dc.contributor.author | Chen, X | |
dc.contributor.author | Zhang, J | |
dc.contributor.author | Lin, B | |
dc.contributor.author | Chen, Z | |
dc.contributor.author | Wolter, K | |
dc.contributor.author | Min, G | |
dc.date.accessioned | 2021-09-21T08:24:58Z | |
dc.date.issued | 2021-07-27 | |
dc.description.abstract | Deep Neural Networks (DNNs) have become an essential and important supporting technology for smart Internet-of-Things (IoT) systems. Due to the high computational costs of large-scale DNNs, it might be infeasible to directly deploy them in energy-constrained IoT devices. Through offloading computation-intensive tasks to the cloud or edges, the computation offloading technology offers a feasible solution to execute DNNs. However, energy-efficient offloading for DNN based smart IoT systems with deadline constraints in the cloud-edge environments is still an open challenge. To address this challenge, we first design a new system energy consumption model, which takes into account the runtime, switching, and computing energy consumption of all participating servers (from both the cloud and edge) and IoT devices. Next, a novel energy-efficient offloading strategy based on a Self-adaptive Particle Swarm Optimization algorithm using the Genetic Algorithm operators (SPSO-GA) is proposed. This new strategy can efficiently make offloading decisions for DNN layers with layer partition operations, which can lessen the encoding dimension and improve the execution time of SPSO-GA. Simulation results demonstrate that the proposed strategy can significantly reduce energy consumption compared to other classic methods. | en_GB |
dc.description.sponsorship | Natural Science Foundation of Fujian Province | en_GB |
dc.description.sponsorship | Young and Middle-aged Teacher Education Foundation of Fujian Province | en_GB |
dc.identifier.citation | Vol. 33 (3), pp. 683 - 697 | en_GB |
dc.identifier.doi | 10.1109/TPDS.2021.3100298 | |
dc.identifier.grantnumber | 2020J06014 | en_GB |
dc.identifier.grantnumber | 2019J01286 | en_GB |
dc.identifier.grantnumber | JT180098 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/127158 | |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers | en_GB |
dc.rights | © 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
See https://www.ieee.org/publications/rights/index.html for more information. | en_GB |
dc.subject | Energy consumption | en_GB |
dc.subject | Internet of Things | en_GB |
dc.subject | Cloud computing | en_GB |
dc.subject | Servers | en_GB |
dc.subject | Data communication | en_GB |
dc.subject | Quality of service | en_GB |
dc.subject | Task analysis | en_GB |
dc.subject | Cloud-edge computing | en_GB |
dc.subject | IoT systems | en_GB |
dc.subject | energy-efficient offloading | en_GB |
dc.subject | deep neural network | en_GB |
dc.subject | particle swarm optimization | en_GB |
dc.title | Energy-Efficient Offloading for DNN-Based Smart IoT Systems in Cloud-Edge Environments | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2021-09-21T08:24:58Z | |
dc.identifier.issn | 1045-9219 | |
dc.description | This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record. | en_GB |
dc.identifier.journal | IEEE Transactions on Parallel and Distributed Systems | en_GB |
dc.rights.uri | http://www.rioxx.net/licenses/all-rights-reserved | en_GB |
dcterms.dateAccepted | 2021-07-20 | |
rioxxterms.funder | National Natural Science Foundation of China | en_GB |
rioxxterms.identifier.project | 62072108 | en_GB |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2022-03-01 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2021-09-21T08:21:08Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2021-09-21T08:25:01Z | |
refterms.panel | B | en_GB |
rioxxterms.funder.project | 17be3531-a823-4e9f-b93d-7b55239afd12 | en_GB |