WO2017113868A1 - Cdn平台自适应带宽控制方法和系统 - Google Patents
Cdn平台自适应带宽控制方法和系统 Download PDFInfo
- Publication number
- WO2017113868A1 WO2017113868A1 PCT/CN2016/097987 CN2016097987W WO2017113868A1 WO 2017113868 A1 WO2017113868 A1 WO 2017113868A1 CN 2016097987 W CN2016097987 W CN 2016097987W WO 2017113868 A1 WO2017113868 A1 WO 2017113868A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- control
- agent
- cdn
- data
- control center
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/80—Responding to QoS
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/76—Admission control; Resource allocation using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/61—Network streaming of media packets for supporting one-way streaming services, e.g. Internet radio
- H04L65/612—Network streaming of media packets for supporting one-way streaming services, e.g. Internet radio for unicast
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
- H04L67/289—Intermediate processing functionally located close to the data consumer application, e.g. in same machine, in same home or in same sub-network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/568—Storing data temporarily at an intermediate stage, e.g. caching
- H04L67/5682—Policies or rules for updating, deleting or replacing the stored data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04847—Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Definitions
- the present invention relates to a self-protection of a content distribution network (CDN) platform, and in particular, a method and system for self-protection at an adaptive bandwidth flow control level
- CDN content distribution network
- Digital content can include web objects (eg, text, graphics, URLs, scripts), downloadable objects (eg, media files, software, documents, etc.), web applications, streaming media (eg, audio and video content), and the like.
- web objects eg, text, graphics, URLs, scripts
- downloadable objects eg, media files, software, documents, etc.
- web applications eg, streaming media
- streaming media eg, audio and video content
- a CDN technology which is called a Content Delivery Network, that is, a content distribution network.
- the purpose of the technology is to add a new network architecture to the existing Internet to publish the content of the website to the "edge" of the network closest to the user, so that the user can obtain the required content and solve the Internet network congestion.
- the situation improving the responsiveness of users visiting the website.
- a CDN is a distributed network that is built on top of a bearer network and consists of service nodes distributed in different areas.
- the CDN Content Delivery Network
- the CDN technology can transmit the information of the remote data center to the local server, and the local user can access the local server to complete the service.
- the Content Delivery Network is a strategically deployed overall system that includes distributed storage, load balancing, network request redirection and content management, and content management and global network traffic management ( Traffic Management is at the heart of the CDN. Through the judgment of user proximity and server load, the CDN ensures that the content serves the user's request in an extremely efficient manner.
- the content service is based on a cache server, also known as a proxy cache, which is located at the edge of the network and is only from the user. "Single Hop”.
- the proxy cache is a transparent image of the content provider source server (usually located in the data center of the CDN service provider).
- CDN technology can handle 70% to 95% of the content of the entire website, reducing the pressure on the server and improving the performance and scalability of the website.
- CDN bandwidth control line for the accelerated customer on the platform in advance.
- the threshold of the control line is usually communicated to the customer for confirmation and then static planning.
- the CDN technology After the control line is set, when the bandwidth usage rate in the CDN platform exceeds the bandwidth control line, the CDN technology provides various control modes according to the static planning configuration, such as directly disconnecting, returning to the source source station, and slow.
- One of a variety of ways, such as speed connection performs bandwidth control, thereby achieving the purpose of reducing bandwidth usage to ensure normal service of the platform.
- the above-mentioned traditional control line mechanism may lead to the fact that when the CDN platform may be capable of serving itself, but due to the limitation of the planned control line in advance, some services must be stopped to solve the bandwidth problem, thereby failing to maximize the use of the CDN. resource of.
- a customer's business volume bursts or a short-term increase in business volume may result in a decline in the service capacity of the entire CDN platform service resources, which affects many other customers in the platform.
- the factors affecting the bandwidth considered when the command is assigned the value are relatively simple, and usually only factors such as bandwidth or traffic are considered. Therefore, the distribution may have a large error with the actual use situation, causing some resources to be overwhelmed and another part of the resources to be too idle. The irrationality of such resource allocation seriously affects the security and stability of the CDN platform.
- the CDN platform needs to have certain self-protection capabilities, and there is a need for a solution that can adaptively control the CDN platform under the above circumstances to prevent affecting other customers or minimizing the number of affected customers.
- the solution must be able to take into account more bandwidth factors and have good timeliness.
- the technical problem to be solved by the present invention is to provide an adaptive bandwidth controller for a CDN platform. Laws and systems to provide good self-protection capabilities for the CDN platform.
