Self-controlling photonic-on-chip networks with deep reinforcement learning

Abstract We present a novel photonic chip design for high bandwidth four-degree optical switches that support high-dimensional switching mechanisms with low insertion loss and low crosstalk in a low power consumption level and a short switching time. Such four-degree photonic chips can be used to bu...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Nguyen Do, Dung Truong, Duy Nguyen, Minh Hoai, Cuong Pham
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/17b98fa5209c4fa59d1328acecb91af3
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:17b98fa5209c4fa59d1328acecb91af3
record_format dspace
spelling oai:doaj.org-article:17b98fa5209c4fa59d1328acecb91af32021-12-05T12:12:43ZSelf-controlling photonic-on-chip networks with deep reinforcement learning10.1038/s41598-021-02583-72045-2322https://doaj.org/article/17b98fa5209c4fa59d1328acecb91af32021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-02583-7https://doaj.org/toc/2045-2322Abstract We present a novel photonic chip design for high bandwidth four-degree optical switches that support high-dimensional switching mechanisms with low insertion loss and low crosstalk in a low power consumption level and a short switching time. Such four-degree photonic chips can be used to build an integrated full-grid Photonic-on-Chip Network (PCN). With four distinct input/output directions, the proposed photonic chips are superior compared to the current bidirectional photonic switches, where a conventionally sizable PCN can only be constructed as a linear chain of bidirectional chips. Our four-directional photonic chips are more flexible and scalable for the design of modern optical switches, enabling the construction of multi-dimensional photonic chip networks that are widely applied for intra-chip communication networks and photonic data centers. More noticeably, our photonic networks can be self-controlling with our proposed Multi-Sample Discovery model, a deep reinforcement learning model based on Proximal Policy Optimization. On a PCN, we can optimize many criteria such as transmission loss, power consumption, and routing time, while preserving performance and scaling up the network with dynamic changes. Experiments on simulated data demonstrate the effectiveness and scalability of the proposed architectural design and optimization algorithm. Perceivable insights make the constructed architecture become the self-controlling photonic-on-chip networks.Nguyen DoDung TruongDuy NguyenMinh HoaiCuong PhamNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-18 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Nguyen Do
Dung Truong
Duy Nguyen
Minh Hoai
Cuong Pham
Self-controlling photonic-on-chip networks with deep reinforcement learning
description Abstract We present a novel photonic chip design for high bandwidth four-degree optical switches that support high-dimensional switching mechanisms with low insertion loss and low crosstalk in a low power consumption level and a short switching time. Such four-degree photonic chips can be used to build an integrated full-grid Photonic-on-Chip Network (PCN). With four distinct input/output directions, the proposed photonic chips are superior compared to the current bidirectional photonic switches, where a conventionally sizable PCN can only be constructed as a linear chain of bidirectional chips. Our four-directional photonic chips are more flexible and scalable for the design of modern optical switches, enabling the construction of multi-dimensional photonic chip networks that are widely applied for intra-chip communication networks and photonic data centers. More noticeably, our photonic networks can be self-controlling with our proposed Multi-Sample Discovery model, a deep reinforcement learning model based on Proximal Policy Optimization. On a PCN, we can optimize many criteria such as transmission loss, power consumption, and routing time, while preserving performance and scaling up the network with dynamic changes. Experiments on simulated data demonstrate the effectiveness and scalability of the proposed architectural design and optimization algorithm. Perceivable insights make the constructed architecture become the self-controlling photonic-on-chip networks.
format article
author Nguyen Do
Dung Truong
Duy Nguyen
Minh Hoai
Cuong Pham
author_facet Nguyen Do
Dung Truong
Duy Nguyen
Minh Hoai
Cuong Pham
author_sort Nguyen Do
title Self-controlling photonic-on-chip networks with deep reinforcement learning
title_short Self-controlling photonic-on-chip networks with deep reinforcement learning
title_full Self-controlling photonic-on-chip networks with deep reinforcement learning
title_fullStr Self-controlling photonic-on-chip networks with deep reinforcement learning
title_full_unstemmed Self-controlling photonic-on-chip networks with deep reinforcement learning
title_sort self-controlling photonic-on-chip networks with deep reinforcement learning
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/17b98fa5209c4fa59d1328acecb91af3
work_keys_str_mv AT nguyendo selfcontrollingphotoniconchipnetworkswithdeepreinforcementlearning
AT dungtruong selfcontrollingphotoniconchipnetworkswithdeepreinforcementlearning
AT duynguyen selfcontrollingphotoniconchipnetworkswithdeepreinforcementlearning
AT minhhoai selfcontrollingphotoniconchipnetworkswithdeepreinforcementlearning
AT cuongpham selfcontrollingphotoniconchipnetworkswithdeepreinforcementlearning
_version_ 1718372118650945536