CN113965568A - Edge computing system for urban road C-V2X network - Google Patents
Edge computing system for urban road C-V2X network Download PDFInfo
- Publication number
- CN113965568A CN113965568A CN202111213957.0A CN202111213957A CN113965568A CN 113965568 A CN113965568 A CN 113965568A CN 202111213957 A CN202111213957 A CN 202111213957A CN 113965568 A CN113965568 A CN 113965568A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- mec
- edge
- queue
- edge computing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
- H04L41/0826—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability for reduction of network costs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an edge computing system for an urban road C-V2X network, which comprises three levels of a vehicle end MEC unit, a roadside MEC unit and a base station MEC unit and a distributed resource allocation and scheduling strategy, wherein the three levels cooperate to realize edge computing functions of five categories of traffic target detection and identification, traffic event discovery and prediction, traffic scene fusion analysis and processing, local traffic situation comprehensive perception, assistance and automatic driving decision for the urban road C-V2X network. The edge computing system can clearly divide and accurately meet the functional requirements of C-V2X network operation on the edge computing unit in urban road traffic environment, is beneficial to the reasonable distribution and scheduling of computing power, storage, network and application resources of edge computing equipment at vehicle, road and edge ends, furthest exerts the capability of edge computing in improving the safety, efficiency and service quality of road traffic intelligent network connection application, and lays a foundation for realizing a perception, computation and communication integrated vehicle-road cooperative system in the future.
Description
Technical Field
The invention relates to the field of edge computing, Internet of vehicles and vehicle road cooperation, in particular to an edge computing system for an urban road C-V2X network.
Background
Urban road traffic is suffering from aeipathia such as traffic jam and frequent accidents in the global range. The amount of motor vehicles kept is rapidly increasing year by year, and the mere increase of road supply to alleviate traffic problems has proven to have its limitations. The intelligent traffic comprehensively utilizes the technologies of modern communication, perception, calculation, network exchange, new energy automobiles, automatic driving, big data and the like, can be used as effective supplement for solving the problem, and vehicles are becoming more and more smart and roads are becoming more and more smart by means of the addition of high and new technologies.
Edge computing has received a great deal of attention in recent years in academia and industry, and distributed transformation of the deployment of computing power and resources close to customers has been a trend. The edge computing has incomparable advantages of centralized cloud computing in the aspects of saving data bandwidth, reducing return capacity, reducing transmission cost, reducing time delay, improving data real-time analysis capability, protecting user data privacy and the like, so that the edge computing and the cloud computing can provide stronger computing capability and a more optimized analysis processing means for intelligent transportation.
Due to the diversity of application scenarios, there is no unified scheme for the specific implementation architecture of edge computation. The main influencing factors include the specific requirements of the application (time delay, bandwidth, real-time performance, data transmission and security), technical conditions (edge configuration and distance from the cloud end and the terminal equipment), service characteristics (requirements and economic considerations) and the like. For example, understanding only the location of the "edge" is the terminal device, the service site, the vicinity of the base station, the aggregation point, the transmission network, the core network, the near cloud, and so on. Different edge computing systems are provided by communication equipment manufacturers, IT manufacturers, operators, car factories, solution providers and the like according to the industry advantages of the systems, the systems have various characteristics, but a set of intelligent special edge computing system for traffic, which is clear in hierarchical design, reasonable in function division and strong in scene directivity, is lacked in terms of understanding and pertinence design of traffic services.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to solve the technical problem of the prior art and provides an edge computing system for an urban road C-V2X (Cellular-Vehicle to evolution) network.
In order to solve the technical problem, the invention discloses an Edge Computing system facing an urban road C-V2X network, which comprises an infrastructure layer, a network layer, a resource layer, a platform layer, a scene layer and a service application layer, wherein the infrastructure layer comprises three layers of a vehicle end MEC (Multi-Access Edge Computing) unit, a roadside MEC unit and a base station MEC unit and a set of distributed resource allocation and scheduling strategy, and the MEC units are connected with a wired network through a C-V2X network to form a vehicle, road and station integrated deployment architecture; edge computing tasks are processed among the MEC units through distributed resource allocation and scheduling strategies.
The vehicle-end MEC Unit comprises a special vehicle-mounted MEC terminal, a vehicle-mounted computer and a vehicle-mounted OBU (On board Unit) which are deployed at a vehicle end and used for processing edge calculation tasks approaching a vehicle target On a road;
the roadside MEC unit comprises a portable computer which is arranged on a roadside signal lamp pole, a monitoring pole, a special upright post and a case, is generally an embedded architecture, can support AI deep learning and the like, and is used for processing edge calculation tasks of more than two traffic targets in a road junction and a road section from the roadside;
the base station MEC unit comprises a general edge computing server deployed in a cellular network base station machine room and used for processing edge computing tasks of a large number of traffic targets related to situation awareness and cooperative control in a base station coverage area;
the edge calculation tasks comprise traffic target detection and identification, traffic event discovery and prediction, traffic scene fusion analysis and processing, local traffic situation comprehensive perception and auxiliary and automatic driving decision tasks in task categories.
Distributed resource allocation and scheduling policies refer to policies for the distributed configuration and management of edge computing resources (including computing power, bandwidth, storage, etc.) in a C-V2X network. The general principle is that technologies such as virtual machines, containers, micro-services, heterogeneous computation and deep learning are flexibly adopted, factors such as geographic positions, network time delay, message periods, event properties, complexity and transmission conditions are comprehensively considered, and resources are dynamically allocated and scheduled according to specific scene requirements. The method comprises the steps that a same set of general distributed resource allocation and scheduling strategies are preset in various MECs to support flexible and rapid scene design development and deployment operation, and scene edge calculation tasks such as traffic target detection and identification, traffic event discovery and prediction, intelligent networking service scene realization, local traffic situation comprehensive perception, assistance and automatic driving decision making are effectively supported.
The distributed management of the three levels of edge computing units is scientific, reasonable, flexible and efficient, and five types of traffic edge computing tasks of traffic target detection and identification, traffic event discovery and prediction, traffic scene fusion analysis and processing, local traffic situation comprehensive perception, assistance and automatic driving decision are respectively realized.
In one implementation, the dedicated on-board MEC terminal includes a lightweight edge computing device dedicated to vehicle sensing data analysis processing and simple fusion computations. The System needs to provide rich external interfaces to be docked with devices such as a vehicle-mounted camera, a millimeter wave radar, a laser radar, an ultrasonic radar, a Controller Area Network (CAN) bus, a Beidou/GPS (Global Positioning System) Positioning device, a vehicle-mounted OBU and the like, and the computing power of the System supports fusion processing of original data sensed by the docked vehicle-mounted camera, the millimeter wave radar, the laser radar, the ultrasonic radar, the CAN bus and the Beidou/GPS Positioning device, so that real-time traffic target detection and identification are completed, including dynamic and static characteristics such as distance, speed, direction, acceleration, contour, color, license plate number and the like of a target, and the dynamic and static characteristics are transmitted to the vehicle-mounted OBU in a structured data form and are sent out by the OBU.
