arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.00162cs.NIcs.ET
收藏

光计算使能网络:光层智能的新曙光?

Optical-computing-enabled Network: A New Dawn for Optical-layer Intelligence?

Dao Thanh Hai, Minh Nguyen, Isaac Woungang

AI总结:

本文提出光计算使能网络架构,通过在光节点中引入光计算能力实现光通信与计算的无缝融合,初步仿真表明该模式较光旁路模式可显著节省光谱并提升容量效率。

摘要:

受近期光计算复兴的启发,本海报提出了一种颠覆性展望,探讨光通信与光计算基础设施无缝融合的可能性,为实现光层智能并进而提升容量效率铺平道路。这要求光节点架构发生范式转变,从当前使用的光旁路转向一种名为光计算使能模式的新模式;在该模式下,除传统的上下路和交叉连接功能外,光节点还升级为在光层的光路实体之间直接具备光计算能力。文中考察了一项聚焦光聚合操作的初步研究,早期仿真结果表明,与光旁路模式相比,光计算使能模式可带来可观的光谱节省。

英文摘要:

Inspired by the renaissance of optical computing recently, this poster presents a disruptive outlook on the possibility of seamless integration between optical communications and optical computing infrastructures, paving the way for achieving optical-layer intelligence and consequently boosting the capacity efficiency. This entails a paradigm shift in optical node architecture from the currently used optical-bypass to a novel one, entitled, optical-computing-enabled mode, where in addition to the traditional add-drop and cross-connect functionalities, optical nodes are upgraded to account for optical-computing capabilities between the lightpath entities directly at the optical layer. A preliminary study focusing on the optical aggregation operation is examined and early simulation results indicate a promising spectral saving enabled by the optical-computing-enabled mode compared with the optical-bypass one.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