Title of Invention

A LAYERED CONTENT DELIVERY NETWORK AND METHOD THEREOF

Abstract

The present invention discloses a layered content delivery network comprising a content release layer, a content delivery layer with at least one level of delivery sub-layer, and an edge service layer, wherein the content release layer comprises at least one ICP node and is directly connected to the first-level delivery sub-layer in the content delivery layer, each delivery sub-layer of the content delivery layer comprises at least one delivery node and the lowest-level delivery sub-layer is directly connected to the edge service layer, the edge service layer comprises at least one edge service area; and the content to be released by the content release layer is distributed, via the delivery node of the first-level delivery sub-layer that is directly connected to the content release layer, downward level by level to the edge service layers. Meanwhile, the present invention discloses a method of layered content delivery. The present invention makes the network structure of CDN more flexible, the dispatching mode of traditional CDN optimized, the QoS of CDN improved, the distributed service as well as local balancing of service load implemented, and the access success ratio increased.

Full Text

A Layered Content Delivery Network and Method for Layered Content Delivery Field of the Technology The present invention relates to the technique of content delivery network, more particularly to a layered content delivery network and a method for layered content delivery. Background of the Invention With the rapid increase of Internet users and the increasing demand for improved Internet service quality, the traditional mode of directly providing information service by Internet Content Provider (ICP) is facing severe challenge. Usually, an ICP application site comprises physical sites established in one or a few places and provides information service for nationwide and even worldwide Internet users. This mode of Internet service makes accesses to global web sites slow and inefficient due to the structural characteristic of the Internet and such problems as bandwidth bottleneck. Information distribution is an effective method for solving these problems, i.e. establishing a totally new Content Delivery Network (CDN) based on the existing Internet, specially used to effectively transfer various multimedia contents via the Internet. With CDN, it is possible for Internet users to enjoy Internet services by accessing only nearby network sites and intelligent distribution of network data flow can be achieved. CDN has greatly increased the responding speed of network and has provided a comprehensive technical solution to such problems as narrow network bandwidth, large quantity of user access, and unbalanced distribution of network sites that have a negative impact on the effect of user access. The working principle of CDN is to transfer contents of web sites from backbone of the network to network edges close to users so as to reduce such factors as transmission delay and network jittering that affect the effect of access, thus providing orderly and high-quality services for users. As a result, it is possible for users to obtain the requested information from the closest locations at the highest speed. As this technique has greatly alleviated the congestion of Internet, web sites are able to provide more content services with large volume of data flow like video programs, music on-demand and so on. Meanwhile, reliability of various services such as online transaction and network-based banking is guaranteed effectively. To sum up, CDN is able to release content information of ICP web sites to edge devices of network beforehand such that users could get rapid responses from nearby edge devices when accessing web sites, thereby improving the quality of service for users and at the same time reducing the load of central nodes. Network structures of CDN in the prior art are all relatively simple, and the single-level structure is adopted whether it is a CDN of an enterprise scale, metropolitan scale or national scale, which is shown in figure 1. Main components of a CDN include such device as global load balancer, Center server (CS), and Edge Server (ES). The network architecture of a CDN is mainly composed of central part and edge part. The central part typically comprises devices like global load balancer and CS while the edge part typically comprises a plurality of ESs which act as edge devices to provide access information for users. Information of ICP sites is released to each ES beforehand through CS, and each user request for accessing an ICP site is dispatched by the global load balancer. As seen from the network structure of CDN shown in figure 1, although the ESs of CDN are distributed at the edge of the network, the global load balancers, which act as the dispatchers, are located at the center of the network. A typical user access dispatch procedure in the above-described CDN structure is shown in figure 2, comprising the following steps: Step 201: a user accesses a site of World Wide Web through a browser and clicks on a uniform resource locator (URL) of a content of the web site. Step 202: the browser of the user terminal requests