Service migration method, communication device, communication system and storage medium

Abstract

The invention provides a service migration method, communication equipment, a communication system and a storage medium, and the method comprises the steps: responding to a condition that first equipment needs to carry out service migration, and determining a first parameter based on a network environment of a non-ground network NTN where the first equipment is located; wherein the network environment comprises at least one second device, and the second device is a device which is visible to the first device and can execute services; inputting the first parameter into a first model to obtain a first path output by the first model; the first model is used for deep reinforcement learning, and the first path is a service migration path determined by the first model based on the first parameter; and carrying out service migration based on the first path. According to the invention, low-delay and high-efficiency service migration can be realized in the NTN system, and the execution performance of the service is ensured.

Description

Business migration method, communication device, communication system, storage medium TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a business migration method, a communication device, a communication system and a storage medium. BACKGROUND

[0002] In a communication system, when the load of a communication device cannot support processing of a service, the communication device can perform business migration to distribute the service of the communication device to other communication devices for processing. Wherein, how to realize low-latency and high-efficiency business migration in a non-terrestrial network (NTN) system is a technical problem to be solved at present.

[0003] SUMMARY

[0004] The present disclosure provides a business migration method, a communication device, a communication system and a storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a business migration method is provided, executed by a first device, and the method comprises:

[0006] In response to the first device needing to perform business migration, a first parameter is determined based on a network environment of a non-terrestrial network (NTN) in which the first device is located; wherein the network environment comprises at least one second device, and the second device is a device visible to the first device and capable of performing a service;

[0007] The first parameter is input into a first model to obtain a first path output by the first model; the first model is used for deep reinforcement learning, and the first path is a business migration path determined by the first model based on the first parameter;

[0008] The business migration is performed based on the first path.

[0009] According to a second aspect of an embodiment of the present disclosure, a first device is provided, comprising:

[0010] A processing module is configured to, in response to the first device needing to perform business migration, determine a first parameter based on a network environment of a non-terrestrial network (NTN) in which the first device is located; wherein the network environment comprises at least one second device, and the second device is a device visible to the first device and capable of performing a service;

[0011] The processing module is further configured to input the first parameter into a first model to obtain a first path output by the first model; the first model is used for deep reinforcement learning, and the first path is a business migration path determined by the first model based on the first parameter;

[0012] The processing module is further configured to perform service migration based on the first path.

[0013] According to a third aspect of the embodiments of the present disclosure, a communication device is provided, comprising:

[0014] one or more processors;

[0015] The processor is configured to invoke instructions to cause the communication device to perform the method of the first aspect.

[0016] According to a fourth aspect of the embodiments of the present disclosure, a storage medium is provided, which stores instructions, and the instructions, when executed on a communication device, cause the communication device to perform the method of the first aspect.

[0017] In a fifth aspect, the embodiments of the present disclosure provide a program product, which, when executed on a communication device, causes the communication device to perform the method of the first aspect.

[0018] In a sixth aspect, the embodiments of the present disclosure provide a computer program, which, when executed on a computer, causes the computer to perform the method of the first aspect.

[0019] In a seventh aspect, the embodiments of the present disclosure provide a chip or chip system. The chip or chip system comprises processing circuitry configured to perform the method of the first aspect.

[0020] It can be understood that the terminal, network device, communication device, communication system, storage medium, program product, computer program are all used to perform the method provided by the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0021] The above and / or additional aspects and advantages of the present disclosure will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

[0022] FIG. 1 is a schematic diagram of the architecture of some communication systems according to embodiments of the present disclosure;

[0023] FIG. 2A is an interaction diagram of a service migration method according to an embodiment of the present disclosure;

[0024] FIG. 2B is a schematic diagram of a network environment of an NTN in which a first device is located according to an embodiment of the present disclosure;

[0025] FIG. 2C is a schematic diagram of a first model training according to an embodiment of the present disclosure;

[0026] FIG. 3 is an interaction diagram of a service migration method according to an embodiment of the present disclosure;

[0027] FIG. 4 is a schematic diagram of a satellite edge computing service migration process according to an embodiment of the present disclosure;

[0028] FIG. 5 is a structural schematic diagram of a first device according to an embodiment of the present disclosure;

[0029] FIG. 6A is a structural schematic diagram of a communication device according to an embodiment of the present disclosure;

[0030] FIG. 6B is a structural schematic diagram of a chip according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The embodiments of the present disclosure provide a service migration method, a communication device, a communication system and a storage medium.

[0032] In a first aspect, the embodiments of the present disclosure provide a service migration method, executed by a first device, comprising:

[0033] In response to the first device needing to perform service migration, determining a first parameter based on a network environment of a non-terrestrial network (NTN) in which the first device is located; wherein the network environment comprises at least one second device, and the second device is a device capable of performing service and visible to the first device;

[0034] Inputting the first parameter into a first model to obtain a first path output by the first model; the first model is used for deep reinforcement learning, and the first path is a service migration path determined by the first model based on the first parameter;

[0035] Performing service migration based on the first path.

[0036] In the above embodiment, when the first device needs to perform service migration, the first parameter can be determined based on the network environment of the NTN in which the first device is located, and the first parameter is input to the first model, so that the first model outputs the first path, and then the first device can perform service migration based on the first path. The first model is used for deep reinforcement learning, the first path is a service migration path determined by the first model based on the first parameter, and the first parameter is determined based on the network environment of the NTN in which the first device is located. Therefore, it can be known that the service migration path in the present disclosure is determined by the first model through deep reinforcement learning based on the NTN network environment. The first model can determine a service migration path with better effect in the NTN network environment through deep reinforcement learning, and the better effect can include lower service delay and higher service efficiency. Therefore, when the first device performs service migration based on the determined service migration path subsequently, the delay can be ensured to be low and the efficiency can be ensured to be high, and the execution performance of the service is ensured.

[0037] In some embodiments of the first aspect, in some embodiments, the first parameter is used to indicate at least one of the following:

[0038] a second path, the second path being a service migration path at a last service migration in the network environment;

[0039] a second parameter, the second parameter being a parameter that affects the service load of the second device;

[0040] a service load available to the second device;

[0041] at least one third path, the third path being a service migration path available to the first device.

[0042] In the above embodiment, it is explained that the first parameter can be which parameters, so that the first device can successfully determine these parameters based on the network environment of the NTN in which the first device is located, and further determine a service migration path with lower service delay and higher service efficiency based on these parameters, ensure low delay and high efficiency during service migration, and ensure the execution performance of the service.