- a method for adaptive bandwidth control of a CDN platform comprising:
- the control center After receiving the task registration from the agent, the control center allocates a range of CDN service resources that it can control to the agent;
- the CDN service resource After receiving the data collection command, the CDN service resource returns the real-time data to the agent that sends the data collection command;
- the agent transmits the collected data to the control center;
- the control center summarizes the collected data and generates an adaptive control line through data analysis
- the control center generates and releases a control instruction for the agent according to the collected data of each CDN service resource and in combination with the control line;
- the agent After receiving the control instruction, the agent generates a control policy for each CDN service resource it controls through self-learning adjustment, and delivers the control policy to the corresponding CDN service resource.
- a system for adaptive bandwidth control of a CDN platform comprising:
- the UI platform configures relevant parameters of the adaptive task through the UI platform and sends the related parameters to the control center;
- One or more agents for controlling one or more of the plurality of CDN service resources are One or more agents for controlling one or more of the plurality of CDN service resources
- control center the control center is configured to:
- the agent is configured to:
- the CDN service resource is configured to:
- the real-time data is returned to the agent that sent the data collection command.
- FIG. 1 shows a schematic diagram of implementing a system structure in accordance with an embodiment of the present invention.
- FIG. 2 shows a proxy registration flow diagram in accordance with an embodiment of the present invention.
- FIG. 3 shows a flow chart of data summary analysis in accordance with an embodiment of the present invention.
- FIG. 4 shows a flow chart of control policy generation in accordance with an embodiment of the present invention.
- Figure 5 shows a diagram of an overall operational example in accordance with an embodiment of the present invention.
- FIG. 1 A schematic diagram of implementing a system structure in accordance with an embodiment of the present invention is shown in FIG. 1
- the system platform of the present invention is primarily comprised of a CDN service resource pool 102, an acquisition control distributed agent cluster 104, a UI platform 106, and a control center 108.
- the CDN service resource pool 102 includes a plurality of CDN service resources 102-1, ..., 102-n
- the agent cluster 104 includes a plurality of agents 104-1, ..., 104-n.
- the CDN service resources 102-1, ..., 102-n and the agents 104-1, ..., 104-n may include any number of CDN service resources and agents, and are not limited to those shown in the figure. Quantity.
- the data center 108 includes a data summary analysis module 108a and a control line module 108b.
- a CDN service resource refers to various resources capable of providing a CDN service, such as a server, a website, and the like.
- the adaptive control of the CDN resources described in the present invention is intended to rationally allocate these CDN service resources in order to provide a self-protection capability for the CDN platform.
- the UI platform 106 provides a unified configuration portal and a functional operation interface, and through the UI platform, multiple modules of the entire system can be automatically connected to control the entire adaptive bandwidth control system.
- the UI platform can be used by the user to manage the configuration, operation, and maintenance of the entire system.
- Agents are generally located at the edge of the network and are therefore also referred to as edge proxies.
- the agent can register the task with the control center 108, obtain the CDN service resource that needs to be controlled from the control center through registration, and automatically perform task scheduling when a certain agent has a machine failure, so as to ensure that all service resources are allocated. There are agents that control it.
- the registration process of the agent will be described in further detail in FIG. Subsequently, the agent collects and merges relevant data for the controlled CDN service resources, and then transmits the processed data to the control center 108 through the optimized UDP protocol.
- the control center 108 collects the data collected by the agent and aggregated into the machine data set in real time, and the data summary analysis module 108a performs real-time summarization and analysis on various factors included in the data, and calculates redundant proportion data such as resources. And data such as the bandwidth growth ratio of the client channel, the data is compared with the corresponding ratio configured on the UI, and if the set comparison result is satisfied, the adaptive control line is generated by the control line module 108b.
- a summary analysis of the data described will be described in further detail in FIG.
- control center 108 ultimately generates the control instructions required for each CDN service resource pool 102 based on the generated adaptive control lines, and finally reaches all of the edges at the edge of the task and control commands according to the CDN service resource range controlled by the agent.
- the server of the proxy After the agent at the edge receives the task assigned by the control center 108, the corresponding control policy can be further generated through processing, and then the task and the control policy are reached to the corresponding CDN service resources to implement self-protection of the CDN platform.
- FIG. 2 a proxy registration flow diagram in accordance with an embodiment of the present invention is depicted.
- Heartbeat packets see step 202 to control center 108.
