CN113791899A - Edge server management system for mobile Web augmented reality - Google Patents
Edge server management system for mobile Web augmented reality Download PDFInfo
- Publication number
- CN113791899A CN113791899A CN202110985747.7A CN202110985747A CN113791899A CN 113791899 A CN113791899 A CN 113791899A CN 202110985747 A CN202110985747 A CN 202110985747A CN 113791899 A CN113791899 A CN 113791899A
- Authority
- CN
- China
- Prior art keywords
- edge
- server
- service
- mobile web
- edge server
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
Abstract
The invention discloses a mobile Web augmented reality-oriented edge server management system, which comprises: the server AR task scheduling module: the system is used for providing AR task scheduling based on GPS or calibration server position perception in a user mobile scene; edge server collaboration module: the method is used for the cooperative scheduling of services and resources among edge servers in an edge system; web AR service management Module: the method is used for performing centralized management of the mobile Web AR service in the edge server by using the edge server performance information, the task scheduling information, the load balancing information and the service migration information. The invention can position the edge mobile node and schedule the edge server resource and the mobile Web AR service, thereby providing the location-aware mobile Web AR service experience for the user.
Description
Technical Field
The invention relates to mobile Web augmented reality, in particular to an edge server management system for the mobile Web augmented reality.
Background
In recent years, the development of artificial intelligence and computer vision technologies has greatly promoted the application of AR technologies. The technology can seamlessly integrate virtual content into a real environment, and greatly enriches the interaction mode of a user and the real world through immersive visual experience.
The Web-based mobile AR technology not only provides convenience for users to experience AR services on mobile equipment, but also provides a uniform platform for development and deployment of mobile AR applications. However, achieving efficient AR service provisioning in 5G edge networks requires consideration of specific requirements for Web AR and mobility.
First, AR service subscribers are able to access AR services through their mobile devices anytime and anywhere during motion, and are no longer restricted to a particular area. Second, mobile Web AR, as a computationally intensive application, needs to consume a large amount of computing resources to provide a real-time immersive visual interactive experience for mobile users. Third, in hot-spot scenes such as sporting events, mall promotions, music festivals, etc., most AR virtual content is geo-location dependent and needs to be delivered to AR service subscribers in real-time.
Because the computing power of the mobile Web platform is weak, the existing mobile Web AR solution under the 5G network mostly utilizes the edge computing technology to realize the short-distance AR service provision, aims to avoid intensive data transmission to a cloud server, and can also alleviate the problem of high time delay of AR visual data in network transmission. However, the current edge-assisted mobile Web AR solution is mainly designed for a single edge server, and is difficult to cope with complex situations such as edge system distribution characteristics, edge node mobility, location-related AR content distribution, and changes in service request density caused by hot spot areas or events, thereby greatly limiting the user experience of the mobile Web AR.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a mobile Web augmented reality-oriented edge server management system which can position an edge mobile node and schedule edge server resources and mobile Web AR services, so that the mobile Web AR service experience of position perception is provided for a user.
The technical scheme of the invention is realized as follows:
an edge server management system facing mobile Web augmented reality, comprising:
the server performance detection module is used for periodically monitoring the calculation and network communication performance information of all edge servers in the management range;
the Web AR service function module is used for providing task processing capacity required by the mobile Web AR service;
the AR task scheduling module: the system is used for providing AR task scheduling based on GPS or calibration server position perception in a user mobile scene;
edge server collaboration module: the method is used for the cooperative scheduling of services and resources among edge servers in the edge system, balancing the mobile Web AR service query request of the edge server managed in the edge server system and the workload of AR calculation tasks, and carrying out migration operation on the mobile Web AR service based on the position information of a user and other requirements in the edge server system;
web AR service management Module: the method is used for performing centralized management of the mobile Web AR service in the edge server by using the edge server performance information, the task scheduling information, the load balancing information and the service migration information.
