Fault analysis and research of wireless sensor network based on kernel partial least squares

With the development of intelligent and networked sensor technology,wireless sensor networks were widely used in human life and commercial fields,because wireless sensor network nodes usually only carry limited resources,it is prone to failures due to insufficient resources,the accurate and timely fault diagnosis of WSN nodes can ensure the reliability of information,thus improving the maintainability of WSN and prolonging the service life of WSN.A method of using kernel partial least squares has been proposed to predict the fault reasons,the method overcomes the defects of traditional linear regression method and the nonlinear high dimensional space for data analysis.Through many experiments,the method can absorb the characteristics of canonical correlation analysis and principal component analysis method,provide a more thorough and rich content analysi,that the reason of the fault can be predicted effectively.     

Energy efficient fault-tolerant multipath routing scheme for wireless sensor networks

In wireless sensor network （MSN）, reliability is the main issue to design any routing technique. To design a comprehensive reliable wireless sensor network, it is essential to consider node failure and energy constrain as inevitable phenomena. In this paper we present energy efficient node fault diagnosis and recovery for wireless sensor networks referred as energy efficient fault tolerant multipath routing scheme for wireless sensor network. The scheme is based on multipath data routing. One shortest path is used for main data routing in our scheme and other two backup paths are used as alternative path for faulty network and to handle the overloaded traffic on main channel. Shortest pat data routing ensures energy efficient data routing. Extensive simulation results have revealed that the performance of the proposed scheme is energy efficient and can tolerates more than 60% of fault.     

Fault diagnosis and its prediction in wireless sensor networks using regressional learning to achieve fault tolerance

Due to the wide range of critical applications and resource constraints, sensor node gives unexpected responses, which leads to various kind of faults in sensor node and failure in wireless sensor networks. Many research studies focus only on fault diagnosis, and comparatively limited studies have been conducted on fault diagnosis along with fault tolerance in sensor networks. This paper reports a complete study on both 2 aspects and presents a fault tolerance approach using regressional learning with fault diagnosis in wireless sensor networks. The proposed method diagnose the different types of faulty nodes such as hard permanent, soft permanent, intermittent, and transient faults with better detection accuracy. The proposed method follows a fault tolerance phase where faulty sensor node values would be predicted by using the data sensed by the fault free neighbors. The experimental evaluation of the fault tolerance module shows promising results with R² of more than 0.99. For the periodic fault such as intermittent fault, the proposed method also predict the possible occurrence time and its duration of the faulty node, so that fault tolerance can be achieved at that particular time period for better performance of the network.     

Sensor network localization using kernel spectral regression

This paper addresses the localization problem in wireless sensor networks using signal strength. We use a kernel function to measure the similarities between sensor nodes. The kernel matrix can be naturally defined in terms of the signal strength matrix. We show that the relative locations of sensor nodes can be obtained by solving a dimension reduction problem. To capture the structure of the whole network, we use the kernel spectral regression (KSR) method to estimate the relative locations of the sensor nodes. Given sufficient anchor nodes, the relative locations can be aligned to global locations. The key benefits of adopting KSR are that it allows us to define a graph to optimally preserve the topological structure of the sensor network, and a kernel function can capture the nonlinear relationship in the signal space. Simulation results show that we can achieve small average location error with a small number of anchors. We also compare our method with several related methods, and the results show that KSR is more efficient than the others in our simulated sensor networks. Copyright © 2009 John Wiley & Sons, Ltd.     

无线传感器网络自适应功率控制策略

无线传感器网络功率控制技术对于网络的拓扑连通、能量效率、网络容量、吞吐量、实时性等性能均有显著影响,是其实用化的重要支撑技术。该文提出了一种适用于无线传感器网络的自适应功率控制策略APCS(Adaptive Power Control Strategy),该策略是只需要局部信息的分布式算法,通过调整路径损耗指数和功率控制参数可以获得性能极佳的目标拓扑,并能满足实时性和容错能力要求较高的应用场景。另外,该算法还采用了动态功率调整以保持网络的连通性,延长网络的生命周期。仿真结果证实了所提方法的有效性。     

An improved fault detection crow search algorithm for wireless sensor network

In wireless sensor networks (WSNs), the collected data during monitoring environment can have some faulty data, and these faults can lead to the failure of a system. These faults may occur due to many factors such as environmental interference, low battery, and sensors aging etc. We need an efficient fault detection technique for preventing the failures of a WSN or an IoT system. To address this major issue, we have proposed a new nature-inspired approach for fault detection for WSNs called improved fault detection crow search algorithm (IFDCSA). IFDCSA is an improved version of the original crow search algorithm (CSA). The proposed algorithm first injects the faults into the datasets, and then the faults are classified using improved CSA and machine learning classifiers. The proposed work has been evaluated on the three real-world datasets, ie, Intel lab data, multihop labeled data, and SensorScope data, and predicts the faults with an average accuracy of 99.94%. The results of the proposed algorithm have been compared with the three different machine learning classifiers (random forest, k-nearest neighbors, and decision trees) and Zidi model. The proposed algorithm outperforms the other classifiers/models, thus generating higher accuracy and lower features without degrading the performance of the system. Index Terms—big data, crow search algorithm, IoT, machine learning, nature-inspired algorithm, wireless sensor network.     