- the control center 108 collects the heartbeat packets, and in step 206, determines to send the heartbeat by determining whether the difference between the time of the last heartbeat packet upload and the current time exceeds the configured heartbeat packet expiration time. Whether the autonomous machine (agent) of the package survives.
- the difference exceeds the heartbeat packet expiration time, it is considered that the autonomous machine (agent) has failed and there is no way to upload the latest heartbeat packet, so the autonomous machine (agent) does not survive; or the data content of the heartbeat packet ( For example, if the software is running OK, it is determined whether the agent that sent the heartbeat packet is still alive.
- step 208 the agent registration is successful and the control center 108 assigns a range of controlled CDN service resources to it based on the configuration information that the agent is planning on the CDN platform.
- step 210 the control center 108 culls the CDN service resource tasks scheduled by the agent on the CDN platform and performs a diffusion search through the regional proximity principle. Obtain other surviving agents to take over the CDN service resources originally controlled by the failed agent, thereby implementing automatic scheduling of the agent.
- the agent After the agent has successfully registered with the control center 108, it can obtain from the control center 108 the range of CDN service resources it needs to control. Subsequently, the data summary analysis flow according to an embodiment of the present invention described in FIG. 3 can be performed.
- the agent performs data collection on the switch for the node of the CDN service resource to obtain real-time bandwidth data (eg, real-time bandwidth value) of the node.
- real-time bandwidth data eg, real-time bandwidth value
- the agent collects data on the server of the CDN service resource to obtain machine data such as real-time bandwidth, software health, and various physical attributes (such as CPU, memory, load, etc.) of the server. .
- a planned bandwidth value that is expected to be available is stored on the CDN platform by storing the stored expected bandwidth value and the smoothed processed real-time bandwidth of the collected node. The values are analyzed and compared to calculate the service capabilities of each node.
- step 308 according to the server such as real-time bandwidth, health values, and various physical attributes
- the machine data of the class is comprehensively analyzed for the proportion of the influence of the machine to calculate the machine service capability of each server.
- step 310 after collecting data such as the service capability of the node of the CDN resource and the machine, the big data is analyzed through the association relationship between the customer channel and its resource usage, and if the redundancy ratio value of the customer channel resource is analyzed, the client
- the bandwidth growth ratio value of the channel and the like have already met the redundancy ratio value or the bandwidth growth ratio value configured on the UI, and a control line (also called an adaptive control line) of the channel is generated in real time according to the bandwidth capability of the current channel.
- control center 106 can combine the data collected from each CDN service resource to generate control instructions for each agent and down to each agent machine.
- the control policy can be assigned to the CDN server according to the control policy generation process according to the embodiment of the present invention shown in FIG.
- the agent collects network data such as the number of requests, the number of rejections, and the current bandwidth of each CDN server according to the range of controllable CDN service resources allocated to it by the control center 106.
- the amount of bandwidth that each request brings is predicted by the case of the history request, thereby presuming that if the rejection is not performed, the actual data is calculated according to the network data such as the number of requests, the number of rejections, and the current bandwidth.
- step 406 based on the actual bandwidth of the calculated channel on the CDN server, and the service capabilities of the node to which the server set belongs and the machine service capabilities of the server set itself (see steps 306 and 308 in the flow described in FIG. 3), Assign a control policy to the server collection.
- the policy includes a bandwidth control value.
- the autonomous machine collects the bandwidth control policy value according to the real-time bandwidth and load capacity of each machine in the server set collected in real time. Appropriate allocation is made, and each server is finally assigned a control value to be finally released.
- control policy After the control policy is generated, the control policy is released to the corresponding CDN service resource to implement self-protection of the CDN platform.
- the policy may be sent to the corresponding CDN server through the proxy for bandwidth management.
- FIG. 5 After describing various important aspects of the adaptive bandwidth control scheme of the CDN platform according to FIGS. 2-4, the overall operation scheme of the adaptive bandwidth control scheme of the CDN platform according to the embodiment of the present invention is based on FIG. 5 below. Give an example.
- the UI platform 106 configures the relevant parameters of the adaptive task and pushes the configured data containing the relevant parameters to the control center 108 after the configuration is complete.
- Nodes at the edge of the network traditionally adopt node autonomy technology, and each edge will be deployed with an agent (ie, a proxy server).
- agent ie, a proxy server
- An acquisition control distributed agent cluster 104 At step 504, each agent in the agent cluster will go to the control center 108 for task registration.
