IFS-RL: An intelligent forwarding strategy based on reinforcement learning in named-data networking

Yi Zhang, Kuai Xu, Bo Bai, Kai Lei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Named-Data Networking (NDN) is a new communication paradigm where network primitives are based on named-data rather than host identifiers. Compared with IP, NDN has a unique feature that forwarding plane enables each router to select the next forwarding hop independently without relying on routing. Therefore, forwarding strategies play a significant role for adaptive and efficient data transmission in NDN. Most of the existing forwarding strategies use fixed control rules based on simplified or inaccurate models of the deployment environment. As a result, existing schemes inevitably fail to achieve optimal performance across a broad set of network conditions and application demands. In this paper, We propose IFS-RL, an intelligent forwarding strategy based on reinforcement learning. IFS-RL trains a neural network model which chooses appropriate interfaces for the forwarding of Interest based on observations collected by routing node. Not relying on pre-programmed models, IFS-RL learns to make decisions solely through observations of the resulting performance of past decisions. Therefore, IFS-RL can implement intelligent forwrarding which adapt to a wide range of network conditions. Besides, we also researches the learning granularity and the enhancement for network topology change. We compare IFS-RL to state-of-the-art forwarding strategies in ndnSIM. Experimental results show that IFS-RL can achieve higher throughput and lower packet drop rates.

Original languageEnglish (US)
Title of host publicationNetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018
PublisherAssociation for Computing Machinery, Inc
Pages54-59
Number of pages6
ISBN (Electronic)9781450359115
DOIs
StatePublished - Aug 7 2018
Event2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018 - Budapest, Hungary
Duration: Aug 24 2018 → …

Other

Other2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018
CountryHungary
CityBudapest
Period8/24/18 → …

Fingerprint

Reinforcement learning
Routers
Data communication systems
Throughput
Topology
Neural networks
Communication

Keywords

  • Forwarding strategy
  • Learning granularity
  • Named-Data Networking
  • Network topology
  • Reinforcement learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Zhang, Y., Xu, K., Bai, B., & Lei, K. (2018). IFS-RL: An intelligent forwarding strategy based on reinforcement learning in named-data networking. In NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018 (pp. 54-59). Association for Computing Machinery, Inc. https://doi.org/10.1145/3229543.3229547

IFS-RL : An intelligent forwarding strategy based on reinforcement learning in named-data networking. / Zhang, Yi; Xu, Kuai; Bai, Bo; Lei, Kai.

NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. Association for Computing Machinery, Inc, 2018. p. 54-59.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, Y, Xu, K, Bai, B & Lei, K 2018, IFS-RL: An intelligent forwarding strategy based on reinforcement learning in named-data networking. in NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. Association for Computing Machinery, Inc, pp. 54-59, 2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018, Budapest, Hungary, 8/24/18. https://doi.org/10.1145/3229543.3229547
Zhang Y, Xu K, Bai B, Lei K. IFS-RL: An intelligent forwarding strategy based on reinforcement learning in named-data networking. In NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. Association for Computing Machinery, Inc. 2018. p. 54-59 https://doi.org/10.1145/3229543.3229547
Zhang, Yi ; Xu, Kuai ; Bai, Bo ; Lei, Kai. / IFS-RL : An intelligent forwarding strategy based on reinforcement learning in named-data networking. NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. Association for Computing Machinery, Inc, 2018. pp. 54-59
@inproceedings{44384d93e3b04d15a37257ce60606c85,
title = "IFS-RL: An intelligent forwarding strategy based on reinforcement learning in named-data networking",
abstract = "Named-Data Networking (NDN) is a new communication paradigm where network primitives are based on named-data rather than host identifiers. Compared with IP, NDN has a unique feature that forwarding plane enables each router to select the next forwarding hop independently without relying on routing. Therefore, forwarding strategies play a significant role for adaptive and efficient data transmission in NDN. Most of the existing forwarding strategies use fixed control rules based on simplified or inaccurate models of the deployment environment. As a result, existing schemes inevitably fail to achieve optimal performance across a broad set of network conditions and application demands. In this paper, We propose IFS-RL, an intelligent forwarding strategy based on reinforcement learning. IFS-RL trains a neural network model which chooses appropriate interfaces for the forwarding of Interest based on observations collected by routing node. Not relying on pre-programmed models, IFS-RL learns to make decisions solely through observations of the resulting performance of past decisions. Therefore, IFS-RL can implement intelligent forwrarding which adapt to a wide range of network conditions. Besides, we also researches the learning granularity and the enhancement for network topology change. We compare IFS-RL to state-of-the-art forwarding strategies in ndnSIM. Experimental results show that IFS-RL can achieve higher throughput and lower packet drop rates.",
keywords = "Forwarding strategy, Learning granularity, Named-Data Networking, Network topology, Reinforcement learning",
author = "Yi Zhang and Kuai Xu and Bo Bai and Kai Lei",
year = "2018",
month = "8",
day = "7",
doi = "10.1145/3229543.3229547",
language = "English (US)",
pages = "54--59",
booktitle = "NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - IFS-RL