The vehicle-mounted computer comprises a highly integrated vehicle-scale special computer, and meets strict temperature environment, vibration and impact resistance, reliability, consistency requirements, manufacturing process and the like. The computer is installed in front of a vehicle factory, software and hardware are relatively closed, and the computer is mainly used for carrying out real-time dynamic monitoring and fault detection and early warning on the working state of a vehicle.
The on-board OBU includes a vehicle networking specific on-board communication device employing C-V2X technology and having some marginal effort. The edge calculation force can be matched with a special vehicle-mounted MEC terminal to cooperatively complete a large number of complex vehicle-end calculation tasks. The vehicle-mounted OBU can interact data of the vehicle-end MEC units with the base station MEC units through the cellular network, and interact with other vehicle-end MEC units and road-side MEC units through the V2X network, so that efficient cooperation among the MEC units is realized. The cellular network refers to a Uu cellular communication mode of a 4G/5G cellular communication network, namely a C-V2X network; the V2X network refers to the PC5 direct communication mode of the C-V2X network.
In one implementation, the roadside MEC unit needs to be designed at an industrial level to ensure its operational reliability and stability due to the severe requirements of the operating environment. The roadside MEC Unit is mainly connected with an RSU (Road Side Unit), a roadside camera, a millimeter wave radar, a laser radar, an information board/induction screen, a big dipper/GPS, a signal machine, a meteorological sensor, an environmental sensor and the like in an abutting joint mode through an ethernet switch, and is connected with the base station MEC through an optical fiber or a cellular network.
The base station MEC units may be deployed on racks or individually depending on the specific equipment and field conditions. In the base station where the MEC device has been deployed by the operator, the MEC unit can select to reuse the operator device, and share resources such as computing power, storage, network and the like, so as to save cost and improve benefit. The base station MEC may be connected to the roadside MEC unit through an optical fiber or a cellular network, and connected to the vehicle end MEC through the cellular network.
In one implementation, the resource layer includes a heterogeneous resource sublayer, a resource configuration sublayer and a resource scheduling sublayer, where the heterogeneous resource sublayer includes a unified representation of a heterogeneous processor, a network bandwidth, and a storage resource involved in edge computing, and the resource configuration sublayer performs virtualization configuration management, including a virtual machine mode and a containerization mode; the resource scheduling sublayer performs resource calculation, resource scheduling, resource isolation, scheduling optimization, job queue management, load balancing, virtual machine migration and resource unloading according to the characteristics of the edge calculation task;
the platform layer deploys micro-services according to the requirements on instantaneity, safety and heterogeneous computing of each MEC unit, and the platform layer support components comprise service registration, service discovery, a service gateway, service arrangement, API (Application Programming Interface) management, an integrated framework and a distributed management and calling chain; the platform layer also provides traffic AI (Artificial Intelligence) algorithm support and safety certification;
the scene layer provides calculation support for intelligent network connection edge scenes including traffic safety, traffic efficiency, travel service and automatic driving and can be elastically expanded according to requirements;
the service application layer is cooperated with the cloud service application layer on the basis of scene layer service, and provides intelligent network connection and intelligent traffic service application including bus priority, holographic intersection, traffic sequencing, digital twinning, signal optimization and free flow charging for traffic managers, traffic transportation industries and driver users.
In one implementation, the distributed resource allocation and scheduling policy includes:
step 1, determining service application, and determining related traffic participation objects and action ranges of the service application;
step 2, dividing edge scenes, and dividing the determined service application into different edge scene application combinations;
step 3, analyzing detailed characteristics of the edge scene application, wherein the detailed characteristics comprise application properties, event types, high-precision map and positioning requirements, time delay requirements, reliability requirements, transmission bandwidth requirements, message periods, data packet sizes, data types, AI requirements, multi-source fusion requirements, decision and control requirements, road characteristics, target motion characteristics, static characteristics and environmental and meteorological influences of the edge scene application;
step 4, determining an edge calculation task, and determining an edge calculation task for realizing an edge scene according to the detailed characteristics of the application of the edge scene;
step 5, determining the detailed description of the edge computing resources, submitting an edge computing task request to a platform layer, calling a corresponding micro-service and algorithm model by the platform layer through a micro-service API gateway according to the request, and issuing the detailed description of the needed computing resources to a resource layer through the micro-service;
and 6, performing distributed resource scheduling, wherein the resource layer performs fine scheduling of calculation power, bandwidth and storage according to the detailed description of the required edge calculation resources, and allocates the appropriate resources to the appropriate edge calculation tasks.
In one implementation, the edge computing tasks include latency sensitive, security sensitive, bandwidth sensitive, computational power consumption, storage footprint, and heterogeneous collaboration type tasks in terms of task characteristics.
In one implementation mode, distributed resource scheduling is carried out, a scheduling scheme based on a distributed resource scheduling algorithm and a combination thereof are preset aiming at different task characteristics of edge computing tasks by integrating the conditions of the existing resource pools, a menu-type resource scheduling scheme service is provided, trivial resource scheduling details are shielded for upper-layer application, and the acceleration and optimization of scheduling are realized; for the vehicle end MEC unit, the computing resources are preferentially allocated to the vehicle; for the roadside MEC unit, the resource scheduling range supported by the roadside MEC unit is within the signal coverage range of the RSU, and the roadside MEC unit is used for scene calculation including roadside video analysis, laser radar point cloud processing algorithm and high-precision map matching, and supporting the provision of calculation resources from the roadside to the vehicle end, so that cooperative auxiliary driving and automatic driving support of the vehicle are realized; for the base station MEC unit, the method is used for scene calculation of long period (minute level), medium time delay (20ms-200ms) and weak locality (crossing multiple adjacent intersections).
In one implementation, the distributed resource scheduling algorithm includes:
step 6.1, initializing a queue, dividing the edge calculation task into 6 queues according to task characteristics, wherein the queue where the time delay sensitive task is located is r1R is the queue where the security sensitive task is located2The queue where the bandwidth sensitive task is located is r3The queue where the computing power consumption type task is located is r4The queue where the storage occupation type task is positioned is r5And the queue where the heterogeneous cooperative task is positioned is r6Each queue is allocated with a fixed length when being initialized; edge computing task requests with different task characteristics enter corresponding queues in parallel;
step 6.2, setting the priority of each queue, preferentially distributing resources to the queue with high authority, and defining the priority of each queue as r1>r2>r3＝r4＝r5＝r6I.e. the system priority processing queue r1The request of (1); in the process of receiving the request, if the queue with the highest priority reaches the distribution length, merging the queue with the next-priority queue; if a certain queue is empty in a set time interval, merging the queue with the highest priority; after the request in the highest priority queue is completely processed, processing the next priority queue;
6.3, determining the scheduling sequence of different requests in the same queue;
and 6.4, sequentially carrying out resource allocation processing on the requests in each queue according to the scheduling sequence.
