In ocean environments, underwater sensor nodes (USNs) are susceptible to failure due to various factors, such as seawater corrosion, hardware failure, depleted battery, harsh deployment scenarios, and intentional sabotage. This article focuses on the topology restoration problem of disconnected subnetworks (TR-DSNs) caused by large-scale USN failures in underwater wireless sensor networks (UWSNs). The existing research cannot be well adapted to dynamic ocean environments because they ignore the effects of underwater communication channel and current movement on the cost and reliability of network restoration. It would consequently lead to high restoration cost and unreliable data transmission for UWSNs. To solve the mentioned problem, we first build a reliability evaluation model of topology restoration that considers the link quality, network connectivity, and data transmission of UWSNs in dynamic ocean environments. Then, a reliability-driven topology restoration strategy (called RDTRS) based on underwater relay node (URN) placement is designed. RDTRS comprises three key algorithms: 1) URN placement path generation; 2) URN location determination; and 3) URN location adjustment. By RDTRS, the number of URNs can be reduced on the premise of ensuring the restoration reliability of UWSNs. In the end, we validate the performance of RDTRS in terms of network restoration cost, packet delivery ratio, and transmission latency.

In Underwater Acoustic Sensor Networks (UASNs), the robustness of network is greatly affected by complex marine environments when implementing multi-hop data transmission. Factors such as the underwater acoustic channel and dynamic topological changes induced by multi-layered oceanic vortices exacerbate this influence. However, there is currently a research gap in the specific area of robustness optimization for UASNs. Existing studies on robustness optimization are unsuitable for UASNs as they neglect the considerations of the marine environment and node characteristics (e.g., residual energy). In this work, we propose PRobust, a percolation-based robustness optimization model for UASNs. PRobust consists of two distinct phases: percolation modeling and bottleneck optimization. In the percolation modeling phase, we incorporate both node and edge features, considering the physical and topological properties, and introduce a novel approach for calculating link quality. In the bottleneck optimization phase, we devise a graph theory-based method to identify bottlenecks, leveraging the flow information recorded by nodes to improve the accuracy of bottleneck discovery. Moreover, we integrated time slots and a current movement model into the proposed model, allowing its applicability to dynamically changing UASNs. Extensive simulation results indicate that, compared to existing methods, PRobust significantly enhances network robustness and performance with the same overhead after bottleneck optimization.

Unknown industrial control protocols (ICPs) seriously hamper the device intercommunication and security analysis of the Industrial Internet of Things due to the absence of public specification information. Protocol reverse analysis has emerged as a promising technology to infer their specifications, where the primary step is to extract protocol fields by locating their boundaries in the network packet. Previous works leverage various algorithms, such as sequence alignment, keyword mining, and statistic analysis for field extraction. However, they have limitations in excavating the unique features of ICP fields, leading to inaccuracies in boundary localization. To address this problem, we propose an entropy-based field segmentation method for unknown ICPs. After stacking protocol packets vertically, we calculate the information entropy and information gain ratio of data values at each location in the packet. By analyzing the distribution variations of these entropy features in diverse ICP fields, we derive multiple packet segmentation rules to locate the field boundaries. Extensive comparative experiments demonstrate the superiority of our method for ICP field extraction.

In recent years, multimodal underwater wireless sensor networks (M-UWSNs) have attracted widespread concern in academia. Due to the complex underwater communication environment and the increasing marine applications, it is a crucial issue for M-UWSNs to design an energy-efficient routing strategy that can satisfy multiple transmission latency requirements of different marine applications. Reinforcement learning (RL) approaches with distributed dynamic optimization ability provide a prospective way to solve the aforementioned problem. Therefore, we propose an improved RL framework and then design an energy-efficient multilevel routing strategy (MLRS-RL) based on this framework for multiple transmission latency requirements. In MLRS-RL, a method of model knowledge collection based on the time backoff principle is proposed to preliminarily learn the network environment information before network operates. The convergence speed of the RL framework can be accelerated by utilizing the model knowledge. Then, underwater nodes use the improved RL model to calculate the transmission rewards that data packets with different transmission latency requirements are sent to different candidate relay nodes. Finally, a cooperative transmission strategy using multiple relay nodes is designed to further improve the reliability of data transmission. We verify the effectiveness of the MLRS-RL strategy in terms of packet delivery ratio, transmission latency, energy efficiency, network lifetime, and delivery quantity.