the local Domain Name Server (DNS) to analyze the domain name of the web site. Step 203: the local DNS requests an authorized DNS of the web site to analyze the domain name of the web site. Step 204: the authorized DNS of the web site notifies the local DNS that a global load balancer acts as the authorized DNS for the sub-domain name of the web site's domain name, and returns the IP address of the global load balancer. Step 205: the local DNS sends an analysis request to the global load balancer. Step 206: the global load balancer selects an optimal ES based on a certain preset strategy, typically by polling, and returns the IP address of the selected ES to the local DNS,. Step 207: the local DNS returns the IP address of the selected ES to the browser of the user terminal. Step 208: the user accesses the selected ES according to the returned IP address and sends a content request to the selected ES. Step 209: if the selected ES does not have the content requested by the user, the selected ES will obtain the user-desired content from the CS and then step 210 will be executed; otherwise, step 210 will be executed directly. Step 210: the selected ES provides the desired content according to the request of said user. Although the access quality of the user is improved to a certain extent by adopting the above-described scheme, there are still some problems that make service quality and network utilization efficiency of CDN far from being satisfactory. For instance, first, large-scale CDN networking is difficult; second, since a unified and centralized dispatching mode is adopted, global load balancers acting as dispatchers are centralized together however wide the coverage thereof is, which leads to heavy load on and slow response from the dispatchers, and requires high parallel load capacity of the dispatchers; third, it is impossible to detect the closeness of a user according to the user's IP address and impossible to make accurate dispatching to nearby servers; fourth, in terms of releasing and managing contents, only PULL function is supported while PUSH function is not supported so that the active push capability is weak; fifth, contents are not detected when selecting an ES, which leads to a low access success ratio, moreover, as it is not detected how busy the network is, it is impossible to select a network with small data flow to provide the service. At present, there is another scheme adopting Layer 4 (L4) switch, wherein the L4 switch has the functions of the global load balancer in the above scheme. A typical user access dispatch procedure according to this scheme is shown in figure 3, comprising the following steps: Step 301: a user accesses a site of World Wide Web through a browser and clicks on a URL of a content of the web site. Step 302: the browser of the user terminal requests the local DNS to analyze the domain name of the web site. Step 303: the local DNS forwards the analysis request to a L4 switch. Step 304: the L4 switch requests the authorized DNS of the web site to analyze the domain name. Step 305: the authorized DNS of the web site obtains by analysis the IP addresses of multiple ES according to the request, and then returns these IP addresses to the L4 switch. Step 306: the L4 switch selects an optimal ES based on a certain preset strategy, typically by polling, and then returns the IP address of the selected ES to the local DNS. Step 307: the local DNS returns the IP address of the selected ES to the browser of the user terminal. Step 308: the user accesses the selected ES according to the IP address returned by the local DNS and sends a content request to the selected ES. Step 309: if the selected ES does not have the content requested by the user, the selected ES will obtain the user desired content from the CS and then step 310 will be executed; otherwise, step 310 will be executed directly. Step 310: the selected ES provides the desired content according to the request of said user. There are still some problems in the CDN adopting the L4-switch scheme, for example, the load of the L4 switch is much heavy since almost all accesses are handled by it; and the L4 switch can only make processing of the information of Layer 4 network protocol while being unable to make processing of the information of Layer 7 network protocol, i.e. unable to detect the content. As seen from the above two schemes, with the increase of users, the current widely adopted single-level CDN becomes unsuitable for an environment with large-scale and high-density applications, and unable to implement distributed services and local balancing of service load. Summary of the Invention The present invention provides a layered content delivery network as well as a method for layered content delivery so that the network structure of CDN can be more flexible and the traditional dispatching mode of CDN can be optimized, thereby improving the Quality of Service (QoS) of CDN, implementing distributed service as well as local balancing of service load, and increasing the access success ratio. The technical scheme of the present invention is implemented as follows: A layered content delivery network comprises a content release layer including at least one internet content provider(ICP) node, a content delivery layer