In one implementation, the step 6.3 includes:
step 6.3.1, defining QoS model indexes of the edge computing system, wherein the model indexes comprise computing time, transmission time, scheduling time, bandwidth overhead, computational resources, storage resources, safety requirements and permission indexes;
step 6.3.2, definitionVector S ═ S1,s2,...,si,...,snThe request service set in a certain queue is used as the index, n is the number of requests, and i is more than or equal to 1 and less than or equal to n; vector Q ═ Q1,q2,...,qj,...,qmThe index set is a QoS model index set, m is the total number of QoS model indexes, and j is more than or equal to 1 and less than or equal to m; the weight matrix is P ═ P (P)ij)n×m，pijRepresenting the importance requirement of the ith request in the queue on the jth QoS index;
step 6.3.3, normalization processing is performed on the weight matrix to obtain a calculation matrix Y (Y ═ Y)ij)n×m：
Wherein the content of the first and second substances,
maxp.j＝max{pij},1≤i≤n，minp.j＝min{pij},1≤i≤n；
step 6.3.4, calculate the information entropy H of the ith requestiComprises the following steps:
step 6.3.5, calculate the evaluation index w of the ith requestiComprises the following steps:
step 6.3.6, the requests of each queue are all according to the evaluation index wiAnd (5) sequencing in a descending manner to obtain the scheduling sequences of different requests.
In one implementation, the distributed resource scheduling is completed in step 6, that is, after the edge calculation task is completed, the corresponding container and its mirror image are deleted, and the occupied resources are released in time.
Has the advantages that:
according to the invention, through integrating three different types and levels of edge computing equipment of the vehicle end MEC unit, the roadside MEC unit and the base station MEC unit, the scientific and reasonable allocation of edge computing resources at the vehicle end, the roadside and the base station is realized by utilizing a distributed resource allocation and scheduling strategy designed aiming at a traffic application scene, the dynamic use efficiency of the resources is improved, and the overall deployment cost of edge computing is reduced. By dividing the edge calculation tasks into different categories such as a target detection identification category, an event discovery prediction category, a service scene realization category, a comprehensive situation perception category, an auxiliary and automatic driving decision category and the like, the method is beneficial to purposefully determining resource allocation and scheduling strategies and realizing traffic edge calculation deployment targets of 'task determination by scene', 'strategy determination by task', 'resource determination by strategy'.
The invention can provide a multi-type hierarchical edge computing framework close to the actual traffic scene requirement for the urban road C-V2X network by utilizing the technologies of edge computing, distributed resource allocation and scheduling, virtual machines, containerization, micro-service, heterogeneous computing, deep learning and the like, can effectively improve the edge computing efficiency and the edge resource utilization rate, reduce the scene analysis time delay, improve the cooperative application reliability of the vehicle road, reduce the overall deployment cost and improve the project fund use benefit.
Drawings
The foregoing and/or other advantages of the invention will become further apparent from the following detailed description of the invention when taken in conjunction with the accompanying drawings.
FIG. 1 is a schematic diagram of the physical system architecture of the present invention.
Fig. 2 is a schematic diagram of the general technical architecture of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The embodiment of the application provides an edge computing system facing an urban road C-V2X network, as shown in FIG. 2, the edge computing system comprises an infrastructure layer, a network layer, a resource layer, a platform layer, a scene layer and a service application layer, wherein the infrastructure layer comprises vehicle-end MEC units, roadside MEC units and base station MEC units, as shown in FIG. 1, the MEC units are closely connected through a C-V2X network, a wired (Ethernet/optical fiber) network and the like to form a vehicle-road-station integrated deployment architecture. Through a distributed resource allocation and scheduling strategy, each MEC unit orderly organizes resources, runs an algorithm, arranges services, interacts communication, stores data and the like, and realizes various types of edge calculation tasks such as a target detection identification type, an event discovery prediction type, a service scene realization type, a comprehensive situation perception type, an auxiliary and automatic driving decision type and the like.
The vehicle-end MEC unit comprises a special vehicle-mounted MEC terminal, a vehicle-mounted computer and a vehicle-mounted OBU, wherein the special vehicle-mounted MEC terminal, the vehicle-mounted computer and the vehicle-mounted OBU are deployed at a vehicle end and are used for processing edge calculation tasks on a road, which are close to a vehicle target;
the roadside MEC unit comprises a portable computer which is arranged on a roadside signal lamp pole, a monitoring pole, a special upright post and a case and is used for processing edge calculation tasks of more than two traffic targets in a road junction and a road section from the roadside;
the base station MEC unit comprises a general edge computing server deployed in a cellular network base station machine room and used for processing edge computing tasks of a large number of traffic targets related to situation awareness and cooperative control in a base station coverage area;
the distributed resource allocation and scheduling strategy refers to a strategy for performing distributed configuration and management on all edge computing resources in a C-V2X network and a wired network, wherein the edge computing resources comprise computing power, bandwidth and storage;
the vehicle-end MEC unit focuses on processing tasks such as identification and detection, safety event early warning, emergency decision, automatic driving and the like of an approaching vehicle target on a road, and the roadside MEC unit focuses on completing tasks such as identification and detection, multi-element perception data fusion, event early warning, blind area and beyond-the-horizon risk reminding of a plurality of traffic targets in a road junction and a road section from the roadside, auxiliary driving scene realization and the like for improving safety and efficiency. The MEC unit of the base station focuses on completing tasks of controlling the overall traffic situation in a coverage area, fusing and processing multi-source event information, realizing intelligent networking services (such as bus priority, holographic intersections and the like), issuing and updating high-precision maps, issuing static and quasi-static information and the like. It should be noted that there may be some overlapping intersections among the three levels of MEC for each type of task, but the view angle, the starting point and the action range are all emphasized and cannot be replaced with each other.
In this embodiment, the special vehicle-mounted MEC terminal includes a lightweight edge computing device specially used for vehicle sensing data analysis processing and simple fusion computing, and the lightweight edge computing device has an external interface and is in butt joint with a vehicle-mounted camera, a millimeter wave radar, a laser radar, an ultrasonic radar, a CAN bus, a compass/GPS positioning device and a vehicle-mounted OBU device through the external interface; the computing power of the lightweight edge computing equipment supports fusion processing of original data sensed by the butted vehicle-mounted camera, the millimeter wave radar, the laser radar, the ultrasonic radar, the CAN bus and the Beidou/GPS positioning equipment, real-time traffic target detection and identification are completed, the characteristics of the distance, the speed, the direction, the acceleration, the contour, the color and the license plate number of the target are included, and the data are transmitted to a vehicle-mounted OBU in a structured data form;
the vehicle-mounted computer comprises a vehicle gauge-level special computer, the vehicle gauge-level special computer is installed in front of a vehicle factory, software and hardware are relatively closed, and the vehicle gauge-level special computer is used for carrying out real-time dynamic monitoring and fault detection and early warning on the working state of a vehicle;
the vehicle-mounted OBU comprises vehicle-mounted special vehicle-mounted communication equipment which adopts a C-V2X technology and has edge calculation force, and the edge calculation force of the vehicle-mounted special vehicle-mounted communication equipment can be matched with a special vehicle-mounted MEC terminal to cooperatively complete a vehicle-end edge calculation task; as shown in fig. 1, the vehicle-mounted OBU can interact data of the vehicle-end MEC unit with the base station MEC unit through the cellular network, and interact with other vehicle-end MEC units and roadside MEC units through the V2X network.
