Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA Implementation

Network-on-Chip (NoC) has emerged as the most promising on-chip interconnection framework in Multi-Processor System-on-Chips (MPSoCs) due to its efficiency and scalability. In the deep sub-micron level, NoCs are vulnerable to faults, which leads to the failure of network components such as links and...

Full description

Bibliographic Details
Main Authors: Samala Jagadheesh, P. Veda Bhanu, J. Soumya, Linga Reddy Cenkeramaddi
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9760423/
_version_ 1818572210339577856
author Samala Jagadheesh
P. Veda Bhanu
J. Soumya
Linga Reddy Cenkeramaddi
author_facet Samala Jagadheesh
P. Veda Bhanu
J. Soumya
Linga Reddy Cenkeramaddi
author_sort Samala Jagadheesh
collection DOAJ
description Network-on-Chip (NoC) has emerged as the most promising on-chip interconnection framework in Multi-Processor System-on-Chips (MPSoCs) due to its efficiency and scalability. In the deep sub-micron level, NoCs are vulnerable to faults, which leads to the failure of network components such as links and routers. Failures in NoC components diminish system efficiency and reliability. This paper proposes a Reinforcement Learning based Fault-Tolerant Routing (RL-FTR) algorithm to tackle the routing issues caused by link and router faults in the mesh-based NoC architecture. The efficiency of the proposed RL-FTR algorithm is examined using System-C based cycle-accurate NoC simulator. Simulations are carried out by increasing the number of links and router faults in various sizes of mesh. Followed by simulations, real-time functioning of the proposed RL-FTR algorithm is observed using the FPGA implementation. Results of the simulation and hardware shows that the proposed RL-FTR algorithm provides an optimal routing path from the source router to the destination router.
first_indexed 2024-12-14T18:54:08Z
format Article
id doaj.art-f403086019124ef89630e6aadc192c59
institution Directory Open Access Journal
issn 2169-3536
language English
last_indexed 2024-12-14T18:54:08Z
publishDate 2022-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj.art-f403086019124ef89630e6aadc192c592022-12-21T22:51:09ZengIEEEIEEE Access2169-35362022-01-0110447244473710.1109/ACCESS.2022.31689929760423Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA ImplementationSamala Jagadheesh0https://orcid.org/0000-0003-2354-3289P. Veda Bhanu1https://orcid.org/0000-0001-5663-8407J. Soumya2https://orcid.org/0000-0003-2276-1698Linga Reddy Cenkeramaddi3https://orcid.org/0000-0002-1023-2118Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science-Pilani, Hyderabad Campus, Hyderabad, Telangana, IndiaDepartment of Electrical and Electronics Engineering, Birla Institute of Technology and Science-Pilani, Hyderabad Campus, Hyderabad, Telangana, IndiaDepartment of Electrical and Electronics Engineering, Birla Institute of Technology and Science-Pilani, Hyderabad Campus, Hyderabad, Telangana, IndiaDepartment of Information and Communication Technology, University of Agder (UiA), Grimstad, Kristiansand, NorwayNetwork-on-Chip (NoC) has emerged as the most promising on-chip interconnection framework in Multi-Processor System-on-Chips (MPSoCs) due to its efficiency and scalability. In the deep sub-micron level, NoCs are vulnerable to faults, which leads to the failure of network components such as links and routers. Failures in NoC components diminish system efficiency and reliability. This paper proposes a Reinforcement Learning based Fault-Tolerant Routing (RL-FTR) algorithm to tackle the routing issues caused by link and router faults in the mesh-based NoC architecture. The efficiency of the proposed RL-FTR algorithm is examined using System-C based cycle-accurate NoC simulator. Simulations are carried out by increasing the number of links and router faults in various sizes of mesh. Followed by simulations, real-time functioning of the proposed RL-FTR algorithm is observed using the FPGA implementation. Results of the simulation and hardware shows that the proposed RL-FTR algorithm provides an optimal routing path from the source router to the destination router.https://ieeexplore.ieee.org/document/9760423/Fault-toleranceFPGAnetwork-on-chipreinforcement learningrouting
spellingShingle Samala Jagadheesh
P. Veda Bhanu
J. Soumya
Linga Reddy Cenkeramaddi
Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA Implementation
IEEE Access
Fault-tolerance
FPGA
network-on-chip
reinforcement learning
routing
title Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA Implementation
title_full Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA Implementation
title_fullStr Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA Implementation
title_full_unstemmed Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA Implementation
title_short Reinforcement Learning Based Fault-Tolerant Routing Algorithm for Mesh Based NoC and Its FPGA Implementation
title_sort reinforcement learning based fault tolerant routing algorithm for mesh based noc and its fpga implementation
topic Fault-tolerance
FPGA
network-on-chip
reinforcement learning
routing
url https://ieeexplore.ieee.org/document/9760423/
work_keys_str_mv AT samalajagadheesh reinforcementlearningbasedfaulttolerantroutingalgorithmformeshbasednocanditsfpgaimplementation
AT pvedabhanu reinforcementlearningbasedfaulttolerantroutingalgorithmformeshbasednocanditsfpgaimplementation
AT jsoumya reinforcementlearningbasedfaulttolerantroutingalgorithmformeshbasednocanditsfpgaimplementation
AT lingareddycenkeramaddi reinforcementlearningbasedfaulttolerantroutingalgorithmformeshbasednocanditsfpgaimplementation