WO2017113373A1 - 一种缓存的方法及分组数据网关 - Google Patents

一种缓存的方法及分组数据网关 Download PDF

Info

Publication number
WO2017113373A1
WO2017113373A1 PCT/CN2015/100290 CN2015100290W WO2017113373A1 WO 2017113373 A1 WO2017113373 A1 WO 2017113373A1 CN 2015100290 W CN2015100290 W CN 2015100290W WO 2017113373 A1 WO2017113373 A1 WO 2017113373A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
base station
pgw
stored
storage
Prior art date
Application number
PCT/CN2015/100290
Other languages
English (en)
French (fr)
Inventor
吴问付
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2015/100290 priority Critical patent/WO2017113373A1/zh
Publication of WO2017113373A1 publication Critical patent/WO2017113373A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W28/00Network traffic management; Network resource management
    • H04W28/02Traffic management, e.g. flow control or congestion control
    • H04W28/06Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information

Definitions

  • the present invention relates to the field of communications technologies, and in particular, to a method for buffering and a packet data gateway.
  • a CDN network data is backed up to multiple cache servers, and user requests can be responded to at the nearest cache server. In this way, the user's request and the data requested by the user can no longer pass through the central network area, thereby greatly alleviating the pressure on the central network.
  • this technology is not enough to meet the user's requirements for the video viewing experience.
  • the video data requested by the user is obtained from the CDN cache server, it still needs to go through the core network (Core Network, CN) and then pass the wireless.
  • Core Network, CN Core Network
  • CN Core Network
  • RAN Radio Access Network
  • a multi-level cache system is applied to the mobile network.
  • PGW Packet Data Network Gateway
  • adding a cache device to the mobile base station can further reduce the user's access delay and reduce the consumption of the CN network wireless backhaul bandwidth.
  • the CDN cache, the PGW cache, and the base station cache together constitute a three-level cache system for mobile video. Each cache node selects the content to store based on the frequency of clicks on the video in its service area.
  • the technical problem to be solved by the embodiments of the present invention is to provide a method for buffering and a packet data gateway. To solve the problem of high cache redundancy.
  • an embodiment of the present invention provides a method for caching, including:
  • packet data gateway PGW updating the base station j of the i-demand video frequency f ij of the buffer unit comprises at least the cooperating base station and the j PGW;
  • the PGW calculates a storage income P ij of the video i on the base station j according to the on-demand frequency f ij and the source of the video i obtained by the base station j;
  • the PGW instructs the base station j to update the stored video
  • the storage revenue is used to characterize the saving of the user access delay by the cache node storing the video.
  • the PGW may calculate the storage revenue of the video on the base station according to the on-demand frequency of the video on the base station, and the source of the video obtained by the base station, and then the video is The storage revenue is compared with the storage revenue of the stored video of the base station, and finally, according to the comparison result, the PGW indicates whether the base station performs the update of the stored video. It is ensured that the video buffered on the base station is a video with higher storage revenue, and since the calculation of the storage revenue needs to be determined according to the source of the video obtained by the base station, it can be ensured between the base station and other base stations in the cache cooperation unit and the PGW.
  • the cache redundancy is low, thereby improving the utilization of the multi-level cache system, and the calculation is simple and convenient, the result is accurate, and the complexity of the multi-level cache system management is reduced.
  • the base station j updates the stored video according to the indication of the PGW, or
  • the PGW updates the on-demand frequency f i of its own video i ;
  • the PGW calculates a storage income P i of the video i on the PGW according to the on-demand frequency f i and the storage condition of the video i in each base station in the cache coordinating unit;
  • the PGW updates the stored video if the stored revenue P i is greater than or equal to the stored revenue of the stored video on the PGW.
  • the video stored on the PGW is a video with higher storage revenue, thereby improving the utilization of the PGW storage space, and the determination of the storage revenue needs to be based on all the cache cooperation units.
  • the video storage situation of the base station is determined, thereby improving the validity and accuracy of the storage revenue calculation, further improving the space utilization rate of the multi-level cache system, and the calculation is simple and convenient, the result is accurate, and the complexity of the multi-level cache system management is reduced.
  • the PGW acquires the video i according to the on-demand frequency f ij and the base station j
  • the source calculates the storage revenue P ij of the video i on the base station j, including:
  • the PGW calculates the storage revenue P ij according to the on-demand frequency f ij and the access delay of the base station j to the PGW;
  • the base station j acquires the source of the video i as other base stations in the cache coordinating unit, the PGW according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the video Calculating the stored benefit P ij by the access delay of the base station to the PGW; or
  • the PGW is based on the on-demand frequency f ij , the access delay of the base station j to the PGW, and the PGW to the content distribution network.
  • the access delay calculates the stored benefit P ij .
  • the PGW calculates the storage revenue P i of the video i on the PGW, including:
  • the PGW calculates the storage income P i according to the on-demand frequency f i and the access delay of the PGW to the content distribution network, the on-demand The frequency P i is the sum of the on-demand frequencies of the respective base stations; or
  • the PGW according to the on-demand frequency f i and the respective access to the base station calculates the delay memory PGW gains P i, F i is the frequency of the demand is not within said cache memory cooperating means on-demand frequencies of the base station i, and video.
  • an embodiment of the present invention provides a packet data gateway, including:
  • An update unit configured to update an on-demand frequency f ij of the video i on the base station j if the base station j in the cache cooperating unit receives a user request for the on-demand video i, the cache cooperating unit at least including the base station j and The packet data gateway PGW;
  • a calculating unit configured to calculate, according to the on-demand frequency f ij and the source of the video i by the base station j, a storage income P ij of the video i on the base station j;
  • An indicating unit configured to instruct the base station j to update the stored video if the storage revenue P ij is greater than or equal to a storage income of the stored video on the base station j;
  • the storage revenue is used to characterize the saving of the user access delay by the cache node storing the video.
  • the updating unit is further configured to: after the base station j updates the stored video according to the indication of the indication unit, or
  • the calculating unit is further configured to calculate a storage income P i of the video i on the PGW according to the on-demand frequency f i and a storage situation of each base station in the cache cooperating unit;
  • the updating unit is further configured to update the video stored by the PGW if the storage revenue P i is greater than or equal to a storage income of the stored video on the PGW.
  • the calculating unit is specifically configured to:
  • the storage income P ij is calculated according to the on-demand frequency f ij and the access delay of the base station j to the PGW;
  • the base station j acquires the source of the video i as another base station in the cache coordinating unit, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the base station where the video i is located Calculating the stored benefit P ij by the access delay to the PGW; or
  • the base station j acquires the source of the video i as a content distribution network, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the access delay of the PGW to the content distribution network.
  • the stored revenue P ij is calculated.
  • the third possible implementation in the second aspect is specifically configured to:
  • the storage revenue P i is calculated according to the on-demand frequency f i and the access delay of the PGW to the content distribution network, and the on-demand frequency P i The sum of the on-demand frequencies of the respective base stations; or
  • At least one base station in the cache cooperating unit stores the video i, and the access delays of the respective base stations in the cache cooperating unit to the PGW are the same, according to the on-demand frequency f i and the respective base stations to the accessing said memory of said computing PGW delay return P i, F i is the frequency of the demand on demand without storing the frequency of the base station i and a video buffer in said cooperating means.
  • an embodiment of the present invention provides a packet data gateway, including:
  • processor configured to invoke program code stored in the memory, and perform the following operations:
  • the cache cooperating unit includes at least the base station j and the PGW;
  • the base station j is instructed by the interface circuit to update the stored video
  • the storage revenue is used to characterize the saving of the user access delay by the cache node storing the video.
  • the processor is further configured to: after the base station j updates the stored video according to the indication of the processor, or
  • the stored video is updated.
  • the processor is specifically configured to:
  • the storage income P ij is calculated according to the on-demand frequency f ij and the access delay of the base station j to the PGW;
  • the base station j acquires the source of the video i as another base station in the cache coordinating unit, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the base station where the video i is located Calculating the stored benefit P ij by the access delay to the PGW; or
  • the base station j acquires the source of the video i as a content distribution network, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the access delay of the PGW to the content distribution network.
  • the stored revenue P ij is calculated.
  • the processor is specifically configured to:
  • the storage revenue P i is calculated according to the on-demand frequency f i and the access delay of the PGW to the content distribution network, and the on-demand frequency P i The sum of the on-demand frequencies of the respective base stations; or
  • At least one base station in the cache cooperating unit stores the video i, and the access delays of the respective base stations in the cache cooperating unit to the PGW are the same, according to the on-demand frequency f i and the respective base stations to the accessing said memory of said computing PGW delay return P i, F i is the frequency of the demand on demand without storing the frequency of the base station i and a video buffer in said cooperating means.
  • an embodiment of the present invention provides a computer storage medium, the computer storage medium comprising a set of program code, for performing the method according to any implementation manner of the first aspect of the embodiment of the present invention.