including at least one level of delivery sub-layer, and an edge service layer; wherein the content release layer is connected to a first-level delivery sub-layer of the content delivery layer; each level of delivery sub-layer of the content delivery layer comprises at least one delivery node, and a lowest-level delivery sub-layer is connected to the edge service layer; the edge service layer includes at least one edge service area; and the content release layer releasing the content, and the content is distributed via the delivery node of the first-level delivery sub-layer, downwarding level by level to the edge service layer. Each of said ICP nodes includes at least one ICP operating terminal and at least one ICP. Each of said delivery nodes includes at least one media manager (MM) and at least one CS. Each of said edge service areas includes at least one CS, at least one MM, at least one media request broker (MRB) and at least one ES. The MRB in each edge service area is deployed in the local center of each edge service area in a distributed manner. The ICP node in the content release layer is the upper-level node of the delivery node'in the delivery sub-layer that is directly connected to the content release layer, and the edge service area in the edge service layer is the lower-level node of the delivery node in the lowest-level delivery sub-layer that is directly connected to the edge service layer. A method for layered delivery by CDN comprises the following steps: a. an ICP node distributes the content to be released to at least one delivery node of a content delivery layer that is directly connected to the ICP node; b. the delivery node receives a content delivery command for determines whether it is a delivery node of the lowest-level delivery sub-layer, if yes, executes the step of c; otherwise, reads the content to be released from an upper-level node that is directly connected to the delivery node receiving the content delivery command, stores the content in a CS of the delivery node, distributes the content to one or more than one lower-level delivery node that is directly connected to the delivery node that receives the content delivery command, and repeating the step of determining whether it is a delivery node of the lowest-level delivery sub-layer; c. according to the received content delivery command, the delivery node receives the content to be released from the upper-level delivery node that is directly connected to the delivery node, stores the content in a CS of the delivery node, distributes the content to one or more than one edge service area that is directly connected to the delivery node. The step of a further comprises: dispatches a user access to ICP by an MRB in the edge service area where the user is located, and provides the user desired service by a CS or an ES in the edge service area where the user is located. The step of dispatching a user access to ICP at least comprises: analyzes the domain name of the ICP accessed by the user, detects the ESs in the edge service area or selects an optimal ES. The step of detecting ESs comprises at least: detects how close to the user the ESs are, whether there is the user desired content, or whether the network is busy or idle. The step of selecting an optimal ES comprises: determines the optimal ES according to how close the ESs are to the user, whether there is the user required content in the ESs, or whether the network is busy or idle. Compared with the technique in the prior art, the present invention makes it possible to construct networks of various scales, including metropolitan area networks, province-level networks or nationwide networks. Meanwhile step-by-step expansion of a network is also supported by the invention, for example, a metropolitan area network can be expanded to a network of province-level and even to a nationwide network with more flexible networking architecture of CDN. In the present invention, the traditional dispatching mode in CDN is optimized, that is, distributed dispatching is adopted so that the service areas of MRB is made smaller, the load is reduced and response time shortened, thereby improving the service quality of CDN. As layered and leveled content delivery management is adopted in the present invention, it is guaranteed that ICP can implement network-wide release and network-wide service for one-point accesses so that distributed services and local balancing of service load could be achieved. Meanwhile, in accordance with the present invention, user accesses are dispatched based on how busy the ESs are and how close to the ESs the user is so that ESs that are relatively idle could be selected to provide services to improve the service quality. Furthermore, as user accesses can be dispatched based on content, the access success ratio is raised. Brief Description of the Drawings Figure 1 is a schematic diagram illustrating the network structure of the schemes in the prior art; Figure 2 is a flowchart illustrating the user access dispatch procedure of scheme 1 in the prior art; Figure 3 is a flowchart illustrating the user access dispatch procedure of scheme 2 in the prior art; Figure 4 is a schematic diagram illustrating network structure of an embodiment of the present invention; Figure 5 is