Название: Optimising IoT Networks: Energy-Efficient Resource Management through Machine LearningАвтор: Suvarna Patil, Manisha Bhende, Swati Sharma
Издательство: CRC Press
Год: 2025
Страниц: 280
Язык: английский
Формат: epub (true)
Размер: 22.6 MB
With a specific focus on energy efficiency, Optimizing IoT Networks examines the application of Machine Learning to enhance resource allocations in IoT networks. It discusses various algorithms, including neural networks and Reinforcement Learning, to optimise resource use and improve network performance. It addresses challenges such as the dynamic behaviour of IoT devices and the need for real-time decision-making. It discusses optimisation methods used alongside Machine Learning to enhance resource allocation efficiency.
• Provides a foundational understanding of IoT network architecture and the importance of efficient resource allocation
• Discusses complexities in resource allocation due to dynamic device behaviour and varying data traffic patterns
• Covers key machine learning concepts and algorithms relevant to optimising resource allocation in IoT networks
• Emphasises the significance of energy efficiency in IoT networks and its impact on resource allocation strategies
• Explores algorithms such as clustering, regression, and reinforcement learning for effective resource allocation
The Internet of Things (IoT) has rapidly transformed the modern world, bringing unprecedented connectivity and enabling smarter, data-driven decision-making across a wide spectrum of applications. From smart cities to industrial automation, healthcare, agriculture, and beyond, IoT is reshaping industries and enhancing human lives. However, with great opportunities come significant challenges, including energy efficiency, resource allocation, network optimisation, and scalability. These issues are compounded by the sheer heterogeneity and dynamic nature of IoT networks, demanding innovative solutions.
This book, Optimising IoT Networks: Energy-Efficient Resource Management through Machine Learning, aims to bridge the gap between theory and practice in addressing these challenges. It provides a comprehensive exploration of resource allocation, energy optimisation, traffic prediction, and advanced machine learning techniques tailored for IoT networks. Spanning nine chapters, this book offers a holistic approach to understanding, designing, and implementing efficient IoT systems.
Chapter 1 lays the groundwork by introducing the IoT ecosystem, highlighting the principles of machine-to-machine communication, resource allocation, and energy consumption, along with a detailed examination of IoT protocols and their role in addressing network challenges. Chapter 2 delves into network models and gateway placement strategies, offering a comparative analysis of link scheduling algorithms while identifying research gaps and performance metrics essential for IoT networks. Chapter 3 focuses on distance-aware gateway placement, with insights into clustering models, multi-hop traffic algorithms, and transmission models, culminating in a discussion on case studies for smart cities and industrial IoT. Chapter 4 introduces machine learning-driven traffic prediction for link selection, emphasising Long Short-Term Memory (LSTM) models and their applications in dynamic IoT environments, alongside fairness-driven resource allocation models. Chapter 5 examines fairness in resource allocation, introducing Analytical Hierarchy Process (AHP)-based algorithms and dynamic scheduling in heterogeneous gateways, supported by novel Machine Learning approaches...
The book is designed for researchers, practitioners, and scholars in Computer Science and technology who are interested in or actively working on optimising IoT networks.
Скачать Optimising IoT Networks: Energy-Efficient Resource Management through Machine Learning