物联网感知层多路径传输策略研究

多路径数据传输是无线传感器网络亟需解决的一个关键问题.本文针对节点故障、链路失效和外界干扰影响网络稳定性和可靠性,提出一种基于混合蛙跳算法的无线传感器网络多路径传输策略.首先我们详细介绍了蛙跳算法及其原理,之后我们将其应用到无线传感器网络多路径传输策略之中,接着运用混合蛙跳算法对传感网络节点其进行更新、划分、重组以便选择出最优节点建立传输最优路径,提高网络的稳定性和可靠性.通过算法仿真与结果对比提出的算法与AODV、粒子群PSO算法相比,在网络能耗、传输时延、丢包率、连通率和可靠度等方面都具有较好的性能.其中网络能耗比AODV、PSO算法降低了62.5％和35.8％.     

节点失效对无线传感器网络覆盖与连通可靠性影响的模型研究

针对节点失效引起无线传感器网络监测性能下降的问题,该文以节点随机均匀部署的网络为研究对象,从节点失效的角度提出了评价网络覆盖与连通两个基本监测性能的量化指标,建立了评价模型,通过设计节点失效算法对随机失效与恶意入侵两种节点失效类型进行了计算机模拟,利用仿真结果比较了网络监测性能在不同失效类型时的变化情况,总结出经验公式,为网络参数的选取提供了依据。     

基于特征根优化的无线网络控制系统故障检测滤波器设计

为提高无线传感器执行器网络(WSANs)的可靠性,本文提出了一种面向WSANs的故障检测滤波器的优化设计方法.针对无线网络固有的较大的数据包传输延迟,本文将该传输延迟对网络控制系统的影响建模为一种外部噪音,创造性地提出了基于特征根分解和扰动频率估计的优化算法,以滤除网络传输延迟导致的噪音.该方法只需在有限个频率点对目标函数进行优化,且避免了马尔科夫转移矩阵难以获得的难题.最后,通过MATLAB/NS2的混合仿真验证了该设计的有效性.     

Network Partitioning Recovery Mechanisms in WSANs: a Survey

Wireless sensor and actor networks (WSANs) are more promising and most addressing research field in the area of wireless sensor networks in recent scenario. It composed of possibly a large number of tiny, autonomous sensor devices and resources rich actor nodes equipped with wireless communication and computation capabilities. Actors collect sensors’ information and respond collaboratively to achieve an application specific mission. Since actors have to coordinate their operation, a strongly connected inter-actor network would be required at all the time in the network. Actor nodes may fail for many reasons (i.e. due of battery exhaustion or hardware failure due to hash environment etc.) and failures may convert connected network into disjoint networks. This can hinder sometimes not only the performance of network but also degrade the usefulness and effectiveness of the network. Thus, having a partitioning detection and connectivity restoration procedure at the time of failure occurs in the network is crucial for WSANs. In this paper, we review the present network partitioning recovery approaches and provide an overall view of this study by summarizing previous achievements.     

A Green Clustering Protocol for Mobile Sensor Network Using Particle Swarm Optimization

Energy consumption of sensor nodes is one of the crucial issues in prolonging the lifetime of wireless sensor networks. One of the methods that can improve the utilization of sensor nodes batteries is the clustering method. In this paper, we propose a green clustering protocol for mobile sensor networks using particle swarm optimization (PSO) algorithm. We define a new fitness function that can optimize the energy consumption of the whole network and minimize the relative distance between cluster heads and their respective member nodes. We also take into account the mobility factor when defining the cluster membership, so that the sensor nodes can join the cluster that has the similar mobility pattern. The performance of the proposed protocol is compared with well-known clustering protocols developed for wireless sensor networks such as LEACH (low-energy adaptive clustering hierarchy) and protocols designed for sensor networks with mobile nodes called CM-IR (clustering mobility-invalid round). In addition, we also modify the improved version of LEACH called MLEACH-C, so that it is applicable to the mobile sensor nodes environment. Simulation results demonstrate that the proposed protocol using PSO algorithm can improve the energy consumption of the network, achieve better network lifetime, and increase the data delivered at the base station.     