- the specific process of the agent's task registration can be referred to the previous detailed description with respect to FIG. 2. It will not be repeated here.
- the control center 106 After receiving the task registration request from the agent, in step 506, the control center 106 will generally adopt ping according to the physical area attribute of the agent (for example, the province of the machine room to which the machine belongs) and the network status (for example, the access effect between the nodes).
- the delay and packet loss rate), the state of the machine (such as CPU usage, load and other machine data) and the state of availability of the UI registration (such as the platform registration identifier) are assigned to the state.
- the agent controls the scope of the corresponding service resource and returns it to the agent as registration status data.
- the edge agent After receiving the registration status data returned by the control center 106, the edge agent can obtain information of the controllable CDN service resources allocated thereto. And, in step 508, the agent sends a data collection command to the CDN service resource it controls over the defined data interface.
- step 510 the CDN service resource 102 returns the real-time data to the agent that sent the data collection command according to the type of the collected data contained in the data collection command sent by the proxy.
- the agent aggregates the collected data according to certain rules and sends it to the control center 106.
- the control center 106 performs a summary accumulation of the entire network data, and automatically generates a corresponding control line from the aggregated data according to the resource usage of the client, the use of the machine, and the usage of the node through the data analysis.
- the specific process of the aggregate analysis of the data can be seen in the previous detailed description with respect to FIG. It will not be repeated here. Since the control line is dynamically generated according to data collected from a CDN service resource in real time, the present invention can better enable bandwidth allocation and network operation compared to a preset fixed control line used in the prior art. The actual situation is matched to improve the utilization of network resources.
- control center 106 generates control instructions for each agent based on the data collected from each of the CDN service resources in conjunction with the generated control lines and down to each agent machine.
- step 518 after the agent receives the corresponding control instruction, as long as the instruction is within the validity period, the agent will be based on the data collected in real time, and according to the historically issued control instruction data and finally The situation of control comes from my learning adjustments to generate the final control strategy (such as control instructions) for each CDN service resource it controls.
- the generation of the control strategy has already been mentioned in the previous detailed description with respect to Figure 4 and will not be repeated here. However, if the control instruction has exceeded the validity period, the control instruction is ignored, that is, no control strategy is executed.
- step 520 the agent will eventually reach the corresponding CDN service resource of the actual service in the form of, for example, a control instruction, to achieve the final adaptive bandwidth control effect.
- the solution of the present invention adopts a method of generating a policy at the control center and a distributed control at the edge, compared to the centralized control method adopted by the prior art.
- the data transmission adopts a protocol such as an improved stable transmission protocol, which is a self-developed transmission protocol supported by UDP, which utilizes the resource advantage of the CDN node to perform route detection, thereby being able to The situation of each route intelligently selects the optimal transmission path to improve the timeliness and reliability of the control.
- the solution of the present invention also considers the number of requests and the number of rejections to estimate the actual traffic, and considers the service capability of the CDN server, and combines various factors to make the allocation. More reasonable, and will carry out the gap control of the front and rear control values; calculate the actual gap between the released control value and the actual bandwidth value through real-time self-learning by negative feedback, and calculate a relatively stable proportional coefficient.