[0043] In some embodiments of the first aspect, in some embodiments, the first path output by the first model is a path with the highest service efficiency among the at least one third path.

[0044] In some embodiments of the first aspect, in some embodiments, the first path output by the first model is any path in the at least one third path with a service efficiency higher than a first value.

[0045] In the above embodiment, the first path output by the first model is a path with higher service efficiency, so that when the first device subsequently performs service migration based on the first path, lower latency and higher efficiency can be ensured, and the execution performance of the service is ensured.

[0046] In some embodiments of the first aspect, the first device is a satellite, and the second device includes a satellite and / or a cloud server.

[0047] In the above embodiment, it is explained which devices the first device and the second device can be, so that the terminal can successfully implement service migration in these devices.

[0048] In some embodiments of the first aspect, the service migration based on the first path includes:

[0049] determining a third device based on the first path, the third device being a device for executing the service to be migrated;

[0050] sending a first request to the third device, the first request being used to request service migration, and / or the first request carrying service parameters of the service to be migrated;

[0051] receiving a first response sent by the third device, the first response being used to indicate that the third device accepts service migration of the first device.

[0052] In some embodiments of the first aspect, the service migration based on the first path includes:

[0053] determining a third device based on the first path, the third device being a device for executing the service to be migrated;

[0054] sending a first request to the third device, the first request being used to request service migration, and / or the first request being used to indicate a service load required by the service to be migrated;

[0055] receiving a first response sent by the third device, the first response being used to indicate that the third device accepts service migration of the first device.

[0056] sending service parameters of the service to be migrated to the third device.

[0057] In the above embodiment, a method for how the first device performs service migration based on the first path is provided, ensuring successful execution of service migration.

[0058] In some embodiments of the first aspect, the model algorithm of the first model includes a competitive double deep Q-network (D3QN) algorithm.

[0059] In the above embodiments, it is explained which model algorithms of the first model are, so that the first model can successfully and accurately determine a low-latency, high-efficiency service migration path, ensuring the execution performance of the service.

[0060] In combination with some embodiments of the first aspect, in some embodiments, the method further includes:

[0061] Before inputting the first parameter into the first model, receiving a trained first model; or

[0062] Before inputting the first parameter into the first model, training the first model.

[0063] In the above embodiments, the first device can train the first model, so that the trained first model can successfully and accurately determine a low-latency, high-efficiency service migration path, ensuring the execution performance of the service. In the above embodiments, the first device can also not train the first model locally, but can receive a first model trained by another device, thereby reducing the execution complexity of the first device.

[0064] In a second aspect, the embodiments of the present disclosure provide a first device, including:

[0065] a processing module configured to, in response to the first device needing to perform service migration, determine a first parameter based on a network environment of a non-terrestrial network (NTN) in which the first device is located, wherein the network environment includes at least one second device, and the second device is a device that is visible to the first device and can perform a service;

[0066] the processing module is further configured to input the first parameter into a first model to obtain a first path output by the first model, wherein the first model is configured to perform deep reinforcement learning, and the first path is a service migration path determined by the first model based on the first parameter;

[0067] the processing module is further configured to perform service migration based on the first path.

[0068] In combination with some embodiments of the second aspect, in some embodiments, the first parameter is used to indicate at least one of:

[0069] a second path, wherein the second path is a service migration path at a previous service migration in the network environment;

[0070] a second parameter, wherein the second parameter is a parameter that affects a service load of the second device;

[0071] a service load available to the second device;

[0072] at least one third path, the third path being a service migration path available to the first device.

[0073] In some embodiments combined with the second aspect, in some embodiments, the first path output by the first model is: a path with the highest service efficiency among the at least one third path.

[0074] In some embodiments combined with the second aspect, in some embodiments, the first path output by the first model is: any path with service efficiency higher than a first value among the at least one third path.

[0075] In some embodiments combined with the second aspect, in some embodiments, the first device is a satellite, and the second device includes a satellite and / or a cloud server.

[0076] In some embodiments combined with the second aspect, in some embodiments, the service migration based on the first path includes:

[0077] determining a third device based on the first path, the third device being a device for executing the service to be migrated;

[0078] sending a first request to the third device, the first request being used for requesting service migration, and / or the first request carrying service parameters of the service to be migrated;

[0079] receiving a first response sent by the third device, the first response being used for indicating that the third device accepts service migration of the first device.

[0080] In some embodiments combined with the second aspect, in some embodiments, the service migration based on the first path includes:

[0081] determining a third device based on the first path, the third device being a device for executing the service to be migrated;

[0082] sending a first request to the third device, the first request being used for requesting service migration, and / or the first request being used for indicating a service load required by the service to be migrated;

[0083] receiving a first response sent by the third device, the first response being used for indicating that the third device accepts service migration of the first device.

[0084] sending service parameters of the service to be migrated to the third device.

[0085] In some embodiments combined with the second aspect, in some embodiments, a model algorithm of the first model includes a competitive double deep Q-network (D3QN) algorithm.

[0086] In combination with some embodiments of the second aspect, in some embodiments, the method further comprises:

[0087] receiving the trained first model before inputting the first parameter into the first model; or

[0088] training the first model before inputting the first parameter into the first model.

[0089] In a third aspect, the embodiments of the present disclosure provide a communication device, which comprises one or more processors, one or more memories for storing instructions, wherein the processor is configured to invoke the instructions to enable the communication device to perform the method described in the first aspect, the optional implementation manners of the first aspect, the second aspect, and the optional implementation manners of the second aspect.

[0090] In a fourth aspect, the embodiments of the present disclosure provide a storage medium, which stores instructions, and when the instructions are run on a communication device, enable the communication device to perform the method described in the first aspect and the optional implementation manners of the first aspect.

[0091] In a fifth aspect, the embodiments of the present disclosure provide a program product, which comprises a computer program, and when the computer program is executed by a communication device, enables the communication device to perform the method described in the first aspect and the optional implementation manners of the first aspect.

[0092] In a sixth aspect, the embodiments of the present disclosure provide a computer program, and when the computer program is run on a computer, enables the computer to perform the method described in the first aspect and the optional implementation manners of the first aspect.

[0093] In a seventh aspect, the embodiments of the present disclosure provide a chip or a chip system, which comprises processing circuitry configured to perform the method described in the first aspect and the optional implementation manners of the first aspect.

