WO2024098814A1 - 一种数据传输处理方法、装置、存储介质及电子装置 - Google Patents

一种数据传输处理方法、装置、存储介质及电子装置 Download PDF

Info

Publication number
WO2024098814A1
WO2024098814A1 PCT/CN2023/105174 CN2023105174W WO2024098814A1 WO 2024098814 A1 WO2024098814 A1 WO 2024098814A1 CN 2023105174 W CN2023105174 W CN 2023105174W WO 2024098814 A1 WO2024098814 A1 WO 2024098814A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
smoothed
link
packet loss
client
Prior art date
Application number
PCT/CN2023/105174
Other languages
English (en)
French (fr)
Inventor
刘志龙
陈俊江
郭成峰
李军
丁元欣
卢建
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 WO2024098814A1 publication Critical patent/WO2024098814A1/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
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • 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
    • H04L45/12—Shortest path evaluation
    • H04L45/124—Shortest path evaluation using a combination of metrics
    • 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
    • H04L45/30—Routing of multiclass traffic

Definitions

  • the embodiments of the present disclosure relate to the field of communications, and in particular, to a data transmission processing method, device, storage medium, and electronic device.
  • RTC Real Time Communication
  • the audio and video transmission network RTN system is an end-to-end audio and video transmission system, which can be divided into two parts: end-side transmission and in-cloud transmission.
  • End-side transmission refers to the part between the terminal and the edge node in the cloud, also known as the last mile transmission.
  • In-cloud transmission refers to the part of forwarding transmission between edge nodes in the cloud through one or more forwarding nodes.
  • the core of end-side transmission is to match the optimal edge node access, referred to as optimal access; the core of in-cloud transmission is to select the optimal forwarding path, referred to as routing scheduling.
  • optimal access and routing scheduling are handled by the access center and routing scheduling center respectively, and the access center and routing scheduling center operate independently of each other, which can achieve local optimality, but it is not necessarily the global optimal solution for end-to-end audio and video transmission.
  • the optimal access and routing scheduling are handled by the access center and the routing scheduling center respectively, which leads to the problem of local optimality and the problem that the end-to-end audio and video transmission is not necessarily the global optimality. No solution has been proposed yet.
  • the embodiments of the present disclosure provide a data transmission processing method, device, storage medium and electronic device to at least solve the problem in the related art that optimal access and routing scheduling are respectively processed by an access center and a routing scheduling center, which results in local optimization and is not necessarily globally optimal for end-to-end audio and video transmission.
  • a data transmission processing method which is applied to a full-link management center, and the method includes:
  • the optimal media transmission path is sent to the starting client so that the starting client can
  • the data transmission path is used to transmit data to the destination client.
  • a data transmission processing device which is applied to a full-link management center, and the device includes:
  • a receiving module configured to receive an acquisition request for acquiring a media transmission path sent by an initiating client, wherein the acquisition request carries a destination client;
  • An acquisition module configured to acquire an optimal media transmission path between the starting client and the destination client according to the acquisition request
  • the sending module is configured to send the optimal media transmission path to the starting client, so that the starting client performs data transmission with the destination client according to the optimal media transmission path.
  • 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.
  • 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.
  • FIG1 is a hardware structure block diagram of a device for a data transmission processing method according to an embodiment of the present disclosure
  • FIG2 is a flow chart of a data transmission processing method according to an embodiment of the present disclosure
  • FIG3 is a flow chart of a data transmission processing method according to an optional embodiment of the present disclosure.
  • FIG4 is a schematic diagram of the composition of a full-link acceleration RTN system according to an embodiment of the present disclosure
  • FIG5 is a block diagram of a client according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic diagram of a data packet format after encapsulation of a transmission path according to an embodiment of the present disclosure
  • FIG7 is a block diagram of edge node composition according to an embodiment of the present disclosure.
  • FIG8 is a block diagram of a transfer node according to an embodiment of the present disclosure.
  • FIG9 is a block diagram of a full-link management center according to an embodiment of the present disclosure.
  • FIG. 10 is a block diagram of a data transmission processing device according to an embodiment of the present disclosure.
  • FIG1 is a hardware structure block diagram of a device of the data transmission processing method of the embodiment of the present disclosure.
  • the device may include one or more (only one is shown in FIG1 ) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device) and a memory 104 for storing data, wherein the above-mentioned device may also include a transmission device 106 and an input-output device 108 for communication functions.
  • processors 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device
  • a memory 104 for storing data
  • the above-mentioned device may also include a transmission device 106 and an input-output device 108 for communication functions.
  • FIG1 is only for illustration and does not limit the structure of the above-mentioned device.
  • the device may also include more or fewer components than those shown in FIG1 , or have a configuration different from that shown in FIG1 .
  • 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 data transmission processing method in the embodiment of the present disclosure.
  • the processor 102 executes various functional applications and data transmission 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 may be connected to the device 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 the communication provider of the device.
  • 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
  • FIG. 2 is a flow chart of the data transmission processing method according to an embodiment of the present disclosure. As shown in FIG. 2 , the method is applied to a full-link management center. The process includes the following steps:
  • Step S202 receiving an acquisition request for acquiring a media transmission path sent by an originating client, wherein the acquisition request carries a destination client;
  • Step S204 obtaining an optimal media transmission path between the source client and the destination client according to the acquisition request
  • Step S206 sending the optimal media transmission path to the originating client, so that the originating client performs data transmission with the destination client according to the optimal media transmission path.
  • the global optimal media transmission path is planned from the whole link, breaking the local optimal problem and realizing full link acceleration. The quality of audio and video media transmission is further improved, thereby improving the user experience.
  • FIG. 3 is a flow chart of a data transmission processing method according to an optional embodiment of the present disclosure. As shown in FIG. 3 , before the above step S202, the method further includes:
  • Step S302 obtaining link data between the client and the connected edge node, link data between the edge node and the connected transit node, and link data between the transit nodes, wherein the client includes the starting client and the destination client;
  • the above-mentioned step S302 may specifically include: sending information of the connected edge node to the client, sending information of the connected transit node to the edge node and the transit node, and sending a detection request to the client, the edge node and the transit node; receiving link data between the client and the connected edge node detected, and receiving link data between the edge node and the connected transit node detected, and link data between the connected transit nodes detected by the transit node.
  • Step S304 converting the target link data into a link quality index, wherein the target link data includes link data between the client and the accessed edge node, link data between the edge node and the connected transit node, and link data between the transit nodes;
  • Step S306 plan the optimal media between all the starting clients and all the destination clients according to the link quality index.
  • the above step S306 may specifically include: obtaining the topological relationship among the client, the edge node and the transit node; and planning the optimal media transmission path with the minimum link quality index according to the topological relationship and the link quality index.
  • Step S308 All the starting clients, all the destination clients, and all the optimal media transmission paths are associated and stored.
  • step S304 may specifically include:
  • each link data in the target link data includes: packet loss data, delay data, jitter data, and available bandwidth data; respectively smooth the packet loss data, the delay data, the jitter data, and the available bandwidth data to obtain smoothed packet loss data, smoothed delay data, smoothed jitter data, and smoothed available bandwidth data; determine the quality score of the target link data according to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, the smoothed available bandwidth data and the corresponding trend weight;
  • respectively smoothing the packet loss data, the delay data, the jitter data, and the available bandwidth data to obtain the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data may specifically include: determining the standardized packet loss data, the standardized delay data, the standardized jitter data, and the standardized available bandwidth data; determining the average packet loss data of the current packet loss, the average delay data of the current packet loss, the average jitter data of the current packet loss, and the average available bandwidth data of the current packet loss; determining the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data according to the standardized packet loss data, the standardized delay data, the standardized jitter data, the standardized available bandwidth data and the average packet loss data of the current packet loss, the average delay data of the current packet loss, the average jitter data of the current packet loss, and the average available bandwidth data of the current
  • determining the quality score of the target link data according to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, the smoothed available bandwidth data and the corresponding trend weight may specifically include:
  • the trend weights corresponding to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data are determined respectively in the following ways:
  • the quality score of the link data is determined according to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, the smoothed available bandwidth data and the corresponding trend weights in the following ways respectively:
  • L smooth , D smooth , J smooth , and B smooth are respectively the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data
  • T l , T d , T j , and T b are respectively the trend weights corresponding to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data
  • Q l , Q d , Q j , and Q b are respectively the quality scores of the packet loss data, the delay data, the jitter data, and the available bandwidth data
  • L smooth , D smooth , J smooth , and B smooth are respectively the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data
