size, current day of the week, current month, and / or current time of month can all be input into a machine learning algorithm.

[0032] The marine communication management server 40 obtains historical satellite communication network usage data 32 using the marine communication terminals 30a-30n (block 74). The historical satellite communication network usage data 32 may include, for example, vessel committed information rate (CIR) data, vessel bandwidth usage data, and satellite capacity. As will be appreciated by those skilled in the art, the historical satellite communication network usage data 32 may include other and / or additional data. The historical satellite communication network usage data 32 may be stored in the memory 42. The marine communication network usage server 40 may obtain the historical satellite communication network usage data 32 from a remote device or server associated with the satellite.

[0033] At block 76, the maritime communications management server 40 uses machine learning to determine predicted satellite communications network usage 33 for the maritime terminals 30a-30n based on the historical satellite communications network usage data 32 and the predicted ship travel route 43. Thus, for a given maritime vessel 23a-23n, predicted satellite communications usage (e.g., bandwidth) can be predicted. Those skilled in the art will recognize that satellite communications network usage may vary based on a variety of factors, such as the geographic location of the vessel, weather, etc. Therefore, the communications management server 40 can use historical satellite communications network usage or usage patterns (e.g., bandwidth) to predict future bandwidth requirements for a particular geographic area.

[0034] More specifically, the communication management server 40 operates a machine learning algorithm that is initially trained on historical or stored satellite communication network usage data 32 and stored historical ship route data 26. The communication management server 40 can continuously (e.g., at predetermined intervals) receive the satellite communication network usage data 32. As the communication management server 40 obtains the satellite communication network usage data 32 and the predicted ship route 43, the predicted satellite communication network usage 33 is updated to be more accurate. Advantageously, by using the output of another machine learning algorithm (i.e., the predicted ship route) as an input feed to the machine learning algorithm, the communication management server 40 operates nested machine learning algorithms, which provides higher accuracy and faster processing, as opposed to processing each algorithm serially. Of course, the communication management server 40 can process each prediction or machine learning algorithm serially.

[0035] The machine learning algorithm may accept additional parameters or inputs as inputs to further improve the accuracy of the predicted satellite communication network usage 33 of the maritime communication terminals 30a-30n. For example, geographic area boundaries, satellite beam coverage, satellite capacity information, radio frequency (RF) parameters (e.g., signal-to-noise ratio, MODCOD, etc.), maritime vessel type, maritime vessel size, current day of the week, current month, and / or current time of month may all be input into the machine learning algorithm.

[0036] At block 78, the communication management server 40 may also optionally obtain historical satellite communication degradation data 34 associated with the marine vessels 23a-23n and corresponding to the historical travel route data 26. In other words, the communication management server 40 obtains historical degradation data from each marine vessel 23a-23n for the routes previously traveled by these vessels. The historical satellite communication degradation data 34 may include signal-to-noise ratio (SNR) data, geographic data of the area adjacent to the marine vessels 23a-23n and associated with the historical vessel travel route data 26. More specifically, historical information about satellite obstruction areas (e.g., caused by vessel structures and / or geographic features (e.g., mountains)) is obtained.

[0037] The communication management server 40 uses machine learning to determine the predicted satellite communication degradation 44 of the marine communication terminal 30a-30n based on the historical satellite communication degradation data 34 and the predicted ship travel route 33 (box 80). More specifically, the communication management server 40 operates a machine learning algorithm that is initially trained on the stored historical satellite communication degradation data 34. The communication management server 40 can continuously receive satellite communication degradation data at predetermined intervals and / or while the marine vessel 23a-23n is traveling, for example, similar to the satellite communication network usage data. When the communication management server 40 obtains the satellite communication degradation data, the machine learning algorithm is updated so that the predicted satellite communication degradation 44 of the marine communication terminal 23a-23n is updated to be more accurate. The machine learning algorithm can accept additional parameters or inputs as its input to further improve the accuracy of the predicted satellite communication degradation 44. For example, antenna directional direction, vessel geographic location, satellite location, satellite beam coverage, historical SNR data, bit error rate, marine vessel type, marine vessel size, weather data (current and historical), previous satellite acquisition success rate, communication failure data, current day of the week, current month and / or current time of month can all be input into the machine learning algorithm. Advantageously, the communication management server 40 uses the above factors to predict the degradation of satellite signals at certain geographic locations or locations around the world. Therefore, for a given antenna 31a, for example, at a given location and oriented in a certain direction, it can be more accurately determined whether degradation will be encountered, for example, when acquiring a lock on a desired satellite signal.