  • FIG. 1 is a schematic diagram of an architecture and an access delay of a multi-level cache system according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method for buffering according to an embodiment of the present invention
  • FIG. 3 is a schematic flowchart of a method for buffering according to an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of a packet data gateway according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of another packet data gateway according to an embodiment of the present invention.
  • CDN Content Delivery Network
  • the basic idea of CDN is to avoid the possibility of data transmission speed and stability on the Internet. The bottlenecks and links make the content transfer faster and more stable.
  • the CDN system can real-time based on network traffic and connection, load status, and distance and response time to users.
  • the integrated information redirects the user's request to the service node closest to the user. The goal is to enable users to get the content they need, solve the problem of network congestion, and improve the response speed of users visiting the website.
  • PGW is an important network element in the mobile communication network, and is a border gateway of the core network, providing functions such as session management and bearer control, data forwarding, IP address allocation, and non-3GPP user access.
  • the base station is a Radio Access Network (RAN) device, which is used to connect the terminal to the core network, including but not limited to: an evolved NodeB (eNodeB), and a wireless network control.
  • Radio Network Controller RNC
  • 3G base station NodeB
  • BSC Base Station Controller
  • BTS Base Transceiver Station
  • HNB Home NodeB
  • BBU Base Band Unit
  • a terminal also known as a User Equipment (UE)
  • UE User Equipment
  • a terminal is a device that provides voice and/or data connectivity to a user, for example, a handheld device with wireless connectivity, an in-vehicle device, and a connection to Other processing devices for wireless modems, etc.
  • the above base station, PGW, and CDN all have their own cache unit to store data, and the multi-level cache system in the embodiment of the present invention is composed of the base station, the PGW, and the CDN three types of cache nodes.
  • the following base station j is the sequence number or number of the base station, and is used to identify the base station to distinguish it from other base stations; similarly, i in the video i is the serial number or number of the video, and is used to identify the video to distinguish it from other videos.
  • the on-demand frequency, storage revenue and access delay of the video will also be involved. among them:
  • the on-demand frequency is used to characterize the number of times the video is broadcasted per unit time.
  • Storage revenue used to characterize the savings that cache nodes store video to user access latency.
  • the access delay is used to characterize the time interval from the user request to the time the user receives the video.
  • the UE-to-base station access delay is t 0
  • multiple base stations and PGWs form a cache coordinating unit.
  • each base station to PGW access delay is t 1
  • PGW to CDN is assumed that each base station to PGW access delay.
  • the access delay is t 2 .
  • FIG. 2 is a schematic flowchart diagram of a method for buffering according to an embodiment of the present invention.
  • the cache cooperating unit includes a base station j, a PGW, and at least one other of the methods:
  • the packet data gateway PGW updates the on-demand frequency f ij of the video i on the base station j.
  • the cache cooperating unit includes at least the base station j and the PGW.
  • the PGW calculates a storage income P ij of the video i on the base station j according to the on-demand frequency f ij and the source of the video i obtained by the base station j.
  • step S201 after the base station j receives the user request for the video i, if the base station j stores the video i, the video i is directly transmitted to the UE, and if the base station j does not store the video i, the base station j puts the user The request is forwarded to the PGW, and then the PGW searches for the video i according to the order of the PGW cache-other base station buffer-CDN buffer, and then sends it to the base station j.
  • the base station j After receiving the video i, the base station j can send the video to the UE, and at the same time, based on this On-demand of the secondary video i, the PGW updates the on-demand frequency f ij of the video i on the base station j. For example, if the base station j never receives an on-demand request for video i in a unit time, its previous on-demand frequency is 0, and after the on-demand is increased by 1, the on-demand frequency is updated to 1; if the base station j receives in unit time When the on-demand request to video i is 5 times, the previous on-demand frequency is 5, and after adding 1 by this on-demand, the on-demand frequency after the update is 6.
  • the device manufacturer can set or configure some optional options at the factory for the operator to select or directly customize by the operator, which is not limited in the embodiment of the present invention.
  • the PGW may calculate the stored revenue P ij of the video on the base station j based on the on-demand frequency f ij and the base station j acquiring the source of the video i.
  • the storage revenue of video on one base station is affected by the storage contents of other base stations and PGW buffers.
  • the storage revenue of a video on a base station represents the difference in the user access delay between storing the video on the base station and not storing the video.
  • t' ij represents the access delay of the user when the video i is not stored on the base station j
  • t ij represents the access delay of the user when the video i is stored on the base station j.
  • the PGW calculates the storage revenue P according to the on-demand frequency f ij and the access delay of the base station j to the PGW. Ij ;
  • the base station j acquires the source of the video i as other base stations in the cache coordinating unit, the PGW according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the video Calculating the stored income P ij by the access delay of the base station to the PGW;
  • the PGW is based on the on-demand frequency f ij , the access delay of the base station j to the PGW, and the PGW to the content distribution network.
  • the access delay calculates the stored benefit P ij .
  • t ij t 0 .
  • the video storage revenue of the base station j is determined by the video on-demand frequency of the base station j, the PGW, and the video storage conditions of other base stations. If there are no other base stations in the buffer cooperating unit, the video storage revenue of the base station j is determined by the video on-demand frequency of the base station j and the video storage condition of the PGW.
  • step S203 may be performed.
  • the PGW may compare the storage income of the video i with the storage income of the stored video of the base station j, generally The base station j will store a batch of videos with large storage revenue according to its own storage capacity. Therefore, if the storage income of the video i is greater than or equal to the storage income of the stored video, the PGW will send an update instruction to indicate the base station j to store. The video is updated. In the update, it can delete the video with lower storage revenue in the stored video and add the video i. Of course, if the storage capacity allows, you can also delete the stored video and directly add the video i to the cache. in. When the storage revenue of video i is less than the storage revenue of the stored video, no update is needed.
  • the PGW can calculate the storage revenue of the video on the base station according to the on-demand frequency of the video on the base station, and the source of the video obtained by the base station, and then The storage revenue of the video is compared with the stored revenue of the stored video of the base station, and finally, according to the comparison result, the PGW indicates whether the base station performs the update of the stored video.
  • the base station obtains the source determining of the video, so that the cache redundancy between the base station and other base stations and the PGW in the cache cooperating unit can be ensured, thereby improving the utilization of the multi-level caching system, and the calculation is simple and convenient.
  • the result is accurate and reduces the complexity of multi-level cache system management.
  • FIG. 3 is a schematic flowchart of another method for buffering according to an embodiment of the present invention.
  • steps S301-S303 are the same as steps S201-S203 in the previous embodiment, and are no longer
  • the method further includes the following steps:
  • the PGW calculates a storage income P i of the video i on the PGW according to the on-demand frequency f i and the storage condition of the video i in each base station in the cache coordinating unit.
  • the on-demand frequency f i of the video i of the PGW itself is determined by the on-demand frequency and storage condition of the video i on all base stations included in the buffer cooperating unit. Therefore, the storage revenue P i of the video i on the PGW is also related to the on-demand frequency and storage of the video i on all base stations included in the buffer cooperating unit.
  • the PGW calculates the storage revenue P i according to the on-demand frequency f i and the access delay of the PGW to the content distribution network.
  • P i is the frequency of the demand on demand and the frequency of each base station;
  • the PGW according to the on-demand frequency f i and the respective access to the base station calculates the delay memory PGW gains P i, F i is the frequency of the demand is not within said cache memory cooperating means on-demand frequencies of the base station i, and video.
  • the storage revenue of the video on the PGW cache is affected by the storage state of all base stations.
  • the role of the PGW in the multi-level cache system is to act as a cache server for the base station, so the PGW should aim to provide the best service to the base station.
  • the calculation of video storage revenue on the PGW is divided into two cases.
  • P i represents the revenue of storing video i on the PGW
  • k ij ⁇ ⁇ 0, 1 ⁇ indicates whether the base station j stores the video i for description:
  • the PGW does not store the video i, then all base stations need to acquire video data from the CDN.
  • the storage revenue of storage video i is:
  • At least one base station stores video i
  • the access delay of the user accessing the video on the base station storing the video i is t 0
  • the base station not storing the video i can transit from the PGW to the base station storing the video i.
  • this delay is t 0 +2*t 1 .
  • the access delay of the user accessing the video on the base station where the video i is stored is still t 0
  • the base station without the video i can directly acquire the video data from the PGW.
  • the access delay is t 0 + t 1 . So in this case the storage revenue of the PGW storage video i is:
  • the storage revenue of the stored video i on the PGW is:
  • the storage revenue of the video on the PGW is determined by the on-demand frequency and video storage of the video on all base stations. If there are no other base stations in the cache cooperating unit, the video storage revenue of the PGW is determined only by the video on demand frequency and video storage condition of the base station j.
  • step S306 may be performed.
  • the PGW may compare the storage income of the video i with the stored revenue of the stored video.
  • the PGW Will store one according to the storage capacity of its corresponding cache unit