Further, the Web AR service function module includes: the mobile Web AR function service module is used for providing a bottom layer supporting function required by the mobile Web AR service, and the bottom layer supporting function comprises a feature extraction function, a target detection function, a target identification function and a template matching function; the AR virtual content management module is used for realizing management of AR virtual content which is stored in an edge server in a distributed mode, wherein the storage format of the AR virtual content which is stored in the distributed mode is position information, mobile Web AR service ID, AR virtual content data and access heat; and the mobile Web AR service maintenance and migration management module is used for communicating based on the Web Socket connection established by the edge server and the cloud server and managing AR service support functions and virtual content data deployed in the edge server.
Further, the AR task scheduling module includes: the edge node positioning module is used for providing positioning capacity of all edge nodes including mobile Web AR user terminal equipment and an edge server; and the mobile sensing server selection module is used for selecting a proper edge server in the edge server system according to the current position of the user so as to provide services.
Further, the edge node positioning module includes: a positioning mechanism module based on GPS method, which is used for providing positioning service directly based on GPS data provided by mobile user terminal equipment and edge nodes; and the positioning mechanism module based on the calibration server is used for realizing the positioning of the edge node based on the calibration server under the condition that the GPS data is unavailable.
Further, when the edge node based on the calibration server is positioned, the positioning mechanism module based on the calibration server calculates RTT values between the node and all calibration servers, and obtains a subscript sequence of the calibration server corresponding to the edge node according to the RTT values; and each edge node generates a respective hash value by means of a hash function, the prefix of each edge node is replaced by the obtained subscript sequence of the calibration server to obtain the hash value of each edge node, the distance between the two edge nodes is obtained by comparing the difference value of the hash values, and the positioning of the edge nodes is determined according to the judgment of the distance and the RTT value.
Further, when the calibration server-based positioning mechanism module obtains the subscript sequence of the calibration server corresponding to the edge node according to the RTT value, the subscript sequence of the calibration server corresponding to the edge node is obtained through the order of the RTT value from small to large or from large to small.
Further, when the positioning mechanism module based on the calibration server determines the positioning of the edge node according to the judgment of the distance and the RTT value, the edge node closest to the distance is determined through the judgment of the distance, and then the positioning of the calibration server is used as the positioning of the edge node according to the subscript sequence of the calibration server corresponding to the edge node.
Further, the edge server coordination module includes: the working load balancing module is used for balancing the mobile Web AR service query request of the managed edge server in the edge server system and the working load of the AR calculation task; and the service migration module is used for performing migration operation on the mobile Web AR service in the edge server system based on the position information of the user and other requirements.
Further, the workload balancing module comprises: the query request workload balancing module is used for carrying out Hash on the URL addresses of the mobile Web AR services to obtain Hash values, determining different computing capacities of each edge server according to the Hash values, distributing different numbers of mobile Web AR service query requests according to the different computing capacities of each edge server, and meanwhile, adjusting the upper limit value of the distribution interval of the mobile Web AR services in charge of each edge server to realize dynamic adjustment of the distribution of the mobile Web AR service query requests in an edge server system; and the AR computing task workload balancing module is used for periodically constructing all the edge servers into a maximum heap structure according to the computing performance of the edge servers, and distributing the AR computing tasks to the edge servers which can provide the strongest maximum heap structure in the selection process of the edge servers so as to provide auxiliary computing.
Optionally, the migration policy of the migration operation includes: selecting an edge server closest to the mobile Web AR user as a migration target; selecting a server with the minimum workload in the whole edge network as a target of service migration; acquiring the motion tracks of a large number of users in an edge network, analyzing to obtain a transition probability matrix accessed between edge servers, and selecting a service migration target according to the transition probability; and selecting a proper edge server as a service migration target by evaluating the requirements of the requested mobile Web AR service on resources such as a CPU (Central processing Unit), a memory and the like and the conditions of computing resources which can be provided by each edge server at present.
