无人机辅助的基于前馈神经网络的节点定位算法

针对无线传感网络(WSNs)的节点定位问题,提出无人机辅助的基于前馈神经网络的节点定位(UAV-NN)算法。UAV-NN算法利用无人机(UAV)作为锚节点,并由UAV周期地发射beacon信号,利用极端学习机(LEM)训练单隐藏前向反馈的神经网络(SLFN),未知节点接收来自UAV发射的beacon信号,并记录其接收信号强度指示(RSSI),已训练的SLFN再依据RSSI值估计节点位置。仿真结果表明,相比于传统的基于RSSI定位算法,提出的UAV-NN算法无需部署地面锚节点;相比其他传统的机器学习算法,UAV-NN算法通过引用ELM,减少了定位误差。     

Implementation of an Efficient Artificial Bee Colony Algorithm for Node Localization in Unmanned Aerial Vehicle Assisted Wireless Sensor Networks

Node localization is a fundamental task in wireless sensor networks as it is useful for several localization based protocols and applications. Node localization using Global Poisoning System (GPS) employed fixed terrestrial anchor nodes suffers from high deployment cost and poor localization accuracy in GPS denied locations. These issues can be easily handled by deploying movable Unmanned Aerial Vehicles (UAVs). A movable UAV equipped with a single GPS module virtually increases number of anchor nodes and localizes a node at different locations. Hence, UAVs are cost effective and also provides high localization accuracy. As the flying altitude of UAV greatly influence localization accuracy, the present work firstly optimizes the flying height and then the node localization is defined as least square optimization problem using this optimal height. Since the classical received signal strength indicator based multilateration results high localization error, the least square localization using optimization techniques is found to be better alternative. The recently proposed Artificial Bee Colony (ABC) algorithm is a powerful optimization technique that can be applied for this optimization problem to achieve high accuracy. Thus, this paper aims at designing an ABC localization technique using UAV anchors to achieve minimum localization error. Further, we provide detailed simulation analysis to support the proposed ABC localization scheme.

     

WSNs中基于无人机的强健节点定位算法

通过移动无人机(UAV)收集无线传感网络数据的方案已受到广泛关注,将感测的数据与产生此数据的传感节点位置关联起来是十分必要的。为此提出了基于无人机的强健节点定位算法(UAV-NL)。UAV-NL算法将UAV位置作为未知信息。传感节点接收由UAV在随机位置传输的beacon包,并记录接收信号强度指示(RSSI)矢量;通过理论推导2个RSSI矢量的范数距离与这2节点距离的线性关系;最后,通过RSSI值测距,并利用半定规划(SDP)算法估计节点位置。仿真结果表明,提出的UAV-NL算法即使在噪声信道条件下仍具有高的定位精确度。     

Power‐aware range‐free wireless sensor network localization using neighbor distance distribution

In large‐scale wireless sensor networks, cost‐effective and energy‐efficient localization of sensor nodes is an important research topic. In spite of their coarse accuracy, range‐free (connectivity‐based) localization methods are considered as cost‐effective alternatives to the range‐based localization schemes with specialized hardware requirements.In this paper, we derive closed‐form expressions for the average minimum transmit powers required for the localization of sensor nodes, under deterministic path loss, log‐normal shadowing, and Rayleigh fading channel models. The impacts of propagation environment and spatial density of anchor nodes on the minimum transmit power for node localization are evaluated analytically as well as through simulations. Knowledge of the minimum transmit power requirements for localizability of a sensor node enables improving energy efficiency and prolonging lifetime of the network. We also propose a novel distance metric for range‐free localization in large‐scale sensor networks. The target and anchor nodes are assumed to be positioned according to two statistically independent two‐dimensional homogeneous Poisson point processes. Analytical expression for the average distance from a target node to its kth nearest neighbor anchor node is derived and is used for estimating the target‐to‐anchor node distances for localization. The Cramér–Rao lower bound on the localization accuracy for the new distance estimator is derived. Simulation results show the accuracy of the proposed distance estimate compared with some existing ones for range‐free localization. The results of our investigation are significant for low‐cost, energy‐efficient localization of wireless sensor nodes. Copyright © 2011 John Wiley & Sons, Ltd.     

