Название: Data-Driven Intelligence in Wireless Networks: Concepts, Solutions, and Applications
Автор: Muhammad Khalil Afzal, Muhammad Ateeq, Sung Won Kim
Издательство: CRC Press
Год: 2023
Страниц: 267
Язык: английский
Формат: pdf (true)
Размер: 19.0 MB

This book highlights the importance of data-driven techniques to solve wireless communication problems. It presents a number of problems (e.g., related to performance, security, and social networking), and provides solutions using various data-driven techniques, including Machine Learning, Deep Learning, Federated Learning, and Artificial Intelligence.

This book details wireless communication problems that can be solved by data-driven solutions. It presents a generalized approach toward solving problems using specific data-driven techniques. The book also develops a taxonomy of problems according to the type of solution presented and includes several case studies that examine data-driven solutions for issues such as quality of service (QoS) in heterogeneous wireless networks, 5G/6G networks, and security in wireless networks.

In modern communication systems, wireless has become a prevailing medium in establishing the Internet of Things (IoT) that uses all sorts of communication networks including WiFi, wireless sensor networks, and cellular networks. In our physical environment, we are surrounded by an enormous amount of information that we sense and to which we appropriately react. With the progression of the world and fast-growing technology, environments are intended to be smart where both sensing and decision-making are autonomous, fast, and robust. Such ubiquitous sensing requires support and facilitation to put the sensed data to use. There is an established need for resilient, adaptive, and futuristic communication infrastructure. To serve
this purpose, wireless sensor networks (WSNs) have been around for the past two decades. WSNs consist of resource-constrained nodes capable of sensing and communicating over low-power radio interfaces. The number of nodes may range from in the 10s to the 1000s, depending on the application domain and deployment scenario. These nodes collect large-scale data and relay it to a base station that carries out the relevant processing tasks.

Two prominent features of modern computing systems are intelligence and adaptivity, driven by Artificial Intelligence (AI) and Machine Learning (ML). The communication domain is no different in this regard. Data-driven networking (DDN) has been proposed with centralized control. Using the data-driven approach, WSNs can learn their performance recordings and then harmonize and fine-tune their own responses in accordance with the QoS requirements. The sole purpose of using the centralized approach is to enable sophisticated algorithms to run on a substantial volume of data without putting the load on the constrained sensor nodes. The performance data is collected from heterogeneous deployments of WSNs and centrally processed using techniques like ML to learn the QoS attributes based on various characteristics and parameters of the network. The prediction results are used for making intelligent decisions to meet desired QoS goals. This learning loop continues as the transitions in different settings of the WSNs occur and the system evolves.

The target audience of this book includes professionals, researchers, professors, and students working in the field of networking, communications, Machine Learning, and related fields.