scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Clustering and Data Aggregation in Wireless Sensor Networks Using Machine Learning Algorithms

Shahina K1, V. Vaidehi1
01 Sep 2018-
TL;DR: This paper proposes an improved similarity based clustering and data aggregation, which uses Independent Component Analysis (ICA), which provides a comparative analysis of the performance of different methods to help the designers for designing appropriate machine learning based solutions for clusteringand data aggregation applications.
Abstract: Wireless Sensor Networks (WSN) are resource constrained Clustering and data aggregations are used to reduce the energy consumption in the network by decreasing the amount of data transmission Machine Learning algorithms such as swarm intelligence, reinforcement learning, neural networks significantly reduce the amount of data transmission and use the distributive characteristics of the network It provides a comparative analysis of the performance of different methods to help the designers for designing appropriate machine learning based solutions for clustering and data aggregation applications This paper presents a literature review of different machine learning based methods which are used for clustering and data aggregation in WSN and proposes an improved similarity based clustering and data aggregation, which uses Independent Component Analysis (ICA)
Citations
More filters
Journal ArticleDOI
TL;DR: This is the first in-depth literature survey of all ML techniques in the field of low power consumption WSN-IoT for smart cities and shows that the supervised learning algorithms have been most widely used as compared to reinforcement learning and unsupervised learning for smart city applications.
Abstract: Artificial intelligence (AI) and machine learning (ML) techniques have huge potential to efficiently manage the automated operation of the internet of things (IoT) nodes deployed in smart cities. In smart cities, the major IoT applications are smart traffic monitoring, smart waste management, smart buildings and patient healthcare monitoring. The small size IoT nodes based on low power Bluetooth (IEEE 802.15.1) standard and wireless sensor networks (WSN) (IEEE 802.15.4) standard are generally used for transmission of data to a remote location using gateways. The WSN based IoT (WSN-IoT) design problems include network coverage and connectivity issues, energy consumption, bandwidth requirement, network lifetime maximization, communication protocols and state of the art infrastructure. In this paper, the authors propose machine learning methods as an optimization tool for regular WSN-IoT nodes deployed in smart city applications. As per the author’s knowledge, this is the first in-depth literature survey of all ML techniques in the field of low power consumption WSN-IoT for smart cities. The results of this unique survey article show that the supervised learning algorithms have been most widely used (61%) as compared to reinforcement learning (27%) and unsupervised learning (12%) for smart city applications.

71 citations

Journal ArticleDOI
TL;DR: A Nash Q-Learning based node scheduling algorithm for coverage and connectivity maintenance (CCM-RL) is proposed where each node autonomously learns its optimal action (active/hibernate/sleep/customize the sensing range) to maximize the coverage rate and maintain network connectivity.
Abstract: The fundamental challenge for randomly deployed resource-constrained wireless sensor network is to enhance the network lifetime without compromising its performance metrics such as coverage rate and network connectivity. One way is to schedule the activities of sensor nodes and form scheduling rounds autonomously in such a way that each spatial point is covered by at least one sensor node and there must be at least one communication path from the sensor nodes to base station. This autonomous activity scheduling of the sensor nodes can be efficiently done with Reinforcement Learning (RL), a technique of machine learning because it does not require prior environment modeling. In this paper, a Nash Q-Learning based node scheduling algorithm for coverage and connectivity maintenance (CCM-RL) is proposed where each node autonomously learns its optimal action (active/hibernate/sleep/customize the sensing range) to maximize the coverage rate and maintain network connectivity. The learning algorithm resides inside each sensor node. The main objective of this algorithm is to enable the sensor nodes to learn their optimal action so that the total number of activated nodes in each scheduling round becomes minimum and preserves the criteria of coverage rate and network connectivity. The comparison of CCM-RL protocol with other protocols proves its accuracy and reliability. The simulative comparison shows that CCM-RL performs better in terms of an average number of active sensor nodes in one scheduling round, coverage rate, and energy consumption.

39 citations

Journal ArticleDOI
TL;DR: In this article, a distributed asynchronous deep reinforcement learning framework is proposed to intensify the dynamics and prediction of adaptive packet scheduling, which contains two parts: local asynchronous packet scheduling and distributed cooperative control center.
Abstract: Adaptive packet scheduling can efficiently enhance the performance of multipath Data Transmission. However, realizing precise packet scheduling is challenging due to the nature of high dynamics and unpredictability of network link states. To this end, this paper proposes a distributed asynchronous deep reinforcement learning framework to intensify the dynamics and prediction of adaptive packet scheduling. Our framework contains two parts: local asynchronous packet scheduling and distributed cooperative control center. In local asynchronous packet scheduling, an asynchronous prioritized replay double deep Q-learning packets scheduling algorithm is proposed for dynamic adaptive packet scheduling learning, which makes a combination of prioritized replay double deep Q-learning network (P-DDQN) to make the fitting analysis. In distributed cooperative control center, a distributed scheduling learning and neural fitting acceleration algorithm to adaptively update neural network parameters of P-DDQN for more precise packet scheduling. Experimental results show that our solution has a better performance than Random weight algorithm and Round-Robin algorithm in throughput and loss ratio. Further, our solution has 1.32 times and 1.54 times better than Random weight algorithm and Round—Robin algorithm on the stability of multipath data transmission, respectively.