  • wl inc , wd inc , wj inc , and wb inc are respectively the trend parameters of the trend parameters of packet loss, delay,
  • the link quality index may be determined in the following manner:
  • Q link W l ⁇ Q l +W d ⁇ Q d +W j ⁇ Q j +W b ⁇ Q b ;
  • Q link is the link quality index
  • Q l , Q d , Q j , and Q b are the quality scores of the packet loss data, the delay data, the jitter data, and the available bandwidth data respectively
  • W l , W d , W j , and W b are the weight coefficients of the packet loss data, the delay data, the jitter data, and the available bandwidth data respectively.
  • This embodiment proposes to globally optimize the two independent functions of optimal access and routing scheduling in the current RTN system, integrate the optimal access center and routing scheduling center to form a full-link management center, plan the global optimal access and routing scheduling solution from the full link, break the local optimal problem, and achieve true full-link acceleration. Further improve the quality of audio and video media transmission, and thus improve user experience.
  • FIG4 is a schematic diagram of the composition of the full-link acceleration RTN system according to an embodiment of the present disclosure.
  • the optimal access center and the routing scheduling center in the current RTN system are integrated to form a full-link management center, and the global optimal access and routing scheduling scheme is planned from the whole link to break the local optimal problem and realize the real full-link acceleration.
  • the client is an audio and video terminal or related SDK, which is mainly responsible for processing audio and video services, querying and encapsulating path information, and accessing edge nodes, covering the audio and video media display part and the audio and video media generation part.
  • the video conferencing scenario includes PC clients, mobile clients, and terminals in conference rooms;
  • the cloud desktop scenario includes thin terminals, PCs, and back-end servers;
  • the AR/VR scenario includes VR glasses, terminal helmets, and back-end servers.
  • the edge node is responsible for client access and has the ability to send and receive data. It is also responsible for receiving data detection requests from the routing scheduling center and detecting the network parameters of the transit nodes connected to it.
  • the detection data includes packet loss, delay, jitter, bandwidth, etc., and is responsible for reporting the detection results to the full-link management center.
  • the transit node is responsible for high-performance data forwarding. It is also responsible for receiving data detection requests from the routing scheduling center and detecting the network parameters of the transit nodes and edge nodes connected to it.
  • the detection data includes packet loss, delay, jitter, bandwidth, node load, etc., and is responsible for reporting the detection results to the full-link management center.
  • the full-link management center is responsible for the global unified planning of access and forwarding links; it is responsible not only for the planning of links from clients to edge nodes, but also for the planning of links from edge points to destination edge nodes via transit nodes. It is also responsible for the overall network topology.
  • the management and link detection requests of the PUSH are sent to the client, edge node and transfer node, and the link network parameter data reported by the client, edge node and forwarding node are collected, including packet loss, delay, jitter, bandwidth, etc.
  • FIG. 5 is a block diagram of the client composition according to an embodiment of the present disclosure.
  • the client in the full-link accelerated audio and video transmission RTN system in this embodiment is mainly composed of a media content module, a path management module, a data transceiver module, and a link detection module.
  • the media content module is responsible for the production/display of audio and video media and other related business processing.
  • the path management module is responsible for querying the global optimal path from the full-link management center, and encapsulating the path information and original data into a new data packet for transmission.
  • Figure 6 is a schematic diagram of the data packet format after encapsulating the transmission path according to an embodiment of the present disclosure, and the format after encapsulation is shown in Figure 6, which is responsible for converting the received encapsulated data into the original data.
  • the data transceiver module is responsible for receiving data and also has the function of sending data to the next hop according to the path information indicated in the transmission path.
  • the link detection module is responsible for registering with the full-link planning module of the full-link management center and receiving the detection request instructions issued by it.
  • the instructions will include the specific nodes that need to be detected. After receiving the instructions, random link detection is performed.
  • the detection indicators include packet loss, delay, jitter, bandwidth, and load. After the detection is completed, the specific parameters of the detection will be sent to the full-link planning module of the full-link management center at a regular interval.
  • FIG. 7 is a block diagram of the edge node composition according to an embodiment of the present disclosure.
  • the edge node in the full-link accelerated audio and video transmission RTN system in this embodiment is mainly composed of a client access module, a data transceiver module, and a link detection module.
  • the client access module is responsible for the client access function.
  • the data transceiver module is responsible for receiving data and also has the function of sending data to the next hop according to the path information indicated in the transmission path.
  • the link detection module is responsible for registering with the full-link planning module of the full-link management center and receiving the detection request instructions issued by it.
  • the instructions will include the specific nodes that need to be detected. After receiving the instructions, link detection will be performed randomly.
  • the detection indicators include packet loss, delay, jitter, bandwidth, and load. After the detection is completed, the specific parameters of the detection will be sent to the full-link planning module of the full-link management center at a regular interval.
  • FIG8 is a block diagram of the transit node composition according to an embodiment of the present disclosure.
  • the transit node in the full-link accelerated audio and video transmission RTN system of the present disclosure embodiment is mainly composed of a data transceiver module and a link detection module.
  • the data transceiver module is responsible for high-performance data reception, and also has the function of sending data to the next hop according to the path information indicated in the transmission path.
  • the link detection module is responsible for registering with the full-link planning module of the full-link management center and receiving the detection request instructions issued by it.
  • the instructions will include the specific nodes that need to be detected. After receiving the instructions, link detection will be performed randomly.
  • the detection indicators include packet loss, delay, jitter, bandwidth, and load. After the detection is completed, the specific parameters of the detection will be sent to the full-link planning module of the full-link management center at a regular interval.
  • FIG. 9 is a block diagram of the full-link management center according to an embodiment of the present disclosure.
  • the transit node in the full-link accelerated audio and video transmission RTN system of this embodiment is mainly composed of a topology management module, a detection management module, and a full-link planning module.
  • the topology management module is responsible for the management of the topology of the entire RTN network, including the addition and deletion of edge nodes and transit nodes, and the change of the connection relationship between nodes. It is also responsible for the registration function of clients, edge nodes, and forwarding nodes.
  • the detection management module is responsible for sending detection requests to the client, edge nodes and transit nodes, receiving detection data from edge nodes and transit nodes, and converting specific link parameters into specific link quality indexes.
  • Q link is the link quality index
  • Q l , Q d , Q j , Q b are the quality scores of the packet loss data, the delay data, the jitter data, and the available bandwidth data, respectively
  • W l , W d , W j , and W b are the weight coefficients of the packet loss data, the delay data, the jitter data, and the available bandwidth data, respectively; the smaller the score of Q link , the better the link quality.
  • Q l , Q d , Q j , and Q b are the quality scores corresponding to packet loss, delay, jitter, and available bandwidth, respectively, and the smaller the score, the better the quality of the relevant parameters.
  • W l , W d , W j , and W b are the packet loss quality parameter, the delay quality parameter, the jitter quality parameter, and the available bandwidth quality parameter, respectively, and the sum of W l , W d , W j , and W b is 1, and the specific value thereof can be specified according to the specific service scenario.
  • L smooth represents the smoothed packet loss data
  • T l represents the trend weight, which shows the trend of packet loss change, indicating whether the packet loss increases or decreases.
  • D smooth represents the smoothed delay data
  • T d represents the trend weight, which indicates the trend of delay change, indicating whether the delay increases or decreases.
  • D smooth represents the smoothed jitter data
  • T d represents the trend weight, which indicates the trend of jitter change, indicating whether the jitter increases or decreases.
  • T b represents the trend weight, which indicates the trend of the available bandwidth change, indicating whether the available bandwidth increases or decreases.
  • L smooth , D smooth , J smooth , and B smooth are the smoothed packet loss data, the smoothed the delay data after standardization, the smoothed jitter data, and the smoothed available bandwidth data;
  • L std , D std , J std , and B std are respectively the standardized packet loss data, the standardized delay data, the standardized jitter data, and the standardized available bandwidth data;
  • L avg , D avg , J avg , and B avg are respectively the average packet loss data of the current packet loss, the average delay data of the current packet loss, the average jitter data of the current packet loss, and the average available bandwidth data of the current packet loss;
  • ⁇ represents the smoothing parameter, which defaults to 0.8 and can also be adjusted according to actual effects.
  • L represents the original packet loss rate
  • the data range of the original packet loss rate is 0-1
  • the data range after L std standardization is 0-5.
  • D represents the original delay data
  • the data range of the original delay is 0-2000ms
  • the delay data exceeding 20000ms is set to 20000ms
  • the data range after D std standardization is 0-5.
  • J represents the original jitter data
  • the data range of the original jitter is 0-2000ms
  • the jitter data exceeding 20000ms is set to 20000ms
  • the data range after D std standardization is 0-5.
  • B represents the original available bandwidth, the data range of the original available bandwidth is 0-100000Mbps (10Gbps), and the data range after B std standardization is 1-5.
  • T l , T d , T j , and T b are shown in Formula 7-5.
  • wl inc is the trend parameter of packet loss increase, which defaults to 1.2 and can be adjusted according to the actual effect.
  • wl dec is the trend parameter of packet loss reduction, which defaults to 0.8 and can be adjusted according to the actual effect.
  • L(i) smooth represents the smooth packet loss parameter at the current moment, and L(i-1) smooth represents the smooth packet loss parameter at the previous sampling moment.
