WO2023082431A1 - 一种多口字环形结构下的流量调度方法和系统 - Google Patents

一种多口字环形结构下的流量调度方法和系统 Download PDF

Info

Publication number
WO2023082431A1
WO2023082431A1 PCT/CN2021/139854 CN2021139854W WO2023082431A1 WO 2023082431 A1 WO2023082431 A1 WO 2023082431A1 CN 2021139854 W CN2021139854 W CN 2021139854W WO 2023082431 A1 WO2023082431 A1 WO 2023082431A1
Authority
WO
WIPO (PCT)
Prior art keywords
network
path
candidate
paths
determining
Prior art date
Application number
PCT/CN2021/139854
Other languages
English (en)
French (fr)
Inventor
王玉梁
薛希俊
李忠
张宇峰
李金岭
徐俊华
朱文进
刘少卿
张宇
Original Assignee
中电信数智科技有限公司
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 中电信数智科技有限公司 filed Critical 中电信数智科技有限公司
Publication of WO2023082431A1 publication Critical patent/WO2023082431A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/12Avoiding congestion; Recovering from congestion
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/22Alternate routing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/24Traffic characterised by specific attributes, e.g. priority or QoS

Definitions

  • the present invention relates to the technical field of computer networks, in particular to a flow scheduling method, system, electronic equipment and storage medium in a multi-word ring structure.
  • SDN Software Defined Network
  • SDN technology for traffic scheduling is a current research hotspot, but routing is generally based on the shortest link algorithm, and then extended to K shortest links, heuristic search algorithm, load balancing algorithm ECMP, adaptive multi-objective optimized routing Algorithm AMOGR et al.
  • these algorithms can find one or K shortest routing links that meet the requirements, data flows are easily aggregated because they choose the same forwarding link, resulting in network congestion, which greatly reduces link utilization.
  • nodes that have already generated congestion they cannot be processed or the processing time is too long.
  • the invention provides a traffic dispatching method under a multi-port ring structure to solve the technical problems in the prior art, such as path planning of service traffic in the network and traffic congestion of the backbone network.
  • the first aspect of the present invention provides a traffic scheduling method under a multi-port ring structure, including: obtaining the global network state of the topological network, wherein the topological network includes multiple levels, and the multi-level topological network includes V nodes, the V nodes constitute a plurality of network links; when a network link in the topological network fails, an alternative path is determined according to the state of the grid, wherein the alternative path Including one or more; when there are multiple candidate paths, the priority of the multiple candidate paths is determined according to constraint conditions, wherein the priority is used to indicate the order of transmitting data traffic.
  • the determining an alternative path according to the grid state includes:
  • the determining the alternative path according to the grid state includes: acquiring a traffic scheduling threshold;
  • the path of the network delay threshold and the traffic scheduling threshold is determined as the candidate path.
  • the determining the candidate path according to the grid state includes: calculating the bandwidth utilization rate of each path in the plurality of candidate paths; A link is determined as the candidate path, where the constraint condition includes the bandwidth utilization rate, and the candidate paths include one or more.
  • the method further includes: generating a command line corresponding to the device side, And send it to the device through the interface.
  • the method further includes: when the topological network is an n-level multi-word ring network topology and the abnormal position is i, the candidate path P from the first level to the nth level network is: Wherein, 1 ⁇ i ⁇ n, the candidate path is determined from the candidate path P according to the constraint condition, wherein the constraint condition includes network delay, bandwidth utilization rate, remaining bandwidth or multiple constraint conditions in accordance with Constraints for combining proportions.
  • a second aspect of the present invention provides a traffic scheduling system under a multi-port ring structure, including: an acquisition unit, configured to acquire the global network status of a topological network, wherein the topological network includes multiple levels, the The multi-level topology network includes V nodes, and the V nodes form a plurality of network links; the first determining unit is configured to, in the case of a network link failure in the topology network, according to the grid state Determine alternative paths, wherein the alternative paths include one or more; a second determination unit is configured to determine the number of alternative paths according to constraints when there are multiple alternative paths Priority, where the priority is used to indicate the order of transmitting data traffic.
  • the first determining unit includes: a first determining module, configured to determine a path satisfying a traffic scheduling threshold among the plurality of network paths as the candidate path, wherein the candidate path includes one or more.
  • the first determination unit includes: an acquisition module, configured to acquire a traffic scheduling threshold; a first calculation module, configured to calculate the network delay of each link in the plurality of candidate paths, wherein, The constraint conditions include the network delay, and the alternative paths include one or more; the second determination module is configured to select the path that satisfies the network delay threshold and the traffic scheduling threshold among the plurality of network paths Determined as the alternative path.
  • the first determination unit includes: a second calculation module, configured to calculate the bandwidth utilization of each link in the plurality of candidate paths; a third determination module, configured to combine the plurality of A path that satisfies a bandwidth utilization threshold among network paths is determined as the candidate path, where the constraint condition includes the bandwidth utilization rate, and the candidate paths include one or more.
  • the system further includes: a sending unit, configured to generate a device-side corresponding The command line is issued to the device through the interface; the calculation unit is used to calculate the network from the first level to the nth level when the topological network is an n-level multi-port word ring network topology and the abnormal position is i.
  • the candidate path P of is: Wherein, 1 ⁇ i ⁇ n, the third determination unit is configured to determine the candidate path from the candidate paths P according to the constraints, wherein the constraints include network delay, bandwidth utilization, remaining Bandwidth or constraints that combine multiple constraints proportionally.
  • a third aspect of the present invention provides a computer-readable storage medium, which is characterized in that a computer program is stored in the storage medium, wherein the computer program is set to execute the above-mentioned multi-word loop The traffic scheduling method under the structure.
  • a fourth aspect of the present invention 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 above multiple A traffic scheduling method under the Zizi ring structure.
  • the multi-level topological network includes V nodes, and the V nodes form a plurality of network links; the network links in the topological network
  • Fig. 1 is a flow chart of a flow scheduling method under an optional multi-word ring structure according to an embodiment of the present invention
  • Fig. 2 is a kind of optional 5-stage multi-port word ring network structure schematic diagram according to the embodiment of the present invention
  • Fig. 3 is a schematic diagram of alternative path calculation when an optional five-level multi-word ring structure is abnormal according to an embodiment of the present invention
  • FIG. 4 is a flow chart of an optional flow scheduling calculation scheme according to an embodiment of the present invention.
  • Fig. 5 is a schematic diagram of an optional centralized controllable solution according to an embodiment of the present invention.
  • Fig. 6 is a structural block diagram of a traffic scheduling system in a multi-port ring structure according to an embodiment of the present invention.
  • Fig. 1 is a flowchart of a traffic scheduling method under a multi-port ring structure according to an embodiment of the present invention, as shown in Fig. 1 , the traffic scheduling The method flow includes the following steps:
  • Step S202 acquiring the global network state of the topological network, wherein the topological network includes multiple levels, the multi-level topological network includes V nodes, and the V nodes form a plurality of network links.