This article focuses on the topology optimization problem to decrease transmission delay and prolong network lifetime on the premise of reliable transmission in underwater wireless sensor networks (UWSNs). This is extremely challenging owing to dynamic ocean current movement, harsh underwater communication channel, and increasingly demanding application requirements. With the development of software-defined network architectures, the centralized topology control (TC) strategy with a global perspective in UWSNs is expected to become a more effective way to tackle the above challenges compared with the existing distributed and heuristic TC strategies involving local network state information. Therefore, we first transform the topology optimization problem of UWSNs into an integer nonlinear programming (INLP) model and design a centralized TC framework to solve the INLP model. In this framework, a TC center is built to periodically generate the network topology for UWSNs according to the current network state information. Further, an efficient topology generation algorithm based on deep reinforcement learning (TGA-DRL) is proposed in the TC center. In TGA-DRL, to reduce computing overhead and improve operational efficiency, we formulate an action-space narrowed Markov decision process suitable for network topology generation and solve it with the aid of the rainbow algorithm which is a deep reinforcement learning model. Finally, the performance of our centralized TC framework is verified in terms of the node out-degree, algorithm convergence, and optimization effect.

This paper focuses on the anti-interference transmission strategy for underwater acoustic sensor networks(UASNs). The interference existing between nodes communicating in a shared channel may significantly decrease the communication quality and increase the energy consumption of nodes. However, existing researches on transmission strategies for UASNs either do not consider inter-node interference or ignore the effect of acoustic channels. To solve the above problems, we propose to characterize the interference communication problem of nodes as an ordinal potential game model. Furthermore, a deep reinforcement learning (DRL)- based algorithm is designed to solve the problem, which selects the transmission power for nodes by learning historical information of signal-to-interference-plus-noise ratio(SINR) to minimize network interference. Finally, we verify that the DRL-based anti-interference transmission strategy proposed in this paper can obtain the optimal transmission strategy from variable underwater environment through extensive simulations, and show the feasibility of the algorithm under large-scale networks.

In underwater wireless sensor networks (USWNs), autonomous underwater vehicle (AUV)-assisted data collection has received significant attention for its characteristics of low energy consumption and long network lifetime. However, the existing AUV-assisted data collection schemes ignore the communication range of sensor nodes and the kinematics of AUVs. In this way, the path planned is inefficient and difficult to be applied in practice. To address the problems mentioned above, this paper proposes an AUV-assisted data collection scheme based on Fermat’s spiral (FS-PPS), which considers path planning within and outside the communication range of sensor nodes. Firstly, an improved firefly algorithm is used to determine the traversal order of nodes. Based on the determined sequence, we plan the path by adjusting the turning point and the steering angle of Fermat’s spiral. It can shorten the data collection path length. significantly while meeting the requirements. In the simulation, compared with two other schemes, FS-PPS can reduce data collection time by 17% and 6% on average.

In underwater monitoring systems, it is important to guarantee high availability of the data collection service. An effective approach is the use of autonomous underwater vehicles (AUVs) to gather data from the sensor nodes. In mobile underwater wireless sensor networks, node locations change continuously, which increases the difficulty of data collection. In this paper, a dynamic data collection algorithm based on mobile nodes (DDCA) is proposed to collect underwater data. AUVs can move directly to the predicted node location to shorten the time of data collection. The algorithm is divided into two parts: mobility prediction and data collection. The locations of the mobility sensor nodes are predicted, and then the trajectory of the AUV is planned according to the predicted locations of sensor nodes to achieve reliable data collection. Furthermore, a region partitioning strategy is proposed to reduce the time difference of each AUV completing the data collection. The simulation results demonstrate that the DDCA effectively reduces the time of data collection and shortens the time difference of AUVs returning to the sink node.

