.png){kind=icon}
Return
Real-time batch processing at a GPU-based edge with a passive optical network
.png){kind=icon}
OA
AI
DOI：10.1364/JOCN.476116.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In recent years, advances in deep learning technology have significantly improved the research and services relating to artificial intelligence. Real-time object recognition is an important technique in smart cities, in which low-cost network deployment and low-latency data transfer are key technologies. In this study, we focus on time- and wavelength-division multiplexed passive optical network (TWDM-PON)-based inference systems to deploy cost-efficient networks that accommodate several network cameras. A significant issue for a graphics processing unit (GPU)-based inference system via a TWDM-PON is the optimal allocation of the upstream wavelength and bandwidth to enable real-time inference. However, an increase in the batch size of the arrival data at the edge servers, thereby ensuring low-latency transmission, has not been considered previously. Therefore, this study proposes the concept of an inference system in which a large number of cameras periodically upload image data to a GPU-based server via the TWDM-PON. Moreover, we propose a cooperative wavelength and bandwidth allocation algorithm to ensure low-latency and time-synchronized data arrivals at the edge. The performance of the proposed scheme is verified through a computer simulation.
Keywords:
Delays
Cameras
Real-time systems
Servers
Resource management
Optical network units
Low latency communication
Journal
IF:
4.3
Papers:
2.3K
Citations:
3.8K
Organization
Cited Papers
ShareSaveDistributed Edge Computing Offloading Algorithm Based on Deep Reinforcement Learning.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveA Deep Learning Approach for Energy Efficient Computational Offloading in Mobile Edge ComputingIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveShareSave
View more