  • the batch stores a video with a large revenue. Therefore, if the storage income of the video i is greater than or equal to the storage revenue of the stored video, the PGW updates the stored video, specifically, when the update is performed, the storage in the stored video may be deleted.
  • Video with lower yields and video i added of course, if the storage capacity allows, you can also delete the stored video and add video i directly to the cache.
  • no update is needed.
  • the storage revenue of the video on the PGW is further calculated, so that the video stored on the PGW can be used as a video with higher storage revenue, thereby improving the utilization of the PGW storage space, and the determination of the storage revenue needs to be determined according to
  • the video storage status of all base stations in the cache coordinating unit is determined, thereby improving the validity and accuracy of the storage revenue calculation, further improving the space utilization rate of the multi-level cache system, and the calculation is simple and convenient, the result is accurate, and the multi-level cache system is reduced.
  • the embodiment of the present invention only describes a process of processing a video buffer by a cache cooperating unit under a CDN.
  • multiple cache cooperating units may further be further processed.
  • the storage revenue can refer to the calculation method described in the embodiment of the present invention.
  • the selection may be performed according to factors such as a data transmission speed, an access delay, and the like, which are not limited in the embodiment of the present invention.
  • the storage revenue calculation of the base station side in the cache decision process is determined based on the video storage condition of the PGW, and after the base station cache decision is completed, the PGW performs the cache decision, and the PGW is at this time.
  • the video storage situation may have changed, so the base station calculates the storage revenue based on the original video storage situation of the PGW and performs video update. It is also conceivable to perform the migration of the PGW new video data between the base station and the PGW, that is, to transmit the newly stored video of the PGW to the base station to further optimize the storage result on the base station side.
  • the packet data gateway includes:
  • the updating unit 100 is configured to update the on-demand frequency f ij of the video i on the base station j if the base station j in the buffer cooperating unit receives the user request of the on-demand video i, and the cache cooperating unit includes at least the base station j And the packet data gateway PGW;
  • the calculating unit 200 is configured to calculate a storage income P ij of the video i on the base station j according to the on-demand frequency f ij and the source of the video i obtained by the base station j;
  • the indicating unit 300 is configured to, if the storage revenue P ij is greater than or equal to the storage revenue of the stored video on the base station j, instruct the base station j to update the stored video;
  • the storage revenue is used to characterize the saving of the user access delay by the cache node storing the video.
  • the updating unit 100 is further configured to: after the base station j updates the stored video according to the indication of the indication unit, or
  • the calculating unit 200 is further configured to calculate a storage income P i of the video i on the PGW according to the on-demand frequency f i and a storage situation of each base station in the cache cooperating unit;
  • the updating unit 100 is further configured to update the video stored by the PGW if the storage revenue P i is greater than or equal to a storage income of the stored video on the PGW.
  • the calculating unit 200 is specifically configured to:
  • the storage income P ij is calculated according to the on-demand frequency f ij and the access delay of the base station j to the PGW;
  • the base station j acquires the source of the video i as another base station in the cache coordinating unit, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the base station where the video i is located Calculating the stored benefit P ij by the access delay to the PGW; or
  • the base station j acquires the source of the video i as a content distribution network, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the access delay of the PGW to the content distribution network.
  • the stored revenue P ij is calculated.
  • the computing unit 200 When calculating the video storage revenue on the PGW, the computing unit 200 is specifically configured to:
  • the storage revenue P i is calculated according to the on-demand frequency f i and the access delay of the PGW to the content distribution network, and the on-demand frequency P i The sum of the on-demand frequencies of the respective base stations; or
  • At least one base station in the cache cooperating unit stores the video i, and the access delays of the respective base stations in the cache cooperating unit to the PGW are the same, according to the on-demand frequency f i and the respective base stations to the accessing said memory of said computing PGW delay return P i, F i is the frequency of the demand on demand without storing the frequency of the base station i and a video buffer in said cooperating means.
  • the base station includes, but is not limited to, an evolved Node B, a Node B, a base station controller, a base transceiver station, a home base station, a baseband unit, and the like.
  • the indication unit 300 in this embodiment may be an interface circuit of the PGW, and the interface circuit may be connected to the radio frequency transceiver part of the base station for implementing communication with the base station.
  • the computing unit 200 may be a separately set processor, or may be implemented in one processor of the PGW, or may be stored in the memory of the PGW in the form of program code, and is called and executed by a processor of the PGW. The function of the above calculation unit 200.
  • the implementation of the update unit 100 is the same as that of the computing unit 200, and may be integrated with the computing unit 200, or may be implemented independently.
  • the processor described herein may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated systems configured to implement embodiments of the present invention. Circuit.
  • the packet data gateway includes:
  • the processor 1101, the interface circuit 1102, the memory 1103, and the bus 1104, the processor 1101, the interface circuit 1102, and the memory 1103 are connected by the bus 1104 and complete communication with each other, wherein the memory 1103 is used to store video data. And for storing a set of program code, the processor 1101 is configured to invoke the program code stored in the memory 1103, and perform the following operations:
  • the cache cooperating unit includes at least the base station j and the PGW;
  • the base station j is instructed by the interface circuit 1102 to update the stored video;
  • the storage revenue is used to characterize the saving of the user access delay by the cache node storing the video.
  • processor 1101 is further configured to:
  • the stored video is updated.
  • the processor 1101 is specifically configured to:
  • the storage income P ij is calculated according to the on-demand frequency f ij and the access delay of the base station j to the PGW;
  • the base station j acquires the source of the video i as another base station in the cache coordinating unit, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the base station where the video i is located Calculating the stored benefit P ij by the access delay to the PGW; or
  • the base station j acquires the source of the video i as a content distribution network, according to the on-demand frequency f ij , the access delay of the base station j to the PGW, and the access delay of the PGW to the content distribution network.
  • the stored revenue P ij is calculated.
  • the processor 1101 is specifically configured to:
  • the storage revenue P i is calculated according to the on-demand frequency f i and the access delay of the PGW to the content distribution network, and the on-demand frequency P i The sum of the on-demand frequencies of the respective base stations; or
  • At least one base station in the cache cooperating unit stores the video i, and the access delays of the respective base stations in the cache cooperating unit to the PGW are the same, according to the on-demand frequency f i and the respective base stations to the accessing said memory of said computing PGW delay return P i, F i is the frequency of the demand on demand without storing the frequency of the base station i and a video buffer in said cooperating means.
  • the processor 1101 herein may be a processor or a collective name of multiple processing elements.
  • the processor may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.
  • CPU Central Processing Unit
  • ASIC Application Specific Integrated Circuit
  • DSP digital signal processor
  • FPGA Field Programmable Gate Array
  • the memory 1103 may be a storage device or a collective name of a plurality of storage elements, and is used to store executable program code or parameters, data, and the like required for operation of the access network device. And memory 1103 It may include random access memory (RAM), and may also include non-volatile memory such as disk storage, flash memory, and the like.
  • RAM random access memory
  • non-volatile memory such as disk storage, flash memory, and the like.
  • the bus 1104 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component
  • EISA Extended Industry Standard Architecture
  • the bus 1104 can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in FIG. 10, but it does not mean that there is only one bus or one type of bus.
  • the present invention has the following advantages:
  • the PGW may calculate the storage revenue of the video on the base station according to the on-demand frequency of the video on the base station, and the source of the video obtained by the base station, and then the video is The storage revenue is compared with the storage revenue of the stored video of the base station, and finally, according to the comparison result, the PGW indicates whether the base station performs the update of the stored video. It is ensured that the video buffered on the base station is a video with higher storage revenue, and since the calculation of the storage revenue needs to be determined according to the source of the video obtained by the base station, it can be ensured between the base station and other base stations in the cache cooperation unit and the PGW.
  • the cache redundancy is low, thereby improving the utilization of the multi-level cache system, and the calculation is simple and convenient, the result is accurate, and the complexity of the multi-level cache system management is reduced; by further calculating the storage revenue of the video on the PGW, It can ensure that the video stored on the PGW is a video with higher revenue, so that the utilization of the PGW storage space can be improved, and the determination of the storage revenue needs to be determined according to the video storage condition of all the base stations in the cache cooperation unit, thereby improving the storage revenue.
  • the validity and accuracy of the calculation further improve the space utilization of the multi-level cache system, and the calculation is simple and convenient, and the result is accurate, which reduces the complexity of the multi-level cache system management.
  • the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
  • the foregoing steps include the steps of the foregoing method embodiments; and the foregoing storage medium includes: a medium that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