Optimal tracking interval for predictive tracking in wireless sensor network

An important application of wireless sensor networks is tracking moving objects. Prediction-based techniques have been proposed to reduce the power consumption in wireless sensor networks by limiting the sensor active time. This paper proposes a quantitative method to optimize the power efficiency by analyzing the effect of prediction on the energy consumption in such networks. To our best knowledge, our efforts are the first attempt made to calculate the optimal tracking interval for a given predictive tracking algorithm. Based on this method, the lifetime and power efficiency of a sensor network can be effectively improved.     

Fault diagnosis in wireless sensor network using clonal selection principle and probabilistic neural network approach

The fault diagnosis in wireless sensor networks is one of the most important topics in the recent years of research work. The problem of fault diagnosis in wireless sensor network can be resembled with artificial immune system in many different ways. In this paper, a detection algorithm has been proposed to identify faulty sensor nodes using clonal selection principle of artificial immune system, and then the faults are classified into permanent, intermittent, and transient fault using the probabilistic neural network approach. After the actual fault status is detected, the faulty nodes are isolated in the isolation phase. The performance metrics such as detection accuracy, false alarm rate, false‐positive rate, fault classification accuracy, false classification rate, diagnosis latency, and energy consumption are used to evaluate the performance of the proposed algorithm. The simulation results show that the proposed algorithm gives superior results as compared with existing algorithms in terms of the performance metrics. The fault classification performance is measured by fault classification accuracy and false classification rate. It has also seen that the proposed algorithm provides less diagnosis latency and consumes less energy than that of the existing algorithms proposed by Mohapatra et al, Panda et al, and Elhadef et al for wireless sensor network.     

A cluster‐based fault‐tolerant routing protocol for wireless sensor networks

Energy conservation and fault tolerance are two critical issues in the deployment of wireless sensor networks (WSNs). Many cluster‐based fault‐tolerant routing protocols have been proposed for energy conservation and network lifetime maximization in WSNs. However, these protocols suffer from high frequency of re‐clustering as well as extra energy consumption to tolerate failures and consider only some very normal parameters to form clusters without any verification of the energy sufficiency for data routing. Therefore, this paper proposes a cluster‐based fault‐tolerant routing protocol referred as CFTR. This protocol allows higher energy nodes to become Cluster Heads (CHs) and operate multiple rounds to diminish the frequency of re‐clustering. Additionally, for the sake to get better energy efficiency and balancing, we introduce a cost function that considers during cluster formation energy cost from sensor node to CH, energy cost from CH to sink, and another significant parameter, namely, number of cluster members in previous round. Further, the proposed CFTR takes care of nodes, which have no CH in their communication range. Also, it introduces a routing algorithm in which the decision of next hop CH selection is based on a cost function conceived to select routes with sufficient energy for data transfer and distribute uniformly the overall data‐relaying load among the CHs. As well, a low‐overhead algorithm to tolerate the sudden failure of CHs is proposed. We perform extensive simulations on CFTR and compare their results with those of two recent existing protocols to demonstrate its superiority in terms of different metrics.     

A Rate-Distortion Based Aggregation Method Using Spatial Correlation for Wireless Sensor Networks

Today we are witnessing an amazing growth of wireless sensor networks due to many factors including but limited to reducing cost of semiconductor components, rapid deployment of wireless networks, and attention to low-power aspect that makes these networks suitable for energy sensitive applications to a large extent. The power consumption requirement has raised the demand for the new concepts such as data aggregation. Data correlation plays an important role in an efficient aggregation process. This paper introduces a new correlation-based aggregation algorithm called RDAC (Rate Distortion in Aggregation considering Correlation) that works based on centralized source coding. In our method, by collecting correlated data at an aggregation point while using the Rate-Distortion (RD) theory, we can reduce the load of data transmitted to the base station by considering the maximum tolerable distortion by the user. To the best of our knowledge, nobody has yet used the RD theory for the data aggregation in wireless sensor networks. In this paper, a mathematical model followed by implementations demonstrates the efficiency of the proposed method under different conditions. By using the unique features of the RD theory, the correlation matrix and observing the behavior of the proposed method in different network topologies, we can find the mathematical upper and lower bounds for the amount of aggregated data in a randomly distributed sensor network. The bounds not only determine the upper and lower limits of the data compressibility, it also makes possible the estimation of the required bit count of the network without having to invoke the aggregation algorithm. This method therefore, allows us to have a good estimation of the amount of energy consumed by the network.     