This paper discusses the data transmission strategy based on underwater multimodal communication for marine applications in underwater wireless sensor networks (UWSNs). Underwater data required by various applications have different values of information (VoIs) depending on the type and timeliness of events. These data should be transmitted in different time latency according to their VoIs to accommodate the both application requirements and network performance. Our objective is to design a multi-level transmission strategy by using underwater multimodal communication system so that multiple paths with different transmission latency and energy consumption are provided for underwater data in UWSNs. For this purpose, we first define a minimum cost flow (MCF) model for the design of transmission strategy that considers transmission latency, energy efficiency, and transfer load. Then a distributed multilevel transmission strategy EMTS is proposed based on time backoff method for large-scale UWSNs. Finally, we compared the transmission latency, energy efficiency and network lifetime obtained by our EMTS strategy to those of the optimum solution of the MCF model, and a transmission algorithm based on greedy strategy. Although the latency of EMTS is slightly higher than that of other algorithms, our average network lifetime can reach 88.7% of that of the optimum solution of the MCF model.

Efficient neighbor discovery in vehicular ad hoc networks is crucial to a number of applications such as driving safety and data transmission. The main challenge is the high mobility of vehicles. In this paper, we proposed a new algorithm for quickly discovering neighbor node in such a dynamic environment. The proposed rapid discovery algorithm is based on a novel mobility prediction model using Kalman filter theory, where each vehicular node has a prediction model to predict its own and its neighbors' mobility. This is achieved by considering the nodes' temporal and spatial movement features. The prediction algorithm is reinforced with threshold triggered location broadcast messages, which will update the prediction model parameters, and improve the efficiency of the neighbor discovery algorithm. Through extensive simulations, the accuracy, robustness, and efficiency properties of our proposed algorithm are demonstrated. Compared with other methods of neighbor discovery, which are frequently used in HP-AODV, ARH, and ROMSG, the proposed algorithm needs the least overheads and can reach the lowest neighbor error rate while improving the accuracy rate of neighbor discovery. In general, the comparative analysis of different neighbor discovery methods in routing protocol is obtained, which shows that the proposed solution performs better than HP-AODV, ARH, and ROMSG.

For the development of the Underwater Internet of Things, reliable transmission of underwater wireless sensor networks to monitor the marine environment is important. However, for ocean monitoring, the reliability of data transmission is difficult to guarantee because of node mobility. In addition, energy consumption must be reduced during data transmission because node energy is limited. To entirely address these problems, this paper proposes a self-organising routing algorithm based on a joint clustering and routing strategy for ocean monitoring (JCR-OM) to increase reliable data transmission in underwater wireless sensor networks. Firstly, the reliable communication distance of the node is calculated in a multilayer current model by using a force analysis of the anchor node. Then, in cluster head selection, the reliable transmission distance and a backoff strategy are introduced to improve the impact of node mobility on data transmission. In intercluster routing selection, a greedy strategy is used to construct a routing strategy with minimum communication cost. The simulation results verify that JCR-OM can improve data transmission and prolong network lifetime.

Effectively analyzing and mining large-scale heterogeneous information networks (HINs) by adopting network representation learning (NRL) approaches have received increasing attention. The abundant semantic and structural information contained in HINs not only facilitates network analysis and downstream tasks, but also poses special challenges to well capture that rich information. With the intention to preserve such rich yet potential information during HIN embedding, we first discuss the latent dependence existed in indirect neighbors, then study the different abilities of forward layer and backward layer of bidirectional recurrent neural network to remain semantic of HINs. And finally, we propose a novel representation learning model for HIN, namely RL4HIN. RL4HIN utilizes a skip-dependence strategy for enhancing the latent dependence between farther neighbors, and then develops a proposed weighted loss function in order to balance such difference between forward and backward layer. Extensive experiments, including node classification and visualization, have been conducted on two large- scale and real-world HINs. The experimental results show that RL4HIN significantly outperforms several state-of-the-art NRL approaches.

Underwater wireless sensor networks (UWSNs) have become crucial for many different applications, such as marine pastures, which needs stratified aquaculture according to the habitat and range of activities of marine organisms. This type of application poses a significant challenge to network topology because strengthening the monitoring of the living conditions and collecting underwater data on organisms in different regions is necessary. In this paper, a new concept of "subregional monitoring" is proposed, and subregions with frequent activities of marine organisms are taken as the key monitoring areas, i.e., the areas of interest (AOIs). Then, SFRG, an energy-balanced and robust topology based on scale-free network and rigid graph theory, is proposed to strengthen the monitoring of the AOIs. The topology of a rigid graph is constructed in AOI, and the entire network is scale-free network with power-law degree distribution, when the rigid graph is regarded as a "node". Furthermore, a transmission algorithm based on the SFRG is suggested to prolong the network lifetime. The algorithm guarantees that 90% of the received packets are from the AOIs. The simulation results demonstrate that the SFRG effectively prolongs the network lifetime and improves the network robustness, which provides a strong support in strengthening the monitoring of AOIs and balancing the energy consumption.