a flowchart illustrating the content release procedure of an embodiment of the present invention; Figure 6 is a flowchart illustrating the user access dispatch procedure of an embodiment of the present invention. Detailed Description of the Invention To make the object, technical scheme and advantages of the present invention clearer, the present invention will be described in detail hereinafter with reference to the accompanying drawings and specific embodiments. The key of the embodiment of the present invention is to construct a network capable of distributed dispatch and layered delivery; dispatchers are not located in the network center but distributed at local center of each service area in charge of dispatching accesses in the local area; management of content delivery is conducted in a layered and leveled mode, thus ensuring that ICP can implement network-wide release and network-wide service for one-point accesses. The layered CDN of the embodiment of the present invention comprises a content release layer, a content delivery layer with at least one level of delivery sub-layer and an edge service layer. Suppose that the content delivery layer comprises two levels of delivery sub-layer, as shown in figure 4, the CDN comprises such major device as ICP, ICP operating terminal, CS, Media Managers (MM), Media Request Brokers (MRB), and ES. MM is in charge of processing signaling, and the main function of MM is to receive the release commands concerning content release sent by the ICP operating terminal, send content delivery commands to ES or MM of the lower level or CS of each level according to the release commands, and receive the feedback information from ES or MM of lower level or CS of each level. CS of each level is in charge of storing and distributing the content of the center as well as providing services. MRB in each edge service area of the edge service layer is distributed at the local center of the edge service area, mainly in charge of dispatching accesses within the network of the local area and implementing load balancing. The solid line in figure 4 denotes the content release and delivery procedure while the dotted line denotes the content release commands. The above-described components of CDN can be assembled into ICP nodes, delivery nodes and edge service areas. Each ICP node at least comprises one ICP operating terminal and one or more than one ICP Each delivery node at least comprises one MM and one CS. Each edge service area at least comprises one CS, one MM, one MRB and one or more than one ES. The content release layer comprises one or more than one ICP nodes. The content delivery layer comprises one or more delivery sub-layers, and each delivery sub-layer comprises at least one delivery node. The edge service layer comprises one or more edge service areas. The content release layer is directly connected to the content delivery layer, and the content delivery layer is directly connected to the edge service layer, and the content to be released by the content release layer is distributed to the edge service layer through the content delivery layer. The delivery sub-layer and the delivery nodes of the delivery sub-layer in the above-noted content delivery layer can be divided into different levels according to the connecting way: the delivery nodes directly connected to the content release layer act as the first-level delivery nodes; the set of all the first-level delivery nodes is called the first-level delivery sub-layer; the ICP nodes in the content release layer are the upper-level nodes of the first-level delivery nodes directly connected to the ICP nodes; the delivery nodes directly connected to the first-level delivery nodes and of the same role as the first-level delivery nodes are called the second-level delivery nodes; the set of all the second-level delivery nodes is called the second-level delivery sub-layer; the first-level delivery nodes are the upper-level nodes of the second-level nodes directly connected to the first-level delivery nodes; and the rest may be deduced by analogy The edge service areas of the edge service layer are directly connected to the lowest-level delivery nodes; the set of all the lowest-level delivery nodes is called the lowest-level delivery sub-layer; the lowest-level delivery nodes are the upper-level nodes of the edge service areas directly connected to the lowest-level delivery nodes. There is at least one level of delivery node in the content delivery layer. The content to be released by the content release layer is first distributed to one or more first-level delivery nodes directly connected to the content release layer, said first-level delivery nodes distribute the content to be released to one or more second-level delivery nodes directly connected to the first-level delivery nodes, and then said second-level delivery nodes distribute the content to be released to one or more third-level delivery nodes directly connected to the second-level delivery nodes; and the rest may be deduced by analogy, until the content is distributed downwards level by level to the edge service layer, thus implementing the layered delivery of the content. Based on the network structure of CDN shown in figure 4, a typical content release procedure is shown