  • Step S204 when a network link in the topological network fails, determine an alternative path according to the state of the grid, where the alternative path includes one or more.
  • step S206 when there are multiple candidate paths, priorities of the multiple candidate paths are determined according to constraint conditions, where the priority is used to represent the sequence of data traffic transmission.
  • the topology network may include, but not limited to, a multi-port ring network whose topology is T(V, L), with a total of n levels.
  • V is all the nodes in the network
  • v is one of the nodes
  • S is the source node
  • D is the destination node
  • L is all the links in the network
  • l is one of the paths.
  • R1 and R2 are routers at the same level in the network, and so on, R3, R4, R5, R6, ..., R(2n+1), R(2n+2) are routers at the same level respectively.
  • the alternative paths from the first level to the n-level network are (calculated after a path flow between the same levels):
  • calculate the normalization coefficient under the constraints Determine the set of candidate paths subject to constraints. Determine thresholds for traffic scheduling under constraints.
  • a library of available alternative paths is determined by a threshold, and each element in the library of available alternative paths is prioritized.
  • the priority sorting can be arranged according to the order of constraints from largest to smallest, or from smallest to largest.
  • the global network state of the topological network is obtained, wherein the topological network includes multiple levels, the multi-level topological network includes V nodes, and the V nodes form a plurality of network links; the network links in the topological network
  • determining the candidate path according to the grid state may include: determining a path satisfying a traffic scheduling threshold among multiple network paths as the candidate path, where the candidate path includes one or more paths.
  • determining the alternative path according to the grid state may include: obtaining a traffic scheduling threshold; calculating the network delay of each link in multiple alternative paths, wherein the constraints include network delay, and the alternative paths include One or more; determine the path that satisfies the network delay threshold and the traffic scheduling threshold among the multiple network links as the candidate path.
  • determining the candidate path according to the grid state may include: calculating the bandwidth utilization rate of each link in the multiple candidate paths; determining the link that meets the bandwidth utilization threshold in the multiple network paths as the candidate Paths, where the constraints include bandwidth utilization, and the candidate links include one or more.
  • the above method may further include: generating a command line corresponding to the device side, and sending it to the equipment.
  • the above method may also include: when the topological network is an n-level multi-port ring network topology and the abnormal position is i, the candidate path P from the first level to the nth level network is: Wherein, 1 ⁇ i ⁇ n, the candidate path is determined from the candidate paths P according to the constraint conditions, wherein the constraint conditions include network delay, bandwidth utilization, remaining bandwidth, or a proportional combination of multiple constraint conditions.
  • the present invention also provides a flow scheduling method in a multi-port ring structure.
  • FIG. 2 a structural diagram of a flow scheduling method under a multi-port ring structure.
  • Step S301 start;
  • Step S302 obtaining multi-port ring network topology T (V, L), source node S, destination node D, network level n, and abnormal location i;
  • the topology of the multi-port ring network is T(V, L), with n levels in total.
  • V is all the nodes in the network
  • v is one of the nodes
  • S is the source node
  • D is the destination node
  • L is all the links in the network
  • l is one of the paths.
  • R1 and R2 are routers at the same level in the network, and so on, R3, R4, R5, R6, ..., R(2n+1), R(2n+2) are routers at the same level respectively.
  • Step S303 calculating all optional paths P
  • Step S304 in the case of setting the user policy, execute step S305, and in the case of not setting the user policy, execute step S306;
  • Step S305 in the case of delay calculation, execute step S306, and in the case of not delay calculation, execute step S309;
  • Step S306 for each path p, calculate the network delay tp;
  • Step S307 obtain the alternative path T from the network time delay tp;
  • Step S308 for each path p, calculate the available network delay path set BL(T) (equivalent to the candidate link);
  • Step S309 in the case of calculating according to the bandwidth utilization rate, execute step S310, and in the case of not calculating according to the bandwidth utilization rate, execute step S313;
  • Step S310 for each path p, calculate the bandwidth utilization rate up;
  • Step S311 obtain the alternative path U from the bandwidth utilization rate up;
  • Step S312 for each path p, calculate the available bandwidth utilization path set BL(U);
  • Step S315, obtain the alternative path TU from the mixing parameter utp;
  • Step S316 for each path p, calculate the available hybrid parameter path set BL(TU);
  • Step S317 in the case of calculating according to any artificially set parameter x, execute step S317, and in the case of not calculating according to parameter x, execute step S321;
  • Step S319 from the parameter data xp, obtain an alternative path set X of xp;
  • Step S320 for each path p, calculate the available parameter data path set BL(X);
  • the traffic scheduling method under the multi-port ring structure includes a traffic scheduling calculation scheme and a centralized controllable scheme.
  • the traffic scheduling scheme calculates the available alternative paths through the real-time global network status, and prioritizes the alternative paths according to the constraint conditions.
  • the constraint conditions can be one or more, which can be defined by the user.
  • the centralized controllable solution is to centrally collect the state of the global network through the software platform and with the help of the SDN controller, provide data for the traffic scheduling calculation scheme, and automatically send the output results of the traffic calculation scheduling scheme to the network.
  • the traffic scheduling calculation scheme includes the following contents:
  • V is all nodes in the network
  • v is one of the nodes
  • S is the source node
  • D is the destination node
  • L is all the links in the network
  • l is one of the links.
  • R1 and R2 are routers at the same level in the network, and so on, R3, R4, R5, R6, ..., R(2n+1), R(2n+2) are routers at the same level respectively .
  • the alternative paths from the 1st level to the n-th level network are (calculated after a link flow between the same levels):
  • calculate the normalization coefficient under the constraints Determine the set of candidate paths subject to constraints. Determine thresholds for traffic scheduling under constraints.
  • a library of available alternative paths is determined by a threshold, and each element in the library of available alternative paths is prioritized.
  • the priority sorting can be arranged according to the order of constraints from largest to smallest, or from smallest to largest.
  • a schematic diagram of the centralized controllable scheme includes the following contents:
  • the information collection of network status and network traffic and the delivery of traffic policies are realized in the form of a software platform.
  • the information collection module collects network device information, link information, and flow information through the SDN controller and the southbound interface. The information is collected periodically, and the cycle time can be set.
  • the traffic policy delivery module uses the traffic policy settings and the traffic policy module to directly generate a command line corresponding to the device, as an element of the command warehouse, and directly sends it to the device through the southbound interface.
  • the description is as follows, as shown in Figure 4, the topological structure diagram of the 5-level ring network.
  • t l is the delay of the alternative link l, ignoring the sending and receiving delays, d is the distance between each link, and s is the propagation speed of the signal in the transmission medium.
  • min(T) min ⁇ tp
  • the elements of network delay are:
  • the user defines a single constraint condition, and sets the delay threshold ⁇ as but:
  • the library of available alternative paths using the delay constraint is:
  • BL(T) ⁇ tp6, tp7, tp8, tp9, tp10, tp11, tp12 ⁇
  • constraints can be combined in proportion to bandwidth utilization, remaining bandwidth, or multiple constraints to implement a traffic scheduling calculation scheme.