- the control value is adjusted in real time by the data, and after the prediction model of the actual bandwidth is established for the relationship between the bandwidth, the number of requests, and the number of rejections, the control value is allocated according to the bandwidth to improve the accuracy of the control and reduce the fluctuation, especially the small bandwidth or small. Good control of flow.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
Claims (8)
- 一种用于CDN平台的自适应带宽控制的方法,其特征在于,包括:通过UI平台配置自适应任务的相关参数并将其发送给控制中心;由多个代理中的一个代理向所述控制中心注册任务;接收到来自所述代理的任务注册之后,所述控制中心为所述代理分配其可控制的CDN服务资源的范围;所述代理根据所述控制中心所分配的可控制的CDN服务资源的范围向所述范围中的CDN服务资源发送数据采集命令;CDN服务资源接收到所述数据采集命令之后,将实时数据返回给发送所述数据采集命令的代理;所述代理将采集到的数据传送给所述控制中心;所述控制中心对采集的数据进行汇总,并通过数据分析生成自适应的控制线;所述控制中心根据每个CDN服务资源的所采集的数据并结合所述控制线,为所述代理生成并下达控制指令;在接收到所述控制指令之后,所述代理通过自我学习调整生成针对其所控制的每个CDN服务资源的控制策略,并将所述控制策略下达给相应的CDN服务资源。
- 如权利要求1所述的方法,其特征在于,所述由多个代理中的一个代理向所述控制中心注册任务的步骤包括:所述代理向所述控制中心主动上传其心跳包;所述控制中心收集所述心跳包,并基于所述心跳包内存在的过期状态以及所述心跳包的数据内容来判断发送该心跳包的代理是否还存活;如果确定所述代理是存活的,则所述代理注册成功,并且所述控制中心根据所述代理在CDN平台上规划的配置信息为其分配所控制的CDN服务器资源的范围;如果确定所述代理不是存活的,则控制中心剔除所述代理在CDN平台上规划的CDN服务资源的任务,并使用其它存活的代理接手发生故障的所述代理原本控制的CDN服务资源。
- 如权利要求2所述的方法,其特征在于,所述控制中心对采集的数据进行汇总,并通过数据分析生成自适应的控制线的步骤包括:所述代理对于CDN服务资源的节点进行数据采集并传送给所述控制中心,并由所述控制中心通过将所存储的预期可用的带宽值和经平滑处理过的所采集的数据中的节点的实时带宽值进行分析比对来计算各个节点的服务能力;所述代理对于CDN服务资源的服务器上的数据进行采集并传送给所述控制中心,并由所述控制中心根据与所述服务器相关联的机器数据进行综合分析以计算各个服务器的服务能力;由所述控制中心基于所述节点的服务能力和服务器的服务能力与设定的标准的比较来实时生成一个控制线。
- 如权利要求3所述的方法,其特征在于,所述代理通过自我学习调整生成针对其所控制的每个CDN服务资源的控制策略的步骤包括:所述代理根据控制中心分配给其的可控制的CDN服务资源的范围收集该范围内的各台CDN服务器的请求数、拒绝数以及当前带宽等网络数据;基于所述请求数、拒绝数以及当前带宽等网络数据采用预测算法分析计算出该台CDN服务器的真实的实际带宽;所述代理根据计算出的真实的实际带宽、历史上的下达的控制指令数据和最终控制的情况来进行自我学习调整,从而生成最终的针对其所控制的每个CDN服务资源的控制策略;其中,所述自我学习调整包括:对于控制中的任务,通过一段时间内的策略分配分析、前后控制值浮动窗口控制等进行频道分配带宽值的二次调整以保证控制的平稳性,并且通过负反馈学习以保证更好的控制的精准度。
- 如权利要求1所述的方法,其特征在于,在所述方法中的数据传输采用经改进的稳定UDP协议,所述经改进的稳定UDP协议通过充分利用CDN节点的资源优势进行路由探测,从而在数据传输时可以根据各个路由的情况智能地选择最佳传输路径以提高控制的时效性以及可靠性。
- 如权利要求1所述的方法,其特征在于,还包括:在所述代理接收到所述控制指令之后,判断所述控制指令是否在有效期内,如果所述控制指令是在有效期内,则执行所述代理生成控制策略的步骤,如果所述控制指令不在有 效期内则忽略所述控制指令。
- 如权利要求1所述的方法,其特征在于,在所述方法中,所有的数据都存在内存中而没有落地到文件,从而提高了控制的时效性。
- 一种用于CDN平台的自适应带宽控制的系统,其特征在于,包括:UI平台,通过所述UI平台配置自适应任务的相关参数并将其发送给控制中心;多个CDN服务资源,用于提供CDN服务;一个或多个用于控制所述多个CDN服务资源中的一个或多个的代理;控制中心,所述控制中心被配置为:在接收来自所述代理的任务注册之后,为所述代理分配其可控制的CDN服务资源的范围;对所述代理采集的数据进行汇总,并通过数据分析生成自适应的控制线;根据每个CDN服务资源的所采集的数据并结合所述控制线,为所述代理生成并下达控制指令;所述代理被配置为:向所述控制中心注册任务;根据所述控制中心所分配的可控制的CDN服务资源的范围向所述范围中的CDN服务资源发送数据采集命令;将采集到的数据传送给所述控制中心;以及在从所述控制中心接收到所述控制指令之后,通过自我学习调整生成针对其所控制的每个CDN服务资源的控制策略,并将所述控制策略下达给相应的CDN服务资源CDN服务资源;所述CDN服务资源被配置为:接收到所述数据采集命令之后,将实时数据返回给发送所述数据采集命令的代理。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/769,610 US10574586B2 (en) | 2015-12-29 | 2016-09-04 | Method and system for self-adaptive bandwidth control of CDN platform |
EP16880661.0A EP3382963B1 (en) | 2015-12-29 | 2016-09-04 | Method and system for self-adaptive bandwidth control for cdn platform |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511009412.2 | 2015-12-29 | ||
CN201511009412.2A CN105634992B (zh) | 2015-12-29 | 2015-12-29 | Cdn平台自适应带宽控制方法和系统 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017113868A1 true WO2017113868A1 (zh) | 2017-07-06 |
Family
ID=56049503