In this embodiment, as shown in fig. 1, the roadside MEC unit is connected to the RSU, the roadside camera, the millimeter wave radar, the laser radar, the information board/the inductive screen, the beidou/GPS, the signal machine, the weather sensor, and the environmental sensor through the ethernet switch, and is connected to the base station MEC unit through the optical fiber or the cellular network.
As shown in fig. 2, the overall technical architecture of the present embodiment mainly includes an infrastructure layer, a network layer, a resource layer, a platform layer, a scene layer, and a service application layer. The infrastructure layer mainly comprises a vehicle end MEC, a roadside MEC, a base station MEC and devices such as perception and communication accessed by the vehicle end MEC, the network layer comprises three networking modes of a C-V2X Uu, a C-V2X PC5 and a wired network (Ethernet/optical fiber), the resource layer comprises a heterogeneous resource sublayer, a resource configuration sublayer and a resource scheduling sublayer, the heterogeneous resource sublayer mainly comprises various heterogeneous processors possibly involved in edge computing, and unified representation of network bandwidth and storage resources, and the resource configuration sublayer carries out virtualization configuration management and comprises a virtual machine mode and a containerization mode. The Virtual Machine mode comprises Virtual Machine software VMware (Virtual Machine ware), open-source Virtual Machine KVM (Kernel-Based Virtual Machine), Virtual box Virtualbox and open-source cloud computing management platform project OpenStack, and the containerization mode comprises an application container engine Docker and a container cluster management/orchestration tool K8S (Kubernets), compound, Marathon and Swarm. Compared with cloud computing, the lightweight characteristic of edge computing mainly uses container technology to support the running environment of micro services, but the container can be provided with safer isolation by combining with virtual machine technology. And the resource scheduling sublayer performs resource calculation, resource scheduling, resource isolation, scheduling optimization, job queue management, load balancing, virtual machine migration, resource unloading and the like according to the task characteristics of the edge calculation. The platform layer is mainly used for deploying a large number of micro services according to the requirements on the real-time performance, the safety performance and the heterogeneous computing of the MEC unit, and supporting components of the platform layer comprise service registration, service discovery, service gateways, business arrangement, API (application programming interface) management, an integrated framework, distributed management, a call chain and the like. The platform also needs to provide traffic AI algorithm support, security authentication (including software-based security authentication and underlying hardware-based security trust root, etc.), and the like. The scene layer provides calculation support for dozens of intelligent networking scenes such as traffic safety, traffic efficiency, travel service and automatic driving, and can be elastically expanded according to requirements. The service application layer is cooperated with the cloud service application layer on the basis of scene layer service, and provides intelligent network connection and intelligent traffic service application including bus priority, holographic intersection, traffic sequencing, digital twinning, signal optimization and free flow charging for users such as traffic managers, traffic transportation industries and drivers.
The distributed resource allocation and scheduling strategy of the present invention is as follows:
step 1, determining specific service application
Determining specific service applications required to be realized according to design functions, such as bus priority, holographic intersections, signal optimization and the like; the method specifically relates to the traffic participation objects, including departments, personnel, vehicles, facilities, equipment, terminals and the like; it should also be clear that the scope of the service application, such as single point, trunk, intersection, road section, area, city, etc., is limited to the coverage of a single base station for the architecture of the present invention.
Step 2, dividing supported edge scene application
According to the definition and the connotation of the business application, the business application is divided into different edge scene application combinations in detail, the scene applications are generally standard scenes supported by the existing standard framework, and can be cut and expanded according to the actual needs of the business.
Step 3, analyzing the detailed characteristics of the edge scene application
For the divided scene application, detailed characteristics of the scene application are further analyzed, including application properties (safety, efficiency, service and automatic driving), event types, high-precision map and positioning requirements, time delay requirements, reliability requirements, transmission bandwidth requirements, message periods, data packet sizes, data types (whether structured data or streaming media data) and the like, AI requirements, multi-source fusion requirements, decision and control requirements, road characteristics, target motion characteristics, static characteristics, environmental and meteorological influences and the like.
Step 4, determining the specific requirements of the scene edge calculation task
And determining the specific edge calculation task requirement required for realizing the scene according to the characteristics of the scene application. The method generally comprises five types of scene calculation requirements, namely traffic target detection and identification, traffic event discovery and prediction, traffic scene fusion analysis and processing, local traffic situation comprehensive perception, assistance, automatic driving decision and the like; specifically, the task characteristics can be divided into task requirements of delay sensitivity, security sensitivity, bandwidth sensitivity, computational power consumption, storage occupation, heterogeneous cooperation and the like. For example, intersection collision prevention, emergency brake early warning and the like are typical delay sensitive task requirements, illegal behavior forensics and high-precision map matching are typical storage occupation type task requirements, and video AI analysis is typical computational power consumption task requirements.
Step 5, determine the detailed description of the required edge computing resources
After the task requirement is determined, an edge computing task request can be submitted to the platform layer, the platform layer calls the corresponding micro-service and algorithm model through the micro-service API gateway according to the request, and the detailed description of the needed computing resource is issued to the resource layer through the micro-service.
Step 6, carrying out distributed resource scheduling, and distributing proper edge computing resources to proper tasks in a micro-service mode
And the resource layer performs fine scheduling of calculation power, bandwidth and storage according to the detailed description of the required edge calculation resources, and allocates the appropriate resources to the appropriate edge calculation tasks. The process is to provide a 'menu' resource scheduling scheme service by combining the current resource pool condition and pre-formulating a series of scheduling schemes and combinations thereof based on a distributed resource scheduling algorithm aiming at the typical traffic edge calculation task characteristic, shield trivial and variable resource scheduling details for upper-layer application and realize the acceleration and optimization of scheduling. The scheduling scheme set is configured on each distributed edge computing node in advance, has the characteristics of dynamics, flexibility, scene directivity, resource correlation and the like, and is the core of a scheduling strategy. Generally, a CPU (Central Processing Unit) is suitable for tasks such as decision control and rule management, a GPU (Graphics Processing Unit) is suitable for tasks requiring massively parallel computation such as AI training and target detection, a DSP (Digital Signal Processing) is suitable for image and video Processing, an FPGA (Field Programmable Gate Array) is suitable for tasks such as multi-source information fusion, video segmentation, target tracking and event prediction, and has a Programmable and easily-upgradable property, and an ASIC (Application Specific Integrated Circuit) is suitable for tasks such as powerful, mature and stable customized vision Processing and AI algorithm tasks. Such as NPU (Neural-network Processing Unit) and TPU (temporal Processing Unit), belong to ASIC processors for AI deep learning. For the MEC at the vehicle end, since the MEC is in a high-speed motion state and the allocated moving bandwidth resource is limited, the computing resource is preferentially allocated to the vehicle in principle. If an intelligent internet vehicle supporting the architecture is arranged nearby, edge resources can support sharing, but network fast switching caused by vehicle movement needs to be considered, and resources should support fast allocation and unloading. For the roadside MEC, the resource scheduling range supported by the roadside MEC is generally within the signal coverage range of the RSU, and is generally used for scene calculation such as roadside video analysis, laser radar point cloud processing algorithm, high-precision map matching and the like, and support to provide calculation resources from the roadside to the vehicle end, so that cooperative auxiliary driving and automatic driving support of the vehicle and vehicle end calculation force are realized, and vehicle end calculation force is less utilized. In addition, two networking modes, namely wireless networking mode and wired networking mode, are arranged between the road side MEC and the base station MEC, the positions are fixed, the sharing of computing power, bandwidth and storage resources is easy to realize, and more flexible resource scheduling can be realized. For example, short-period, low-delay, strong-locality scene computation may be performed at the roadside MEC, and long-period, medium-delay, weak-locality scene computation may be performed at the base station MEC. As another example, the training and modeling process in the AI scenario can be completed at the base station MEC, while the inference process with strong real-time performance is completed at the roadside MEC. The base station MEC is usually a server of an x86 architecture or a virtualized edge cloud, the architecture is relatively single, resources are relatively rich, and the base station MEC can play a role of a certain 'resource buffer area', a 'regional field scheduling center' and a 'security authentication center' in the architecture. Due to the feature of resource virtualization, the above scheduling process is transparent to the end user.
