WO2024066626A1 - 实时音视频网络的路由规划方法及装置 - Google Patents

实时音视频网络的路由规划方法及装置 Download PDF

Info

Publication number
WO2024066626A1
WO2024066626A1 PCT/CN2023/105176 CN2023105176W WO2024066626A1 WO 2024066626 A1 WO2024066626 A1 WO 2024066626A1 CN 2023105176 W CN2023105176 W CN 2023105176W WO 2024066626 A1 WO2024066626 A1 WO 2024066626A1
Authority
WO
WIPO (PCT)
Prior art keywords
rtn
data
network topology
routing
real
Prior art date
Application number
PCT/CN2023/105176
Other languages
English (en)
French (fr)
Inventor
陈俊江
卢建
廖凯
郭成峰
刘志龙
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2024066626A1 publication Critical patent/WO2024066626A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/302—Route determination based on requested QoS
    • H04L45/306—Route determination based on the nature of the carried application
    • H04L45/3065—Route determination based on the nature of the carried application for real time traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
    • H04L65/80—Responding to QoS

Definitions

  • the embodiments of the present invention relate to the technical field of real-time audio and video communication, and in particular to a method and device for routing planning of a real-time audio and video network.
  • Real-time communication is a technology for real-time interaction of video, audio and other data.
  • digital technologies such as 5G, artificial intelligence (AI), and extended reality (XR), as well as the objective demand for onlineization
  • AI artificial intelligence
  • XR extended reality
  • the integration of the digital world and the physical world is also accelerating.
  • People's experience of interactive modes is also undergoing fundamental changes.
  • the demand for stronger interactivity and higher immersion is driving the transformation of the carrier network of RTC applications, the real-time audio and video network (RTN), which is evolving towards lower latency and better quality.
  • Routing planning between network element nodes is the core technology of RTN.
  • Reasonable routing planning can provide faster and better data transmission experience for RTC applications, thus providing important competitiveness for RTN systems.
  • RTN Routing planning technology
  • the routing planning in the related technology only selects the route to the node cluster.
  • the business data is forwarded according to the routing table, it is necessary to plan and select the data forwarding instance from the cluster, which results in high latency in the data forwarding stage, a long time to establish the data link, poor real-time performance, and reduced user experience.
  • the routing planning in related technologies is generally a static planning, which cannot be reasonably planned dynamically and globally according to the real-time changes in network topology, changes in network detection indicators, changes in network element node load, etc.
  • the embodiments of the present invention provide a method and device for routing planning of a real-time audio and video network, so as to at least solve the problem in the related art that the planned routing link is inaccurate due to the failure to plan the routing according to the real-time network topology.
  • a route planning method for a real-time audio and video network comprising: collecting data of each edge node in the audio and video network RTN according to the acquired real-time network topology information of the RTN; mapping the data into a quantized score of a link between each edge node according to routing strategies of different demand types to obtain a multi-strategy full RTN link quantized network topology; performing a first route planning for multiple edge nodes in the multi-strategy full RTN link quantized network topology, and based on the first edge node in the first route, performing a second route planning for the data instance in the first edge node.
  • the invention relates to a method for performing a first route planning on multiple edge nodes in the multi-strategy full RTN link quantization network topology, and performing a second route planning on the data instance in the first edge node based on the first edge node in the first route.
  • a computer-readable storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when executed.
  • an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
  • FIG. 1 is a hardware block diagram of a computer terminal for running a routing planning method for a real-time audio and video network according to an embodiment of the present invention
  • FIG2 is a schematic diagram of a network architecture of an RTN according to an embodiment of the present invention.
  • FIG. 3 is a flow chart of a method for routing planning of a real-time audio and video network according to an embodiment of the present invention
  • FIG. 4 is a structural block diagram of a routing planning device for a real-time audio and video network according to an embodiment of the present invention
  • FIG. 5 is a structural block diagram of a routing planning device for a real-time audio and video network according to another embodiment of the present invention.
  • FIG. 6 is a structural block diagram of a routing planning device for a real-time audio and video network according to another embodiment of the present invention.
  • FIG. 7 is a block diagram of a routing planning device for a real-time audio and video network according to another embodiment of the present invention.
  • FIG8 is a flow chart of a routing planning method according to an embodiment of the present invention.
  • FIG9 is a schematic diagram of an initial network topology according to an embodiment of the present invention.
  • FIG10 is a schematic diagram of a method for acquiring real-time edge data according to an embodiment of the present invention.
  • FIG11 is a schematic diagram of a multi-strategy quantization network topology according to an embodiment of the present invention.
  • FIG12 is a schematic diagram of a primary routing according to an embodiment of the present invention.
  • FIG. 13 is a schematic diagram of a two-level optimal routing table according to an embodiment of the present invention.
  • FIG. 1 is a hardware structure block diagram of a computer terminal for running a routing planning method for a real-time audio and video network in an embodiment of the present invention.
  • the computer terminal may include one or more (only one is shown in FIG.
  • processors 102 may include but is not limited to a processing device such as a microprocessor or a programmable logic device (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data, wherein the above-mentioned computer terminal may also include a transmission device 106 and an input and output device 108 for communication functions.
  • a processing device such as a microprocessor or a programmable logic device (Field Programmable Gate Array, FPGA)
  • memory 104 for storing data
  • the above-mentioned computer terminal may also include a transmission device 106 and an input and output device 108 for communication functions.
  • the structure shown in FIG. 1 is only for illustration, and it does not limit the structure of the above-mentioned computer terminal.
  • the computer terminal may also include more or fewer components than those shown in FIG. 1 , or have a configuration different from that shown in FIG. 1 .
  • the memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the routing planning method of the real-time audio and video network in the embodiment of the present invention.
  • the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method.
  • the memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.
  • the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the transmission device 106 is used to receive or send data via a network.
  • the specific example of the above network may include a wireless network provided by a communication provider of a computer terminal.
  • the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet.
  • the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.
  • RF Radio Frequency
  • the embodiment of the present application can be run on the RTN network architecture shown in Figure 2.
  • the network architecture includes: a central node and multiple edge nodes.
  • the central node also includes: a topology management and routing center, and each edge node also includes multiple forwarding instances (i.e., data instances).
  • the central node is the brain of RTN and is responsible for computing, controlling, and scheduling edge nodes in RTN.
  • topology management configures the RTN network topology information, and the routing center performs intelligent routing planning for edge nodes.
  • Edge nodes are neurons of RTN, responsible for forwarding service data. Among them, forwarding instances are applications that actually forward data in edge nodes.
  • An edge node represents a forwarding instance cluster, which can contain multiple forwarding instances.
  • FIG. 3 is a flow chart of a method for routing planning of a real-time audio and video network according to an embodiment of the present invention. As shown in FIG. 3 , the process includes the following steps:
  • Step S302 collecting data of each edge node in the RTN according to the acquired real-time network topology information of the audio and video network RTN;