Has the advantages that: the invention is characterized in that the edge server for the mobile Web AR application is cooperated and managed to support the extensible high-quality mobile Web AR service provision. The system of the invention positions the edge nodes by means of landmark information to realize the management of dynamic changes of the edge network, including the dynamic changes of the position caused by the movement of the user and the dynamic changes of the AR service request. Secondly, while balancing the workload and managing the service quality, the system of the invention also considers the performance of the request service processing and the cost of the computation unloading, and utilizes a dynamic hash mechanism and a maximum heap mechanism to carry out efficient mobile Web AR service searching and computation workload management. Meanwhile, the system of the invention optimizes a plurality of performance factors such as message transmission efficiency, scheduling waiting time delay, mobile Web AR service migration accuracy and the like in the service migration scheme design. The system aims to optimize the application performance of the mobile Web AR through the collaborative design of the distributed edge network system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an edge server management system facing mobile Web augmented reality according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a mobile Web AR function service module according to an embodiment of the present invention;
FIG. 3 is a block diagram of an AR task scheduling module according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an edge server cooperation module according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
According to the embodiment of the invention, a mobile Web augmented reality-oriented edge server management system is provided.
As shown in fig. 1, the edge server management system facing to the mobile Web augmented reality according to the embodiment of the present invention includes:
the server performance detection module is used for periodically monitoring the calculation and network communication performance information of all edge servers in the management range;
the Web AR service function module is used for providing task processing capacity required by the mobile Web AR service;
the AR task scheduling module: the system is used for providing AR task scheduling based on GPS or calibration server position perception in a user mobile scene;
edge server collaboration module: the method is used for the cooperative scheduling of services and resources among edge servers in the edge system, balancing the mobile Web AR service query request of the edge server managed in the edge server system and the workload of AR calculation tasks, and carrying out migration operation on the mobile Web AR service based on the position information of a user and other requirements in the edge server system;
web AR service management Module: the method is used for performing centralized management of the mobile Web AR service in the edge server by using the edge server performance information, the task scheduling information, the load balancing information and the service migration information.
In practical application, for the server performance detection module, the server performance detection module can be used for monitoring the conditions of main frequency information, CPU, memory, storage space occupation and the like of each edge server so as to evaluate the computing capacity of the server; meanwhile, the module is further configured to periodically detect network attributes such as Round-Trip Time (RTT) and bandwidth, and even packet loss rate of data transmission between edge servers in the managed area, so as to evaluate communication cost of data in the edge server system.
For the Web AR service function module, all mobile Web AR service functions can be implemented in different ways, such as traditional computer vision based implementation and neural network based implementation. All functional modules can provide uniform service capability for AR application, but specific service capability can be provided according to different mobile Web AR service requirements. In addition, the AR virtual content management is only responsible for the distributed deployment and management of AR virtual data related to each mobile Web AR application in the managed area.
For the AR task scheduling module, the mobile user terminal device may be connected to the edge server through a Web Socket or other technology, and when the edge server receives an AR service request sent by a mobile user, the edge server will first locate the edge node through a GPS or calibration server-based manner, where the location information of the edge node may be actual geographic location information based on GPS data, or a relative location in a coordinate system constructed by the calibration server. The request is then forwarded to the designated edge server by means of the mobility-aware server selection module.
For the edge server cooperation module, the distribution condition of each mobile Web AR service in the edge server system is dynamically adjusted by periodically monitoring the computing performance and the network communication performance of each edge server, so that the balance of the working load in the edge server system is realized; on the other hand, for the situation that the user is constantly moving in the process of accessing the mobile Web AR service, the mobile Web AR service needs to be migrated in the edge server system according to the situation of the moving position of the user equipment.
For the Web AR service management module, the module performs centralized management of the mobile Web AR service in the edge server based on the edge server performance information, task scheduling information, load balancing information, and service migration information monitored by the edge server management system, including operations such as deployment decision and update of the service.