Knowledge representation learning (KRL), which transforms both the entities and relations into continuous low dimensional continuous vector space, has attracted considerable research. Most of existing knowledge graph (KG) completion models only considers the structural representation of triples, but do not consider the important text information about entity descriptions in the knowledge base. We propose a text-enhanced KG model based on gated convolution network (GConvTE), which can learn entity descriptions and symbol triples jointly by feature fusion. Specifically, each triple (head entity, relation, tail entity) is represented as a 3-column structural embedding matrix, a 3-column textual embedding matrix and a 3-column joint embedding matrix where each column vector represents a triple element. Textual embeddings are obtained by bidirectional gated recurrent unit with attention (A-BGRU) encoding entity descriptions and joint embeddings are obtained by the combination of textual embeddings and structural embeddings. Extending feature dimension in embedding layer, these three matrixs are concatenated into 3-channel feature block to be fed into convolution layer, where the gated unit is added to selectively output the joint features maps. These feature maps are concatenated and then multiplied with a weight vector via a dot product to return a score. The experimental results show that our model GConvTE achieves better link performance than previous state-of-art embedding models on two benchmark datasets.

In recent years, underwater acoustic sensor networks (UASNs) have attracted widespread attention in academia. Prolonging the network lifetime is a crucial issue for UASNs. Compared with traditional wireless sensor networks (WSNs), stringent energy becomes more critical in UASNs because the battery equipped at sensor nodes has the limited amount of energy and it is much more difficult to replace or recharge in underwater circumstance. This fact motivates us to pursue the solutions to reduce power consumption by using relay nodes and flow allocation mechanism in order to extend the network lifetime. In this paper, the issues of relay node placement and the flow allocation have been considered as a joint problem and are formulated into an integer nonlinear programming problem, which is node placement-hard in general. To solve the problem efficiently, this paper proposes a novel heuristic scheme for UASNs, which works based on a 3-D architecture. The proposed scheme consists of three algorithms, named as Alternative Flow and Relay-node Adjustment as a whole. Extensive simulation experiments demonstrate that the proposed scheme offers a simple yet attractive solution to the problem.

Recently, large scale vehicle ad hoc networks (VANETs)-based navigation systems have drawn much research attention. Although an enhanced secure and privacy VANET-based navigation (EVSPN) scheme has been proposed to prevent the replay and man-in-the- middle attacks, providing signature and verification on the public key infrastructure (PKI) based signatures of all messages relayed costs much computation resource and incurs a high authentication delay for not only the vehicles but also the roadside units (RSUs), especially when the navigation service is busy. In this paper, we propose a lightweight secure VANET-based navigation scheme (LSVN) that has a lower computation cost and a lower authentication delay. By the LSVN, a vehicle firstly initiates the navigation service with a RSU nearby to request a shared symmetric key for further communication with other RSUs in the VANET. Then, the best route will be calculated. The pseudo identity of the vehicle and the shared keying materials are sent to the RSUs on the route of the vehicle to its destination. At last, the vehicle will be led to the destination by these RSUs in series. We formally verify, by BAN Logic, that the LSVN scheme can provide the guarantee of the integrity of messages and mutual authentication. Performance analysis shows that the LSVN can minimize the use of cryptographic operations and reduce authentication delay significantly comparing with the VSPN scheme and the EVSPN scheme.