  • Step S304 mapping the data into quantized scores of links between edge nodes according to routing strategies of different demand types, and obtaining a multi-strategy full RTN link quantized network topology;
  • Step S306 Perform a first route planning for multiple edge nodes in the multi-strategy full RTN link quantization network topology, and perform a second route planning for the data instance in the first edge node based on the first edge node in the first route.
  • the method further includes: obtaining an initial network topology of the RTN; updating the initial network topology of the RTN in real time according to a notification of a message subscription mechanism to obtain a real-time network topology; or periodically querying the network topology of the RTN to obtain the real-time network topology.
  • step S302 of this embodiment it includes: sending a data detection request to each edge node according to the real-time network topology information; and sending a data collection request to each edge node at a regular interval to collect detection data information and instance data information.
  • the detection data information includes at least one of the following detection indicators: packet loss rate, delay, jitter, and link bandwidth of the RTN.
  • step S304 of this embodiment it includes: according to the requirement type of the routing policy, all the detection indicators are The data is input into a quantitative model so that the data is mapped into a quantitative score of the link between each edge node; wherein each type of routing strategy corresponds to one quantitative model.
  • the requirement type of the routing strategy includes at least one of the following: a quality priority strategy, a cost priority strategy, or a comprehensive strategy of quality priority and cost priority.
  • step S304 of this embodiment it includes: when the change rate of the quantization score does not exceed the preset threshold, keeping the quantization score of the corresponding link in the multi-strategy full RTN link quantization network topology unchanged; when the change rate of the quantization score exceeds the preset threshold, updating the quantization score of the corresponding link in the multi-strategy full RTN link quantization network topology.
  • step S306 of this embodiment it includes: selecting a link with the smallest quantization score between any two or more edge nodes to plan a first routing link.
  • step S306 of this embodiment it includes: obtaining instance data information in the first edge node; and selecting the data instance with the lightest load in the first edge node for planning the second route according to the instance data information.
  • the topology information and edge node information of the real-time audio and video network RTN are obtained to generate a multi-strategy full RTN link quantized network topology, so as to perform dynamic routing planning according to the multi-strategy full RTN link quantized network topology. Therefore, the problem of inaccurate routing links caused by the inability to plan routes according to the real-time network topology in the related technology can be solved, and the accuracy of routing planning is improved.
  • the technical solution of the present invention in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory/random access memory (ROM/RAM), a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.
  • a storage medium such as a read-only memory/random access memory (ROM/RAM), a magnetic disk, or an optical disk
  • a terminal device which can be a mobile phone, a computer, a server, or a network device, etc.
  • a route planning device for a real-time audio and video network is also provided, and the device is used to implement the above-mentioned embodiment and preferred implementation mode, and the descriptions that have been made are not repeated.
  • the term "module” can implement a combination of software and/or hardware of a predetermined function.
  • the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.
  • FIG4 is a structural block diagram of a route planning device for a real-time audio and video network according to an embodiment of the present invention. As shown in FIG4 , the device includes: a collection module 10 , a mapping module 20 and a planning module 30 .
  • the collection module 10 is configured to collect data of each edge node in the audio and video network RTN according to the acquired real-time network topology information of the RTN;
  • a mapping module 20 is configured to map the data into quantized scores of links between edge nodes according to routing strategies of different demand types, and obtain a multi-strategy full RTN link quantized network topology;
  • the planning module 30 is configured to perform a first route planning for multiple edge nodes in the multi-strategy full RTN link quantization network topology, and based on the first edge node in the first route, perform a second route planning for the data instance in the first edge node.
  • FIG5 is a structural block diagram of a route planning device for a real-time audio and video network according to an embodiment of the present invention. As shown in FIG5 , the device includes, in addition to all the modules shown in FIG4 , further including:
  • a first acquisition module 40 is configured to acquire an initial network topology of the RTN
  • the second acquisition module 50 is configured to update the initial network topology of the RTN in real time according to the notification of the message subscription mechanism to obtain the real-time network topology; or to query the network topology of the RTN at regular intervals to obtain the real-time network topology.
  • FIG6 is a structural block diagram of a routing planning device for a real-time audio and video network according to an embodiment of the present invention.
  • the acquisition module 10 further includes:
  • a first sending unit 11 is configured to send a data detection request to each edge node according to the real-time network topology information
  • the second sending unit 12 is configured to periodically send a data collection request to each edge node to collect detection data information and instance data information.
  • FIG. 7 is a structural block diagram of a route planning device for a real-time audio and video network according to an embodiment of the present invention. As shown in FIG. 7 , in addition to all the modules shown in FIG. 6 , the planning module 30 further includes:
  • the first selection unit 31 is configured to select a link with a smallest quantization score between the plurality of edge nodes to plan a first routing link.
  • An acquiring unit 32 is configured to acquire instance data information in the first edge node
  • the second selection unit 33 is configured to select the data instance with the lightest load in the first edge node for planning a second route according to the instance data information.
  • the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.
  • FIG. 8 is a flow chart of the routing planning method according to an embodiment of the present invention. As shown in FIG. 8 , the method includes the following steps:
  • Step S801 Acquire the RTN initial network topology or network topology change.
  • the routing center needs to dynamically obtain the topology information of the RTN, that is, obtain the network topology information in real time.
  • Step S802 Send a data detection request to the edge node to collect edge data.
  • the routing center sends data detection requests to edge nodes based on the real-time network topology. After that, each edge node performs network detection on the edge nodes connected to it. At the same time, the routing center periodically initiates data collection requests to edge nodes to collect detection data, instance data and other information.
  • Step S803 determining whether to return detection data
  • step S804 if it is determined that no detection data is returned, go to step S804;
  • Step S804 initiate a data detection request again.
  • a data detection request is sent to the edge node again.
  • Step S805 mapping edge data into a multi-strategy quantitative network topology.
  • the routing center maps edge data into a quantitative network topology for the entire network based on different routing strategies.
  • Step S806 filtering and selecting the quantization scores in the multi-strategy quantization network topology.
  • Step S807 primary routing.
  • the routing center plans the primary routing between nodes based on real-time multi-strategy quantitative network topology
  • Step S808 secondary routing.
  • the routing center plans secondary routing between instances based on real-time edge node instance data.
  • the network topology represents the distribution of edge nodes in the RTN and the connection status of the edges between edge nodes.
  • the network topology needs to be configured in the topology management of the central node, which is completely configured according to the actual node distribution and connection status, and also includes information such as the distance between edge nodes and the total allocable bandwidth.
  • the routing center needs to obtain the RTN initialization network topology from the topology management.
  • the initial network topology is a mesh structure consisting of 6 edge nodes, the edge nodes are A, B, C, D, E, and F, and the connected edges are A-B, A-D, A-E, B-C, B-F, C-D, D-E, and D-F.
  • the topology management During the RTN network topology change phase, if nodes are added or deleted, or connected edges are added or deleted, the topology management will notify the routing center of the topology change in real time through the Kafka message subscription mechanism. In addition, the routing center will also query the topology management and update the network topology regularly.
  • the Kafka mechanism can ensure real-time performance, and the timing mechanism can ensure reliability.
  • the routing center of the central node will periodically collect detection data, instance data and other information from the edge nodes based on the real-time RTN network topology.
  • the routing center analyzes the connection status between edge nodes based on the current real-time RTN network topology and sends data detection requests to each node; each node parses the request data and performs network detection on its connected nodes, including network packet loss rate, latency, jitter, bandwidth and other detection indicator data.
  • the routing center will again send a new data detection request based on the real-time node connection status.
  • the routing center periodically sends data collection requests to edge nodes.
  • the data that needs to be collected also includes the forwarding instance information of each node, such as the instance load, CPU, etc.
  • the collection time granularity is in seconds, that is, it is collected once per second. If it is found that there is no detection data in the collected data, it is necessary to resend the data detection request.
  • the method for obtaining real-time edge data includes the following steps:
  • Step 1.1 According to the initial network topology of RTN, the routing center of the central node initiates a data detection request to the edge node A;
  • Step 1.2 After receiving the request, edge node A performs network detection on edge node B, edge node D, and edge node E.
  • Step 2.1 the routing center periodically initiates a data collection request to edge node A;
  • edge node A returns the detection data information of edge node B, edge node D, and edge node E and the instance data information of this node. Similarly, the detection and collection process of the remaining edge nodes is similar to that of edge node A.
  • the routing center will select edge data based on different routing strategies, map it into a quantitative network topology for the entire network, and filter the quantitative scores.
  • mapping quantized network topology
  • the routing center has formulated a variety of routing strategies.
  • Each routing strategy has a corresponding link quantification mathematical model.
  • the multiple edge indicators obtained above are input into the quantification model, which will be mapped into the quantification score of the edge links connected between nodes, and then the quantified network topology of the entire network is obtained.
  • the routing center will traverse all routing strategies and quantification models based on real-time edge data to generate a multi-strategy full-network link quantification network topology.
  • the routing strategy when the routing strategy is quality-first, the goal is to pursue quality and require the selection of the link with the lowest transmission delay.
  • the quantitative model will select packet loss rate (%), delay (ms), jitter (ms) and other indicators, and map these network indicators to link scores; when the routing strategy is cost-first, the goal is to save costs and require the selection of the link with the lowest transmission cost.
  • the node distance, link bandwidth and other indicators will be selected; when the routing strategy is comprehensive, the goal is to balance quality and cost, and the model indicators of quality strategy and cost strategy are comprehensively considered.
  • the routing center will generate a multi-strategy quantitative network topology in real time, as shown in Figure 11.
  • real-time edge data is mapped into a real-time multi-strategy quantitative network topology, ensuring the accuracy of the quantitative scores of the edges connecting the nodes.
  • the routing center will filter the link quantization score of each edge. When the score change rate does not exceed the set threshold, the link score will not be updated in the calculation model of route planning.
  • the last link score from node A to node B was 100. New edge data is now arriving, and the link score from node A to node B calculated by the routing center based on the latest quantized network topology is 101.
  • the score change rate threshold is set to 10%, and the change rate between the current score and the last score is 1%, which does not exceed 1%, so it is not updated to the calculation model.
  • a multi-strategy quantitative network topology is generated for dynamic multi-level routing planning.
  • problems such as high latency in the data forwarding stage and non-real-time planning of routes can be solved, thereby improving the timeliness of routing planning.
  • problems such as single and simple routing rules and calculation methods are also solved, thereby improving the accuracy of routing planning.
  • the computing model of the routing center plans the routing between nodes based on the real-time quantitative network topology, i.e., primary routing; and plans the routing between instances based on the real-time edge node instance data, i.e., secondary routing.
  • the routing center plans the optimal route between edge nodes, i.e., first-level routing, based on the filtered and screened multi-strategy quantitative network topology.
  • a node is selected as the starting node, and the optimal route from the node to other nodes is calculated. It is agreed that if the node can be directly connected to other nodes, the link score is used as its distance. If it cannot be directly connected to other nodes, infinity is used as its distance.
  • the node with the smallest distance is selected as the next point. Then, the distance from the starting point through the selected node to other nodes is recalculated, and the minimum distance data is updated. Finally, this process is repeated until all nodes are traversed.
  • the selected node is the optimal routing node that has been determined and will no longer participate in subsequent calculations.
  • the routing center quantifies the network topology based on multi-strategy updates in real time, and calculates the optimal route from any node to any other node in real time.
  • the optimal route from node A to any node is planned.
  • the optimal route from node A to node B is "A ⁇ B”
  • the optimal route from node A to node C is "A ⁇ E ⁇ D ⁇ C”
  • the optimal route from node A to node D is "A ⁇ E ⁇ D”
  • the optimal route from node A to node E is "A ⁇ E”
  • the optimal route from node A to node F is "A ⁇ E ⁇ D ⁇ F", as shown in Figure 12.
  • the optimal routes of the remaining nodes to any node are shown in Figure 12.
  • the routing center plans the optimal routing between instances under the node, i.e., the second-level routing.
  • the routing center receives a routing query request, it selects an optimal routing link based on the routing strategy, source node, and target node information. Then, the routing node is determined based on the optimal routing link, and the instance data information under the node is determined based on the collected edge data information. Finally, the instance with the lightest load under the routing node is selected in real time, and the optimal routing table is finally generated by traversing the nodes.
  • the primary routing from source node A to target node B is planned, that is, "A ⁇ B", where the instance with the lightest load under node A is a1, and the instance with the lightest load under node B is b1, so the planned secondary routing is "a1 ⁇ b1", and the final routing expression is shown in Figure 13.
  • the optimal routing table of the remaining nodes to any node is shown in Figure 13.
  • the above embodiments of the present invention are applicable to RTC-related industries, such as video conferencing, cloud computing, interactive live broadcast, and extended reality (Extended Reality, XR).
  • RTC-related industries such as video conferencing, cloud computing, interactive live broadcast, and extended reality (Extended Reality, XR).
  • the instance routing process of edge nodes is moved to the central node for unified calculation and planning, which can avoid high latency in the data forwarding stage and improve the real-time performance of business transmission.
  • the data for multi-level routing comes from real-time network topology and edge data, which further ensures the real-time performance of data. Dynamically planning new routes based on real-time data changes improves the accuracy of route planning.
  • An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.
  • the above-mentioned computer-readable storage medium may include, but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.
  • An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
  • the electronic device may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
  • modules or steps of the above-mentioned embodiments of the present invention can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation.
  • the present invention is not limited to any specific combination of hardware and software.

Abstract

本发明实施例提供了一种实时音视频网络的路由规划方法及装置。该方法包括：根据获取的音视频网络RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据；根据不同需求类型的路由策略，将所述数据映射成各边缘节点之间的链路的量化分数，得到多策略全RTN链路量化网络拓扑；对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，并基于所述第一路由中的第一边缘节点，对所述第一边缘节点中的数据实例进行第二路由规划。、

Description

实时音视频网络的路由规划方法及装置 技术领域
本发明实施例涉及实时音视频通信技术领域，具体而言，涉及一种实时音视频网络的路由规划方法及装置。
背景技术
实时音视频通信(Real Time Communication，RTC)是一种面向视频、音频等数据的实时交互的技术。近年来，随着5G、人工智能(Artificial Intelligence，AI)、扩展现实(Extended Reality，XR)等数字技术的发展，以及线上化客观需求，数字世界和物理世界的融合也在加速推进。人们对于交互模式的体验也在发生根本性变化，互动性更强、沉浸感更高的需求，驱动着RTC应用的承载网络——实时音视频网络(Real Time Network，RTN)进行变革，总体朝着时延更小、质量更好的方向不断演进。
网元节点之间的路由规划是RTN的核心技术，合理的路由规划能够为RTC应用提供更快更好的数据传输体验，从而为RTN系统提供重要竞争力。但是，目前业界RTN中的路由规划技术，还存在着诸多痛点：
一是，实时性差。相关技术中的路由规划仅仅是选路到节点集群。业务数据根据路由表进行转发的时候，还需要再从集群中规划选择数据转发实例，这就造成数据转发阶段时延高，建立数据链路的时间漫长，实时性变差，从而降低用户体验感。
二是，准确度低。相关技术中的路由规划普遍是一种静态规划，不能根据实时的网络拓扑变化、网络探测指标变化、网元节点负载变化等动态全局合理规划；同时，还存在选路规则、计算方式单一的问题，不能满足不同的业务需求。这些都造成规划出来的路由链路并不准确，仅仅适合用于专网传输，不适合用于互联网。
发明内容
本发明实施例提供了一种实时音视频网络的路由规划方法及装置，以至少解决相关技术中的因不能根据实时网络拓扑规划路由而造成规划的路由链路不准确的问题。
根据本发明的一个实施例，提供了一种实时音视频网络的路由规划方法，包括：根据获取的音视频网络RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据；根据不同需求类型的路由策略，将所述数据映射成各边缘节点之间的链路的量化分数，得到多策略全RTN链路量化网络拓扑；对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，并基于所述第一路由中的第一边缘节点，对所述第一边缘节点中的数据实例进行第二路由规划。
根据本发明的另一个实施例，提供了一种实时音视频网络的路由规划装置，包括：采集模块，设置为根据获取的音视频网络RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据；映射模块，设置为根据不同需求类型的路由策略，将所述数据映射成各边缘节点 之间的链路的量化分数，得到多策略全RTN链路量化网络拓扑；规划模块，设置为对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，并基于所述第一路由中的第一边缘节点，对所述第一边缘节点中的数据实例进行第二路由规划。
根据本发明的又一个实施例，还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，其中，所述计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
根据本发明的又一个实施例，还提供了一种电子装置，包括存储器和处理器，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行上述任一项方法实施例中的步骤。
附图说明
图1是根据本发明实施例的运行实时音视频网络的路由规划方法的计算机终端的硬件结构框图；
图2是根据本发明实施例的RTN的网络架构的示意图；
图3是根据本发明实施例的实时音视频网络的路由规划方法的流程图；
图4是根据本发明实施例的实时音视频网络的路由规划装置的结构框图；
图5是根据本发明另一实施例的实时音视频网络的路由规划装置的结构框图；
图6是根据本发明又一实施例的实时音视频网络的路由规划装置的结构框图；
图7是根据本发明又一实施例的实时音视频网络的路由规划装置的结构框图；
图8是根据本发明实施例的路由规划方法的流程图；
图9是根据本发明实施例的初始网络拓扑的示意图；
图10是根据本发明实施例的获取实时边缘数据方法的示意图；
图11是根据本发明实施例的多策略量化网络拓扑的示意图；
图12是根据本发明实施例的一级选路的示意图；
图13是根据本发明实施例的二级选路最优路由表示意图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本发明的实施例。
需要说明的是，本发明实施例的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
本申请实施例中所提供的方法实施例可以在移动终端、计算机终端或者类似的运算装置中执行。以运行在计算机终端上为例，图1是本发明实施例的运行实时音视频网络的路由规划方法的计算机终端的硬件结构框图。如图1所示，计算机终端可以包括一个或多个(图1中仅示出一个)处理器102(处理器102可以包括但不限于微处理器或可编程逻辑器件(Field Programmable Gate Array，FPGA)等的处理装置)和用于存储数据的存储器104，其中，上述计算机终端还可以包括用于通信功能的传输设备106以及输入输出设备108。本领域普通技术人员可以理解，图1所示的结构仅为示意，其并不对上述计算机终端的结构造成限定。例如，计算机终端还可包括比图1中所示更多或者更少的组件，或者具有与图1所示不同的配置。
存储器104可用于存储计算机程序，例如，应用软件的软件程序以及模块，如本发明实施例中的实时音视频网络的路由规划方法对应的计算机程序，处理器102通过运行存储在存储器104内的计算机程序，从而执行各种功能应用以及数据处理，即实现上述的方法。存储器104可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器104可进一步包括相对于处理器102远程设置的存储器，这些远程存储器可以通过网络连接至计算机终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输设备106用于经由一个网络接收或者发送数据。上述的网络具体实例可包括计算机终端的通信供应商提供的无线网络。在一个实例中，传输设备106包括一个网络适配器(Network Interface Controller，简称为NIC)，其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中，传输设备106可以为射频(Radio Frequency，简称为RF)模块，其用于通过无线方式与互联网进行通讯。
本申请实施例可以运行于图2所示的RTN的网络架构上，如图2所示，该网络架构包括：中心节点和多个边缘节点。其中，中心节点还包括：拓扑管理和路由中心，每个边缘节点中还包括多个转发实例(即数据实例)。
具体地，中心节点：是RTN的大脑，负责对RTN中的边缘节点进行计算、控制和调度。
其中，拓扑管理配置了RTN网络拓扑信息，路由中心对边缘节点进行智能路由规划。
边缘节点：是RTN的神经元，负责对业务数据进行转发。其中，转发实例为边缘节点中真正转发数据的应用程序。一个边缘节点代表的是一个转发实例集群，可以包含多个转发实例。
在本实施例中提供了一种运行于上述计算机终端或网络架构的实时音视频网络的路由规划方法，图3是根据本发明实施例的实时音视频网络的路由规划方法的流程图，如图3所示，该流程包括如下步骤：
步骤S302，根据获取的音视频网络RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据；
步骤S304，根据不同需求类型的路由策略，将所述数据映射成各边缘节点之间的链路的量化分数，得到多策略全RTN链路量化网络拓扑；
步骤S306，对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，并基于所述第一路由中的第一边缘节点，对所述第一边缘节点中的数据实例进行第二路由规划。
在本实施例的步骤S302之前，还包括：获取所述RTN的初始网络拓扑；根据消息订阅机制的通知实时更新所述RTN的初始网络拓扑，以获取实时网络拓扑；或，定时查询所述RTN的网络拓扑，以获取所述实时网络拓扑。
在本实施例的步骤S302中，包括：根据所述实时网络拓扑信息向所述各边缘节点发送数据探测请求；定时向所所述各边缘节点发送数据采集请求，以采集探测数据信息和实例数据信息。
在本实施例中，所述探测数据信息至少包括以下之一探测指标：所述RTN的丢包率、时延、抖动、链路带宽。
在本实施例的步骤S304中，包括：根据所述路由策略的需求类型，将多个探测指标的所 述数据输入量化模型中，以使所述数据映射成各边缘节点之间的链路的量化分数；其中，每种类型的路由策略对应一个所述量化模型。
在一个示例性实施例中，所述路由策略的需求类型至少包括以下之一：质量优先策略、成本优先策略、质量优先和成本优先综合策略。
在本实施例的步骤S304中，包括：在所述量化分数的变化率未超出预设阈值的情况下，保持所述多策略全RTN链路量化网络拓扑中的对应链路的量化分数不变；在所述量化分数的变化率超出预设阈值的情况下，更新所述多策略全RTN链路量化网络拓扑中的对应链路的量化分数。
在本实施例的步骤S306中，包括：选择任意两个或两个以上边缘节点之间的量化分数最小的链路规划第一路由链路。
在本实施例的步骤S306中，包括：获取所述第一边节点中的实例数据信息；根据所述实例数据信息，选择所述第一边缘节点中负载最轻的数据实例用于规划第二路由。
通过上述步骤，通过获取的实时音视频网络RTN的拓扑信息和边缘节点信息，生成多策略全RTN链路量化网络拓扑，以根据多策略全RTN链路量化网络拓扑进行动态的路由规划。因此，可以解决相关技术中的因不能根据实时网络拓扑规划路由而造成规划的路由链路不准确的问题，提升了路由规划的准确性。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如只读存储器/随机存取存储器(Read-Only Memory/Random Access Memory，ROM/RAM)、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本发明各个实施例所述的方法。
在本实施例中还提供了一种实时音视频网络的路由规划装置，该装置用于实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图4是根据本发明实施例的实时音视频网络的路由规划装置的结构框图，如图4所示，该装置包括：采集模块10、映射模块20和规划模块30。
采集模块10，设置为根据获取的音视频网络RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据；
映射模块20，设置为根据不同需求类型的路由策略，将所述数据映射成各边缘节点之间的链路的量化分数，得到多策略全RTN链路量化网络拓扑；
规划模块30，设置为对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，并基于所述第一路由中的第一边缘节点，对所述第一边缘节点中的数据实例进行第二路由规划。
图5是根据本发明实施例的实时音视频网络的路由规划装置的结构框图，如图5所示，该装置除包括图4所示的所有模块外，还包括：
第一获取模块40，设置为获取所述RTN的初始网络拓扑；
第二获取模块50，设置为根据消息订阅机制的通知实时更新所述RTN的初始网络拓扑，以获取实时网络拓扑；或，定时查询所述RTN的网络拓扑，以获取所述实时网络拓扑。
图6是根据本发明实施例的实时音视频网络的路由规划装置的结构框图，如图6所示，该装置除包括图5所示的所有模块外，采集模块10还包括：
第一发送单元11，设置为根据所述实时网络拓扑信息向所述各边缘节点发送数据探测请求；
第二发送单元12，设置为定时向所所述各边缘节点发送数据采集请求，以采集探测数据信息和实例数据信息。
图7是根据本发明实施例的实时音视频网络的路由规划装置的结构框图，如图7所示，该装置除包括图6所示的所有模块外，规划模块30还包括：
第一选择单元31，设置为选择所述多个边缘节点之间的量化分数最小的链路规划第一路由链路。
获取单元32，设置为获取所述第一边节点中的实例数据信息；
第二选择单元33，设置为根据所述实例数据信息，选择所述第一边缘节点中负载最轻的数据实例用于规划第二路由。
需要说明的是，上述各个模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：上述模块均位于同一处理器中；或者，上述各个模块以任意组合的形式分别位于不同的处理器中。
为便于对本发明所提供的技术方案的理解，下面将结合具体场景的实施例进行详细的阐述。
本发明实施例提供一种可运行于图2的网络架构的路由规划方法，图8是根据本发明实施例的路由规划方法的流程图，如图8所示，该方法包括如下步骤：
步骤S801，获取RTN初始网络拓扑或者网络拓扑变更。
具体地，路由中心需要动态地获取到RTN的拓扑信息，即实时获取网络拓扑信息。
步骤S802，向边缘节点下发数据探测请求，以采集边缘数据。
具体地，路由中心根据实时网络拓扑，向边缘节点下发数据探测请求，之后，各边缘节点向其相连的边缘节点进行网络探测；同时路由中心定时向边缘节点发起数据采集请求，采集探测数据和实例数据等信息。
步骤S803，判断是否返回探测数据；
具体地，在确定未返回探测数据则转至步骤S804；
在确定已返回探测数据则转至步骤S805。
步骤S804，再次发起数据探测请求。
具体地，在确定未返回探测数据的情况下，再次向边缘节点下发数据探测请求。
步骤S805，将边缘数据映射为多策略量化网络拓扑。
具体地，路由中心根据不同的路由策略，将边缘数据映射为全网量化网络拓扑。
步骤S806，对多策略量化网络拓扑中的量化分数进行过滤筛选。
步骤S807，一级选路。
具体地，路由中心根据实时的多策略量化网络拓扑规划节点之间的一级选路；
步骤S808，二级选路。
具体地，路由中心根据实时的边缘节点实例数据规划实例之间的二级选路。
以下是结合具体实施场景对上述路由规划方法中的相关步骤进行的详细描述。
一、关于获取实时网络拓扑
网络拓扑表示RTN中边缘节点的分布以及边缘节点之间相连边的连接情况。本发明实施例中网络拓扑需要在中心节点的拓扑管理配置，其完全按照真实的节点分布和连接情况配置，也包含了边缘节点之间的距离、可分配总带宽等信息。
具体地，路由中心在初始化阶段，需要向拓扑管理获取RTN初始化网络拓扑。
例如：如图9所示，初始网络拓扑为6个边缘节点组成的网状结构，边缘节点为A、B、C、D、E、F，相连边为A-B、A-D、A-E、B-C、B-F、C-D、D-E、D-F
RTN网络拓扑变更阶段，如出现节点增删、相连边增删等情况时，拓扑管理会通过kafka消息订阅机制实时通知到路由中心进行拓扑变更，除此之外，路由中心也会定时向拓扑管理查询并更新网络拓扑。在本实施例中，通过kafka机制可保证实时性，定时机制则可保证可靠性。
二、关于获取实时边缘数据
中心节点的路由中心会根据实时的RTN网络拓扑，定时向边缘节点采集探测数据和实例数据等信息。
具体地，关于下发数据探测请求：
路由中心根据当前实时的RTN网络拓扑，分析边缘节点之间的连接情况，向各节点下发数据探测请求；各节点解析请求数据，向其相连节点进行网络探测，包括网络的丢包率、时延、抖动、带宽等探测指标数据。
当RTN网络拓扑发生变更后，路由中心会再次根据实时的节点连接情况，下发新的数据探测请求。
关于定时采集数据：
路由中心定时向边缘节点发起数据采集请求。其中，需要采集的数据除了上述的探测数据之外，还包括各节点下的转发实例信息，如实例的负载、CPU等。采集时间粒度为秒级，即每秒采集一次。如果发现采集的数据中没有探测数据，则需要重新下发数据探测请求。
例如：如图10所示，获取实时边缘数据方法包括以下步骤：
探测阶段：
步骤1.1，根据RTN初始网络拓扑，中心节点的路由中心向边缘节点A发起数据探测请求；
步骤1.2，边缘节点A收到请求后，向边缘节点B、边缘节点D、边缘节点E进行网络探测。
采集阶段：
步骤2.1，路由中心向边缘节点A定时发起数据采集请求；
步骤2.2，边缘节点A返回与边缘节点B、边缘节点D、边缘节点E的探测数据信息和本节点下的实例数据信息。以此类推，其余边缘节点的探测和采集过程与边缘节点A类似。
三、关于多策略量化网络拓扑
路由中心会根据不同的路由策略，选取边缘数据，映射为全网量化网络拓扑，并且对量化分数进行过滤筛选。
具体地，关于映射量化网络拓扑：
为了应对不同业务的不同需求，路由中心制定了多种路由策略。每一种路由策略都有对应的链路量化数学模型，将上述获取的多个边缘指标输入量化模型，就会映射成为节点之间相连边链路的量化分数，进而得到全网的量化网络拓扑。路由中心会根据实时的边缘数据，遍历所有的路由策略和量化模型，生成多策略的全网链路量化网络拓扑。
例如：在路由策略为质量优先策略时，以追求质量为目的，要求选择传输时延最低的链路，量化模型会选取丢包率(％)、时延(ms)、抖动(ms)等作为指标，将这些网络指标映射为链路分数；在路由策略为成本优先策略时，以节约成本为目的，要求选择传输成本最低的链路，会选取节点距离、链路带宽等作为指标；在路由策略为综合策略时，以平衡质量和成本为目的，要求综合考虑质量策略和成本策略的模型指标。路由中心会实时生成多策略量化网络拓扑，如图11所示。
通过制定多种由策略来应对不同业务的不同需求，将实时的边缘数据映射为实时的多策略量化网络拓扑，保证了节点相连边量化分数的准确性。
关于过滤量化分数：
为了减少由于链路分数变化太小导致新规划的路由链路不变而做的无用功，同时为了减轻规划路由时的计算压力，需要减少更新链路分数的频率。路由中心会对每条边的链路量化分数进行筛选过滤，当分数变化率没有超过设定的阈值时，就不会更新链路分数到路由规划的计算模型中。
例如：上一次节点A到节点B的链路分数为100。当前有新的边缘数据到来，路由中心根据最新的量化网络拓扑计算出的节点A到节点B的链路分数值为101。此时设定的分数变化率阈值为10％，当前的分数值与上一次分数值的变化率为1％，没有超过，所以不更新到计算模型中。通过对量化分数进行过滤筛选，减少由于链路分数变化太小导致新规划的路由链路不变而做的无用功，也减轻了规划路由时的计算压力。
在本实施例中，通过实时获取RTN网络拓扑和边缘数据等信息，生成多策略量化网络拓扑，以用于动态多级路由规划，如此，能够解决数据转发阶段时延高和规划路由非实时等问题，提升了路由规划的时效性；同时，也解决了选路规则、计算方式单一简易等问题，提升了路由规划的准确性。
四、关于多级选路规划路由
路由中心的计算模型会根据实时的量化网络拓扑规划节点之间的路由，即一级选路；并根据实时的边缘节点实例数据规划实例之间的路由，即二级选路。
关于一级选路
路由中心根据过滤筛选后的多策略量化网络拓扑，规划边缘节点之间的最优路由，即一级选路。首先，选定某个节点作为起始节点，计算该节点到其他节点的最优路由，约定该节点如果能够直接与其他节点相连，则使用链路分数作为其距离，如果不能直接与其他节点相连，则使用无穷大作为其距离。接着，选取距离最小的节点作为下一个点。然后，重新计算从起始点经过该选定节点到其他节点的距离，更新最小距离数据。最后，以此类推直至遍历完所有节点，已经选定的节点就是确定了的最优路由节点，不会再参与到之后的计算中。
路由中心根据实时更新的多策略量化网络拓扑，实时的计算任意节点到其他任意节点的最优路由。
例如：以质量优先策略为例，规划节点A到任意节点的最优路由，节点A到节点B的最优路由为“A→B”，节点A到节点C的最优路由为“A→E→D→C”，节点A到节点D的最优路由为“A→E→D”，节点A到节点E的最优路由为“A→E”，节点A到节点F的最优路由为“A→E→D→F”，如图12所示。以此类推，其余节点与到任意节点的最优路由如图12所示。
关于二级选路：
路由中心根据一级选路的结果，规划节点下的实例之间的最优路由，即二级选路。首先，当路由中心收到路由查询请求时，会根据路由策略、源节点和目标节点等信息选定一条最优路由链路。然后，根据最优路由链路确定路由节点，再根据采集的边缘数据信息确定节点下的实例数据信息。最后，实时选取路由节点下负载最轻的实例，遍历节点最终生成最优路由表。
例如：以质量优先策略为例，按照上述一级选路的规划方法，规划从源节点A到目标节点B的一级选路，即“A→B”，其中，节点A下负载最轻的实例为a1，节点B下负载最轻的实例为b1，所以规划的二级选路为“a1→b1”，最终的路由表达如图13所示。以此类推，其余节点与到任意节点的最优路由表如图13所示。
本发明上述实施例适用于RTC相关产业，如视频会议、云电脑、互动直播、扩展现实(Extended Reality，XR)等。
通过动态多级选路规划路由，将边缘节点的实例选路过程上移到中心节点统一计算规划，可以避免数据转发阶段的高时延，提升了业务传输的实时性。并且，多级选路的数据来源于实时的网络拓扑和边缘数据等信息，进一步保证了数据的实时性，而根据实时的数据变化动态规划新的路由，又提升了路由规划的准确性。
本发明的实施例还提供了一种计算机可读存储介质，该计算机可读存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
在一个示例性实施例中，上述计算机可读存储介质可以包括但不限于：U盘、只读存储器(Read-Only Memory，简称为ROM)、随机存取存储器(Random Access Memory，简称为RAM)、移动硬盘、磁碟或者光盘等各种可以存储计算机程序的介质。
本发明的实施例还提供了一种电子装置，包括存储器和处理器，该存储器中存储有计算机程序，该处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
在一个示例性实施例中，上述电子装置还可以包括传输设备以及输入输出设备，其中，该传输设备和上述处理器连接，该输入输出设备和上述处理器连接。
本实施例中的具体示例可以参考上述实施例及示例性实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本发明实施例的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件结合。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员 来说，本发明可以有各种更改和变化。凡在本发明的原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (12)

  1. 一种实时音视频网络的路由规划方法，包括：
    根据获取的音视频网络RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据；
    根据不同需求类型的路由策略，将所述数据映射成各边缘节点之间的链路的量化分数，得到多策略全RTN链路量化网络拓扑；
    对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，并基于所述第一路由中的第一边缘节点，对所述第一边缘节点中的数据实例进行第二路由规划。
  2. 根据权利要求1所述的方法，其中，根据获取的RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据之前，还包括：
    获取所述RTN的初始网络拓扑；
    根据消息订阅机制的通知实时更新所述RTN的初始网络拓扑，以获取实时网络拓扑信息；或，定时查询所述RTN的网络拓扑，以获取所述实时网络拓扑信息。
  3. 根据权利要求1所述的方法，其中，根据获取的所述RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据，包括：
    根据所述实时网络拓扑信息向所述各边缘节点发送数据探测请求；
    定时向所述各边缘节点发送数据采集请求，以采集探测数据信息和实例数据信息。
  4. 根据权利要求3所述的方法，其中，所述探测数据信息至少包括以下之一探测指标：
    所述RTN的丢包率、时延、抖动、链路带宽。
  5. 根据权利要求1所述的方法，其中，根据不同需求类型的路由策略，将所述数据映射成各边缘节点之间的链路的量化分数，包括：
    根据所述路由策略的需求类型，将多个探测指标的所述数据输入量化模型中，以使所述数据映射成各边缘节点之间的链路的量化分数；其中，每种类型的路由策略对应一个所述量化模型。
  6. 根据权利要求5所述的方法，其中，所述路由策略的需求类型至少包括以下之一：
    质量优先策略、成本优先策略、质量优先和成本优先综合策略。
  7. 根据权利要求1所述的方法，其中，所述得到多策略全RTN链路量化网络拓扑，包括：
    在所述量化分数的变化率未超出预设阈值的情况下，保持所述多策略全RTN链路量化网络拓扑中的对应链路的量化分数不变；
    在所述量化分数的变化率超出预设阈值的情况下，更新所述多策略全RTN链路量化网络拓扑中的对应链路的量化分数。
  8. 根据权利要求1所述的方法，其中，对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，包括：
    选择任意两个或两个以上边缘节点之间的量化分数最小的链路规划第一路由链路。
  9. 根据权利要求1所述的方法，其中，对所述第一边缘节点中的数据实例进行的第二路由规划，包括：
    获取所述第一边节点中的实例数据信息；
    根据所述实例数据信息，选择所述第一边缘节点中负载最轻的数据实例用于规划第二路由。
  10. 一种实时音视频网络的路由规划装置，包括：
    采集模块，设置为根据获取的音视频网络RTN的实时网络拓扑信息采集所述RTN中的各边缘节点的数据；
    映射模块，设置为根据不同需求类型的路由策略，将所述数据映射成各边缘节点之间的链路的量化分数，得到多策略全RTN链路量化网络拓扑；
    规划模块，设置为对所述多策略全RTN链路量化网络拓扑中的多个边缘节点进行第一路由规划，并基于所述第一路由中的第一边缘节点，对所述第一边缘节点中的数据实例进行第二路由规划。
  11. 一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，其中，所述计算机程序被处理器执行时实现所述权利要求1至9任一项中所述的方法的步骤。
  12. 一种电子装置，包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现所述权利要求1至9任一项中所述的方法的步骤。
PCT/CN2023/105176 2022-09-29 2023-06-30 实时音视频网络的路由规划方法及装置 WO2024066626A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211207270.0A CN116668364A (zh) 2022-09-29 2022-09-29 实时音视频网络的路由规划方法及装置
CN202211207270.0 2022-09-29

Publications (1)

Publication Number Publication Date
WO2024066626A1 true WO2024066626A1 (zh) 2024-04-04

Family

ID=87717690

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/105176 WO2024066626A1 (zh) 2022-09-29 2023-06-30 实时音视频网络的路由规划方法及装置

Country Status (2)

Country Link
CN (1) CN116668364A (zh)
WO (1) WO2024066626A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117014636B (zh) * 2023-10-07 2024-03-19 中兴通讯股份有限公司 音视频网络的数据流调度方法、存储介质和电子装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102025621A (zh) * 2010-12-07 2011-04-20 南京邮电大学 基于映射机制的认知网络路由选择方法
US20130165187A1 (en) * 2011-12-27 2013-06-27 Fujitsu Limited Apparatus and method for controlling data transmission based on power consumption of nodes in a communication network
CN104104718A (zh) * 2014-07-02 2014-10-15 北京邮电大学 一种基于软件定义网络的用户自主路由定制系统和方法
CN108173766A (zh) * 2017-12-19 2018-06-15 北京邮电大学 一种基于差异化QoS的多业务分层拓扑路由方法和系统
CN110011913A (zh) * 2019-03-20 2019-07-12 烽火通信科技股份有限公司 一种路径计算方法及系统
CN111935011A (zh) * 2020-08-14 2020-11-13 浩鲸云计算科技股份有限公司 应用于ptn网络的动态多策略端到端路由计算方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102025621A (zh) * 2010-12-07 2011-04-20 南京邮电大学 基于映射机制的认知网络路由选择方法
US20130165187A1 (en) * 2011-12-27 2013-06-27 Fujitsu Limited Apparatus and method for controlling data transmission based on power consumption of nodes in a communication network
CN104104718A (zh) * 2014-07-02 2014-10-15 北京邮电大学 一种基于软件定义网络的用户自主路由定制系统和方法
CN108173766A (zh) * 2017-12-19 2018-06-15 北京邮电大学 一种基于差异化QoS的多业务分层拓扑路由方法和系统
CN110011913A (zh) * 2019-03-20 2019-07-12 烽火通信科技股份有限公司 一种路径计算方法及系统
CN111935011A (zh) * 2020-08-14 2020-11-13 浩鲸云计算科技股份有限公司 应用于ptn网络的动态多策略端到端路由计算方法及系统

Also Published As

Publication number Publication date
CN116668364A (zh) 2023-08-29

Similar Documents

Publication Publication Date Title
CN109617992A (zh) 一种基于区块链的边缘计算节点动态选举方法
CN104901989B (zh) 一种现场服务提供系统及方法
CN110601973A (zh) 一种路由规划方法、系统、服务器及存储介质
WO2024066626A1 (zh) 实时音视频网络的路由规划方法及装置
US20170078207A1 (en) Network prioritization based on node-level attributes
US20230042747A1 (en) Message Processing Method and Device, Storage Medium, and Electronic Device
CN109213792A (zh) 数据处理的方法、服务端、客户端、装置及可读存储介质
CN113891426A (zh) 一种分布式多节点组网方法及装置
CN113328953B (zh) 网络拥塞调整的方法、装置和存储介质
CN103179045B (zh) 支持p2p流量优化的资源节点选择方法
CN107040466B (zh) 基于物联网分层架构的多域协同数据传输的路径选择方法
CN109474696B (zh) 一种网络服务方法、装置、电子设备及可读存储介质
CN116527558A (zh) 基于q学习的多目标路由规划方法及装置
CN111385151A (zh) 一种基于多目标优化的虚拟网络的映射方法及装置
US10951690B2 (en) Near real-time computation of scaling unit's load and availability state
CN114885028B (zh) 业务调度方法、装置及计算机可读存储介质
US10812390B2 (en) Intelligent load shedding of traffic based on current load state of target capacity
CN109361625A (zh) 核查转发表项的方法、装置和控制器
CN109670691A (zh) 用于客服队列管理及客服分配的方法、设备与客服系统
CN111294553B (zh) 处理视频监控业务信令的方法、装置、设备和存储介质
TW201429205A (zh) 自動配置伺服器及其用戶終端設備的管理方法
CN104301220A (zh) 路径计算单元、路径计算客户端、负荷分担方法及系统
CN113064951A (zh) 基于区块链的数据同步方法和装置
CN108683533B (zh) 配置更新方法、配置更新的响应方法及服务器、系统
CN116436978B (zh) 面向云计算的内存分配方法、内存获取方法、装置和设备