  • wd inc is the delay increase trend parameter, the default value is 1.2, and it can also be adjusted according to the actual effect.
  • wd dec is the delay reduction trend parameter, the default value is 0.8, and it can also be adjusted according to the actual effect.
  • D(i) smooth represents the smooth delay parameter at the current moment, and D(i-1) smooth represents the smooth delay parameter at the previous sampling moment.
  • wj inc is the jitter increase trend parameter, the default value is 1.2, and it can also be adjusted according to the actual effect.
  • wj dec is the jitter reduction trend parameter, the default value is 0.8, and it can also be adjusted according to the actual effect.
  • J(i) smooth represents the smooth jitter parameter at the current moment
  • J(i-1) smooth represents the smooth jitter parameter at the previous sampling moment.
  • wb inc is the trend parameter for the increase of available bandwidth, which defaults to 1.2 and can be adjusted according to the actual effect.
  • wb dec is the trend parameter for the decrease of available bandwidth, which defaults to 0.8 and can be adjusted according to the actual effect.
  • L(i) smooth represents the smoothed available bandwidth parameter at the current moment, and L(i-1) smooth represents the smoothed available bandwidth parameter at the previous sampling moment.
  • the full-link planning module is responsible for global unified planning of access and forwarding links in real time according to the topological relationship of the client, edge node and transit node and the link quality based on the detection data.
  • the global optimal transmission link information planned in real time is stored in the memory for client query. It is worth pointing out that in the process of global planning based on the topological relationship and link quality index, not only the planning of undirected graphs is supported, but also the planning of directed graphs. At the same time, the number of path hops is added to the planning algorithm as a penalty parameter during the planning process, because for two links with the same link quality index, the link with fewer hops will have better transmission quality due to fewer forwarding hops and lower failure rate.
  • Step 1 The client, edge node, and transit node register with the topology management module of the full-link management center;
  • Step 2 After registration is completed, the topology management module of the full-link management center saves the client, edge node and transit node in the RTN system configured by the user and the link relationship between them.
  • Step 3 After the topology relationship is configured, the detection management module of the full-link management center sends the edge node information that can be accessed by the client to the client; sends the node information connected to the node to each edge node and transit node, and instructs them to start detection;
  • Step 4 After receiving the detection request, the link detection module in the client starts to dynamically detect the data information of the link between the edge nodes connected to it, including packet loss, delay, jitter, bandwidth, load, etc., and reports the relevant data information to the detection management module of the full link management center;
  • Step 5 After receiving the detection request, the link detection module of the edge node and the link detection module of the transit node start to dynamically detect the data information between the transit nodes connected to them, including packet loss, delay, jitter, bandwidth, load, etc., and report the relevant data information to the detection management module of the full link management center;
  • Step 6 After receiving the relevant detection data, the detection management module of the full-link management center will hand over the detection data to the full-link planning module to quantify the link parameters such as packet loss, delay, jitter, bandwidth, and load into a specific link quality index through the link quality quantification model. The smaller the value, the higher the link quality.
  • Step 7 The full-link planning module of the full-link management center will dynamically plan the optimal path for media transmission between clients based on the real-time link quality index through the path planning algorithm and store it in the memory;
  • step 8 before sending media data to client B, client A will query the full-link planning module of the full-link management center to obtain the globally optimal media transmission path, and encapsulate the globally optimal transmission path and the original data.
  • the format is shown in Figure 7.
  • Step 9 After the data encapsulation is completed, the data transceiver module of the client A sends the data to the edge node according to the path information indicated in the transmission path.
  • Step 10 after receiving the data packet containing sufficient path information, the data transceiver module of the edge node forwards the data packet to the corresponding forwarding node according to the path information instruction;
  • Step 11 after receiving the data packet containing sufficient path information, the data transceiver module of the forwarding node forwards the data packet to the corresponding next hop according to the path information instruction, until it is sent to the edge node connected to the destination client B;
  • Step 12 After receiving the data, the data transceiver module of the edge node to which the client B is connected will remove the path-related information in the data and send the original data to the client B according to the instructions in the path information.
  • FIG. 10 is a block diagram of a data transmission processing device according to an embodiment of the present disclosure. As shown in FIG. 10 , the device is applied to a full-link management center. The device includes:
  • the receiving module 102 is configured to receive an acquisition request for acquiring a media transmission path sent by an initiating client, wherein the acquisition request carries a destination client;
  • An acquisition module 104 is configured to acquire an optimal media transmission path between the originating client and the destination client according to the acquisition request;
  • the sending module 106 is configured to send the optimal media transmission path to the originating client, so that the originating client performs data transmission with the destination client according to the optimal media transmission path.
  • the device further comprises:
  • An acquisition module configured to acquire link data between a client and an accessed edge node, link data between an edge node and a connected transit node, and link data between transit nodes, wherein the client includes the start client and the destination client;
  • a conversion module configured to convert target link data into a link quality index, wherein the target link data includes link data between the client and an accessed edge node, link data between the edge node and a connected transit node, and link data between the transit nodes;
  • a planning module configured to plan an optimal media transmission path between all starting clients and all destination clients according to the link quality index
  • the associated storage module is configured to associate and store all the starting clients, all the destination clients, and all the optimal media transmission paths.
  • the acquisition module is also configured to send information of the connected edge node to the client, send information of the connected transit node to the edge node and the transit node, and send detection requests to the client, the edge node and the transit node; receive link data between the client and the connected edge node, and receive link data between the edge node and the connected transit node, as well as link data between the connected transit nodes detected by the transit node.
  • the planning module is further configured to obtain the topological relationship among the client, the edge node and the transit node; and plan the optimal media transmission path with the minimum link quality index based on the topological relationship and the link quality index.
  • the conversion module includes:
  • a first determination submodule configured to determine a quality score of the target link data
  • the second determination submodule is configured to determine the link quality index according to the quality score of the target link data and the corresponding weight coefficient.
  • the first determining submodule includes:
  • An acquisition unit configured to acquire the target link data, wherein each link data in the target link data includes: packet loss data, delay data, jitter data, and available bandwidth data;
  • a smoothing processing unit used to respectively smooth the packet loss data, the delay data, the jitter data, and the available bandwidth data to obtain smoothed packet loss data, smoothed delay data, smoothed jitter data, and smoothed available bandwidth data;
  • a determination unit is used to determine the quality score of the target link data according to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, the smoothed available bandwidth data and the corresponding trend weight.
  • the smoothing processing unit is further used to determine the normalized packet loss data, the normalized delay data, the normalized jitter data, and the normalized available bandwidth data;
  • the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data are determined based on the standardized packet loss data, the standardized delay data, the standardized jitter data, the standardized available bandwidth data, and the average packet loss data of the current packet loss, the average delay data of the current packet loss, the average jitter data of the current packet loss, and the average available bandwidth data of the current packet loss.
  • the determining unit is further configured to determine trend weights corresponding to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data respectively in the following manners:
  • the quality score of the link data is determined according to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, the smoothed available bandwidth data and the corresponding trend weights in the following ways respectively:
  • L smooth , D smooth , J smooth , and B smooth are the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data, respectively;
  • T l , T d , T j , and T b are the smoothed the trend weights corresponding to the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data;
  • Q l , Q d , Q j , and Q b are respectively the quality scores of the packet loss data, the delay data, the smoothed jitter data, and the available bandwidth data;
  • L smooth , D smooth , J smooth , and B smooth are respectively the smoothed packet loss data, the smoothed delay data, the smoothed jitter data, and the smoothed available bandwidth data;
  • wl inc , wd inc , wj inc , and wb inc are respectively the trend parameters
  • the second determination submodule is configured to determine the link quality index according to the quality score of the target link data and the corresponding weight coefficient in the following manner:
  • Q link W l ⁇ Q l +W d ⁇ Q d +W j ⁇ Q j +W b ⁇ Q b ;
  • Q link is the link quality index
  • Q l , Q d , Q j , and Q b are the quality scores of the packet loss data, the delay data, the jitter data, and the available bandwidth data respectively
  • W l , W d , W j , and W b are the weight coefficients of the packet loss data, the delay data, the jitter data, and the available bandwidth data respectively.
  • An embodiment of the present disclosure 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 disclosure 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 present disclosure 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 than 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. In this way, the present disclosure is not limited to any specific combination of hardware and software.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本公开实施例提供了一种数据传输处理方法、装置、存储介质及电子装置，该方法包括：接收起始客户端发送的获取媒体传输路径的获取请求，该获取请求中携带有目的客户端；根据该获取请求获取该起始客户端与该目的客户端之间的最优媒体传输路径；将该最优媒体传输路径发送给该起始客户端，以使该起始客户端根据该最优媒体传输路径与该目的客户端进行数据传输，可以解决相关技术中最优接入和路由调度分别由接入中心和路由调度中心分别进行处理，存在局部最优的问题，且对于端到端的音视频传输不一定是全局最优的问题，从全链路规划全局最优的媒体传输路径，打破局部最优问题，实现全链路加速。进一步提升音视频媒体传输的质量，进而提升用户体验。