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2016/097987 WO2017113868A1 (zh) | 2015-12-29 | 2016-09-04 | Cdn平台自适应带宽控制方法和系统 |
Country Status (4)
Country | Link |
---|---|
US (1) | US10574586B2 (zh) |
EP (1) | EP3382963B1 (zh) |
CN (1) | CN105634992B (zh) |
WO (1) | WO2017113868A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3525400A4 (en) * | 2017-10-29 | 2019-11-27 | Wangsu Science & Technology Co., Ltd. | METHOD AND SYSTEM FOR MANAGING NETWORK SERVICES |
CN113672486A (zh) * | 2021-08-18 | 2021-11-19 | 上海哔哩哔哩科技有限公司 | 卡顿分析方法及cdn服务器 |
Families Citing this family (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105634992B (zh) * | 2015-12-29 | 2019-01-11 | 网宿科技股份有限公司 | Cdn平台自适应带宽控制方法和系统 |
CN107623580B (zh) * | 2016-07-15 | 2021-06-29 | 阿里巴巴集团控股有限公司 | 内容分发网络中的任务处理方法、装置和系统 |
CN106385455A (zh) * | 2016-09-23 | 2017-02-08 | 成都知道创宇信息技术有限公司 | 一种基于cdn镜像的整站锁设置方法 |
CN108241528B (zh) * | 2017-01-19 | 2020-10-09 | 上海直真君智科技有限公司 | 一种用户自定义海量网络安全数据动态采集方法 |
CN107124375B (zh) * | 2017-03-27 | 2020-02-18 | 网宿科技股份有限公司 | Cdn网络带宽资源的错峰调度方法、系统以及服务器 |
CN106850859A (zh) * | 2017-03-28 | 2017-06-13 | 浙江大学 | 一种基于sdn的cdn网络的用户请求分配方法 |
CN107733681B (zh) | 2017-07-28 | 2018-10-30 | 贵州白山云科技有限公司 | 一种调度方案配置方法和装置 |
US11284294B2 (en) * | 2018-01-18 | 2022-03-22 | Nec Corporation | Communication apparatus, traffic control method, non-transitory computer readable medium storing control program, and control apparatus |
CN109361622B (zh) * | 2018-11-30 | 2022-04-05 | 网宿科技股份有限公司 | 对cdn系统的业务连接进行带宽控制的方法及cdn系统 |
CN111464323A (zh) * | 2019-01-18 | 2020-07-28 | 北京沃东天骏信息技术有限公司 | 节点带宽的调度方法和调度装置 |
JP7109391B2 (ja) * | 2019-02-26 | 2022-07-29 | 株式会社日立製作所 | 不正通信検知装置および不正通信検知プログラム |
CN110221917B (zh) * | 2019-05-23 | 2023-02-28 | 创新先进技术有限公司 | 用于分配流式数据的方法及装置 |
CN110191007B (zh) * | 2019-06-27 | 2022-05-03 | 广州虎牙科技有限公司 | 节点管理方法、系统及计算机可读存储介质 |
CN111225279B (zh) * | 2020-01-06 | 2022-03-22 | 浙江云诺通信科技有限公司 | 一种基于宽带电视cdn智能调度算法 |
CN111585824B (zh) * | 2020-05-21 | 2022-10-25 | 北京奇艺世纪科技有限公司 | 资源分发方法、装置、系统及电子设备 |
CN111756646B (zh) * | 2020-07-08 | 2023-09-29 | 腾讯科技(深圳)有限公司 | 网络传输控制方法、装置、计算机设备及存储介质 |
CN112260962B (zh) * | 2020-10-16 | 2023-01-24 | 网宿科技股份有限公司 | 一种带宽控制方法及装置 |
CN114629737B (zh) * | 2020-12-14 | 2024-03-12 | 深圳Tcl新技术有限公司 | 一种带宽调整方法、装置、网关设备及存储介质 |
US11606265B2 (en) | 2021-01-29 | 2023-03-14 | World Wide Technology Holding Co., LLC | Network control in artificial intelligence-defined networking |
CN112911007A (zh) * | 2021-02-04 | 2021-06-04 | 上海七牛信息技术有限公司 | 一种pcdn资源管理系统及pcdn资源管理方法 |
CN114071569B (zh) * | 2021-11-04 | 2023-06-16 | 中国联合网络通信集团有限公司 | 一种数据传输方法、装置和电子设备 |
CN114448809A (zh) * | 2021-12-22 | 2022-05-06 | 网宿科技股份有限公司 | Cdn加速资源的规划方法、装置、设备及存储介质 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101150421A (zh) * | 2006-09-22 | 2008-03-26 | 华为技术有限公司 | 一种分布式内容分发方法、边缘服务器和内容分发网 |
CN101242432A (zh) * | 2008-02-28 | 2008-08-13 | 蓝汛网络科技(北京)有限公司 | 一种互联网内容分发方法、系统及装置 |
US20140258546A1 (en) * | 2011-10-14 | 2014-09-11 | Alcatel-Lucent | Method and apparatus for dynamically assigning resources of a distributed server infrastructure |
US20150032854A1 (en) * | 2013-07-24 | 2015-01-29 | Futurewei Technologies Inc. | System and method for network-assisted adaptive streaming |
