Improved wireless communication in vehicle macro clouds

By introducing distributed control planes and data planes into the vehicle macro cloud, wireless communication between vehicle micro clouds is optimized, and the problem of low communication efficiency between vehicle micro clouds in the vehicle macro cloud is solved, and faster data transmission and Higher reliability.

CN118945197APending Publication Date: 2024-11-12TOYOTA JIDOSHA KK
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411204634.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2018-11-14
Filing Date
2019-11-14
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing wireless communication between vehicle micro-clouds in the macro clouds of vehicles has problems such as long waiting time and high data loss, especially when the content provider is away from the requester during data transmission, resulting in low delivery efficiency.

Method used

A distributed control plane and data plane are introduced into the vehicle macro cloud, and a state data structure is established between the vehicle micro cloud through the plane client, waiting time and packet delivery rate are measured, data request routing is optimized, and the most suitable content provider is selected. And cache popular data locally to reduce latency and loss risk.

Benefits of technology

It effectively reduces the waiting time and data loss of wireless communication between vehicles and micro-clouds, improves the efficiency and reliability of data transmission, and optimizes data routing and storage through distributed control planes and data planes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945197A_ABST
    Figure CN118945197A_ABST
Patent Text Reader

Abstract

The invention relates to an improved wireless communication in a vehicle macro cloud. The present disclosure includes embodiments for improving wireless communication between vehicle microclouds within a vehicle macro cloud. In some embodiments, a method for a control plane (CP) node in a vehicle microcloud includes receiving a data request via a vehicle-to-everything (V2X) network; analyzing the data request using a control plane to select a target content provider for providing data content requested by the data request; processing the data request using the data plane; generating feedback data including one or more of result data describing a processing result of the data request and control plane data; and modifying an operation of the CP node based on the feedback data such that a reduction in one or more of latency including data transfer and data packet loss is achieved for a data request processed by the CP node. The reduction is improved over time due to generation of more feedback data.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This divisional application is a divisional application of Chinese patent application No. 201911111278.5, entitled “Improved Wireless Communication in Vehicle Macro Cloud”, filed on November 14, 2019. Technical Field

[0002] The present specification relates to improving wireless communications between groups of vehicle micro clouds within a vehicle macro cloud. Background Art

[0003] Cloud computing facilitates emerging services for connected and autonomous vehicles, as vehicles are expected to exchange increasing amounts of data content with remote cloud servers (e.g., via cellular networks). Examples of such data content include three-dimensional road maps for autonomous driving, content for infotainment services, etc. The growing network traffic between vehicles and cloud servers may result in a significant load on the radio access network and the underlying backbone network.

[0004] Distributed data storage by a cluster of connected vehicles (i.e., a "vehicle cloud") is a promising solution to cope with the increasing network traffic generated for and by connected vehicles. Vehicles collaboratively store (or cache) data content in their onboard data storage devices and share data content via vehicle-to-vehicle (V2V) networks upon request from other vehicles.

[0005] The vehicle micro cloud itself can also be organized into a vehicle macro cloud. In this way, each vehicle micro cloud can benefit from the computing resources of other vehicle micro clouds. Summary of the invention

[0006] Embodiments of a plane client installed in a control plane (CP) node for improving wireless communication between a group of vehicle cloudlets are described, wherein each vehicle cloudlet is a member of a vehicle macro cloud. The vehicle cloudlets each have a CP node with a plane client. Individual plane clients in individual CP nodes corresponding to a group of vehicle cloudlets may provide a mechanism for the vehicle cloudlets to communicate with each other with less latency and data loss. In contrast, existing solutions for vehicle macro clouds that require V2V communication between constituent vehicle cloudlets suffer from latency and data loss in V2V communication.

[0007] In some embodiments described herein, it is assumed that the group of vehicle micro-clouds includes a first vehicle micro-cloud and a second vehicle micro-cloud without loss of generality. The plane client is installed in a vehicle of the vehicle macro cloud. The plane client includes code and routines that are operable when executed by one or more processors to cause the one or more processors to establish (1) a distributed control plane and (2) a data plane between the first vehicle micro-cloud and the second vehicle micro-cloud and any other vehicle micro-clouds included in the vehicle macro cloud. For example, the distributed control plane is used for distributed vehicle-to-everything (V2X) (e.g., V2V) communication between the vehicle micro-cloud and its member vehicles.

[0008] Plane clients in various vehicles included in the vehicle cloudlet are operable to cooperate with each other to provide the functionality described herein. Each plane client includes code and routines operable to perform one or more of the following operations (1)-(11).

[0009] Operation (1): Plane clients of two or more CP nodes (eg, two or more vehicles) in two or more vehicle micro-clouds in different micro-vehicle clouds establish (a) a distributed control plane and (b) a data plane between the two or more vehicle micro-clouds.

[0010] Operation (2): A plane client of at least one CP node in each vehicle cloudlet generates state data. The state data of a vehicle cloudlet is digital data describing one or more of the following types of state information: (a) the geographic location of the vehicle cloudlet; (b) a list of data files stored by the vehicle cloudlet (i.e., a "content list") and information described by each data file; (c) one or more computing resources available for that particular vehicle cloudlet; and (d) any requests for data transfer, data replication, or data recovery that that particular vehicle cloudlet may need to satisfy.

[0011] This operation (2) and any other operations performed by the CP node can be performed by a single vehicle within a specific vehicle micro-cloud, or by multiple vehicles in a specific vehicle micro-cloud in collaboration. Accordingly, the CP node for a specific vehicle micro-cloud can be a single vehicle within the vehicle micro-cloud, or can be multiple vehicles in the vehicle micro-cloud that work collaboratively to provide the functions of the CP node for the specific vehicle micro-cloud.

[0012] Operation (3): The plane client of each CP node of the vehicle macro cloud periodically exchanges its status data with other CP nodes of the vehicle macro cloud. The control plane established at operation (1) can be used for such exchange of status data.

[0013] Operation (4): The plane client of each CP node establishes a state data structure, which respectively includes (and organizes) the state data received at operation (3).

[0014] Operation (5): If V2X (e.g., V2V) communication is used for operation (3), the plane client of the CP node respectively measures (a) latency (i.e., described by "latency data") and (b) packet delivery rate (i.e., described by "packet data") when performing operation (4). Accordingly, after performing operation (5), each CP node may include the following digital data collectively referred to as "resource data": (a) its own status data; (b) one or more status data structures, including status data of one or more other CP nodes; (c) latency data measured when exchanging status data at operation (4); and (d) packet data measured when exchanging status data at operation (4).

[0015] Operation (6): A flat client of a vehicle (which is not necessarily a CP node or even a member of a micro-cloud) wants to obtain data content from a vehicle micro-cloud. Assume that the flat client of the vehicle generates a request for the data content and transmits the request to a nearby first vehicle micro-cloud. The vehicle that performs this operation (6) can be referred to as a requester.

[0016] Operation (7): The flat client of the CP node of the first vehicle micro cloud for operation (6) retrieves the content list of the first vehicle micro cloud and determines whether the requested data content is stored by the first vehicle micro cloud. Operation (7) can proceed to branch (7.a) or branch (7.b).

[0017] At branch (7.a), if the requested data content is stored by the first vehicle micro-cloud, the plane client of the CP node of the first vehicle micro-cloud replies to the data request of operation (6) with a V2X wireless message including the requested data content as its payload.

[0018] At branch (7.b), if the first vehicle micro-cloud does not store the requested data, the plane client of the CP node of the first vehicle micro-cloud analyzes its resource data to determine the provider that best suits the requested data content. It is assumed that this most suitable provider is the second vehicle micro-cloud. The plane client of the CP node of the first vehicle micro-cloud uses the control plane established at operation (1) to forward the data request received at operation (6) to the CP node of the second vehicle micro-cloud. The following operations (8)-(11) assume that branch (7.b) is executed instead of branch (7.a).

[0019] Operation (8): Data prefetching can be performed. The plane client for the CP nodes of the second vehicle micro-cloud and the first vehicle micro-cloud records the "request data" describing the data content requested by the requester at operation (6). In this way, the plane client monitors the frequency of requesting specific data content (the requested data content can be used for future calculations to improve performance in terms of reducing waiting time and reducing data packet loss). The plane client monitors the popularity of different data content and prefetches popular data content. In this way, when the requester requests popular data content, branch (7.a) can be executed without executing branch (7.b) and the operations after branch (7.b).

[0020] Operation (9): The plane client of the CP node of the second vehicle micro-cloud provides the data content to the CP node of the first vehicle micro-cloud.

[0021] Operation (10): Data caching may be performed. The flat client caches for the CP nodes of the second vehicle cloudlet and the first vehicle cloudlet include the "content data" of the data content requested by the requester at operation (6). In this way, the flat client caches the content data for future requests received for the data content, thereby reducing the latency of these future requests because future requests for the same data content in branch 7(b) and its subsequent operations will no longer be required. This also reduces the risk of losing data packets for these future requests.

[0022] Operation (11): The plane client of the CP node of the first vehicle micro-cloud responds to the request of operation (6) by providing the requested data content to the requester.

[0023] In some embodiments, data replication and failover as implemented by the control plane may also be performed.

[0024] The (one or more) plane clients described herein can beneficially reduce latency and data packet loss of wireless communications between various vehicle micro clouds that are components of a vehicle macro cloud. The (one or more) plane clients described herein provide this functionality in part by establishing a distributed control plane. In contrast, no existing solution uses a distributed control plane to reduce latency and data packet loss of wireless communications between various vehicle micro clouds.

[0025] A system of one or more computers may be configured to perform specific operations or actions by installing software, firmware, hardware, or a combination thereof on the system, which in operation causes the system to perform these actions. One or more computer programs may be configured to perform specific operations or actions by including instructions that, when executed by a data processing device, cause the device to perform these actions.

[0026] A general aspect includes a method for a first control plane (CP) node in a first vehicle micro-cloud of a vehicle macro cloud, the method comprising: receiving a data request from a requester via a vehicle-to-everything (V2X) network; analyzing the data request using a control plane to select a target content provider for providing data content requested by the data request, wherein the target content provider is a second CP node in a second vehicle micro-cloud of the vehicle macro cloud; processing the data request using a data plane; generating feedback data, the feedback data including one or more of result data describing a result of processing the data request and control plane data associated with the control plane; and modifying the operation of the first CP node based on the feedback data, so that a reduction in one or more of data transfer latency and data packet loss is achieved for the data request processed by the first CP node, wherein the reduction is improved over time due to the generation of more feedback data. Other embodiments of this aspect include corresponding computer systems, apparatuses, and computer programs recorded on one or more computer storage devices, each of which is configured to perform the actions of the method.