Description

一种数据传输处理方法、装置、存储介质及电子装置
相关申请的交叉引用
本公开基于2022年11月08日提交的发明名称为“一种数据传输处理方法、装置、存储介质及电子装置”的中国专利申请CN202211395987.2，并且要求该专利申请的优先权，通过引用将其所公开的内容全部并入本公开。
技术领域
本公开实施例涉及通信领域，具体而言，涉及一种数据传输处理方法、装置、存储介质及电子装置。
背景技术
随着互联网的不断发展，音视频媒体数据已经成为互联网流量的主体，近年来AR/VR、云游戏、互动直播、云电脑、远程教育、视频会议等场景的出现对音视频传输的实时性、稳定性提出了新的挑战，也推动实时音视频传输(Real Time Communication，简称为RTC)技术成为当下炙手可热的领域，国内外RTC产业规模均保持着较高增长速度。为了解决各种场景下媒体传输的问题，各个厂商都根据自己的业务构建了自己的音视频传输网络(Real Time Network，简称为RTN)。
音视频传输网络RTN系统为端到端的音视频传输系统，可以划分为端侧传输和云内传输两部分。其中端侧传输是指终端到云内边缘节点之间的部分，也称之为最后一公里传输。云内传输是指云内边缘节点之间经过一个或多个转发节点进行转发传输的部分。在RTN中，端侧传输的核心是匹配最优的边缘节点接入，简称最优接入；云内传输的核心是选择最优的转发路径，简称路由调度。在当前的RTN方案中，最优接入和路由调度分别由接入中心和路由调度中心分别进行处理，且接入中心和路由调度中心相互独立运行，能够实现局部最优，但对于端到端的音视频传输不一定是全局最优的方案。
针对相关技术中最优接入和路由调度分别由接入中心和路由调度中心分别进行处理，存在局部最优的问题，且对于端到端的音视频传输不一定是全局最优的问题，尚未提出解决方案。
发明内容
本公开实施例提供了一种数据传输处理方法、装置、存储介质及电子装置，以至少解决相关技术中最优接入和路由调度分别由接入中心和路由调度中心分别进行处理，存在局部最优的问题，且对于端到端的音视频传输不一定是全局最优的问题。
根据本公开的一个实施例，提供了一种数据传输处理方法，应用于全链路管理中心，所述方法包括：
接收起始客户端发送的获取媒体传输路径的获取请求，其中，所述获取请求中携带有目的客户端；
根据所述获取请求获取所述起始客户端与所述目的客户端之间的最优媒体传输路径；
将所述最优媒体传输路径发送给所述起始客户端，以使所述起始客户端根据所述最优媒 体传输路径与所述目的客户端进行数据传输。
根据本公开的另一个实施例，还提供了一种数据传输处理装置，应用于全链路管理中心，所述装置包括：
接收模块，设置为接收起始客户端发送的获取媒体传输路径的获取请求，其中，所述获取请求中携带有目的客户端；
获取模块，设置为根据所述获取请求获取所述起始客户端与所述目的客户端之间的最优媒体传输路径；
发送模块，设置为将所述最优媒体传输路径发送给所述起始客户端，以使所述起始客户端根据所述最优媒体传输路径与所述目的客户端进行数据传输。
根据本公开的又一个实施例，还提供了一种计算机可读的存储介质，所述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。
根据本公开的又一个实施例，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是本公开实施例的数据传输处理方法的设备的硬件结构框图；
图2是根据本公开实施例的数据传输处理方法的流程图；
图3是根据本公开可选实施例的数据传输处理方法的流程图；
图4是根据本公开实施例的全链路加速RTN系统组成的示意图；
图5是根据本公开实施例的客户端组成的框图；
图6是根据本公开实施例的封装传输路径后的数据包格式的示意图；
图7是根据本公开实施例的边缘节点组成的框图；
图8是根据本公开实施例的中转节点组成的框图；
图9是根据本公开实施例的全链路管理中心的框图；
图10是根据本公开实施例的数据传输处理装置的框图。
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公开的实施例。
需要说明的是，本公开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。
本公开实施例中所提供的方法实施例可以在设备或者类似的运算装置中执行。以运行在设备上为例，图1是本公开实施例的数据传输处理方法的设备的硬件结构框图，如图1所示，设备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MCU或可编程逻辑器件等的处理装置)和用于存储数据的存储器104，其中，上述设备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，其并不对上述设备的结构造成限定。例如，设备还可包括比图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，如本公开实施例中的数据传输处理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传输处理，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设备。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设备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。
在本实施例中提供了一种运行于上述设备的数据传输处理方法，图2是根据本公开实施例的数据传输处理方法的流程图，如图2所示，应用于全链路管理中心，该流程包括如下步骤：
步骤S202，接收起始客户端发送的获取媒体传输路径的获取请求，其中，所述获取请求中携带有目的客户端；
步骤S204，根据所述获取请求获取所述起始客户端与所述目的客户端之间的最优媒体传输路径；
步骤S206，将所述最优媒体传输路径发送给所述起始客户端，以使所述起始客户端根据所述最优媒体传输路径与所述目的客户端进行数据传输。
通过上述步骤S202至S206，可以解决相关技术中最优接入和路由调度分别由接入中心和路由调度中心分别进行处理，存在局部最优的问题，且对于端到端的音视频传输不一定是全局最优的问题，从全链路规划全局最优的媒体传输路径，打破局部最优问题，实现全链路加速。进一步提升音视频媒体传输的质量，进而提升用户体验。
图3是根据本公开可选实施例的数据传输处理方法的流程图，如图3所示，在上述步骤S202之前，所述方法还包括：
步骤S302，获取客户端与接入的边缘节点之间的链路数据、边缘节点与相连中转节点之间的链路数据以及中转节点之间的链路数据，其中，所述客户端包括所述起始客户端与所述目的客户端；
本实施例中，上述步骤S302具体可以包括：向所述客户端下发接入的边缘节点的信息，向所述边缘节点、所述中转节点下发相连中转节点的信息，并向所述客户端、所述边缘节点以及所述中转节点发送探测请求；接收所述客户端探测的与接入的边缘节点之间的链路数据，并接收所述边缘节点探测的与相连中转节点之间的链路数据、以及所述中转节点探测的相连中转节点之间的链路数据。
步骤S304，将目标链路数据转换为链路质量指数，其中，所述目标链路数据包括所述客户端与接入的边缘节点之间的链路数据、所述边缘节点与相连中转节点之间的链路数据以及所述中转节点之间的链路数据；
步骤S306，根据所述链路质量指数规划所有起始客户端与所有目的客户端之间的最优媒 体传输路径；
本实施例中，上述步骤S306具体可以包括：获取所述客户端、所述边缘节点以及所述中转节点的拓扑关系；根据所述拓扑关系与所述链路质量指数规划出所述链路质量指数最小的所述最优媒体传输路径。
步骤S308，将所有起始客户端、所有目的客户端以及所有最优媒体传输路径进行关联存储。
本实施例中，上述步骤S304具体可以包括：
S3041，确定所述目标链路数据的质量分数，进一步的，获取所述目标链路数据，其中，所述目标链路数据中每个链路数据均包括：丢包数据、延迟数据、抖动数据、可用带宽数据；分别对所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据进行平滑处理，得到平滑后的丢包数据、平滑后的延迟数据、平滑后的抖动数据、平滑后的可用带宽数据；根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述目标链路数据的质量分数；
在一实施例中，上述S3041中，分别对所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据进行平滑处理，得到平滑后的丢包数据、平滑后的延迟数据、平滑后的抖动数据、平滑后的可用带宽数据具体可以包括：确定标准化之后的丢包数据、标准化之后的延迟数据、标准化之后的抖动数据、标准化之后的可用带宽数据；确定当前丢包的平均丢包数据、当前丢包的平均延迟数据、当前丢包的平均抖动数据、当前丢包的平均可用带宽数据；根据所述标准化之后的丢包数据、所述标准化之后的延迟数据、所述标准化之后的抖动数据、所述标准化之后的可用带宽数据以及所述当前丢包的平均丢包数据、所述当前丢包的平均延迟数据、所述当前丢包的平均抖动数据、所述当前丢包的平均可用带宽数据确定所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据。
在另一实施例中，上述S3041中，根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述目标链路数据的质量分数具体可以包括：
分别通过以下方式确定所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据对应的趋势权重：