Abstract

本发明实施例公开了一种缓存的方法及分数数据网关,所述方法包括:若缓存协作单元内的基站j接收到点播视频i的用户请求,分组数据网关PGW更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述PGW;所述PGW根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij;若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则所述PGW指示所述基站j更新存储的视频;其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。采用本发明,可降低缓存冗余度,提高多级缓存系统的资源利用率。

Description

一种缓存的方法及分组数据网关 技术领域
本发明涉及通信技术领域,尤其涉及一种缓存的方法及分组数据网关。
背景技术
随着智能手机、平板电脑等手持移动终端的性能不断提升,越来越多的用户选择通过移动终端来随时随地的访问网络。通过手机、平板来观看在线视频的人数也在不断的增加,视频数据已经成为了移动网络流量的主力。据估计,全球的移动数据量每年增长92%,其中三分之二以上的数据为视频数据。网络视频数据的不断增长,海量多媒体数据的传输需求给互联网带来了极大的数据传输压力,并导致了网络拥塞、服务器过载、用户请求响应时间过长和网络服务质量下降等一系列问题。为了应对这一挑战,内容分发网络(Content Delivery Network,CDN)技术应用而生。在传统网络当中,用户的请求需要到达中心服务器才可以得到响应。而在CDN网络当中,数据被备份到多个缓存服务器上,用户的请求可以在最近的缓存服务器处得到响应。这样,用户的请求和用户请求的数据都可以不再通过中心网络区域,从而极大的缓解了中心网络的压力。但是在移动网络当中,这一项技术并不足以满足用户对视频观看体验的要求,因为用户请求的视频数据从CDN缓存服务器获得后,依然需要经过核心网络(Core Network,CN),再经过无线接入网络(Radio Access Network,RAN),才能到达用户设备(User Equipment,UE)。这样,在CDN技术解决了从中心服务器到边缘网络设备之间的流量瓶颈之后,限制用户通过移动网络观看视频的最主要的流量瓶颈转移到了CN网络当中。
在现有技术中,为了进一步提高移动网络用户访问视频的速度,多级缓存系统被应用到移动网络之中。通过在CN网络的分组数据网关(Packet Data Network Gateway,PGW)服务器处增加缓存设备可以避免从CDN服务器获取视频,从而能够进一步增加用户访问视频的速度。此外在移动基站上增加缓存设备则可以进一步降低用户的访问延迟并减少对CN网络无线回程带宽的消耗。CDN缓存、PGW缓存、基站缓存共同构成了移动视频的三级缓存体系。各个缓存节点都依据其服务区内视频的点击频率来选择要存储的内容。由于各节点的服务区存在着地理上的临近性,各节点服务区内用户的访问行为存在相 似性,缓存节点的存储内容存在着大量的数据冗余。开发多级缓存系统中各缓存节点之间的协作式缓存算法对降低缓存数据的冗余度、提升缓存系统的利用率具有重要意义。
发明内容
本发明实施例所要解决的技术问题在于,提供一种缓存的方法及分组数据网关。以解决缓存冗余度高的问题。
第一方面,本发明实施例提供了一种缓存的方法,包括:
若缓存协作单元内的基站j接收到点播视频i的用户请求,分组数据网关PGW更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述PGW;
所述PGW根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则所述PGW指示所述基站j更新存储的视频;
其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
当某基站接收到点播视频的用户请求时,PGW可以根据该视频在该基站上的点播频率,并结合该基站获取该视频的来源计算该视频在该基站上的存储收益,然后将该视频的存储收益与该基站已存储视频的存储收益进行比较,最后根据比较结果由PGW指示该基站是否进行存储视频的更新。确保了该基站上缓存的视频是存储收益较高的视频,且由于存储收益的计算需要根据该基站获取该视频的来源确定,因此可以确保该基站与缓存协作单元内的其他基站以及PGW之间,缓存冗余度较低,从而提升了多级缓存系统的利用率,且计算简单方便,结果准确,降低了多级缓存系统管理的复杂度。
结合第一方面,在第一方面第一种可能的实现方式中,在所述基站j根据所述PGW的指示更新存储的视频之后,或者
若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则所述PGW更新自身的视频i的点播频率fi
所述PGW根据所述点播频率fi以及所述视频i在所述缓存协作单元内各 个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则所述PGW更新存储的视频。
通过进一步计算了PGW上视频的存储收益,因此可以确保PGW上存储的视频为存储收益较高的视频,从而可提升PGW存储空间的利用率,且其存储收益的确定需要根据缓存协作单元中所有基站的视频存储情况确定,因此可提升存储收益计算的有效性和准确性,进一步提升多级缓存系统的空间利用率,且计算简单方便,结果准确,降低了多级缓存系统管理的复杂度。
结合第一方面或结合第一方面第一种可能的实现方式,在第一方面第二种可能的实现方式中,所述PGW根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij,包括:
若所述基站j获取所述视频i的来源为所述PGW,则所述PGW根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则所述PGW根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为内容分发网络,则所述PGW根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
结合第一方面第一种可能的实现方式,在第一方面第三种可能的实现方式中,所述PGW根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi,包括:
若所述缓存协作单元内各个基站均未存储所述视频i,则所述PGW根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;或者,
若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则所述PGW根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播 频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
第二方面,本发明实施例提供了一种分组数据网关,包括:
更新单元,用于若缓存协作单元内的基站j接收到点播视频i的用户请求,更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述分组数据网关PGW;
计算单元,用于根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
指示单元,用于若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则指示所述基站j更新存储的视频;
其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
结合第二方面,在第二方面第一种可能的实现方式中,所述更新单元还用于在所述基站j根据所述指示单元的指示更新存储的视频之后,或者
若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则更新所述PGW的视频i的点播频率fi
所述计算单元还用于根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
所述更新单元还用于若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则更新所述PGW存储的视频。
结合第二方面或结合第二方面第一种可能的实现方式,在第二方面第二种可能的实现方式中,所述计算单元具体用于:
若所述基站j获取所述视频i的来源为所述PGW,则根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为内容分发网络,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
结合第二方面第一种可能的实现方式,在第二方面第三种可能的实现方式 中,所述计算单元具体用于:
若所述缓存协作单元内各个基站均未存储所述视频i,则根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;或者,
若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
第三方面,本发明实施例提供了一种分组数据网关,包括:
处理器、接口电路、存储器和总线,所述处理器、接口电路和存储器通过所述总线连接并完成相互间的通信,其中,所述存储器用于存储视频数据,以及用于存储一组程序代码,所述处理器用于调用所述存储器中存储的程序代码,执行以下操作:
若缓存协作单元内的基站j接收到点播视频i的用户请求,更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述PGW;
根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则通过所述接口电路指示所述基站j更新存储的视频;
其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
结合第三方面,在第三方面第一种可能的实现方式中,所述处理器还用于:在所述基站j根据所述处理器的指示更新存储的视频之后,或者
若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则更新所述PGW的视频i的点播频率fi
根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则更新存储的视频。
结合第三方面或结合第三方面第一种可能的实现方式,在第三方面第二种可能的实现方式中,所述处理器具体用于:
若所述基站j获取所述视频i的来源为所述PGW,则根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为内容分发网络,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
结合第三方面第一种可能的实现方式,在第三方面第三种可能的实现方式中,所述处理器具体用于:
若所述缓存协作单元内各个基站均未存储所述视频i,则根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;或者,