  • path planning is carried out for business traffic under a multi-port ring network structure, avoiding the traffic congestion problem of the backbone network, reducing investment and operation costs of backbone network lines, improving bandwidth utilization and user online experience, and improving the network Flexibility and management operational efficiency.
  • the SDN controller collects the global network status in real time to provide data information for the traffic scheduling calculation module, and the SDN controller can directly call the traffic scheduling results, and the platform generates related calculation commands, and the scheduling has been completed.
  • the issuing of commands replaces the process of manually issuing commands by network operation and maintenance personnel, improves the efficiency of network management and operation and maintenance, reduces the dependence on operation and maintenance personnel, and realizes network management automation.
  • a traffic scheduling system under a multi-port ring structure is also provided.
  • the system is used to implement the above embodiments and preferred implementation modes, and those that have already been explained will not be repeated.
  • the term "module” may be a combination of software and/or hardware that realizes a predetermined function.
  • the systems described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
  • Fig. 6 is a structural block diagram of a traffic scheduling system under a multi-word ring structure according to an embodiment of the present invention. As shown in Fig. 6, the traffic scheduling system includes:
  • the acquisition unit 71 is configured to acquire the global network state of the topological network, wherein the topological network includes multiple levels, the multi-level topological network includes V nodes, and the V nodes form a plurality of network links.
  • the first determining unit 73 is configured to determine an alternative path according to the state of the grid when a network link in the topological network fails, where the alternative path includes one or more.
  • the second determining unit 75 is configured to determine priorities of multiple candidate paths according to constraint conditions when there are multiple candidate paths, wherein the priority is used to indicate the order of transmitting data traffic.
  • the obtaining unit 71 obtains the global network state of the topological network, wherein the topological network includes multiple levels, the multi-level topological network includes V nodes, and the V nodes form a plurality of network links; the first determining unit 73 When a network link in the topological network fails, determine an alternative path according to the state of the grid, wherein the alternative path includes one or more; the second determination unit 75 in the case of multiple alternative paths , determine the priority of multiple alternative paths according to the constraint conditions, where the priority is used to indicate the order of transmission data traffic, plan the path of business traffic under the topology network structure, and send instructions to the device according to the priority of the planned path , to avoid backbone network traffic congestion, reduce backbone network line investment and operating costs, improve bandwidth utilization and user Internet experience, improve network flexibility and management and operation efficiency, and thus solve the problem of business traffic path planning and backbone Technical problem with network traffic congestion problem.
  • the first determining unit 73 may include: a first determining module, configured to determine a path satisfying a traffic scheduling threshold among the plurality of network links as the candidate path, wherein the candidate path Selected paths include one or more.
  • the first determining unit 73 may include:
  • the obtaining module is used to obtain the traffic scheduling threshold.
  • the first calculation module is configured to calculate the network delay of each link in multiple candidate paths, wherein the constraints include network delay, and the candidate paths include one or more.
  • the second determination module is configured to determine a path satisfying the network delay threshold and the traffic scheduling threshold among the plurality of network links as a candidate path.
  • the above-mentioned second determination module 75 may include: an acquiring submodule, configured to acquire a traffic scheduling threshold; a determining submodule, configured to determine a path that satisfies the network delay threshold and the traffic scheduling threshold among multiple network links as an alternative path.
  • the above-mentioned first determination unit 73 may include: a second calculation module, configured to calculate the bandwidth utilization rate of each path in multiple candidate paths; a third determination module, configured to combine the A path that satisfies the bandwidth utilization threshold is determined as a candidate path, where the constraint condition includes bandwidth utilization, and the candidate paths include one or more.
  • the above system may further include: a delivery unit, configured to generate a command line corresponding to the device after determining the priorities of the multiple candidate paths according to the constraints when there are multiple candidate paths, And send it to the device through the interface.
  • a delivery unit configured to generate a command line corresponding to the device after determining the priorities of the multiple candidate paths according to the constraints when there are multiple candidate paths, And send it to the device through the interface.
  • the above system may also include: a calculation unit, used to calculate the candidate path P from the first level to the nth level network when the topological network is an n-level multi-word ring network topology and the abnormal position is i: Wherein, 1 ⁇ i ⁇ n, the third determination unit is used to determine the candidate path from the candidate path P according to the constraints, wherein the constraints include network delay, bandwidth utilization, remaining bandwidth or a plurality of constraints proportional to Combine constraints.
  • the above-mentioned modules can be realized by software or hardware. For the latter, it can be realized by the following methods, but not limited to this: the above-mentioned modules are all located in the same processor; or, the above-mentioned modules can be combined in any combination The forms of are located in different processors.
  • An embodiment of the present invention also provides a storage medium, in which a computer program is stored, wherein the computer program is set to execute the steps in any one of the above method embodiments when running.
  • the above-mentioned storage medium may be configured to store a computer program for performing the following steps:
  • the topological network includes multiple levels
  • the multi-level topological network includes V nodes
  • the V nodes form a plurality of network links
  • priorities of the multiple candidate paths are determined according to constraint conditions, where the priorities are used to indicate the order of transmitting data traffic.
  • the above-mentioned storage medium may include but not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), Various media that can store computer programs, such as removable hard disks, magnetic disks, or optical disks.
  • ROM read-only memory
  • RAM random access memory
  • Various media that can store computer programs such as removable hard disks, magnetic disks, or optical disks.
  • An embodiment of the present invention also provides an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.
  • the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.
  • the above-mentioned processor may be configured to execute the following steps through a computer program:
  • the topological network includes multiple levels
  • the multi-level topological network includes V nodes
  • the V nodes form a plurality of network links
  • priorities of the multiple candidate paths are determined according to constraint conditions, where the priorities are used to indicate the order of transmitting data traffic.
  • each module or each step of the present invention described above can be realized by a general-purpose computing device, and they can be concentrated on a single computing device, or distributed in a network formed by multiple computing devices Alternatively, they may be implemented in program code executable by a computing device so that they may be stored in a storage device to be executed by a computing device, and in some cases in an order different from that shown here
  • the steps shown or described are carried out, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps among them are fabricated into a single integrated circuit module for implementation.
  • the present invention 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

