WO2015131692A1 - 一种带宽分配方法及装置 - Google Patents

一种带宽分配方法及装置 Download PDF

Info

Publication number
WO2015131692A1
WO2015131692A1 PCT/CN2015/071331 CN2015071331W WO2015131692A1 WO 2015131692 A1 WO2015131692 A1 WO 2015131692A1 CN 2015071331 W CN2015071331 W CN 2015071331W WO 2015131692 A1 WO2015131692 A1 WO 2015131692A1
Authority
WO
WIPO (PCT)
Prior art keywords
bandwidth
preset threshold
uplink
downlink
type
Prior art date
Application number
PCT/CN2015/071331
Other languages
English (en)
French (fr)
Inventor
邵长春
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
Priority to EP15758045.7A priority Critical patent/EP3197110B1/en
Publication of WO2015131692A1 publication Critical patent/WO2015131692A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/64—Hybrid switching systems
    • H04L12/6418—Hybrid transport
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/22—Traffic shaping
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/50—Queue scheduling
    • H04L47/62—Queue scheduling characterised by scheduling criteria
    • H04L47/625—Queue scheduling characterised by scheduling criteria for service slots or service orders
    • H04L47/627—Queue scheduling characterised by scheduling criteria for service slots or service orders policing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/215—Flow control; Congestion control using token-bucket