若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
第四方面,本发明实施例提供了一种计算机存储介质,所述计算机存储介质包括一组程序代码,用于执行如本发明实施例第一方面任一实现方式所述的方法。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1为本发明实施例中多级缓存系统的架构及访问延迟的示意图;
图2为本发明实施例提供的一种缓存的方法的流程示意图;
图3为本发明实施例提供的一种缓存的方法的流程示意图;
图4为本发明实施例提供的一种分组数据网关的组成示意图;
图5是本发明实施例提供的另一种分组数据网关的组成示意图。
具体实施方式
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
首先,对本申请中的多级缓存系统的架构进行解释说明,以便于本领域技术人员理解。
1)、内容分发网络(Content Delivery Network,CDN)服务器,其用于缓存数据文件,为用户提供就近性的服务,CDN的基本思路是尽可能避开互联网上有可能影响数据传输速度和稳定性的瓶颈和环节,使内容传输的更快、更稳定。通过在网络各处放置节点服务器所构成的在现有的互联网基础之上的一层智能虚拟网络,CDN系统能够实时地根据网络流量和各节点的连接、负载状况以及到用户的距离和响应时间等综合信息将用户的请求重新导向离用户最近的服务节点上。其目的是使用户可就近取得所需内容,解决网络拥挤的状况,提高用户访问网站的响应速度。
2)、PGW是移动通信网络中的重要网元,是核心网络的边界网关,提供用户的会话管理和承载控制、数据转发、IP地址分配以及非3GPP用户接入等功能。
3)、基站是一种无线接入网(Radio Access Network,RAN)设备,用于将终端接入到核心网络,其包括但不限于:演进型网络基站(evolved NodeB,eNodeB)、无线网络控制器(Radio Network Controller,RNC)、3G基站(NodeB)、基站控制器(Base Station Controller,BSC)、基站收发台(Base Transceiver Station,BTS)、家庭基站(例如,Home evolved NodeB,或Home NodeB,HNB)、基带单元(Base Band Unit,BBU)等。
4)、终端,又称之为用户设备(User Equipment,UE),是一种向用户提供语音和/或数据连通性的设备,例如,具有无线连接功能的手持式设备、车载设备、连接到无线调制解调器的其他处理设备等。
以上基站、PGW、CDN均具备自己的缓存单元来存储数据,由基站、PGW和CDN三类缓存节点共同组成了本发明实施例中的多级缓存系统。以下基站j为基站的序号或编号,用于对基站进行标识以区别于其他基站;类似地,视频i中的i为视频的序号或编号,用于对视频进行标识以区别于其他视频。
在本发明的实施例中,还将涉及到视频的点播频率、存储收益和访问延迟。其中:
点播频率,用于表征视频在单位时间内的点播次数。
存储收益,用于表征缓存节点存储视频对用户访问延迟的节省量。
访问延迟,用于表征从用户请求发出到用户接收到视频的时间间隔。
如图1所示,UE到基站的访问延迟为t0,多个基站和PGW组成一个缓存协作单元,为了便于解释说明,假设每个基站到PGW的访问延迟均为t1,PGW到CDN的访问延迟为t2
下面结合附图2-3对本发明缓存的方法进行举例说明。
请参考图2,为本发明实施例提供的一种缓存的方法的流程示意图。在本实施例中,缓存协作单元由一个基站j、一个PGW以及至少一个其他的所述方法包括:
S201:若缓存协作单元内的基站j接收到点播视频i的用户请求,分组数据网关PGW更新所述基站j上所述视频i的点播频率fij。所述缓存协作单元至少包括所述基站j和所述PGW。
S202:所述PGW根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
S203:若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则所述PGW指示所述基站j更新存储的视频。
具体地,在步骤S201中,基站j接收到针对视频i的用户请求之后,若基站j存储了视频i,则把视频i直接传输给UE,若基站j没有存储视频i,则基 站j把用户请求转发给PGW,然后PGW按照PGW缓存—其它基站缓存—CDN缓存的先后顺序寻找视频i,找到之后发送给基站j,基站j在接收到视频i之后,便可以发送给UE,同时,基于此次视频i的点播,PGW对基站j上视频i的点播频率fij进行更新。例如,若基站j单位时间内从未接收到视频i的点播请求,则其以前的点播频率为0,通过这次点播之后增加了1,则点播频率更新为1;若基站j单位时间内接收到视频i的点播请求为5次,则其以前的点播频率为5,通过这次点播之后增加了1,则更新之后的点播频率为6。
需要说明的是,此处的单位时间可以设备生产商在出厂时设定或配置一些可选的选项供操作人员选择或直接由操作人员自定义,本发明实施例不作任何限定。
在步骤S202中,PGW可以根据点播频率fij以及所述基站j获取所述视频i的来源计算基站j上视频的存储收益Pij
一个基站上视频的存储收益受到其他基站和PGW缓存的存储内容的影响。一个基站上某视频的存储收益代表的是在该基站上存储该视频与不存储该视频的用户访问延迟的差异。以fij代表视频i在基站j上的点播频率,Pij代表基站j上存储视频i的收益,则:
Pij=fij*(t’ij-tij)       (1)
其中,t’ij表示在基站j上没有存储视频i时用户的访问延迟,tij表示在基站j上存储了视频i时用户的访问延迟。上述公式表明视频的存储代表了用户访问延迟的减少量。
可选地,若所述基站j获取所述视频i的来源为所述PGW,则所述PGW根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij
若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则所述PGW根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij
若所述基站j获取所述视频i的来源为内容分发网络,则所述PGW根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
具体地,当基站j存储了视频i时,tij=t0。t’ij的取值则由缓存协作单元内其他基站和PGW缓存的存储状况共同决定,如果PGW存储了视频i,则t’ij=t0+t1;如果PGW没有存储视频i,但是缓存协作单元内的其他基站存储了视频i,则基站j需要经过PGW中转来从其他基站获取视频数据,由于前面假设了缓存协作单元内每个基站到PGW的访问延迟均为t1,因此此时的t’ij=t0+2t1(如果基站j到PGW的访问延迟为t1,存储了视频i的基站到PGW的访问延迟为t3,则此时的t’ij=t0+t1+t3);如果缓存协作单元内任何一个缓存节点上都没有存储i即PGW和所有基站都没有存储视频i,则基站j只能从远程的CDN获取视频数据,所以此时的t’ij=t0+t1+t2。结合公式(1)可得:
Figure PCTCN2015100290-appb-000001
因此,基站j的视频存储收益由基站j的视频点播频率、PGW和其他基站的视频存储情况共同决定。若缓存协作单元内没有其他基站,则基站j的视频存储收益由基站j的视频点播频率和PGW的视频存储情况共同决定。
当根据公式(2)计算得到基站j上视频i的存储收益之后,便可以执行步骤S203,在S203中,PGW可以将视频i的存储收益与基站j已存储视频的存储收益进行比较,一般地,基站j上将根据自身的存储容量存储一批存储收益较大的视频,因此,若视频i的存储收益大于或等于已存储视频的存储收益时,PGW则将发送更新指令指示基站j对存储的视频进行更新,具体在更新时,可以是删除已存储视频中存储收益较低的视频并添加视频i,当然,若存储容量允许,也可以不删除已存储视频并直接将视频i添加至缓存中。而当视频i的存储收益小于已存储视频的存储收益时,则无需进行更新。
这样,当某基站接收到点播视频的用户请求时,PGW可以根据该视频在该基站上的点播频率,并结合该基站获取该视频的来源计算该视频在该基站上的存储收益,然后将该视频的存储收益与该基站已存储视频的存储收益进行比较,最后根据比较结果由PGW指示该基站是否进行存储视频的更新。确保了该基站上缓存的视频是存储收益较高的视频,且由于存储收益的计算需要根据 该基站获取该视频的来源确定,因此可以确保该基站与缓存协作单元内的其他基站以及PGW之间,缓存冗余度较低,从而提升了多级缓存系统的利用率,且计算简单方便,结果准确,降低了多级缓存系统管理的复杂度。
请参考图3,其为本发明实施例提供的另一种缓存的方法的流程示意图,在本实施例中,步骤S301-S303与上一实施例中的步骤S201-S203相同,此处不再赘述,在基站j根据PGW的指示更新存储的视频之后,或者若存储收益Pij小于基站j上已存储视频的存储收益时,所述方法还包括如下步骤:
S304:在所述基站j根据所述PGW的指示更新存储的视频之后,或者若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则所述PGW更新自身的视频i的点播频率fi
S305:所述PGW根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
S306:若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则所述PGW更新存储的视频。
在步骤S304和S305中,PGW自身的视频i的点播频率fi由缓存协作单元内所包含的所有基站上视频i的点播频率和存储情况确定。因此,PGW上视频i的存储收益Pi也和缓存协作单元内所包含的所有基站上视频i的点播频率和存储情况相关。
可选地,若所述缓存协作单元内各个基站均未存储所述视频i,则所述PGW根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;
若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则所述PGW根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
具体地,PGW缓存上视频的存储收益受到所有基站的存储状态的影响。PGW在多级缓存系统中的作用是充当基站的缓存服务器,因此PGW应该以向基站提供最佳服务为目标。PGW上视频存储收益的计算分两种情况,下面 以Pi代表在PGW上存储视频i的收益,以kij∈{0,1}表示基站j是否存储了视频i进行说明:
1)所有的基站上都没有存储视频i
这种情况下,如果PGW也没有存储视频i,则所有基站都需要从CDN获取视频数据,这个访问延迟是t0+t1+t2;如果PGW存储了视频,则所有基站都可以从PGW获取视频数据,这个访问延迟是t0+t1,因此PGW存储视频节省的时间是(t0+t1+t2)-(t0+t1)=t2,所以在该情况下PGW存储视频i的存储收益为:
Figure PCTCN2015100290-appb-000002
2)至少一个基站存储了视频i
