The emergence of coverage holes will dramatically degrade the quality of service of the industrial wireless sensor networks (IWSNs). Based on the novel confident information coverage (CIC) model, this work focuses on how to heal the CIC holes in hybrid IWSNs containing both static nodes and mobile nodes. We pinpoint the CIC hole healing (CICHH) problem with the goal of selecting and dispatching some randomly scattered mobile nodes to the CIC holes detected by the stationary nodes such that the CIC holes can be repaired and the CIC performance can be satisfied, and prove its NP-completeness. For handling the CICHH problem, we devise two energy-efficient heuristic solutions including a centralized CICHH algorithm and a distributed one. Both the proposed schemes aim at efficiently healing the CIC holes while minimizing the total moving energy consumption of the dispatched mobile nodes, or maximizing the mobile nodes’ average remaining energy after movement, or minimizing the maximum mobile energy consumption of each dispatched mobile node. Experimental simulation results show the proposed schemes can energy-efficiently heal the CIC holes and outperform three peer algorithms in terms of energy efficiency and coverage ratio.

Confident Information Coverage Hole Healing in Hybrid Industrial Wireless Sensor Networks

A norm-space, adaptive, and blind audio watermarking algorithm by discrete wavelet transform

Wireless sensor networks (WSNs) have drawn much research attention in recent years due to the superior performance in multiple applications, such as military and industrial monitoring, smart home, disaster restoration etc. In such applications, massive sensor nodes are randomly deployed and they remain static after the deployment, to fully cover the target sensing area. This will usually cause coverage redundancy or coverage hole problem. In order to effectively deploy sensors to cover whole area, we present a novel node deployment algorithm based on mobile sensors. First, sensor nodes are randomly deployed in target area, and they remain static or switch to the sleep mode after deployment. Second, we partition the network into grids and calculate the coverage rate of each grid. We select grids with lower coverage rate as candidate grids. Finally, we awake mobile sensors from sleep mode to fix coverage hole, particle swarm optimization (PSO) algorithm is used to calculate moving position of mobile sensors. Simulation results show that our algorithm can effectively improve the coverage rate of WSNs.

/pdf/a-mobile-assisted-coverage-hole-patching-scheme-based-on-43uzsqmakw.pdf

A mobile assisted coverage hole patching scheme based on particle swarm optimization for WSNs

In Wireless Sensor Networks (WSNs), various anomalies may arise and reduce their reliability and efficiency. For example, Coverage Hole can occur in such networks due to several causes, such as damaging events, sensors battery exhaustion, hardware failure, and software bugs. Modern trends to use relocation of deployed sensor nodes when the manual addition of nodes is neither doable nor economical in many applications have attracted attention. The lack of central supervision and control in harsh and hostile environments have encouraged researchers to shift from centralized to distributed node relocation schemes. In this paper, a new game theory approach based on reinforcement learning to recover Coverage Holes in a distributed way is proposed. For the formulated potential game, sensor nodes can recover Coverage Holes using only local acquaintances. To reduce the coverage gaps, the combined action of node reposition and sensing range adjustment is chosen by each sensor node. The simulation results prove that, unlike previous methods, the proposed approach can sustain a network overall coverage in the presence of random damage events.

A distributed coverage hole recovery approach based on reinforcement learning for Wireless Sensor Networks

Distributed machine learning (DML) techniques, such as federated learning, partitioned learning, and distributed reinforcement learning, have been increasingly applied to wireless communications. This is due to improved capabilities of terminal devices, explosively growing data volume, congestion in the radio interfaces, and increasing concern of data privacy. The unique features of wireless systems, such as large scale, geographically dispersed deployment, user mobility, and the massive amount of data, give rise to new challenges in the design of DML techniques. There is a clear gap in the existing literature that the DML techniques are yet to be systematically reviewed for their applicability to wireless systems. This survey bridges the gap by providing a contemporary and comprehensive survey of DML techniques with a focus on wireless networks. Specifically, we review the latest applications of DML in power control, spectrum management, user association, and edge cloud computing. The optimality, accuracy, convergence rate, computation cost, and communication overhead of DML are analyzed. We also discuss the potential adversarial attacks faced by DML applications, and describe state-of-the-art countermeasures to preserve privacy and security. Last but not least, we point out a number of key issues yet to be addressed, and collate potentially interesting and challenging topics for future research.

Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applications

Coverage holes (CHs) can compromise the reliability and functionality of wireless sensor networks. The recovery of CHs is challenging, especially in distributed applications where sensors have little knowledge about other sensors’ actions. We propose a new game theoretic approach for recovering the CHs in a distributed manner. The key idea is that we formulate a potential game between the sensors, where each mobile sensor in the network only depends on local knowledge of its neighboring nodes and takes CH recovery actions recursively with global convergence. An appropriate combined action of physical relocation and sensing range adjustment can be taken by each sensor to reduce the CHs in an energy-efficient way. Simulation results show that the proposed game theoretic approach is able to substantially increase network lifetime and maintain network coverage in the presence of random damage events, as compared with the prior counterpart(s).