Definitions

  • the present invention relates to the field of communications, and in particular, to a bandwidth allocation method and apparatus.
  • a router generally hangs multiple devices to share network bandwidth. If one device uses Thunder download to preempt the entire bandwidth, it is difficult for other devices to preempt the bandwidth, causing other devices to fail to use the network service.
  • some similar P2P downloading software uses a special download mechanism, so that software using this mechanism can quickly grab a large bandwidth when downloading, until the entire bandwidth is preempted.
  • Thunder download software, BT download software, popular download software, potatoes, Youku online video, etc. in the multi-threaded mode, when downloading multiple movies, you can preempt all bandwidth, causing other devices can not preempt the bandwidth again, affecting other devices to use the network. Service, not even browsing the web.
  • the present invention provides a bandwidth allocation method and apparatus for solving the above technical problem.
  • an embodiment of the present invention provides a bandwidth allocation method, including: dividing an uplink/downlink total bandwidth of a router into an uplink/downstream parent class bandwidth and an uplink/downlink reserved bandwidth according to a preset allocation ratio. Monitoring the bandwidth traffic of each device connected to the router; each device whose bandwidth traffic exceeds a preset threshold is a first type device, and each device whose bandwidth traffic does not exceed a preset threshold is a second type device; The monitoring result is that the upper/downstream parent class bandwidth and the uplink/downlink reserved bandwidth are respectively allocated to the first type device and the second type device.
  • the bandwidth traffic exceeds the preset threshold, and includes one of the following four conditions: the uplink bandwidth of each device exceeds an uplink preset threshold; and the downlink bandwidth of each device exceeds a downlink preset threshold; The upstream bandwidth of the device exceeds the uplink preset threshold, and the downstream bandwidth of each device exceeds the downlink preset threshold. The upstream bandwidth of each device exceeds the uplink preset threshold, or the downstream bandwidth of each device exceeds the threshold. Downstream preset threshold;
  • the uplink/downlink preset threshold is smaller than the uplink/downlink reserved bandwidth value.
  • bandwidth allocation of the first type of device is performed by using at least one of the following manners on the uplink/downlink parent class bandwidth: average allocation, allocation according to a preset ratio, and priority allocation.
  • an embodiment of the present invention further provides a bandwidth allocation apparatus, including: a bandwidth division module, configured to divide an uplink/downlink total bandwidth of a router into an upper/downstream parent class according to a preset allocation ratio. Bandwidth and uplink/downlink reserved bandwidth; a traffic monitoring module configured to monitor bandwidth traffic of each device connected to the router; each device whose bandwidth traffic exceeds a preset threshold is a first type of device, and bandwidth traffic does not exceed Each device of the preset threshold is a second type of device; a bandwidth allocation module, It is configured to allocate the uplink/downstream parent class bandwidth and the uplink/downlink reserved bandwidth to the first type device and the second type device according to the monitoring result.
  • a bandwidth division module configured to divide an uplink/downlink total bandwidth of a router into an upper/downstream parent class according to a preset allocation ratio. Bandwidth and uplink/downlink reserved bandwidth
  • a traffic monitoring module configured to monitor bandwidth traffic of each device connected to the router; each device whose bandwidth traffic exceeds a preset threshold
  • the bandwidth traffic exceeds the preset threshold, and includes one of the following four conditions: the uplink bandwidth of each device exceeds an uplink preset threshold; and the downlink bandwidth of each device exceeds a downlink preset threshold; The upstream bandwidth of the device exceeds the uplink preset threshold, and the downstream bandwidth of each device exceeds the downlink preset threshold. The upstream bandwidth of each device exceeds the uplink preset threshold, or the downstream bandwidth of each device exceeds the threshold. Downstream preset threshold;
  • the uplink/downlink preset threshold is smaller than the uplink/downlink reserved bandwidth value.
  • the bandwidth allocation module is configured to perform bandwidth allocation of the first type of device by using at least one of the following methods: average allocation, allocation according to a preset ratio, and priority allocation.
  • the embodiment of the invention further provides a computer program and a carrier thereof, the computer program comprising program instructions, when the program instruction is executed by the routing device, enabling the routing device to implement the bandwidth allocation method described above.
  • the embodiment of the present invention utilizes the existing bandwidth control function in the HTB algorithm to reserve bandwidth, set thresholds, and dynamically configure device bandwidth in the total bandwidth, so that all users can achieve less total bandwidth. Preemptively share the bandwidth in real time and achieve the goal of fair sharing of bandwidth, which improves the user experience of enjoying network services.
  • 1 is a first schematic diagram of allocating bandwidth for two devices based on an HTB algorithm according to the related art
  • FIG. 2 is a second schematic diagram of allocating bandwidth for two devices based on an HTB algorithm according to the related art
  • FIG. 3 is a flow chart of a bandwidth allocation method according to an embodiment of the present invention.
  • FIG. 5 is a second schematic diagram of bandwidth allocation according to an embodiment of the present invention.
  • FIG. 6 is a third schematic diagram of bandwidth allocation according to an embodiment of the present invention.
  • FIG. 7 is a fourth schematic diagram of bandwidth allocation according to an embodiment of the present invention.
  • FIG. 8 is a block diagram showing the structure of a bandwidth allocation apparatus according to an embodiment of the present invention.
  • the embodiment of the present invention provides a bandwidth allocation method and device.
  • FIG. 3 is a flowchart of a bandwidth allocation method according to an embodiment of the present invention. As shown in FIG. 3, the method includes the following steps (step S302- Step S306):
  • Step S302 the total uplink/downlink bandwidth of the router is divided into upper/downstream parent class bandwidth and uplink/downlink reserved bandwidth according to a preset allocation ratio.
  • the preset allocation ratio can be determined according to actual conditions, for example, upper/downstream parent class bandwidth accounts for 80%, and uplink/downstream reserved bandwidth accounts for 20%.
  • Step S304 Monitor the bandwidth traffic of each device connected to the router; classify each device whose bandwidth traffic exceeds the preset threshold as the first type device, and classify each device whose bandwidth traffic does not exceed the preset threshold into the second type device.
  • the value of the preset threshold can be set according to the actual operation.
  • the bandwidth traffic exceeds a preset threshold, and may include one of the following four conditions:
  • the upstream bandwidth of each device exceeds the uplink preset threshold, or the downstream bandwidth of each device exceeds the downlink preset threshold.
  • the upper/lower downlink preset threshold is smaller than the upper/downstream reserved bandwidth value.
  • Step S306 According to the monitoring result, the uplink/downstream parent class bandwidth and the uplink/downlink reserved bandwidth are correspondingly allocated to the first type device and the second type device.
  • the bandwidth used by the first type of device is not necessarily equal to the upper/downstream parent class bandwidth allocated to it, that is, the first type of device does not necessarily use all of the upper/downstream parent class bandwidth allocated for it.
  • the bandwidth control function existing in the HTB algorithm is used to reserve bandwidth, set a threshold, and dynamically configure device bandwidth in a total bandwidth, so that all users can real-time in a situation where less total bandwidth is wasted. Seize the equal bandwidth and achieve the goal of fair sharing of bandwidth, which improves the user experience of enjoying network services.
  • the bandwidth allocation principle of the first type of device may be at least one of the following modes: average allocation, allocation according to a preset ratio, and priority allocation.
  • Parent class bandwidth is shared for all devices that exceed the preset threshold, and these devices are not allowed to borrow the total bandwidth.
  • a part of the bandwidth is reserved in the total bandwidth as the burst bandwidth (that is, the reserved bandwidth), and the remaining bandwidth (parent type bandwidth) is dynamically divided into the downlink devices, and initially all the devices are allowed to preempt the bandwidth.
  • the bandwidth of the parent class is defined as the total bandwidth minus the reserved bandwidth.
  • a subclass can borrow the bandwidth of the parent class and is not obligated to repay the bandwidth, which easily causes other subclasses to “starve to death”.
  • the present invention reserves part of the bandwidth in the total bandwidth, and does not allow the remaining bandwidth of the total bandwidth to be preempted. Subclasses are borrowed so that other subclasses can reserve bandwidth bursts through this part.
  • a preset threshold is specifically set. When other sub-type bursts exceed a preset threshold, the parent class bandwidth can be shared with all other sub-classes that exceed the threshold. among them,
  • the total bandwidth includes the total uplink bandwidth and the total downlink bandwidth.
  • the reserved bandwidth includes an uplink reserved bandwidth and a downlink reserved bandwidth.
  • the parent class bandwidth includes the upstream parent class bandwidth and the downstream parent class bandwidth.