As shown in fig. 2, in a specific application, the Web AR service function module includes: the mobile Web AR function service module is used for providing a bottom layer supporting function required by the mobile Web AR service, and the bottom layer supporting function comprises a feature extraction function, a target detection function, a target identification function and a template matching function; the AR virtual content management module is used for realizing management of AR virtual content which is stored in an edge server in a distributed mode, wherein the storage format of the AR virtual content which is stored in the distributed mode is position information, mobile Web AR service ID, AR virtual content data and access heat; and the mobile Web AR service maintenance and migration management module is used for communicating based on the Web Socket connection established by the edge server and the cloud server and managing AR service support functions and virtual content data deployed in the edge server.
In practical application, the Web AR service function module adds service support functions facing mobile Web AR application, such as feature extraction, target detection, target identification, template matching and the like, on the basis of the existing edge server general function. Each support function can be implemented in a number of different ways, including traditional image processing-based ways and neural network-based ways. Specifically, considering that the time complexity and the space complexity of each different implementation mode are different, the mobile Web AR service maintenance and migration management module may also select to download different mobile Web AR functions to provide services according to the calculation and storage capabilities of the current edge server through the Web Socket connection established with the cloud server. In addition, the selection of different service function implementations also depends on the requirements of the particular service for the processing efficiency and accuracy of the respective functions. In addition, the AR virtual content management module is used for realizing the management of the AR virtual content which is distributed and stored in the edge server. Specifically, in the edge server database, all the AR virtual contents are stored in the form of "location information + mobile Web AR service ID + AR virtual content data + access heat", and since the AR virtual contents are usually huge in data volume and it is difficult to store all the data contents in a single edge server, a distributed data storage manner is usually adopted in the edge server system, which also benefits from the service characteristics of the mobile Web AR application that are strongly related to the geographical location, and therefore, the data storage efficiency can be effectively improved. On the other hand, by recording the request heat of each AR virtual content data, a popularity-based data sorting mechanism can be further realized, and the overall response efficiency of the AR service is further improved. The mobile Web AR service maintenance and migration management module is mainly used for managing AR service support functions and virtual content data deployed in the edge server. The module is used for carrying out communication based on Web Socket connection established by the edge server and the cloud server, and updating a mobile Web AR service function and AR virtual content data deployed in the edge server by receiving a service and data management instruction sent by the cloud server.
As shown in fig. 3, in a specific application, the AR task scheduling module includes: (1) the edge node positioning module is used for providing positioning capacity of all edge nodes including mobile Web AR user terminal equipment and an edge server; (2) and the mobile sensing server selection module is used for selecting a proper edge server in the edge server system according to the current position of the user. Specifically, the edge node positioning module may directly provide the location information of the corresponding edge node in the case that the mobile user terminal device and the edge server GPS data are available;
in addition, in the case that the edge node GPS data cannot be provided due to privacy problems, the edge node can be located by a predefined calibration server in the edge system. In particular, if the GPS data of the calibration servers are provided, the calibration servers can be used to form a uniform reference coordinate system of the edge server system, and the position information of the edge nodes can be analyzed and inferred through the known proportion relation between the actual distance and RTT between the edge nodes,
in particular, two edge nodes that are far apart tend to have high round-trip transmission delays for packets. In addition, when the GPS data of the calibration server cannot be provided, all edge nodes may first calculate RTT values between the node and all calibration servers, and obtain a subscript sequence of the calibration server corresponding to the edge node in the order from small RTT value to large RTT value or from large RTT value to small RTT value, and at the same time, each edge node generates a respective hash value by means of a hash function (e.g., MD5, SHA-256, etc.), and replaces the prefix of the hash value with the obtained subscript sequence of the calibration server, thereby obtaining the hash value of each edge node. Obviously, edge nodes that are closer in distance will be more likely to send data packets to the same edge server over the same/close network transmission path. Meanwhile, the distance between any two edge nodes can be calculated by using the difference value of the corresponding hash values. The scheme can ensure the randomness of the distribution of all edge node hash values and can also ensure that the hash values distributed by two edge nodes with similar physical distances have a closer distance, thereby achieving the purpose of edge node positioning. Since the request of the mobile Web AR user is usually related to the location, after obtaining the location information of all nodes, the mobile-aware server selection module can select a suitable edge server for the mobile user to access the edge system according to the location information.