Path planning using a mobile anchor node based on trilateration in wireless sensor networks

In wireless sensor networks (WSNs), many applications require sensor nodes to obtain their locations. Now, the main idea in most existing localization algorithms has been that a mobile anchor node (e.g., global positioning system‐equipped nodes) broadcasts its coordinates to help other unknown nodes to localize themselves while moving according to a specified trajectory. This method not only reduces the cost of WSNs but also gets high localization accuracy. In this case, a basic problem is that the path planning of the mobile anchor node should move along the trajectory to minimize the localization error and to localize the unknown nodes. In this paper, we propose a Localization algorithm with a Mobile Anchor node based on Trilateration (LMAT) in WSNs. LMAT algorithm uses a mobile anchor node to move according to trilateration trajectory in deployment area and broadcasts its current position periodically. Simulation results show that the performance of our LMAT algorithm is better than that of other similar algorithms. Copyright © 2011 John Wiley & Sons, Ltd.     

Ranging error‐tolerable localization in wireless sensor networks with inaccurately positioned anchor nodes

Localization is essential for wireless sensor networks (WSNs). It is to determine the positions of sensor nodes based on incomplete mutual distance measurements. In this paper, to measure the accuracy of localization algorithms, a ranging error model for time of arrival (TOA) estimation is given, and the Cramer—Rao Bound (CRB) for the model is derived. Then an algorithm is proposed to deal with the case where (1) ranging error accumulation exists, and (2) some anchor nodes broadcast inaccurate/wrong location information. Specifically, we first present a ranging error‐tolerable topology reconstruction method without knowledge of anchor node locations. Then we propose a method to detect anchor nodes whose location information is inaccurate/wrong. Simulations demonstrate the effectiveness of our algorithm. Copyright © 2008 John Wiley & Sons, Ltd.     

An enhanced wireless sensor network localization scheme for radio irregularity models using hybrid fuzzy deep extreme learning machines

Localization is one of the key challenges facing wireless sensor networks (WSNs), particularly in the absence of global positioning equipment such as GPS. However, equipping WSNs with GPS sensors entails the additional costs of hardware logic and increased power consumption, thereby lowering the lifetime of the sensor, which is normally operated on a non-rechargeable battery. Range-free-based localization schemes have shown promise compared to range-based approaches as preferred and cost-effective solutions. Typical range-free localization algorithms have a key advantage: simplicity. However, their precision must be improved, especially under varying node densities, sensing coverage conditions, and topology diversity. Thus, this work investigates the probable integration of two soft-computing techniques, namely, Fuzzy Logic (FL) and Extreme Learning Machines (ELMs), with the goal of enhancing the approximate localization precision while considering the above factors. In stark contrast to ELMs, FL methods yield high accuracy under low node density and limited coverage conditions. In addition, as a hybrid scheme, extra steps are integrated to compensate for the effects of irregular topology (i.e., noisy signal density due to obstacles). Signal and weight are normalized during the fuzzy states, while the ELM uses a deep learning concept to adjust the signal coverage, including the spring force error estimation enhancement. The performance of our hybrid scheme is evaluated via simulations that demonstrate the scheme’s effectiveness compared with other soft-computing-based range-free localization schemes.     

A survey on mobile anchor assisted localization techniques in wireless sensor networks

Identifying locations of sensor nodes in wireless sensor networks (WSNs) is significant for both network operations and most application level tasks. Although, geographical positioning system (GPS) based localization schemes are used for determining node locations but the cost of GPS devices and non-availability of GPS signals in indoor environments prevent their use in large scale WSNs. A substantial amount of research work exist that intend at obtaining precise and relative spatial locations of sensor nodes without requiring large amount of specialized hardware. Mobile anchor assisted localization is one typical approach that significantly reduces the implementation cost by using limited number of mobile anchors. In this survey, we present key issues and inherent challenges faced by the mobile anchor assisted localization techniques in WSNs. We take a closer look at the algorithmic approaches of various important fine-grained mobile anchor assisted localization techniques applicable in WSNs. In addition, we highlight the error refinement mechanisms adopted by the state-of-the-art works associated with their approaches. Well known mobile anchor trajectories presented in existing works are also reviewed. Finally, open research issues are discussed for future research scope in this field.     