  • Each device corresponds to a subclass, and each subclass allocates bandwidth based on the device MAC (Media Access Control).
  • MAC Media Access Control
  • the reserved bandwidth can be reserved according to the total bandwidth percentage. Generally, the reserved bandwidth should be able to browse the webpage normally in the case of non-preemption, that is, the reserved bandwidth is generally non-zero.
  • the reserved bandwidth can also be combined with the absolute value of the bandwidth to limit the reserved size, that is, the minimum and maximum values can be limited based on the percentage of the total bandwidth.
  • the reserved bandwidth includes an uplink reserved bandwidth and a downlink reserved bandwidth. When there is only one device at present, the reserved bandwidth is zero, that is, the bandwidth is no longer reserved, and the device can use the entire bandwidth.
  • the reserved bandwidth setting is as small as possible to ensure successful bandwidth preemption.
  • the default threshold is the minimum traffic that the device can share the bandwidth of the parent class. Devices with traffic exceeding this minimum have the right to share parent class bandwidth fairly.
  • the preset threshold is divided into an uplink bandwidth preset threshold and a downlink bandwidth preset threshold. The preset threshold is generally smaller than the reserved bandwidth.
  • the preset threshold is smaller, it is easier to trigger the dynamic equalization bandwidth. However, frequent equalization of bandwidth is likely to cause bandwidth waste, especially in the case where some devices use only small traffic.
  • the sensitivity of preempting the bandwidth is related to the preset threshold. The lower the preset threshold, the higher the sensitivity; the lower the reverse.
  • a timer may be set to detect the traffic of each device in real time.
  • the sensitivity of preempting bandwidth is related to the time interval of the timer. The smaller the time interval, the higher the sensitivity, and vice versa. The time interval is not as small as possible. The smaller the interval, the longer the CPU (Central Processing Unit) is, which affects the system to run other services.
  • the time interval is set to achieve the best user experience based on ensuring that the system performance is not affected, that is, it has higher sensitivity.
  • the device When the device traffic exceeding the preset threshold is detected to be lower than the preset threshold for a period of time, the device will no longer share the parent class bandwidth with other devices.
  • the device only guarantees that the minimum bandwidth is the average bandwidth after all devices have divided the total bandwidth, and allows the device to borrow the total bandwidth.
  • the device can use the entire total bandwidth.
  • Embodiment of this embodiment when initializing, the total bandwidth is reserved by 20%, and the remaining 80% is equally distributed to All hanging devices. If the total bandwidth is reserved 20% over 1 Mbps (Million bits per second), 1 Mbps is reserved. The bandwidth of 80% of the total bandwidth is called the parent class bandwidth.
  • the start timer can detect the uplink and downlink network traffic every second. If the uplink or downlink traffic of the N devices exceeds a certain threshold, the bandwidth of the parent class is equally distributed to the N devices (no borrowing is allowed), and other The device bursts to the parent class bandwidth on the basis of the parent class bandwidth. A device whose uplink and downlink traffic does not exceed the preset threshold can use the reserved bandwidth of the total bandwidth to preempt the bandwidth until the bandwidth is shared with other devices exceeding the preset threshold.
  • the total downlink bandwidth of the network environment is 10 Mbps and the total uplink bandwidth is 1 Mbps.
  • the downlink reserved bandwidth is 1 Mbps
  • the downlink parent bandwidth is 9 Mbps
  • the uplink reserved bandwidth is 200 Kbps
  • the uplink parent bandwidth is 800 Kbps.
  • the preset threshold of the upstream bandwidth threshold and the downlink bandwidth are both 50 Kbps.
  • the dynamic configuration bandwidth triggering mechanism type is: the uplink preset threshold is exceeded or the downlink preset threshold is exceeded.
  • Tc class add dev ifb0 parent 1:2 classid 1:101 htb rate 10000kbit ceil 10000kbit prio 0
  • Tc class add dev eth0 parent 1:2 classid 1:101 htb rate 1000kbit ceil 1000kbit prio 0
  • the TC rules can be configured as follows:
  • Tc class add dev ifb0 parent 1:2 classid 1:101 htb rate 4500kbit ceil 4500kbitprio 0
  • Tc class add dev ifb0 parent 1:2 classid 1:102 htb rate 4500kbit ceil 4500kbit prio 0
  • Tc class add dev ifb0 parent 1:2 classid 1:103 htb rate 2500kbit ceil 10000kbit prio 0
  • Tc class add dev ifb0 parent 1:2 classid 1:104 htb rate 2500kbit ceil 10000kbit prio 0
  • the available bandwidth resources of the foregoing device 103 and the device 104 may be limited to 2500 kbits to 10000 kbits, wherein 2500 kbits are obtained by dividing the total downlink bandwidth by 10 Mbps by 4 (the total number of devices).
  • Tc class add dev eth0 parent 1:2 classid 1:101 htb rate 400kbit ceil 400kbit prio 0
  • Tc class add dev eth0 parent 1:2 classid 1:102 htb rate 400kbit ceil 400kbit prio 0
  • Tc class add dev eth0 parent 1:2 classid 1:103 htb rate 250kbit ceil 1000kbit prio 0
  • Tc class add dev eth0 parent 1:2 classid 1:104 htb rate 250kbit ceil 1000kbit prio 0
  • the available bandwidth resources of the foregoing device 103 and device 104 may be limited to 250 kbit to 1000 kbit, wherein 250 kbit is obtained by dividing the total uplink bandwidth by 1 Mbps by 4 (the total number of devices).
  • both devices can use the downlink bandwidth of 4.5 Mbps and do not preempt more bandwidth. See the first schematic diagram of bandwidth allocation shown in FIG.
  • the device 103 or 104 can borrow the downlink reserved bandwidth 1 Mbps+ (4.5 Mbps-device use bandwidth)*2 (Note: two devices 101 and 102) of the total downlink bandwidth to preempt the bandwidth, and once the traffic exceeds the preset threshold, A shared 9 Mbps downstream bandwidth can be shared with devices 101 and 102.
  • the device usage bandwidth is not necessarily equal to 3 Mbps or 2.25 Mbps, that is, the downlink parent class bandwidth allocated to the device 103 or 104, and is not necessarily used by the device 103 or 104.
  • the bandwidth of the device 103 exceeds the preset threshold. See the second schematic diagram of the bandwidth allocation shown in FIG. 5.
  • the bandwidth of the device 104 also exceeds the preset threshold. See the third schematic diagram of the bandwidth allocation shown in FIG. 6.
  • the devices 102, 103, and 104 are all lower than the preset threshold. See the fourth schematic diagram of the bandwidth allocation shown in FIG.
  • FIG. 8 is a structural block diagram of a bandwidth allocation apparatus according to an embodiment of the present invention. As shown in FIG. 8, the apparatus includes: a bandwidth division module 10, a traffic monitoring module 20, and a bandwidth allocation module 30. The structure is described in detail below.
  • the bandwidth division module 10 is configured to divide the total uplink/downlink bandwidth of the router into upper/downstream parent class bandwidth and uplink/downlink reserved bandwidth according to a preset allocation ratio.
  • the traffic monitoring module 20 is connected to the bandwidth dividing module 10, and is configured to monitor bandwidth traffic of each device connected to the router; wherein each device whose bandwidth traffic exceeds a preset threshold is classified as a first type device, and the bandwidth traffic does not exceed the pre-pre- Each device with a threshold is classified as a second type of device;
  • the bandwidth allocation module 30 is connected to the traffic monitoring module 20 and is adapted to allocate the uplink/downstream parent class bandwidth and the uplink/downlink reserved bandwidth to the first type device and the second type device according to the monitoring result.
  • the bandwidth control function existing in the HTB algorithm is used to reserve bandwidth, set a threshold, and dynamically configure device bandwidth in a total bandwidth, so that all users can real-time in a situation where less total bandwidth is wasted. Seize the equal bandwidth and achieve the goal of fair sharing of bandwidth, which improves the user experience of enjoying network services.
  • the bandwidth of the device exceeds the preset threshold.
  • the upstream bandwidth of each device exceeds the upstream preset threshold.
  • the downstream bandwidth of each device exceeds the downlink preset threshold.
  • the upstream bandwidth of each device exceeds the upstream threshold.
  • the threshold bandwidth is exceeded, and the downlink bandwidth of each device exceeds the downlink preset threshold; the upstream bandwidth of each device exceeds the uplink preset threshold, or the downlink bandwidth of each device exceeds the downlink preset threshold;
  • the uplink/downlink preset threshold is smaller than the uplink/downlink reserved bandwidth value.
  • At least one of the following manners may be used to perform bandwidth allocation of the first type of device: average allocation, allocation according to a preset ratio, and priority allocation.
  • some similar P2P downloading software uses a special download mechanism, so that software using this mechanism can quickly grab a large bandwidth when downloading, until the entire bandwidth is preempted.
  • Thunder download software, BT download software, popular download software, potatoes, Youku online video, etc. in the multi-threaded mode, when downloading multiple movies, you can preempt all bandwidth, causing other devices can not preempt the bandwidth again, affecting other devices to use the network. Service, not even browsing the web. After using the present invention, these preemptive bandwidth software will not be able to preempt all bandwidth, and other devices can preempt and share the bandwidth fairly.
  • the embodiment of the present invention utilizes the existing bandwidth control function in the HTB algorithm to reserve bandwidth, set thresholds, and dynamically configure device bandwidth in the total bandwidth, so that all users can achieve less total bandwidth. Preemptively share the bandwidth in real time and achieve the goal of fair sharing of bandwidth, which improves the user experience of enjoying network services.