这种情况下,如果PGW没有存储视频i,那些存储了视频i的基站上用户访问该视频的访问延迟是t0,而没有存储视频i的基站可以经PGW中转后从存储了视频i的基站上获取视频数据,这个延迟是t0+2*t1。如果PGW存储了视频i,那些存储了视频i的基站上用户访问该视频的访问延迟依然是t0,而没有存储视频i的基站就可以直接从PGW获取视频数据,这个访问延迟是t0+t1。所以在该情况下PGW存储视频i的存储收益为:
Figure PCTCN2015100290-appb-000003
综合公式(3)和(4),PGW上存储视频i的存储收益为:
Figure PCTCN2015100290-appb-000004
PGW上视频的存储收益由所有基站上视频的点播频率和视频存储情况共同决定。若缓存协作单元内没有其他基站,则PGW的视频存储收益仅由基站j的视频点播频率和视频存储情况决定。
当根据公式(5)计算得到PGW上视频i的存储收益之后,便可以执行步骤S306,在S306中,PGW可以将视频i的存储收益与自身已存储视频的存储收益进行比较,一般地,PGW将根据自身对应缓存单元的存储容量存储一 批存储收益较大的视频,因此,若视频i的存储收益大于或等于其已存储视频的存储收益时,PGW则对存储的视频进行更新,具体在更新时,可以是删除已存储视频中存储收益较低的视频并添加视频i,当然,若存储容量允许,也可以不删除已存储视频并直接将视频i添加至缓存中。而当视频i的存储收益小于已存储视频的存储收益时,则无需进行更新。
在本实施例中,进一步计算了PGW上视频的存储收益,因此可以确保PGW上存储的视频为存储收益较高的视频,从而可提升PGW存储空间的利用率,且其存储收益的确定需要根据缓存协作单元中所有基站的视频存储情况确定,因此可提升存储收益计算的有效性和准确性,进一步提升多级缓存系统的空间利用率,且计算简单方便,结果准确,降低了多级缓存系统管理的复杂度。
需要说明的是,本发明实施例仅描述了一个CDN下的一个缓存协作单元对视频缓存的处理流程,当一个CDN下连接了多个缓存协作单元时,还可以将多个缓存协作单元进行进一步的协作处理,其存储收益可参考本发明实施例中所述的计算方法。具体在选择协作的缓存协作单元时,可根据数据传输速度、访问延迟等因素进行选择,本发明实施例不作任何限定。
且缓存协作单元内基站与PGW之间进行数据传输时,由于缓存决策过程中基站侧的存储收益计算基于PGW的视频存储情况而定,而基站缓存决策完成之后PGW进行了缓存决策,这个时候PGW的视频存储情况可能发生了变化,所以基站基于PGW原来的视频存储情况计算得到的存储收益并进行视频更新之后。还可以考虑在基站与PGW之间进行PGW新增视频数据的迁移,即将PGW新存储的视频传输至基站以进一步优化基站侧的存储结果。
请参考图4,为本发明实施例提供的一种分组数据网关的组成示意图,在本发明实施例中,所述分组数据网关包括:
更新单元100,用于若缓存协作单元内的基站j接收到点播视频i的用户请求,更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述分组数据网关PGW;
计算单元200,用于根据所述点播频率fij以及所述基站j获取所述视频i 的来源计算所述基站j上所述视频i的存储收益Pij
指示单元300,用于若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则指示所述基站j更新存储的视频;
其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
可选地,所述更新单元100还用于在所述基站j根据所述指示单元的指示更新存储的视频之后,或者
若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则更新所述PGW的视频i的点播频率fi
所述计算单元200还用于根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
所述更新单元100还用于若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则更新所述PGW存储的视频。
在计算基站上的视频存储收益时,所述计算单元200具体用于:
若所述基站j获取所述视频i的来源为所述PGW,则根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为内容分发网络,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
在计算PGW上的视频存储收益时,所述计算单元200具体用于:
若所述缓存协作单元内各个基站均未存储所述视频i,则根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;或者,
若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
需要说明的是,基站包括但不限于:演进型节点B、节点B、基站控制器、基站收发台、家庭基站、基带单元等。本实施例中的指示单元300可以为PGW的接口电路,该接口电路可以与基站的射频收发部分连接,用于实现与基站的通信。计算单元200可以为单独设立的处理器,也可以集成在PGW的某一个处理器中实现,此外,也可以以程序代码的形式存储于PGW的存储器中,由PGW的某一个处理器调用并执行以上计算单元200的功能。更新单元100的实现同计算单元200,且可以与计算单元200集成在一起,也可以独立实现。这里所述的处理器可以是一个中央处理器(Central Processing Unit,CPU),或者是特定集成电路(Application Specific Integrated Circuit,ASIC),或者是被配置成实施本发明实施例的一个或多个集成电路。
请参照图5,为本发明实施例提供的另一种分组数据网关的组成示意图,在本发明实施例中,所述分组数据网关包括:
处理器1101、接口电路1102、存储器1103和总线1104,所述处理器1101、接口电路1102和存储器1103通过所述总线1104连接并完成相互间的通信,其中,所述存储器1103用于存储视频数据,以及用于存储一组程序代码,所述处理器1101用于调用所述存储器1103中存储的程序代码,执行以下操作:
若缓存协作单元内的基站j接收到点播视频i的用户请求,更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述PGW;
根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则通过所述接口电路1102指示所述基站j更新存储的视频;
其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
可选地,所述处理器1101还用于:
在所述基站j根据所述处理器的指示更新存储的视频之后,或者
若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则更新所述PGW的视频i的点播频率fi
根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则更新存储的视频。
可选地,所述处理器1101具体用于:
若所述基站j获取所述视频i的来源为所述PGW,则根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
若所述基站j获取所述视频i的来源为内容分发网络,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
可选地,所述处理器1101具体用于:
若所述缓存协作单元内各个基站均未存储所述视频i,则根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;或者,
若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
需要说明的是,这里的处理器1101可以是一个处理器,也可以是多个处理元件的统称。例如,该处理器可以是中央处理器(Central Processing Unit,CPU),也可以是特定集成电路(Application Specific Integrated Circuit,ASIC),或者是被配置成实施本发明实施例的一个或多个集成电路,例如:一个或多个微处理器(digital signal processor,DSP),或,一个或者多个现场可编程门阵列(Field Programmable Gate Array,FPGA)。
存储器1103可以是一个存储装置,也可以是多个存储元件的统称,且用于存储可执行程序代码或接入网设备运行所需要参数、数据等。且存储器1103 可以包括随机存储器(RAM),也可以包括非易失性存储器(non-volatile memory),例如磁盘存储器,闪存(Flash)等。
总线1104可以是工业标准体系结构(Industry Standard Architecture,ISA)总线、外部设备互连(Peripheral Component,PCI)总线或扩展工业标准体系结构(Extended Industry Standard Architecture,EISA)总线等。该总线1104可以分为地址总线、数据总线、控制总线等。为便于表示,图10中仅用一条粗线表示,但并不表示仅有一根总线或一种类型的总线。
需要说明的是,本说明书中的各个实施例均采用递进的方式描述,每个实施例重点说明的都是与其它实施例的不同之处,各个实施例之间相同相似的部分互相参见即可。对于装置实施例而言,由于其与方法实施例基本相似,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
通过上述实施例的描述,本发明具有以下优点:
当某基站接收到点播视频的用户请求时,PGW可以根据该视频在该基站上的点播频率,并结合该基站获取该视频的来源计算该视频在该基站上的存储收益,然后将该视频的存储收益与该基站已存储视频的存储收益进行比较,最后根据比较结果由PGW指示该基站是否进行存储视频的更新。确保了该基站上缓存的视频是存储收益较高的视频,且由于存储收益的计算需要根据该基站获取该视频的来源确定,因此可以确保该基站与缓存协作单元内的其他基站以及PGW之间,缓存冗余度较低,从而提升了多级缓存系统的利用率,且计算简单方便,结果准确,降低了多级缓存系统管理的复杂度;通过进一步计算了PGW上视频的存储收益,因此可以确保PGW上存储的视频为存储收益较高的视频,从而可提升PGW存储空间的利用率,且其存储收益的确定需要根据缓存协作单元中所有基站的视频存储情况确定,因此可提升存储收益计算的有效性和准确性,进一步提升多级缓存系统的空间利用率,且计算简单方便,结果准确,降低了多级缓存系统管理的复杂度。
本领域普通技术人员可以理解:实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成,前述的程序可以存储于一计算机可读取存储介质中,该程序在执行时,执行包括上述方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上对本发明实施例所提供的一种缓存的方法及分组数据网关进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。