in figure 5, comprising the following steps: Step 501: the ICP operating terminal of a certain ICP node in the content release layer sends a content release command to the MM of one or more first-level delivery nodes directly connected to the content release layer. Step 502: according to the received content release command, the MM of said first-level delivery node sends a content release command to the CS of the delivery node where the MM is located. Step 503: according to the received content release command, the CS of said first-level delivery node reads the content to be released by the ICP from the ICP content storage equipment of the ICP node, and stores the content in itself. Step 504: the CS of the first-level delivery node notifies the MM of the delivery node where the CS is located that the content to be released by the ICP node is already stored in the CS of the first-level delivery node. Step 505: the MM of the first-level delivery node sends a content delivery command to the MM of the second-level delivery node directly connected to the first-level delivery node. Step 506: according to the received content delivery command, the MM of the second-level delivery node sends a content delivery command to the CS of the delivery node where the MM is located. Step 507: according to the received content delivery command, the CS of the second-level delivery node reads the content to be released from the upper-level CS, namely the CS in the first-level delivery node, and stores the content in itself. Step 508: the CS of the second-level delivery node notifies the MM of the delivery node where the CS is located that the content to be released is already stored in the CS of the second-level delivery node. Step 509: the MM of the second-level delivery node sends a content release command to the MM of the edge service area directly connected to the delivery node. Step 510: according to the received content release command, the MM of said edge service area sends a content release command to the CS of the edge service area. Step 511: according to the received content release command, the CS of said edge service area reads the content to be released from the upper-level CS, namely CS of the second-level delivery node, and stores the content in the local CS, namely CS of said edge service area. Step 512: the CS of said edge service area notifies the MM of the node where the CS is located that the content to be released is already stored in CS of said edge service area. Step 513: the MM of said edge service area sends a content delivery command to the ES of said edge service area. Step 514: according to the received content delivery command, the ES of said edge service area reads the content to be released from the CS of the edge service area where the ES is located, and stores the content in itself. After the above content release procedure, the content to be released by ICP is pushed to network edge beforehand through the above layered CDN, namely to the ES in the edge network. The above-described content release procedure is not only applicable to a province-level CDN, but also applicable to a metropolitan CDN and a nationwide CDN. Based on the network structure of the CDN in accordance with the embodiment of the present invention, a typical user access dispatch procedure, as shown in figure 6, comprises the following steps: Step 601: a user accesses a site of World Wide Web and clicks on a URL of a content thereof. Step 602: the browser of the user terminal requests the local DNS to analyze the domain name of the web site. Step 603: the local DNS requests an authorized DNS of the web site to analyze the domain name of the web site. Step 604: the authorized DNS of the web site notifies the local DNS that the authorized DNS of the corresponding content of the web site is the locally deployed MRB, and returns the IP address of the MRB. Step 605: the local DNS returns the IP address of the MRB to the browser. Step 606: the browser of the user terminal accesses the MRB. Step 607: the MRB detects all ESs in the local group area, selects an optimal ES according to how close the ES is or whether there is the content in the ES, and returns the IP address of the selected ES to the browser. Step 608: the user accesses the selected ES and sends a content request to the selected ES. Step 609: if the selected ES does not have the user desired content, the selected ES will obtain the content from the local CS before executing step 610; otherwise, execute step 610 directly. Step 610: the selected ES provides the user desired content according to said request of the user. As seen from the above procedure, after the analysis by DNS, accesses of local users are dispatched by local MRB and services are provided by local ES, which embodies the idea of implementing services in a distributed mode. As distributed dispatch and layered delivery are adopted by the embodiment of the present invention to construct a network, compared with traditional CDN, the embodiment of the present invention has the advantage of supporting layered and leveled network construction, by which both small-scale CDN and large-scale CDN can be constructed. As content delivery management in the embodiment of the present invention is also conducted in a layered