Failure Location Algorithm for Transparent Optical Networks

Fault and attack management has become a very important issue for network operators that are interested to offer a secure and resilient network capable to prevent and localize, as accurately as possible, any failure (fault or attack) that may occur. Hence, an efficient failure location method is needed. To locate failures in opaque optical networks, existing methods which allow monitoring of the optical signal at every regeneration site can be used. However, to the best of our knowledge, no method exists today that performs failure location for transparent optical networks. Such networks are more vulnerable to failures than opaque networks since failures propagate without being isolated due to optoelectronic conversions. In this paper, we present a failure location algorithm that aims to locate single and multiple failures in transparent optical networks. The failure location algorithm developed in this paper can cope with ideal scenarios (i.e., no false and/or lost alarms), as well as with nonideal scenarios having false and/or lost alarms.     

具有小世界现象的无线传感器网络构造方法

小世界特性是复杂网络最重要的特性之一，将小世界理论引入到无线传感器网络(WSNs)，对优化网络拓扑结构及提高其性能具有十分重要的意义。 提出了一种新的具有小世界现象的WSNs构造方法RSLCS (Removing Superfluous Links and Creating Shortcuts). 该方法首先基于对集聚系数的分析，有选择性地删除一些边，然后基于Sink节点建立捷径，两个步骤交替进行，直到两个小世界特性同时达到最优。仿真表明此方法不仅增大了网络的集聚系数，降低了平均路径长度，使网络具有明显的小世界特性，而且简化了网络拓扑结构，使网络在低冗余的条件下具有好的抗毁性。      

An ant colony optimization based routing algorithm for extending network lifetime in wireless sensor networks

Reducing the energy consumption of network nodes is one of the most important problems for routing in wireless sensor networks because of the battery limitation in each sensor. This paper presents a new ant colony optimization based routing algorithm that uses special parameters in its competency function for reducing energy consumption of network nodes. In this new proposed algorithm called life time aware routing algorithm for wireless sensor networks (LTAWSN), a new pheromone update operator was designed to integrate energy consumption and hops into routing choice. Finally, with the results of the multiple simulations we were able to show that LTAWSN, in comparison with the previous ant colony based routing algorithm, energy aware ant colony routing algorithms for the routing of wireless sensor networks, ant colony optimization-based location-aware routing algorithm for wireless sensor networks and traditional ant colony algorithm, increase the efficiency of the system, obtains more balanced transmission among the nodes and reduce the energy consumption of the routing and extends the network lifetime.     

An efficient fault-tolerant approach for Mobile IP in wireless systems

This paper presents the fault tolerance of Mobile IP in wireless systems. Mobile IP can support wireless users with continuous network connections while changing locations. It is achieved by allocating a number of mobility agents (foreign agents and home agents) in the architecture of a wireless system. If a failure occurs in a mobility agent, the wireless users located in the coverage area of the faulty mobility agent will lose their network connections. To tolerate the failures of mobility agents, this paper proposes an efficient approach to maintaining the network connections of wireless users without being affected by the failures. Once detecting a failure in a mobility agent, failure-free mobility agents are dynamically selected to be organized as a backup set to take over the faulty mobility agent. Compared to the previous approaches, the proposed approach does not take any actions against failures during the failure-free period. Besides, the hardware redundancy technique is also not used in the proposed approach. The overhead of the proposed approach is analyzed using the M/G/c/c queuing model. The results show that the proposed approach can effectively resolve the fault-tolerant problem of Mobile IP in wireless systems.     

阵元失效条件下的高精度DOA估计方法

为解决波达方向（Direction Of Arrival,DOA）估计方法在阵元失效条件下性能下降甚至失效的问题,本文提出一种基于Toeplitz协方差矩阵重构的DOA估计方法.首先,提出了一种失效阵元检测方法,并根据阵列的鲁棒性将失效阵元分为冗余阵元失效和非冗余阵元失效两种情况.然后,分别针对两种失效场景提出相应DOA估计方法：一是冗余阵元失效,利用阵列冗余度,结合差联合阵列对失效阵元进行填充;二是非冗余阵元失效,利用阵列冗余度进行填充后仍存在空洞,结合矩阵填充理论,用迹范数代替秩范数进行凸松弛以恢复协方差矩阵,进而实现对虚拟阵元空洞的填充,恢复阵列自由度.相对于稀疏类算法,有效消除了模型失配的影响.最后,基于子空间方法进行DOA估计.理论和仿真结果表明,相对于现有方法,本文方法有效避免了阵元失效的影响,提高了估计精度.