Trust and energy aware routing algorithm for Internet of Things networks

The expansion in the Internet of Things (IoT) has led to a shift towards smart technologies. IoT focuses on integrating networks to facilitate smooth services to humans. The interface between the mobility patterns and the routing protocols is considered to increase the performance of the network. Ho...

Full description

Saved in:
Bibliographic Details
Published in:International journal of numerical modelling Vol. 34; no. 4
Main Authors: Mujeeb, Shaik Mohammed, Sam, Rachapudy Praveen, Madhavi, Kasa
Format: Journal Article
Language:English
Published: Chichester, UK John Wiley & Sons, Inc 01.07.2021
Wiley Subscription Services, Inc
Subjects:
Adaptive algorithms
Algorithms
Belief networks
big data classification
Classification
energy efficiency
Energy harvesting
Internet of Things
Machine learning
Optimization
routing
Routing (telecommunications)
trust
ISSN:0894-3370, 1099-1204
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The expansion in the Internet of Things (IoT) has led to a shift towards smart technologies. IoT focuses on integrating networks to facilitate smooth services to humans. The interface between the mobility patterns and the routing protocols is considered to increase the performance of the network. However, incorporating security in the IoT network has been a major issue that continues to nurture with increasing IoT devices. This article addresses this issue by developing a novel technique, namely energy harvesting trust aware routing algorithm (EHTARA) for initiating a trust‐based routing model in the IoT network in the presence of ambient energy sources. The cost metric is newly devised by considering energy, distance, and trust parameters for determining the best path. At the base station, big data classification is performed using the adaptive exponential‐Bat (adaptive E‐Bat) algorithm based deep belief network (DBN). The training of DBN is performed using the adaptive E‐Bat algorithm, which is the combination of adaptive concept, exponential weighted moving average (EWMA), and Bat algorithm (BA). Here, the optimization‐based map‐reduce framework helps to deal with the imbalanced data by adapting the deep learning in classification. The proposed EHTARA outperformed other methods with a maximal energy of 0.927.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0894-3370
1099-1204
DOI:10.1002/jnm.2858