The most common approach adopted in the literatures to study the aggregated ICT (Inter-Contact Time) is focused on a certain mobile wireless network, and then characterizing the ICT in this type of network. Tip to now, it still lacks a general approach to model the aggregated ICT effectively in different type of networks. This paper proposes a new approach to characterize the aggregated ICT based on EVT (extreme value theory), which uses the GPD (generalized Pareto distribution) as the unique asymptotic model of the tail distribution. Parameter estimation methods are discussed and applied to real mobility traces collected on different opportunistic networks, such as social pocket switched networks and VANET (vehicular ad hoc network). By performing extensive experiments using EVT-based model, the statistical characteristics of aggregated ICT are found to generally have a power-law behavior in the tail distribution in social opportunistic networks, while an exponential behavior in VANETs. According to the KS (Kolmogorov-Smirnov) test, it illustrates that EVT-based model performs better than other models in characterizing the tail behavior of real mobility traces. Our results thus provide fundamental guidelines on design a new mobility models in opportunistic networks, new routing protocols and their performance analysis.

When a node is not abiding by the rules of the protocol of a wireless network for its own benefit, it can cause severe degradation to network performance. Therefore it is important to detect such selfish behaviour. However, this is not an easy task. The main difficulty comes from the random operation of the carrier-sense multiple-access with collision avoidance (CSMA/CA) protocol, and is exacerbated by the nature of the wireless medium itself. The authors propose in this study a simple and quick algorithm, called sliding window non-parametric cumulative sum (SWN-CUSUM), to detect selfish nodes that deliberately modify its backoff window to gain unfair access to the network resources. SWN-CUSUM uses a sliding window to prevent unlimited build-up of the cumulating sum used in the protocol. The efficiency of this detection algorithm has been validated by extensive simulations using a Qualnet simulator. Comparative analysis of the proposed algorithm with a traditional CUSUM method demonstrates its superior performance with high detection accuracy and low false alarm rate. In addition, the authors compared SWN-CUSUM with other detection techniques, such as sequential probability ratio test and exponentially weighted moving average, the results show that our algorithm has a good performance in detection delay.

Selfish behavior at the MAC (medium access control) layer can have devastating side effects on the performance of wireless ad hoc networks. In this work, we consider the problem of detecting selfish behavior at the MAC layer in IEEE 802.11 wireless networks when a selfish node can manipulate the backoff operation. We propose a simple and robust mechanism based on CUSUM (cumulative sum) test by tracing the statistics characteristic in real time to detect the selfish behavior. This method can be used with any random access MAC protocols and it does not require any modification on the existing protocols. The efficacy of this detection mechanism has been validated by a Qualnet simulator. Our simulation results show that the detection mechanism has short detection time and high detection accuracy.

Security is a fundamental prerequisite for the survivability and reliability of wireless networks. In a network where limited wireless resources have to be shared, selfish nodes can manipulate relevant network parameters to gain more access to the resources, and hence obtain a higher performance than their fair share, while the performance of well-behaved nodes will be significantly degraded. This paper considers the environment of an IEEE802.11 WLAN, and proposes a solution from the prospective of a principal-agent system. Our solution uses an incentive and a constraint mechanism to encourage the selfish agent to perform normally. Our method does not modify the IEEE 802.11 protocol, but requires an additional principal node only. Simulation results show that our method can overcome the influence of selfish nodes improve the network fairness performance while maintaining the throughput performance.

Research on the effect of selfish node in wireless ad hoc networks has received considerable attention recently. However, most work concentrates on simulation study, but lacks an analytical study to accurately predict the throughput. This paper investigates the saturated and non-saturated load throughputs of IEEE 802.11 DCF (distributed coordinated function) in the presence of a selfish node. Using a modified Markov model, we have derived the throughput of a node under various traffic loads in the PHY (PHYsical) layer using DSSS (direct sequence spread spectrum) and the wireless MAC (medium access layer). The analytical model and throughput results have been validated by simulations.

It is important to study the traffic in the wireless network control and management. This paper proposes the use of the EVT (extreme value theory) for the analysis of wireless network traffic. The role of EVT is to allow the development of procedures that are scientifically and statistically rational to estimate the extreme behavior of random processes. We have performed extensive simulation experiments by taking traffic data that is greater than a given threshold value. The results of our experiments and analysis show the wireless network traffic model obtained through the EVT fits well with the empirical distribution of traffic. Meanwhile, we can obtain EVT model has the lowest "average deviation" compared with other popular distribution model such as exponential, lognormal, gamma, Weibull. Thus illustrates EVT is more suitable than other distributions to model the traffic and it has a good application foreground in the analysis of wireless network traffic.