[0027] Implementations may include one or more of the following features. The method, wherein the data request processed by the first CP node requests popular data content, and modifying the operation of the first CP node based on feedback data includes: analyzing the feedback data to determine one or more types of popular data content; and modifying the operation of the communication unit of the first CP node so that the communication unit pre-fetches and stores the one or more types of popular data content on the first CP node to achieve one or more reductions in latency of data transfer and data packet loss for the data request. The method, wherein the data request processed by the first CP node requests data content again, and modifying the operation of the first CP node based on feedback data includes: modifying the operation of the communication unit of the first CP node so that the communication unit caches data content on the first CP node based on feedback data to achieve one or more reductions in latency of data transfer and data packet loss for the data request. The method also includes: cooperating with at least a second CP node of a second vehicle micro cloud to establish a control plane and a data plane for a vehicle macro cloud, wherein the control plane is a distributed control plane and includes at least a first CP node of the first vehicle micro cloud and a second CP node of the second vehicle micro cloud. The method, wherein the control plane is used to handle the distributed V2X communication of the control type between the vehicle micro cloud of the vehicle macro cloud and the member vehicles of the vehicle micro cloud; and the data plane is used to handle the distributed V2X communication of the data transfer type between the vehicle micro cloud of the vehicle macro cloud and the member vehicles of the vehicle micro cloud. The method also includes: generating first state data describing the state of the first vehicle micro cloud; and applying the control plane to perform state data exchange in the vehicle macro cloud, including: sending the first state data to the second CP node of the second vehicle micro cloud; and receiving the second state data describing the state of the second vehicle micro cloud from the second CP node of the second vehicle micro cloud. The method, wherein the first state data includes data describing one or more of the following: the geographical location of the first vehicle micro cloud; a content list describing a list of data files stored by the first vehicle micro cloud and the information described by each data file; one or more computing resources available on the first vehicle micro cloud; one or more data transfer requests that the first vehicle micro cloud needs to satisfy; one or more data replication requests that the first vehicle micro cloud needs to satisfy; and one or more data recovery requests that the first vehicle micro cloud needs to satisfy. The method also includes: based on the status data exchange performed in the vehicle macro cloud, measuring network data including waiting time data describing the waiting time of data transmission and packet data describing the packet transmission rate, and generating resource data of the first vehicle micro cloud, which includes one or more of the following: first status data of the first vehicle micro cloud; a status data structure including second status data of the second vehicle micro cloud; and network data including waiting time data and packet data.The method, wherein analyzing a data request using a control plane to select a target content provider includes: retrieving a content list from first state data describing a state of a first vehicle micro-cloud to determine whether the data content requested by the data request is stored by the first vehicle micro-cloud; and in response to the data content requested by the data request not being stored by the first vehicle micro-cloud, analyzing resource data of the first vehicle micro-cloud to determine that the target content provider is a second CP node of a second vehicle micro-cloud. The method, wherein the target content provider is a second CP node of a second vehicle micro-cloud, which satisfies one or more of the following: the second CP node stores the data content in a storage device of the second vehicle micro-cloud; the second CP node has the shortest distance to the first CP node compared to one or more other CP nodes of one or more other vehicle micro-clouds in a vehicle macro cloud; the second CP node has the shortest waiting time to the first CP node compared to one or more other CP nodes; and the second CP node has the highest packet delivery rate to the first CP node compared to one or more other CP nodes. The method, wherein processing a data request using a data plane includes: processing a data request using a data plane based on a decision made by a control plane. The method, wherein the data request is forwarded to the target content provider via the V2X network as a control message through the control plane. The method, wherein based on the decision made by the control plane, using the data plane to process the data request includes: receiving data content from the target content provider via the V2X network using the data plane; and forwarding the data content received from the target content provider to the requester via the V2X network using the data plane. The method also includes: monitoring a data replication trigger event in the first vehicle micro cloud; and in response to the occurrence of the data replication trigger event, replicating the data of the first vehicle micro cloud to another vehicle micro cloud in the vehicle macro cloud. The method also includes: determining that a data content group is lost in the first vehicle micro cloud; and obtaining the group of data content from another vehicle micro cloud in the vehicle macro cloud to restore the group of data content in the first vehicle micro cloud. The method, wherein the first CP node of the first vehicle micro cloud includes a vehicle of the first vehicle micro cloud or a plurality of vehicles of the first vehicle micro cloud that work in collaboration to provide the functions of the first CP node. Implementations of the described technology may include hardware, methods or processes, or computer software on a computer-accessible medium.

[0028] One general aspect includes a system, the system including an onboard computer system of a networked vehicle acting as a first control plane (CP) node of a first vehicle micro-cloud in a vehicle macro cloud, including a communication unit, a processor, and a non-transitory memory storing computer code, the computer code, when executed by the processor, causes the processor to: receive a data request from a requester via a vehicle-to-everything (V2X) network; analyze the data request using a control plane to select a target content provider for providing data content requested by the data request, wherein the target content provider is a second CP node in a second vehicle micro-cloud of the vehicle macro cloud; process the data request using a data plane; generate feedback data, the feedback data including one or more of result data describing the processing result of the data request and control plane data associated with the control plane; and modify the operation of the first CP node based on the feedback data, so that for the data request processed by the first CP node, a reduction is achieved including one or more of latency of data transfer and data packet loss, wherein the reduction is improved over time due to the generation of more feedback data. Other embodiments of this aspect include corresponding computer systems, apparatuses, and computer programs recorded on one or more computer storage devices, each of which is configured to perform the actions of the method.

[0029] Implementations may include one or more of the following features. The system, wherein the computer code, when executed by the processor, further causes the processor to: cooperate with at least the second CP node of the second vehicle micro-cloud to establish a control plane and a data plane for the vehicle macro cloud, wherein the control plane is a distributed control plane and includes at least the first CP node of the first vehicle micro-cloud and the second CP node of the second vehicle micro-cloud. The system, wherein the control plane is used to handle distributed V2X communications of a control type between a vehicle micro-cloud of a vehicle macro cloud and member vehicles of the vehicle micro-cloud; and the data plane is used to handle distributed V2X communications of a data transfer type between a vehicle micro-cloud of a vehicle macro cloud and member vehicles of the vehicle micro-cloud. Implementations of the described technology may include hardware, methods or processes, or computer software on a computer-accessible medium.

[0030] One general aspect includes a computer program product, the computer program product including a non-transitory memory storing computer executable code, the computer executable code, when executed by a processor of a first control plane (CP) node in a first vehicle micro-cloud of a vehicle macro cloud, causes the processor to: receive a data request from a requester via a vehicle-to-everything (V2X) network; analyze the data request using a control plane to select a target content provider for providing data content requested by the data request, wherein the target content provider is a second CP node in a second vehicle micro-cloud of the vehicle macro cloud; process the data request using a data plane; generate feedback data, the feedback data including one or more of result data describing the processing result of the data request and control plane data associated with the control plane; and modify the operation of the first CP node based on the feedback data, so that for the data request processed by the first CP node, a reduction is achieved including one or more of latency of data delivery and data packet loss, wherein the reduction is improved over time due to the generation of more feedback data. Other embodiments of this aspect include corresponding computer systems, apparatuses, and computer programs recorded on one or more computer storage devices, each of which is configured to perform the actions of the method.

[0031] Implementations may include one or more of the following features. The computer program product, wherein the computer code, when executed by a processor, further causes the processor to: cooperate with at least a second CP node of a second vehicle micro cloud to establish a control plane and a data plane for a vehicle macro cloud, wherein the control plane is a distributed control plane and includes at least a first CP node of a first vehicle micro cloud and a second CP node of a second vehicle micro cloud. Implementations of the described technology may include hardware, methods or processes, or computer software on a computer-accessible medium. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present disclosure is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings in which like references are used to refer to similar elements.

[0033] Figure 1A is a block diagram illustrating an example vehicle macro cloud according to some embodiments.

[0034] Figure 1B is a block diagram illustrating an example CP node for a vehicle cloudlet according to some embodiments.

[0035] Figure 1C is a block diagram illustrating an operating environment for a flat client according to some embodiments.

[0036] Figure 1D is another block diagram illustrating an operating environment for a flat client according to some embodiments.

[0037] Figure 1E is a block diagram illustrating an example flow process for a data request according to some embodiments.

[0038] Figure 2 is a block diagram illustrating an example computer system including a flat client according to some embodiments.

[0039] Figure 3 A method for improving wireless communication between a group of vehicle micro-clouds within a vehicle macro-cloud is described in accordance with some embodiments.

[0040] Figures 4A-4C Another method for improving wireless communications between a group of vehicle micro-clouds within a vehicle macro-cloud is described in accordance with some embodiments.

[0041] Figure 5 is a graphical representation illustrating an example structure of a vehicle macro cloud for bridging isolation, according to some embodiments.

[0042] Fig. 6A and Figure 6B is a graphical representation illustrating example DSRC data in accordance with some embodiments. DETAILED DESCRIPTION

[0043] Connected vehicles that are close to each other can form a vehicle micro-cloud and are referred to herein as "micro-cloud members" or "member vehicles". Connected vehicles collaborate to perform computing, data storage, sensing, communication tasks and any combination thereof among micro-cloud members through a V2X (e.g., V2V) network, including but not limited to the following: (1) collaboratively perform resource-intensive computing tasks among multiple member vehicles; (2) collaboratively maintain and update data content among multiple member vehicles; (3) collaboratively perform sensing of road conditions through on-board sensors of multiple member vehicles; and (4) collaboratively download data content from a cloud server (or edge server) or collaboratively upload data content to a cloud server (or edge server).

[0044] Using a vehicle micro cloud in a vehicle macro cloud eliminates the need for connected vehicles to access a remote cloud server or edge server through vehicle-to-network (V2N) communication (e.g., through a cellular network) whenever they need to access data (e.g., a high-definition road map for autonomous driving). Depending on the mobility of the vehicle micro cloud, as an example, the vehicle micro cloud can be divided into two types: a fixed vehicle micro cloud; and a mobile vehicle micro cloud.

[0045] A fixed vehicle micro-cloud can be bound to a certain geographic area (e.g., an intersection). When a vehicle enters a predefined geographic area of ​​a fixed vehicle micro-cloud, the vehicle joins the fixed vehicle micro-cloud, and when the vehicle leaves the predefined geographic area, the vehicle leaves the fixed vehicle micro-cloud. When leaving the predefined geographic area, the vehicle also transfers the ongoing tasks of the fixed vehicle micro-cloud to other member vehicles. In some embodiments, parked vehicles can also be members of a fixed vehicle micro-cloud.

[0046] In a mobile vehicle micro-cloud, a member leader (e.g., a connected vehicle that acts as a leader in a vehicle micro-cloud) can invite its neighboring vehicles to join the mobile vehicle micro-cloud. Unlike a fixed vehicle micro-cloud, a mobile vehicle micro-cloud moves with the movement of the member leader. The member leader recruits other member vehicles into the mobile vehicle micro-cloud and assigns subtasks to other member vehicles for collaborative task execution.

[0047] Multiple vehicle micro-clouds can be interconnected through a V2X (e.g., V2V) network to form a large-scale vehicle macro cloud. A vehicle can request data content and task execution from any vehicle micro-cloud (or any other vehicle) by accessing the vehicle micro-cloud (or, other vehicles) on the V2X (e.g., V2V) network. For example, the vehicle micro-cloud performs a task when requested by the vehicle and sends the task execution result back to the vehicle through the V2X (e.g., V2V) network. Moreover, the vehicle micro-cloud can also send the requested data back to the vehicle through the V2X (e.g., V2V) network, so that the vehicle retrieves the requested data from the vehicle micro-cloud. In this way, service discovery and provisioning can be performed for the vehicle macro cloud.

[0048] In existing solutions, the latency of data delivery through the V2V network in the vehicle macro cloud may be high, while the reliability of data delivery may be low. For example, if the content provider is far away from the requester vehicle, the data forwarded through the V2V network may result in high latency, or even fail due to packet loss. In addition, the risk of data loss in the vehicle micro cloud is high. For example, when the number of vehicles in the vehicle micro cloud decreases, the data content stored in the vehicle micro cloud may be lost.

