# US 12,113,718 B2 · Apparatus and method for resource allocation in edge computing environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,113,718 B2 - Document ID: US12113718B2 - Status: Granted - Kind: B2 - Application number: 17/983,577 - Filed: 2022-11-09 - Published: 2023-05-18 - Granted: 2024-10-08 - Earliest claimed: 2021-11-12 - Assignees: Electronics and Telecommunications Research Institute - Applicants: Electronics and Telecommunications Research Institute - Inventors: Hyun-Hwa Choi; Dae-Won Kim; Sun-Wook Kim; Su-Min Jang; Jae-Geun Cha - Web page: https://patentgrep.com/patent/US12113718B2 ## CPC - H04L 47/801: {Real time traffic} - H04L 47/781: {Centralised allocation of resources} - H04L 47/822: {Collecting or measuring resource availability data} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Disclosed herein is a method for resource allocation in an edge-computing environment. The method includes receiving a request for an intelligent edge service, selecting the worker server to execute the service based on an input/output congestion level, allocating resources based on topology information of the worker server, and configuring a virtual environment based on the allocated resources. ## Claims ### Claim 1 A method for allocating computing resources in a master server in an edge-computing environment, comprising: receiving a request for an intelligent edge service; receiving available computing resources in worker servers; selecting a worker server among the worker servers to execute the intelligent edge service; allocating computing resources in the selected worker server based on input/output (I/O) congestion levels and topology information of the worker servers; and configuring a virtual environment based on the allocated computing resources, wherein: the I/O congestion levels are calculated based on average bandwidth against maximum bandwidth of I/O devices among the worker servers for a preset time, and the topology information includes connection information on how nodes in the worker servers are connected. ### Claim 2 (depends on 1) The method of claim 1, wherein selecting the worker server comprises selecting a worker server of which an input device, corresponding to execution of the service, has a lowest congestion level. ### Claim 3 (depends on 1) The method of claim 1, wherein allocating the computing resources includes: selecting an input resource based on resource requirements for the service; selecting a computing resource to be used based on information about a distance from the selected input resource; and selecting an additional computing resource to be used based on information about a connection with the previously selected computing resource. ### Claim 4 (depends on 3) The method of claim 3, wherein selecting the additional computing resource to be used comprises, when an available computing resource having a preset connection relationship with the previously selected computing resource is present, selecting the available computing resource having the preset connection relationship as the additional computing resource to be used. ### Claim 5 (depends on 4) The method of claim 4, wherein selecting the additional computing resource to be used comprises, when the available computing resource having a preset connection relationship with the previously selected computing resource is not present, selecting another available computing resource corresponding to a preset condition as the additional computing resource to be used. ### Claim 6 (depends on 5) The method of claim 5, wherein selecting the additional computing resource to be used comprises, when the available computing resource having a preset connection relationship with the previously selected computing resource is not present, selecting another available computing resource that is most distant from an immediately previously selected computing resource as the additional computing resource to be used. ### Claim 7 (depends on 5) The method of claim 5, wherein the preset connection relationship corresponds to a second connection relationship that supports higher bandwidth than a first connection relationship. ### Claim 8 An apparatus for allocating computing resources in a master server in an edge-computing environment, comprising: a memory for storing at least one program; a processor for executing the program, wherein the program is configured to perform the steps of: receiving, by a global scheduler, a request for an intelligent edge service, receiving available resources in worker servers, and selecting a worker server among the worker servers to execute the intelligent edge service based on input/output (I/O) congestion levels and topology information of the worker servers; and managing, by a global resource manager, the I/O congestion levels and available resource information of the worker servers, wherein: the I/O congestion levels are calculated based on average bandwidth against maximum bandwidth of I/O devices for a preset time, and the topology information includes connection information on how nodes in the worker servers are connected. ### Claim 9 (depends on 8) The apparatus of claim 8, wherein the global scheduler selects the worker server of which an input device, corresponding to execution of the service, has a lowest congestion level. ### Claim 10 An apparatus for allocating computing resources in a worker server in an edge-computing environment, comprising: a memory for storing at least one program; a processor for executing the program, wherein the program is configured to perform the steps of: monitoring, by a congestion manager, an input/output (I/O) congestion level of an input/output (I/O) device; receiving, by a local scheduler, a request for an intelligent edge service from a master server and configuring virtual environment configuration information; and allocating, by a topology manager, computing resources based on topology information and the I/O congestion level, wherein: the I/O congestion level is calculated based on average bandwidth against maximum bandwidth of I/O devices for a preset time, and the topology information includes connection information on how nodes in the worker server are connected. ### Claim 11 (depends on 10) The apparatus of claim 10, wherein the topology manager selects an input resource based on resource requirements for the requested service, selects a computing resource to be used based on information about a distance from the selected input resource, and selects an additional computing resource to be used based on information about a connection with the previously selected computing resource. ### Claim 12 (depends on 11) The apparatus of claim 11, wherein, when an available computing resource having a preset connection relationship with the previously selected computing resource is present, the topology manager selects the available computing resource having the preset connection relationship as the additional computing resource to be used. ### Claim 13 (depends on 12) The apparatus of claim 12, wherein, when the available computing resource having a preset connection relationship with the previously selected computing resource is not present, the topology manager selects another available computing resource corresponding to a preset condition as the additional computing resource to be used. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein, when the available computing resource having a preset connection relationship with the previously selected computing resource is not present, the topology manager selects another computing resource that is most distant from an immediately previously selected computing resource as the additional computing resource to be used.