分别通过以下方式，根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述链路数据的质量分数：
Ql＝Lsmooth×Tl
Qd＝Dsmooth×Td
Qj＝Jsmooth×Tj
Qb＝Bsmooth×Tb；
其中，Lsmooth、Dsmooth、Jsmooth、Bsmooth分别为所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据；Tl、Td、Tj、Tb分别为所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据对应的趋势权重；Ql、Qd、Qj、Qb分别为丢包数据、延迟数据、抖动数据、可用带宽数据的质量分数；Lsmooth、Dsmooth、Jsmooth、Bsmooth分别为所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据；wlinc、wdinc、wjinc、wbinc分别为丢包、延时、抖动、丢包增加的趋势参数增加的趋势参数；wldec、wddec、wjdec、wbdec分别为丢包、延时、抖动、丢包减少的趋势参数增加的趋势参数。
S3042，根据所述目标链路数据的质量分数与对应的权重系数确定所述链路质量指数，进一步的，具体可以通过以下方式，确定所述链路质量指数包括：
Qlink＝Wl×Ql+Wd×Qd+Wj×Qj+Wb×Qb；
其中，Qlink为所述链路质量指数，Ql、Qd、Qj、Qb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的质量分数，Wl、Wd、Wj、Wb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的权重系数。
本实施例提出将当前RTN系统中最优接入和路由调度两部分相互独立的功能进行全局统一优化处理，将最优接入中心和路由调度中心进行融合形成全链路管理中心，从全链路规划全局最优的接入和路由调度方案，打破局部最优问题，实现真正意义的全链路加速。进一步提升音视频媒体传输的质量，进而提升用户体验。
图4是根据本公开实施例的全链路加速RTN系统组成的示意图，如图4所示，将当前RTN系统中最优接入中心和路由调度中心进行融合形成全链路管理中心，从全链路规划全局最优的接入和路由调度方案，打破局部最优问题，实现真正意义的全链路加速。
客户端为音视频终端或相关SDK，主要负责音视频业务的处理，路径信息查询和封装，并负责向边缘节点接入，涵盖音视频媒体展示部分和音视频媒体生成部分，例如，视频会议场景下包含PC客户端、手机移动客户端、会议室的会议中的终端；云桌面场景包含瘦终端、PC端、后端服务器；AR/VR场景下包含VR眼镜、终端头盔、后台服务器。
边缘节点负责客户端的接入，并具有数据收发能力，同时还负责接收路由调度中心的数据探测请求，并探测与其相连的中转节点的网络参数，探测数据包含丢包、延迟、抖动、带宽等，并负责将探测结果上报到全链路管理中心。
中转节点负责数据的高性能转发，同时还负责接收路由调度中心的数据探测请求，并探测与其相连的中转节点和边缘节点的网络参数，探测数据包含丢包、延迟、抖动、带宽以及节点负载等，并负责将探测结果上报到全链路管理中心。
全链路管理中心负责接入和转发链路的全局统一规划；不仅负责客户端到边缘节点的链路规划，还负责边缘点经过中转节点到达目的边缘节点之间的链路规划。还负责整体网络拓 扑的管理、链路探测请求下发到客户端、边缘节点和中转节点，并收集客户端、边缘节点和转发节点上报的链路网络参数数据，数据包含丢包、延迟、抖动、带宽等。
图5是根据本公开实施例的客户端组成的框图，如图5所示，本实施例中的全链路加速的音视频传输RTN系统中客户端的主要由媒体内容模块、路径管理模块、数据收发模块、链路探测模块组成。
媒体内容模块负责音视频媒体的生产/展示等相关业务的处理。
路径管理模块负责向全链路管理中心查询全局最优路径，并将路径信息和原始数据封装成新的数据包进行传输。图6是根据本公开实施例的封装传输路径后的数据包格式的示意图，封装后的格式如图6所示，负责接收到封装后数据转换为原始数据的转换。
数据收发模块负责数据的接收，同时也兼有按照传输路径中指示的路径信息将数据发送到下一跳的功能。
链路探测模块负责向全链路管理中心的全链路规划模块进行注册并接收其下发的探测请求指令，指令中会包含需要边探测的具体节点，接收指令后随机进行链路探测，探测指标包含丢包、延迟、抖动、带宽以及负载等，探测完成后将探测的具体参数定时发送到全链路管理中心的全链路规划模块。
图7是根据本公开实施例的边缘节点组成的框图，如图7所示，本实施例中的全链路加速的音视频传输RTN系统中边缘节点的主要由客户端接入模块、数据收发模块、链路探测模块组成。
客户端接入模块负责客户端的接入功能。
数据收发模块负责数据的接收，同时也兼有按照传输路径中指示的路径信息将数据发送到下一跳的功能。
链路探测模块负责向全链路管理中心的全链路规划模块进行注册并接收其下发的探测请求指令，指令中会包含需要边探测的具体节点，接收指令后随机进行链路探测，探测指标包含丢包、延迟、抖动、带宽以及负载等，探测完成后将探测的具体参数定时发送到全链路管理中心的全链路规划模块。
图8是根据本公开实施例的中转节点组成的框图，如图8所示，本公开实施例的全链路加速的音视频传输RTN系统中中转节点的主要由数据收发模块、链路探测模块组成。
数据收发模块负责数据的高性能接收，同时也兼有按照传输路径中指示的路径信息将数高性能发送到下一跳的功能。
链路探测模块负责向全链路管理中心的全链路规划模块进行注册并接收其下发的探测请求指令，指令中会包含需要边探测的具体节点，接收指令后随机进行链路探测，探测指标包含丢包、延迟、抖动、带宽以及负载等，探测完成后将探测的具体参数定时发送到全链路管理中心的全链路规划模块。
图9是根据本公开实施例的全链路管理中心的框图，如图9所示，本实施例的全链路加速的音视频传输RTN系统中中转节点的主要由拓扑管理模块、探测管理模块、全链路规划模块组成。
拓扑管理模块负责整个RTN网络的拓扑关系的管理，包含边缘节点和中转节点的增加、删除操作，节点之间连接关系的变更操作。同时负责客户端、边缘节点、转发节点的注册功能。
探测管理模块负责向客户端、边缘节点和中转节点下发探测请求，并负责接收边缘节点和中转节点的探测数据，同时还负责将具体的链路参数转换为具体的链路质量指数。具体的转换模型如公式(7-1)下：
Qlink＝Wl×Ql+Wd×Qd+Wj×Qj+Wb×Qb   (7-1)
其中，Qlink为所述链路质量指数，Ql、Qd、Qj、Qb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的质量分数，Wl、Wd、Wj、Wb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的权重系数；Qlink的分数越小表明链路质量越好。Ql、Qd、Qj、Qb分别为丢包、延迟、抖动、可用带宽对应的质量分数，分数越小表明相关参数质量越好。Wl、Wd、Wj、Wb分别为丢包质量参数、延迟质量参数、抖动质量参数、可用带宽质量参数，Wl、Wd、Wj、Wb的和为1，其具体的取值可根据具体的业务场景指定。例如，在视频会议场景下Wl＝0.3、Wd＝0.35、Wj＝0.25、Wb＝0.1；在OTT点播场景下Wl＝0.25、Wd＝0.1、Wj＝0.25、Wb＝0.4；在互动直播场景下Wl＝0.3、Wd＝0.3、Wj＝0.25、Wb＝0.15。
Ql、Qd、Qj、Qb丢包、延迟、抖动、可用带宽对应的质量分数的计算方法如公式7-2所示。
其中，Lsmooth表示平滑后的丢包数据，Tl表示趋势权重，表明丢包变化的趋势，表示丢包是增加还是减少。
Dsmooth表示平滑后的延迟数据，Td表示趋势权重，表明延迟变化的趋势，表示延迟是增加还是减少。
Dsmooth表示平滑后的抖动数据，Td表示趋势权重，表明抖动变化的趋势，表示抖动是增加还是减少。
Bsmooth表示平滑后的可用带宽数据，Tb表示趋势权重，表明丢可用带宽变化的趋势，表示可用带宽是增加还是减少。
Lsmooth、Dsmooth、Jsmooth和Bsmooth的计算方式如公式7-3所示。
其中，其中，Lsmooth、Dsmooth、Jsmooth、Bsmooth分别为所述平滑后的丢包数据、所述平滑后 的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据；Lstd、Dstd、Jstd、Bstd分别为所述标准化之后的丢包数据、所述标准化之后的延迟数据、所述标准化之后的抖动数据、所述标准化之后的可用带宽数据；Lavg、Davg、Javg、Bavg分别为所述当前丢包的平均丢包数据、所述当前丢包的平均延迟数据、所述当前丢包的平均抖动数据、所述当前丢包的平均可用带宽数据；
α表示平滑参数，默认为0.8，也可以根据实际效果调整。
Lstd、Dstd、Jstd和Bstd标准化数据计算公式如7-4所示。
其中，L表示原始丢包率，原始丢包率的数据范围为0-1，Lstd标准化之后的数据范围为0-5。D表示原始延迟数据，原始延迟的数据范围为0-2000ms，超过20000ms的延迟数据设置为20000ms，Dstd标准化之后的数据范围为0-5。J表示原始抖动数据，原始抖动的数据范围为0-2000ms，超过20000ms的抖动数据设置为20000ms，Dstd标准化之后的数据范围为0-5。B表示原始可用带宽，原始可用带宽的数据范围为0-100000Mbps(10Gbps)，Bstd标准化之后的数据范围为1-5。
Tl、Td、Tj、Tb趋势权重如公式7-5所示。
其中，wlinc为丢包增加的趋势参数，默认为1.2，也可以根据实际效果调整。wldec为丢包减少趋势参数，默认为0.8，也可以根据实际效果调整。L(i)smooth表示当前时刻的平滑丢包参数，L(i-1)smooth表示上一采样时刻的平滑丢包参数。
wdinc为延迟增加的趋势参数，默认为1.2，也可以根据实际效果调整。wddec为延迟减少趋势参数，默认为0.8，也可以根据实际效果调整。D(i)smooth表示当前时刻的平滑延迟参数，D(i-1)smooth表示上一采样时刻的平滑延迟参数。
wjinc为抖动增加的趋势参数，默认为1.2，也可以根据实际效果调整。wjdec为抖动减少趋势参数，默认为0.8，也可以根据实际效果调整。J(i)smooth表示当前时刻的平滑抖动参数，J(i-1)smooth表示上一采样时刻的平滑抖动参数。
wbinc为可用带宽增加的趋势参数，默认为1.2，也可以根据实际效果调整。wbdec为可用带宽减少趋势参数，默认为0.8，也可以根据实际效果调整。L(i)smooth表示当前时刻的平滑可用带宽参数，L(i-1)smooth表示上一采样时刻的平滑可用带宽参数。
全链路规划模块负责根据客户端、边缘节点和中转节点的拓扑关系和基于探测数据的链路质量指出实时进行接入和转发链路的全局统一规划，实时规划出的全局最优传输链路信息保存在内存中供客户端查询使用。值得指出的是，在根据拓扑关系和链路质量指数进行全局规划的过程中，不仅支持无向图的规划，同时还是支持有向图的规划，同时在规划过程中还将连路径跳数作为惩罚参数加入规划算法，因为链路质量指数相同的两条链路，跳数更少的链路由于转发跳数少，故障率低等因素会有更好的传输质量。
本实施例提出的全链路加速的RTN系统方法流程如下：
步骤1，客户端、边缘节点、中转节点向全链路管理中心的拓扑管理模块进行注册；
步骤2，注册完成后，全链路管理中心的拓扑管理模块将用户配置的RTN系统中客户端、边缘节点和中转节点及其之间链接关系保存。
步骤3，拓扑关系配置完成后，全链路管理中心的探测管理模块向客户下发可供客户端接入的边缘节点信息；向各个边缘节点和中转节点下发与本节点相连的节点信息，并指示其开始探测；
步骤4，客户端中的链路探测模块收到探测请求后，随即开始动态探测与其相连的边缘节点之间链路的数据信息，包含丢包、延迟、抖动、带宽、负载等，并将相关数据信息上报到全链路管理中心的探测管理模块；
步骤5，边缘节点的链路探测模块和中转节点的链路探测模块收到探测请求后，随即开始动态探测与其相连的中转节点之间的数据信息，包含丢包、延迟、抖动、带宽、负载等，并将相关数据信息上报到全链路管理中心的探测管理模块；
步骤6，全链路管理中心的探测管理模块在在接收到相关的探测数据后，将探测数据交由全链路规划模块通过链路质量量化模型将丢包、延迟、抖动、带宽、负载等链路参数量化为具体的链路质量指数，数值越小表明链路质量越高；
步骤7，全链路管理中心的全链路规划模块会根据实时的链路质量指数，通过路径规划算法动态规划出客户端之间媒体传输的最优路径，并存储在内存；
步骤8，客户端A在发送媒体数据到客户端B之前，会向全链路管理中心的全链路规划模块查询获取全局最优的媒体传输路径，并将全局最优的传输路径和原始数据进行封装，格式参见图7所示。
步骤9，数据封装完成后，客户端A的数据收发模块按照传输路径中指示的路径信息将数据发送到边缘节点。
步骤10，边缘节点的数据收发模块收到包含足有路径信息的数据包后，根据路径信息指示将数据包转发到对应转发节点；
步骤11，转发节点的数据收发模块收到包含足有路径信息的数据包后，根据路径信息指示将数据包转发到对应下一跳，直至发送到目的客户端B连接的边缘节点；
步骤12，客户端B连接的边缘节点的数据收发模块在收到数据后，会将数据中路径相关信息剥离，将原始数据按照路径信息中的指示发送到客户端B。
至此，完成了媒体数据从客户端A经过全局最优路径传输到客户端B的过程。
根据本公开的另一个实施例，还提供了一种数据传输处理装置，图10是根据本公开实施例的数据传输处理装置的框图，如图10所示，应用于全链路管理中心，所述装置包括：
接收模块102，设置为接收起始客户端发送的获取媒体传输路径的获取请求，其中，所述获取请求中携带有目的客户端；
获取模块104，设置为根据所述获取请求获取所述起始客户端与所述目的客户端之间的最优媒体传输路径；
发送模块106，设置为将所述最优媒体传输路径发送给所述起始客户端，以使所述起始客户端根据所述最优媒体传输路径与所述目的客户端进行数据传输。
在一实施例中，所述装置还包括：
获取模块，设置为获取客户端与接入的边缘节点之间的链路数据、边缘节点与相连中转节点之间的链路数据以及中转节点之间的链路数据，其中，所述客户端包括所述起始客户端与所述目的客户端；
转换模块，设置为将目标链路数据转换为链路质量指数，其中，所述目标链路数据包括所述客户端与接入的边缘节点之间的链路数据、所述边缘节点与相连中转节点之间的链路数据以及所述中转节点之间的链路数据；
规划模块，设置为根据所述链路质量指数规划所有起始客户端与所有目的客户端之间的最优媒体传输路径；
关联存储模块，设置为将所有起始客户端、所有目的客户端以及所有最优媒体传输路径进行关联存储。
在一实施例中，所述获取模块，还设置为向所述客户端下发接入的边缘节点的信息，向所述边缘节点、所述中转节点下发相连中转节点的信息，并向所述客户端、所述边缘节点以及所述中转节点发送探测请求；接收所述客户端探测的与接入的边缘节点之间的链路数据，并接收所述边缘节点探测的与相连中转节点之间的链路数据、以及所述中转节点探测的相连中转节点之间的链路数据。
在一实施例中，所述规划模块，还设置为获取所述客户端、所述边缘节点以及所述中转节点的拓扑关系；根据所述拓扑关系与所述链路质量指数规划出所述链路质量指数最小的所述最优媒体传输路径。
在一实施例中，所述转换模块包括：
第一确定子模块，设置为确定所述目标链路数据的质量分数；
第二确定子模块，设置为根据所述目标链路数据的质量分数与对应的权重系数确定所述链路质量指数。
在一实施例中，所述第一确定子模块包括：
获取单元，用于获取所述目标链路数据，其中，所述目标链路数据中每个链路数据均包括：丢包数据、延迟数据、抖动数据、可用带宽数据；
平滑处理单元，用于分别对所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据进行平滑处理，得到平滑后的丢包数据、平滑后的延迟数据、平滑后的抖动数据、平滑后的可用带宽数据；
确定单元，用于根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述目标链路数据的质量分数。
在一实施例中，所述平滑处理单元，还用于确定标准化之后的丢包数据、标准化之后的延迟数据、标准化之后的抖动数据、标准化之后的可用带宽数据；
确定当前丢包的平均丢包数据、当前丢包的平均延迟数据、当前丢包的平均抖动数据、当前丢包的平均可用带宽数据；
根据所述标准化之后的丢包数据、所述标准化之后的延迟数据、所述标准化之后的抖动数据、所述标准化之后的可用带宽数据以及所述当前丢包的平均丢包数据、所述当前丢包的平均延迟数据、所述当前丢包的平均抖动数据、所述当前丢包的平均可用带宽数据确定所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据。
在一实施例中，所述确定单元，还用于分别通过以下方式确定所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据对应的趋势权重：



