DQN-Based Optimization Framework for Secure Sharded Blockchain Systems

Jusik Yun; Yunyeong Goh; Jong Moon Chung

doi:10.1109/JIOT.2020.3006896

DQN-Based Optimization Framework for Secure Sharded Blockchain Systems

Jusik Yun, Yunyeong Goh, Jong Moon Chung

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

Abstract

High levels of scalability and reliability are needed to support the massive Internet-of-Things (IoT) services. In particular, blockchains can be effectively used to safely manage data from large-scale IoT networks. However, current blockchain systems have low transactions per second (TPS) rates and scalability limitations that make them unsuitable. To solve the above issues, this article proposes a deep Q network shard-based blockchain (DQNSB) scheme that dynamically finds the optimal throughput configuration. In this article, a novel analysis of sharded blockchain latency and security-level characterization is provided. Using the analysis equations, the DQNSB scheme estimates the level of maliciousness and adapts the blockchain parameters to enhance the security level considering the amount of malicious attacks on the consensus process. To achieve this purpose, deep reinforcement learning (DRL) agents are trained to find the optimal system parameters in response to the network status, and adaptively optimizes the system throughput and security level. The simulation results show that the proposed DQNSB scheme provides a much higher TPS than the existing DRL-enabled blockchain technology while maintaining a high security level.

Original language	English
Article number	9133069
Pages (from-to)	708-722
Number of pages	15
Journal	IEEE Internet of Things Journal
Volume	8
Issue number	2
DOIs	https://doi.org/10.1109/JIOT.2020.3006896
Publication status	Published - 2021 Jan 15

Bibliographical note

Funding Information:
Manuscript received March 27, 2020; revised May 29, 2020; accepted June 30, 2020. Date of publication July 3, 2020; date of current version January 7, 2021. This work was supported by the Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center Support Program supervised by the Institute for Information and communications Technology Planning and Evaluation (IITP) under Grant IITP-2020-2018-0-01799. (Corresponding author: Jong-Moon Chung.) The authors are with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, South Korea (e-mail: awp212@yonsei.ac.kr; rhdbsdud@yonsei.ac.kr; jmc@yonsei.ac.kr). Digital Object Identifier 10.1109/JIOT.2020.3006896

Publisher Copyright:
© 2014 IEEE.

All Science Journal Classification (ASJC) codes

Signal Processing
Information Systems
Hardware and Architecture
Computer Science Applications
Computer Networks and Communications

Access to Document

10.1109/JIOT.2020.3006896

Cite this

@article{a270b4692a0749609b181cab70c13e36,

title = "DQN-Based Optimization Framework for Secure Sharded Blockchain Systems",

abstract = "High levels of scalability and reliability are needed to support the massive Internet-of-Things (IoT) services. In particular, blockchains can be effectively used to safely manage data from large-scale IoT networks. However, current blockchain systems have low transactions per second (TPS) rates and scalability limitations that make them unsuitable. To solve the above issues, this article proposes a deep Q network shard-based blockchain (DQNSB) scheme that dynamically finds the optimal throughput configuration. In this article, a novel analysis of sharded blockchain latency and security-level characterization is provided. Using the analysis equations, the DQNSB scheme estimates the level of maliciousness and adapts the blockchain parameters to enhance the security level considering the amount of malicious attacks on the consensus process. To achieve this purpose, deep reinforcement learning (DRL) agents are trained to find the optimal system parameters in response to the network status, and adaptively optimizes the system throughput and security level. The simulation results show that the proposed DQNSB scheme provides a much higher TPS than the existing DRL-enabled blockchain technology while maintaining a high security level.",

