
엣지 컴퓨팅은 연산 및 저장 장치를 데이터 소스에 더 가까운 곳으로 재배치하여 데이터 처리를 분산화함으로써 분산 네트워크에서 지연 시간과 대역폭 사용량을 최소화합니다. 엣지 노드, 마이크로 데이터 센터, 게이트웨이를 통합하여 실시간 분석을 지원합니다. IoT 네트워크 주변부에서 애플리케이션 및 AI 추론을 구현합니다. 아키텍처 고려 사항에는 이기종 엣지 환경 내에서의 리소스 관리, 오케스트레이션, 가상화 및 보안이 포함됩니다. 아래는 엣지 컴퓨팅 시스템의 기능과 도입을 촉진하는 엣지 인프라 설계, 프로토콜 개발, 워크로드 최적화 및 확장 가능한 배포 전략에 대한 혁신을 자세히 설명하는 최근 논문 및 특허 모음입니다.
본 자료는 엣지 컴퓨팅, 포그 컴퓨팅, 엣지 노드, 지연 시간 감소, 분산 컴퓨팅, 엣지 분석, IoT 엣지, 엣지 AI, 엣지 데이터 센터, 마이크로 데이터 센터, 엣지 오케스트레이션, 엣지 보안, 엣지 네트워크, 실시간 처리, 엣지 디바이스, 엣지 인프라, 엣지 클라우드, 데이터 지역화, 엣지 캐싱, 엣지 게이트웨이, 엣지 리소스 관리, 엣지 가상화 및 엣지 워크로드 등 다양한 주제로 분류 및 집중적으로 다룬 전 세계 영문 논문과 특허를 엄선하여 정리한 온라인 과학 저널 모음입니다.
Memory-resident execution of persistent executable objects in distributed computing systems
Patent published on the 2026-06-11 in US under Ref US20260161466 by CLARK NICHOLAS [US] (Clark Nicholas [us])
Abstract: A computer-implemented method and system for executing semantic computation in distributed computing environments. Each computational task is instantiated as a persistent executable object comprising an intent field, a context block, and a memory field that stores execution history. The persistent executable object propagates among execution nodes, each of which independently evaluates the object based on embedded intent, context, memory, and locally applied policy. Execution actions including e[...]
Our summary: The method enables memory-resident execution of persistent executable objects in distributed systems. Each task is evaluated independently based on intent, context, and memory without centralized control. This approach allows for adaptive execution across heterogeneous environments, maintaining continuity across asynchronous cycles.
persistent executable objects, distributed computing, semantic computation, memory-resident execution
Patent
Cloud-based mathematical modeling and simulation service system
Patent published on the 2026-06-11 in WO under Ref WO2026118756 by CHONGQING BUSINESS VOCATIONAL COLLEGE [CN] (Yue Siwei [cn])
Abstract: The present application relates to the technical field of cloud-based mathematical modeling and simulation service systems, and particularly relates to a cloud-based mathematical modeling and simulation service system. The system comprises distributed computing nodes, a dynamic resource scheduler, a modular modeling unit, a data storage pool and a communication interface, wherein the distributed computing nodes are connected by means of a high-speed network to form a cluster, the dynamic resourc[...]
Our summary: The system is a cloud-based mathematical modeling and simulation service. It utilizes distributed computing nodes and a dynamic resource scheduler to enhance efficiency. The architecture supports high-concurrency scenarios for industrial simulation and scientific research.
Cloud computing, Mathematical modeling, Distributed computing, Resource scheduling
Patent
System and method for managing access in a network
Patent published on the 2026-06-11 in WO under Ref WO2026120622 by JIO PLATFORMS LTD [IN] (Bhatnagar Aayush [in], Singh Kumar Gaurav [in], Maddheshiya Utkarsh [in], Kumar Vivek [in], Dewna Arun [in])
Abstract: The present disclosure provides system and method for managing access in a network. The method includes receiving user equipment (UE) attachment request corresponding to UE from second network function. The method includes extracting slicing information from received UE attachment request. The method further include initiating session with edge node based on extracted slicing information. Upon initiating the session, the method includes transmitting Traffic Detection Function (TDF)-Session-Reque[...]
Our summary: The system manages network access by processing user equipment attachment requests. It extracts slicing information to initiate sessions with edge nodes. The method includes handling detachment requests and managing stored mapping information.
network access management, user equipment attachment, session initiation, edge node communication
Patent
Systems and methods implementing decentralized payment processing at edge device of payment processing network
Patent published on the 2026-06-11 in US under Ref US20260162117 by CAPITAL ONE SERVICES LLC [US] (Wieker Jeffrey Carlyle [us], Macomber Jackson [us], Rule Jeffrey [us])
Abstract: [0000] An exemplary payment gateway device includes a processor and a memory. The processor is configured to: receive, from a server, merchant specific data associated with a user; validate card data of a card of the user based on the merchant specific data; perform, using a machine learning model, an analysis on a transaction being conducted using the card by the user with a merchant associated with the payment gateway device, the analysis including comparing a transaction size of the transacti[...]