As shown in fig. 4, in a specific application, the edge server cooperation module is mainly divided into two modules, including: (1) the work load balancing module is used for balancing the load of the mobile Web AR service query request and the load of the AR computing task in the edge server system; (2) a service migration module: the method is used for carrying out migration operation on the mobile Web AR service in the edge server system based on the position information and other requirements of the user.
Specifically, the workload balancing module is configured to balance a mobile Web AR service query request of the managed edge server in the edge server system and a workload of an AR computing task. The service query request load balancing mechanism can adopt a scheme based on dynamic hash, namely hash is carried out on URL addresses of the mobile Web AR services, so that different quantities of mobile Web AR services are distributed according to different computing capacities of the edge servers; the edge server with higher computing power can inquire more mobile Web AR service requests. In addition, aiming at the condition that the computing capacity of the edge server dynamically changes, the distribution mode of the mobile Web AR service can be dynamically adjusted, so that the purpose of load balancing of the service query request is achieved. Specifically, each edge server in the edge server system is allocated with a specific interval for representing the mobile Web AR service which is responsible for processing, and dynamic adjustment of the allocation of the mobile Web AR service query request in the edge server system can be realized by adjusting the upper limit value of each pickup. On the other hand, the load balancing mechanism of the AR computing task may adopt a maximum heap scheme, that is, periodically construct all edge servers into a maximum heap structure according to their computing performance, and in the selection process of the edge servers, the system may allocate the AR computing task to the edge server that can provide the AR computing service and has the strongest computing capability to provide the auxiliary computing.
In the edge server cooperation module, the service migration module is designed to mainly deal with the problem of continuous service provision caused by the movement of the mobile Web AR user. In particular, the module may provide migration services according to different policies. For example, the edge server closest to the mobile Web AR user may be selected as the migration target, or the server with the smallest workload in the entire edge network may be selected as the target of service migration. In addition, a transition probability matrix accessed between edge servers can be obtained by collecting the motion tracks of a large number of users in the edge network and analyzing, so that the target of service migration is turned according to the transition probability, namely, a service migration mechanism based on a discrete time Markov chain. In addition, the requirements of the requested mobile Web AR service on resources such as CPUs, memories and the like and the conditions of computing resources which can be provided by each edge server at present can be evaluated, so that an appropriate edge server can be selected as a target of service migration. The module mainly provides a migration scheme of the mobile Web AR service in the edge server system, and because the complexity of each different service migration scheme is different, the migration processing time delay and the migration precision of the service are different, so that a mobile Web AR service provider needs to select different service migration schemes according to different service migration requirements.
In summary, with the above technical solution of the present invention, the system of the present invention locates the edge node by using the landmark information to implement management of dynamic changes of the edge network, including dynamic changes of the location due to the user movement and dynamic changes of the AR service request. Secondly, while balancing the workload and managing the service quality, the system of the invention also considers the performance of the request service processing and the cost of the computation unloading, and utilizes a dynamic hash mechanism and a maximum heap mechanism to carry out efficient mobile Web AR service searching and computation workload management. Meanwhile, the system of the invention optimizes a plurality of performance factors such as message transmission efficiency, scheduling waiting time delay, mobile Web AR service migration accuracy and the like in the service migration scheme design. The system aims to optimize the application performance of the mobile Web AR through the collaborative design of the distributed edge network system.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An edge server management system for mobile Web augmented reality, comprising:
the server performance detection module is used for periodically monitoring the calculation and network communication performance information of all edge servers in the management range;
the Web AR service function module is used for providing task processing capacity required by the mobile Web AR service;
the AR task scheduling module: the system is used for providing AR task scheduling based on GPS or calibration server position perception in a user mobile scene;
edge server collaboration module: the method is used for the cooperative scheduling of services and resources among edge servers in the edge system, balancing the mobile Web AR service query request of the edge server managed in the edge server system and the workload of AR calculation tasks, and carrying out migration operation on the mobile Web AR service based on the position information of a user and other requirements in the edge server system;
web AR service management Module: the method is used for performing centralized management of the mobile Web AR service in the edge server by using the edge server performance information, the task scheduling information, the load balancing information and the service migration information.