[0094] It can be understood that the terminal, the network device, the communication device, the communication system, the storage medium, the program product, and the computer program are all used to perform the method proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved by them can refer to the beneficial effects in the corresponding method, which will not be described here again.

[0095] The embodiments of the present disclosure propose a service migration method, a communication device, a communication system, and a storage medium. In some embodiments, the service migration method and the information processing method, the information sending method, the information receiving method, and the like can be replaced with each other, the communication device and the information processing device, the information sending device, the information receiving device, and the like can be replaced with each other, and the information processing system, the communication system, the information sending system, the information receiving system, and the like can be replaced with each other.

[0096] The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing part of the steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, part or all steps of different embodiments can be combined arbitrarily, an embodiment can be combined with optional implementation of other embodiments.

[0097] In each embodiment of the present disclosure, the terms and / or descriptions between the embodiments are consistent if there is no special description and logical conflict, and can be referred to each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0098] The terms used in the embodiments of the present disclosure are only for the purpose of describing the specific embodiments, and not as a limitation on the present disclosure.

[0099] In the embodiments of the present disclosure, unless otherwise specified, the elements expressed in singular form, such as "one", "a", "the", "above", "said", "preceding", "this" and the like, can represent "one and only one", or "one or more", "at least one" and the like. For example, in the case of using articles such as "a", "an", "the" and the like in English, the noun after the article can be understood as singular expression, or can be understood as plural expression.

[0100] In the embodiments of the present disclosure, "a plurality of" means two or more.

[0101] In some embodiments, the terms "at least one of", "at least one of", "at least one of", "one or more", "a plurality of", "multiple" and the like can be replaced with each other.

[0102] The description manner such as "at least one of A, B, C, …", "A and / or B and / or C, …" and the like in the embodiments of the present disclosure includes any one of A, B, C, … existing alone, and also includes any combination of any multiple of A, B, C, …, each of which can exist alone; for example, "at least one of A, B, C" includes a case of A alone, a case of B alone, a case of C alone, a case of combination of A and B, a case of combination of A and C, a case of combination of B and C, and a case of combination of A and B and C; for example, A and / or B includes a case of A alone, a case of B alone, and a case of combination of A and B.

[0103] In some embodiments, the description manner such as "A in a case, B in another case", "in response to a case A, in response to another case B" and the like can include the following technical solutions according to the case: A is executed regardless of B, that is, A in some embodiments; B is executed regardless of A, that is, B in some embodiments; A and B are selectively executed, that is, from A and B, execution is selected in some embodiments; A and B are both executed, that is, A and B in some embodiments. When there are more branches of A, B, C and the like, it is similar to the above.

[0104] The prefix words "first", "second" and the like in the embodiments of the present disclosure are only used to distinguish different description objects, and do not constitute limitation on the position, order, priority, quantity or content of the description objects. The description of the description objects should refer to the description in the context of the claims or embodiments, and should not constitute redundant limitation because of the use of the prefix words. For example, the description object is "field", and the ordinal words before "field" in "first field" and "second field" do not limit the position or order between "fields", and "first" and "second" do not limit whether the "fields" modified thereby are in the same message or not, nor limit the order of "first field" and "second field". For another example, the description object is "level", and the ordinal words before "level" in "first level" and "second level" do not limit the priority between "levels". For another example, the quantity of the description object is not limited by the ordinal words, and can be one or more. For example, "first device", wherein the quantity of "device" can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description object is "device", and "first device" and "second device" can be the same device or different devices, and the types thereof can be the same or different; for another example, the description object is "information", and "first information" and "second information" can be the same information or different information, and the contents thereof can be the same or different.

[0105] In some embodiments, "including A", "containing A", "for indicating A", "carrying A" can be interpreted as directly carrying A, or indirectly indicating A.

[0106] In some embodiments, the terms “in response to,” “in response to determining,” “in the event that,” “when,” “if,” “upon,” and the like can be replaced with each other.

[0107] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” “above,” and the like can be replaced with each other, and the terms “less than,” “less than or equal to,” “not greater than,” “fewer than,” “fewer than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” “below,” and the like can be replaced with each other.

[0108] In some embodiments, an apparatus and the like can be interpreted as an entity, and can also be interpreted as virtual, and the name thereof is not limited to the name described in the embodiments, and the terms “apparatus,” “equipment,” “device,” “circuit,” “network element,” “node,” “function,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” “subject,” and the like can be replaced with each other.

[0109] In some embodiments, “network” can be interpreted as an apparatus (for example, an access network device, a core network device, and the like) included in the network.

[0110] In some embodiments, the terms “access network device (AN device),” “radio access network device (RAN device),” “base station (BS),” “radio base station,” “fixed station,” “node,” “access point,” “transmission point (TP),” “reception point (RP),” “transmission / reception point (TRP),” “panel,” “antenna panel,” “antenna array,” “cell,” “macro cell,” “small cell,” “femto cell,” “pico cell,” “sector,” “cell group,” “carrier,” “component carrier,” “bandwidth part (BWP),” and the like can be used interchangeably.

[0111] In some embodiments, the terms "terminal," "terminal device," "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," and so on can be replaced with each other.

[0112] In some embodiments, an access network device, a core network device, or a network device can be replaced with a terminal. For example, for a structure in which communication between an access network device, a core network device, or a network device and a terminal is replaced with communication between a plurality of terminals (for example, also referred to as device-to-device (D2D), vehicle-to-everything (V2X), and so on), embodiments of the present disclosure can also be applied. In this case, a structure in which a terminal has all or part of the functions of an access network device can also be provided. Furthermore, the language of "uplink," "downlink," and so on can also be replaced with language corresponding to communication between terminals (for example, "side"). For example, an uplink channel, a downlink channel, and so on can be replaced with a side channel, and an uplink, a downlink, and so on can be replaced with a side link.

[0113] In some embodiments, a terminal can be replaced with an access network device, a core network device, or a network device. In this case, a structure in which an access network device, a core network device, or a network device has all or part of the functions of a terminal can also be provided.

[0114] In some embodiments, the data, information, etc. can be obtained in compliance with the laws and regulations of the country in which the location is situated.

[0115] In some embodiments, the data, information, etc. can be obtained after obtaining the consent of the user.