Taking an intersection anti-collision scene as an example, the edge calculation tasks related to the scene generally comprise main vehicle motion state perception, motor vehicles, non-motor vehicles and pedestrian target detection and identification on an intersection road, motion parameter extraction, track prediction, collision early warning, event reporting and storage and the like. Most tasks have high requirements on time delay and safety. At the moment, the motion state perception of the main vehicle is suitable for directly collecting vehicle computer data by a vehicle end OBU and sending the data to an RSU, the computational power consumption of motor vehicles, non-motor vehicles and pedestrians on an intersecting road is large, the time delay requirement is high, the fusion perception of data such as roadside videos and millimeter wave radars, map matching data and vehicle end OBU reporting data is suitable for being carried out by a roadside MEC, the result is broadcasted to roadside vehicles, and the main vehicle sends early warning to drivers after receiving the broadcast. When a collision event cannot be avoided, event original data needs to be uploaded to a cloud control platform, the task belongs to bandwidth sensitive and storage occupation tasks, but the time delay requirement can be relaxed, and the calculation priority is lower. In addition, the dynamic update of the map data belongs to a time delay insensitive, long-period and burst transmission task, and can be issued to the road side MEC by the cloud control platform or the base station MEC at regular time.
The edge computing task in the urban road C-V2X network has the characteristics of strong real-time performance, high concurrency and multiple functions, has higher requirements on the waiting time, the service quality, the load balance, the resource utilization rate and the like of edge computing, and the traditional resource scheduling algorithm cannot meet the requirements.
The invention adopts a weighting method to carry out optimized scheduling on resources, combines the scheduling characteristics under different scenes of vehicle-road cooperation, and uses a selection model to convert the scheduling problem into a multi-attribute decision problem, thereby realizing real-time dynamic scheduling.
Aiming at the scheduling strategies, a distributed resource scheduling algorithm is designed as follows:
step 6.1, initializing a queue, dividing the edge calculation task into 6 queues according to task characteristics, wherein the queue where the time delay sensitive task is located is r1R is the queue where the security sensitive task is located2The queue where the bandwidth sensitive task is located is r3For computing power consumption type tasksThe queue is r4The queue where the storage occupation type task is positioned is r5And the queue where the heterogeneous cooperative task is positioned is r6When each queue is initialized, a fixed length (the total number of requests in the queue) n is distributed, a large part of message request frequency in the Internet of vehicles is fixed, and a value of n is determined according to the known fixed message request frequency and the estimated random message request frequency in combination with scene requirements; different types of requests enter different queues in parallel.
And 6.2, presetting the priority of each queue, and preferentially distributing resources to the queue with high authority. According to the resource demand characteristics of the vehicle-road cooperative task, sequentially defining the priority of each type as r1>r2>r3＝r4＝r5＝r6I.e. the system priority processing queue r1The request of (1). In receiving requests, if the highest priority queue reaches the allocated length, it is merged with the next-priority queue, i.e., the requests in queues r1 and r2 use 2n length together; if a queue is empty in a set time interval, merging the queue with the highest priority, namely temporarily canceling the priority in a specified time interval and increasing the length of the request queue with the highest priority; and after the request in the highest priority queue is completely processed, processing the next priority queue. In this way, the success rate of high priority requests is improved.
6.3, determining the scheduling sequence of different requests in the same queue;
step 6.3.1, defining typical QoS model indexes of the edge computing system, wherein the model indexes comprise computation time, transmission time, scheduling time, bandwidth overhead, computational resource, storage resource, safety requirement and authority indexes;
step 6.3.2, define vector S ═ S1,s2,...,si,...,snThe request service set in a certain queue is used as the index, n is the number of requests, and i is more than or equal to 1 and less than or equal to n; vector Q ═ Q1,q2,...,qj,...,qmThe index set is a QoS model index set, m is the total number of QoS model indexes, and j is more than or equal to 1 and less than or equal to m; the weight matrix is P ═ P (P)ij)n×m，pijThe importance requirement of the ith request in the queue on the jth QoS index is represented, the weight can be determined through an expert evaluation method, and the weight can be adjusted according to the actual scene requirement in application.
Step 6.3.3, normalization processing is performed on the weight matrix to obtain a calculation matrix Y (Y ═ Y)ij)n×m：
Wherein the content of the first and second substances,
maxp.j＝max{pij},1≤i≤n，minp.j＝min{pij},1≤i≤n；
step 6.3.4, calculate the information entropy H of the ith requestiComprises the following steps:
step 6.3.5, calculate the evaluation index w of the ith requestiComprises the following steps:
step 6.3.6, the requests of each queue are all according to the evaluation index wiAnd (5) sequencing in a descending manner to obtain the scheduling sequences of different requests.
And 6.4, sequentially carrying out resource allocation processing on the requests in each queue according to the scheduling sequence.
And 7, completing the task and releasing the resources. And after the edge calculation task is completed, deleting the corresponding container and the mirror image thereof, and releasing the occupied resources in time.
The present invention provides an edge computing system based on the urban road C-V2X oriented network, and the method and the way for implementing the architecture are many, the above description is only one of the embodiments of the present invention, it should be noted that, for those skilled in the art, many modifications and embellishments can be made without departing from the principle of the present invention, and these should be regarded as the protection scope of the present invention. The components not specified in the present embodiment can be realized by the prior art.
