Underwater acoustic sensor networks (UASNs) have emerged as a viable networking approach due to their numerous aquatic applications in recent years. As a vital component of UASNs, routing protocols are essential for ensuring reliable data transmissions and extending the longevity of UASNs. Recently, several clustering-based routing protocols have been proposed to reduce energy consumption and overcome the resource constraints of deployed sensor nodes. However, they rarely consider the hot-spots problem and the sink node isolation problem in the multihop underwater sensor networks. In this paper, we propose a Q-learning-based hierarchical routing protocol with unequal clustering (QHUC) for determining an effective data forwarding path to extend the lifespan of UASNs. First, a hierarchical network structure is constructed for initialization. Then a combination of unequal clustering and the Q-learning algorithm is applied to the hierarchical structure to disperse the remaining energy more evenly throughout the network. With the use of the Q-learning algorithm, a global optimal CH and next-hop can be determined better than a greedy one. In addition, the Q-value that guarantees the optimal routing decisions can be computed without incurring any additional costs by combining the Q-learning algorithm with clustering. The simulation results show that the QHUC can achieve an efficient routing and prolong the network lifetime significantly.

With the rapid development of autonomous underwater vehicles (AUVs) and the continuous improvement of marine exploration requirements, AUV formation has emerged as a promising technique for performing underwater tasks with greater flexibility, adaptability, and scalability. To achieve AUV formation control, underwater acoustic communication networks (UACNs) are widely used to support information exchange among AUVs. Considering broadcast communications in fully connected mobile UACNs, existing medium access control (MAC) protocols face severe packet collision risk or low reuse efficiency. To improve the timeliness and reliability of the information exchange among AUVs, we develop an efficient scheduling-based adaptive broadcasting MAC (AB-MAC) protocol. The AB-MAC protocol is incompletely centralized, which can be reflected in two aspects. First, to ensure the consistency of the transmission schedule in the network, the AB-MAC protocol selects a control node for each frame to schedule the transmission of all nodes according to the updated network topology. The slot lengths and transmission sequences are changeable in each frame to avoid packet collisions and minimize frame lengths. Second, to further improve the efficiency and robustness of the protocol, all nodes adaptively adjust their transmission time by integrating the information contained in their previously received control packets and ordinary packets. The transmission scheduling problem is formulated as a combinatorial optimization problem, which can be solved by our proposed improved Genetic Algorithm. Numerical results demonstrate that the AB-MAC protocol not only performs well in terms of network throughput and average update interval but also has a high level of robustness even in low-quality underwater acoustic channels.

With the development of the Internet of Underwater Things (IoUT), underwater acoustic sensor networks (UASNs) have become an enabling system to support real-time and continuous data transmission. Existing scheduling-based medium access control (MAC) protocols ignored the limitations between the generation time and the transmission time of forwarding packets. This results in unavailability of some scheduled slots, and makes packets endure more waiting time on relay nodes and thereafter longer end-to-end delay. To reduce transmission latency, this article develops a novel scheduling-based MAC protocol, which schedules slots in the packet level. All packets to be generated and transmitted in a frame are predicted and scheduled. Considering our defined packet collision constraint and traffic-flow constraint, we formulate the slot scheduling problem in a frame into a combinatorial optimization problem, which ensures that all source packets transmitted in a frame can be delivered to the sink node with the minimum average end-to-end delay within the same frame. To solve this problem, two algorithms are proposed, namely, an optimal packet-level slot scheduling (PLSS) algorithm and a heuristic approximate PLSS (PLSS-A) algorithm. The performances of our proposed protocol using both algorithms are evaluated with different network scales, packet lengths, and offered traffic loads. Numerical results demonstrate that both PLSS and PLSS-A perform well in terms of average end-to-end delay and service fairness, and have an advantage in the network throughput in large-scale networks. Our proposed PLSS MAC protocol is predicted to be promising in large-scale UASNs with demand for real-time and long-term monitoring.

The characteristics of volatile ocean environments and complex acoustic communication channels have posed great difficulties to the design of real-time data transmission in underwater wireless sensor networks (UWSNs). In this paper, we develop a centralized cross-layer protocol that mitigates network interference and maximizes concurrent transmissions to reduce end-to-end delay. Instead of optimizing individual layers separately, we blend the traditional layered architecture and combine the physical layer, medium access control (MAC) layer, and network layer functions together. Specifically, we optimize the power control in the physical layer, link scheduling in the MAC layer, and routing in the network layer jointly to achieve a global optimization of end-to-end delay. Firstly, the joint design problem is formulated as a mixed integer linear programming (MILP) problem, which is an NP-hard problem and hard to solve mathematically. Then, we propose a bio-inspired-algorithm-based solution, namely discrete improved artificial bee colony (DIABC) algorithm, aiming at finding an approximate optimal cross-layer scheduling scheme. To further reduce end-to-end delay, we optimize the uplink frame structure and routing metric in the centralized cross-layer framework. The simulation results show that the proposed protocol achieves network performance improvement in terms of end-to-end delay, service rate, and energy consumption.

For specific wideband sound source localization tasks performed in underwater environments, high precision, low computational complexity, and high robustness are required to meet the demand for accurate location in real-time processes. Traditional sound source localization methods that rely on models and signal processing techniques perform poorly in complex but common scenarios where noise, reverberation, and array deviations exist. Sound source localization systems based on deep neural networks are proposed recently and show superiority over conventional localization methods. However, lighter neural network structures for common wideband signals localization have been underexplored, which are crucial for improving the operational efficiency and practicability in underwater localization systems. In this paper, we propose a light neural network structure to locate the typical underwater wideband sound sources in communication and localization systems. The network mainly consists of convolutional and residual blocks. We train the network with simulated single tones and finetune it with multiple sets of single tones received in the experiment. As for the training feature, we choose the phase component of the covariance matrix and reshape the upper triangle into one column to reduce the feature dimension. The test signals include chirps, single-carrier modulation quadrature phase shift keying(SC-QPSK), multi-carrier modulations such as multi-tone and orthogonal frequency division multiplexing(OFDM). Both the simulation and experiment results have verified the high accuracy and robustness of our proposed method. Compared with the state-of-the-arts, our method obtains superior performance, especially in scenarios with low signal-to-noise ratio (SNR).

The dynamic production environments and stringent quality of service (QoS) requirements in discrete manufacturing smart factories pose significant challenges to deploying edge intelligence networks. These networks must simultaneously satisfy critical QoS metrics while maintaining adaptability to fluctuations in resource availability and task priorities. To address the industrial demands for real-time responsiveness, lightweight design, and flexible deployment, this paper proposes an adaptive deployment optimization strategy for edge intelligent networks based on an improved K-means particle swarm optimization (IK-PSO) algorithm. The strategy incorporates dynamic clustering and weight adjustment mechanisms to optimize multiple performance metrics, including latency, throughput, reliability, and interference mitigation. Experimental results validate that the IK-PSO-based deployment optimization strategy rapidly converges to high-quality solutions across different scenarios and various factory complexities, significantly improving network performance. This study provides a practical and efficient solution for network deployment in smart factories, contributing to the ongoing development of intelligent production and resource management.