[0116] In addition, each element, each row, or each column in the table of the embodiments of the present disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0117] The correspondence shown in each table in the present disclosure can be configured or predefined. The values of the information in each table are merely examples, and other values can be configured, and the present disclosure is not limited thereto. When configuring the correspondence between the information and each parameter, it is not necessarily required to configure all the correspondences shown in each table. For example, the correspondences shown in some rows in the table in the present disclosure can also not be configured. For another example, the above table can be appropriately deformed, adjusted, etc., such as splitting, merging, etc. The names of the parameters shown in the titles of the above tables can also use other names understandable by the communication device, and the values or representations of the parameters can also use other values or representations understandable by the communication device. The above tables can also use other data structures when implemented, such as arrays, queues, containers, stacks, linear tables, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables, etc.

[0118] The predefinition in the present disclosure can be understood as definition, predefinition, storage, pre-storage, pre-negotiation, pre-configuration, solidification, or pre-burning.

[0119] FIG. 1 is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG. 1, the communication system 100 can include one or more of a first device, at least one second device (two second devices are taken as an example in FIG. 1), a third device, and a fourth device. Among them, the first device can be a device of a service to be migrated, that is, the first device can be a source device of service migration; the second device can be a device visible to the first device and capable of performing the service; the third device can be a device for performing the service to be migrated, that is, the third device can be a target device of service migration, wherein the third device can be any one of the at least one second device; and the fourth device can be a device for training a first model.

[0120] Optionally, the first device can be a satellite, and the second device, the third device, and the fourth device can include at least one of a satellite, a cloud server, a network device, and a terminal. Optionally, the network device can include an access network device and / or a core network device, for example.

[0121] In some embodiments, the terminal includes at least one of a mobile phone, a wearable device, an Internet of Things device, a communication-capable automobile, a smart automobile, a tablet (Pad), a wireless transceiver-equipped computer, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, a wireless terminal device in a smart home, and the like, but is not limited thereto.

[0122] In some embodiments, the access network device is at least one of a node or a device that accesses a terminal to a wireless network, and can include an evolved NodeB (eNB) in a 5G communication system, a next generation eNB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an Open RAN, a Cloud RAN, a base station in other communication systems, an access node in a wireless fidelity (WiFi) system, and the like, but is not limited thereto.

[0123] In some embodiments, the technical solutions of the present disclosure can be applied to an Open RAN architecture, in which case, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can become internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0124] In some embodiments, the access network device can be composed of a central unit (CU) and a distributed unit (DU), wherein the CU can also be referred to as a control unit. The CU-DU structure can split the protocol layers of the access network device, and the functions of part of the protocol layers are controlled by the CU, and the functions of the remaining part or all of the protocol layers are distributed in the DU, and the CU controls the DU.

[0125] In some embodiments, the core network device can be one device including one or more network elements, or can be multiple devices or device groups including all or part of the one or more network elements. The network element can be virtual or physical. The core network includes at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next-generation core (NGC), for example. Alternatively, the core network device can also be a location management function network element. The location management function network element includes a location server, which can be implemented as any one of the following: a location management function (LMF), an enhanced serving mobile location center (E-SMLC), a secure user plane location (SUPL), and a SUPL location platform (SUPL LP).

[0126] It can be understood that the communication system described in the embodiments of the present disclosure is for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and does not constitute a limitation on the technical solutions proposed in the embodiments of the present disclosure. Those skilled in the art can know that, as the system architecture evolves and new business scenarios appear, the technical solutions proposed in the embodiments of the present disclosure are also applicable to similar technical problems.

[0127] The following embodiments of the present disclosure can be applied to the communication system 100 shown in FIG. 1, or part of the main bodies, but are not limited thereto. The main bodies shown in FIG. 1 are illustrative, and the communication system can include all or part of the main bodies in FIG. 1, or other main bodies other than those in FIG. 1. The number and form of each main body is arbitrary, and the connection relationship between the main bodies is illustrative. The main bodies can be connected or not connected, and the connection can be in any manner, can be direct or indirect, and can be wired or wireless.

[0128] Embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (Bluetooth (registered trademark)), Public Land Mobile Network (PLMN) network, Device-to-Device (D2D) system, Machine to Machine (M2M) system, Internet of Things (IoT) system, Vehicle-to-Everything (V2X), system using other service migration method, next-generation system expanded based on them, and the like. In addition, a plurality of systems can be combined (for example, combination of LTE or LTE-A and 5G, and the like).

[0129] FIG. 2A is an interaction diagram of a service migration method according to an embodiment of the present disclosure. As shown in FIG. 2A, the present embodiment relates to a service migration method for the communication system 100, and the above method includes:

[0130] Step 2101, the fourth device sends the trained first model to the first device.

[0131] In some embodiments, the service migration method provided by the present disclosure can be used for service migration in a satellite edge computing process, or can also be used for service migration in other communication scenarios, which is not limited by the present disclosure.

[0132] Optionally, the first device can be a device that needs to perform service migration (or service migration), that is, the first device can be a source device of service migration, and the first device can be a satellite, for example, and the service can be a service in a terminal communication process. Optionally, the fourth device can be a device with model training capability, and the fourth device can include at least one of a cloud server, a satellite, a terminal, and a network device, for example.

[0133] Optionally, the first model can be used for deep reinforcement learning to determine a service migration path of the first device. Optionally, in some embodiments, the trained first model can be requested from the fourth device when the first device needs to perform service migration; or the fourth device can send the trained first model to the first device in advance, so that the first device can directly use the first model to determine the service migration path when the first device needs to perform service migration.

[0134] Optionally, the method for determining the service migration path by the first model can be: inputting a first parameter to the first model, so that the first model determines the service migration path of the first device based on the first parameter.

[0135] In some embodiments, the first parameter can be determined based on a network environment of an NTN in which the first device is located. The network environment can be a network environment of satellite edge computing, for example. Optionally, the network environment can include at least one second device, and the second device can be a device that can perform service and is visible to the first device. Optionally, the device that is visible to the first device can be a device that can communicate with the first device, for example. Optionally, the device that can perform service can include a device that has available service load and / or a device that has sufficient computing power to support processing service. Optionally, FIG. 2B is a structural schematic diagram of a network environment of an NTN in which a first device is located, according to an embodiment of the present disclosure. As shown in FIG. 2B, the first device can be any low earth orbit satellite in FIG. 2B, and the second device can include at least one of a remote cloud (or cloud server), a ground user (or terminal), and another low earth orbit satellite that communicates with the low earth orbit satellite.

