Abstract

Scalability is essential for next generation blockchain technology to integrate with large mobile networks like Internet of Things (IoT). The IOTA distributed ledger protocol has combined transaction generation and verification to address this, but at the expense of increased reliance on connectivity to resolve conflicts with a novel ledger data structure. Intelligent Ledger Construction (ILC) was proposed as an auditable lightweight reinforcement-learning scheme to address this constraint with proposal of local conflict resolution with machine-learning classification. This effort presents an improved reliability reward model to enhance training for ILC and further reduce adversarial gaming and resource usage. Testing this revision in an idealistic setting showed vast improvement in transaction throughput efficiency and delay while also reducing unapproved transactions by 60% in a realistic IoT-like network. Future work will improve auditability of the underlying intelligence for stronger security.

Department(s)

Electrical and Computer Engineering

Second Department

Computer Science

Comments

National Science Foundation, Grant OAC-1919789

Keywords and Phrases

Blockchain and Machine Learning/Artificial Intelligence; Blockchain for Internet of Things; IOTA

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2023 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Jan 2023

Download

Full Text Link

Share

 
COinS