Lossy image compression can reduce the bandwidth required for image transmission in a network and the storage space of a device, which is of great value in improving network efficiency. With the rapid development of deep learning theory, neural networks have achieved great success in image processing. In this paper, inspired by the diverse extent of attention in human eyes to each region of the image, we propose an image compression framework based on semantic analysis, which creatively combines the application of deep learning in the field of image classification and image compression. We first use a convolutional neural network (CNN) to semantically analyze the image, obtain the semantic importance map, and propose a compression bit allocation algorithm to allow the recurrent neural network (RNN)-based compression network to hierarchically compress the image according to the semantic importance map. Experimental results validate that the proposed compression framework has better visual quality compared with other methods at the same compression ratio.

Low Earth Orbit (LEO) satellite networks can provide complete connectivity and worldwide data transmission capability for the internet of things. However, arbitrary flow arrival and uneven traffic load among areas bring about unbalanced traffic distribution over the LEO constellation. Therefore, the routing strategy in LEO networks should have the ability to adjust routing paths based on changes in network status adaptively. In this paper, we propose a Two-Hops State-Aware Routing Strategy Based on Deep Reinforcement Learning (DRL-THSA) for LEO satellite networks. In this strategy, each node only needs to obtain the link state within the range of two-hop neighbors, and the optimal next-hop node can be output. The link state is divided into three levels, and the traffic forwarding strategy for each level is proposed, which allows DRL-THSA to cope with link outage or congestion. The Double-Deep Q Network (DDQN) is proposed in DRL-THSA to figure out the optional next hop by inputting the two-hops link states. The DDQN is analyzed from three aspects: model setting, training process and running process. The effectiveness of DRL-THSA, in terms of end-to-end delay, throughput, and packet drop rate, is verified via a set of simulations using the Network Simulator 3 (NS3).

With the development of wireless sensor network technology, the routing strategy has important significance in the Internet of Things. An efficient routing strategy is one of the fundamental technologies to ensure the correct and fast transmission of wireless sensor networks. In this paper, we study how to combine deep learning technology with routing technology to propose an efficient routing strategy to cope with network topology changes. First, we use the recurrent neural network combined with the deep deterministic policy gradient method to predict the network traffic distribution. Second, the multi-hop node state is considered as the input of a double deep Q network. Therefore, the nodes can make routing decisions according to the current state of the network. Multi-hop state-aware routing strategy based on traffic flow forecasting (MHSA-TFF) is proposed. Simulation results show that the MHSA-TFF can improve transmission delay, average routing length, and energy efficiency.

Due to the time-varying and non-uniform terrestrial traffic requirements, efficiently utilizing limited satellite resources to match non-uniform traffic demands brings challenges for Low Earth Orbit (LEO) beam-hopping (BH) technology. Existing LEO BH systems typically assume the fixed beam coverage sizes, potentially leading to resource congestion or wastage. In this letter, we present a novel multi-satellite collaborative two-dimensional load-balancing beam-hopping scheme based on dynamic beam coverage (MSDBC-BH), which encompasses both inter-beam load balancing and inter-satellite load balancing. This letter proposes the dynamic beam coverage design to achieve effective inter-beam load balancing. Additionally, a cell-satellite assignment scheme based on a game-matching algorithm is introduced to satisfy inter-satellite load balancing. Simulation results illustrate that the proposed MSDBC-BH effectively addresses the load imbalance among satellites and improves system throughput.

Satellite constellation design is crucial to meet the increasing demand for seamless global coverage. In this paper, we propose a dual-layer satellite constellation with satellites deployed collaboratively in different orbital altitudes and inclinations to achieve enhanced coverage while avoiding resource redundancy and cost surges caused by single-layer constellation deployment. Firstly, by deriving the coverage of the Walker constellation, we design the minimum number of satellites in a single orbit to achieve maximum continuous coverage. Subsequently, we study how orbital parameters affect coverage performance, user requirements, and satellite lifetime. We aim to design a dual-layer satellite constellation by leveraging different orbital altitudes, inclinations, and other key parameters. Additionally, we analyze the cost constraints and utilize an adaptive Particle Swarm Optimization (PSO) algorithm to address the multi-objective optimization constellation design problem. Simulation results confirm the effectiveness of our dual-layer satellite constellation in achieving seamless global coverage, particularly in enhancing coverage in mid-latitude and low-latitude hotspots. Moreover, the dual-layer constellation can increase capacity with fewer satellites, meet quality of service (QoS) requirements, and reduce deployment costs.

Spectrum sharing of wireless vehicle-to-vehicle (V2V) communication and automotive radar in intelligent transportation systems (ITS) can provide higher spectrum utilization efficiency. However, spectrum sharing between two systems might bring severe interference, which needs to be well solved. To address the communication-radar spectrum sharing (CRSS) and inter-system interference issue, we first model the radar interference estimation as an off-grid compressed sensing problem. Then, we propose an interference cancellation algorithm based on the atomic norm (AN) minimization theory. Simulation results show that the proposed algorithm facilitates the coexistence between radar and communication and improves the V2V communication performance efficiently in the presence of automotive radar interference.