[0136] In some embodiments, the first parameter can be used to indicate at least one of the following:

[0137] a second path;

[0138] a second parameter;

[0139] a service load available to the second device;

[0140] at least one third path.

[0141] Optionally, the second path described above can be a service migration path at a last service migration in a network environment of the NTN where the first device is located. Optionally, for the first device, it can know the service migration path at the last service migration of itself, but can not know the service migration path at the last service migration of other devices in the network environment, or the first device can only know the service migration path at the last service migration of part of the devices in the network environment. Thus, in some embodiments, the second path can be the service migration path at the last service migration in the network environment known by the first device; wherein the last service migration path known by the first device can or can not be the actual last service migration path in the network environment. Or, in other embodiments, the first device can communicate with each second device in the network environment in advance to determine the actual last service migration path in the network environment, and determine the actual last service migration path as the second path.

[0142] Optionally, the second parameter described above can be a parameter that will affect the service load of the second device.

[0143] Optionally, the third path described above can be a service migration path available to the first device. For example, assuming that the second device #1 in the network environment supports executing the service to be migrated by the first device, and the second device #2 does not support executing the service to be migrated by the first device, the path of "migrating the service from the first device to the second device #1" is determined as a service migration path available to the first device, and the path of "migrating the service from the first device to the second device #2" is determined as a service migration path unavailable to the first device.

[0144] Optionally, the model algorithm of the first model can include a Dueling-Double Deep-Q-Network (D3QN) algorithm; and the first model can be trained by a fourth device. FIG. 2C is a structural schematic diagram of the first model during training according to an embodiment of the present disclosure, as shown in FIG. 2C, the training process of the first model can include the following steps:

[0145] Step a, determining a data set Dm based on a historical service migration process in the network environment.

[0146] Optionally, the data set Dm includes at least one group of data of the network environment wherein the data This can be data from historical business migrations, optionally... This can represent the first parameter corresponding to the network environment before the service migration. This first parameter may include at least one of the following: the previous service migration path in the network environment, parameters affecting service load in the network environment, available service load in the network environment, and at least one available service migration path in the network environment. For detailed information on this part, please refer to the steps described above. It can be represented based on The identified historical migration path; This can represent the rewards of historical migration paths, for example, the service latency and service efficiency during historical migration paths; optionally, the service latency can include at least one of the following three parts: service migration delay, communication delay, and computation delay; optionally, the service migration delay can refer to the delay during the service migration process; that is, the delay of migrating the service from the source device to the target device; the communication delay can refer to the communication delay during the service migration process and / or service processing process; such as the communication delay between the source device and the target device during the service migration process and / or service processing process; the computation delay can refer to the computation delay during the service migration process and / or service processing process. Optionally, the above... This can represent the first parameter corresponding to the network environment after the service migration based on the historical migration path. For a detailed introduction to the first parameter, please refer to the above description.

[0147] Step b: Randomly sample small batches from the dataset Dm to obtain dataset Bm.

[0148] Step c: Train the first model (i.e., the main network model in Figure 2C) based on the dataset Bm, and update the model parameters until the loss function converges.

[0149] Optionally, one set of data can be... In Input is given to the main network model, making the main network model based on... Determine And determine the output of the main network model. of Based on this Determine the loss function value, update the model parameters θm of the main network model based on the loss function value, and then use another set of data. middle The input is fed into the updated main network model, the loss function value is calculated, and the model parameters are updated again. This process is repeated until the loss function converges. Optionally, the convergence of the loss function means that the current main network model can perform calculations based on the input. The low-latency and high-efficiency service migration path is successfully output, at this time, it is considered that the model training is completed, the model parameters of the target network model are updated based on the model parameters of the trained master network model, and the parameter updated target network model is determined as the trained first model.

[0150] Optionally, in some embodiments, the value of each training algorithm parameter in the training process can include:

[0151] The value of training epochs (EP) is 5000, the value of training steps (T) is 20, the value of batch size is 64, the value of the size of experience replay (D) is 100000, the value of learning rate (α) is 10 -3 , the value of discount factor (γ) is 0.9, and the value of greedy factor (ε) is 0.9.

[0152] Step 2102, the first device determines the trained first model.

[0153] Optionally, the first device can receive the trained first model sent by the fourth device, or the first device can obtain the trained first model after training the first model locally. Optionally, in some embodiments, the first device can train the first model locally when service migration is needed; or the first device can also train the first model locally in advance, and when the first device needs to perform service migration, the trained first model can be directly used to determine the service migration path.

[0154] Wherein, the detailed description of the first device and the first model can be referred to the description of step 2101 above.

[0155] Step 2103, the first device determines the first parameter.

[0156] Optionally, the first parameter can be determined when the first device needs to perform service migration. The first parameter can be determined by the first device based on the network environment of the NTN in which it is located. The first parameter can be used to indicate at least one of the following:

[0157] The second path;

[0158] The second parameter;

[0159] The amount of service load available to the second device;

[0160] At least one third path.

[0161] For a detailed description of this part, please refer to step 2101 above.

[0162] Step 2104: The first device inputs the first parameter into the first model to obtain the first path output by the first model.

[0163] For a detailed description of the first model and the first path, please refer to step 2101 above.

[0164] Optionally, the first path output by the first model can be: the path with the highest business efficiency among at least one third path. Alternatively, the first path output by the first model can be: any path among at least one third path with a business efficiency higher than the first value.

[0165] Optionally, the first path can be used to indicate: "Migrate the services of the first device to the third device".

[0166] Step 2105: The first device determines the third device based on the first path.

[0167] Optionally, the third device is a device used to perform the services to be migrated. That is, the third device is the target device for the service migration.

[0168] Step 2106: The first device sends a first request to the third device.

[0169] Optionally, the first request can be used to request a service migration. In some embodiments, the first request can carry service parameters of the service to be migrated. In other embodiments, the first request can indicate the workload required by the service to be migrated.

[0170] Step 2107: The third device sends a first response to the first device.

[0171] Optionally, the first response can be used to instruct the third device to accept the service migration of the first device.

[0172] In some embodiments, when a third device determines that its available load capacity can support the execution of the service to be migrated based on the service parameters of the service to be migrated and / or the service load required by the service to be migrated, the third device may send a first response to the first device.

[0173] Step 2108: The first device sends the service parameters of the service to be migrated to the third device.

[0174] Optionally, if the first request in step 2106 carries the service parameters of the service to be migrated, step 2108 may not be executed. If the first request in step 2106 does not carry the service parameters of the service to be migrated, step 2108 may be executed.