Distributed Hybrid Coverage Hole Recovery in Wireless Sensor Networks

Physical damage and/or node power exhaustion may lead to coverage holes in WSNs. Coverage holes can be directly detected by certain proximate nodes known as boundary nodes (B-nodes). Due to the sensor nodes' redundant deployment and autonomous fault detection, holes are surrounded by a margin of B-nodes (MB-nodes). If all B-nodes in the margin take part in the hole recovery processes, either by increasing their transmission power or by relocating towards region of interest (ROI), the probability of collision, interference, disconnection, and isolation may increase affecting the rest of the network's performance and QoS. Thus, distributed boundary node selection algorithms (BNS-Algorithms) are proposed to address these issues. BNS-algorithms allow B-nodes to self-select based on available 1-hop information extracted from nodes' simple geometrical and statistical features. Our results show that the performance of the proposed distributed BNS-algorithms approaches that of their centralized counterparts.

/pdf/boundary-node-selection-algorithms-in-wsns-2dzr8h57f2.pdf

Boundary node selection algorithms in WSNs

The use of Probabilistic Neural Network (PNN) is very common in supervised pattern recognition applications. PNN is based on Bayes decision rule and it uses Gaussian Parzen windows for estimating the probability density functions (pdf) required in Bayes rule. The conventional PNN needs a single spread value for pdf estimation which is proportional to Gaussian window width. In this paper we will suggest the use of a multi-spread PNN structure whose spread values are estimated using the training data. In addition, we will introduce several new discriminating features of acoustic radiated noise which can be used for ship noise classification. These features will be used as discriminating features in the conventional and multi-spread PNN. Finally, the performance of the conventional PNN and the suggested multi-spread PNN in classifying real ship noise data will be compared. Results of this comparison show that the performance of the multi-spread PNN is better than the conventional PNN.

A new method for spread value estimation in multi-spread PNN and its application in ship noise classification

In harsh and hostile environments, swift relocation of currently deployed nodes in the absence of centralized paradigm is a challenging issue in WSNs. Reducing the burden of centralized relocation paradigms by the distributed movement models comes at the price of unpleasant oscillations and excessive movements due to nodes' local and limited interactions. If the nodes' careless movements in the distributed relocation models are not properly addressed, their power will be exhausted. Therefore, in order to exert proper amount of virtual radial/angular push/pull forces among the nodes, a fuzzy logic relocation model is proposed and by considering linear combination of the presented performance metric(s)(i.e. coverage, uniformity, and average movement), its parameters are locally and globally tuned by particle swarm optimization(PSO). In order to tune fuzzy parameters locally and globally, PSO benefits respectively from nodes' neighbours within different ranges and all the given deployed area. Performance of locally and globally tuned fuzzy relocation models is compared with one another in addition to the distributed self-spreading algorithm (DSSA). It is shown that by applying PSO to the linear combinations of desired metric(s) to obtain tuned fuzzy parameters, the relocation model outperforms and/or is comparable to DSSA in one or more performance metric(s).

/pdf/a-tuned-fuzzy-logic-relocation-model-in-wsns-using-particle-3ztkx3bb00.pdf

A Tuned Fuzzy Logic Relocation Model in WSNs Using Particle Swarm Optimization

—In WSNs, in order to recover from coverage holesand to mitigate their indirect/direct effects on networks’ perfor-mance, different recovery strategies such as increasing proximatenodes’ transmission range and/or relocation of nodes towardscoverage holes seem to be appropriate solutions. Since the major-ity of a mobile node’s energy is consumed by movement and sincenodes’ residual energy may be affected by damage events, nodemovements should be performed sparingly. Conventional nodes’information exchange in real-time applications with security andinterference concerns are neither practical nor secure. Therefore,for the aforementioned scenarios, at the price of possible node col-lisions, disconnections, and reasonable compromises, promisingdistributed and autonomous node movement algorithms based onlimited 1-hop neighbour knowledge are proposed. Our proposedautonomous and constrained node movement model based on anode’s 1-hop perception provides a feasible and rapid recoverymechanism for large scale coverage holes in real-time and harshenvironments. Our model not only maintains moving nodes’connectivity to the rest of network to some extent, but also offersemergent cooperative recovery behaviour among autonomousmoving nodes. Our movement model based on virtual chordsformed by nodes and their real and virtual 1-hop neighbours,not only conﬁnes node movement range, but also takes the issueof moving nodes’ connectivity into account. Suitable performancemetrics for partial recovery via constrained movement are intro-duced to compare the performance and efﬁciency of our modelwith conventional Voronoi-based movement algorithms. Resultsshow that our proposed model’s performance is comparable withVoronoi-based movement algorithms.Index Terms—Coverage holes; autonomous and constrainedmovements; Wireless sensor networks; virtual chord.

Ali Rafiei

Papers

Distributed Hybrid Coverage Hole Recovery in Wireless Sensor Networks

Boundary node selection algorithms in WSNs

A new method for spread value estimation in multi-spread PNN and its application in ship noise classification

A Tuned Fuzzy Logic Relocation Model in WSNs Using Particle Swarm Optimization

WSNs Coverage Hole Partial Recovery by Nodes' Constrained and Autonomous Movements Using Virtual alpha-chords