[0038] At block 82, the communications management server 40 operates either or both of the satellite communications network 21 and the maritime communications terminals 30a-30n based on the predicted satellite communications network usage and optionally predicted satellite communications degradation 44. More particularly, the communications management server 40 may operate the satellite communications network 21 by facilitating the purchase of bandwidth and / or allocating bandwidth to selected satellites 22a-22n. The communications management server 40 may collaborate with remote and shore servers or computers to facilitate the purchase of bandwidth and / or allocate bandwidth based on the predicted satellite communications network usage and optionally predicted satellite communications degradation 44. The purchase and / or allocation of bandwidth for the individual satellites 22a-22n may be performed, for example, in real time, or may be performed in conjunction with other operations (e.g., dynamically), such as, for example, operating the maritime terminals 30a-30n based on the predicted satellite communications network usage and optionally predicted satellite communications degradation 44.

[0039] The communication management server 40 can operate the maritime terminals 30a-30n independently or in conjunction with the operation of the satellite communication network 31 by selecting antenna feeds 32a-34a from different antenna feeds and operating the positioner 35a to direct the antenna 31a to the selected satellite 22a-22n. Although the communication management server 40 can operate either or both of the satellite communication network 21 and the maritime terminals 30a-30n, those skilled in the art will recognize that the communication management server can be programmed to operate the satellite communication network alone, programmed to operate the maritime terminals alone, or programmed to operate either or both of the satellite communication network and the maritime mobile terminals alone or in combination.

[0040] In some embodiments, the communication management server 40 can score and rank the satellites 22a-22n based on the predicted satellite communication usage 33 and the predicted satellite communication degradation 44. For example, each satellite can be assigned a score indicating the predicted lower degradation and the predicted higher available bandwidth. Monetary cost can also be considered when scoring. For example, based on the weight of the above factors, the satellite 22a-22n with the best score can be selected for communication. Those skilled in the art will recognize that various factors can determine whether a given satellite can provide the best communication based on certain factors. For example, a ship at sea may change its route based on weather, port traffic and closures, etc., which may cause a given satellite 22a-22n to be overloaded with communications, resulting in poor and / or ineffective satellite communications. The marine ship communication system 20 can advantageously solve these problems by more accurately predicting the ship's position and the amount and quality of each satellite's communication, so that communications across satellites and marine communication terminals 30a-30n can be optimized. The operation ends at box 84.

[0041] The method aspect is directed to a method for marine vessel communication. The method includes using a communication management server 40 to obtain a vessel geographic location 24 and heading data 25 associated with a plurality of marine vessels, and obtaining historical ship route data 26 associated with a plurality of marine vessels. The method also includes using the communication management server 40 to use machine learning to determine a predicted ship route 43 based on the vessel geographic location 24 and heading data 25 and the historical ship route data 26, and obtain historical satellite communication network usage data 32 associated with a plurality of marine communication terminals 30a-30n, the plurality of marine communication terminals 30a-30n being associated with a plurality of marine vessels 23a-23n and being operable through a satellite communication network 21. The method also includes using the communication management server 40 to use machine learning to determine predicted satellite communication network usage 33 of a plurality of marine communication terminals 30a-30n based on the historical satellite communication network usage data 32 and predicted ship route 43, and operating the plurality of marine communication terminals based on the predicted satellite communication network usage.

[0042] The computer-readable medium aspect is directed to a non-transitory computer-readable medium for marine vessel communications. The non-transitory computer-readable medium includes computer-executable instructions that, when executed by a processor 41 of a communication management server 40, cause the processor to perform operations. The operations include obtaining ship geographic location and heading data associated with a plurality of marine vessels, and obtaining historical ship route data associated with a plurality of marine vessels. The operations also include using machine learning to determine a predicted ship route 43 based on the ship geographic location and heading data 24 and the historical ship route data 26, and obtaining historical satellite communication network usage data 32 associated with a plurality of marine communication terminals 30a-30n, the plurality of marine communication terminals 30a-30n being associated with a plurality of marine vessels and operable through a satellite communication network. The operations also include using machine learning to determine predicted satellite communication network usage 33 of a plurality of marine communication terminals 30a-30n based on historical satellite communication network usage data and predicted ship routes, and operating a plurality of marine communication terminals based on predicted satellite communication network usage.