[0175] Step 2109, the third device performs the migrated service.

[0176] To sum up, in the above embodiment, when the first device needs to perform service migration, the first parameter can be determined based on the network environment of the NTN where the first device is located, and the first parameter is input into the first model, so that the first model outputs the first path, and then the first device can perform service migration based on the first path. The first model is used for deep reinforcement learning, the first path is a service migration path determined by the first model based on the first parameter, and the first parameter is determined based on the network environment of the NTN where the first device is located. Therefore, it can be known that the service migration path in the present disclosure is determined by the first model through deep reinforcement learning based on the NTN network environment. The first model can determine a service migration path with better effect in the NTN network environment through deep reinforcement learning function. The better effect can include lower service delay and higher service efficiency. Therefore, when the first device performs service migration based on the determined service migration path subsequently, the delay can be ensured to be low and the efficiency can be ensured to be high, and the execution performance of the service is ensured.

[0177] In the above embodiment, the first device can also not train the first model locally, but can receive the first model trained by other devices, thereby reducing the execution complexity of the first device.

[0178] The service migration method related to the embodiments of the present disclosure can include at least one of steps 2101-2109. For example, step 2101 can be implemented as an independent embodiment, step 2102 can be implemented as an independent embodiment, step 2103 can be implemented as an independent embodiment, and step 2101+S2102 can be implemented as an independent embodiment, but not limited thereto.

[0179] In the present embodiment or example, each step can be independent, arbitrarily combined or exchanged in order, the optional mode or optional example can be arbitrarily combined, and can be arbitrarily combined with any step of other embodiments or other examples.

[0180] FIG. 3 is an interaction schematic diagram of a service migration method according to an embodiment of the present disclosure. As shown in FIG. 3, the present embodiment relates to a service migration method for a first device, and the above method includes:

[0181] Step 3101, in response to the first device needing to perform service migration, determining a first parameter based on the network environment of the NTN where the first device is located.

[0182] Step 3102, inputting the first parameter into the first model to obtain a first path output by the first model.

[0183] Step 3103, migrating the service based on the first path.

[0184] Optionally, the network environment comprises at least one second device, the second device being a service-executable device visible to the first device.

[0185] Optionally, the first model is used for deep reinforcement learning, and the first path is a service migration path determined by the first model based on the first parameter.

[0186] The first parameter is used to indicate at least one of the following:

[0187] A second path, the second path being a service migration path at the last service migration in the network environment.

[0188] A second parameter, the second parameter being a parameter affecting the service load of the second device.

[0189] The service load available to the second device.

[0190] At least one third path, the third path being a service migration path available to the first device.

[0191] Optionally, the first path output by the first model is a path with the highest service efficiency among the at least one third path.

[0192] Optionally, the first path output by the first model is any path in the at least one third path with service efficiency higher than a first value.

[0193] Optionally, the first device is a satellite, and the second device comprises a satellite and / or a cloud server.

[0194] Optionally, the migrating the service based on the first path comprises:

[0195] Determining a third device based on the first path, the third device being a device for executing the service to be migrated.

[0196] Sending a first request to the third device, the first request being used for requesting to migrate the service, and / or the first request carrying a service parameter of the service to be migrated.

[0197] Receiving a first response sent by the third device, the first response being used for indicating that the third device accepts the service migration of the first device.

[0198] Optionally, the migrating the service based on the first path comprises:

[0199] determining a third device based on the first path; the third device is a device for performing the service to be migrated;

[0200] sending a first request to the third device, the first request being used for requesting service migration, and / or the first request being used for indicating a service load required by the service to be migrated;

[0201] receiving a first response sent by the third device, the first response being used for indicating that the third device accepts service migration of the first device;

[0202] sending a service parameter of the service to be migrated to the third device.

[0203] Optionally, a model algorithm of the first model comprises a Dueling-Double Deep-Q-Network (D3QN) algorithm.

[0204] Optionally, the method further comprises:

[0205] receiving the first model trained before the first parameter is input into the first model; or

[0206] training the first model before the first parameter is input into the first model.

[0207] For detailed descriptions of steps 3101-3103, refer to the descriptions of the above embodiments.

[0208] The determination method related to the embodiments of the present disclosure can include at least one of steps S3101-S3103. For example, step S3101 can be implemented as an independent embodiment, step S3102 can be implemented as an independent embodiment, and steps S3101-S3102 can be implemented as an independent embodiment, but are not limited thereto.

[0209] In the present embodiment or example, each step can be independently combined or exchanged in order, and optional modes or examples can be combined with any step of other embodiments or examples.

[0210] The following is an exemplary introduction to the above method.

[0211] The present disclosure adopts a deep reinforcement learning technology in a 6G network, and uses a distributed scheme of a Dueling-Double Deep-Q-Network (D3QN) algorithm for split path selection to find an optimal solution.

[0212] The algorithm based on deep reinforcement learning usually has high training time and computational complexity, and it is beneficial if the training operation can be performed on the cloud. A distributed scheme based on D3QN algorithm is designed. D3QN, as a variant of Deep-Q Network (DQN), is very suitable for solving problems in discrete action space. The scheme based on D3QN can be trained on the remote cloud due to its off-policy learning ability.

[0213] Optionally, the diagram of the satellite edge computing network can refer to FIG. 2B described above.

[0214] Optionally, FIG. 4 is a schematic diagram of a satellite edge computing service migration process according to an embodiment of the present disclosure.

[0215] In the satellite network, a task offloading scheme with service migration is proposed to maintain the continuity of services. In the satellite edge computing framework, the offloading decision of delay-sensitive tasks is determined.

[0216] The goal is to minimize the long-term average delay of all users under the constraints of energy and storage resources. This goal is limited by the limited service range and limited resource capacity of the satellite.

[0217] When selecting the offloading path, the actual problem of high-speed maneuvering and load imbalance of LEO satellites is considered.

[0218] This problem is formulated as a Markov Decision Process (MDP) to meet the high-speed satellite motion and dynamic service demand. In order to solve the problem of large discrete action space, a distributed scheme based on D3QN is trained on the cloud to obtain a real-time offloading strategy.

[0219] The service delay of user m at time slot t is composed of the following three parts

[0220] Service migration delay: the service migration delay of user m is caused by the service migration between LEO satellites, the service migration between LEO satellites and remote clouds

[0221] Communication delay: the communication delay of user to offloading node includes the transmission time between user and LEO satellite and the transmission time between user and remote cloud.