Landscapes

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

Abstract

一种带宽分配方法及装置。其中，该方法包括：将路由器的上/下行总带宽按照预设分配比，划分为上/下行父类带宽和上/下行预留带宽；监测路由器下挂的每个设备的带宽流量；将带宽流量超过预设门限的每个设备为第一类设备，带宽流量未超过预设门限的每个设备为第二类设备；根据监测结果，将上/下行父类带宽和上/下行预留带宽，相应分配给第一类设备和第二类设备。本发明实施例利用HTB算法中已有的带宽控制功能，设定门限以及动态配置设备带宽等机制，在较少浪费总带宽的情况下，实现所有用户均能实时抢占均分带宽，达到公平共享带宽的目的，提升了用户享受网络服务的体验。

Description

一种带宽分配方法及装置 技术领域
本发明涉及通信领域，特别是涉及一种带宽分配方法及装置。
背景技术
目前路由器一般下挂多台设备共享网络带宽，如果一台设备使用迅雷下载抢占整个带宽后，其他设备很难再将带宽抢占过来，导致其他设备无法正常使用网络服务。
目前一些类似P2P下载软件使用了特殊的下载机制，使得使用该机制的软件在下载时可以迅速抢占较大带宽，直至抢占到整个带宽。比如迅雷下载软件，BT下载软件，风行下载软件，土豆、优酷在线视频等，在开启多线程模式下，下载多部电影时可以抢占所有带宽，导致其他设备无法再次抢占带宽，影响其他设备使用网络服务，甚至不能浏览网页。
在相关技术中，即使使用HTB算法(Hierarchical Token Bucket，算法的流量管理功能)将总带宽均分给每台设备，依然不能完美解决这个问题。目前可分为两种情况分析，一种情况是均分带宽且允许借用带宽，这种情况下某台设备抢占整个带宽后，因其无义务偿还其他设备的带宽，导致其他设备无法再次抢占带宽，参见图1所示的根据相关技术的基于HTB算法为两台设备分配带宽的第一示意图，图1中设备A抢占了绝大部分带宽，而设备B无法再次抢占更多带宽。另外一种情况，均分带宽且不允许借用带宽，此时虽然不存在某些设备无法抢到带宽的情况，但是当某些设备使用带宽较少时，整个带宽的浪费较为严重，参见图2所示的根据相关技术的基于HTB算法为两台设备分配带宽的第二示意图，设备A最多只能占用部分带宽，设备B占用较少带宽，造成其余带宽的资源浪费。由上文分析可知，现有HTB算法的固有特性导致多台设备无法公平使用总带宽。
针对相关技术中带宽分配方法不够合理的问题，目前尚未提出有效的解决方案。
发明内容
针对相关技术中带宽分配方法不够合理的问题，本发明实施例提供了一种带宽分配方法及装置，用以解决上述技术问题。
根据本发明的一个方面，本发明实施例提供了一种带宽分配方法，包括：将路由器的上/下行总带宽按照预设分配比，划分为上/下行父类带宽和上/下行预留带宽；监测所述路由器下挂的每个设备的带宽流量；将带宽流量超过预设门限的每个设备为第一类设备，带宽流量未超过预设门限的每个设备为第二类设备；根据监测结果，将上/下行父类带宽和上/下行预留带宽，分别分配给所述第一类设备和第二类设备。
可选地，所述带宽流量超过所述预设门限，包括以下四种情况之一：每个设备的上行带宽流量超过上行预设门限；每个设备的下行带宽流量超过下行预设门限；每个设备的上行带宽流量超过上行预设门限，且，每个设备的下行带宽流量超过下行预设门限；每个设备的上行带宽流量超过上行预设门限，或，每个设备的下行带宽流量超过下行预设门限；
可选地，根据监测结果，将上/下行父类带宽和上/下行预留带宽，分别分配给所述第一类设备和第二类设备，包括：将所述上/下行父类带宽，分配给所述第一类设备使用；将剩余带宽分配给所述第二类设备使用；其中，所述剩余带宽＝上/下行预留带宽+(上/下行父类带宽－所述第一类设备使用的带宽)。
可选地，所述上/下行预设门限值小于上/下行预留带宽值。
可选地，对所述上/下行父类带宽采取以下方式至少之一进行所述第一类设备的带宽分配：平均分配、按预设比例分配、按优先级分配。
根据本发明的另一方面，本发明实施例还提供了一种带宽分配装置，包括：带宽划分模块，设置为将路由器的上/下行总带宽按照预设分配比，划分为上/下行父类带宽和上/下行预留带宽；流量监测模块，设置为监测所述路由器下挂的每个设备的带宽流量；将带宽流量超过预设门限的每个设备为第一类设备，带宽流量未超过预设门限的每个设备为第二类设备；带宽分配模块， 设置为根据监测结果，将上/下行父类带宽和上/下行预留带宽，分别分配给所述第一类设备和第二类设备。
可选地，所述带宽流量超过所述预设门限，包括以下四种情况之一：每个设备的上行带宽流量超过上行预设门限；每个设备的下行带宽流量超过下行预设门限；每个设备的上行带宽流量超过上行预设门限，且，每个设备的下行带宽流量超过下行预设门限；每个设备的上行带宽流量超过上行预设门限，或，每个设备的下行带宽流量超过下行预设门限；
可选地，所述带宽分配模块包括：第一分配单元，设置为将所述上/下行父类带宽分配给所述第一类设备使用；第二分配单元，设置为将剩余带宽分配给所述第二类设备使用；其中，所述剩余带宽＝上/下行预留带宽+(上/下行父类带宽－所述第一类设备使用的带宽)。
可选地，所述上/下行预设门限值小于上/下行预留带宽值。
可选地，所述带宽分配模块是设置为采取以下方式至少之一进行所述第一类设备的带宽分配：平均分配、按预设比例分配、按优先级分配。
本发明实施例还提供一种计算机程序及其载体，该计算机程序包括程序指令，当该程序指令被路由设备执行时，使得该路由设备可实施上述的带宽分配方法。
本发明实施例有益效果如下：
本发明实施例利用HTB算法中已有的带宽控制功能，通过在总带宽中预留带宽，设定门限以及动态配置设备带宽等机制，在较少浪费总带宽的情况下，实现所有用户均能实时抢占均分带宽，达到公平共享带宽的目的，提升了用户享受网络服务的体验。
附图概述
图1是根据相关技术的基于HTB算法为两台设备分配带宽的第一示意图；
图2是根据相关技术的基于HTB算法为两台设备分配带宽的第二示意图；
图3是根据本发明实施例的带宽分配方法的流程图；
图4是根据本发明实施例的带宽分配的第一示意图；
图5是根据本发明实施例的带宽分配的第二示意图；
图6是根据本发明实施例的带宽分配的第三示意图；
图7是根据本发明实施例的带宽分配的第四示意图；
图8是根据本发明实施例的带宽分配装置的结构框图。
本发明的较佳实施方式