Our summary: The payment gateway device processes transactions at the edge of a network. It utilizes machine learning to analyze user transaction behavior for fraud detection. Upon validating a legitimate transaction, it verifies account balance and approves the transaction.
decentralized payment processing, edge device, machine learning, fraud detection
Patent
Context adaptive sensor system
Patent published on the 2026-06-11 in US under Ref US20260163811 by ANALOG DEVICES INC [US] (Chaves Armindo [us], Malepati Hazarathaiah [us], Stein Yosef [us])
Abstract: [0000] Aspects of the present disclosure include a detection system, a method, and/or a base node for providing the electrical energy to a plurality of edge nodes, transmitting a sensor interrogation signal to at least one of the plurality of edge nodes in the detection system, receiving, in response to the sensor interrogation signal, sensor information, send the sensor information to a predictor configured to: receive sensor training data, train an artificial intelligence engine using the sens[...]
Our summary: The content describes a detection system that utilizes a context adaptive sensor system. It involves a base node providing energy and transmitting signals to edge nodes. The system trains an AI engine to identify anomalies and determine appropriate actions based on sensor data.
sensor system, edge nodes, artificial intelligence, anomaly detection
Patent
Apparatus and method for managing ip address in a distributed computing environment
Patent published on the 2026-06-04 in US under Ref US20260156100 by SPECTRO CLOUD INC [US] (Sharma Vipin K [us], Shen Nianyu [us], Anand Fnu Rishi [us], Smith Anton Gisli [se])
Abstract: [0000] Method and apparatus are provided for managing IP address in a distributed computing environment. The method comprises gathering, by a management agent (MA) of each node in the cluster of nodes, broadcast information of peer nodes; identifying, by the MA of each node in the cluster of nodes, one or more nodes without an overlay IP address using the broadcast information gathered about its peer nodes; electing a candidate node among the one or more nodes without an overlay IP address using[...]
Our summary: The method involves a management agent gathering broadcast information from peer nodes in a cluster. It identifies nodes lacking an overlay IP address and elects a candidate node to assign an available overlay IP address. Communication among the nodes occurs based on the assigned overlay IP address.
IP address management, distributed computing, management agent, cluster nodes
Patent
Probing a theoretical framework for a photonic extreme learning machine
Published on 2026-05-29 by Vicente Rocha, Duarte Silva, Felipe C Moreira, Catarina S Monteiro, Tiago D Ferreira and Nuno A Silva @IOP SCIENCE
Abstract: The development of computing paradigms alternative to von Neumann architectures has recently fueled significant progress in novel all-optical processing solutions. In this work, we investigate how the coherence properties can be exploited for computing by expanding information onto a higher-dimensional space in the photonic extreme learning machine framework. A theoretical framework is provided based on the transmission matrix formalism, mapping the input plane onto the output camera plane, resu[...]
Our summary: This work investigates a theoretical framework for photonic extreme learning machines using coherence properties for computing. It establishes connections with complex extreme learning machines and derives upper bounds for hidden space dimensionality. Experiments validate the model, suggesting potential advancements in all-optical hardware and edge computing solutions.
photonic computing, extreme learning machine, coherence properties, dimensionality estimation
Publication
Adaptive Multi-Camera Fusion and Calibration for Large-Scale Multi-Vehicle Cooperative Simulation Scenarios
Published on 2026-02-03 by Hui Zhang, Chenyu Xia, Huantao Zeng @MDPI
Abstract: In the development of multi-vehicle cooperative hardware-in-the-loop (HIL) simulation platforms based on machine vision, accurate vehicle pose estimation is crucial for achieving efficient cooperative control. However, monocular vision systems inevitably suffer from limited fields of view and insufficient image resolution during target detection, making it difficult to meet the requirements of large-scale, multi-target real-time perception. To address these challenges, this paper proposes an eng[...]
Our summary: This paper presents a multi-camera cooperative vision detection method for large-scale vehicle simulations. It enhances vehicle pose estimation by projecting images onto a unified plane and optimizing image stitching. Experimental results show high accuracy and real-time performance, achieving a 93.41% identification rate and 30 frames per second output.
Multi-Camera Fusion, Vehicle Pose Estimation, Real-Time Processing, Image Mosaicking
Publication