Claims (12)

  1. 一种缓存的方法,其特征在于,包括:
    若缓存协作单元内的基站j接收到点播视频i的用户请求,分组数据网关PGW更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述PGW;
    所述PGW根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
    若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则所述PGW指示所述基站j更新存储的视频;
    其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
  2. 根据权利要求1所述的方法,其特征在于,还包括:
    在所述基站j根据所述PGW的指示更新存储的视频之后,或者
    若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则所述PGW更新自身的视频i的点播频率fi
    所述PGW根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
    若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则所述PGW更新存储的视频。
  3. 根据权利要求1或2所述的方法,其特征在于,所述PGW根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij,包括:
    若所述基站j获取所述视频i的来源为所述PGW,则所述PGW根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则所述PGW根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及 所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为内容分发网络,则所述PGW根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
  4. 根据权利要求2所述的方法,其特征在于,所述PGW根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi,包括:
    若所述缓存协作单元内各个基站均未存储所述视频i,则所述PGW根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;或者,
    若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则所述PGW根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
  5. 一种分组数据网关,其特征在于,包括:
    更新单元,用于若缓存协作单元内的基站j接收到点播视频i的用户请求,更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述分组数据网关PGW;
    计算单元,用于根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
    指示单元,用于若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则指示所述基站j更新存储的视频;
    其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
  6. 根据权利要求5所述的分组数据网关,其特征在于,所述更新单元还用于在所述基站j根据所述指示单元的指示更新存储的视频之后,或者
    若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则更新所述 PGW的视频i的点播频率fi
    所述计算单元还用于根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
    所述更新单元还用于若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则更新所述PGW存储的视频。
  7. 根据权利要求5或6所述的分组数据网关,其特征在于,所述计算单元具体用于:
    若所述基站j获取所述视频i的来源为所述PGW,则根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为内容分发网络,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
  8. 根据权利要求6所述的分组数据网关,其特征在于,所述计算单元具体用于:
    若所述缓存协作单元内各个基站均未存储所述视频i,则根据所述点播频率fi和所述PGW至内容分发网络的访问延迟计算所述存储收益Pi,所述点播频率Pi为所述各个基站的点播频率之和;或者,
    若所述缓存协作单元内至少一个基站存储了所述视频i,且所述缓存协作单元内各个基站至所述PGW的访问延迟相同,则根据所述点播频率fi和所述各个基站至所述PGW的访问延迟计算所述存储收益Pi,所述点播频率fi为所述缓存协作单元内没有存储所述视频i的基站的点播频率之和。
  9. 一种分组数据网关,其特征在于,包括:
    处理器、接口电路、存储器和总线,所述处理器、接口电路和存储器通过 所述总线连接并完成相互间的通信,其中,所述存储器用于存储视频数据,以及用于存储一组程序代码,所述处理器用于调用所述存储器中存储的程序代码,执行以下操作:
    若缓存协作单元内的基站j接收到点播视频i的用户请求,更新所述基站j上所述视频i的点播频率fij,所述缓存协作单元至少包括所述基站j和所述PGW;
    根据所述点播频率fij以及所述基站j获取所述视频i的来源计算所述基站j上所述视频i的存储收益Pij
    若所述存储收益Pij大于或等于所述基站j上已存储视频的存储收益,则通过所述接口电路指示所述基站j更新存储的视频;
    其中,存储收益用于表征缓存节点存储视频对用户访问延迟的节省量。
  10. 根据权利要求9所述的分组数据网关,其特征在于,所述处理器还用于:在所述基站j根据所述处理器的指示更新存储的视频之后,或者
    若所述存储收益Pij小于所述基站j上已存储视频的存储收益,则更新所述PGW的视频i的点播频率fi
    根据所述点播频率fi以及所述视频i在所述缓存协作单元内各个基站的存储情况计算所述PGW上所述视频i的存储收益Pi
    若所述存储收益Pi大于或等于所述PGW上已存储视频的存储收益,则更新存储的视频。
  11. 根据权利要求9或10所述的分组数据网关,其特征在于,所述处理器具体用于:
    若所述基站j获取所述视频i的来源为所述PGW,则根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为内容分发网络,则根据所述点播频 率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
  12. 根据权利要求10所述的分组数据网关,其特征在于,所述处理器具体用于:
    若所述基站j获取所述视频i的来源为所述PGW,则根据所述点播频率fij以及所述基站j至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为所述缓存协作单元中的其他基站,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述视频i所在基站至所述PGW的访问延迟计算所述存储收益Pij;或者,
    若所述基站j获取所述视频i的来源为内容分发网络,则根据所述点播频率fij、所述基站j至所述PGW的访问延迟以及所述PGW至所述内容分发网络的访问延迟计算所述存储收益Pij
PCT/CN2015/100290 2015-12-31 2015-12-31 一种缓存的方法及分组数据网关 WO2017113373A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/100290 WO2017113373A1 (zh) 2015-12-31 2015-12-31 一种缓存的方法及分组数据网关