10 citations

Proceedings ArticleDOI
01 Oct 2019
TL;DR: Considering the difference in the amount of data collected and the speed of data acquisition, a new Minimum Spanning Tree (MST) algorithm is proposed which is devoted to construct a data aggregation tree with the lowest energy consumption so that the network lifetime is maximized.
Abstract: Sensor play an important role in the growth of big data. It is a basic operation for nodes to periodically transmit reports to a sink in many applications in a Wireless Sensor Network (WSN). Because of the limited energy of the nodes, it is important to process data efficiently. Under such applications, a tree is generally adopted the path structure for maintaining the routing tables of sensors. In this paper, considering the difference in the amount of data collected and the speed of data acquisition, we assign different acquisition frequency to the nodes. In addition, we propose a new Minimum Spanning Tree (MST) algorithm which is devoted to construct a data aggregation tree with the lowest energy consumption so that the network lifetime is maximized. Simulation results illustrate that the proposed algorithm outperforms traditional MST in terms of energy consumption.

3 citations


Cites background from "Clustering and Data Aggregation in ..."

  • ...Data aggregation could be realized through the cluster [16], where a spanning tree could be formed to conduct data aggregation along a specific path....

    [...]

Journal ArticleDOI
Zhi Wang1, Ronghui Hou
TL;DR: In this paper, the authors investigated a balanced and efficient caching strategy based on similarity in vehicular networks and applied McCormick Envelopes to convert the MINLP problem into LP problem, and then adopted improved branch and bound algorithm to obtain the optimal offloading decision and computing resource allocation strategy.
Abstract: To meet the requirement of constrained delay and computation resource of the future vehicular networks, it is imperative to develop efficient content caching strategy and computation resource allocation strategy in mobile edge computing (MEC) servers. In the proposed network framework, since the caching capacity and computing resource of each MEC are limited, and the coverage areas of MECs are overlapped, the vehicular networks have to decide what contents to cache, how to offload tasks and how much computing resource needs to be allocated for each task. In this study, in order to jointly tackle these issues, we formulate caching strategy, offloading decision and computing resource allocation coordinately as a mixed integer non-linear programming (MINLP) problem. To solve the MINLP problem, we divide it into two subproblems. Firstly, we investigate a balanced and efficient caching strategy based on similarity in vehicular networks. Secondly, we apply McCormick Envelopes to convert MINLP problem into LP problem, and then adopt improved branch and bound algorithm to obtain the optimal offloading decision and computing resource allocation strategy. Simulation results indicate that the proposed schemes have a good performance in reducing economic cost under the deadline of each task.

2 citations

References
More filters
Proceedings ArticleDOI
04 Jan 2000
TL;DR: The Low-Energy Adaptive Clustering Hierarchy (LEACH) as mentioned in this paper is a clustering-based protocol that utilizes randomized rotation of local cluster based station (cluster-heads) to evenly distribute the energy load among the sensors in the network.
Abstract: Wireless distributed microsensor systems will enable the reliable monitoring of a variety of environments for both civil and military applications. In this paper, we look at communication protocols, which can have significant impact on the overall energy dissipation of these networks. Based on our findings that the conventional protocols of direct transmission, minimum-transmission-energy, multi-hop routing, and static clustering may not be optimal for sensor networks, we propose LEACH (Low-Energy Adaptive Clustering Hierarchy), a clustering-based protocol that utilizes randomized rotation of local cluster based station (cluster-heads) to evenly distribute the energy load among the sensors in the network. LEACH uses localized coordination to enable scalability and robustness for dynamic networks, and incorporates data fusion into the routing protocol to reduce the amount of information that must be transmitted to the base station. Simulations show the LEACH can achieve as much as a factor of 8 reduction in energy dissipation compared with conventional outing protocols. In addition, LEACH is able to distribute energy dissipation evenly throughout the sensors, doubling the useful system lifetime for the networks we simulated.