[0049] Embodiments of a flat client are described herein that improve wireless communications between groups of vehicle micro-clouds via V2X communications. Examples of V2X communications described herein include, but are not limited to, one or more of: Dedicated Short Range Communications (DSRC) (including Basic Safety Messages (BSM) and Pedestrian Safety Messages (PSM), as well as other types of DSRC communications); Long Term Evolution (LTE); Millimeter Wave (mmWave) communications; 3G; 4G; 5G; LTE-V2X; LTE Vehicle-to-Vehicle (LTE-V2V); LTE Device-to-Device (LTE-D2D); LTE Voice (VoLTE), and the like. In some examples, V2X communications may include V2V communications, vehicle-to-infrastructure (V2I) communications, vehicle-to-network (V2N) communications, or any combination thereof.

[0050] Examples of V2X wireless messages described herein include, but are not limited to, the following messages: dedicated short range communication (DSRC) messages; basic safety message (BSM); long term evolution (LTE) messages; LTE-V2X messages (e.g., LTE vehicle-to-vehicle (LTE-V2V) messages, LTE vehicle-to-infrastructure (LTE-V2I) messages); 5G-LTE messages; and millimeter wave messages, among others.

[0051] Example Overview

[0052] refer to Figure 1A , depicts an example vehicle macro cloud 102, which may include one or more vehicle micro clouds 110. Each vehicle micro cloud 110 includes a CP node 112. For example, the vehicle macro cloud 102 includes a first vehicle micro cloud 110A, a second vehicle micro cloud 110B, ..., and an Mth vehicle micro cloud 110M, where M is a positive integer (M≥1). The first vehicle micro cloud 110A includes a CP node 112A, the second vehicle micro cloud 110B includes a CP node 112B, and the Mth vehicle micro cloud 110M includes a CP node 112M. The first vehicle micro cloud 110A, the second vehicle micro cloud 110B, and the Mth vehicle micro cloud 110M are collectively or individually referred to herein as "vehicle micro clouds 110". The first CP node 112A, the second CP node 112B, and the Mth CP node 112M are collectively or individually referred to herein as "CP nodes 112". These vehicle micro clouds 110 of the vehicle macro cloud 102 can be communicatively coupled to the network 105.

[0053] Although in Figure 1A Three vehicle micro clouds 110 and one network 105 are depicted in FIG. 1 , but in reality, the vehicle macro cloud 102 may include one or more vehicle micro clouds 110 and one or more networks 105 .

[0054] The network 105 may be of a conventional type, either wired or wireless, and may have many different configurations, including a star configuration, a token ring configuration, or other configurations. In addition, the network 105 may include a local area network (LAN), a wide area network (WAN) (e.g., the Internet), or other interconnected data paths across which multiple devices and / or entities can communicate. In some embodiments, the network 105 may include a peer-to-peer network. The network 105 may also be coupled to a telecommunications network or may include portions of a telecommunications network for transmitting data in a variety of different communication protocols. In some embodiments, the network 105 includes a plurality of communication protocols for transmitting and receiving data. Communication network or cellular communication network, including via short messaging service (SMS), multimedia messaging service (MMS), hypertext transfer protocol (HTTP), direct data connection, wireless application protocol (WAP), email, DSRC, full-duplex wireless communication, millimeter wave, WiFi (infrastructure mode), WiFi (ad hoc mode), visible light communication, TV white space communication and satellite communication. Network 105 can also include a mobile data network, which can include 3G, 4G, LTE, LTE-V2V, LTE-V2I; LTE-V2X, LTE-D2D, VoLTE, LTE-5G or any other mobile data network or combination of mobile data networks. In addition, network 105 can include one or more IEEE 802.11 wireless networks.

[0055] In some embodiments, the network 105 includes a V2X network (e.g., a V2X wireless network). The V2X network is a communication network that enables entities such as the vehicle micro cloud 110 (e.g., the CP node 112 and other members of the vehicle micro cloud) to communicate wirelessly with each other via one or more of the following: Wi-Fi; cellular communication, including 3G, 4G, LTE, 5G, etc.; dedicated short-range communication (DSRC); millimeter wave communication; etc.

[0056] refer to Figure 1B , depicts an example of a CP node 112 for a particular vehicle micro cloud 110. The CP node 112 may include a single connected vehicle 121 or multiple connected vehicles 121 within the vehicle micro cloud 110, which work in collaboration to provide the functionality of the CP node to the vehicle micro cloud 110. For example, Figure 1B As depicted, the CP node 112 includes a first networked vehicle 121A, ..., and an Nth networked vehicle 121N (which may be individually or collectively referred to herein as "networked vehicles 121"), where N is a positive integer (N ≥ 1). Figure 1B Two connected vehicles 121 are depicted in the figure, but in fact the CP node 112 can include any number of connected vehicles 121 in the vehicle micro cloud 110.

[0057] Each networked vehicle 121 is installed with a plane client 199. For example, the first networked vehicle 121A includes a plane client 199A, and the Nth networked vehicle 121N includes a plane client 199N. The plane client 199A and the plane client 199N may be individually or collectively referred to herein as "plane clients 199".

[0058] In some embodiments, the flat client 199 of the connected vehicle 121 includes software that, when executed by a processor of the connected vehicle 121, is operable to cause the processor to perform a reference Figure 1E and Figure 3-4C The process of processing 160 and one or more steps of methods 300 and 400.

[0059] In some embodiments, the plane client 199 may be implemented using hardware including a field programmable gate array ("FPGA") or an application specific integrated circuit ("ASIC"). In some other embodiments, a combination of hardware and software may be used to implement the plane client 199. The plane client 199 may be stored in a combination of devices (e.g., a vehicle or other device), or in one of the devices.

[0060] Reference below Figure 2-4C The flat client 199 is further described.

[0061] refer to Figure 1C , depicts an operating environment 130 for a flat client 199. In addition to Figure 1A and Figure 1B In addition to the elements shown in FIG. 1 , the operating environment 130 may additionally include a requester 141. The requester 141 may be installed with a flat client 199X (which is an example of the flat client 199 and may also be referred to as the flat client 199 for simplicity and convenience of description). These elements of the operating environment 130 may be communicatively coupled to the network 105.

[0062] As an example, the first vehicle micro-cloud 110A stores data content 131A, the second vehicle micro-cloud 110B stores data content 131B, and the Mth vehicle micro-cloud 110M stores data content 131M. Data content 131A, data content 131B, and data content 131M may share at least a subset of data content in common with each other, or may be completely different from each other. Data content 131A, data content 131B, and data content 131M may be individually or collectively referred to as "data content 131".

[0063] The data content 131 may include one or more data files stored by the corresponding vehicle micro cloud. For example, the data content 131 may include, but is not limited to, audio content files (e.g., podcasts, music, voice recordings, etc.), video content files (e.g., movies, videos, etc.), map data files (e.g., high-definition maps of one or more cities, states, or countries / regions), and any other type of data files.

[0064] In some embodiments, data content 131 may include popular data content. In some examples, the popularity of the piece of data content may be determined based on the number of requests intended to retrieve the piece of data content. If the number of requests for the piece of data content exceeds a threshold, the piece of data content is determined to be popular data content. Alternatively or additionally, the popularity of a piece of data content may be determined from web-based ratings or crowdsourcing. For example, the top 100 songs on a music download website may be popular data content. Other examples of popular data content are possible.

[0065] exist Figure 1C 1 shows an expanded diagram of a CP node 112 (e.g., CP node 112A, 112B, or 112M) of a vehicle micro cloud 110. The CP node 112 includes, for example, one or more networked vehicles 121 (e.g., a first networked vehicle 121A, ..., and an Nth networked vehicle 121N), a processor (in Figure 1C (not shown) and memory 127.

[0066] The memory 127 stores instructions or data that can be executed by the processor of the CP node 112. The instructions or data may include code for executing the techniques described herein. The memory 127 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory, or some other memory device. In some embodiments, the memory 127 also includes a non-volatile memory or similar permanent storage device and medium, including a hard drive, a floppy disk drive, a CD-ROM device, a DVD-ROM device, a DVD-RAM device, a DVD-RW device, a flash memory device, or some other large-capacity storage device for more permanent storage of information. The CP node 112 may include one or more memories 127.

[0067] The memory 127 may store one or more of the following elements: resource data 139 ; and data content 131 .

[0068] Resource data 139 includes one or more of the following elements: state data 133 ; state data structure 134 ; latency data 135 ; and packet data 137 .

[0069] The state data 133 of the CP node 112 in the vehicle micro cloud 110 includes digital data describing state information of the vehicle micro cloud 110. For example, the state data includes data describing one or more of the following elements: the geographical location of the vehicle micro cloud (e.g., a fixed location of the vehicle micro cloud, such as an intersection, or the location of a member leader in the vehicle micro cloud); a list of data files stored by the vehicle micro cloud and a content list of information described by each data file; one or more computing resources available on the vehicle micro cloud (e.g., computing power, memory, network bandwidth, etc.); one or more data transfer requests that the vehicle micro cloud needs to satisfy; one or more data replication requests that the vehicle micro cloud needs to satisfy; and one or more data recovery requests that the vehicle micro cloud needs to satisfy.

[0070] The state data structure 134 of the CP node 112 includes digital data describing the state data of other CP nodes 112. For example, the CP node 112 receives one or more sets of state data from one or more other CP nodes 112 through a state data exchange process and organizes the one or more sets of state data into one or more state data structures 134. In some embodiments, the one or more state data structures 134 also respectively include one or more distances between the CP node 112 and the one or more other CP nodes 112. The one or more distances may also be measured during the state data exchange process.

[0071] The latency data 135 includes digital data describing one or more latency values ​​between the CP node 112 of the vehicle micro cloud 110 and one or more other CP nodes 112 of one or more other vehicle micro clouds 110. For example, the latency data 135 includes: (1) a first latency for data transfer between the vehicle micro cloud 110 and a first other vehicle micro cloud 110; (2) a second latency for data transfer between the vehicle micro cloud 110 and a second other vehicle micro cloud 110; and (3) any other latency for data transfer between the vehicle micro cloud 110 and any other vehicle micro cloud 110.

[0072] The packet data 137 includes digital data describing the packet delivery rate (or packet loss rate) between the CP node 112 of the vehicle cloudlet 110 and one or more other CP nodes 112 of one or more other vehicle cloudlets 110. For example, the packet data 137 includes: (1) a first packet delivery rate between the vehicle cloudlet 110 and a first other vehicle cloudlet 110; (2) a second packet delivery rate between the vehicle cloudlet 110 and a second other vehicle cloudlet 110; and (3) any other packet delivery rate between the vehicle cloudlet 110 and any other vehicle cloudlet 110.

[0073] Data content 131 is described above, and similar descriptions will not be repeated here. In some embodiments, each micro-cloud member stores data content that can be requested by other members of the same vehicle micro-cloud 110 or members of other vehicle micro-clouds 110. Requester 141 is a networked vehicle that requests data content from a micro-cloud member. Requester 141 may or may not be a member of a vehicle micro-cloud. For example, requester 141 is a member vehicle of a specific vehicle micro-cloud 110 in a vehicle macro cloud. In another example, requester 141 is not a member vehicle of any vehicle micro-cloud 110 in a vehicle macro cloud.

[0074] In some embodiments, one or more of the connected vehicle 121 and the requestor 141 may be a DSRC-equipped vehicle. A DSRC-equipped vehicle is a vehicle that: (1) includes a DSRC radio; (2) includes a DSRC-compliant global positioning system (GPS) unit; and (3) is operable to legally send and receive DSRC messages in the jurisdiction in which the DSRC-equipped vehicle is located. A DSRC radio is hardware that includes a DSRC receiver and a DSRC transmitter. A DSRC radio is operable to wirelessly send and receive DSRC messages.

[0075] The DSRC-compliant GPS unit is operable to provide location information with lane-level accuracy to a vehicle (or some other DSRC-equipped device that includes the DSRC-compliant GPS unit). In some embodiments, the DSRC-compliant GPS unit is operable to identify, monitor, and track its two-dimensional location within 1.5 meters of its actual location 68% of the time in the clear sky.