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/100290 WO2017113373A1 (zh) 2015-12-31 2015-12-31 一种缓存的方法及分组数据网关

Publications (1)

Publication Number Publication Date
WO2017113373A1 true WO2017113373A1 (zh) 2017-07-06

Family

ID=59224314

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/100290 WO2017113373A1 (zh) 2015-12-31 2015-12-31 一种缓存的方法及分组数据网关

Country Status (1)

Country Link
WO (1) WO2017113373A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107548102A (zh) * 2017-08-16 2018-01-05 北京邮电大学 一种边缘缓存网络中最小化用户时延的基站缓存方法
CN112118604A (zh) * 2020-07-27 2020-12-22 哈尔滨工业大学(深圳) 一种面向移动存储系统的中继协作数据修复方法及系统
CN112711730A (zh) * 2021-01-21 2021-04-27 上海观察者信息技术有限公司 一种数据的缓存方法、装置、存储介质及电子设备
CN113573103A (zh) * 2021-09-26 2021-10-29 深圳飞骧科技股份有限公司 分布式移动网络视频缓存放置方法、系统及相关设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102202418A (zh) * 2011-02-23 2011-09-28 华为技术有限公司 业务建立的方法、业务提供的方法、设备及系统
CN102204324A (zh) * 2011-04-27 2011-09-28 华为技术有限公司 提高移动互联网用户访问速度的方法及设备
WO2012128487A2 (ko) * 2011-03-23 2012-09-27 삼성전자 주식회사 무선 통신 시스템 및 그 무선 통신 시스템에서 컨텐츠 전송 방법
CN104507124A (zh) * 2014-12-24 2015-04-08 中国科学院声学研究所 一种基站缓存的管理方法及用户访问的处理方法
CN105072151A (zh) * 2015-07-03 2015-11-18 中国联合网络通信集团有限公司 一种cdn的内容协同调度方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102202418A (zh) * 2011-02-23 2011-09-28 华为技术有限公司 业务建立的方法、业务提供的方法、设备及系统
WO2012128487A2 (ko) * 2011-03-23 2012-09-27 삼성전자 주식회사 무선 통신 시스템 및 그 무선 통신 시스템에서 컨텐츠 전송 방법
CN102204324A (zh) * 2011-04-27 2011-09-28 华为技术有限公司 提高移动互联网用户访问速度的方法及设备
CN104507124A (zh) * 2014-12-24 2015-04-08 中国科学院声学研究所 一种基站缓存的管理方法及用户访问的处理方法
CN105072151A (zh) * 2015-07-03 2015-11-18 中国联合网络通信集团有限公司 一种cdn的内容协同调度方法及系统

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107548102A (zh) * 2017-08-16 2018-01-05 北京邮电大学 一种边缘缓存网络中最小化用户时延的基站缓存方法
CN112118604A (zh) * 2020-07-27 2020-12-22 哈尔滨工业大学(深圳) 一种面向移动存储系统的中继协作数据修复方法及系统
CN112118604B (zh) * 2020-07-27 2023-06-20 哈尔滨工业大学(深圳) 一种面向移动存储系统的中继协作数据修复方法及系统
CN112711730A (zh) * 2021-01-21 2021-04-27 上海观察者信息技术有限公司 一种数据的缓存方法、装置、存储介质及电子设备
CN113573103A (zh) * 2021-09-26 2021-10-29 深圳飞骧科技股份有限公司 分布式移动网络视频缓存放置方法、系统及相关设备
CN113573103B (zh) * 2021-09-26 2022-01-28 深圳飞骧科技股份有限公司 分布式移动网络视频缓存放置方法、系统及相关设备

Similar Documents

Publication Publication Date Title
WO2019119897A1 (zh) 一种边缘计算服务缓存方法、系统、装置及可读存储介质
US10270884B2 (en) Control method, network system and control platform for mobile-edge computing
US20210234798A1 (en) Data transmission method and apparatus, computer readable medium, and electronic device
US8355384B2 (en) System and method of handover in wireless network
WO2017113373A1 (zh) 一种缓存的方法及分组数据网关
US11683392B2 (en) Cache decision method and apparatus
US9736872B2 (en) Data transmission method, apparatus, and system
US20140310339A1 (en) Content delivery method and apparatus, and access network device
US9432440B2 (en) Method of content delivery in LTE RAN, an eNB and communication system
JP6617838B2 (ja) 伝送損失率を低減するための方法および装置
TW201345285A (zh) 為無線使用者提供智慧型編解碼率調整的方法及設備
US11190448B2 (en) Transport congestion control optimization based on network context
US20150049612A1 (en) Determining a Traffic Bearer for Data Traffic Between a Terminal and a Content Data Source of a Content Data Network
CN111211933B (zh) 一种确定传输链路的质量的方法及装置
CN112788698B (zh) 一种数据处理方法、装置及终端设备
US20140136645A1 (en) Content distribution system, cache server, and content distribution method
WO2018176439A1 (zh) 地址获取方法、业务能力开放网元和移动边缘计算网元
WO2013189038A1 (zh) 内容处理的方法和网络侧设备
CN107733949B (zh) 一种无线接入网缓存方法及系统
US10887236B2 (en) Method, network interface card, and computer program product for load balance
WO2015100647A1 (zh) 内容分发方法和装置
CN113613291B (zh) 一种下行gbr业务流传送方法、终端及流量控制单元
WO2018086575A1 (zh) 媒体资源的控制方法及装置
WO2016114767A1 (en) Location based cooperative caching at the ran
EP2997489B1 (en) Method and device for efficient mobile data transmission

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: 15911998

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15911998

Country of ref document: EP

Kind code of ref document: A1