CN104660700A (zh) * | 2015-03-03 | 2015-05-27 | 网宿科技股份有限公司 | 一种内容分发网络的方法和系统 |
CN104994123A (zh) * | 2015-05-12 | 2015-10-21 | 段利平 | 一种cdn云平台及cdn云平台的流量调度方法 |
CN105634992A (zh) * | 2015-12-29 | 2016-06-01 | 网宿科技股份有限公司 | Cdn平台自适应带宽控制方法和系统 |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2002224448A1 (en) * | 2000-10-26 | 2002-05-06 | Prismedia Networks, Inc. | Method and apparatus for large payload distribution in a network |
US20040117427A1 (en) * | 2001-03-16 | 2004-06-17 | Anystream, Inc. | System and method for distributing streaming media |
US20090163183A1 (en) * | 2007-10-04 | 2009-06-25 | O'donoghue Hugh | Recommendation generation systems, apparatus and methods |
US8069236B2 (en) * | 2008-12-12 | 2011-11-29 | At&T Intellectual Property I, L.P. | Flow control of events based on threshold, grace period, and event signature |
US9032060B2 (en) * | 2010-09-14 | 2015-05-12 | Mocana Corporation | Agent-based bandwidth monitoring for predictive network selection |
US10652087B2 (en) * | 2012-12-13 | 2020-05-12 | Level 3 Communications, Llc | Content delivery framework having fill services |
US20140226711A1 (en) * | 2013-02-13 | 2014-08-14 | Hcl Technologies Limited | System and method for self-adaptive streaming of multimedia content |
US10841353B2 (en) * | 2013-11-01 | 2020-11-17 | Ericsson Ab | System and method for optimizing defragmentation of content in a content delivery network |
US9516084B2 (en) * | 2013-11-01 | 2016-12-06 | Ericsson Ab | System and method for pre-provisioning adaptive bitrate (ABR) assets in a content delivery network |
US9712408B2 (en) * | 2014-03-17 | 2017-07-18 | Telefonaktiebolaget L M Ericsson (Publ) | Bandwidth management in a content distribution network |
US20150304187A1 (en) * | 2014-04-17 | 2015-10-22 | Invent.ly LLC | Bandwidth Management in Local Premise Networks |
US20160188821A1 (en) * | 2014-12-24 | 2016-06-30 | Larry Ozeran | System and method for aggregation and intelligent analysis of individual health data with multimodal communication |
US9774889B2 (en) * | 2015-09-10 | 2017-09-26 | Verizon Patent And Licensing Inc. | Content delivery network integration for home media client content |
-
2015
- 2015-12-29 CN CN201511009412.2A patent/CN105634992B/zh active Active
-
2016
- 2016-09-04 WO PCT/CN2016/097987 patent/WO2017113868A1/zh active Application Filing
- 2016-09-04 EP EP16880661.0A patent/EP3382963B1/en active Active
- 2016-09-04 US US15/769,610 patent/US10574586B2/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101150421A (zh) * | 2006-09-22 | 2008-03-26 | 华为技术有限公司 | 一种分布式内容分发方法、边缘服务器和内容分发网 |
CN101242432A (zh) * | 2008-02-28 | 2008-08-13 | 蓝汛网络科技(北京)有限公司 | 一种互联网内容分发方法、系统及装置 |
US20140258546A1 (en) * | 2011-10-14 | 2014-09-11 | Alcatel-Lucent | Method and apparatus for dynamically assigning resources of a distributed server infrastructure |
US20150032854A1 (en) * | 2013-07-24 | 2015-01-29 | Futurewei Technologies Inc. | System and method for network-assisted adaptive streaming |
CN104660700A (zh) * | 2015-03-03 | 2015-05-27 | 网宿科技股份有限公司 | 一种内容分发网络的方法和系统 |
CN104994123A (zh) * | 2015-05-12 | 2015-10-21 | 段利平 | 一种cdn云平台及cdn云平台的流量调度方法 |