Claims (10)
1. An edge computing system facing an urban road C-V2X network comprises an infrastructure layer, a network layer, a resource layer, a platform layer, a scene layer and a service application layer, and is characterized in that the infrastructure layer comprises vehicle end MEC units, roadside MEC units and base station MEC units, and the MEC units are connected with a wired network through a C-V2X network to form a vehicle, road and station integrated deployment architecture; edge computing tasks are processed among the MEC units through distributed resource allocation and scheduling strategies;
the vehicle-end MEC unit comprises a special vehicle-mounted MEC terminal, a vehicle-mounted computer and a vehicle-mounted OBU, wherein the special vehicle-mounted MEC terminal, the vehicle-mounted computer and the vehicle-mounted OBU are deployed at a vehicle end and are used for processing edge calculation tasks on a road, which are close to a vehicle target;
the roadside MEC unit comprises a portable computer which is arranged on a roadside signal lamp pole, a monitoring pole, a special upright post and a case and is used for processing edge calculation tasks of more than two traffic targets in a road junction and a road section from the roadside;
the base station MEC unit comprises a general edge computing server deployed in a cellular network base station machine room and used for processing edge computing tasks of a large number of traffic targets related to situation awareness and cooperative control in a base station coverage area;
the distributed resource allocation and scheduling strategy refers to a strategy for performing distributed configuration and management on all edge computing resources in a C-V2X network and a wired network, wherein the edge computing resources comprise computing power, bandwidth and storage;
the edge calculation tasks comprise traffic target detection and identification, traffic event discovery and prediction, traffic scene fusion analysis and processing, local traffic situation comprehensive perception and auxiliary and automatic driving decision tasks in task categories.
2. The edge computing system of claim 1, wherein the dedicated on-board MEC terminal comprises a lightweight edge computing device dedicated to vehicle sensing data analysis processing and simple fusion computing, the lightweight edge computing device having an external interface through which to interface with on-board cameras, millimeter wave radar, lidar, ultrasonic radar, CAN bus, Beidou/GPS positioning, and on-board OBU devices; the computing power of the lightweight edge computing equipment supports fusion processing of original data sensed by the butted vehicle-mounted camera, the millimeter wave radar, the laser radar, the ultrasonic radar, the CAN bus and the Beidou/GPS positioning equipment, real-time traffic target detection and identification are completed, the characteristics of the distance, the speed, the direction, the acceleration, the contour, the color and the license plate number of the target are included, and the data are transmitted to a vehicle-mounted OBU in a structured data form;
the vehicle-mounted computer comprises a vehicle gauge-level special computer, the vehicle gauge-level special computer is installed in front of a vehicle factory, software and hardware are relatively closed, and the vehicle gauge-level special computer is used for carrying out real-time dynamic monitoring and fault detection and early warning on the working state of a vehicle;
the vehicle-mounted OBU comprises vehicle-mounted special vehicle-mounted communication equipment which adopts a C-V2X technology and has edge calculation force, and the edge calculation force of the vehicle-mounted special vehicle-mounted communication equipment can be matched with a special vehicle-mounted MEC terminal to cooperatively complete a vehicle-end edge calculation task; the vehicle-mounted OBU can interact data of the vehicle-end MEC unit with the base station MEC unit through the cellular network, and interact with other vehicle-end MEC units and road-side MEC units through the V2X network.
3. The edge computing system of claim 1, wherein the roadside MEC units interface with RSUs, roadside cameras, millimeter wave radars, lidar, message boards/inductive screens, beidou/GPS, semaphores, meteorological sensors and environmental sensors through ethernet switches, and connect with base station MEC units through optical fibers or cellular networks.
4. The edge computing system facing the urban road C-V2X network according to claim 1, wherein the resource layer includes a heterogeneous resource sublayer, a resource configuration sublayer and a resource scheduling sublayer, the heterogeneous resource sublayer includes a unified representation of heterogeneous processors, network bandwidth and storage resources involved in edge computing, and the resource configuration sublayer performs virtualization configuration management including a virtual machine mode and a containerization mode; the resource scheduling sublayer performs resource calculation, resource scheduling, resource isolation, scheduling optimization, job queue management, load balancing, virtual machine migration and resource unloading according to the characteristics of the edge calculation task;
the platform layer deploys micro-services according to the requirements on real-time performance, safety and heterogeneous computing of each MEC unit, and the platform layer support component comprises service registration, service discovery, a service gateway, service arrangement, API management, an integrated framework, distributed management and a calling chain; the platform layer also provides traffic AI algorithm support and safety certification;
the scene layer provides calculation support for intelligent network connection edge scenes including traffic safety, traffic efficiency, travel service and automatic driving and can be elastically expanded according to requirements;
the service application layer is cooperated with the cloud service application layer on the basis of scene layer service, and provides intelligent network connection and intelligent traffic service application including bus priority, holographic intersection, traffic sequencing, digital twinning, signal optimization and free flow charging for traffic managers, traffic transportation industries and driver users.
5. The edge computing system facing urban road C-V2X network according to claim 4, wherein the distributed resource allocation and scheduling strategy comprises:
step 1, determining service application, and determining related traffic participation objects and action ranges of the service application;
step 2, dividing edge scenes, and dividing the determined service application into different edge scene application combinations;
step 3, analyzing detailed characteristics of the edge scene application, wherein the detailed characteristics comprise application properties, event types, high-precision map and positioning requirements, time delay requirements, reliability requirements, transmission bandwidth requirements, message periods, data packet sizes, data types, AI requirements, multi-source fusion requirements, decision and control requirements, road characteristics, target motion characteristics, static characteristics and environmental and meteorological influences of the edge scene application;
step 4, determining an edge calculation task, and determining an edge calculation task for realizing an edge scene according to the detailed characteristics of the application of the edge scene;
step 5, determining the detailed description of the edge computing resources, submitting an edge computing task request to a platform layer, calling a corresponding micro-service and algorithm model by the platform layer through a micro-service API gateway according to the request, and issuing the detailed description of the needed computing resources to a resource layer through the micro-service;
and 6, performing distributed resource scheduling, wherein the resource layer performs fine scheduling of calculation power, bandwidth and storage according to the detailed description of the required edge calculation resources, and allocates the appropriate resources to the appropriate edge calculation tasks.
6. The urban road C-V2X network-oriented edge computing system according to claim 5, wherein the edge computing tasks include delay-sensitive, security-sensitive, bandwidth-sensitive, power-consuming, storage-occupied, and heterogeneous collaborative tasks in terms of task characteristics.
7. The urban road C-V2X network-oriented edge computing system according to claim 6, wherein distributed resource scheduling is performed, and by integrating the existing resource pool conditions, scheduling schemes and combinations thereof based on a distributed resource scheduling algorithm are pre-formulated for the difference of task characteristics of edge computing tasks, providing menu-type resource scheduling scheme services; for the vehicle end MEC unit, the computing resources are preferentially allocated to the vehicle; for the roadside MEC unit, the resource scheduling range supported by the roadside MEC unit is within the signal coverage range of the RSU, and the roadside MEC unit is used for scene calculation including roadside video analysis, laser radar point cloud processing algorithm and high-precision map matching, and supporting the provision of calculation resources from the roadside to the vehicle end, so that cooperative auxiliary driving and automatic driving support of the vehicle are realized; and for the base station MEC unit, the method is used for scene calculation of long period, medium time delay and weak locality.