本发明涉及计算机网络技术领域,提供了一种多口字环形结构下的流量调度方法和系统,所述方法包括:获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路;在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,备选路径包括一个或多个;在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,优先级用于表示传输数据流量的顺序。本发明对拓扑网络结构下的业务流量进行路径规划,根据规划路径的优先级,向设备发送指令,避免骨干网络流量拥塞问题,降低骨干网线路投资和运营成本,进而解决了现有技术中,业务流量路径规划,骨干网络流量拥塞问题的技术问题。

Description

一种多口字环形结构下的流量调度方法和系统 技术领域
本发明涉及计算机网络技术领域,具体地,涉及一种多口字环形结构下的流量调度方法、系统、电子设备以及存储介质。
背景技术
大型骨干、广域网络跨越距离远,线路资源有限,高速带宽费用昂贵,快速增加的业务流量与有限的带宽资源之间的矛盾,使得广域网上的流量很容易产生拥塞,导致业务延时增加、流量抖动,甚至丢包,用户网络体验极差。如何有效利用现有的网络带宽资源,降低网络建设投资及运营成本,是网络中一直要解决的问题。
SDN(Software Defined Network)技术以其将网络设备的控制平面和转发平面分离的核心思想,能够从全局网络视角监控设备及链路,为提供完整的网络流量调度提供了解决方案。
采用SDN技术进行流量调度是当前的研究热点,但路由实现中一般以最短链路算法为基础,进而延伸出K条最短链路、启发式搜索算法、负载均衡算法ECMP、自适应多目标优化路由算法AMOGR等。这些算法虽然能够找到符合需求的一条或K条最短路由链路,但是数据流很容易因为选择同一条转发链路而聚集到一起,从而导致网络拥塞,这极大地降低了链路利用率。而且,对于已经产生拥塞的节点,无法进行处理或处理时间过长。
发明内容
本发明提供了一种多口字环形结构下的流量调度方法,以解决现有技术中,业务流量在网络中的路径规划,骨干网络流量拥塞问题的技术问题。
本发明的第一个方面,提供了一种多口字环形结构下的流量调度方法,包括:获取拓扑网络的全局网络状态,其中,所述拓扑网络包括多级,所述多级拓扑网络包括V个节点,所述V个节点构成多个网络链路;在所述拓扑网络中的网络链路出现故障的情况下,根据所述网格状态确定备选路径,其中,所述备选路径包括一个或多个;在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级,其中,所述优先级用于表示传输数据流量的顺序。
可选的,所述根据所述网格状态确定备选路径,包括:
将所述多个网络路径中满足流量调度阈值的路径确定为所述备选路径,其中,所述备 选路径包括一个或多个。
可选的,所述根据所述网格状态确定备选路径,包括:获取流量调度阈值;
计算所述多个备选路径中每个路径的网络时延,其中,所述约束条件包括所述网络时延,所述备选路径包括一个或多个;将所述多个网络路径中满足网络时延阈值和所述流量调度阈值的路径确定为所述备选路径。
可选的,所述根据所述网格状态确定备选路径,包括:计算所述多个备选路径中每个路径的带宽利用率;将所述多个网络路径中满足带宽利用率阈值的链路确定为所述备选路径,其中,所述约束条件包括所述带宽利用率,所述备选路径包括一个或多个。
可选的,所述在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级之后,所述方法还包括:生成与设备端对应的命令行,并通过接口下发至所述设备。
可选的,所述方法还包括:在所述拓扑网络为n级多口字环形网络拓扑、异常位置为i时,从第1级至第n级网络的候选路径P为:
Figure PCTCN2021139854-appb-000001
其中,1≤i≤n,根据所述约束条件从所述候选路径P中确定所述备选路径,其中,所述约束条件包括网络时延、带宽利用率、剩余带宽或者多个约束条件按比例进行组合的约束条件。
本发明的第二个方面,提供了一种多口字环形结构下的流量调度系统,包括:获取单元,用于获取拓扑网络的全局网络状态,其中,所述拓扑网络包括多级,所述多级拓扑网络包括V个节点,所述V个节点构成多个网络链路;第一确定单元,用于在所述拓扑网络中的网络链路出现故障的情况下,根据所述网格状态确定备选路径,其中,所述备选路径包括一个或多个;第二确定单元,用于在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级,其中,所述优先级用于表示传输数据流量的顺序。
可选的,所述第一确定单元,包括:第一确定模块,用于将所述多个网络路径中满足流量调度阈值的路径确定为所述备选路径,其中,所述备选路径包括一个或多个。
可选的,所述第一确定单元,包括:获取模块,用于获取流量调度阈值;第一计算模块,用于计算所述多个备选路径中每个链路的网络时延,其中,所述约束条件包括所述网络时延,所述备选路径包括一个或多个;第二确定模块,用于将所述多个网络路径中满足网络时延阈值和所述流量调度阈值的路径确定为所述备选路径。
可选的,所述第一确定单元,包括:第二计算模块,用于计算所述多个备选路径中每个链路的带宽利用率;第三确定模块,用于将所述多个网络路径中满足带宽利用率阈值的路径确定为所述备选路径,其中,所述约束条件包括所述带宽利用率,所述备选路径包括 一个或多个。
可选的,所述系统还包括:下发单元,用于在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级之后,生成与设备端对应的命令行,并通过接口下发至所述设备;计算单元,用于在所述拓扑网络为n级多口字环形网络拓扑、异常位置为i时,计算从第1级至第n级网络的候选路径P为:
Figure PCTCN2021139854-appb-000002
其中,1≤i≤n,第三确定单元,用于根据所述约束条件从所述候选路径P中确定所述备选路径,其中,所述约束条件包括网络延时、带宽利用率、剩余带宽或者多个约束条件按比例进行组合的约束条件。
本发明的第三个方面,提供了一种计算机可读的存储介质,其特征在于,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多口字环形结构下的流量调度方法。
本发明的第四个方面,提供了一种电子装置,包括存储器和处理器,其特征在于,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多口字环形结构下的流量调度方法。
在本发明实施例中,通过获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路;在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,其中,备选路径包括一个或多个;在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,其中,优先级用于表示传输数据流量的顺序,对拓扑网络结构下的业务流量进行路径规划,根据规划路径的优先级,向设备发送指令,避免骨干网络流量拥塞问题,降低骨干网线路投资和运营成本,提高带宽利用率和用户上网体验,提升网络灵活性和管理运维效率,进而解决了现有技术中,业务流量路径规划,骨干网络流量拥塞问题的技术问题。
附图说明
此处所说明的附图用来提供对本发明的进一步理解,构成本发明的一部分,本发明的示意性实施例及其说明用于解释本发明,并不构成对本发明的不当限定。在附图中:
图1是根据本发明实施例的一种可选的多口字环形结构下的流量调度方法的流程图;
图2是根据本发明实施例的一种可选的5级多口字环形网络结构示意图;
图3是根据本发明实施例的一种可选的5级多口字环形结构异常时备选路径计算示意图;
图4是根据本发明实施例的一种可选的流量调度计算方案流程图;
图5是根据本发明实施例的一种可选的集中可控方案示意图;
图6是根据本发明实施例的多口字环形结构下的流量调度系统的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分的实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都应当属于本发明保护的范围。