[0222] Computing delay: the computing delay is the total computing time of user in all offloading nodes (including LEO satellites and remote clouds) in the network

[0223] The energy consumption of satellite n at time slot t includes the following three parts:

[0224] Service migration consumption: service migration consumption is used to transfer state information between different computing servers.

[0225] Communication consumption: the communication consumption of satellite n is represented as the transmission consumption between the access satellite and the offloading node.

[0226] Computational consumption: the computational consumption of satellite n.

[0227] The structure of the deep learning method can refer to the above-mentioned FIG. 2C.

[0228] The process of migrating services is converted into a Markov decision process:

[0229] D3QN introduces a duel network based on the DDQN algorithm to improve stability and efficiency

[0230] The distributed task offloading algorithm based on D3QN for user m is as follows:

[0231] Initialization stage

[0232] 1. Initialize the data Dm, M is the number of set first models in the network environment.

[0233] 2. Initialize the D3QN network parameters θm, θm-=θm; θm is the network parameter of the main network model, and θm- is the network parameter of the target network model.

[0234] 3. Initialize the Q value of the main network model and the value of the target network model.

[0235] 4. From episode equal to 1, until episode equal to EP, the following steps 5 to 12 are executed in a loop.

[0236] 5. Initialize

[0237] 6. From t equal to 1, until t equal to T, the following steps 7 to 12 are executed in a loop.

[0238] 7. Use the € greedy strategy in Q to select an action based on the state .

[0239] 8. Perform the action , then obtain the immediate reward and the next state .

[0240] 9. Store the experience data into Dm.

[0241] 10. Randomly draw a small batch Bm from Dm.

[0242] 11. Set the target and update θmby gradient descent steps Update θmuntil the main network model can output the optimal solution.

[0243] 12. Update the target parameter θm-=θmevery G steps.

[0244] Optionally, the training can refer to the following parameters:

[0245] Algorithm Parameters

[0246] Training epochs (EP): 5000;

[0247] Training steps (T): 20;

[0248] Batch size: 64;

[0249] The size of experience replay (D): 100000;

[0250] Learning rate (α): 10 -3 ;

[0251] Discount factor (γ): 0.9;

[0252] Greedy factor (ε): 0.9.

[0253] Compared with the centralized scheduling mechanism, the designed algorithm adopts a distributed scheduling manner. In this case, the computational complexity is distributed to each user. The optimal strategy is to maximize the total return of all agents. The designed algorithm iterates until the optimal task offloading strategy is obtained. By utilizing the off-policy property of the D3QN framework, we train using a remote cloud. The remote cloud sends the trained model to the satellites, enabling them to make real-time offloading decisions.

[0254] The method of the present disclosure is to minimize the long-term average delay of all users under the constraints of energy and storage resources in the satellite network of 6G by using deep reinforcement learning technology.

[0255] As can be seen from the above, the deep reinforcement learning technology and the distributed scheme of the D3QN algorithm are used in the present disclosure to find the optimal solution for offloading path selection. The goal is to minimize the long-term average delay of all users under the constraints of energy and storage resources.

[0256] The embodiments of the present disclosure further provide a device for implementing any of the above methods, for example, a device comprising units or modules for implementing the steps performed by the terminal in any of the above methods. For another example, another device is provided, comprising units or modules for implementing the steps performed by the network equipment (such as an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0257] It should be understood that the division of each unit or module in the above device is only a logical function division, and all or part of the units or modules can be integrated into one physical entity or physically separated in actual implementation. In addition, the units or modules in the device can be implemented in the form of processor invoking software: for example, the device comprises a processor connected with a memory, the memory stores instructions, and the processor invokes the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit or module of the device, wherein the processor is a general processor such as a central processing unit (CPU) or a microprocessor, and the memory is a memory in the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuit, and the functions of part or all of the units or modules can be implemented by the design of the hardware circuit, and the hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC), and the functions of part or all of the units or modules are implemented by the design of the logical relationship between the elements in the circuit; for another example, in another implementation, the hardware circuit is a programmable logic device (PLD), and taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to implement the functions of part or all of the units or modules. All units or modules of the above device can be implemented in the form of processor invoking software, or all units or modules can be implemented in the form of hardware circuit, or part of the units or modules are implemented in the form of processor invoking software, and the remaining part is implemented in the form of hardware circuit.

[0258] In the embodiments of the present disclosure, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and running capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), a digital signal processor (DSP), and the like. In another implementation, the processor can implement certain functions through a logical relationship of hardware circuits, and the logical relationship of the hardware circuits is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In the reconfigurable hardware circuit, the processor loads a configuration document to implement the configuration of the hardware circuit. It can be understood that the processor loads instructions to implement the functions of the above part or all units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), and the like.

[0259] FIG. 5 is a structural schematic diagram of a first device according to an embodiment of the present disclosure. As shown in FIG. 5, the first device includes:

[0260] The processing module is configured to determine a first parameter based on a network environment of a non-terrestrial network (NTN) in which the first device is located, in response to the first device needing to perform service migration. The network environment includes at least one second device, and the second device is a device that can perform services and is visible to the first device.

[0261] The processing module is further configured to input the first parameter into a first model to obtain a first path output by the first model. The first model is used for deep reinforcement learning, and the first path is a service migration path determined by the first model based on the first parameter.

[0262] The processing module is further configured to perform service migration based on the first path.

[0263] Optionally, the processing module is configured to perform the steps related to "processing" performed by the first device in any of the above methods, and the transceiver module is configured to perform the steps related to "transceiving" performed by the first device in any of the above methods.

[0264] FIG. 6A is a structural schematic diagram of a communication device 6100 according to the embodiments of the present disclosure. The communication device 6100 can be a network device (e.g., an access network device, a core network device, etc.), a terminal (e.g., a user equipment or the first device described above, etc.), a chip, a chip system, or a processor supporting the network device to implement any of the above methods, or a chip, a chip system, or a processor supporting the terminal to implement any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments, and details can be referred to the descriptions in the above method embodiments.

[0265] As shown in FIG. 6A, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general processor or a special-purpose processor, etc., for example, a baseband processor or a central processing unit. The baseband processor can be configured to process communication protocols and communication data, and the central processing unit can be configured to control the communication device (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process data of the programs. The processor 6101 is configured to invoke instructions to enable the communication device 6100 to perform any of the above methods.