8. The edge computing system facing the urban road C-V2X network according to claim 7, wherein the distributed resource scheduling algorithm comprises:
step 6.1, initializing a queue, dividing the edge calculation task into 6 queues according to task characteristics, wherein the queue where the time delay sensitive task is located is r1R is the queue where the security sensitive task is located2The queue where the bandwidth sensitive task is located is r3The queue where the computing power consumption type task is located is r4The queue where the storage occupation type task is positioned is r5And the queue where the heterogeneous cooperative task is positioned is r6Each queue is allocated with a fixed length when being initialized; edge computing task requests with different task characteristics enter corresponding queues in parallel;
step 6.2, setting the priority of each queue, preferentially distributing resources to the queue with high authority, and defining the priority of each queue as r1>r2>r3＝r4＝r5＝r6I.e. the system priority processing queue r1The request of (1); in the process of receiving the request, if the queue with the highest priority reaches the distribution length, merging the queue with the next-priority queue; if a certain queue is empty in a set time interval, merging the queue with the highest priority; after the request in the highest priority queue is completely processed, processing the next priority queue;
6.3, determining the scheduling sequence of different requests in the same queue;
and 6.4, sequentially carrying out resource allocation processing on the requests in each queue according to the scheduling sequence.
9. An edge computing system facing a C-V2X network for urban roads according to claim 8, wherein the step 6.3 comprises:
step 6.3.1, defining QoS model indexes of the edge computing system, wherein the model indexes comprise computing time, transmission time, scheduling time, bandwidth overhead, computational resources, storage resources, safety requirements and permission indexes;
step 6.3.2, define vector S ═ S1,s2,...,si,...,snThe request service set in a certain queue is used as the index, n is the number of requests, and i is more than or equal to 1 and less than or equal to n; vector Q ═ Q1,q2,...,qj,...,qmThe index set is a QoS model index set, m is the total number of QoS model indexes, and j is more than or equal to 1 and less than or equal to m; the weight matrix is P ═ P (P)ij)n×m，pijRepresenting the importance requirement of the ith request in the queue on the jth QoS index;
step 6.3.3, normalization processing is performed on the weight matrix to obtain a calculation matrix Y (Y ═ Y)ij)n×m：
Wherein the content of the first and second substances,
maxp.j＝max{pij},1≤i≤n，minp.j＝min{pij},1≤i≤n；
step 6.3.4, calculate the information entropy H of the ith requestiComprises the following steps:
step 6.3.5, calculate the evaluation index w of the ith requestiComprises the following steps:
step 6.3.6, the requests of each queue are all according to the evaluation index wiAnd (5) sequencing in a descending manner to obtain the scheduling sequences of different requests.
10. The edge computing system for the urban road C-V2X network according to claim 5, wherein after completing the distributed resource scheduling in step 6, that is, after completing the edge computing task, deleting the corresponding container and its mirror image, and releasing the occupied resources in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111213957.0A CN113965568B (en) | 2021-10-19 | 2021-10-19 | Edge computing system for urban road C-V2X network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111213957.0A CN113965568B (en) | 2021-10-19 | 2021-10-19 | Edge computing system for urban road C-V2X network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113965568A true CN113965568A (en) | 2022-01-21 |
| CN113965568B CN113965568B (en) | 2023-07-04 |
Family
ID=79465086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111213957.0A Active CN113965568B (en) | 2021-10-19 | 2021-10-19 | Edge computing system for urban road C-V2X network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113965568B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114501378A (en) * | 2022-03-06 | 2022-05-13 | 南京理工大学 | Special environment emergency communication method and system based on vehicle-road cooperation |
| CN114625174A (en) * | 2022-05-12 | 2022-06-14 | 之江实验室 | Vehicle-mounted unmanned aerial vehicle control method and device based on V2X |
| CN114637262A (en) * | 2022-03-10 | 2022-06-17 | 广东泰云泽科技有限公司 | Decision control method and system of intelligent factory digital twin information based on 5G drive |
| CN114648870A (en) * | 2022-02-11 | 2022-06-21 | 行云新能科技（深圳）有限公司 | Edge calculation system, edge calculation decision prediction method, and computer-readable storage medium |
| CN114724391A (en) * | 2022-03-30 | 2022-07-08 | 重庆长安汽车股份有限公司 | System and method for guiding vehicles on congested road section |
| CN115100866A (en) * | 2022-07-18 | 2022-09-23 | 北京邮电大学 | Vehicle-road cooperative automatic driving decision-making method based on hierarchical reinforcement learning |
| CN115632939A (en) * | 2022-12-23 | 2023-01-20 | 浩鲸云计算科技股份有限公司 | Automatic network selection and routing method for achieving multi-target achievement of computational power network |
| CN116308153A (en) * | 2023-03-01 | 2023-06-23 | 北京图安世纪科技股份有限公司 | Holographic intersection management system and method based on digital twinning |
| CN116405905A (en) * | 2022-12-20 | 2023-07-07 | 联通智网科技股份有限公司 | Information processing method, device, equipment and storage medium |
| CN116403402A (en) * | 2023-04-13 | 2023-07-07 | 交通运输部公路科学研究所 | Traffic state prediction method for urban intersection area in network environment |
| CN116887357A (en) * | 2023-09-08 | 2023-10-13 | 山东海博科技信息***股份有限公司 | Computing platform management system based on artificial intelligence |
| CN117939538A (en) * | 2024-03-21 | 2024-04-26 | 北京烽火万家科技有限公司 | Mobile Internet of things edge intelligent management multimode gateway |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190244521A1 (en) * | 2018-02-06 | 2019-08-08 | Cavh Llc | Intelligent road infrastructure system (iris): systems and methods |
| CN110621006A (en) * | 2019-09-27 | 2019-12-27 | 腾讯科技（深圳）有限公司 | Access processing method of user equipment, intelligent equipment and computer storage medium |
| US20200120182A1 (en) * | 2018-10-10 | 2020-04-16 | Verizon Patent And Licensing Inc. | Method and system for edge computing network interfacing |
| CN111554088A (en) * | 2020-04-13 | 2020-08-18 | 重庆邮电大学 | Multifunctional V2X intelligent roadside base station system |
| US20200296054A1 (en) * | 2019-03-11 | 2020-09-17 | Wipro Limited | Method and system for providing network resource sharing in multi-access edge computing (mec) network |
| CN112289059A (en) * | 2020-10-22 | 2021-01-29 | 中电智能技术南京有限公司 | Vehicle-road cooperative road traffic system |
| CN112309122A (en) * | 2020-11-19 | 2021-02-02 | 北京清研宏达信息科技有限公司 | Intelligent bus grading decision-making system based on multi-system cooperation |
| KR20210026171A (en) * | 2019-08-29 | 2021-03-10 | 인제대학교 산학협력단 | Multi-access edge computing based Heterogeneous Networks System |