2. The edge server management system for mobile Web-oriented augmented reality of claim 1, wherein the Web AR service function module comprises:
the mobile Web AR function service module is used for providing a bottom layer supporting function required by the mobile Web AR service, and the bottom layer supporting function comprises a feature extraction function, a target detection function, a target identification function and a template matching function;
the AR virtual content management module is used for realizing management of AR virtual content which is stored in an edge server in a distributed mode, wherein the storage format of the AR virtual content which is stored in the distributed mode is position information, mobile Web AR service ID, AR virtual content data and access heat;
and the mobile Web AR service maintenance and migration management module is used for communicating based on the Web Socket connection established by the edge server and the cloud server and managing AR service support functions and virtual content data deployed in the edge server.
3. The mobile Web-augmented reality-oriented edge server management system of claim 1, wherein the AR task scheduling module comprises:
the edge node positioning module is used for providing positioning capacity of all edge nodes including mobile Web AR user terminal equipment and an edge server;
and the mobile sensing server selection module is used for selecting a proper edge server in the edge server system according to the current position of the user so as to provide services.
4. The mobile Web-augmented reality-oriented edge server management system of claim 3, wherein the edge node location module comprises:
a positioning mechanism module based on GPS method, which is used for providing positioning service directly based on GPS data provided by mobile user terminal equipment and edge nodes;
and the positioning mechanism module based on the calibration server is used for realizing the positioning of the edge node based on the calibration server under the condition that the GPS data is unavailable.
5. The edge server management system for mobile Web-oriented augmented reality according to claim 4, wherein the calibration server-based positioning mechanism module calculates RTT values between the edge node and all calibration servers when the edge node based on the calibration server is positioned, and obtains a subscript sequence of the calibration server corresponding to the edge node according to the RTT values; and each edge node generates a respective hash value by means of a hash function, the prefix of each edge node is replaced by the obtained subscript sequence of the calibration server to obtain the hash value of each edge node, the distance between the two edge nodes is obtained by comparing the difference value of the hash values, and the positioning of the edge nodes is determined according to the judgment of the distance and the RTT value.
6. The edge server management system for mobile Web-oriented augmented reality according to claim 5, wherein when the positioning mechanism module based on the calibration server obtains the subscript sequence of the calibration server corresponding to the edge node according to the RTT value, the subscript sequence of the calibration server corresponding to the edge node is obtained through the order of the RTT value from small to large or from large to small.
7. The edge server management system for mobile Web-oriented augmented reality according to claim 5, wherein when the location mechanism module based on the calibration server determines the location of the edge node according to the judgment of the distance and the RTT value, the edge node closest to the distance is determined through the judgment of the distance, and then the location of the calibration server is used as the location of the edge node according to the subscript sequence of the calibration server corresponding to the edge node.
8. The edge server management system for mobile Web-oriented augmented reality of claim 1, wherein the edge server coordination module comprises:
the working load balancing module is used for balancing the mobile Web AR service query request of the managed edge server in the edge server system and the working load of the AR calculation task;
and the service migration module is used for performing migration operation on the mobile Web AR service in the edge server system based on the position information of the user and other requirements.
9. The mobile Web-augmented reality-oriented edge server management system of claim 8, wherein the workload balancing module comprises:
the query request workload balancing module is used for carrying out Hash on the URL addresses of the mobile Web AR services to obtain Hash values, determining different computing capacities of each edge server according to the Hash values, distributing different numbers of mobile Web AR service query requests according to the different computing capacities of each edge server, and meanwhile, adjusting the upper limit value of the distribution interval of the mobile Web AR services in charge of each edge server to realize dynamic adjustment of the distribution of the mobile Web AR service query requests in an edge server system;
and the AR computing task workload balancing module is used for periodically constructing all the edge servers into a maximum heap structure according to the computing performance of the edge servers, and distributing the AR computing tasks to the edge servers which can provide the strongest maximum heap structure in the selection process of the edge servers so as to provide auxiliary computing.
