A hybrid approach for latency and battery lifetime optimization in IoT devices through offloading and CNN learning

dc.authoridHeidari, Arash/0000-0003-4279-8551
dc.authorwosidHeidari, Arash/AAK-9761-2021
dc.contributor.authorHeidari, Arash
dc.contributor.authorNavimipour, Nima Jafari
dc.contributor.authorJamali, Mohammad Ali Jabraeil
dc.contributor.authorAkbarpour, Shahin
dc.date.accessioned2023-10-19T15:11:41Z
dc.date.available2023-10-19T15:11:41Z
dc.date.issued2023
dc.department-temp[Heidari, Arash] Islamic Azad Univ, Dept Comp Engn, Tabriz Branch, Tabriz, Iran; [Heidari, Arash; Jamali, Mohammad Ali Jabraeil; Akbarpour, Shahin] Islamic Azad Univ, Dept Comp Engn, Shabestar Branch, Shabestar, Iran; [Navimipour, Nima Jafari] Kadir Has Univ, Dept Comp Engn, Istanbul, Turkiye; [Navimipour, Nima Jafari] Natl Yunlin Univ Sci & Technol, Future Technol Res Ctr, Touliu 64002, Yunlin, Taiwanen_US
dc.description.abstractOffloading assists in overcoming the resource constraints of specific elements, making it one of the primary technical enablers of the Internet of Things (IoT). IoT devices with low battery capacities can use the edge to offload some of the operations, which can significantly reduce latency and lengthen battery lifetime. Due to their restricted battery capacity, deep learning (DL) techniques are more energy-intensive to utilize in IoT devices. Because many IoT devices lack such modules, numerous research employed energy harvester modules that are not available to IoT devices in real-world circumstances. Using the Markov Decision Process (MDP), we describe the offloading problem in this study. Next, to facilitate partial offloading in IoT devices, we develop a Deep Reinforcement learning (DRL) method that can efficiently learn the policy by adjusting to network dynamics. Convolutional Neural Network (CNN) is then offered and implemented on Mobile Edge Computing (MEC) devices to expedite learning. These two techniques operate together to offer the proper offloading approach throughout the length of the system's operation. Moreover, transfer learning was employed to initialize the Qtable values, which increased the system's effectiveness. The simulation in this article, which employed Cooja and TensorFlow, revealed that the strategy outperformed five benchmarks in terms of latency by 4.1%, IoT device efficiency by 2.9%, energy utilization by 3.6%, and job failure rate by 2.6% on average.en_US
dc.identifier.citation23
dc.identifier.doi10.1016/j.suscom.2023.100899en_US
dc.identifier.issn2210-5379
dc.identifier.issn2210-5387
dc.identifier.scopus2-s2.0-85166020565en_US
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.suscom.2023.100899
dc.identifier.urihttps://hdl.handle.net/20.500.12469/5166
dc.identifier.volume39en_US
dc.identifier.wosWOS:001061194900001en_US
dc.identifier.wosqualityQ1
dc.khas20231019-WoSen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofSustainable Computing-Informatics & Systemsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectOffloadingen_US
dc.subjectConvolutional neural networken_US
dc.subjectIoTen_US
dc.subjectEnergy utilizationen_US
dc.subjectModelEn_Us
dc.subjectEdgeen_US
dc.subjectDeep reinforcement learningen_US
dc.subjectModel
dc.subjectMarkov decision processen_US
dc.titleA hybrid approach for latency and battery lifetime optimization in IoT devices through offloading and CNN learningen_US
dc.typeArticleen_US
dspace.entity.typePublication

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
5166.pdf
Size:
5.52 MB
Format:
Adobe Portable Document Format
Description:
Tam Metin / Full Text