CN105634992A (zh) * | 2015-12-29 | 2016-06-01 | 网宿科技股份有限公司 | Cdn平台自适应带宽控制方法和系统 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3382963A4 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3525400A4 (en) * | 2017-10-29 | 2019-11-27 | Wangsu Science & Technology Co., Ltd. | METHOD AND SYSTEM FOR MANAGING NETWORK SERVICES |
US10992770B2 (en) | 2017-10-29 | 2021-04-27 | Wangsu Science & Technology Co., Ltd. | Method and system for managing network service |
CN113672486A (zh) * | 2021-08-18 | 2021-11-19 | 上海哔哩哔哩科技有限公司 | 卡顿分析方法及cdn服务器 |
Also Published As
Publication number | Publication date |
---|---|
EP3382963A4 (en) | 2018-11-21 |
CN105634992B (zh) | 2019-01-11 |
CN105634992A (zh) | 2016-06-01 |
US20180316623A1 (en) | 2018-11-01 |
EP3382963A1 (en) | 2018-10-03 |
US10574586B2 (en) | 2020-02-25 |
EP3382963B1 (en) | 2020-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017113868A1 (zh) | Cdn平台自适应带宽控制方法和系统 | |
US10791168B1 (en) | Traffic aware network workload management system | |
Bhat et al. | Network assisted content distribution for adaptive bitrate video streaming | |
US7760641B2 (en) | Distributed traffic shaping across a cluster | |
US7764615B2 (en) | Distributing rate limits and tracking rate consumption across members of a cluster | |
US7813276B2 (en) | Method for distributed hierarchical admission control across a cluster | |
CN105340234B (zh) | 在电缆Wi-Fi网络上用于多屏幕视频应用的自适应资源管理 | |
Scoca et al. | Scheduling latency-sensitive applications in edge computing | |
WO2016074323A1 (zh) | 内容分发网络的http调度系统和方法 | |
CN104104973B (zh) | 一种应用于云媒体系统的群组带宽管理优化方法 | |
Petrangeli et al. | Quality of experience-centric management of adaptive video streaming services: Status and challenges | |
Farahani et al. | ES-HAS: an edge-and SDN-assisted framework for HTTP adaptive video streaming | |
CN102780610B (zh) | 网关QoS保障方法及分组交换网络系统 | |
CN101980505A (zh) | 一种基于3Tnet的视频点播的负载均衡方法 | |
Viola et al. | Predictive CDN selection for video delivery based on LSTM network performance forecasts and cost-effective trade-offs | |
CN113206796A (zh) | 一种转算存一体化协同系统及方法 | |
Farahani et al. | CSDN: CDN-aware QoE optimization in SDN-assisted HTTP adaptive video streaming | |
Ahmad et al. | Towards information-centric collaborative QoE management using SDN | |
Clayman et al. | Virtualized cache placement in an sdn/nfv assisted sand architecture | |
Sina et al. | CaR-PLive: Cloud-assisted reinforcement learning based P2P live video streaming: a hybrid approach | |
Kalan et al. | Design of a layer-based video streaming system over software-defined networks | |
Ran et al. | Dynamic resource allocation for video transcoding with QoS guaranteeing in cloud-based DASH system | |
Kalan et al. | Implementation of sand architecture using sdn | |
US11627358B2 (en) | Communication entity and a method for transmitting a video data stream | |
CN109040102A (zh) | 一种互联网直播cdn的实时传输方法及系统 |
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: 16880661 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15769610 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2016880661 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2016880661 Country of ref document: EP Effective date: 20180629 |