10. The edge server management system for mobile Web-oriented augmented reality of claim 8, wherein the migration policy of the migration operation comprises:
selecting an edge server closest to the mobile Web AR user as a migration target;
selecting a server with the minimum workload in the whole edge network as a target of service migration;
acquiring the motion tracks of a large number of users in an edge network, analyzing to obtain a transition probability matrix accessed between edge servers, and selecting a service migration target according to the transition probability;
and selecting a proper edge server as a service migration target by evaluating the requirements of the requested mobile Web AR service on resources such as a CPU (Central processing Unit), a memory and the like and the conditions of computing resources which can be provided by each edge server at present.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110985747.7A CN113791899A (en) | 2021-08-26 | 2021-08-26 | Edge server management system for mobile Web augmented reality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110985747.7A CN113791899A (en) | 2021-08-26 | 2021-08-26 | Edge server management system for mobile Web augmented reality |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113791899A true CN113791899A (en) | 2021-12-14 |
Family
ID=78876573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110985747.7A Pending CN113791899A (en) | 2021-08-26 | 2021-08-26 | Edge server management system for mobile Web augmented reality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113791899A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023158284A1 (en) * | 2022-02-21 | 2023-08-24 | 삼성전자 주식회사 | Method and device for optimizing augmented reality service performance |
-
2021
- 2021-08-26 CN CN202110985747.7A patent/CN113791899A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023158284A1 (en) * | 2022-02-21 | 2023-08-24 | 삼성전자 주식회사 | Method and device for optimizing augmented reality service performance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220107848A1 (en) | Edge service providing method and apparatus, and device | |
| Gomes et al. | Edge caching with mobility prediction in virtualized LTE mobile networks | |
| US11445039B2 (en) | Method and apparatus for providing edge computing services | |
| Xu et al. | Optimal information centric caching in 5G device-to-device communications | |
| US9503308B2 (en) | Method, device and system for processing content | |
| CN107517228B (en) | Dynamic acceleration method and device in content distribution network | |
| CN110769038B (en) | Server scheduling method and device, storage medium and electronic equipment | |
| JP7037511B2 (en) | Base stations, access request response methods, equipment and systems | |
| CN103339522B (en) | Peer-to-peer location service | |
| CN113596191B (en) | Data processing method, network element equipment and readable storage medium | |
| CN109327542B (en) | Game service access response method, request forwarding method, connection method and device | |
| CN113596863B (en) | Method, equipment and medium for determining user plane function and providing information | |
| KR20210119504A (en) | Communication method and apparatus, entity and computer readable storage medium | |
| CN114902634A (en) | Apparatus and method for providing information of application server in mobile communication system | |
| Shaheen et al. | A lightweight location-aware fog framework (LAFF) for QoS in Internet of Things paradigm | |
| US20160269297A1 (en) | Scaling the LTE Control Plane for Future Mobile Access | |
| CN113791899A (en) | Edge server management system for mobile Web augmented reality | |
| Ren et al. | Distributed edge system orchestration for web-based mobile augmented reality services | |
| Kottursamy et al. | Optimized D-RAN aware data retrieval for 5G information centric networks | |
| CN111600929B (en) | Transmission line detection method, routing strategy generation method and proxy server | |
| Yang et al. | A network-embedding-based approach for scalable network navigability in content-centric social IoT | |
| KR20200130186A (en) | Method and apparatus for acquiring and managing location information of mobile terminal in an edge computing system | |
| US10862858B2 (en) | Information centric approach in achieving anycast in machine type communications | |
| EP3491790B1 (en) | A hybrid approach with classification for name resolution and producer selection in icn | |
| WO2021197446A1 (en) | Positioning method, device, and system, and storage medium |
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 |