| CN113347254A (en) * | 2021-06-02 | 2021-09-03 | 安徽工程大学 | Intelligent traffic control car networking system based on V2X and control method thereof |
-
2021
- 2021-10-19 CN CN202111213957.0A patent/CN113965568B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190244521A1 (en) * | 2018-02-06 | 2019-08-08 | Cavh Llc | Intelligent road infrastructure system (iris): systems and methods |
| US20200120182A1 (en) * | 2018-10-10 | 2020-04-16 | Verizon Patent And Licensing Inc. | Method and system for edge computing network interfacing |
| US20200296054A1 (en) * | 2019-03-11 | 2020-09-17 | Wipro Limited | Method and system for providing network resource sharing in multi-access edge computing (mec) network |
| KR20210026171A (en) * | 2019-08-29 | 2021-03-10 | 인제대학교 산학협력단 | Multi-access edge computing based Heterogeneous Networks System |
| CN110621006A (en) * | 2019-09-27 | 2019-12-27 | 腾讯科技（深圳）有限公司 | Access processing method of user equipment, intelligent equipment and computer storage medium |
| CN111554088A (en) * | 2020-04-13 | 2020-08-18 | 重庆邮电大学 | Multifunctional V2X intelligent roadside base station system |
| CN112289059A (en) * | 2020-10-22 | 2021-01-29 | 中电智能技术南京有限公司 | Vehicle-road cooperative road traffic system |
| CN112309122A (en) * | 2020-11-19 | 2021-02-02 | 北京清研宏达信息科技有限公司 | Intelligent bus grading decision-making system based on multi-system cooperation |
| CN113347254A (en) * | 2021-06-02 | 2021-09-03 | 安徽工程大学 | Intelligent traffic control car networking system based on V2X and control method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 林凡 等: "网联汽车智能管控云平台设计", 物联网技术, no. 09 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648870B (en) * | 2022-02-11 | 2023-07-28 | 行云新能科技（深圳）有限公司 | Edge computing system, edge computing decision prediction method, and computer-readable storage medium |
| CN114648870A (en) * | 2022-02-11 | 2022-06-21 | 行云新能科技（深圳）有限公司 | Edge calculation system, edge calculation decision prediction method, and computer-readable storage medium |
| CN114501378A (en) * | 2022-03-06 | 2022-05-13 | 南京理工大学 | Special environment emergency communication method and system based on vehicle-road cooperation |
| CN114637262B (en) * | 2022-03-10 | 2022-11-15 | 天津科技大学 | Decision control method and system of intelligent factory digital twin information based on 5G drive |
| CN114637262A (en) * | 2022-03-10 | 2022-06-17 | 广东泰云泽科技有限公司 | Decision control method and system of intelligent factory digital twin information based on 5G drive |
| CN114724391A (en) * | 2022-03-30 | 2022-07-08 | 重庆长安汽车股份有限公司 | System and method for guiding vehicles on congested road section |
| CN114625174A (en) * | 2022-05-12 | 2022-06-14 | 之江实验室 | Vehicle-mounted unmanned aerial vehicle control method and device based on V2X |
| CN115100866B (en) * | 2022-07-18 | 2023-08-18 | 北京邮电大学 | Vehicle-road cooperative automatic driving decision-making method based on layered reinforcement learning |
| CN115100866A (en) * | 2022-07-18 | 2022-09-23 | 北京邮电大学 | Vehicle-road cooperative automatic driving decision-making method based on hierarchical reinforcement learning |
| CN116405905A (en) * | 2022-12-20 | 2023-07-07 | 联通智网科技股份有限公司 | Information processing method, device, equipment and storage medium |
| CN116405905B (en) * | 2022-12-20 | 2024-01-30 | 联通智网科技股份有限公司 | Information processing method, device, equipment and storage medium |
| CN115632939A (en) * | 2022-12-23 | 2023-01-20 | 浩鲸云计算科技股份有限公司 | Automatic network selection and routing method for achieving multi-target achievement of computational power network |
| CN115632939B (en) * | 2022-12-23 | 2023-03-31 | 浩鲸云计算科技股份有限公司 | Automatic network selection and routing method for achieving multi-target achievement of computational power network |
| CN116308153A (en) * | 2023-03-01 | 2023-06-23 | 北京图安世纪科技股份有限公司 | Holographic intersection management system and method based on digital twinning |
| CN116308153B (en) * | 2023-03-01 | 2024-03-29 | 北京图安世纪科技股份有限公司 | Holographic intersection management system and method based on digital twinning |
| CN116403402A (en) * | 2023-04-13 | 2023-07-07 | 交通运输部公路科学研究所 | Traffic state prediction method for urban intersection area in network environment |
| CN116887357A (en) * | 2023-09-08 | 2023-10-13 | 山东海博科技信息***股份有限公司 | Computing platform management system based on artificial intelligence |
| CN116887357B (en) * | 2023-09-08 | 2023-12-19 | 山东海博科技信息***股份有限公司 | Computing platform management system based on artificial intelligence |
| CN117939538A (en) * | 2024-03-21 | 2024-04-26 | 北京烽火万家科技有限公司 | Mobile Internet of things edge intelligent management multimode gateway |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113965568B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113965568B (en) | Edge computing system for urban road C-V2X network | |
| CN111371904B (en) | Cloud-side-end-coordinated highway cloud control system and control method | |
| Liu et al. | High-efficiency urban traffic management in context-aware computing and 5G communication | |
| WO2016161676A1 (en) | Resource allocation system, base station, device, and method | |
| CN112466115A (en) | Bus intersection priority passing control system and method based on edge calculation | |
| Dai et al. | A scheduling algorithm for autonomous driving tasks on mobile edge computing servers | |
| CN112925657A (en) | Vehicle road cloud cooperative processing system and method | |
| EP3750145A2 (en) | Intelligent road infrastructure system (iris): systems and methods | |
| CN110491147B (en) | Traffic information processing method, traffic information processing device and terminal equipment | |
| Billhardt et al. | Dynamic coordination in fleet management systems: Toward smart cyber fleets | |
| Zhou et al. | Edge-facilitated augmented vision in vehicle-to-everything networks | |
| CN113808389A (en) | Vehicle-road cooperation system, edge computing unit, central cloud platform and information processing method | |
| EP3467800B1 (en) | Lane scheduling method, lane information acquisition method, vehicle and management device | |
| Elkin et al. | IoT in traffic management: review of existing methods of road traffic regulation | |
| Roopa et al. | Dynamic management of traffic signals through social IoT | |
| CN115116257A (en) | Vehicle scheduling method, device, equipment and medium based on edge cloud service | |
| CN107395757B (en) | Parallel vehicle networking system based on ACP method and social physical information system | |
| Agarwal et al. | EMVD: efficient multitype vehicle detection algorithm using deep learning approach in vehicular communication network for radio resource management | |
| Choudhary et al. | Novel algorithm for leader election process in virtual traffic light protocol | |
| Jurczenia et al. | A survey of vehicular network systems for road traffic management | |
| Xia et al. | Lane scheduling around crossroads for edge computing based autonomous driving | |
| Sharma et al. | Review of recent developments in sustainable traffic management system | |
| CN111143995B (en) | Traffic pollution emission mobile edge calculation scheduling method based on information physical system | |
| Xiao et al. | A hierarchical decision architecture for network-assisted automatic driving | |
| Zou et al. | Vehicle-based intersection management with intelligent agents |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |