product iamge

Wireless Sensor Networks: Evolutionary Algorithms for Optimizing Performance

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Download
Search on Amazon

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

Wireless Sensor Networks: Evolutionary Algorithms for Optimizing Performance provides an integrative overview of bio-inspired algorithms and their applications in the area of Wireless Sensor Networks (WSN). Along with the usage of the WSN, the number of risks and challenges occurs while deploying any WSN. Therefore, to defeat these challenges some of the bio-inspired algorithms are applied and discussed in this book.

Discussion includes a broad, integrated perspective on various challenges and issues in WSN and also impact of bio-inspired algorithms on the lifetime of the WSN. It creates interdisciplinary theory, concepts, definitions, models and findings involved in WSN and Bio-inspired algorithms making it an essential guide and reference. It includes various WSN examples making the book accessible to a broader interdisciplinary readership.

The book offers comprehensive coverage of the most essential topics, including:

  • Evolutionary algorithms

  • Swarm intelligence

  • Hybrid algorithms

  • Energy efficiency in WSN

  • Load balancing of gateways

  • Localization

  • Clustering and routing

  • Designing fitness functions according to the issues in WSN.

The book explains about practices of shuffled complex evolution algorithm, shuffled frog leaping algorithm, particle swarm optimization and dolphin swarm optimization to defeat various challenges in WSN. The author elucidates how we must transform our thinking, illuminating the benefits and opportunities offered by bio-inspired approaches to innovation and learning in the area of WSN. This book serves as a reference book for scientific investigators who shows an interest in evolutionary computation and swarm intelligence as well as issues and challenges in WSN.

Author(s): Damodar Reddy Edla, Mahesh Chowdary Kongara, Amruta Lipare, Venkatanareshbabu Kuppili, Kannadasan K
Publisher: CRC Press
Year: 2020

Language: English
Pages: 146
City: London

Cover
Half Title
Title Page
Copyright Page
Contents
Preface
Authors
1. Introduction
1.1 Introduction
1.2 Challenges in WSNs
1.3 Motivation
1.4 Objectives and contributions of the book
1.5 Resources used
1.6 Organization of the book
1.7 Conclusion
2. Literature Survey
2.1 Heuristic approaches
2.2 Meta-heuristic approaches
2.3 Localization-related work
2.4 Conclusion
3. Load Balancing of Gateways Using Shu ed Complex Evolution Algorithm
3.1 Introduction
3.2 Preliminaries
3.2.1 Energy model
3.2.2 An overview of shuffled complex evolution algorithm
3.3 Proposed load balancing algorithm
3.3.1 Individual representation
3.3.2 Initial population generation
3.3.3 Proposed novel fitness function
3.3.4 Sorting and partitioning of individuals
3.3.5 Parent selection
3.3.6 O spring generation
3.3.7 Sorting and shu ing
3.4 Results and discussion
3.4.1 Experimental setup
3.4.2 Number of sensor nodes vs energy consumed
3.4.3 Number of heavy loaded sensor nodes vs fitness
3.4.4 Number of generations vs fitness
3.4.5 First node die
3.4.6 Half of the nodes alive
3.4.7 First gateway die
3.4.8 Number of dead sensor nodes
3.5 Conclusion
4. Novel Fitness Function for SCE Algorithm Based Energy E ciency in WSN
4.1 Introduction
4.2 Proposed algorithm
4.2.1 Research contribution
4.2.2 Initial population generation
4.2.3 Proposed fitness function
4.2.4 Sorting and partitioning of complexes
4.2.5 Selection of parent and offspring generation
4.2.6 Relocation phase
4.2.7 Sorting and shuffling
4.3 Results and discussion
4.3.1 Experimental setup
4.3.2 Number of sensor nodes vs energy consumed
4.3.3 Number of heavy loaded sensor nodes vs fitness
4.3.4 Number of generations vs fitness
4.3.5 First node die
4.3.6 Half of the nodes alive
4.3.7 First gateway death
4.3.8 Number of dead sensor nodes
4.4 Conclusion
5. An E cient Load Balancing of Gateways Using Improved SFLA for WSNs
5.1 Introduction
5.2 Preliminaries
5.2.1 An overview of shuffled frog leaping algorithm
5.3 Proposed methodology
5.3.1 Individual representation
5.3.2 Initialization phase
5.3.3 Proposed tness function
5.3.4 Formation of memeplexes phase
5.3.5 Formation of sub-memeplexes phase
5.3.6 Offspring generation phase
5.3.7 Transfer phase
5.3.8 Convergence checking phase
5.3.9 Algorithm description
5.4 Results and discussion
5.4.1 Experimental setup
5.4.2 Number of sensor nodes versus energy consumed
5.4.3 Number of heavy loaded sensor nodes versus fitness
5.4.4 Number of generations versus fitness
5.4.5 First node die
5.4.6 Half of the nodes alive
5.4.7 First gateway death
5.4.8 Number of dead sensor nodes
5.5 Conclusion
6. SCE-PSO Based Clustering Technique for Load Balancing in WSN
6.1 Introduction
6.2 Preliminaries
6.2.1 Terminologies
6.3 Overview of SCE-PSO
6.3.1 Background of SCE-PSO
6.3.2 Background of PSO
6.4 Proposed SCE-PSO based clustering
6.4.1 Random particle generation
6.4.2 Evaluation of fitness function
6.4.3 Particle sorting and partitioning
6.4.4 Complex evolution
6.4.5 Complexes shuffling
6.4.6 Convergence checking
6.5 Results and discussion
6.5.1 Performance analysis
6.5.1.1 Network lifetime vs number of sensor nodes
6.5.1.2 Total energy utilization vs number of sensor nodes
6.5.1.3 First gateway that dissolves its energy and half of the gateways die
6.6 Conclusion
7. PSO Based Routing with Novel Fitness Function for Improving Lifetime of WSN
7.1 Introduction
7.2 Preliminaries
7.2.1 Background of PSO
7.2.2 Terminologies
7.3 Proposed PSO based routing algorithm
7.3.1 Random particle initialization phase
7.3.2 Proposed tness function
7.3.3 Position and velocity updating phase
7.4 Results and discussion
7.4.1 Network lifetime vs number of gateways
7.4.2 Number of hops vs number of gateways
7.4.3 Average relay load vs number of gateways
7.5 Conclusion
8. M-Curves Path Planning for Mobile Anchor Node and Localization of Sensor Nodes Using DSA
8.1 Introduction
8.2 Preliminaries
8.2.1 Overview of dolphin swarm algorithm
8.2.2 Terminologies
8.2.3 Phases of DSA
8.2.4 DSA for localization
8.2.5 System models
8.2.6 Localization technique
8.3 Proposed work
8.3.1 Problem formulation
8.3.2 Mobile anchor movement
8.3.3 Non-collinear messages
8.3.4 Node localization process
8.4 Results and discussion
8.4.1 Performance setup
8.4.2 Parameter setup
8.4.3 Performance analysis
8.5 Conclusion
9. Conclusion and Future Research
9.1 Conclusion
9.2 Future research
Bibliography
Index