基于 RSSI 的无线传感器网络节点定位算法研究

节点位置信息是无线传感器网络应用的基础。基于RSSI（Receive Signal Strength Indicator）的测距技术因其低成本和低复杂度的优点而被广泛用于无线传感器网络的定位技术中。介绍了RSSI信号传输模型,在介绍无线传感器网络定位基本原理的基础上,分析了影响定位精度的因素。综述了近几年提出的无线传感器网络中基于RSSI的节点定位算法及其改进算法,现有基于RSSI定位算法的改进算法主要从测距精度改进、定位精度改进或误差修正改进等方面进行。最后,指出了基于RSSI的无线传感器网络节点定位算法的不足,并进行展望。     

Local Patches Alignment Embedding Based Localization for Wireless Sensor Networks

Localization for wireless sensor networks (WSNs) is a challenging research topic. Let the set of sensor nodes that are close to each other be a “patch”, in this paper, we propose a new manifold learning method named local patches alignment embedding (LPAE), and then present a computationally efficient range-based WSNs localization approach using LPAE. Unlike the existing range-based localization methods using “patching” techniques, LPAE approach has the following features: 1) learning local position of all sensor nodes efficiently on a set of overlapping patches, which are constructed based on anchor nodes, rather than on neighborhood of each node, 2) aligning patches with the constraints of anchor nodes thus avoiding the accumulation of error, and 3) obtaining absolute positions of all sensor nodes directly without any other refinement technology. The proposed approach has been shown to be able to achieve satisfactory performance on both accuracy and efficiency via extensive simulations.     

Performance of some metaheuristic algorithms for localization in wireless sensor networks

In this paper we propose two novel and computationally efficient metaheuristic algorithms based on tabu search (TS) and particle swarm optimization (PSO) principles for locating the sensor nodes in a distributed wireless sensor network (WSN) environment. The WSN localization problem is formulated as a non‐linear optimization problem with mean squared range error resulting from noisy distance measurement as the objective function. Unlike gradient descent methods, both TS and PSO methods ensure minimization of the objective function without the solution being trapped into local optima. We further implement a refinement phase with error propagation control for improvement of the results. The performance of the proposed algorithms are compared with each other and also against simulated annealing based WSN localization. The effects of range measurement error, anchor node density and uncertainty in the anchor node position on localization performance are also studied through various simulations. The simulation results establish better accuracy, computational efficiency and convergence characteristics for TS and PSO methods. Further, the efficacy of the proposed methods is verified with data collected from an experimental sensor network reported in the literature. Copyright © 2008 John Wiley & Sons, Ltd.     

An Interactive and Energy-efficient Node Localization Scheme for Wireless Sensor Networks

How to obtain accurate position of sensor node is still a challenging problem for wireless sensor networks (WSNs). This work concentrates on the problem of node localization with mobile anchor node, which is applied to broadcast beacon packets in the region of interest (ROI). Node localization scheme SAA-ERL (speed adaptive adjustment-energy ratio localization) for WSNs is realized in way of interactive communications. SAA scheme determines the suitable moving speed and direction for the mobile anchor node, while the ERL mechanism generates virtual hyper-spheres to help unknown nodes acquire their locations. Based on the quantitative analysis of the localizing performances, the guidelines for system parameters are obtained. Simulation results validate that when system parameters are jointly designed, SAA-ERL can be adapted to scenarios of diversified applications.     

A mobile sink path planning for wireless sensor networks based on priority‐ordered dependent nonparametric trees

The professional design of the routing protocols with mobile sink(s) in wireless sensor networks (WSNs) is important for many purposes such as maximizing energy efficiency, increasing network life, and evenly distributing load balance across the network. Moreover, mobile sinks ought to first collect data from nodes which have very important and dense data so that packet collision and loss can be prevented at an advanced level. For these purposes, the present paper proposes a new mobile path planning protocol by introducing priority‐ordered dependent nonparametric trees (PoDNTs) for WSNs. Unlike traditional clustered or swarm intelligence topology‐based routing methods, a topology which has hierarchical and dependent infinite tree structure provides a robust link connection between nodes, making it easier to reselect ancestor nodes (ANs). The proposed priority‐ordered infinite trees are sampled in the specific time frames by introducing new equations and hierarchically associated with their child nodes starting from the root node. Hence, the nodes with the highest priority and energy that belong to the constructed tree family are selected as ANs with an opportunistic approach. A mobile sink simply visits these ANs to acquire data from all nodes in the network and return to where it started. As a result, the route traveled is assigned as the mobile path for the current round. We have performed comprehensive performance analysis to illustrate the effectiveness of the present study using NS‐2 simulation environment. The present routing protocol has achieved better results than the other algorithms over various performance metrics.     