需要说明的是,本发明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。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本发明的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一序列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
本实施例提供了一种多口字环形结构下的流量调度方法,图1是根据本发明实施例的多口字环形结构下的流量调度方法的流程图,如图1所示,该流量调度方法流程包括如下步骤:
步骤S202,获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路。
步骤S204,在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,其中,备选路径包括一个或多个。
步骤S206,在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,其中,优先级用于表示传输数据流量的顺序。
在本实施例中,拓扑网络可以包括但不限于多口字环形网络拓扑为T(V,L),共n级。其中,V为网络中的所有节点,v为其中一个节点,S为源节点,D为目的节点;L为网络中的所有链路,l为其中一条路径。R1、R2是网络中处于同一级的路由器,以此类推,R3、R4,R5、R6,……,R(2n+1)、R(2n+2)分别为同一级的路由器。
当多口字环形网络拓扑为n级、异常位置为i(1≤i≤n)时,从第1级至第n级网络的备选路径有(计算经过一次同级间路径流转):
Figure PCTCN2021139854-appb-000003
其中,对于所有候选路径P,其构成备选路径库:
Figure PCTCN2021139854-appb-000004
对于每一条从S至D的候选路径p,确定网络流量调度的约束条件,是否为单一约束条件或多约束条件。
根据约束条件,计算约束条件下的归一化系数。确定约束条件下的候选路径集合。确定约束条件下流量调度的阈值。
由阈值确定可用备选路径库,并对可用备选路径库中的每个元素进行优先级排序。优先级排序可以按照约束条件从大到小、或从小到大的顺序排列。
通过本发明提供的实施例,获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路;在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,其中,备选路径包括一个或多个;在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,其中,优先级用于表示传输数据流量的顺序,对拓扑网络结构下的业务流量进行路径规划,根据规划路径的优先级,向设备发送指令,避免骨干网络流量拥塞问题,降低骨干网线路投资和运营成本,提高带宽利用率和用户上网体验,提升网络灵活性和管理运维效率,进而解决了现有技术中,业务流量路径规划,骨干网络流量拥塞问题的技术问题。
可选的,根据网格状态确定备选路径,可以包括:将多个网络路径中满足流量调度阈值的路径确定为备选路径,其中,备选路径包括一个或多个。
可选的,根据网格状态确定备选路径,可以包括:获取流量调度阈值;计算多个备选路径中每个链路的网络时延,其中,约束条件包括网络时延,备选路径包括一个或多个;将多个网络链路中满足网络时延阈值和流量调度阈值的路径确定为备选路径。
可选的,根据网格状态确定备选路径,可以包括:计算多个备选路径中每个链路的带宽利用率;将多个网络路径中满足带宽利用率阈值的链路确定为备选路径,其中,约束条件包括带宽利用率,备选链路包括一个或多个。
可选的,在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级之后,上述方法还可以包括:生成与设备端对应的命令行,并通过接口下发至设备。
可选的,上述方法还可以包括:在拓扑网络为n级多口字环形网络拓扑、异常位置为i时,从第1级至第n级网络的候选路径P为:
Figure PCTCN2021139854-appb-000005
其中,1≤i≤n,根据约束条件从候选路径P中确定备选路径,其中,约束条件包括网络延时、带宽利用率、剩余带宽或者多个约束条件按比例进行组合的约束条件。
作为一种可选的实施例,本发明还提供了一种多口字环形结构下的流量调度方法。如 图2所示,一种多口字环形结构下的流量调度方法的结构图。
步骤S301,开始;
步骤S302,获取多口字环形网络拓扑T(V,L),源节点S、目的节点D、网络级别n、以及异常位置i;
在本实施例,多口字环形网络拓扑为T(V,L),共n级。其中,V为网络中的所有节点,v为其中一个节点,S为源节点,D为目的节点;L为网络中的所有链路,l为其中一条路径。R1、R2是网络中处于同一级的路由器,以此类推,R3、R4,R5、R6,……,R(2n+1)、R(2n+2)分别为同一级的路由器。
步骤S303,计算所有的可选路径P;
步骤S304,在设置用户策略的情况下,执行步骤S305,在未设置用户策略的情况下,执行步骤S306;
步骤S305,在按延时计算的情况下,执行步骤S306,在未按延时计算的情况下,执行步骤S309;
步骤S306,对于每条路径p,计算网络延时tp;
步骤S307,由网络时延tp,得出备选路径T;
步骤S308,对于每条路径p,计算可用的网络时延路径集合BL(T)(相当于备选链路);
步骤S309,在按带宽利用率计算的情况下,执行步骤S310,在未按带宽利用率计算的情况下,执行步骤S313;
步骤S310,对于每条路径p,计算带宽利用率up;
步骤S311,由带宽利用率up,得出备选路径U;
步骤S312,对于每条路径p,计算可用的带宽利用率路径集合BL(U);
步骤S313,在按时延与带宽利用率混合计算的情况下,执行步骤S314,在未按时延与带宽利用率混合计算的情况下,执行步骤S317;
步骤S314,对于每条路径p,计算混合参数tup;
步骤S315,由混合参数utp,得出备选路径TU;
步骤S316,对于每条路径p,计算可用的混合参数路径集合BL(TU);
步骤S317,在按人为设定的任意参数x计算的情况下,执行步骤S317,在未按参数x计算的情况下,执行步骤S321;
步骤S318,对于每条路径p,计算参数数据xp;
步骤S319,由参数数据xp,得出xp的备选路径集合X;
步骤S320,对于每条路径p,计算可用的参数数据路径集合BL(X);
步骤S321,结束。
在本实施例中,多口字环形结构下的流量调度方法包括流量调度计算方案和集中可控方案。流量调度方案通过实时的全局网络状态,计算出可用的备选路径,并根据约束条件对备选路径进行优先级排序输出,约束条件可以为一个或多个,由用户自定义。集中可控方案是通过以软件平台的方式并借助SDN控制器集中收集全局网络的状态,为流量调度计算方案提供数据,并将流量计算调度方案的输出结果自动下发至网络中。
其中,流量调度计算方案包括如下内容:
假使多口字环形网络拓扑为T(V,L),共n级。其中,V为网络中的所有节点,v为其中一个节点,S为源节点,D为目的节点;L为网络中的所有链路,l为其中一条链路。R1、R2是网络中处于同一级的路由器,以此类推,R3、R4,R5、R6,......,R(2n+1)、R(2n+2)分别为同一级的路由器。
当多口字环形网络拓扑为n级、异常位置为i(1≤i≤n)时,从第1级至第n级网络的备选路径有(计算经过一次同级间链路流转):
Figure PCTCN2021139854-appb-000006
则对于所有候选链路P,其构成备选路径库:
Figure PCTCN2021139854-appb-000007
对于每一条从S至D的候选链路p,确定网络流量调度的约束条件,是否为单一约束条件或多约束条件。
根据约束条件,计算约束条件下的归一化系数。确定约束条件下的候选路径集合。确定约束条件下流量调度的阈值。
由阈值确定可用备选路径库,并对可用备选路径库中的每个元素进行优先级排序。优先级排序可以按照约束条件从大到小、或从小到大的顺序排列。
其中,如图3所示,集中可控方案示意图,集中可控方案包括如下内容:
以软件平台的方式实现对网络状态和网络流量的信息采集和流量策略下发。
信息采集模块,通过SDN控制器与南向接口收集网络设备信息、链路信息、流量信息,是通过周期性方式进行采集的,并可以对周期时间进行设置。
流量策略下发模块,利用流量策略设置及流量策略模块,直接生成与设备对应的命令行,作为命令仓库的元素,直接通过南向接口下发至设备。
以5级口字环形网络拓扑为例说明如下,如图4所示,5级口字环形网络拓扑结构图。
当网络级别为5级时,链路异常位置为1时,说明流量调度计算方法。
如图5所示,5级多口字环形结构异常时备选路径计算示意图,计算从第1级至第5级网络的备选路径有(计算经过一次同级间链路流转)。