分别通过以下方式，根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述链路数据的质量分数：
Ql＝Lsmooth×Tl
Qd＝Dsmooth×Td
Qj＝Jsmooth×Tj
Qb＝Bsmooth×Tb；
其中，Lsmooth、Dsmooth、Jsmooth、Bsmooth分别为所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据；Tl、Td、Tj、Tb分别为所述平 滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据对应的趋势权重；Ql、Qd、Qj、Qb分别为丢包数据、延迟数据、抖动数据、可用带宽数据的质量分数；Lsmooth、Dsmooth、Jsmooth、Bsmooth分别为所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据；wlinc、wdinc、wjinc、wbinc分别为丢包、延时、抖动、丢包增加的趋势参数增加的趋势参数；wldec、wddec、wjdec、wbdec分别为丢包、延时、抖动、丢包减少的趋势参数增加的趋势参数。
在一实施例中，所述第二确定子模块，设置为通过以下方式，根据所述目标链路数据的质量分数与对应的权重系数确定所述链路质量指数包括：
Qlink＝Wl×Ql+Wd×Qd+Wj×Qj+Wb×Qb；
其中，Qlink为所述链路质量指数，Ql、Qd、Qj、Qb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的质量分数，Wl、Wd、Wj、Wb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的权重系数。
本公开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-0nly 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。
本公开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，上述的本公开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，本公开不限制于任何特定的硬件和软件结合。
以上所述仅为本公开的优选实施例而已，并不用于限制本公开，对于本领域的技术人员来说，本公开可以有各种更改和变化。凡在本公开的原则之内，所作的任何修改、等同替换、改进等，均应包含在本公开的保护范围之内。

