University of Surrey

Test tubes in the lab Research in the ATI Dance Research

A Bio-Inspired Self-learning Coevolutionary Dynamic Multiobjective Optimization Algorithm for Internet of Things Services

Yang, Zhen, Jin, Yaochu and Hao, Kuangrong (2018) A Bio-Inspired Self-learning Coevolutionary Dynamic Multiobjective Optimization Algorithm for Internet of Things Services IEEE Transactions on Evolutionary Computation.

[img]
Preview
Text
A Bio-Inspired Self-learning Coevolutionary Dynamic Multiobjective Optimization Algorithm for Internet of Things Services.pdf - Accepted version Manuscript

Download (1MB) | Preview

Abstract

The ultimate goal of the Internet of Things (IoT) is to provide ubiquitous services. To achieve this goal, many challenges remain to be addressed. Inspired from the cooperative mechanisms between multiple systems in the human being, this paper proposes a bio-inspired self-learning coevolutionary algorithm (BSCA) for dynamic multiobjective optimization of IoT services to reduce energy consumption and service time. BSCA consists of three layers. The first layer is composed of multiple subpopulations evolving cooperatively to obtain diverse Pareto fronts. Based on the solutions obtained by the first layer, the second layer aims to further increase the diversity of solutions. The third layer refines the solutions found in the second layer by adopting an adaptive gradient refinement search strategy and dynamic optimization method to cope with changing concurrent multiple service requests, thereby effectively improving the accuracy of solutions. Experiments on agricultural IoT services in the presence of dynamic requests under different distributions are performed based on two service-providing strategies, i.e., single service and collaborative service. The simulation results demonstrate that BSCA performs better than four existing algorithms on IoT services, in particular for high-dimensional problems.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
NameEmailORCID
Yang, Zhen
Jin, YaochuYaochu.Jin@surrey.ac.uk
Hao, Kuangrong
Date : 9 November 2018
DOI : 10.1109/TEVC.2018.2880458
Copyright Disclaimer : © 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information
Uncontrolled Keywords : Coevolutionary optimization; Dynamic multiobjective optimization; Internet of Things (IoT); Self-learning; Services provision
Depositing User : Clive Harris
Date Deposited : 13 Nov 2018 11:36
Last Modified : 13 Nov 2018 11:36
URI: http://epubs.surrey.ac.uk/id/eprint/849862

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800