Figure PCTCN2021139854-appb-000008
P={p x|x∈[1,12],x为整数}
以时延作为单一的约束条件为例,进行可用备选路径库的计算过程。
则对于每一条从S至D的候选路径p,网络时延为:t p=d l*t l
d l为距离归一化系数:
Figure PCTCN2021139854-appb-000009
Figure PCTCN2021139854-appb-000010
其中,t l为备选链路l的时延,忽略发送和接收时延,d为每条链路间的距离,s为信号在传输介质中的传播速度。
Figure PCTCN2021139854-appb-000011
其中,对于所有的候选路径P,其对于网络时延这一约束条件的候选路径集合为:T={t p|p∈P}
使用网络时延计算min(T)=min{tp|p∈P}<α。对min(T)中的元素按照从小到大的优先级顺序进行排列,确定可用备选路径库BL(T)。
在此阶段给出一段计算示例,故假设网络中的每段链路的距离均为d,则:
网络时延各元素为:
Figure PCTCN2021139854-appb-000012
Figure PCTCN2021139854-appb-000013
Figure PCTCN2021139854-appb-000014
Figure PCTCN2021139854-appb-000015
Figure PCTCN2021139854-appb-000016
Figure PCTCN2021139854-appb-000017
网络时延集合为:T={t px|px∈P,x∈[1,121,x为整数}
在本实施例中,用户定义使用单一约束条件,设时延阈值α为
Figure PCTCN2021139854-appb-000018
则:
使用时延这一约束条件的可用备选路径库为:
BL(T)={tp6,tp7,tp8,tp9,tp10,tp11,tp12}
在实际使用中,其他约束条件可以带宽利用率、剩余带宽或者多个约束条件按比例进行组合,进行流量调度计算方案的实施。
通过本发明提供的实施例,对多口字环形网络结构下的业务流量进行路径规划,避免骨干网络流量拥塞问题,降低骨干网线路投资和运营成本,提高带宽利用率和用户上网体验,提升网络灵活性和管理运维效率。
与现有技术相比,本方案具有以下优点:
(1)针对多口字环形网络架构,在链路异常的情况下,优先计算出所有的备选路径,并且可以根据用户需求使用单一约束条件或多个约束条件进行流量调度,可有效降低网络时延,提升带宽利用率,提高用户上网体验。
(2)在集中可控实现上,SDN控制器通过实时收集全局网络状态,为流量调度计算模块提供数据信息,并且SDN控制器可直接调用流量调度结果,平台生成相关的计算命令,已完成调度命令的下发,代替网络运维人员手动下发命令过程,提升网络管理运维效率,降低对运维人员的依赖,实现网络管理自动化。
(3)在全局网络视角完成资源、管理和控制的协同,实现对业务应用层需求的快速反 应,提升网络的灵活性。
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多口字环形结构下的流量调度系统,该系统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系统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6是根据本发明实施例的多口字环形结构下的流量调度系统的结构框图,如图6所示,该流量调度系统包括:
获取单元71,用于获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路。
第一确定单元73,用于在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,其中,备选路径包括一个或多个。
第二确定单元75,用于在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,其中,优先级用于表示传输数据流量的顺序。
通过本发明提供的实施例,获取单元71获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路;第一确定单元73在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,其中,备选路径包括一个或多个;第二确定单元75在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,其中,优先级用于表示传输数据流量的顺序,对拓扑网络结构下的业务流量进行路径规划,根据规划路径的优先级,向设备发送指令,避免骨干网络流量拥塞问题,降低骨干网线路投资和运营成本,提高带宽利用率和用户上网体验,提升网络灵活性和管理运维效率,进而解决了现有技术中,业务流量路径规划,骨干网络流量拥塞问题的技术问题。
可选的,所述第一确定单元73,可以包括:第一确定模块,用于将所述多个网络链路中满足流量调度阈值的路径确定为所述备选路径,其中,所述备选路径包括一个或多个。
可选的,所述第一确定单元73,可以包括:
获取模块,用于获取流量调度阈值。
第一计算模块,用于计算多个备选路径中每个链路的网络时延,其中,约束条件包括网络时延,备选路径包括一个或多个。
第二确定模块,用于将多个网络链路中满足网络时延阈值和流量调度阈值的路径确定为备选路径。
可选的,上述第二确定模块75,可以包括:获取子模块,用于获取流量调度阈值;确定子模块,用于将多个网络链路中满足网络时延阈值和流量调度阈值的路径确定为备选路径。
可选的,上述第一确定单元73,可以包括:第二计算模块,用于计算多个备选路径中每个路径的带宽利用率;第三确定模块,用于将多个网络链路中满足带宽利用率阈值的路径确定为备选路径,其中,约束条件包括带宽利用率,备选路径包括一个或多个。
可选的,上述系统还可以包括:下发单元,用于在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级之后,生成与设备端对应的命令行,并通过接口下发至设备。
可选的,上述系统还可以包括:计算单元,用于在拓扑网络为n级多口字环形网络拓扑、异常位置为i时,计算从第1级至第n级网络的候选路径P为:
Figure PCTCN2021139854-appb-000019
其中,1≤i≤n,第三确定单元,用于根据约束条件从候选路径P中确定备选路径,其中,约束条件包括网络延时、带宽利用率、剩余带宽或者多个约束条件按比例进行组合的约束条件。
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。
本发明的实施例还提供了一种存储介质,该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。
可选地,在本实施例中,上述存储介质可以被设置为存储用于执行以下步骤的计算机程序:
S1,获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路;
S2,在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,其中,备选路径包括一个或多个;
S3,在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,其中,优先级用于表示传输数据流量的顺序。
可选地,在本实施例中,上述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。
可选地,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。
可选地,在本实施例中,上述处理器可以被设置为通过计算机程序执行以下步骤:
S1,获取拓扑网络的全局网络状态,其中,拓扑网络包括多级,多级拓扑网络包括V个节点,V个节点构成多个网络链路;
S2,在拓扑网络中的网络链路出现故障的情况下,根据网格状态确定备选路径,其中,备选路径包括一个或多个;
S3,在备选路径为多个的情况下,根据约束条件确定多个备选路径的优先级,其中,优先级用于表示传输数据流量的顺序。
可选地,本实施例中的具体示例可以参考上述实施例及可选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,可选地,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 (13)