为了解决现有技术中带宽分配方法不够合理的问题，本发明实施例提供了一种带宽分配方法及装置。
下文中将结合附图对本发明的实施例进行详细说明。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互任意组合。另外，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不限定本发明。
本实施例提供了一种带宽分配方法，该方法可以在路由器侧实现，图3是根据本发明实施例的带宽分配方法的流程图，如图3所示，该方法包括以下步骤(步骤S302-步骤S306)：
步骤S302，将路由器的上/下行总带宽按照预设分配比例，划分为上/下行父类带宽和上/下行预留带宽。该预设分配比可根据实际情况确定，例如：上/下行父类带宽占80％，上/下行预留带宽占20％等。
步骤S304，监测路由器下挂的每个设备的带宽流量；将带宽流量超过预设门限的每个设备归为第一类设备，带宽流量未超过预设门限的每个设备归为第二类设备。该预设门限的数值，可根据实际操作情况具体设定。
在本实施例中，基于路由器的上下行两条线路，带宽流量超过预设门限，可以包括以下四种情况之一：
1)每个设备的上行带宽流量超过上行预设门限；
2)每个设备的下行带宽流量超过下行预设门限；
3)每个设备的上行带宽流量超过上行预设门限，且，每个设备的下行带宽流量超过下行预设门限；
4)每个设备的上行带宽流量超过上行预设门限，或，每个设备的下行带宽流量超过下行预设门限。
其中，上/下行预设门限值小于上/下行预留带宽值。
步骤S306，根据监测结果，将上/下行父类带宽和上/下行预留带宽，相应分配给第一类设备和第二类设备。
在该步骤中，带宽的分配方法可以是：将上/下行父类带宽，分配给第一类设备使用；将剩余带宽分配给第二类设备使用；其中，剩余带宽＝上/下行预留带宽+(上/下行父类带宽－第一类设备使用的带宽)。在实际操作过程中，第一类设备使用的带宽不一定等于为其分配的上/下行父类带宽，即第一类设备不一定将为其分配的上/下行父类带宽全部使用。
本实施例利用HTB算法中已有的带宽控制功能，通过在总带宽中预留带宽，设定门限以及动态配置设备带宽等机制，在较少浪费总带宽的情况下，实现所有用户均能实时抢占均分带宽，达到公平共享带宽的目的，提升了用户享受网络服务的体验。
第一类设备的带宽分配原则可以是以下方式至少之一：平均分配、按预设比例分配、按优先级分配。对超过预设门限的所有设备共享父类带宽，且不允许这些设备再借用总带宽。
本实施例在总带宽中预留部分带宽作为突发带宽(即预留带宽)，剩余带宽(父类带宽)动态均分下挂设备，初始时允许所有设备突发抢占带宽。本实施例中定义父类带宽为总带宽减去预留带宽后的剩余带宽。HTB算法中子类可以借用父类带宽，且无义务偿还带宽，从而容易导致其他子类“饿死”，而本发明在总带宽中预留部分带宽，不允许已经抢占了总带宽所有剩余带宽的子类借用，从而可以使其他子类通过该部分预留带宽突发。在本发明中特别设置预设门限值，当其他子类突发流量超过预设门限时，即可与所有其他超过门限值的子类共享父类带宽。其中，
总带宽包括上行总带宽和下行总带宽。
预留带宽包括上行预留带宽和下行预留带宽。
父类带宽包括上行父类带宽和下行父类带宽。
每台设备对应一个子类，每个子类基于设备MAC(Media Access Control)分配带宽。
预留带宽可以按照总带宽百分比预留，一般预留带宽要保证非抢占情况下可以正常浏览网页，即预留带宽一般为非零值。预留带宽也可以结合带宽绝对值共同限制预留大小，即可以在取总带宽百分比的基础上限定最小值和最大值。预留带宽包括上行预留带宽和下行预留带宽。当前只有一台设备时，预留带宽为零，即不再预留带宽，该设备可使用整个带宽。预留带宽的设置在可以保证成功抢占带宽的前提下越小越好。
预设门限是设备可以共享父类带宽的流量最小值。流量超过该最小值的设备有权公平分享父类带宽。预设门限分为上行带宽预设门限和下行带宽预设门限。预设门限一般小于预留带宽。
预设门限虽然越小越容易触发动态均分带宽，但是频繁均分带宽容易造成带宽浪费，特别是有的设备只使用较小流量的情况。抢占带宽的灵敏度与预设门限有关，预设门限越低灵敏度越高；反之越低。
在本实施例中，可选地，可以设置定时器实时检测每台设备流量。抢占带宽的灵敏度与定时器的时间间隔有关。时间间隔越小灵敏度越高，反之越低。时间间隔并非越小越好，时间间隔越小占用CPU(Central Processing Unit)时间越长，影响系统运行其他业务。时间间隔的设置要在保证不影响系统性能的基础上达到最好的用户体验，即具有较高的灵敏度。
当检测到超过预设门限的设备流量经过一段时间低于预设门限时，该设备将不再与其他设备均分父类带宽。该设备仅保证最小带宽为所有设备均分总带宽后的平均带宽，且允许该设备借用总带宽。当路由器只有一台设备在线时，该设备可以使用整个总带宽。
下面举例说明该实施例的具体运行方式。
本实施例的实施方案：初始化时，将总带宽预留20％，剩余80％均分给 所有下挂设备。如果总带宽预留20％超过1Mbps(Million bits per second)，则预留1Mbps。总带宽80％的带宽称为父类带宽。启动定时器可以每隔一秒检测上下行网络流量，若有N个设备上行或下行流量超过某一预设门限，则将父类带宽均分给这N个设备(不允许借用)，允许其他设备在父类带宽均分基础上突发至父类带宽。上下行流量未超过预设门限的设备，可以使用总带宽的预留带宽突发抢占带宽，直至与其他超过预设门限的设备共同均分带宽。
假设网络环境下行总带宽为10Mbps，上行总带宽为1Mbps，那么按照上述实施方案，下行预留带宽为1Mbps，下行父类带宽为9Mbps，上行预留带宽为200Kbps，上行父类带宽为800Kbps，假设上行带宽预设门限和下行带宽预设门限均为50Kbps，动态配置带宽触发机制类型为：超过上行预设门限或超过下行预设门限。
A.当路由器只下挂一台设备时，允许其占用全部带宽，可以配置TC(Traffic Control)规则如下：
tc class add dev ifb0 parent 1:2 classid 1:101 htb rate 10000kbit ceil 10000kbit prio 0
tc class add dev eth0 parent 1:2 classid 1:101 htb rate 1000kbit ceil 1000kbit prio 0
