Abstract: An apparatus and method for split processing of a model are provided. The apparatus for the split processing of the model includes a memory including instructions and a processor electrically connected to the memory and configured to execute the instructions. When the instructions are executed by the processor, the processor may be configured to perform a plurality of operations. The plurality of operations may include obtaining information on a plurality of computing nodes that uses at least one layer among a plurality of layers of a model for an artificial intelligence (AI)-based service, obtaining a requirement for the AI-based service, and controlling split processing of the model based on the information and the requirement.

Abstract: a method and an apparatus for managing a cache for storing content by determining popularity of the content based on content requests received during a current time slot for the content; transmitting information about the popularity of the content to a time-to-live (TTL) controller and receiving, from the TTL controller, TTL values for each popularity level determined by the TTL controller based on the information about the popularity; and managing the content based on the TTL values for each popularity level are provided.

Abstract: The present invention related to a method for federated learning method interworking with a mobile core system, the method comprising: querying terminal information of each individual terminal among a plurality of terminals; querying network performance information; selecting participating terminals among the plurality of terminals on the basis of the terminal information and the network performance information; transmitting respective parameters to the participating terminals and requesting local learning; and integrating the parameters.

Abstract: a method and an apparatus for managing a cache for storing content by determining popularity of the content based on content requests received during a current time slot for the content; transmitting information about the popularity of the content to a time-to-live (TTL) controller and receiving, from the TTL controller, TTL values for each popularity level determined by the TTL controller based on the information about the popularity; and managing the content based on the TTL values for each popularity level are provided.

Abstract: The present invention relates to an apparatus and method for porting any hardware or software entity to a reinforcement learning system. The present invention includes receiving, by a proxy, a message including episode initiation information from an agent interface and delivering the message to an entity interface based on first synchronization; receiving, by the proxy, a message including first observation information from the entity interface and delivering the message to the agent interface based on second synchronization; receiving, by the proxy, a message including action information from the agent interface and delivering the message to the entity interface based on first synchronization; and receiving, by the proxy, a message including second observation information and reward information from the entity interface and delivering the message to the agent interface based on second synchronization.

Abstract: The present invention relates to a method and apparatus where a reinforcement learning agent ensures quality of an initial control operation of an environment on the basis of reinforcement learning, wherein a first action calculated by using an algorithm is selected at an initial learning stage, and a second action calculated by using a Q function is selected when the initial learning stage is ended.

Abstract: An application programming interface (API) authentication method using two API tokens which includes issuing a general API token and providing information required for a one-time API token to a user device; and in response to an API request from the user device, processing an API request according to a result of authentication based on the general API token and a one-time API token, which is generated using the information required for a one-time API token creation.

Abstract: An application programming interface (API) authentication method using two API tokens which includes issuing a general API token and providing information required for a one-time API token to a user device; and in response to an API request from the user device, processing an API request according to a result of authentication based on the general API token and a one-time API token, which is generated using the information required for a one-time API token creation.

Abstract: Provided is a packet processing device for an information-centric network. The packet processing device includes a packet transceiver configured to transmit and receive packets, and a packet processing unit configured to process a transmitted or received packet including a forwarding identifier that identifies information present in the ICN and corresponds to an IP address of a network node holding the information, and at least one sub-identifier that identifies child information of the information, in which the forwarding identifier is used to forward packets.

Abstract: A method for processing a query by accessing information by use of an Information-Centric Network (ICN) includes requesting, by a user device, a file by providing a local storage system with an identifier of the file; determining whether the local storage system stores the requested file; and generating, by the local gateway, an information request message including the identifier of the requested file if it is determined that the local storage system does not store the requested file, and providing the ICN with the generated information requested message. Accordingly, architecture expansion is easily achieved without a large scale update of information since there is no need to share information about a file list of each storage system as a whole, and a data query task is performed on a plurality of unspecified storage systems without establishing a one-to-one connection between end points of storage systems.

Abstract: In a content network over which a plurality of smart nodes is coupled, each smart node receives advertisement messages broadcasted by adjacent smart nodes. The advertisement message may be one of a link state advertisement (LSA) message including link state information indicative of a link that is a network interface, a server state advertisement (SSA) message including server state information indicative of a data storage state and a processing state of a processing unit of the smart node, and a content state advertisement (CSA) message including content state information indicative of content stored in the smart node. Each smart node updates its own database based on the information included in the received advertisement message.