author = "Jusik Yun and Yunyeong Goh and Chung, {Jong Moon}",

note = "Funding Information: Manuscript received March 27, 2020; revised May 29, 2020; accepted June 30, 2020. Date of publication July 3, 2020; date of current version January 7, 2021. This work was supported by the Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center Support Program supervised by the Institute for Information and communications Technology Planning and Evaluation (IITP) under Grant IITP-2020-2018-0-01799. (Corresponding author: Jong-Moon Chung.) The authors are with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, South Korea (e-mail: awp212@yonsei.ac.kr; rhdbsdud@yonsei.ac.kr; jmc@yonsei.ac.kr). Digital Object Identifier 10.1109/JIOT.2020.3006896 Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2021",

month = jan,

day = "15",

doi = "10.1109/JIOT.2020.3006896",

language = "English",

volume = "8",

pages = "708--722",

journal = "IEEE Internet of Things Journal",

issn = "2327-4662",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - DQN-Based Optimization Framework for Secure Sharded Blockchain Systems

AU - Yun, Jusik

AU - Goh, Yunyeong

AU - Chung, Jong Moon

N1 - Funding Information: Manuscript received March 27, 2020; revised May 29, 2020; accepted June 30, 2020. Date of publication July 3, 2020; date of current version January 7, 2021. This work was supported by the Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center Support Program supervised by the Institute for Information and communications Technology Planning and Evaluation (IITP) under Grant IITP-2020-2018-0-01799. (Corresponding author: Jong-Moon Chung.) The authors are with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, South Korea (e-mail: awp212@yonsei.ac.kr; rhdbsdud@yonsei.ac.kr; jmc@yonsei.ac.kr). Digital Object Identifier 10.1109/JIOT.2020.3006896 Publisher Copyright: © 2014 IEEE.

PY - 2021/1/15

Y1 - 2021/1/15

N2 - High levels of scalability and reliability are needed to support the massive Internet-of-Things (IoT) services. In particular, blockchains can be effectively used to safely manage data from large-scale IoT networks. However, current blockchain systems have low transactions per second (TPS) rates and scalability limitations that make them unsuitable. To solve the above issues, this article proposes a deep Q network shard-based blockchain (DQNSB) scheme that dynamically finds the optimal throughput configuration. In this article, a novel analysis of sharded blockchain latency and security-level characterization is provided. Using the analysis equations, the DQNSB scheme estimates the level of maliciousness and adapts the blockchain parameters to enhance the security level considering the amount of malicious attacks on the consensus process. To achieve this purpose, deep reinforcement learning (DRL) agents are trained to find the optimal system parameters in response to the network status, and adaptively optimizes the system throughput and security level. The simulation results show that the proposed DQNSB scheme provides a much higher TPS than the existing DRL-enabled blockchain technology while maintaining a high security level.

AB - High levels of scalability and reliability are needed to support the massive Internet-of-Things (IoT) services. In particular, blockchains can be effectively used to safely manage data from large-scale IoT networks. However, current blockchain systems have low transactions per second (TPS) rates and scalability limitations that make them unsuitable. To solve the above issues, this article proposes a deep Q network shard-based blockchain (DQNSB) scheme that dynamically finds the optimal throughput configuration. In this article, a novel analysis of sharded blockchain latency and security-level characterization is provided. Using the analysis equations, the DQNSB scheme estimates the level of maliciousness and adapts the blockchain parameters to enhance the security level considering the amount of malicious attacks on the consensus process. To achieve this purpose, deep reinforcement learning (DRL) agents are trained to find the optimal system parameters in response to the network status, and adaptively optimizes the system throughput and security level. The simulation results show that the proposed DQNSB scheme provides a much higher TPS than the existing DRL-enabled blockchain technology while maintaining a high security level.

UR - http://www.scopus.com/inward/record.url?scp=85097725901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85097725901&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2020.3006896

DO - 10.1109/JIOT.2020.3006896

M3 - Article

AN - SCOPUS:85097725901

VL - 8

SP - 708

EP - 722

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

IS - 2

M1 - 9133069

ER -

DQN-Based Optimization Framework for Secure Sharded Blockchain Systems

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this