research-article

Blockchain-based edge computing for deep neural network applications

Authors:

Jae-Yun Kim,

Soo-Mook MoonAuthors Info & Claims

INTESA '18: Proceedings of the Workshop on INTelligent Embedded Systems Architectures and Applications

Pages 53 - 55

https://doi.org/10.1145/3285017.3285027

Published: 04 October 2018 Publication History

Get Access

Abstract

Deep neural network (DNN) applications require heavy computations, so an embedded device with limited hardware such as an IoT device cannot run the apps by itself. One solution is to offload DNN computations from the client device to nearby edge servers [1] to request an execution of the DNN computations with their powerful hardware. However, there are several issues with the solution. One is an availability issue that how we can provide the edge server with some incentives to run the client' apps. The other is a scalability issue that how we can use more servers when there are more DNN requests. Finally, there is an integrity issue that how the client can trust the result coming from anonymous edge servers. We think the blockchain technology can solve these issues to make edge computing more practical. This paper proposes a novel architecture for DNN edge computing based on the blockchain technology. Existing blockchains such as Ethereum do not support execution of a complex program, so we propose a modified blockchain structure and protocol to overcome the limitation.

References

[1]

Shi, Weisong, et al. Edge computing: Vision and challenges. IEEE Internet of Things Journal, 2016, 3.5: 637--646

Google Scholar

[2]

Kumar, Karthik, et al. A survey of computation offloading for mobile systems. Mobile Networks and Applications, 2013, 18.1: 129--140.

Digital Library

Google Scholar

[3]

Nakamoto, Satoshi. Bitcoin: A peer-to-peer electronic cash system. 2008.

Google Scholar

[4]

Rivest, Ronald L.; SHAMIR, Adi; ADLEMAN, Leonard. A method for obtaining digital signatures and public-key cryptosystems. Communications of the ACM, 1978, 21.2: 120--126.

Digital Library

Google Scholar

[5]

Buterin, Vitalik, et al. A next-generation smart contract and decentralized application platform. white paper, 2014.

Google Scholar

[6]

Wood, Gavin. Ethereum: A secure decentralised generalised transaction ledger. Ethereum project yellow paper, 2014, 151: 1--32.

Google Scholar

[7]

https://github.com/justadudewhohacks/opencv4nodejs, July, 2018

Google Scholar

Cited By

View all

Djolev DLazarova MNakov O(2023)Blockchain Based Trusted Distributed Machine Learning for Credit Scoring2023 International Scientific Conference on Computer Science (COMSCI)10.1109/COMSCI59259.2023.10315878(1-5)Online publication date: 18-Sep-2023
https://doi.org/10.1109/COMSCI59259.2023.10315878
Li TFang YLu YYang JJian ZWan ZLi Y(2022)SmartVM: A Smart Contract Virtual Machine for Fast On-Chain DNN ComputationsIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2022.317740533:12(4100-4116)Online publication date: 1-Dec-2022
https://doi.org/10.1109/TPDS.2022.3177405
Wang XRen XQiu CXiong ZYao HLeung V(2022)Integrating Edge Intelligence and Blockchain: What, Why, and HowIEEE Communications Surveys & Tutorials10.1109/COMST.2022.318996224:4(2193-2229)Online publication date: Dec-2023
https://doi.org/10.1109/COMST.2022.3189962
Show More Cited By

Recommendations

CoopEdge: A Decentralized Blockchain-based Platform for Cooperative Edge Computing
WWW '21: Proceedings of the Web Conference 2021

Edge computing (EC) has recently emerged as a novel computing paradigm that offers users low-latency services. Suffering from constrained computing resources due to their limited physical sizes, edge servers cannot always handle all the incoming ...
Blockchain based resource allocation in cloud and distributed edge computing: A survey
Abstract
Cloud computing and distributed edge computing provide computing resources to meet the surging demands for computing caused by developments in technologies such as the Internet of Things (IoT) and Mobile communication (5G). Centralized ...
Highlights
- A discussion on resource allocation in cloud and edge computing is provided.
- ...
Enhanced Partitioning of DNN Layers for Uploading from Mobile Devices to Edge Servers
EMDL '19: The 3rd International Workshop on Deep Learning for Mobile Systems and Applications

Offloading computations to servers is a promising method for resource constrained devices to run deep neural network (DNN). It often requires pre-installing DNN models at the server, which is not a valid assumption in an edge server environment where a ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

