Device-to-Device (D2D) communication with short communication distance is an efficient way to improve spectrum efficiency and mitigate interference. To realize the optimal resource configuration including wireless channel matching and power allocation, a distributed resource matching scheme is proposed based on deep reinforcement learning(DRL). The reward is defined as the difference of achieve rate of D2D users and the consumed power, which is limited by the Signal to Interference plus Noise Ratio (SINR) of the other cellular users on the current channel. The proposed algorithm maximizes the D2D throughput and energy efficiency in a distributed manner, without online coordination and message exchange between users. The considered resource allocation problem is formulated as a random non-cooperative game with multiple players (D2D pairs), where each player is a learning agent, whose task is to learn its best strategy based on locally observed information, multi-user communication resource matching algorithm is proposed based on a Double Deep Q-network (DDQN), where the total cellular throughput and user energy efficiency could converge to the Nash equilibrium (NE) under the mixed strategy. Simulation results show that the proposed algorithm can improve the communication rate and energy efficiency of each user by selecting the optimal strategy, and has better convergence performance compared with existing schemes.

Optimal power management of shipboard power system for failure mode (OPMSF) is a significant and challenging problem considering the safety of system and person. Many existing works focused on the transient-time recovery without consideration of the operating cost and the voyage plan. In this paper, the OPMSF problem is formulated considering the mid-time scheduling and the faults at bus and generator. Two side adjustment methods including the load shedding and the reconfiguration are coordinated for reducing the fault effects. To address the formulated non-convex problem, the travel equality constraint and fractional energy efficiency operation indicator (EEOI) limitation are transformed into the convex forms. Then, considering the infeasibility scenario affected by faults, a further relaxation is adopted to formulate a new problem with feasibility guaranteed. Furthermore, a sufficient condition is derived to ensure that the new problem has the same optimal solution as the original one. Because of the mixed-integer nonlinear feature, an optimal management algorithm based on Benders decomposition (BD) is developed to solve the new one. Due to the slow convergence caused by the time-coupled constraints, a low-complexity near-optimal algorithm based on BD (LNBD) is proposed. The results verify the effectivity of the proposed methods and algorithms.

With the rapid development of artificial intelligence and Unmanned Aerial Vehicle (UAV) technology, AI-based UAVs are increasingly utilized in various industrial and civilian applications. This paper presents a distributed Edge-Cloud collaborative framework for UAV object detection, aiming to achieve real-time and accurate detection of ground moving targets. The framework incorporates an Edge-Embedded Lightweight ( ${{\rm{E}}^{2}}\rm{L}$ ) object algorithm with an attention mechanism, enabling real-time object detection on edge-side embedded devices while maintaining high accuracy. Additionally, a decision-making mechanism based on fuzzy neural network facilitates adaptive task allocation between the edge-side and cloud-side. Experimental results demonstrate the improved running rate of the proposed algorithm compared to YOLOv4 on the edge-side NVIDIA Jetson Xavier NX, and the superior performance of the distributed Edge-Cloud collaborative framework over traditional edge computing or cloud computing algorithms in terms of speed and accuracy.

With the advent of Industry 4.0 and the popularization of smart terminal equipment, the interaction between industrial field information systems and production equipment has intensified. To meet the real-time transmission of time-triggered flow and the coordinated transmission of best effort flow, time-sensitive network-related technologies are used to implement flow queue forwarding by strictly following the gate control list. First, response-time analysis method is proposed to predict the upper bound of delay under a scheduling model following IEEE 802.1Qbv. Second, according to response-time analysis, a deadline monotonic scheduling algorithm with temporary priority expansion is proposed to divide the priority into more levels, which is not limited by the queue type, so as to ameliorate the transmission sequence of switch export flow. Finally, an adaptive priority adjustment scheduling algorithm with temporary priority expansion is designed to construct the optimal scheduling method further improving the scheduling success rate and reducing worst-case end-to-end delays. Compared with similar algorithms, the algorithm proposed improves the scheduling success rate by at least 30%, reduces the total delay by at least 21% and the TT flow delay by 11% in high network utilization conditions.

Along with methods such as Hidden Markov Model and Linear Discriminant Analysis, environmental sensors including temperature, humidity or carbon dioxide are used to estimate indoor occupancy, which have various applications. Most of the previous studies have neglected the time-dependent character of the indoor occupancy information or real-time response of the system. In this paper, we propose to use low invasive, fast-sampling infrared array sensors to collect data from the actual scene and establish the Inhomogeneous Hidden Markov Model to capture the time dependence of occupancy for buildings occupancy estimation. First, to avoid raw sensor datas susceptibility to external influences, the non-negative matrix factorization is adopted to reduce the dimension of the raw matrix and eliminate interferences caused by environmental changes. Second, the Softmax Regression Model is used to calculate the emission probability matrix for clarifying the dynamic relationship between environmental parameters and indoor occupancy, which is weak. Third, the Forward algorithm and the Viterbi algorithm are applied to achieve online and off-line estimation. Experiments are made with real recorded data. Our performance results demonstrate that method we proposed is effective for indoor occupancy estimation.

In recent years, underwater acoustic sensor networks (UASNs) have played an increasingly important role in ocean exploration. However, underwater sensor networks suffers from severe propagation attenuation, limited energy and sensor mobility compared with terrestrial networks. Also, the value of sensing data is quite different in some applications of underwater data collection. To tackle these challenges, this paper proposes a hierarchical collection strategy based on value of information (VoI). Taking account of the mobility of nodes close to sea level, we divide the network into two layers according to the Ekman drift current model. In the upper layer, the nodes move violently with the sea water. We adopt opportunistic routing to allow these nodes to search for the appropriate next hop nodes actively. Meanwhile, nodes in the lower layer are clustered. According to the rarity of the data received in the historical data, we propose a novel mathematical formula to measure the VoI of the data, and define the ratio of received data value to energy consumption as the evaluation index of network energy efficiency. AUV-aided transmission and multi-hop transmission are utilized separately to determine the tradeoff between energy consumption and network performance. The choice of transmission mode depends on the VoI in a cluster. Simulation results indicate that the proposed strategy shows satisfactory performance in improving energy efficiency.