Optimal base-station locations in two-tiered wireless sensor networks

We consider generic two-tiered wireless sensor networks (WSNs) consisting of sensor clusters deployed around strategic locations, and base-stations (BSs) whose locations are relatively flexible. Within a sensor cluster, there are many small sensor nodes (SNs) that capture, encode, and transmit relevant information from a designated area, and there is at least one application node (AN) that receives raw data from these SNs, creates a comprehensive local-view, and forwards the composite bit-stream toward a BS. This paper focuses on the topology control process for ANs and BSs, which constitute the upper tier of two-tiered WSNs. Since heterogeneous ANs are battery-powered and energy-constrained, their node lifetime directly affects the network lifetime of WSNs. By proposing algorithmic approaches to locate BSs optimally, we can maximize the topological network lifetime of WSNs deterministically, even when the initial energy provisioning for ANs is no longer always proportional to their average bit-stream rate. The obtained optimal BS locations are under different lifetime definitions according to the mission criticality of WSNs. By studying intrinsic properties of WSNs, we establish the upper and lower bounds of maximal topological lifetime, which enable a quick assessment of energy provisioning feasibility and topology control necessity. Numerical results are given to demonstrate the efficacy and optimality of the proposed topology control approaches designed for maximizing network lifetime of WSNs.     

Multiregional secure localization using compressive sensing in wireless sensor networks

Security and accuracy are two issues in the localization of wireless sensor networks (WSNs) that are difficult to balance in hostile indoor environments. Massive numbers of malicious positioning requests may cause the functional failure of an entire WSN. To eliminate the misjudgments caused by malicious nodes, we propose a compressive‐sensing–based multiregional secure localization (CSMR_SL) algorithm to reduce the impact of malicious users on secure positioning by considering the resource‐constrained nature of WSNs. In CSMR_SL, a multiregion offline mechanism is introduced to identify malicious nodes and a preprocessing procedure is adopted to weight and balance the contributions of anchor nodes. Simulation results show that CSMR_SL may significantly improve robustness against attacks and reduce the influence of indoor environments while maintaining sufficient accuracy levels.     

一种改进的蒙特卡罗定位算法研究

针对移动无线传感器网络中节点随机运动的情况,蒙特卡罗定位(MCL)算法有较好的定位精度,但由于MCL方法严格过滤而进行的频繁重采样带来大量计算,加重了节点能量消耗,针对上述情况提出了基于接收信号强度(received signal strength,RSS)的蒙特卡罗定位算法,该算法利用锚节点之间的距离及其测得的移动节点的RSS值来校正移动节点与每个锚节点之间的权值,缩小了传统MCL算法的采样范围。仿真表明,该方法降低了蒙特卡罗方法的采样次数以及通信开销,同时提高了节点定位精度。     

Computational intelligence based localization of moving target nodes using single anchor node in wireless sensor networks