其中ifb0为下行汇聚口设备，eth0为上行汇聚口设备。
B.当路由器下挂四台设备，其中有两台设备(设备101、设备102)流量超过预设门限时，可以配置TC规则如下：
下行：
tc class add dev ifb0 parent 1:2 classid 1:101 htb rate 4500kbit ceil 4500kbitprio 0
tc class add dev ifb0 parent 1:2 classid 1:102 htb rate 4500kbit ceil 4500kbit prio 0
tc class add dev ifb0 parent 1:2 classid 1:103 htb rate 2500kbit ceil 10000kbit prio 0
tc class add dev ifb0 parent 1:2 classid 1:104 htb rate 2500kbit ceil 10000kbit prio 0
上述设备103和设备104的可用带宽资源可以限定为2500kbit到10000kbit，其中，2500kbit为下行总带宽10Mbps除以4(总设备数量)得到。
上行：
tc class add dev eth0 parent 1:2 classid 1:101 htb rate 400kbit ceil 400kbit prio 0
tc class add dev eth0 parent 1:2 classid 1:102 htb rate 400kbit ceil 400kbit prio 0
tc class add dev eth0 parent 1:2 classid 1:103 htb rate 250kbit ceil 1000kbit prio 0
tc class add dev eth0 parent 1:2 classid 1:104 htb rate 250kbit ceil 1000kbit prio 0
上述设备103和设备104的可用带宽资源可以限定为250kbit到1000kbit，其中，250kbit为上行总带宽1Mbps除以4(总设备数量)得到。
当设备101或102流量超过50Kbps时，两台设备均可使用4.5Mbps下行父类带宽，且不会抢占更多带宽，参见图4所示的带宽分配的第一示意图。
此时设备103或104可以借用下行总带宽的下行预留带宽1Mbps+(4.5Mbps－设备使用带宽)*2(注：两台设备101和102)来抢占带宽，一旦其流量超过预设门限，即可与设备101和102共享均分9Mbps下行带宽。其中，设备使用带宽不一定等于3Mbps或2.25Mbps，即为设备103或104分配的下行父类带宽，不一定被设备103或104全部使用。
设备103带宽流量超过预设门限参见图5所示的带宽分配的第二示意图。
设备104带宽流量也超过预设门限参见图6所示的带宽分配的第三示意图。
设备102、103和104均低于预设门限参见图7所示的带宽分配的第四示意图。
对应于上述实施例介绍的带宽分配方法，本实施例提供了一种带宽分配装置，该装置可以设置在路由器侧，用以实现上述实施例，所述路由器包括处理器、程序存储器和数据存储器。图8是根据本发明实施例的带宽分配装置的结构框图，如图8所示，该装置包括：带宽划分模块10、流量监测模块20和带宽分配模块30。下面对该结构进行详细介绍。
带宽划分模块10，适用于将路由器的上/下行总带宽按照预设分配比，划分为上/下行父类带宽和上/下行预留带宽；
流量监测模块20，连接至带宽划分模块10，适用于监测路由器下挂的每个设备的带宽流量；其中，带宽流量超过预设门限的每个设备归为第一类设备，带宽流量未超过预设门限的每个设备归为第二类设备；
带宽分配模块30，连接至流量监测模块20，适用于根据监测结果，将上/下行父类带宽和上/下行预留带宽，相应分配给第一类设备和第二类设备。
本实施例利用HTB算法中已有的带宽控制功能，通过在总带宽中预留带宽，设定门限以及动态配置设备带宽等机制，在较少浪费总带宽的情况下，实现所有用户均能实时抢占均分带宽，达到公平共享带宽的目的，提升了用户享受网络服务的体验。
带宽流量超过预设门限，包括以下四种情况之一：每个设备的上行带宽流量超过上行预设门限；每个设备的下行带宽流量超过下行预设门限；每个设备的上行带宽流量超过上行预设门限，且，每个设备的下行带宽流量超过下行预设门限；每个设备的上行带宽流量超过上行预设门限，或，每个设备的下行带宽流量超过下行预设门限；
可选地，带宽分配模块30包括：第一分配单元，适用于将上/下行父类带宽分配给第一类设备使用；第二分配单元，适于将剩余带宽分配给第二类设备使用；其中，剩余带宽＝上/下行预留带宽+(上/下行父类带宽－第一类设备使用的带宽)。
本实施例中，上/下行预设门限值小于上/下行预留带宽值。
本实施例中，可以采取以下方式至少之一进行第一类设备的带宽分配：平均分配、按预设比例分配、按优先级分配。
目前一些类似P2P下载软件使用了特殊的下载机制，使得使用该机制的软件在下载时可以迅速抢占较大带宽，直至抢占到整个带宽。比如迅雷下载软件，BT下载软件，风行下载软件，土豆、优酷在线视频等，在开启多线程模式下，下载多部电影时可以抢占所有带宽，导致其他设备无法再次抢占带宽，影响其他设备使用网络服务，甚至不能浏览网页。使用本发明后这些抢占带宽的软件将无法抢占所有带宽，且其他设备可以抢占并公平共享带宽。
本领域普通技术人员可以理解上述方法中的全部或部分步骤可通过程序来指令相关硬件完成，所述程序可以存储于计算机可读存储介质中，如只读存储器、磁盘或光盘等。可选地，上述实施例的全部或部分步骤也可以使用一个或多个集成电路来实现。相应地，上述实施例中的各模块/单元可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。本发明不限制于任何特定形式的硬件和软件的结合。
当然，本发明还可有其他多种实施例，在不背离本发明精神及其实质的情况下，熟悉本领域的技术人员当可根据本发明作出各种相应的改变和变形，但这些相应的改变和变形都应属于本发明的权利要求的保护范围。
工业实用性
本发明实施例利用HTB算法中已有的带宽控制功能，通过在总带宽中预留带宽，设定门限以及动态配置设备带宽等机制，在较少浪费总带宽的情况下，实现所有用户均能实时抢占均分带宽，达到公平共享带宽的目的，提升了用户享受网络服务的体验。