  1. 一种多口字环形结构下的流量调度方法,其特征在于,包括:
    获取拓扑网络的全局网络状态,其中,所述拓扑网络包括多级,所述多级拓扑网络包括V个节点,所述V个节点构成多个网络链路;
    在所述拓扑网络中的网络链路出现故障的情况下,根据所述网格状态确定备选路径,其中,所述备选路径包括一个或多个;
    在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级,其中,所述优先级用于表示传输数据流量的顺序。
  2. 根据权利要求1所述的方法,其特征在于,所述根据所述网格状态确定备选路径,包括:
    将所述多个网络路径中满足流量调度阈值的路径确定为所述备选路径,其中,所述备选路径包括一个或多个。
  3. 根据权利要求1所述的方法,其特征在于,所述根据所述网格状态确定备选路径,包括:
    获取流量调度阈值;
    计算所述多个备选路径中每个链路的网络时延,其中,所述约束条件包括所述网络时延,所述备选路径包括一个或多个;
    将所述多个网络链路中满足网络时延阈值和所述流量调度阈值的路径确定为所述备选路径。
  4. 根据权利要求1所述的方法,其特征在于,所述根据所述网格状态确定备选路径,包括:
    计算所述多个备选路径中每个链路的带宽利用率;
    将所述多个网络路径中满足带宽利用率阈值的路径确定为所述备选路径,其中,所述约束条件包括所述带宽利用率,所述备选路径包括一个或多个。
  5. 根据权利要求1至4任一项所述的方法,其特征在于,所述在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级之后,所述方法还包括:
    生成与设备端对应的命令行,并通过接口下发至所述设备。
  6. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    在所述拓扑网络为n级多口字环形网络拓扑、异常位置为i时,从第1级至第n 级网络的候选路径P为:
    Figure PCTCN2021139854-appb-100001
    其中,1≤i≤n,
    根据所述约束条件从所述候选路径P中确定所述备选路径,其中,所述约束条件包括网络延时、带宽利用率、剩余带宽或者多个约束条件按比例进行组合的约束条件。
  7. 一种多口字环形结构下的流量调度系统,其特征在于,包括:
    获取单元,用于获取拓扑网络的全局网络状态,其中,所述拓扑网络包括多级,所述多级拓扑网络包括V个节点,所述V个节点构成多个网络链路;
    第一确定单元,用于在所述拓扑网络中的网络链路出现故障的情况下,根据所述网格状态确定备选路径,其中,所述备选路径包括一个或多个;
    第二确定单元,用于在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级,其中,所述优先级用于表示传输数据流量的顺序。
  8. 根据权利要求7所述的系统,其特征在于,所述第一确定单元,包括:
    第一确定模块,用于将所述多个网络链路中满足流量调度阈值的路径确定为所述备选路径,其中,所述备选路径包括一个或多个。
  9. 根据权利要求7所述的系统,其特征在于,所述第一确定单元,包括:
    获取模块,用于获取流量调度阈值;
    第一计算模块,用于计算所述多个备选路径中每个链路的网络时延,其中,所述约束条件包括所述网络时延,所述备选路径包括一个或多个;
    第二确定模块,用于将所述多个网络链路中满足网络时延阈值和所述流量调度阈值的路径确定为所述备选路径。
  10. 根据权利要求7所述的系统,其特征在于,所述第一确定单元,包括:
    第二计算模块,用于计算所述多个备选路径中每个路径的带宽利用率;
    第三确定模块,用于将所述多个网络链路中满足带宽利用率阈值的路径确定为所述备选路径,其中,所述约束条件包括所述带宽利用率,所述备选路径包括一个或多个。
  11. 根据权利要求7至10任一项所述的系统,其特征在于,所述系统还包括:
    下发单元,用于在所述备选路径为多个的情况下,根据约束条件确定所述多个备选路径的优先级之后,生成与设备端对应的命令行,并通过接口下发至所述设备;
    计算单元,用于在所述拓扑网络为n级多口字环形网络拓扑、异常位置为i时, 计算从第1级至第n级网络的候选路径P为:
    Figure PCTCN2021139854-appb-100002
    其中,1≤i≤n,
    第三确定单元,用于根据所述约束条件从所述候选路径P中确定所述备选路径,其中,所述约束条件包括网络延时、带宽利用率、剩余带宽或者多个约束条件按比例进行组合的约束条件。
  12. 一种计算机可读的存储介质,其特征在于,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6任一项中所述的方法。
  13. 一种电子装置,包括存储器和处理器,其特征在于,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6任一项中所述的方法。
PCT/CN2021/139854 2021-11-15 2021-12-21 一种多口字环形结构下的流量调度方法和系统 WO2023082431A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111350120.0 2021-11-15
CN202111350120.0A CN114024907A (zh) 2021-11-15 2021-11-15 一种多口字环形结构下的流量调度方法和系统