[0043] Although several embodiments are described herein, it will be appreciated by those skilled in the art that any element or elements in one or more embodiments may be used together with any element or elements in any other embodiment or embodiments. Many modifications and other embodiments of the present invention will occur to those skilled in the art with the benefit of the foregoing description and the teachings presented in the associated drawings. Therefore, it will be understood that the present invention is not limited to the specific embodiments disclosed, and modifications and embodiments are intended to be included within the scope of the appended claims.

Claims

1. A marine vessel communication system, comprising: Satellite communications networks; a plurality of marine communication terminals associated with a plurality of marine vessels and operable via a satellite communication network; as well as a communications management server configured to obtain vessel geographic location and heading data associated with the plurality of marine vessels, obtaining historical ship route data associated with the plurality of marine vessels, Use machine learning to determine predicted ship routes based on ship geolocation and heading data as well as historical ship route data, obtaining historical satellite communication network usage data associated with the plurality of maritime communication terminals, determining predicted satellite communication network usage of the plurality of maritime communication terminals based on historical satellite communication network usage data and predicted ship travel routes using machine learning, and The satellite communication network and at least one of the plurality of maritime communication terminals are operated based on the predicted satellite communication network usage.

2. The marine vessel communication system according to claim 1, wherein the communication management server is configured as: obtaining current weather data associated with the plurality of marine vessels; obtaining historical weather data for historical vessel route data associated with the plurality of marine vessels; and Use machine learning to determine predicted ship routes based on current and historical weather data.

3. The marine vessel communication system according to claim 1, wherein the historical vessel route data includes the route data for each day of the week.

4. The marine vessel communication system according to claim 1, wherein the communication management server is configured as: obtaining historical satellite communication degradation data associated with the plurality of marine vessels corresponding to the historical vessel route data; determining predicted satellite communication degradation for the plurality of maritime communication terminals based on historical satellite communication degradation data and predicted ship travel paths using machine learning; as well as The plurality of maritime communication terminals are operated based on the predicted satellite communication degradation.

5. The marine vessel communication system of claim 4, wherein the historical satellite communication degradation data includes signal-to-noise ratio data.

6. The marine vessel communication system of claim 4, wherein the historical satellite communication degradation data includes geographical area data of a region adjacent to the plurality of marine vessels and associated with the historical vessel travel route data.

7. The marine vessel communication system of claim 1, wherein the historical ship route data comprises Automatic Identification System (AIS) data of the plurality of marine vessels.

8. The marine vessel communication system of claim 1, wherein the historical satellite communication network usage data includes at least one of vessel committed information rate (CIR) data, vessel bandwidth usage data, and satellite capacity.

9. The marine vessel communication system of claim 1, wherein each of the plurality of marine terminals comprises an antenna, the antenna comprising a plurality of antenna feeds operable at respective different frequencies, and a communication circuit system coupled to the plurality of antenna feeds and configurable for a selected antenna feed.

10. The marine vessel communication system of claim 9, wherein the communication management server is configured to operate the plurality of marine communication terminals by selecting an antenna feed from the plurality of antenna feeds.

11. A marine vessel communication system as described in claim 1, wherein the satellite communication network includes a plurality of communication satellites; wherein each of the plurality of marine communication terminals includes an antenna and a locator for mounting the antenna to the marine vessel and directing the antenna; and wherein the communication management server is configured to operate the locator to direct the antenna to a selected communication satellite among the plurality of communication satellites.

12. A communication management server for a marine vessel communication system, the marine vessel communication system comprising a satellite communication network, and a plurality of marine communication terminals associated with a plurality of marine vessels and operable via the satellite communication network, the communication management server comprising: a processor and associated memory configured to obtain vessel geographic location and heading data associated with the plurality of marine vessels, obtaining historical ship route data associated with the plurality of marine vessels, Use machine learning to determine predicted ship routes based on ship geolocation and heading data as well as historical ship route data, obtaining historical satellite communication network usage data associated with the plurality of maritime communication terminals, determining predicted satellite communication network usage of the plurality of maritime communication terminals based on historical satellite communication network usage data and predicted ship travel routes using machine learning, and The satellite communication network and at least one of the plurality of maritime communication terminals are operated based on the predicted satellite communication network usage.