Abstract: In a content network over which a plurality of smart nodes is coupled, a content network management system receives information response messages including pieces of management interface base (MIB) information from smart nodes. Next, the content network management system classifies the pieces of MIB information included in the received response messages into server resource information, topology information, and network resource information, and stores and manages the pieces of information.

Abstract: A network node apparatus for Information-Centric Networking (ICN) and an operating method thereof. The network node apparatus has a control plane and a data plane, which are separate from each other, and manages location information of content on the data plane concentratedly. For example, the network node apparatus includes a Content Service Coordination Function (CSCF) configured to process a content request from a user or a publication request from a content provider; a Content Delivery Control Function (CDCF) configured to select an optimal service node to handle the content request or the publication request; and a Content Delivery Service Function (CDSF) configured to download requested content to the user or to download from the content provider content requested to be published and then register the downloaded content.

Abstract: Disclosed is a virtual file system for interworking between a content server and an information-centric network server, the system including: a file system function processing unit configured to process a file operation for a predetermined content requested from a plurality of content service protocols; a cache control unit configured to process the content requested through the file operation by managing a cache in a node; and a protocol matching unit configured to process the content requested through the file operation by interfacing with a plurality of content transfer protocols.

Abstract: In order to easily prevent traffic of a content data server, which provides an arbitrary content, from being overloaded, the content transmission system according to an exemplary embodiment includes a content data server which provides an arbitrary content to a plurality of terminals when a request signal for the arbitrary content is input from the plurality of terminals, a data control server which when the arbitrary content is provided, monitors whether the traffic of the content data server is overloaded and if the traffic is overloaded as a result of monitoring, generates a traffic distribution request signal, and a node control server which when the traffic distribution request signal is input from the data control server, controls to provide the arbitrary content to an arbitrary distribution node, which satisfies a setting standard among a plurality of distribution nodes, to be provided to an arbitrary terminal among the plurality of terminals.

Abstract: The present invention relates to a content providing system and method combining a transparent Internet cache (TIC) server and a content delivery network (CDN), and more particularly, to a content providing system and method that may overcome limitation on capacity of a cache storage found in a TIC service and may also overcome limitation on service transparency found in a CDN service. According to the present invention, it is possible to overcome limitation on capacity of a cache storage found in an existing TIC service and to overcome limitation on service transparency found in a CDN by combining a TIC server and the CDN.

Abstract: A conventional handover method is performed in units of base stations, so that there is a problem in that a large amount of power for handover is consumed and implementation cost is high. Through dedicated protocol message exchanges between a user equipment and a network or between networks, resource availability of candidate networks is checked in advance, a handover target network is selected from among the candidate networks according to a result of checking, and the selected target network is designated as a network to which the user equipment is handed over.

Abstract: An exemplary embodiment provides a router including: a number calculating unit configured to count an accumulated request number corresponding to a plurality of previously requested contents and a request number of a request signal for an arbitrary content which is currently input; a probability calculating unit configured to calculate an arbitrary probability value for the arbitrary content based on the accumulated request number and the request number; and a policy determining unit configured to determine whether to store the arbitrary content which is provided to an arbitrary terminal which transmits the request signal from an arbitrary content server, based on the arbitrary probability value and a set reference probability value.

Abstract: Disclosed is hop-count based content caching. The present invention implements hop-count based content cache placement strategies that efficiently decrease traffics of a network by the routing node's primarily judging whether to cache a content chunk by grasping an attribute of the received content chunk; the routing node's secondarily judging whether to cache the content chunk based on a caching probability of ‘1/hop count’; and storing the content chunk and the hop count information in the cache memory of the routing node when the content chunk is determined to cache the content chunk as a result of the secondary judgment.

Abstract: The present invention relates to an apparatus for supporting information centric networking. An information centric network (ICN) node based on a switch according to the present invention includes an ICN process configured to request information for providing content desired by a user or process an ICN protocol for responding to the requested information; a line card configured to transfer a received packet to the ICN process by recognizing a header format of the packet and, or output the received packet by determining an output port; and a switch module configured to relay a transfer of the packet between the line cards.