Claims (12)

  1. 一种带宽分配方法，包括：
    将路由器的上/下行总带宽按照预设分配比，划分为上/下行父类带宽和上/下行预留带宽；
    监测所述路由器下挂的每个设备的带宽流量，将带宽流量超过预设门限的每个设备归为第一类设备，带宽流量未超过预设门限的每个设备归为第二类设备；
    根据监测结果，将上/下行父类带宽和上/下行预留带宽，分别分配给所述第一类设备和第二类设备。
  2. 如权利要求1所述的方法，其中，所述带宽流量超过所述预设门限，包括以下四种情况之一：
    每个设备的上行带宽流量超过上行预设门限；
    每个设备的下行带宽流量超过下行预设门限；
    每个设备的上行带宽流量超过上行预设门限，且，每个设备的下行带宽流量超过下行预设门限；
    每个设备的上行带宽流量超过上行预设门限，或，每个设备的下行带宽流量超过下行预设门限。
  3. 如权利要求1所述的方法，其中，所述根据监测结果，将上/下行父类带宽和上/下行预留带宽，分别分配给所述第一类设备和第二类设备，包括：
    将所述上/下行父类带宽，分配给所述第一类设备使用；
    将剩余带宽分配给所述第二类设备使用；其中，所述剩余带宽＝上/下行预留带宽+(上/下行父类带宽－所述第一类设备使用的带宽)。
  4. 如权利要求2所述的方法，其中，所述上/下行预设门限值小于上/下行预留带宽值。
  5. 如权利要求1所述的方法，其中，对所述上/下行父类带宽采取以下方式至少之一进行所述第一类设备的带宽分配：
    平均分配、按预设比例分配、按优先级分配。
  6. 一种带宽分配装置，包括：
    带宽划分模块，设置为将路由器的上/下行总带宽按照预设分配比，划分为上/下行父类带宽和上/下行预留带宽；
    流量监测模块，设置为监测所述路由器下挂的每个设备的带宽流量；将带宽流量超过预设门限的每个设备归为第一类设备，带宽流量未超过预设门限的每个设备归为第二类设备；
    带宽分配模块，设置为根据监测结果，将上/下行父类带宽和上/下行预留带宽，分别分配给所述第一类设备和第二类设备。
  7. 如权利要求6所述的装置，其特征在于，所述带宽流量超过所述预设门限，包括以下四种情况之一：
    每个设备的上行带宽流量超过上行预设门限；
    每个设备的下行带宽流量超过下行预设门限；
    每个设备的上行带宽流量超过上行预设门限，且，每个设备的下行带宽流量超过下行预设门限；
    每个设备的上行带宽流量超过上行预设门限，或，每个设备的下行带宽流量超过下行预设门限。
  8. 如权利要求6所述的装置，其中，所述带宽分配模块包括：
    第一分配单元，设置为将所述上/下行父类带宽分配给所述第一类设备使用；
    第二分配单元，设置为将剩余带宽分配给所述第二类设备使用；其中，所述剩余带宽＝上/下行预留带宽+(上/下行父类带宽－所述第一类设备使用的带宽)。
  9. 如权利要求7所述的装置，其中，所述上/下行预设门限值小于上/下行预留带宽值。
  10. 如权利要求6所述的装置，其中，所述带宽分配模块是设置为采取以下方式至少之一进行所述第一类设备的带宽分配：平均分配、按预设比例分配、按优先级分配。
  11. 一种计算机程序，包括程序指令，当该程序指令被路由设备执行时，使得该路由设备可实施权利要求1-5任一项的方法。
  12. 一种载有权利要求11所述计算机程序的载体。
PCT/CN2015/071331 2014-09-17 2015-01-22 一种带宽分配方法及装置 WO2015131692A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP15758045.7A EP3197110B1 (en) 2014-09-17 2015-01-22 Bandwidth allocation method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410475540.5A CN105490967A (zh) 2014-09-17 2014-09-17 一种带宽分配方法及装置
CN201410475540.5 2014-09-17

Publications (1)

Publication Number Publication Date
WO2015131692A1 true WO2015131692A1 (zh) 2015-09-11

Family

ID=54054541

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/071331 WO2015131692A1 (zh) 2014-09-17 2015-01-22 一种带宽分配方法及装置

Country Status (3)