INTESA '18: Proceedings of the Workshop on INTelligent Embedded Systems Architectures and Applications

October 2018

62 pages

ISBN:9781450365987

DOI:10.1145/3285017

General Chair:
Maurizio Martina
POLITO, IT
,
Program Chair:
William Fornanciari
POLIMI, IT

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 04 October 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

National Research Foundation of Korea

Conference

INTESA

INTESA: INTelligent Embedded Systems Architectures and Applications

October 4, 2018

Turin, Italy

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
575
Total Downloads

Downloads (Last 12 months)13
Downloads (Last 6 weeks)2

Reflects downloads up to 19 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Djolev DLazarova MNakov O(2023)Blockchain Based Trusted Distributed Machine Learning for Credit Scoring2023 International Scientific Conference on Computer Science (COMSCI)10.1109/COMSCI59259.2023.10315878(1-5)Online publication date: 18-Sep-2023
https://doi.org/10.1109/COMSCI59259.2023.10315878
Li TFang YLu YYang JJian ZWan ZLi Y(2022)SmartVM: A Smart Contract Virtual Machine for Fast On-Chain DNN ComputationsIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2022.317740533:12(4100-4116)Online publication date: 1-Dec-2022
https://doi.org/10.1109/TPDS.2022.3177405
Wang XRen XQiu CXiong ZYao HLeung V(2022)Integrating Edge Intelligence and Blockchain: What, Why, and HowIEEE Communications Surveys & Tutorials10.1109/COMST.2022.318996224:4(2193-2229)Online publication date: Dec-2023
https://doi.org/10.1109/COMST.2022.3189962
Wang XQiu CRen XXiong ZLeung VNiyato DWang XQiu CRen XXiong ZLeung VNiyato D(2022)Blockchain Driven Edge IntelligenceIntegrating Edge Intelligence and Blockchain10.1007/978-3-031-10186-1_4(43-78)Online publication date: 30-Jun-2022
https://doi.org/10.1007/978-3-031-10186-1_4
Zhang ZGuo BShen YLi CSuo XSu H(2021)Nakamoto Consensus to Accelerate Supervised Classification Algorithms for Multiparty ComputingSecurity and Communication Networks10.1155/2021/66294332021Online publication date: 1-Jan-2021
https://dl.acm.org/doi/10.1155/2021/6629433
Wang RLuo MWen YWang LRaymond Choo KHe D(2021)The Applications of Blockchain in Artificial IntelligenceSecurity and Communication Networks10.1155/2021/61262472021Online publication date: 1-Jan-2021
https://dl.acm.org/doi/10.1155/2021/6126247
Murshed MMurphy CHou DKhan NAnanthanarayanan GHussain F(2021)Machine Learning at the Network Edge: A SurveyACM Computing Surveys10.1145/346902954:8(1-37)Online publication date: 4-Oct-2021
https://dl.acm.org/doi/10.1145/3469029
Fan YWang LWu WDu D(2021)Cloud/Edge Computing Resource Allocation and Pricing for Mobile Blockchain: An Iterative Greedy and Search ApproachIEEE Transactions on Computational Social Systems10.1109/TCSS.2021.30491528:2(451-463)Online publication date: Apr-2021
https://doi.org/10.1109/TCSS.2021.3049152
Lin YGao ZXiao KWang QMo ZYang YRui LGuo HWang D(2021)A Model Training Mechanism based on Onchain and Offchain Collaboration for Edge ComputingICC 2021 - IEEE International Conference on Communications10.1109/ICC42927.2021.9500604(1-6)Online publication date: Jun-2021
https://doi.org/10.1109/ICC42927.2021.9500604
Malik NAlkhatib KSun YKnight EJararweh Y(2021)A comprehensive review of blockchain applications in industrial Internet of Things and supply chain systemsApplied Stochastic Models in Business and Industry10.1002/asmb.262137:3(391-412)Online publication date: 3-May-2021
https://doi.org/10.1002/asmb.2621
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Recommendations

CoopEdge: A Decentralized Blockchain-based Platform for Cooperative Edge Computing

Blockchain based resource allocation in cloud and distributed edge computing: A survey

Enhanced Partitioning of DNN Layers for Uploading from Mobile Devices to Edge Servers