Author: Anna Förster
Publisher: Sudwestdeutscher Verlag Fur Hochschulschriften AG
ISBN: 9783838109367
Category :
Languages : de
Pages : 236
Get Book Here
Book Description
Routing and clustering for wireless sensor networks (WSN) play a significant role for reliable and energy efficient data dissemination. Although these research areas attract a lot of interest lately, there is still no holistic approach that is able to meet the requirements and challenges of many different applications and network scenarios, like various network sizes and topologies, multiple mobile data sinks, or node failures. The main goal of this work is to demonstrate that machine learning is a practical approach to a range of complex distributed problems in WSNs. Showing this will open up new paths for development at all levels of the communication stack. To achieve this goal we present a robust, energy-efficient, and flexible data dissemination framework consisting of the routing protocol FROMS and the clustering protocol Clique. Both are based on reinforcement learning, and exhibit vital properties such as robustness against mobility, node and link failures, fast recovery after failures, very low control overhead and a wide variety of supported network scenarios and applications. Both protocols are fully distributed and have minimal communication overhead.
Author:
Publisher:
ISBN:
Category :
Languages : en
Pages :
Get Book Here
Book Description
Wireless sensor networks (WSNs) are a fast developing research area with many new exciting applications arising, ranging from micro climate and environmental monitoring through health and structural monitoring to interplanetary communications. At the same time researchers have invested a lot of time and effort into developing high performance energy efficient and reliable communication protocols to meet the growing challenges of WSN applications and deployments. However, some major problems still remain: for example programming, planning and deploying sensor networks, energy efficient communication, and dependability under harsh environmental conditions. Routing and clustering for wireless sensor networks play a significant role for reliable and energy efficient data dissemination. Although these research areas have attracted a lot of interest lately, there is still no general holistic approach that is able to meet the requirements and challenges of many different applications and network scenarios, like various network sizes and topologies, multiple mobile data sinks, or node failures. The current state-of-the-art is rich in specialized routing and clustering protocols, which concentrate on one or a few of the above problems, but perform poorly under slightly different network conditions. The main goal of this thesis is to demonstrate that machine learning is a practical approach to a range of complex distributed problems in WSNs. Showing this will open up new paths for development at all levels of the communication stack. To achieve our goal we contribute a robust, energy-efficient, and flexible data dissemination framework consisting of a routing protocol called \froms and a clustering protocol called Clique. Both protocols are based on Q-Learning, a reinforcement learning technique, and exhibit vital properties such as robustness against mobility, node and link failures, fast recovery after failures, very low control overhead and a wide variety of supported netw.
Author: K. Suganthi
Publisher: CRC Press
ISBN: 1000441857
Category : Technology & Engineering
Languages : en
Pages : 270
Get Book Here
Book Description
This book offers the latest advances and results in the fields of Machine Learning and Deep Learning for Wireless Communication and provides positive and critical discussions on the challenges and prospects. It provides a broad spectrum in understanding the improvements in Machine Learning and Deep Learning that are motivating by the specific constraints posed by wireless networking systems. The book offers an extensive overview on intelligent Wireless Communication systems and its underlying technologies, research challenges, solutions, and case studies. It provides information on intelligent wireless communication systems and its models, algorithms and applications. The book is written as a reference that offers the latest technologies and research results to various industry problems.