Country Link
EP (1) EP3197110B1 (zh)
CN (1) CN105490967A (zh)
WO (1) WO2015131692A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111818585A (zh) * 2020-07-30 2020-10-23 中国联合网络通信集团有限公司 一种用户接入方法及接入网设备
CN111818586A (zh) * 2020-07-30 2020-10-23 中国联合网络通信集团有限公司 一种用户接入方法及接入网设备
CN111897756A (zh) * 2020-06-18 2020-11-06 福建升腾资讯有限公司 一种hid从设备usb带宽自适应调整方法、装置、设备和介质
CN116760785A (zh) * 2023-08-10 2023-09-15 腾讯科技（深圳）有限公司 带宽分配方法、装置、电子设备及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
USD982375S1 (en) 2019-06-06 2023-04-04 Sharkninja Operating Llc Food preparation device
CN113285886B (zh) * 2021-06-11 2021-10-15 北京天融信网络安全技术有限公司 一种带宽分配的方法、装置、电子设备及可读存储介质
CN114900470B (zh) * 2022-06-17 2023-10-31 中国联合网络通信集团有限公司 流量控制方法、装置、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101232449A (zh) * 2008-02-27 2008-07-30 福建星网锐捷网络有限公司 一种带宽分配方法及装置
CN102104874A (zh) * 2009-12-21 2011-06-22 中兴通讯股份有限公司 网络传输资源的分配方法及相关装置
CN102932274A (zh) * 2011-08-11 2013-02-13 中怡(苏州)科技有限公司 带宽控制方法及其计算机程序产品
CN104038442A (zh) * 2014-06-11 2014-09-10 普联技术有限公司 一种带宽分配的方法及路由器

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101009652A (zh) * 2007-01-23 2007-08-01 中兴通讯股份有限公司 以太网无源光网络下行流控信息传递方法
US8024417B2 (en) * 2008-06-04 2011-09-20 Microsoft Corporation Simple flow control protocol over RDMA
US8089971B1 (en) * 2008-11-13 2012-01-03 Qlogic, Corporation Method and system for transmitting flow control information
CN101599908B (zh) * 2009-07-15 2011-11-16 杭州华三通信技术有限公司 一种带宽的自动分配方法和设备
CN103379551B (zh) * 2012-04-20 2017-05-31 中兴通讯股份有限公司 一种高级数据链路控制链路带宽的分配方法及设备
CN103441943B (zh) * 2013-08-28 2016-11-16 迈普通信技术股份有限公司 一种流量报文控制方法及装置
CN103986715B (zh) * 2014-05-21 2017-10-03 海信集团有限公司 一种网络流量控制的方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101232449A (zh) * 2008-02-27 2008-07-30 福建星网锐捷网络有限公司 一种带宽分配方法及装置
CN102104874A (zh) * 2009-12-21 2011-06-22 中兴通讯股份有限公司 网络传输资源的分配方法及相关装置
CN102932274A (zh) * 2011-08-11 2013-02-13 中怡(苏州)科技有限公司 带宽控制方法及其计算机程序产品
CN104038442A (zh) * 2014-06-11 2014-09-10 普联技术有限公司 一种带宽分配的方法及路由器

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111897756A (zh) * 2020-06-18 2020-11-06 福建升腾资讯有限公司 一种hid从设备usb带宽自适应调整方法、装置、设备和介质
CN111818585A (zh) * 2020-07-30 2020-10-23 中国联合网络通信集团有限公司 一种用户接入方法及接入网设备
CN111818586A (zh) * 2020-07-30 2020-10-23 中国联合网络通信集团有限公司 一种用户接入方法及接入网设备
CN111818585B (zh) * 2020-07-30 2022-07-12 中国联合网络通信集团有限公司 一种用户接入方法及接入网设备
CN111818586B (zh) * 2020-07-30 2022-07-12 中国联合网络通信集团有限公司 一种用户接入方法及接入网设备
CN116760785A (zh) * 2023-08-10 2023-09-15 腾讯科技（深圳）有限公司 带宽分配方法、装置、电子设备及存储介质
CN116760785B (zh) * 2023-08-10 2023-10-17 腾讯科技（深圳）有限公司 带宽分配方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
EP3197110A4 (en) 2017-11-01
EP3197110B1 (en) 2020-09-23
EP3197110A1 (en) 2017-07-26
CN105490967A (zh) 2016-04-13

Similar Documents

Publication Publication Date Title
WO2015131692A1 (zh) 一种带宽分配方法及装置
CN107210972B (zh) 控制公平带宽分配效率的系统和方法
CN108337188B (zh) 通信量和负载感知动态队列管理
WO2018086569A1 (zh) 一种基于虚拟网络的应用感知的动态sdn配置方法
Tomovic et al. SDN control framework for QoS provisioning
EP2561660B1 (en) Controlling data transmission over a network
CN105335229B (zh) 一种业务资源的调度方法和装置
WO2016015559A1 (zh) 云化数据中心网络的承载资源分配方法、装置及系统
WO2013078588A1 (zh) 虚拟机内存调整方法和设备
WO2011137727A1 (zh) 一种报文的传输方法和系统
US20150103646A1 (en) Allocating network bandwith
KR102358821B1 (ko) 애플리케이션들에 대한 네트워크 분류
CN104980359A (zh) 以太网光纤通道的流量控制方法、装置及系统
WO2015024158A1 (zh) 一种准入控制方法和装置
EP2938033A1 (en) Device and method for managing resources in multicast service
US9363199B1 (en) Bandwidth management for data services operating on a local network
KR20170126584A (ko) VPN 터널링의 QoS를 위한 다중큐잉 실시간 트래픽 쉐이핑 시스템 및 방법
KR102202458B1 (ko) 네트워크 슬라이스 기반 이동통신 네트워크에서 QoS에 기반한 통신 방법 및 장치
WO2016107368A1 (zh) 一种ip网络中业务带宽确定方法及网络设备
Michel et al. Extending the software-defined network boundary
WO2019119180A1 (zh) 一种分配带宽资源的方法及基站
Altufaili Intelligent network bandwidth allocation using SDN (software defined networking)
US20230138522A1 (en) Queue Bandwidth Estimation for Management of Shared Buffers and Allowing Visibility of Shared Buffer Status
WO2021254202A1 (zh) 数据调度方法、设备和存储介质
TWI648967B (zh) Service chain deployment method considering network latency and physical resources

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: 15758045

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

REEP Request for entry into the european phase

Ref document number: 2015758045

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015758045

Country of ref document: EP