[0076] A conventional GPS unit provides location information describing the location of the conventional GPS unit with an accuracy of plus or minus 10 meters of the actual location of the conventional GPS unit. In contrast, a DSRC-compliant GPS unit provides GPS data describing the location of the DSRC-compliant GPS unit with an accuracy of plus or minus 1.5 meters of the actual location of the DSRC-compliant GPS unit. This degree of accuracy is referred to as "lane-level accuracy" because, for example, a lane on a road is generally about 3 meters wide, and an accuracy of plus or minus 1.5 meters is sufficient to identify which lane a vehicle is traveling in on the road. Some safety or autonomous driving applications provided by advanced driver assistance systems (ADAS) in modern vehicles require positioning information that describes the geographic location of the vehicle with lane-level accuracy. In addition, current standards for DSRC require that the geographic location of the vehicle be described with lane-level accuracy.

[0077] As used herein, the terms "geographic location," "location," "geographic location," and "position" refer to the latitude and longitude of an object, such as the networked vehicle 121. The example embodiments described herein provide positioning information that describes the geographic location of the vehicle with an accuracy of at least plus or minus 1.5 meters relative to the actual geographic location of the vehicle. Thus, the example embodiments described herein are able to describe the geographic location of the vehicle with lane-level accuracy or better.

[0078] The networked vehicle 121 and the requestor 141 may include the same or similar elements. The networked vehicle 121 and the requestor 141 may share a connection or association. For example, the networked vehicle 121 and the requestor 141 each include a communication unit, such that these vehicles are "networked vehicles", wherein the communication unit includes any hardware and software required to enable the corresponding vehicle to communicate with other entities of the operating environment 130 via the network 105.

[0079] The connected vehicle 121 and the requester 141 may be any type of vehicle. The connected vehicle 121 and the requester 141 may be the same type of vehicle relative to each other or different types of vehicles relative to each other. For example, the connected vehicle 121 or the requester 141 may include one of the following types of vehicles: a car; a truck; a sports vehicle; a bus; a semi-truck; a drone or any other road-based vehicle.

[0080] In some embodiments, one or more of the connected vehicle 121 and the requester 141 may include an autonomous vehicle or a semi-autonomous vehicle. For example, one or more of the connected vehicle 121 and the requester 141 may include one or more ADAS systems. One or more ADAS systems may provide some or all of the functions that provide autonomous functionality.

[0081] refer to Figure 1D , another operating environment 150 for a plane client 199 is shown according to some embodiments. In some scenarios, V2X communication between vehicle cloudlets 110 can be divided into a control plane 151 and a data plane 153.

[0082] The control plane 151 is used to handle control-type distributed V2X communications between the vehicle micro-clouds 110 of the vehicle macro cloud 102 and between the member vehicles of the vehicle micro-clouds 110. For example, the CP nodes 112 of the vehicle micro-clouds 110 may communicate with each other on the control plane 151 to coordinate how to forward data content between the vehicle micro-clouds 110. In another example, the CP nodes 112 of the vehicle micro-clouds 110 may communicate with each other on the control plane 151 to decide how to forward data content between the vehicle micro-clouds 110 on the data plane 153, wherein the decision includes, but is not limited to: a target content provider for providing data content; a request forwarding path for forwarding a data request to a target content provider; and a data forwarding path for forwarding data content from a target content provider to a requester, and the like.

[0083] The data plane 153 is used to handle distributed V2X communication of a data transfer type between the vehicle micro cloud 110 of the vehicle macro cloud 102 and the member vehicles of the vehicle micro cloud 110. For example, after a decision is made on the control plane 151, data content can be forwarded between the CP nodes 112 of the vehicle micro cloud 110 on the data plane 153. In another example, the data request can be forwarded to the target content provider through the control plane 151 as a control message according to the request forwarding path determined on the control plane 151, and the data content can be forwarded to the requester through the data plane 153 as a data message according to the data forwarding path determined on the control plane 151.

[0084] Example functions provided by the data plane 153 include forwarding data content through a V2X network (e.g., a V2V network) based on a decision made by the control plane 151. For example, the CP node 112 of the vehicle cloudlet 110 instructs one or more cloudlet members of the vehicle cloudlet 110 to send the data content to the location of the destination vehicle cloudlet 110. The data content is forwarded on the V2X network (e.g., a multi-hop V2V network) via a geo-broadcast routing protocol.

[0085] Both the control plane 151 and the data plane 153 may be deployed in a V2X network. For example, both the control plane 151 and the data plane 153 may be deployed in a V2V network. Optionally, the control plane 151 may also be enabled via vehicle-to-network (V2N) communication (e.g., a cellular network).

[0086] Turning again to the control plane 151, in some embodiments, the control plane 151 is used to efficiently transfer data content between the vehicle micro-clouds 110. For example, the vehicle micro-clouds 110 (or the CP nodes 112 of the vehicle micro-clouds 110) that constitute the vehicle macro cloud 102 exchange their states (e.g., state data) with each other on the control plane 151. The state data of the vehicle micro-clouds 110 is used to make intelligent decisions on how to forward data content between the vehicle micro-clouds 110. The vehicle micro-clouds 110 (or the CP nodes 112 of the vehicle micro-clouds 110) perform coordination with each other on the control plane 151 to facilitate efficient transfer of data content between them.

[0087] Example functions provided by the control plane 151 include, but are not limited to: forwarding data requests to a target content provider; intelligently selecting a target content provider in response to receiving a data request from a requester; performing data pre-fetching from other vehicle micro-clouds 110; performing data replication between vehicle micro-clouds 110; and performing collaborative data recovery between vehicle micro-clouds 110, etc.

[0088] For example, based on the state data exchanged on the control plane 151, the CP node 112 of the vehicle micro cloud 110 that receives the data request from the requester can identify the target content provider (e.g., the most suitable vehicle micro cloud). The CP node 112 of the vehicle micro cloud 110 requests the data content for the requester from the target content provider. In this way, the response time of the data request can be reduced. Figure 1E The selection of a target content provider is further described.

[0089] For example, with respect to performing data pre-fetching, the CP node 112 of the vehicle micro-cloud 110 pre-fetches popular data content (e.g., the latest version of popular data content) from one or more other vehicle micro-clouds 110 before receiving a data request, and stores the popular data content on the memory of the vehicle micro-cloud 110. In this way, when a data request for any popular data content is received from a requester, the CP node 112 of the vehicle micro-cloud 110 can directly respond to the data request by sending the requested popular data content to the requester. In this way, since the CP node 112 of the vehicle micro-cloud 110 itself is the most suitable content provider for the requested popular data content, there is no need to select another target content provider. Therefore, the response time to the data request is reduced.

[0090] For example, with respect to performing data replication between vehicle micro-clouds, when the number of vehicles in a vehicle micro-cloud 110 drops below a certain threshold, the CP node 112 of the vehicle micro-cloud 110 can replicate its data content to a nearby vehicle micro-cloud 110 as a backup. In this way, the availability of data content is improved.

[0091] For example, regarding performing cooperative data recovery between vehicle micro clouds 110, when a piece of data content is lost from the vehicle micro cloud 110, the CP node 112 of the vehicle micro cloud 110 obtains the piece of data content from a nearby vehicle micro cloud to recover it. In this way, the availability of data content is improved.

[0092] Each vehicle micro cloud 110 corresponds to a node (referred to as a CP node 112) on the control plane 151. The CP node 112 may be a virtual entity whose functionality is provided by a member leader of the vehicle micro cloud 110 or by multiple member vehicles in a collaborative manner. For example, a single member vehicle of the vehicle micro cloud 110 may act as a CP node 112 of the vehicle micro cloud 110. Alternatively, multiple member vehicles of the vehicle micro cloud 110 that work collaboratively to provide the functionality of the CP node 112 may collaboratively act as a CP node 112.

[0093] In some embodiments, the CP node 112 maintains a list of data content maintained in the vehicle micro-cloud 110 and the amount of computing resources available in the vehicle micro-cloud 110. The CP node 112 periodically generates state data describing the state of the vehicle micro-cloud 110, wherein the state data includes one or more of the following: the geographic location of the vehicle micro-cloud 110; a list of data content stored by the vehicle micro-cloud 110; the amount of computing resources available on the vehicle micro-cloud 110; one or more data transfer requests that the vehicle micro-cloud 110 needs to satisfy; one or more data replication requests that the vehicle micro-cloud 110 needs to satisfy; and one or more data recovery requests that the vehicle micro-cloud 110 needs to satisfy, etc.

[0094] The CP node 112 periodically exchanges status data with other CP nodes 112 of other vehicle micro-clouds 110. In response to the control plane 151 being deployed in a V2X network (e.g., a V2V network), the CP node 112 also measures the latency and packet delivery rate of V2X communication (e.g., V2V communication) with other CP nodes 112 when exchanging status data.

[0095] exist Figure 1D In the depicted example, three vehicle micro clouds 110A, 110B, and 110C having CP nodes 112A, 112B, and 112C, respectively, are illustrated in the vehicle macro cloud 102. Each of the vehicle micro clouds 110A, 110B, and 110C includes a plurality of member vehicles.

[0096] At the level of the data plane 153, data content is forwarded between different vehicle cloudlets. For example, data B is transmitted between vehicle cloudlet 110B and vehicle cloudlet 110C, so that both vehicle cloudlet 110B and vehicle cloudlet 110C store copies of data B in their corresponding CP nodes 112B and 112C, respectively. In another example, data D is forwarded to vehicle cloudlet 110A via vehicle cloudlet 110B, so that vehicle cloudlet 110A stores a copy of data D in its corresponding CP node 112A.

[0097] At the level of the control plane 151, state data is exchanged between different CP nodes such as CP nodes 112A, 112B, and 112C. CP node 112A includes a content list of vehicle cloudlet 110A, which includes data A and data D. CP node 112B includes a content list of vehicle cloudlet 110B, which includes data B and data E. CP node 112C includes a content list of vehicle cloudlet 110C, which includes data A, data B, and data C.

[0098] refer to Figure 1E , shows an example flow process 160 for a data request according to some embodiments. When a requester 141 needs a piece of data content, it can send a data request to a nearby vehicle micro cloud. Here, it is assumed that the nearby vehicle micro cloud is the vehicle micro cloud 110B. At the level of the control plane 151, the CP node 112B of the vehicle micro cloud 110B determines whether the piece of data content is available on the vehicle micro cloud 110B.

[0099] In response to the piece of data content being available on the vehicle micro-cloud 110B (e.g., the piece of data content is in the content list of the vehicle micro-cloud 110B), the CP node 112B constructs a V2X wireless message including the piece of data content, and sends the V2X wireless message to the requester 141 via the V2X network. For example, assume that the piece of data content requested by the requester 141 is data E. In this case, the CP node 112B directly responds to the requester 141 by sending a V2X wireless message including data E to the requester 141 via the V2X network.

[0100] If the piece of data content is not available on the vehicle micro-cloud 110B (e.g., the piece of data content is not in the content list of the vehicle micro-cloud 110B), the CP node 112B retrieves one or more of the following from its resource data: one or more state data structures describing one or more states of one or more other vehicle micro-clouds; latency data; and packet data. The CP node 112B determines the target content provider based on one or more of the following: one or more state data structures; latency data; and packet data.