Author: Adam Barker
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 0
Get Book Here
Book Description
Wireless sensor networks (WSN) are typically formed ad hoc and utilize mesh topologies which enable the individual nodes to form the infrastructure allowing senders and receivers outside of RF range to pass messages through intermediate nodes. The individual nodes themselves are typically smaller devices, which run on a battery and utilize a microcontroller for processing. The primary function of a WSN is to sense various attributes of the environment and relay that data back to an end point for further exploitation. In most WSN, that end point is fixed, hardwired to a power source, and connected directly to pre-existing network infrastructure. A subset of WSN, which we call peer-to-peer WSN, perform all the functions of a typical WSN, but the end points are not fixed. The individual nodes in these scenarios must rely on their onboard capacity for computation to transform the raw sensor data into usable information while simultaneously optimizing the flow of information and the longevity of the network.This peer-to-peer WSN is the focus of our use case for this thesis in which we develop, with the help of a specific form of machine learning known as reinforcement learning, routing algorithms that can utilize the peer-to-peer WSN structure to efficiently forward and transform data into usable information for utilization at the end point embedded within the network. We will utilize deep reinforcement learning and graph neural networks to develop algorithms that will allow peer-to-peer WSN to learn functions for determining ideal policies within a given state of the network. We will demonstrate, using both simulation and testing on live wireless networks, improvement over the currently deployed WSN routing algorithms that rely on flooding and shortest path algorithms to determine their actions.
Author: Habib M. Ammari
Publisher: Springer Nature
ISBN: 3319923846
Category : Technology & Engineering
Languages : en
Pages : 794
Get Book Here
Book Description
This book presents a broad range of deep-learning applications related to vision, natural language processing, gene expression, arbitrary object recognition, driverless cars, semantic image segmentation, deep visual residual abstraction, brain–computer interfaces, big data processing, hierarchical deep learning networks as game-playing artefacts using regret matching, and building GPU-accelerated deep learning frameworks. Deep learning, an advanced level of machine learning technique that combines class of learning algorithms with the use of many layers of nonlinear units, has gained considerable attention in recent times. Unlike other books on the market, this volume addresses the challenges of deep learning implementation, computation time, and the complexity of reasoning and modeling different type of data. As such, it is a valuable and comprehensive resource for engineers, researchers, graduate students and Ph.D. scholars.
Author: Dinh Thai Hoang
Publisher: John Wiley & Sons
ISBN: 1119873738
Category : Technology & Engineering
Languages : en
Pages : 293
Get Book Here
Book Description
Deep Reinforcement Learning for Wireless Communications and Networking Comprehensive guide to Deep Reinforcement Learning (DRL) as applied to wireless communication systems Deep Reinforcement Learning for Wireless Communications and Networking presents an overview of the development of DRL while providing fundamental knowledge about theories, formulation, design, learning models, algorithms and implementation of DRL together with a particular case study to practice. The book also covers diverse applications of DRL to address various problems in wireless networks, such as caching, offloading, resource sharing, and security. The authors discuss open issues by introducing some advanced DRL approaches to address emerging issues in wireless communications and networking. Covering new advanced models of DRL, e.g., deep dueling architecture and generative adversarial networks, as well as emerging problems considered in wireless networks, e.g., ambient backscatter communication, intelligent reflecting surfaces and edge intelligence, this is the first comprehensive book studying applications of DRL for wireless networks that presents the state-of-the-art research in architecture, protocol, and application design. Deep Reinforcement Learning for Wireless Communications and Networking covers specific topics such as: Deep reinforcement learning models, covering deep learning, deep reinforcement learning, and models of deep reinforcement learning Physical layer applications covering signal detection, decoding, and beamforming, power and rate control, and physical-layer security Medium access control (MAC) layer applications, covering resource allocation, channel access, and user/cell association Network layer applications, covering traffic routing, network classification, and network slicing With comprehensive coverage of an exciting and noteworthy new technology, Deep Reinforcement Learning for Wireless Communications and Networking is an essential learning resource for researchers and communications engineers, along with developers and entrepreneurs in autonomous systems, who wish to harness this technology in practical applications.