12,497 citations

01 Jan 2000
TL;DR: LEACH (Low-Energy Adaptive Clustering Hierarchy), a clustering-based protocol that utilizes randomized rotation of local cluster based station (cluster-heads) to evenly distribute the energy load among the sensors in the network, is proposed.
Abstract: Wireless distributed microsensor systems will enable the reliable monitoring of a variety of environments for both civil and military applications. In this paper, we look at communication protocols, which can have signicant impact on the overall energy dissipation of these networks. Based on our ndings that the conventional protocols of direct transmission, minimum-transmission-energy, multihop routing, and static clustering may not be optimal for sensor networks, we propose LEACH (Low-Energy Adaptive Clustering Hierarchy), a clustering-based protocol that utilizes randomized rotation of local cluster base stations (cluster-heads) to evenly distribute the energy load among the sensors in the network. LEACH uses localized coordination to enable scalability and robustness for dynamic networks, and incorporates data fusion into the routing protocol to reduce the amount of information that must be transmitted to the base station. Simulations show that LEACH can achieve as much as a factor of 8 reduction in energy dissipation compared with conventional routing protocols. In addition, LEACH is able to distribute energy dissipation evenly throughout the sensors, doubling the useful system lifetime for the networks we simulated.

11,412 citations


"Clustering and Data Aggregation in ..." refers methods in this paper

  • ...The simulation shows that the technique increases the performance of CH elections while comparing with Low Energy Adaptive Clustering Hierarchy (LEACH) algorithm [16] and Analytical Hierarchy Process (AHP)....

    [...]

Journal ArticleDOI
TL;DR: The key ideas behind the CSP algorithms for distributed sensor networks being developed at the University of Wisconsin (UW) are described and the approach to tracking multiple targets that necessarily requires classification techniques becomes a reality.
Abstract: Networks of small, densely distributed wireless sensor nodes are being envisioned and developed for a variety of applications involving monitoring and the physical world in a tetherless fashion. Typically, each individual node can sense in multiple modalities but has limited communication and computation capabilities. Many challenges must be overcome before the concept of sensor networks In particular, there are two critical problems underlying successful operation of sensor networks: (1) efficient methods for exchanging information between the nodes and (2) collaborative signal processing (CSP) between the nodes to gather useful information about the physical world. This article describes the key ideas behind the CSP algorithms for distributed sensor networks being developed at the University of Wisconsin (UW). We also describe the basic ideas on how the CSP algorithms interface with the networking/routing algorithms being developed at Wisconsin (UW-API). We motivate the framework via the problem of detecting and tracking a single maneuvering target. This example illustrates the essential ideas behind the integration between UW-API and UW-CSP algorithms and also highlights the key aspects of detection and localization algorithms. We then build on these ideas to present our approach to tracking multiple targets that necessarily requires classification techniques becomes a reality.

997 citations


"Clustering and Data Aggregation in ..." refers background in this paper

  • ...[17] discussed the basic notions for distributed detection and tracking of single target with WSN....

    [...]

Journal ArticleDOI
TL;DR: An extensive literature review over the period 2002-2013 of machine learning methods that were used to address common issues in WSNs is presented and a comparative guide is provided to aid WSN designers in developing suitable machine learning solutions for their specific application challenges.
Abstract: Wireless sensor networks (WSNs) monitor dynamic environments that change rapidly over time. This dynamic behavior is either caused by external factors or initiated by the system designers themselves. To adapt to such conditions, sensor networks often adopt machine learning techniques to eliminate the need for unnecessary redesign. Machine learning also inspires many practical solutions that maximize resource utilization and prolong the lifespan of the network. In this paper, we present an extensive literature review over the period 2002–2013 of machine learning methods that were used to address common issues in WSNs. The advantages and disadvantages of each proposed algorithm are evaluated against the corresponding problem. We also provide a comparative guide to aid WSN designers in developing suitable machine learning solutions for their specific application challenges.

704 citations


"Clustering and Data Aggregation in ..." refers background in this paper

  • ...information is sent to the base station with appropriate routing mechanism [9]....

    [...]

Journal ArticleDOI
TL;DR: The integrated mobile surveillance and wireless sensor system (iMouse) uses static and mobile wireless sensors to detect and then analyze unusual events in the environment.
Abstract: Incorporating the environment-sensing capability of wireless sensor networks into video- based surveillance systems can provide advanced services at a lower cost than traditional surveillance systems.The integrated mobile surveillance and wireless sensor system (iMouse) uses static and mobile wireless sensors to detect and then analyze unusual events in the environment.

170 citations


"Clustering and Data Aggregation in ..." refers background in this paper

  • ...So Tseng et al [6] proposed iMouse which is Integrated Mobile Surveillance and Wireless Sensor Networks....

    [...]

  • ...So Tseng et al [6] proposed iMouse which is Integrated Mobile Surveillance and Wireless Sensor Networks. iMouse adopts high powered mobile sensors for enhancing conventional surveillance system....

    [...]