[0266] In some embodiments, the communication device 6100 further includes one or more memories 6102 configured to store instructions. Optionally, all or part of the memory 6102 can also be located outside the communication device 6100.

[0267] In some embodiments, the communication device 6100 further includes one or more transceivers 6103. When the communication device 6100 includes one or more transceivers 6103, the communication steps such as sending and receiving in the above methods are performed by the transceiver 6103, and other steps are performed by the processor 6101.

[0268] In some embodiments, the transceiver can include a receiver and a transmitter, which can be separate or integrated together. Optionally, the terms of transceiver, transceiving unit, transceiver, transceiving circuit, etc. can be replaced by each other, the terms of transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced by each other, and the terms of receiver, receiving unit, receiver, receiving circuit, etc. can be replaced by each other.

[0269] Optionally, the communication device 6100 further includes one or more interface circuits 6104 connected to the memory 6102, which can be configured to receive and output signals to / from the memory 6102 or other devices. For example, the interface circuit 6104 can read instructions stored in the memory 6102 and transmit the instructions to the processor 6101.

[0270] The communication device 6100 described in the above embodiments can be a network device or a terminal, but the scope of the communication device 6100 described in the present disclosure is not limited thereto, and the structure of the communication device 6100 can not be limited by FIG. 6a. The communication device can be a standalone device or can be part of a larger device. For example, the communication device can be: 1) a standalone integrated circuit (IC), or a chip, or a chip system or subsystem; (2) a set of one or more ICs, which can optionally also include storage components for storing data, programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, a smart terminal device, a cellular phone, a wireless device, a handset, a mobile unit, a vehicle-mounted device, a network device, a cloud device, an artificial intelligence device, etc.; (6) other devices, etc.

[0271] FIG. 6B is a structural schematic diagram of a chip 6200 according to an embodiment of the present disclosure. For the case where the communication device 6100 is a chip or a chip system, the structural schematic diagram of the chip 6200 shown in FIG. 6B can be referred to, but is not limited thereto.

[0272] The chip 6200 includes one or more processors 6201 configured to invoke instructions to cause the chip 6200 to perform any of the above methods.

[0273] In some embodiments, the chip 6200 further includes one or more interface circuits 6202 connected to the memory 6203, which can be configured to receive and output signals to / from the memory 6203 or other devices. For example, the interface circuit 6202 can read instructions stored in the memory 6203 and transmit the instructions to the processor 6201. Optionally, the terms interface circuit, interface, transceiver pin, and transceiver can be replaced by each other.

[0274] In some embodiments, the chip 6200 further includes one or more memories 6203 for storing instructions. Optionally, all or part of the memory 6203 can be outside the chip 6200.

[0275] The disclosure further provides a storage medium having stored instructions which, when executed on the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto and can also be a storage medium readable by other apparatuses. Optionally, the storage medium can be a non-transitory storage medium, but is not limited thereto and can also be a transitory storage medium.

[0276] The disclosure further provides a program product which, when executed by the communication device 6100, causes the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0277] The disclosure further provides a computer program which, when executed on a computer, causes the computer to perform any of the above methods.

[0278] In the above embodiments, all or some of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or some of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs. When the computer programs are loaded on a computer and executed, all or some of the processes or functions described in the embodiments of the disclosure are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer programs can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer programs can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media sets. The available media can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a high-density digital video disc (DVD)), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0279] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software manner depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the disclosure.

[0280] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0281] The above is only a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present disclosure, which should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A business migration method, characterized in that, Performed by a first device, the method includes: In response to the need for service migration of the first device, a first parameter is determined based on the network environment of the non-terrestrial network (NTN) where the first device is located; wherein, the network environment includes at least one second device, which is a device visible to the first device that can perform services; The first parameter is input into the first model to obtain the first path output by the first model; the first model is used for deep reinforcement learning, and the first path is the business migration path determined by the first model based on the first parameter. Business migration is performed based on the first path.

2. The method as described in claim 1, characterized in that, The first parameter is used to indicate at least one of the following: The second path is the service migration path during the last service migration in the network environment. The second parameter is a parameter that will affect the service load of the second device. The available service load of the second device; At least one third path, which is a service migration path available to the first device.

3. The method as described in claim 2, characterized in that, The first path output by the first model is: the path with the highest business efficiency among at least one third path.

4. The method as described in claim 2, characterized in that, The first path output by the first model is any path among at least one third path whose business efficiency is higher than the first value.

5. The method according to any one of claims 1-4, characterized in that, The first device is a satellite, and the second device includes a satellite and / or a cloud server.

6. The method according to any one of claims 1-5, characterized in that, The service migration based on the first path includes: A third device is determined based on the first path; the third device is a device used to perform the service to be migrated. Send a first request to the third device, the first request being used to request service migration, and / or, the first request carrying service parameters of the service to be migrated; The device receives a first response from the third device, which instructs the third device to accept the service migration from the first device.

7. The method according to any one of claims 1-5, characterized in that, The service migration based on the first path includes: A third device is determined based on the first path; the third device is a device used to perform the service to be migrated. Send a first request to the third device, the first request being used to request service migration, and / or, the first request being used to indicate the service load required for the service to be migrated; Receive a first response sent by the third device, wherein the first response is used to instruct the third device to accept the service migration of the first device; Send the service parameters of the service to be migrated to the third device.

8. The method according to any one of claims 1-7, characterized in that, The model algorithm for the first model includes the competitive dual deep Q-network D3QN algorithm.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: Before inputting the first parameter into the first model, receive the trained first model; or The first model is trained before the first parameter is input into the first model.

10. A first device, characterized in that, include: The processing module is configured to determine a first parameter based on the network environment of the non-terrestrial network (NTN) where the first device is located in response to the need for service migration of the first device; wherein the network environment includes at least one second device, which is a device visible to the first device that can perform services; The processing module is further configured to input the first parameter into the first model to obtain the first path output by the first model; the first model is used to perform deep reinforcement learning, and the first path is a business migration path determined by the first model based on the first parameter; The processing module is also used to perform business migration based on the first path.

11. A communication device, characterized in that, include: One or more processors; A memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the communication device to perform the method of any one of claims 1 to 9.

12. A storage medium storing instructions, characterized in that, When the instructions are executed on the communication device, the communication device performs the method as described in any one of claims 1 to 9.

13. A program product, when the program product is run on a communication device, causes the communication device to perform the information processing method as described in any one of claims 1 to 9.

Images