13. The communication management server of claim 12, wherein the processor is configured to: obtaining current weather data associated with the plurality of marine vessels; obtaining historical weather data for historical vessel route data associated with the plurality of marine vessels; and Use machine learning to determine predicted ship routes based on current and historical weather data.

14. The communication management server according to claim 12, wherein the historical ship travel route data includes travel data for days of the week.

15. The communication management server of claim 12, wherein the processor is configured to: obtaining historical satellite communication degradation data associated with the plurality of marine vessels corresponding to the historical vessel route data; determining predicted satellite communication degradation for the plurality of maritime communication terminals based on historical satellite communication degradation data and predicted ship travel paths using machine learning; as well as The plurality of maritime communication terminals are operated based on the predicted satellite communication degradation.

16. A marine vessel communication method, comprising: Using the Communication Management Server Obtaining vessel geographic location and heading data associated with a plurality of marine vessels, obtaining historical ship route data associated with the plurality of marine vessels, Use machine learning to determine predicted ship routes based on ship geolocation and heading data as well as historical ship route data, obtaining historical satellite communication network usage data associated with a plurality of maritime communication terminals associated with the plurality of maritime vessels and operable via a satellite communication network, determining predicted satellite communication network usage of the plurality of maritime communication terminals based on historical satellite communication network usage data and predicted ship travel routes using machine learning, and The satellite communication network and at least one of the plurality of maritime communication terminals are operated based on the predicted satellite communication network usage.

17. The method of claim 16, wherein using the communication management server comprises using the communication management server: obtaining current weather data associated with the plurality of marine vessels; obtaining historical weather data for historical vessel route data associated with the plurality of marine vessels; and Use machine learning to determine predicted ship routes based on current and historical weather data.

18. The method of claim 16, wherein the historical vessel route data includes day of the week travel data.

19. The method of claim 16, wherein using the communication management server comprises using the communication management server: obtaining historical satellite communication degradation data associated with the plurality of marine vessels corresponding to the historical vessel route data; determining predicted satellite communication degradation for the plurality of maritime communication terminals based on historical satellite communication degradation data and predicted ship travel paths using machine learning; as well as The plurality of maritime communication terminals are operated based on the predicted satellite communication degradation.

20. A non-transitory computer-readable medium for marine vessel communications, the non-transitory computer-readable medium comprising computer-executable instructions, which, when executed by a processor of a communication management server, cause the processor to perform operations, comprising: obtaining vessel geographic location and heading data associated with a plurality of marine vessels; obtaining historical ship route data associated with the plurality of marine vessels; Use machine learning to determine predicted ship routes based on ship geolocation and heading data and historical ship route data; obtaining historical satellite communication network usage data associated with a plurality of marine communication terminals associated with the plurality of marine vessels and operable via a satellite communication network; determining predicted satellite communication network usage of the plurality of maritime communication terminals based on historical satellite communication network usage data and predicted ship travel routes using machine learning; and The satellite communication network and at least one of the plurality of maritime communication terminals are operated based on the predicted satellite communication network usage.

21. The non-transitory computer readable medium of claim 20, wherein the operations comprise: obtaining current weather data associated with the plurality of marine vessels; obtaining historical weather data for historical ship route data associated with the plurality of marine vessels; as well as Use machine learning to determine predicted ship routes based on current and historical weather data.

22. The non-transitory computer readable medium of claim 20, wherein the historical vessel travel route data includes travel data for days of the week.

23. The non-transitory computer readable medium of claim 20, wherein the operations comprise: obtaining historical satellite communication degradation data associated with the plurality of marine vessels corresponding to the historical vessel route data; determining predicted satellite communication degradation for the plurality of maritime communication terminals based on historical satellite communication degradation data and predicted ship travel paths using machine learning; as well as The plurality of maritime communication terminals are operated based on the predicted satellite communication degradation.

Images