[0101] In some embodiments, the target content provider is a CP node 112 of another vehicle micro-cloud 110, which stores the piece of data content in the storage device of the other vehicle micro-cloud 110. In some embodiments, the target content provider can be determined based on one or more of the following: (1) the distance to each candidate vehicle micro-cloud (the smaller the distance, the better); (2) the average V2X (e.g., V2V) communication latency to each candidate vehicle micro-cloud (the smaller the latency, the better); (3) the packet delivery rate to or from each candidate vehicle micro-cloud (the higher the packet delivery rate, the better); and (4) any combination thereof. In this example, the candidate vehicle micro-cloud is another vehicle micro-cloud that can be a candidate for the target content provider.

[0102] Here, in Figure 1E In the embodiment, the CP node 112A of the vehicle micro cloud 110A is determined as the target content provider, wherein the CP node 112A satisfies one or more of the following: (1) the CP node 112A stores a copy of the requested data content; (2) compared with one or more other CP nodes 112 in one or more other vehicle micro clouds 110 in the vehicle macro cloud, the CP node 112A has the shortest distance to the CP node 112B; (3) compared with one or more other CP nodes 112, the CP node 112A has the shortest waiting time to the CP node 112B; (4) compared with one or more other CP nodes 112, the CP node 112A has the highest packet delivery rate to the CP node 112B; and (5) any combination thereof.

[0103] At the level of the control plane 151, the CP node 112B determines a request forwarding path for forwarding the data request to the target content provider, and forwards the data request to the target content provider (e.g., the CP node 112A) according to the request forwarding path. For example, the request forwarding path may be a path with the least number of hops on the V2X network, a path with the least latency on the V2X network, a path with the shortest distance on the V2X network, or a path with the highest packet delivery rate. Other examples of request forwarding paths are possible.

[0104] In some embodiments, at the level of the control plane 151, the CP node 112B also determines a data forwarding path for a target content provider (e.g., the CP node 112A) to forward the piece of data content to the requester 141. The data forwarding path may be a path for forwarding the piece of data content to the vehicle micro-cloud 110, from which the requester 141 prefers to receive the piece of data content. For example, the data forwarding path may be a path with the fewest hops on the V2X network, a path with the least latency on the V2X network, a path with the shortest distance on the V2X network, or a path with the highest packet delivery rate. Other examples of data forwarding paths are possible. The data forwarding path may be the same as, overlapping with, or completely different from the request forwarding path.

[0105] Alternatively, at the level of control plane 151, the data forwarding path may be determined by the target content provider itself (eg, CP node 112A).

[0106] Next, at the level of the control plane 151, the CP node 112B forwards the data request to the CP node 112A. In response to receiving the data request, the CP node 112A determines that the data content is available on the vehicle micro cloud 110A, and generates a V2X wireless message including the data content. At the level of the data plane 153, the CP node 112A forwards the V2X wireless message to the requester 141 along the data forwarding path. Figure 1E , assuming that the requested data content is data D, and the CP node 112A forwards the data D to the requester 141 via the vehicle micro cloud 110B along the data forwarding path 162 .

[0107] Example Computer System

[0108] Reference now Figure 2 , depicts a block diagram illustrating an example computer system 200 including a flat client 199 according to some embodiments. In some embodiments, the computer system 200 may include a special-purpose computer system that is programmed to perform the following reference Figure 3-4C One or more steps of methods 300 and 400 are described.

[0109] To simplify and facilitate the description Figure 2 , assuming that: the vehicle macro cloud 102 includes a plurality of vehicle micro clouds 110; and Figure 2 The plane client 199 is installed in the first CP node 112 of the first vehicle micro cloud 110 within the vehicle macro cloud 102 .

[0110] In some embodiments, the first CP node 112 includes at least a networked vehicle 121. The computer system 200 is an onboard computer of the networked vehicle 121. In some embodiments, the computer system 200 is an onboard unit of the networked vehicle 121. In some embodiments, the computer system 200 is an electronic control unit (ECU), a head unit, or some other processor-based computing device of the networked vehicle 121.

[0111] According to some examples, computer system 200 may include one or more of the following elements: plane client 199; processor 225; memory 127; communication unit 245; GPS unit 238; and storage 241. The components of computer system 200 are communicatively coupled via bus 220.

[0112] In the illustrated embodiment, processor 225 is communicatively coupled to bus 220 via signal line 237. Communication unit 245 is communicatively coupled to bus 220 via signal line 246. GPS unit 238 is communicatively coupled to bus 220 via signal line 230. Storage device 241 is communicatively coupled to bus 220 via signal line 242. Memory 127 is communicatively coupled to bus 220 via signal line 244.

[0113] Reference above Figure 1C The memory 127 is described above, and therefore, similar description will not be repeated here. The memory 127 can store the above reference Figures 1A-1E Memory 127 may store any data required by computer system 200 to provide its functionality.

[0114] Processor 225 includes an arithmetic logic unit, a microprocessor, a general purpose controller, or some other processor array to perform calculations and provide electronic display signals to a display device. Processor 225 processes data signals and may include a variety of computing architectures, including a complex instruction set computer (CISC) architecture, a reduced instruction set computer (RISC) architecture, or an architecture that implements a combination of instruction sets. Computer system 200 may include one or more processors 225. Other processors, operating systems, sensors, displays, and physical configurations are possible.

[0115] The communication unit 245 transmits and receives data to and from the network 105 or another communication channel. In some embodiments, the communication unit 245 may include a DSRC transceiver, a DSRC receiver, and other hardware or software necessary to make the networked vehicle 121 a DSRC-enabled device. For example, the communication unit 245 includes a DSRC antenna configured to broadcast DSRC messages via the network. The DSRC antenna may also transmit BSM messages at fixed intervals that are user-configurable (e.g., every 0.1 seconds, at time intervals corresponding to a frequency range from 1.6 Hz to 10 Hz, etc.).

[0116] In some embodiments, the communication unit 245 includes a port for direct physical connection to the network 105 or another communication channel. For example, the communication unit 245 includes a USB, SD, CAT-5, or similar port for wired communication with the network 105. In some embodiments, the communication unit 245 includes a wireless transceiver for exchanging data with the network 105 or other communication channel using one or more wireless communication methods, including: IEEE 802.11; IEEE 802.16, EN ISO 14906:2004 Electronic toll collection - Application interface EN 11253:2004 Dedicated short range communication - Physical layer using 5.8 GHz microwaves (review); EN 12795:2002 Dedicated short range communication (DSRC) - DSRC data link layer: media access and logical link control (review); EN 12834:2002 Dedicated short range communication - Application layer (review); EN 13372:2004 Dedicated short range communication (DSRC) - DSRC profile for RTTT applications (review); the communication method described in U.S. patent application 14 / 471,387, entitled "Full-Duplex Coordination System" filed on August 28, 2014; or other suitable wireless communication methods.

[0117] In some embodiments, the communication unit 245 includes a cellular communication transceiver for sending and receiving data over a cellular communication network, including via short messaging service (SMS), multimedia messaging service (MMS), hypertext transfer protocol (HTTP), direct data connection, WAP, email, or other suitable types of electronic communication. In some embodiments, the communication unit 245 includes a wired port and a wireless transceiver. The communication unit 245 also provides other conventional connections to the network 105 to distribute files or media objects using standard network protocols including TCP / IP, HTTP, HTTPS, and SMTP, millimeter wave, DSRC, etc.

[0118] In some embodiments, the GPS unit 238 is a conventional GPS unit of the connected vehicle 121. For example, the GPS unit 238 may include hardware for wirelessly communicating with GPS satellites to retrieve data describing the geographic location of the connected vehicle 121. For example, the GPS unit 238 acquires GPS data from one or more GPS satellites. In some embodiments, the GPS unit 238 is a DSRC-compliant GPS unit of the connected vehicle 121 that is operable to provide GPS data describing the geographic location of the connected vehicle 121 with lane-level accuracy.

[0119] The storage device 241 may be a non-transitory storage medium that stores data for providing the functionality described herein. The storage device 241 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory, or some other memory device. In some embodiments, the storage device 241 also includes a non-volatile memory or similar permanent storage device and medium, including a hard drive, a floppy disk drive, a CD-ROM device, a DVD-ROM device, a DVD-RAM device, a DVD-RW device, a flash memory device, or some other mass storage device for more permanent storage of information.

[0120] exist Figure 2 In the illustrated embodiment shown, the plane client 199 includes: a communication module 202; a plane establishment module 204; a state module 206; a request processing module 208; a machine learning module 210; and an operation module 212. These components of the plane client 199 are communicatively coupled to each other via a bus 220. In some embodiments, the components of the plane client 199 can be stored in a single device. In some other embodiments, the components of the plane client 199 can be distributed and stored across multiple devices. For example, some components of the plane client 199 can be distributed across the requester 141 and the networked vehicle 121.

[0121] The communication module 202 may be software including routines for handling communications between the plane client 199 and other components of the computer system 200. In some embodiments, the communication module 202 may be stored in the memory 127 of the computer system 200 and may be accessed and executed by the processor 225. The communication module 202 may be adapted to cooperate and communicate with the processor 225 and other components of the computer system 200 via the signal line 222.

[0122] The communication module 202 sends data to and receives data from one or more elements of the operating environment 130 or 150 via the communication unit 245. For example, the communication module 202 receives or transmits one or more of the following elements via the communication unit 245: status data; one or more data requests; and data content. The communication module 202 may send or receive the above-referenced information via the communication unit 245. Figures 1A-1E Describes any data or message.

[0123] In some embodiments, the communication module 202 receives data from components of the plane client 199 and stores the data in one or more of the storage device 241 and the memory 127. For example, the communication module 202 receives the data described above with reference to the memory 127 from the communication unit 245 (via the network 105, DSRC messages, BSM, DSRC probe messages, full-duplex wireless messages, etc.) and stores the data in the memory 127 (or temporarily in the storage device 241, which can act as a buffer for the computer system 200).

[0124] In some embodiments, the communication module 202 can handle communications between components of the plane client 199. For example, the communication module 202 can handle communications between the plane establishment module 204, the state module 206, the request processing module 208, the machine learning module 210, and the operation module 212. Any of these modules can enable the communication module 202 to communicate with other elements of the computer system 200 or the operating environment 130 or 150 (via the communication unit 245).

[0125] The plane establishment module 204 may be software including routines for establishing one or more of a control plane and a data plane between the vehicle micro-clouds 110 within the vehicle macro-cloud 102. In some embodiments, the plane establishment module 204 may be stored in the memory 127 of the computer system 200 and may be accessed and executed by the processor 225. The plane establishment module 204 may be adapted to cooperate and communicate with the processor 225 and other components of the computer system 200 via the signal line 224.

[0126] In some embodiments, the plane establishment module 204 of the plane client 199 (which is installed in the first CP node 112 of the first vehicle micro cloud 110) is operable to cooperate with one or more other CP nodes 112 of one or more other vehicle micro clouds 110 to establish a control plane and a data plane for the vehicle macro cloud 102. For example, the control plane is a distributed control plane and includes at least the first CP node 112 of the first vehicle micro cloud 110 and one or more other CP nodes 112 of one or more other vehicle micro clouds 110. Figure 1D-1EThe control plane and the data plane are described, and similar descriptions are not repeated here.

[0127] The state module 206 may be software including routines that, when executed by the processor 225, cause the processor 225 to generate state data and resource data of the first CP node 112 of the first vehicle micro-cloud 110. In some embodiments, the state module 206 may be an instruction group stored in the memory 127 of the computer system 200 and may be accessed and executed by the processor 225. The state module 206 may be adapted to cooperate and communicate with the processor 225 and other components of the computer system 200 via signal lines 249.