Wireless Sensor Networks (WSNs) have tremendous ability to interact and collect data from the physical world. The main challenges for WSNs regarding performance are data computation, prolong lifetime, routing, task scheduling, security, deployment and localization. In recent years, many Computational Intelligence (CI) based solutions for above mentioned challenges have been proposed to accomplish the desired level of performance in WSNs. Application of CI provides independent and robust solutions to ascertain accurate node position (2D/3D) with minimum hardware requirement (position finding device, i.e., GPS enabled device). The localization of static target nodes can be determined more accurately. However, in the case of moving target nodes, accurate position of each node in network is a challenging problem. In this paper, a novel concept of projecting virtual anchor nodes for localizing the moving target node is proposed using applications of Particle Swarm Intelligence, H-Best Particle Swarm Optimization, Biogeography Based Optimization and Firefly Algorithm separately. The proposed algorithms are implemented for range-based, distributed, non-collaborative and isotropic WSNs. Only single anchor node is used as a reference node to localize the moving target node in the network. Once a moving target node comes under the range of a anchor node, six virtual anchor nodes with same range are projected in a circle around the anchor node and two virtual anchor nodes (minimum three anchor nodes are required for 2D position) in surrounding (anchor and respective moving target node) are selected to find the 2D position. The performance based results on experimental mobile sensor network data demonstrate the effectiveness of the proposed algorithms by comparing the performance in terms of the number of nodes localized, localization accuracy and scalability. In proposed algorithms, problem of Line of Sight is minimized due to projection of virtual anchor nodes.     

DynaChannAl: dynamic channel allocation with minimal end‐to‐end delay for two‐tier wireless sensor networks

With recent advances in wireless networking and in low‐power sensor technology, wireless sensor networks (WSNs) have taken significant roles in various applications. Whereas some WSNs only require minimal bandwidth, newer applications operate with a noticeably larger amount of data. One way to deal with these applications is to maximize the available capacity by utilizing multiple wireless channels. We propose DynaChannAl, a distributed dynamic wireless channel allocation algorithm that effectively distributes nodes to multiple wireless channels in WSNs. Specifically, DynaChannAl targets applications where mobile nodes connect to preexisting wireless backbones and takes the expected end‐to‐end queuing delay as its core metric. We used the link quality indicator values provided by 802.15.4 radios to whitelist high‐quality links and evaluate these links with the aggregated queuing latency, making it useful for applications that require minimal end‐to‐end delay (i.e., health care). DynaChannAl is a lightweight and adoptable scheme that can be incorporated easily with predeveloped systems. As the first study to consider end‐to‐end latency as the core metric for channel allocation in WSNs, we evaluate DynaChannAl on a 45 node test bed and show that DynaChannAl successfully distributes source nodes to different channels and enables them to select channels and links that minimizes the end‐to‐end latency. Copyright © 2012 John Wiley & Sons, Ltd.     

Power efficient range-free localization algorithm for wireless sensor networks

Considering energy consumption, hardware requirements, and the need of high localization accuracy, we proposed a power efficient range-free localization algorithm for wireless sensor networks. In the proposed algorithm, anchor node communicates to unknown nodes only one time by which anchor nodes inform about their coordinates to unknown nodes. By calculating hop-size of anchor nodes at unknown nodes one complete communication between anchor node and unknown node is eliminated which drastically reduce the energy consumption of nodes. Further, unknown node refines estimated hop-size for better estimation of distance from the anchor nodes. Moreover, using average hop-size of anchor nodes, unknown node calculates distance from all anchor nodes. To reduce error propagation, involved in solving for location of unknown node, a new procedure is adopted. Further, unknown node upgrades its location by exploiting the obtained information in solving the system of equations. In mathematical analysis we prove that proposed algorithm has lesser propagation error than distance vector-hop (DV-Hop) and other considered improved DV-Hop algorithms. Simulation experiments show that our proposed algorithm has better localization performance, and is more computationally efficient than DV-Hop and other compared improved DV-Hop algorithms.     

Multiobjective optimization‐based DV‐hop localization using NSGA‐II algorithm for wireless sensor networks

Localization is one of the important requirements in wireless sensor networks for tracking and analyzing the sensor nodes. It helps in identifying the geographical area where an event occurred. The event information without its position information has no meaning. In range‐free localization techniques, DV‐hop is one of the main algorithm which estimates the position of nodes using distance vector algorithm. In this paper, a multiobjective DV‐hop localization based Non‐Sorting Genetic Algorithm‐II (NSGA‐II) is proposed in WSNs. Here, we consider six different single‐objective functions to make three multiobjective functions as the combination of two each. Localization techniques based on proposed multiobjective functions has been evaluated on the basis of average localization error and localization error variance. Simulation results demonstrate that the localization scheme based on proposed multiobjective functions can achieve good accuracy and efficiency as compared to state‐of‐the‐art single‐ and multiobjective GA DV‐hop localization scheme.