Author: F. Richard Yu
Publisher: Springer
ISBN: 3030105466
Category : Technology & Engineering
Languages : en
Pages : 71
Get Book Here
Book Description
This Springerbrief presents a deep reinforcement learning approach to wireless systems to improve system performance. Particularly, deep reinforcement learning approach is used in cache-enabled opportunistic interference alignment wireless networks and mobile social networks. Simulation results with different network parameters are presented to show the effectiveness of the proposed scheme. There is a phenomenal burst of research activities in artificial intelligence, deep reinforcement learning and wireless systems. Deep reinforcement learning has been successfully used to solve many practical problems. For example, Google DeepMind adopts this method on several artificial intelligent projects with big data (e.g., AlphaGo), and gets quite good results.. Graduate students in electrical and computer engineering, as well as computer science will find this brief useful as a study guide. Researchers, engineers, computer scientists, programmers, and policy makers will also find this brief to be a useful tool.
Author: Kunalbhai Shah
Publisher:
ISBN:
Category : Reinforcement learning
Languages : en
Pages :
Get Book Here
Book Description
In wireless sensor networks (WSN), resource-constrained nodes are expected to operate in highly dynamic and often unattended environments. WSN applications need to cope with such dynamicity and uncertainty intrinsic in sensor networks, while simultaneously trying to achieve efficient resource utilization. A middleware framework with support for autonomous, adaptive and distributed sensor management, can simplify development of such WSN applications. We present a reinforcement learning based WSN middleware framework to enable autonomous and adaptive applications with support for efficient resource management. The uniqueness of our framework lies in using a bottom-up approach where each sensor node is responsible for its resource allocation/task selection while ensuring optimization of system-wide parameters like total energy usage, network lifetime etc. The framework allows creation of a distributed and scalable system while meeting applications' goals. In this dissertation, a Q-learning based scheme called DIRL (Distributed Independent Reinforcement Learning) is presented first. DIRL learns the utility of performing various tasks over time with mostly local information at nodes. DIRL uses these utility values along with application constraints for task management subject to optimal energy usage. DIRL scheme is extended to create a two-tier reinforcement learning based framework consisting of micro-learning and macro-learning. Microlearning enables individual sensor nodes to self-schedule their tasks using local information allowing for a real-time adaptation as in DIRL. Macro-learning governs the micro-learners by setting their utility functions in order to steer the system towards applications' optimization goal (e.g. maximize network lifetime etc). The effectiveness of our framework is exemplified by designing a tracking/surveillance application on top of it. Finally, results of simulation studies are presented that compare performance of our scheme against other existing approaches. In general for applications requiring autonomous adaptation, our two-tier reinforcement learning based scheme on average is about 50% more efficient than micro-learning alone and many-fold more efficient than traditional resource management schemes like static scheduling, while maintaining necessary accuracy/performance. Efficient data collection in sparse WSNs by special nodes called Mobile Data Collectors (MDCs) that visit sensor nodes is investigated. As contact times are not known a priori and in order to minimize energy consumption, the discovery of an incoming MDC by the static sensor node is a critical task. Discovery is challenging as MDCs participating in various applications exhibit different mobility patterns and hence require unique design of a discovery strategy for each application. In this context, an adaptive discovery strategy is proposed that exploits the DIRL framework and can be effectively applied to various applications while minimizing energy consumption. The principal idea is to learn the MDC's arrival pattern and tune the sensor node's duty cycle accordingly. Through extensive simulation analysis, the energy efficiency and effectiveness of the proposed framework is demonstrated. Finally, design and evaluation of a complete and generalized middleware framework called DReL is presented with focus on distributed sensor management on top of our multi-layer reinforcement learning scheme. DReL incorporates mechanisms and communication paradigms for task, data and reward distributions. DReL provides an easy-to-use interface to application developers for creating customized applications with specific QoS and optimization requirements. Adequacy and efficiency of DReL is shown by developing few sample applications on top of it and evaluating those applications' performance.
Author: Yi Chu
Publisher:
ISBN:
Category :
Languages : en
Pages :
Get Book Here
Book Description
Author: Wei-Peng Chen
Publisher:
ISBN:
Category :
Languages : en
Pages : 282
Get Book Here
Book Description