[0128] In some embodiments, the state module 206 is operable to generate first state data describing the state of the first vehicle micro cloud 110. The state module 206 applies the control plane to perform state data exchange in the vehicle macro cloud 102, including: sending the first state data to one or more other CP nodes 112 of one or more other vehicle micro clouds 110; receiving one or more groups of state data describing one or more states of one or more other vehicle micro clouds 110 from the one or more other CP nodes 112, respectively.

[0129] For example, the first state data includes data describing one or more of the following: the geographic location of the first vehicle micro cloud 110; a content list describing a list of data files stored by the first vehicle micro cloud 110 and the information described by each data file; one or more computing resources available on the first vehicle micro cloud 110; one or more data transfer requests that the first vehicle micro cloud 110 needs to satisfy; one or more data replication requests that the first vehicle micro cloud 110 needs to satisfy; and one or more data recovery requests that the first vehicle micro cloud 110 needs to satisfy.

[0130] Each set of status data in one or more sets of other status data may include digital data similar to the first status data, and similar descriptions are not repeated here.

[0131] The state module 206 periodically cooperates with one or more other CP nodes 112 to exchange state data with one or more other CP nodes 112 of the vehicle macro cloud 102. The control plane is used for the exchange of such state data. DSRC messages such as basic safety messages (BSM messages) can be used to distribute state data between various CP nodes 112. There is no existing solution to share similar state data between vehicle micro clouds, let alone use, for example, a control plane independent of the data plane to share such state data between vehicle micro clouds.

[0132] When performing the status data exchange process, the status module 206 measures network data, including: (1) latency data describing one or more latency values ​​for data transfer between the first CP node 112 and one or more other CP nodes 112; and (2) packet data describing one or more packet transfer rates between the first CP node 112 and one or more other CP nodes 112.

[0133] Then, after performing the state data exchange process, the state module 206 constructs one or more state data structures that include (and organize) one or more sets of state data received from one or more other CP nodes 112, respectively.

[0134] The state module 206 generates resource data for the first vehicle micro-cloud 110 , which includes one or more of the following: first state data of the first vehicle micro-cloud 110 ; one or more state data structures related to one or more other vehicle micro-clouds 110 ; and network data including latency data and packet data.

[0135] For example, if V2X (e.g., V2V) communication is used for the status data exchange process, then while performing the status data exchange process, the status module 206 measures: (a) latency (i.e., "latency data") and (b) packet delivery rate (i.e., "packet data"). The first CP node 112 then potentially includes the following digital data, collectively referred to as "resource data": (1) its own first status data; (2) one or more status data structures including status data of one or more other CP nodes 112; (3) latency data measured when exchanging status data; and (4) packet data measured when exchanging status data.

[0136] The request processing module 208 may be software including routines that, when executed by the processor 225, cause the processor 225 to process a data request and generate result data describing the result of the processing associated with the data request. In some embodiments, the request processing module 208 may be a set of instructions stored in the memory 127 of the computer system 200 and may be accessed and executed by the processor 225. The request processing module 208 may be adapted to cooperate and communicate with the processor 225 and other components of the computer system 200 via signal lines 228.

[0137] In some embodiments, the request processing module 208 is operable to: receive a data request from a requester via a V2X network; and analyze the data request using a control plane to select a target content provider for providing the data content requested by the data request. For example, the request processing module 208 retrieves a content list from the first state data of the first vehicle micro-cloud 110, and determines whether the data content requested by the data request is stored by the first vehicle micro-cloud 110 based on the content list.

[0138] If the data content is stored by the first vehicle micro-cloud 110, the request processing module 208 of the first CP node 112 answers the data request with a V2X wireless message including the requested data content as its payload. The request processing module 208 sends the V2X wireless message to the requester via the communication unit 245. In this case, the first CP node 112 of the first vehicle micro-cloud 110 is the target content provider.

[0139] In response to the data content requested by the data request not being stored by the first vehicle micro-cloud 110, the request processing module 208 analyzes the resource data of the first vehicle micro-cloud 110 to determine a target content provider for providing the requested data content. In some embodiments, the request processing module 208 also analyzes the resource data of the first vehicle micro-cloud 110 to determine one or more of the following: (1) a request forwarding path for forwarding the data request to the target content provider; and (2) a data forwarding path for forwarding the data content from the target content provider to the requester. Figure 1D-1E The determination of the target content provider, the request forwarding path, and the data forwarding path is described, and similar descriptions are not repeated here.

[0140] Next, the request processing module 208 uses the data plane to process the data request. For example, the request processing module 208 uses the data plane to process the data request based on the decision made by the control plane. Specifically, the request processing module 208 uses the control plane to forward the data request received from the requester as a control message to the target content provider via the V2X network (for example, the request processing module 208 forwards the data request to the target content provider according to the request path determined at the level of the control plane). Upon receiving the data request, the target content provider uses the data plane to provide the data content to the first CP node 112. Therefore, the request processing module 208 of the first CP node 112 uses the data plane to receive the data content from the target content provider, and forwards the data content to the requester via the V2X network (for example, the target content provider provides the content to the requester according to the data forwarding path, wherein the data forwarding path includes the first CP node 112 where the requester can retrieve the data content as a relay node).

[0141] The request processing module 208 is operable to generate result data describing the processing result of the data request. For example, the processing result indicates that the data content requested by the data request is stored by the first vehicle micro-cloud 110, so there is no need to retrieve the data content from other vehicle micro-clouds 110. In another example, the processing result indicates that the data content requested by the data request is not stored by the first vehicle micro-cloud 110, so the data content is retrieved from another vehicle micro-cloud 110. In some embodiments, the processing result may also include one or more of the following elements: response time to complete the data request; request forwarding path; data forwarding path; number of hops along the request forwarding path; and number of hops along the data forwarding path, etc.

[0142] The machine learning module 210 may be software including routines that, when executed by the processor 225, cause the processor 225 to generate feedback data, analyze the feedback data, and modify the operation of the first CP node 112 based on the analysis results of the feedback data. In some embodiments, the machine learning module 210 may be an instruction group stored in the memory 127 of the computer system 200 and may be accessed and executed by the processor 225. The machine learning module 210 may be adapted to cooperate and communicate with the processor 225 and other components of the computer system 200 via the signal line 250.

[0143] In some embodiments, the machine learning module 210 generates feedback data that includes: (1) result data describing the processing results of the data request; (2) control plane data associated with the control plane; or (3) a combination thereof. In some embodiments, the control plane data may include any digital data associated with the control plane and is incorporated into the feedback data. For example, the control plane data includes one or more content lists of one or more vehicle micro clouds. In another example, the control plane data includes data describing a state data exchange process during which state data is exchanged on the control plane (e.g., the duration required to complete the state data exchange process across a specific portion of the vehicle macro cloud 102 or the entire vehicle macro cloud 102). As described below, the feedback data can be used to train the machine learning module 210.

[0144] In some embodiments, the CP nodes 112 of different vehicle micro clouds 110 can exchange their respective feedback data with each other on the control plane, so that the efficiency of data management in the vehicle macro cloud 102 can be further improved. In this case, each individual CP node 112 can use not only its own feedback data but also other feedback data received from other CP nodes 112 to train its respective machine learning module 212, which can improve the training efficiency and the performance of the machine learning module 212 because various feedback data can be used in the training process.

[0145] In some embodiments, the machine learning module 210 is operable to modify the operation of the first CP node 112 based on the feedback data so as to achieve a reduction in one or more of latency of data delivery and data packet loss for data requests processed by the first CP node 112. As more feedback data is generated over time, such reduction in latency of data delivery, data packet loss, or a combination thereof may be improved.

[0146] In some embodiments, the machine learning module 210 modifies the operation of the first CP node 112 based on the feedback data by at least: analyzing the feedback data to determine one or more types of popular data content; and modifying the operation of the communication unit 245 of the first CP node 112 so that the communication unit 245 pre-fetches and stores the one or more types of popular data content on the first CP node 112. For example, the machine learning module 210 monitors the frequency of requesting specific data content (for example, the machine learning module 210 counts the number of data requests for specific data content and determines the popularity of the specific data content based on the number of data requests). In this way, the machine learning module 210 monitors the popularity of different data content and pre-fetches the most popular data content (for example, the data content with the highest request frequency). In this case, in response to receiving a data request for any one of the one or more types of popular data content, the first CP node 112 can directly respond to the data request without forwarding the data request to other vehicle micro-clouds, thereby improving the waiting time for data delivery and the reduction of data packet loss for the data request compared to the scenario of forwarding the data request to other vehicle micro-clouds to obtain the data content.

[0147] In some embodiments, the machine learning module 210 modifies the operation of the first CP node 112 based on the feedback data by at least the following: modifying the operation of the communication unit 245 of the first CP node 112 so that the communication unit 245 caches the data content on the first CP node 112 based on the feedback data. For example, in response to feedback data indicating that the number of data requests for a piece of data content exceeds a threshold, the machine learning module 210 instructs the communication unit 245 to cache the piece of data content on the first CP node 112. In this case, in response to receiving an additional data request for the piece of data content, the first CP node 112 can directly respond to the data request without forwarding the data request to other vehicle micro-clouds, thereby improving the latency of data delivery and the reduction of data packet loss for data requests compared to the scenario of forwarding the data request to other vehicle micro-clouds to obtain the piece of data content.

[0148] In some examples, the modification of the operation of the communication unit 245 includes one or more of the following: modification of the number of active V2X channels to be operated (e.g., modification of the number of active V2X transceivers or the number of active V2X radio transceiver devices to be operated); modification of the operating frequency of the active V2X channels; modification of the beamforming technology applied to the V2X antenna; and modification of the bandwidth allocation of the communication unit 245, etc. For example, in response to the amount of popular data content to be pre-fetched from other vehicle micro-clouds 110 exceeding a threshold, the machine learning module 210 may perform one or more of the following operations: increase the number of active V2X channels so that more V2X channels can be used to pre-fetch popular data content at the same time; change the beamforming technology applied to the V2X antenna so that the popular data content can be received at a higher signal-to-noise ratio at the communication unit 245; and allocate more bandwidth to the communication unit 245 so that the popular data content can be retrieved at a faster speed, etc.

[0149] In some embodiments, the machine learning module 210 uses one or more machine learning techniques (e.g., deep learning techniques, neural networks, etc.) to analyze the feedback data.

[0150] In some embodiments, the machine learning module 210 uses a learning algorithm to construct the feedback data into a learning database, so that as the learning database stores more and more feedback data instances ("more and more feedback data" herein), the latency and packet loss rate of data transmission on the V2X network can be reduced. For example, the machine learning module 210 can construct items of the learning database to include data requests, response times for completing data requests, requested data content, and feedback data, etc. As more and more feedback data is received, more and more items of the learning database can be constructed. The items in the learning database can then be used as training data to train one or more machine learning techniques for analyzing feedback data.

[0151] In some embodiments, the machine learning module 210 utilizes a learning algorithm and provides feedback data as input to the learning algorithm. As time goes by, more and more feedback data is received, and the learning algorithm recursively analyzes the feedback data based on the received feedback data and improves the operation of the first CP node 112 over time. For example, the machine learning module 210 of the first CP node 112 predicts which data content needs to be pre-fetched based on the analysis of the feedback data by the learning algorithm, and modifies the operation of the communication unit 245 (e.g., the V2X antenna of the communication unit 245) so that the predicted data content is pre-fetched. In this case, the operation of the first CP node 112 and the communication unit 245 (e.g., the V2X antenna) is improved.