and leveled mode, ICP can implement network-wide release and provide network-wide service for one-point accesses. Since service areas are divided in the embodiment of the present invention and distributed dispatch is implemented locally in each edge service area, the load of MRB is effectively reduced and the status of the network is efficiently detected. Though the above described embodiment is illustrated by the example of a content delivery layer comprising two levels of delivery sub-layer, the embodiment of the present invention is also applicable to the network structure with the content delivery layer comprising one or more levels of delivery sub-layer. The above description is only a preferable embodiment of the present invention, not to be construed as limiting the protection scope of the present invention. Claims 1. A layered content delivery network (CDN), comprising a content release layer including at least one internet content provider(ICP) node, a content delivery layer including at least one level of delivery sub-layer, and an edge service layer; wherein the content release layer is connected to a first-level delivery sub-layer of the content delivery layer; each level of delivery sub-layer of the content delivery layer comprises at least one delivery node, and a lowest-level delivery sub-layer is connected to the edge service layer; the edge service layer includes at least one edge service area; and the content release layer releasing the content, and the content is distributed via the delivery node of the first-level delivery sub-layer, downwarding level by level to the edge service layer. 2. The content delivery network according to Claim 1, wherein each of said ICP nodes includes at least one ICP operating terminal and at least one ICP. 3. The content delivery network according to Claim 1, wherein each of said delivery nodes includes at least one media manager (MM) and at least one center server (CS). 4. The content delivery network according to Claim 1, wherein each of said edge service areas includes at least one CS, at least one MM, at least one media request broker (MRB) and at least one edge server (ES). 5. The content delivery network according to Claim 4, wherein the MRB in each edge service area is deployed in the local center of each edge service area in distributed manner. 6. The content delivery network according to Claim 1, wherein the ICP node in the content release layer is the upper-level node of the delivery node in the first-level delivery sub-layer that is directly connected to the content release layer, and the edge service area in the edge service layer is the lower-level node of the delivery node in the lowest-level delivery sub-layer that is directly connected to the edge service layer. 7. A method for layered content delivery by a content delivery network, a. an ICP node distributing the content to be released to at least one delivery node in a content delivery layer, wherein the content delivery layer is connected to the ICP node; b. the delivery node receiving a content delivery command for determining whether the delivery node is a delivery node of the lowest-level delivery sub-layer, if yes, executing the step of c; otherwise, reading the content to be released from an upper-level node that is directly connected to the delivery node receiving the content delivery command, storing the content in a CS of the delivery node, distributing the content to one or more than one lower-level delivery node that is_directly connected to the delivery node that receives the content delivery command, and repeating the step of determining whether it is a delivery node of the lowest-level delivery sub-layer; c. according to the received content delivery command, the delivery node receiving the content to be released from the upper-level delivery node that is directly connected to the delivery node, storing the content in a CS of the delivery node, distributing the content to one or more than one edge service area that is directly connected to the delivery node. 8. The method according to Claim 7, wherein the step of a comprising dispatching a user access to ICP by an MRB within the edge service area where the user is located, and providing the user desired service by a CS or an ES within the edge service area where the user is located. 9. The method according to Claim 8, wherein the step of dispatching a user access comprises at least one procedure of analyzing the domain name of the ICP accessed by the user, detecting the ESs within the edge service area and selecting an optimal ES. 10. The method according to Claim 9, wherein the step of detecting the ESs comprising: at least one step of detecting how close the ESs are to the user, whether there is the user desired content in the ESs, and whether the network is busy or idle. 11. The method according to Claim 9, wherein the step of selecting an optimal ES

Documents:

1051-chenp-2006 complete specification as granted.pdf

1051-chenp-2006- abstract.jpg

1051-chenp-2006-abstract.pdf

1051-chenp-2006-claims.pdf

1051-chenp-2006-correspondnece-others.pdf

1051-chenp-2006-description(complete).pdf

1051-chenp-2006-drawings.pdf

1051-chenp-2006-form 1.pdf

1051-chenp-2006-form 3.pdf

1051-chenp-2006-form 5.pdf

1051-chenp-2006-pct.pdf