Claims (12)

  1. 一种数据传输处理方法，应用于全链路管理中心，所述方法包括：
    接收起始客户端发送的获取媒体传输路径的获取请求，其中，所述获取请求中携带有目的客户端；
    根据所述获取请求获取所述起始客户端与所述目的客户端之间的最优媒体传输路径；
    将所述最优媒体传输路径发送给所述起始客户端，以使所述起始客户端根据所述最优媒体传输路径与所述目的客户端进行数据传输。
  2. 根据权利要求1所述的方法，其中，在所述接收起始客户端发送的获取媒体传输路径的获取请求之前，所述方法还包括：
    获取客户端与接入的边缘节点之间的链路数据、边缘节点与相连中转节点之间的链路数据以及中转节点之间的链路数据，其中，所述客户端包括所述起始客户端与所述目的客户端；
    将目标链路数据转换为链路质量指数，其中，所述目标链路数据包括所述客户端与接入的边缘节点之间的链路数据、所述边缘节点与相连中转节点之间的链路数据以及所述中转节点之间的链路数据；
    根据所述链路质量指数规划所有起始客户端与所有目的客户端之间的最优媒体传输路径；
    将所有起始客户端、所有目的客户端以及所有最优媒体传输路径进行关联存储。
  3. 根据权利要求2所述的方法，其中，获取客户端与接入的边缘节点之间的链路数据、边缘节点与相连中转节点之间的链路数据以及中转节点之间的链路数据包括：
    向所述客户端下发接入的边缘节点的信息，向所述边缘节点、所述中转节点下发相连中转节点的信息，并向所述客户端、所述边缘节点以及所述中转节点发送探测请求；
    接收所述客户端探测的与接入的边缘节点之间的链路数据，并接收所述边缘节点探测的与相连中转节点之间的链路数据、以及所述中转节点探测的相连中转节点之间的链路数据。
  4. 根据权利要求2所述的方法，其中，根据所述目标链路质量指数规划所有起始客户端与所有目的客户端之间的最优媒体传输路径包括：
    获取所述客户端、所述边缘节点以及所述中转节点的拓扑关系；
    根据所述拓扑关系与所述链路质量指数规划出所述链路质量指数最小的所述最优媒体传输路径。
  5. 根据权利要求2所述的方法，其中，将所述目标链路数据转换为链路质量指数包括：
    确定所述目标链路数据的质量分数；
    根据所述目标链路数据的质量分数与对应的权重系数确定所述链路质量指数。
  6. 根据权利要求5所述的方法，其中，确定所述目标链路数据的质量分数包括：
    获取所述目标链路数据，其中，所述目标链路数据中每个链路数据均包括：丢包数据、延迟数据、抖动数据、可用带宽数据；
    分别对所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据进行平滑处理，得到平滑后的丢包数据、平滑后的延迟数据、平滑后的抖动数据、平滑后的可用带宽数据；
    根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述目标链路数据的质量分数。
  7. 根据权利要求6所述的方法，其中，分别对所述丢包数据、所述延迟数据、所述抖动 数据、所述可用带宽数据进行平滑处理，得到平滑后的丢包数据、平滑后的延迟数据、平滑后的抖动数据、平滑后的可用带宽数据包括：
    确定标准化之后的丢包数据、标准化之后的延迟数据、标准化之后的抖动数据、标准化之后的可用带宽数据；
    确定当前丢包的平均丢包数据、当前丢包的平均延迟数据、当前丢包的平均抖动数据、当前丢包的平均可用带宽数据；
    根据所述标准化之后的丢包数据、所述标准化之后的延迟数据、所述标准化之后的抖动数据、所述标准化之后的可用带宽数据以及所述当前丢包的平均丢包数据、所述当前丢包的平均延迟数据、所述当前丢包的平均抖动数据、所述当前丢包的平均可用带宽数据确定所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据。
  8. 根据权利要求6所述的方法，其中，根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述目标链路数据的质量分数包括：
    分别通过以下方式确定所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据对应的趋势权重：



    分别通过以下方式，根据所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据以及对应的趋势权重确定所述链路数据的质量分数：
    Ql＝Lsmooth×Tl
    Qd＝Dsmooth×Td
    Qj＝Jsmooth×Tj
    Qb＝Bsmooth×Tb；
    其中，Lsmooth、Dsmooth、Jsmooth、Bsmooth分别为所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据；Tl、Td、Tj、Tb分别为所述平滑后的丢包数据、所述平滑后的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据对应的趋势权重；Ql、Qd、Qj、Qb分别为丢包数据、延迟数据、抖动数据、可用带宽数据的质量分数；Lsmooth、Dsmooth、Jsmooth、Bsmooth分别为所述平滑后的丢包数据、所述平滑后 的延迟数据、所述平滑后的抖动数据、所述平滑后的可用带宽数据；wlinc、wdinc、wjinc、wbinc分别为丢包、延时、抖动、丢包增加的趋势参数增加的趋势参数；wldec、wddec、wjdec、wbdec分别为丢包、延时、抖动、丢包减少的趋势参数增加的趋势参数。
  9. 根据权利要求6所述的方法，其中，根据所述目标链路数据的质量分数与对应的权重系数确定所述链路质量指数包括：
    Qlink＝Wl×Ql+Wd×Qd+Qj×Qj+Wb×Qb；
    其中，Qlink为所述链路质量指数，Ql、Qd、Qj、Qb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的质量分数，Wl、Wd、Wj、Wb分别为所述丢包数据、所述延迟数据、所述抖动数据、所述可用带宽数据的权重系数。
  10. 一种数据传输处理装置，应用于全链路管理中心，所述装置包括：
    接收模块，设置为接收起始客户端发送的获取媒体传输路径的获取请求，其中，所述获取请求中携带有目的客户端；
    获取模块，设置为根据所述获取请求获取所述起始客户端与所述目的客户端之间的最优媒体传输路径；
    发送模块，设置为将所述最优媒体传输路径发送给所述起始客户端，以使所述起始客户端根据所述最优媒体传输路径与所述目的客户端进行数据传输。
  11. 一种计算机可读的存储介质，所述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所述权利要求1至9任一项中所述的方法。
  12. 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所述权利要求1至9任一项中所述的方法。
PCT/CN2023/105174 2022-11-08 2023-06-30 一种数据传输处理方法、装置、存储介质及电子装置 WO2024098814A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211395987.2A CN118041857A (zh) 2022-11-08 2022-11-08 一种数据传输处理方法、装置、存储介质及电子装置
CN202211395987.2 2022-11-08

Publications (1)

Publication Number Publication Date
WO2024098814A1 true WO2024098814A1 (zh) 2024-05-16

Family

ID=91000995

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/105174 WO2024098814A1 (zh) 2022-11-08 2023-06-30 一种数据传输处理方法、装置、存储介质及电子装置

Country Status (2)

Country Link
CN (1) CN118041857A (zh)
WO (1) WO2024098814A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104579961A (zh) * 2013-10-11 2015-04-29 中国移动通信集团公司 数据报文的调度方法及装置
CN107682264A (zh) * 2017-09-26 2018-02-09 迅雷计算机（深圳）有限公司 基于实时动态路径规划的数据传输方法和系统
WO2018112877A1 (zh) * 2016-12-23 2018-06-28 深圳前海达闼云端智能科技有限公司 路径计算和访问请求分发方法、装置及系统
CN110809054A (zh) * 2019-11-11 2020-02-18 腾讯科技（深圳）有限公司 数据传输方法、装置、设备和存储介质
US20200162378A1 (en) * 2018-11-19 2020-05-21 Zhan Ma Method And System For Accelerating Interactive-Streaming-Based Applications Via Cloud Overlay Networks
CN113904974A (zh) * 2021-10-09 2022-01-07 咪咕文化科技有限公司 智能路由方法、装置及设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104579961A (zh) * 2013-10-11 2015-04-29 中国移动通信集团公司 数据报文的调度方法及装置
WO2018112877A1 (zh) * 2016-12-23 2018-06-28 深圳前海达闼云端智能科技有限公司 路径计算和访问请求分发方法、装置及系统
CN107682264A (zh) * 2017-09-26 2018-02-09 迅雷计算机（深圳）有限公司 基于实时动态路径规划的数据传输方法和系统
US20200162378A1 (en) * 2018-11-19 2020-05-21 Zhan Ma Method And System For Accelerating Interactive-Streaming-Based Applications Via Cloud Overlay Networks
CN110809054A (zh) * 2019-11-11 2020-02-18 腾讯科技（深圳）有限公司 数据传输方法、装置、设备和存储介质
CN113904974A (zh) * 2021-10-09 2022-01-07 咪咕文化科技有限公司 智能路由方法、装置及设备

Also Published As

Publication number Publication date
CN118041857A (zh) 2024-05-14

Similar Documents

Publication Publication Date Title
CN108494681B (zh) 多链路的数据流传输方法、无线通信设备及存储介质
US20170244792A1 (en) Power-Line Carrier Terminal Control Apparatus, System, and Method
CN114374647B (zh) 一种对时敏业务流和路由联合调度的规划方法及装置
WO2024098815A1 (zh) 一种数据传输处理方法、装置、存储介质及电子装置
CN102291465B (zh) 负载均衡方法、装置和系统
US12101710B2 (en) Data processing method and apparatus, network element device, storage medium, and program product
CN110381162A (zh) 一种业务处理的方法以及相关装置
CN114553779A (zh) 网络拥塞控制方法、节点、系统及存储介质
TWI531186B (zh) 多重介面網路裝置與網路封包傳送選擇方法
CN105262836A (zh) 服务器推送信息的方法及客户端接收推送信息的方法
WO2014190642A1 (zh) 一种媒体数据的传输方法、装置和系统
WO2022111329A1 (zh) 报文处理方法及设备
US8948050B2 (en) Distribution system, distribution method, and memory medium thereof
US20120102162A1 (en) Dynamic bandwidth adjustment for multiple service support
US8681760B2 (en) Network positioning system and terminal positioning device
CN116915688B (zh) 一种实时音视频传输网络的数据传输方法及系统
CN110072196B (zh) 为命名数据网络提供面向区块链应用的通信方法及系统
US10531168B2 (en) Low-latency data switching device and method
CN103763206A (zh) 一种网络调度方法及网关
CN110048906B (zh) 一种判断节点传输质量的方法、系统、装置及服务器
WO2017041534A1 (zh) 一种电力线网络通信的方法及装置、计算机存储介质
CN111385131A (zh) 网络设备的配置方法、装置、设备及系统
WO2024098814A1 (zh) 一种数据传输处理方法、装置、存储介质及电子装置
CN110417875B (zh) 一种云服务器之间的对接方法、系统、设备及存储介质
WO2015096734A1 (zh) 一种业务数据的下行传输方法及分组数据网关

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23887510

Country of ref document: EP

Kind code of ref document: A1