[0152] In some embodiments, based on the feedback data, the machine learning module 210 changes the resource allocation scheme (e.g., computing power allocation scheme, memory allocation scheme, or bandwidth allocation scheme, etc.) of the first CP node 112 so that resources (e.g., computing power, memory space, bandwidth, etc.) for performing data prefetching and data caching can be allocated. For example, memory space for storing unpopular data content can be released, and new memory space for storing popular data content can be allocated. Regarding network bandwidth allocation, in response to an instruction to prefetch some data content, the machine learning module 210 monitors the load of the V2X network and modifies the operation of the communication unit 245 to prefetch data content when bandwidth on the V2X network is available. If the load of the V2X network exceeds a threshold, the machine learning module 210 modifies the operation of the communication unit 245 so that less bandwidth is allocated for data prefetching.

[0153] The operation module 212 may be software including routines that, when executed by the processor 225, cause the processor 225 to perform data operations on the first CP node 112. In some embodiments, the operation module 212 may be an instruction group stored in the memory 127 of the computer system 200 and may be accessed and executed by the processor 225. The operation module 212 may be adapted to cooperate and communicate with the processor 225 and other components of the computer system 200 via the signal line 251.

[0154] In some embodiments, the operation module 212 is operable to monitor a data replication trigger event in the first vehicle micro cloud 110. In response to the occurrence of the data replication trigger event, the operation module 212 replicates the data of the first vehicle micro cloud 110 to another vehicle micro cloud 110 in the vehicle macro cloud 102. For example, the data replication trigger event includes one or more of the following: the number of vehicles in the first vehicle micro cloud 110 is lower than a first threshold; and the amount of data storage resources available in the first vehicle micro cloud 110 is lower than a second threshold.

[0155] For example, when the amount of data storage resources available in the first vehicle micro-cloud 110 is expected to drop below a predefined threshold within a short period of time (e.g., in the next 30 minutes, 1 hour, etc.), and a piece of data content is only cached by a limited number of vehicle micro-clouds, the operation module 212 of the first CP node 112 can instruct to copy the piece of data content to one or more other vehicle micro-clouds 110 as a backup. The operation module 212 selects one or more other vehicle micro-clouds 110 to which the first vehicle micro-cloud 110 transfers the piece of data content based on metadata exchanged on the control plane. For example, the one or more other vehicle micro-clouds 110 are determined based on one or more of the following: the data storage resources available in each candidate vehicle micro-cloud 110; and the distance from the first vehicle micro-cloud 110 to each candidate vehicle micro-cloud 110 (e.g., the distance between the first CP node 112 and the CP node 112 of each candidate vehicle micro-cloud 110). For example, the candidate vehicle micro-cloud 110 with the largest amount of available data storage resources or the shortest distance can be selected to perform the data copy operation.

[0156] In some embodiments, the operation module 212 determines that a data content group is lost in the first vehicle micro cloud 110, and obtains the group of data content from another vehicle micro cloud 110 in the vehicle macro cloud 102 to restore the data content in the first vehicle micro cloud 110. For example, when a piece of data content is lost from the first vehicle micro cloud 110 (for example, due to vehicle mobility, packet loss, etc.), the operation module 212 of the first CP node 112 searches for one or more state data structures in its resource data, and searches for another CP node 112 whose content list includes the piece of data content based on the one or more state data structures. The operation module 212 requests the other CP node 112 to provide the lost piece of data content through the V2X network. For example, similar to the operation of processing a data request performed by the request processing module 208, the operation module 212 of the first CP node 112 identifies a target content provider for providing the piece of data content based on one or more state data structures and network statistics collected on the control plane. The operation module 212 requests the target content provider to provide the piece of data content.

[0157] Example Processing

[0158] Reference now Figure 3 , depicts a flow chart of an example method 300 for improving wireless communication between vehicle micro-cloud groups 110 within a vehicle macro cloud 102 according to some embodiments. The steps of the method 300 may be performed in any order and are not necessarily Figure 3 Here, it is assumed that the method 300 is executed by the first CP node 112 of the first vehicle micro cloud 110 .

[0159] At step 301 , the communication module 202 receives a data request from a requester via a V2X network.

[0160] At step 303 , the request processing module 208 uses the control plane to analyze the data request to select a target content provider for providing the data content requested by the data request, wherein the target content provider is the second CP node 112 in the second vehicle micro cloud 110 of the vehicle macro cloud 102 .

[0161] At step 305, the request processing module 208 processes the data request using the data plane.

[0162] At step 306 , the machine learning module 210 generates feedback data including one or more of result data describing a result of processing the data request and control plane data associated with the control plane.

[0163] At step 307, the machine learning module 210 modifies the operation of the first CP node 112 based on the feedback data so as to achieve a reduction in one or more of latency of data delivery and data packet loss for data requests processed by the first CP node 112, wherein the reduction improves over time as more feedback data is generated.

[0164] Figures 4A-4C Another method 400 for improving wireless communication between a vehicle micro cloud group 110 within a vehicle macro cloud 102 is depicted according to some embodiments. The steps of the method 400 may be performed in any order and are not necessarily Figures 4A-4C Here, it is assumed that the method 400 is executed by the first CP node 112 of the first vehicle micro cloud 110 .

[0165] refer to Figure 4A At step 401, the plane establishment module 204 cooperates with other CP nodes 112 of other vehicle micro clouds 110 to establish a control plane and a data plane for the vehicle macro cloud 102, wherein the control plane is a distributed control plane and includes a first CP node 112 of the first vehicle micro cloud 110 and one or more other CP nodes 112 of one or more other vehicle micro clouds 110.

[0166] At step 403 , the state module 206 generates first state data describing the state of the first vehicle micro-cloud 110 .

[0167] At step 405 , the state module 206 applies the control plane to perform state data exchange with one or more other CP nodes 112 of one or more other vehicle micro clouds 110 in the vehicle macro cloud 102 .

[0168] At step 407 , the state module 206 constructs one or more state data structures including state data of one or more other vehicle cloudlets 110 .

[0169] At step 409 , the status module 206 measures network data including latency data describing latency of data delivery and packet data describing packet delivery rate based on the status data exchange performed in the vehicle macro cloud 102 .

[0170] At step 411 , the request processing module 208 receives a data request from a requester via the V2X network.

[0171] At step 413 , the request processing module 208 retrieves a content list from the first state data describing the state of the first vehicle cloudlet 110 .

[0172] refer to Figure 4B At step 415, the request processing module 208 determines whether the data content requested by the data request is stored by the first vehicle micro-cloud 110. In response to the data content requested by the data request being stored by the first vehicle micro-cloud 110, the method 400 moves to step 417. Otherwise, the method 400 moves to step 419.

[0173] At step 417, the request processing module 208 responds to the data request with a V2X wireless message including the data content as its payload. The method then continues to Figure 4C Step 435.

[0174] At step 419 , the request processing module 208 analyzes the resource data of the first vehicle cloudlet 110 to determine a target content provider for providing data content.

[0175] At step 421 , the request processing module 208 uses the control plane to forward the data request received from the requester to the target content provider via the V2X network.

[0176] At step 423 , the request processing module 208 receives data content from a target content provider via the V2X network using the data plane.

[0177] At step 425 , the request processing module 208 forwards the data content received from the target content provider to the requester via the V2X network using the data plane.

[0178] At step 427, the machine learning module 210 generates feedback data including one or more of result data describing a result of processing the data request and control plane data associated with the control plane.

[0179] Go to Figure 4CAt step 429, the machine learning module 210 modifies the operation of the communication unit 245 of the first CP node 112 so that the communication unit 245 caches the data content on the first CP node 112 based on the feedback data. Therefore, for a data request for requesting the data content again, the latency of data delivery and the loss of data packets are reduced.

[0180] At step 431 , the machine learning module 210 analyzes the feedback data to determine one or more types of popular data content.

[0181] At step 433, the machine learning module 210 modifies the operation of the communication unit 245 of the first CP node 112 so that the communication unit 245 pre-fetches and stores the one or more types of popular data content on the first CP node 112. Therefore, for data requests requesting the one or more types of popular data content, the latency of data delivery and data packet loss are reduced.

[0182] At step 435 , the operation module 212 monitors the first vehicle cloudlet 110 for a data replication triggering event.

[0183] At step 437 , in response to the occurrence of the data replication triggering event, the operation module 212 replicates the data of the first vehicle micro cloud 110 to another vehicle micro cloud 110 in the vehicle macro cloud 102 .

[0184] At step 439 , the operation module 212 determines that a data content group is lost in the first vehicle cloudlet 110 .

[0185] At step 441 , the operation module 212 obtains the set of data content from another vehicle micro cloud 110 in the vehicle macro cloud 102 to restore the set of data content in the first vehicle micro cloud 110 .

[0186] Figure 5 is a graphical representation illustrating an example structure 500 for bridging isolated vehicle macro clouds 102 according to some embodiments. For example, V2V networks are often isolated from each other in areas with low vehicle density, resulting in multiple isolated vehicle macro clouds 102. In this case, a vehicle macro cloud 102 cannot reach another vehicle macro cloud 102 through the V2V network. Figure 5 , vehicle Hongyun B cannot reach vehicle Hongyun A through the V2V network.

[0187] In some embodiments, the cloud server 501, the edge server 503 (503A, 503B) or a combination thereof in the backbone network can each host a CP node 112 to bridge such gaps between isolated vehicle macro clouds 102. The data plane established therein can also use V2N communication for data transmission across the vehicle macro cloud 102.

[0188] Fig. 6A and 6B 6 is a graphical representation illustrating example DSRC data 600 according to some embodiments. DSRC messages may be used to distribute status data between CP nodes 112 using a distributed control plane. Figure 6A-6B An example of DSRC data 600 is depicted in FIG. DSRC messages are merely one example of V2X wireless communications that may be used to distribute status data according to some embodiments. Any other wireless communication technology may be used to distribute status data. Thus, any routing protocol operating over any wireless medium may be used to distribute status data to other vehicle micro-clouds 110 that are more than one hop away from a given vehicle micro-cloud 110.

[0189] Vehicles are increasingly equipped with DSRC. DSRC-equipped vehicles can broadcast DSRC messages at an adjustable rate of once every 0.10 seconds. For example, DSRC-equipped vehicles can transmit basic safety messages (BSM messages). These BSM messages contain DSRC data. BSM messages can be used to transmit status data between CP nodes 112 of the vehicle macro cloud 102. Fig. 6A A block diagram illustrating some of the DSRC data contained in each BSM message is depicted.

[0190] The following are Figure 6B The first part of the DSRC message contains the core data elements, including vehicle position, heading, velocity, acceleration, steering wheel angle, and vehicle dimensions. DSRC messages are transmitted at an adjustable rate of approximately 10 times per second.

[0191] Part 2 of a DSRC message includes groups of variable data elements drawn from a large list of optional elements. Some of them are selected based on event trigger conditions (e.g., ABS is activated). They are added to Part 1 and sent as part of the DSRC message, but many of them are transmitted less frequently to save bandwidth. DSRC messages contain only the current snapshot (except for path data which is itself limited to a few seconds of past historical data).

[0192] In the above description, for the purpose of explanation, many specific details are set forth in order to provide a thorough understanding of the specification. However, it is obvious to those skilled in the art that the present disclosure can be practiced without these specific details. In some instances, the structures and devices are shown in block diagram form to avoid ambiguous descriptions. For example, the present embodiment is described above mainly with reference to user interfaces and specific hardware. However, the present embodiment can be applied to any type of computer system that can receive data and commands, and any peripheral device that provides services.

[0193] References in the specification to "some embodiments" or "some examples" mean that a particular feature, structure, or characteristic described in conjunction with the embodiments or examples may be included in at least one embodiment described. The phrase "in some embodiments" appearing in various places in the specification does not necessarily refer to the same embodiment.