Publications (1)

Publication Number Publication Date
WO2023082431A1 true WO2023082431A1 (zh) 2023-05-19

Family

ID=80064343

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/139854 WO2023082431A1 (zh) 2021-11-15 2021-12-21 一种多口字环形结构下的流量调度方法和系统

Country Status (2)

Country Link
CN (1) CN114024907A (zh)
WO (1) WO2023082431A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116471225A (zh) * 2023-06-12 2023-07-21 中仪英斯泰克科技有限公司 组播流传输路径的优选方法及装置、电子设备、存储介质
CN117270936A (zh) * 2023-10-10 2023-12-22 武汉碧涯科技有限公司 一种云平台运维方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103973567A (zh) * 2014-05-06 2014-08-06 华为技术有限公司 虚拟专用网络的路由配置方法及装置
US20150341256A1 (en) * 2012-12-19 2015-11-26 Zte Corporation Fast recovery method and device for STP-based backup port
US20170155580A1 (en) * 2014-02-04 2017-06-01 Architecture Technology, Inc. Low-Overhead Routing
US20200044960A1 (en) * 2018-08-03 2020-02-06 Estinet Technologies Incorporation Network automatic link backup method and network system thereof
CN112564964A (zh) * 2020-12-04 2021-03-26 中国石油大学(华东) 一种基于软件定义网络的故障链路检测与恢复方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150032871A1 (en) * 2010-09-08 2015-01-29 Telefonaktiebolaget L M Ericsson (Publ) Automated traffic engineering based upon the use of bandwidth and unequal cost path utilization
CN108337144A (zh) * 2017-01-20 2018-07-27 中国移动通信集团公司 Td-lte城域回传网络、路径保护方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150341256A1 (en) * 2012-12-19 2015-11-26 Zte Corporation Fast recovery method and device for STP-based backup port
US20170155580A1 (en) * 2014-02-04 2017-06-01 Architecture Technology, Inc. Low-Overhead Routing
CN103973567A (zh) * 2014-05-06 2014-08-06 华为技术有限公司 虚拟专用网络的路由配置方法及装置
US20200044960A1 (en) * 2018-08-03 2020-02-06 Estinet Technologies Incorporation Network automatic link backup method and network system thereof
CN112564964A (zh) * 2020-12-04 2021-03-26 中国石油大学(华东) 一种基于软件定义网络的故障链路检测与恢复方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116471225A (zh) * 2023-06-12 2023-07-21 中仪英斯泰克科技有限公司 组播流传输路径的优选方法及装置、电子设备、存储介质
CN116471225B (zh) * 2023-06-12 2023-08-18 中仪英斯泰克科技有限公司 组播流传输路径的优选方法及装置、电子设备、存储介质
CN117270936A (zh) * 2023-10-10 2023-12-22 武汉碧涯科技有限公司 一种云平台运维方法及系统
CN117270936B (zh) * 2023-10-10 2024-03-19 武汉碧涯科技有限公司 一种云平台运维方法及系统

Also Published As

Publication number Publication date
CN114024907A (zh) 2022-02-08

Similar Documents

Publication Publication Date Title
CN109818865B (zh) 一种sdn增强路径装箱装置及方法
WO2023082431A1 (zh) 一种多口字环形结构下的流量调度方法和系统
CN108259367B (zh) 一种基于软件定义网络的服务感知的流策略定制方法
CN108170530B (zh) 一种基于混合元启发式算法的Hadoop负载均衡任务调度方法
Liu et al. Task scheduling in fog enabled Internet of Things for smart cities
CN103346922A (zh) 基于sdn的确定网络状态的控制器及其确定方法
CN106817306B (zh) 一种确定目标路由的方法及装置
CN110213363A (zh) 基于软件定义网络的云资源动态分配系统及方法
CN115277574B (zh) 一种sdn架构下数据中心网络负载均衡方法
WO2018166249A1 (zh) 一种网络业务传输的方法及系统
Abdel-Kader An improved discrete PSO with GA operators for efficient QoS-multicast routing
CN106506275B (zh) 一种预测交换节点目的端口传输时延的方法及装置
CN111741069B (zh) 基于sdn和nfv分层式数据中心资源优化方法和系统
Mollah et al. Rapid calculation of max-min fair rates for multi-commodity flows in fat-tree networks
CN114422453B (zh) 一种在线规划时间敏感流的方法、装置及存储介质
WO2022016969A1 (zh) 一种数据处理方法及装置
Wei et al. Coflow scheduling with unknown prior information in data center networks
Kargahi et al. Utility accrual dynamic routing in real-time parallel systems
CN112601232A (zh) 基于最小费用最大流的负载均衡的多服务迁移方法及系统
Lu et al. SDN routing optimization based on improved Reinforcement learning
Kouvatsos et al. Multicast communication in grid computing networks with background traffic
CN110493068A (zh) 一种网络路由生成方法及系统
CN108900315B (zh) 面向云服务提供商的服务利润优化方法
Nayyer et al. Game Theory-based Routing for Software-Defined Networks
CN113705826B (zh) 面向分布式机器学习的参数同步组播方法

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: 21963869

Country of ref document: EP

Kind code of ref document: A1