T2 - An intelligent forwarding strategy based on reinforcement learning in named-data networking

AU - Zhang, Yi

AU - Xu, Kuai

AU - Bai, Bo

AU - Lei, Kai

PY - 2018/8/7

Y1 - 2018/8/7

N2 - Named-Data Networking (NDN) is a new communication paradigm where network primitives are based on named-data rather than host identifiers. Compared with IP, NDN has a unique feature that forwarding plane enables each router to select the next forwarding hop independently without relying on routing. Therefore, forwarding strategies play a significant role for adaptive and efficient data transmission in NDN. Most of the existing forwarding strategies use fixed control rules based on simplified or inaccurate models of the deployment environment. As a result, existing schemes inevitably fail to achieve optimal performance across a broad set of network conditions and application demands. In this paper, We propose IFS-RL, an intelligent forwarding strategy based on reinforcement learning. IFS-RL trains a neural network model which chooses appropriate interfaces for the forwarding of Interest based on observations collected by routing node. Not relying on pre-programmed models, IFS-RL learns to make decisions solely through observations of the resulting performance of past decisions. Therefore, IFS-RL can implement intelligent forwrarding which adapt to a wide range of network conditions. Besides, we also researches the learning granularity and the enhancement for network topology change. We compare IFS-RL to state-of-the-art forwarding strategies in ndnSIM. Experimental results show that IFS-RL can achieve higher throughput and lower packet drop rates.

AB - Named-Data Networking (NDN) is a new communication paradigm where network primitives are based on named-data rather than host identifiers. Compared with IP, NDN has a unique feature that forwarding plane enables each router to select the next forwarding hop independently without relying on routing. Therefore, forwarding strategies play a significant role for adaptive and efficient data transmission in NDN. Most of the existing forwarding strategies use fixed control rules based on simplified or inaccurate models of the deployment environment. As a result, existing schemes inevitably fail to achieve optimal performance across a broad set of network conditions and application demands. In this paper, We propose IFS-RL, an intelligent forwarding strategy based on reinforcement learning. IFS-RL trains a neural network model which chooses appropriate interfaces for the forwarding of Interest based on observations collected by routing node. Not relying on pre-programmed models, IFS-RL learns to make decisions solely through observations of the resulting performance of past decisions. Therefore, IFS-RL can implement intelligent forwrarding which adapt to a wide range of network conditions. Besides, we also researches the learning granularity and the enhancement for network topology change. We compare IFS-RL to state-of-the-art forwarding strategies in ndnSIM. Experimental results show that IFS-RL can achieve higher throughput and lower packet drop rates.

KW - Forwarding strategy

KW - Learning granularity

KW - Named-Data Networking

KW - Network topology

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85056878340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056878340&partnerID=8YFLogxK

U2 - 10.1145/3229543.3229547

DO - 10.1145/3229543.3229547

M3 - Conference contribution

AN - SCOPUS:85056878340

SP - 54

EP - 59

BT - NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018

PB - Association for Computing Machinery, Inc

ER -