Electronics and Telecommunications Research Institute

Chor Won Kim

Hark Yoo

Geun Yong Kim

Jae In Kim

Hee Do Kim

Byung Hee Son

Ryang Soo Kim

Sung Chang Kim

Gi Ha Yoon

Disclosed is an adaptive deep learning inference system that adapts to changing network latency and executes deep learning model inference to ensure end-to-end data processing service latency when providing a deep learning inference service in a mobile edge computing (MEC) environment. An apparatus and method for providing a deep learning inference service performed in an MEC environment including a terminal device, a wireless access network, and an edge computing server are provided. The apparatus and method provide deep learning inference data having deterministic latency, which is fixed service latency, by adjusting service latency required to provide a deep learning inference result according to a change in latency of the wireless access network when at least one terminal device senses data and requests a deep learning inference service.

Adaptive deep learning inference apparatus and method in mobile edge computing

Provided are a system and method for providing a microservice-based device control interface. The system for providing a microservice-based device control interface includes a Docker registry server in which resources required for providing a device control interface are located and a gateway which receives and installs resources and provides a device control interface using a Docker-based microservice structure.

System and method for providing microservice-based device control interface

Growing community of inventors

Gwangju, South Korea

Chor Won Kim