Abstract: Disclosed are a method and an apparatus for controlling data storage. The method includes: obtaining the number of copies of to-be-placed media content; inputting user set information, server set information, media traffic demand information, and network topology information that are collected into a joint optimization model that is based on server selection and traffic engineering to perform joint optimization, and obtaining output information; performing statistics collection on the output information to obtain user access statistics of the to-be-placed media content on each cache device; and placing, according to the user access statistics of the media content and the number of copies, the copies of the to-be-placed media content so that the copies of the to-be-placed media content are preferentially placed on a cache device having large user access statistics. Embodiments of the present invention also provide an apparatus for controlling data storage.

Abstract: Embodiments of the present invention disclose a method, an apparatus and a system for joint optimization. The method for joint optimization includes: decomposing the joint optimization of an entire network into the joint optimization performed in each sub-network, regarding a bandwidth requirement for a server off the sub-network as a bandwidth requirement for a virtual server on a port, iteratively performing the joint optimization in each sub-network, and applying results of the joint optimization in the network. In the embodiments of the present invention, the bandwidth requirement for the server off the sub-network is regarded as the bandwidth requirement for the virtual server on the port, the joint optimization is iteratively performed in each sub-network, and the results of the joint optimization are applied in the network, so that the joint optimization of the entire network is performed in parallel.

Abstract: An apparatus comprising a traffic engineering (TE) and server selection (SS) component configured to couple to an SS component and operate at a first time scale based on SS policies from the SS component, wherein the SS is configured to operate at a second timescale based on TE policies from the TE and SS component, and wherein the second timescale has a finer time granularity than the first time scale by at least one order of magnitude. Also disclosed is a network component comprising a receiver configured to receive one or more SS policies from a content provider or customer node, a logic circuit configured to compute a plurality of joint TE and SS policies for a plurality of network nodes based on the received SS policies, and a transmitter configured to send the joint TE and SS components to the content provider or customer node.

Abstract: A method for Peer-to-Peer (P2P) streaming media data distribution includes: receiving a media resource request message sent by a Client node, and sending a media resource query request corresponding to the message to multiple resource networks; obtaining response messages to the media resource query request; confirming Cache nodes storing the media resource according to the response messages; and requesting the media resource from the Cache nodes. The present invention further provides a system and a Proxy node for streaming media data distribution, thereby expanding an application range of live/on-demand service of a user, and increasing the flexibility of a system for streaming media distribution.

Abstract: A parameter inference method to solve a problem that precision of a Latent Dirichlet Allocation model is poor is provided.

Abstract: Embodiments of the present invention disclose a data processing method including: sending global initial statistical information to each slave node; merging received local statistical information of each slave node, to obtain new global statistical information; if Gibbs sampling performed by a slave node has ended, calculating a probability distribution between a document and topic and a probability distribution between the topic and a word according to the new global statistical information; according to the probability distributions obtained through calculation, establishing a likelihood function of a text set, and maximizing the likelihood function, to obtain a new hLDA hyper-parameter; and if iteration of solving for an hLDA hyper-parameter has converged, and according to the new hLDA hyper-parameter, calculating and outputting the probability distribution between the document and topic and the probability distribution between the topic and word.

Abstract: Disclosed are a method and an apparatus for controlling data storage. The method includes: obtaining the number of copies of to-be-placed media content; inputting user set information, server set information, media traffic demand information, and network topology information that are collected into a joint optimization model that is based on server selection and traffic engineering to perform joint optimization, and obtaining output information; performing statistics collection on the output information to obtain user access statistics of the to-be-placed media content on each cache device; and placing, according to the user access statistics of the media content and the number of copies, the copies of the to-be-placed media content so that the copies of the to-be-placed media content are preferentially placed on a cache device having large user access statistics. Embodiments of the present invention also provide an apparatus for controlling data storage.

Abstract: A method for Peer-to-Peer (P2P) streaming media data distribution includes: receiving a media resource request message sent by a Client node, and sending a media resource query request corresponding to the message to multiple resource networks; obtaining response messages to the media resource query request; confirming Cache nodes storing the media resource according to the response messages; and requesting the media resource from the Cache nodes. The present invention further provides a system and a Proxy node for streaming media data distribution, thereby expanding an application range of live/on-demand service of a user, and increasing the flexibility of a system for streaming media distribution.

Abstract: An apparatus comprising a traffic engineering (TE) and server selection (SS) component configured to couple to an SS component and operate at a first time scale based on SS policies from the SS component, wherein the SS is configured to operate at a second timescale based on TE policies from the TE and SS component, and wherein the second timescale has a finer time granularity than the first time scale by at least one order of magnitude. Also disclosed is a network component comprising a receiver configured to receive one or more SS policies from a content provider or customer node, a logic circuit configured to compute a plurality of joint TE and SS policies for a plurality of network nodes based on the received SS policies, and a transmitter configured to send the joint TE and SS components to the content provider or customer node.

Abstract: The disclosure relates to a method for sending a message, an access router, and a data cache system. The method for sending a message includes: sending a data request received by the access router to a gateway node in the home routing area of the access router; receiving location information from the gateway node, where the location information identifies a data cache node obtained according to the data request, and obtaining information about the cost of routing from the access router to the data cache node according to the location information; and sending a data obtaining request to the data cache node, where the data obtaining request carries the routing cost information. The method for sending a message, the access router, and the data cache system provided herein utilize the radio bandwidth efficiently and improve the network throughput.