[0194] Some portions of the following detailed description are presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means by which those skilled in the art of data processing most effectively communicate the substance of their work to others skilled in the art. Here, and in general, an algorithm is considered to be a self-consistent sequence of steps leading to a desired result. These steps are steps requiring physical manipulation of physical quantities. Typically, although not necessarily, these quantities take the form of electrical or magnetic signals that can be stored, transmitted, combined, compared, and otherwise manipulated. Sometimes, primarily for general reasons, it has proven convenient to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc.

[0195] It should be remembered, however, that all of these and similar terms are associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated or otherwise apparent from the following discussion, it should be appreciated that throughout this description, discussions utilizing terms including "processing" or "computing" or "determining" or "displaying" refer to the actions and processes by which a computer system or similar electronic computing device manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system's memories or registers or other such information storage, transmission or display devices.

[0196] The current embodiments of the specification may also be directed to an apparatus for performing the operations herein. This apparatus may be specially constructed for the desired purpose, or it may include a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a computer-readable storage medium, including but not limited to any type of disk, including floppy disks, optical disks, CD-ROMs and magnetic disks, read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic or optical cards, flash memory including USB keys with non-volatile memory, or any type of medium suitable for storing electronic instructions, each of which is coupled to a computer system bus.

[0197] The specification can take the form of some complete hardware embodiments, some complete software embodiments or some embodiments containing both hardware and software elements. In some preferred embodiments, the specification is implemented with software, which includes but is not limited to firmware, resident software, microcode, etc.

[0198] Furthermore, the description may take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system. For the purposes of this description, a computer-usable or computer-readable medium may be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device.

[0199] A data processing system suitable for storing or executing program code will include at least one processor coupled directly or indirectly to a memory element via a system bus. The memory element may include local memory, bulk storage, and cache memory that are employed during the actual execution of the program code, wherein the cache memory provides temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution.

[0200] Input / output or I / O devices (including but not limited to keyboards, displays, pointing devices, etc.) can be coupled to the system either directly or through intervening I / O controllers.

[0201] Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.

[0202] Finally, the algorithms and displays presented herein are not inherently related to any particular computer or other device. According to the teachings herein, various general purpose systems can be used with the program, or it may prove convenient to construct a more specialized device to perform the required method steps. The required structure of various these systems can be seen from the following description. In addition, this specification is not described with reference to any specific programming language. It will be appreciated that various programming languages ​​can be used to implement the teachings of the specification as described herein.

[0203] The foregoing description of the embodiments of the present specification has been presented for the purpose of illustration and description. It is not intended to be exhaustive or to limit the specification to the precise form disclosed. In view of the above teachings, many modifications and variations are possible. It is intended that the scope of the present disclosure is not limited by this specific embodiment, but is limited by the claims of the present application. As will be appreciated by those skilled in the art, without departing from the spirit or basic characteristics of the present invention, the present specification can be implemented in other specific forms. Similarly, the specific naming and division of modules, routines, features, attributes, methods and other aspects are not mandatory or important, and the mechanism for implementing the specification or its features can have different names, divisions or formats. In addition, as will be apparent to those of ordinary skill in the relevant art, the modules, routines, features, attributes, methods and other aspects of the present disclosure can be implemented as software, hardware, firmware or any combination of the three. Moreover, anywhere any component of the components of the specification (an example of which is a module) is implemented as software, the component may be implemented as a standalone program, as part of a larger program, as multiple separate programs, as a static or dynamic link library, as a kernel loadable module, as a device driver, or in each and any other manner known to those of ordinary skill in the art of computer programming now or in the future. In addition, the present disclosure is in no way limited to embodiments in any specific programming language or for any specific operating system or environment. Thus, the present disclosure is intended to illustrate, but not to limit, the scope of the present specification, which is set forth in the following claims.

Claims

1. A method for a first control plane (CP) node in a first vehicle micro cloud of a vehicle macro cloud, include: exchanging one or more state data structures describing one or more states of one or more other vehicle cloudlets with one or more other vehicle cloudlets; In response to a requestor requiring data content sending a data request to the first vehicle cloudlet, if the data content is not available on the first vehicle cloudlet, retrieving by the first CP node from its resource data the packet data and latency data measured when exchanging one or more state data structures with one or more other vehicle cloudlets; determining, by the first CP node, a target content provider for providing popular content requested by the data request based on one or more state data structures, latency data, and packet data, wherein the target content provider is a second CP node in a second vehicle micro-cloud of the vehicle macro-cloud, and wherein the popular data content is defined as popular based on a number of requests for the popular data content exceeding a threshold number; and modifying the operation of the communication unit of the first CP node based on the feedback data so that the communication unit pre-fetches and stores popular data content on the first CP node to achieve a reduction in one or more of latency of data delivery or data packet loss for data requests processed by the first CP node; The method further comprises: Cooperate with at least the second CP node of the second vehicle micro cloud to establish a CP and data plane for the vehicle macro cloud, wherein the CP is a distributed CP and includes at least the first CP node of the first vehicle micro cloud and the second CP node of the second vehicle micro cloud.

2. The method according to claim 1, further comprising: include: generating feedback data including one or more of result data describing a result of processing the data request or CP data associated with the CP; as well as analyzing the feedback data to determine one or more types of popular data content; The communication unit pre-fetches and stores the one or more types of popular data contents on the first CP node.

3. The method according to claim 1, in: The data request processed by the first CP node is again a request for the popular data content, and Modifying the operation of the communication unit of the first CP node includes caching the popular data content on the first CP node based on the feedback data to achieve a reduction in one or more of latency of the data delivery or data packet loss for the data request.

4. The method according to claim 1, further comprising: include: Use the data plane to process data requests; as well as Feedback data is generated including one or more of result data describing a result of processing the data request or CP data associated with the CP.

5. The method according to claim 1, further comprising: include: generating first status data describing a status of the first vehicle micro-cloud; as well as Applying the CP to perform status data exchange in the vehicle macro cloud includes: Sending the first status data to the second CP node of the second vehicle micro cloud; as well as Second status data describing a status of the second vehicle cloudlet is received from the second CP node of the second vehicle cloudlet.

6. A method as claimed in claim 5, wherein the first status data includes data describing one or more of the following: the geographical location of the first vehicle micro-cloud; a content list describing a list of data files stored by the first vehicle micro-cloud and the information described by each data file; one or more computing resources available on the first vehicle micro-cloud; one or more data transfer requests that the first vehicle micro-cloud needs to satisfy; one or more data replication requests that the first vehicle micro-cloud needs to satisfy; or one or more data recovery requests that the first vehicle micro-cloud needs to satisfy.

7. The method according to claim 5, further comprising: include: Based on the status data exchange performed in the vehicle macro cloud, measuring network data including latency data describing latency of the data delivery and packet data describing packet delivery rate; as well as Generate resource data of the first vehicle micro-cloud, which includes one or more of the following: the first status data of the first vehicle micro-cloud; a status data structure including second status data of the second vehicle micro-cloud; or the network data including the waiting time data and the packet data.

8. The method of claim 1, wherein the data request is analyzed using the CP to select the target content provider include: retrieving a content list from first state data describing a state of the first vehicle micro-cloud to determine whether the popular data content requested by the data request is stored by the first vehicle micro-cloud; as well as In response to the popular data content requested by the data request not being stored by the first vehicle cloudlet, analyzing resource data of the first vehicle cloudlet to determine that the target content provider is the second CP node of the second vehicle cloudlet.

9. The method as claimed in claim 8, wherein the target content provider is the second CP node of the second vehicle micro-cloud, which satisfies one or more of the following: the second CP node stores the popular data content in the storage device of the second vehicle micro-cloud; compared with one or more other CP nodes of one or more other vehicle micro-clouds in the vehicle macro cloud, the second CP node has the shortest distance to the first CP node; compared with the one or more other CP nodes, the second CP node has the minimum waiting time to the first CP node; or compared with the one or more other CP nodes, the second CP node has the highest packet delivery rate to the first CP node.

10. The method of claim 1, wherein a data plane processes the data request based on a decision made by the CP.

11. The method of claim 10, wherein the data request is forwarded to the target content provider by the CP as a control message via a vehicle-to-everything (V2X) network, and based on the decision made by the CP, the data plane processes the data request by: receiving the popular data content from the target content provider via the V2X network using the data plane; and The popular data content received from the target content provider is forwarded using the data plane to a requester sending a data request via the V2X network. 12 . The method of claim 1 , wherein instructing another vehicle cloudlet to replicate data is based on a distance from the first vehicle cloudlet to the other vehicle cloudlet.

13. The method of claim 1, further comprising: include: determining that a data content group is lost in the first vehicle micro-cloud; as well as The data content group is obtained from another vehicle micro cloud in the vehicle macro cloud to restore the data content group in the first vehicle micro cloud.

14. A system, include: An onboard computer system of a networked vehicle acting as a first control plane (CP) node of a first vehicle micro cloud in a vehicle macro cloud, comprising a communication unit, a processor, and a non-transitory memory storing computer code, the computer code, when executed by the processor, causing the processor to: exchanging one or more state data structures describing one or more states of one or more other vehicle cloudlets with one or more other vehicle cloudlets; In response to a requestor requiring data content sending a data request to the first vehicle cloudlet, if the data content is not available on the first vehicle cloudlet, retrieving by the first CP node from its resource data the packet data and latency data measured when exchanging one or more state data structures with one or more other vehicle cloudlets; determining, by the first CP node, a target content provider for providing the popular data content requested by the data request based on one or more state data structures, latency data, and packet data, wherein the target content provider is a second CP node in a second vehicle micro-cloud of the vehicle macro-cloud, and wherein the popular data content is defined as popular based on a number of requests for the popular data content exceeding a threshold number; modifying the operation of the communication unit of the first CP node based on the feedback data so that the communication unit pre-fetches and stores popular data content on the first CP node to achieve a reduction in one or more of latency of data delivery or data packet loss for data requests processed by the first CP node; When the computer code is executed by the processor, it also causes the processor to cooperate with at least the second CP node of the second vehicle micro cloud to establish a CP and data plane for the vehicle macro cloud, wherein the CP is a distributed CP and includes at least the first CP node of the first vehicle micro cloud and the second CP node of the second vehicle micro cloud.

15. A non-transitory computer readable medium having computer executable code stored thereon, the computer executable code, when executed by a processor of a first control plane (CP) node in a first vehicle micro cloud of a vehicle macro cloud, causes the processor to: exchanging one or more state data structures describing one or more states of one or more other vehicle cloudlets with one or more other vehicle cloudlets; In response to a requestor requiring data content sending a data request to the first vehicle cloudlet, if the data content is not available on the first vehicle cloudlet, retrieving by the first CP node from its resource data the packet data and latency data measured when exchanging one or more state data structures with one or more other vehicle cloudlets; determining, by the first CP node, a target content provider for providing the popular data content requested by the data request based on one or more state data structures, latency data, and packet data, wherein the target content provider is a second CP node in a second vehicle micro-cloud of the vehicle macro-cloud, and wherein the popular data content is defined as popular based on a number of requests for the popular data content exceeding a threshold number; and modifying the operation of the communication unit of the first CP node based on the feedback data so that the communication unit pre-fetches and stores popular data content on the first CP node to achieve a reduction in one or more of latency of data delivery or data packet loss for data requests processed by the first CP node; Wherein, when the computer code is executed by the processor, it also causes the processor to cooperate with at least the second CP node of the second vehicle micro cloud to establish a CP and data plane for the vehicle macro cloud, wherein the CP is a distributed CP and includes at least the first CP node of the first vehicle micro cloud and the second CP node of the second vehicle micro cloud.