Accidents often occur at sea, so effective maritime search and rescue is essential. In the current process of sea search and rescue, the operation efficiency of large search and rescue equipment is low and it can't provide stable communication link. In this paper, UAVs (Unmanned Aerial Vehicles) and USVs (Unmanned Surface Vehicles) are used to form a cognitive mobile computing network for cooperative search and rescue, and RL (Reinforcement Learning) is used to plan search path and improve communication throughput. Based on the scene of marine search and rescue, the grid method is used to model the search and rescue area. Meanwhile, an intra-group communication architecture based on UAVs and USVs is designed to assist intra-group communication by recognizing the link channel state between UAVs. Search and rescue path planning is carried out through the strategy iteration of MDP (Markov Decision Process). Furthermore, In addition, distributed RL is used to recognize the channel state and perform mobile computing, so as to optimize the data throughput in the communication group. The simulation results show that we have successfully completed the path planning task. Compared with conventional methods, RL based on different reward functions has better throughput performance under the same number of UAV auxiliary communications.

Unmanned aerial vehicles (UAVs) are widely used in Internet-of-Things (IoT) networks, especially in remote areas where communication infrastructure is unavailable, due to flexibility and low cost. However, the joint optimization of locations of UAVs and relay path selection can be very challenging, especially when the numbers of IoT devices and UAVs are very large. In this paper, we formulate the joint optimization of UAV locations and relay paths in UAV-relayed IoT networks as a graph problem, and propose a graph neural network (GNN)-based approach to solve it in an efficient and scalable way. In the training procedure, we design a reinforcement learning-based relay GNN (RGNN) to select the best relay path for each user. The theoretical analysis shows that the time complexity of RGNN is two orders lower than the conventional optimization method. Then, we jointly exploit location GNN (LGNN) and RGNN trained to optimize the locations of all UAVs. Both GNNs can be trained without relying on the training data, which is usually unavailable in the context of wireless networks. In inference procedure, LGNN is first used to optimize the location of UAVs, and then RGNN is used to select the best relay path based on the output of LGNN. Simulation results show that the proposed approach can achieve comparable performance to brute-force search with much lower time complexity when the network is relatively small. Remarkably, the proposed approach is highly scalable to large-scale networks and adaptable to dynamics in the environment, which can hardly be achieved using conventional methods.

In the sixth-generation (6G) networks, newly emerging diversified services of massive users in dynamic network environments are required to be satisfied by multi-dimensional heterogeneous resources. The resulting large-scale complicated network optimization problems are beyond the capability of model-based theoretical methods due to the overwhelming computational complexity and the long processing time. Although with fast online inference and universal approximation ability, data-driven deep learning (DL) heavily relies on abundant training data and lacks interpretability. To address these issues, a new paradigm called knowledge-driven DL has emerged, aiming to integrate proven domain knowledge into the construction of neural networks, thereby exploiting the strengths of both methods. This article provides a systematic review of knowledge-driven DL in wireless networks. Specifically, a holistic framework of knowledge-driven DL in wireless networks is proposed, where knowledge sources, knowledge representation, knowledge integration and knowledge application are forming as a closed loop. Then, a detailed taxonomy of knowledge integration approaches, including knowledge-assisted, knowledge-fused, and knowledge-embedded DL, is presented. Several open issues for future research are also discussed. The insights offered in this article provide a basic principle for the design of network optimization that incorporates communication-specific domain knowledge and DL, facilitating the realization of intelligent 6G networks.

The sixth generation (6G) wireless networks are envisioned to feature wide-area coverage, diversified full-scenario services, massive connections and dynamic heterogeneity, resulting in large-scale and complex network optimization problems. Traditional model-based methods, while effective in simple scenarios with precise mathematical models, struggle with high computational intensity and long processing times in the realistic and intricate applications of 6G. Pure data-driven deep learning (DL) methods offer powerful approximation capabilities and fast online inference but are hindered by insufficient datasets and poor interpretability. To address these issues, knowledge-driven DL integrates domain knowledge into neural networks, combining the strengths of both model-based and data-driven approaches. This survey systematically reviews knowledge-driven DL in wireless networks from a novel perspective of the knowledge integration approach. It provides a comprehensive definition of domain knowledge in wireless networks and clarifies the types of knowledge and their representations that can be integrated into neural networks. Furthermore, a leading taxonomy of knowledge integration approaches in wireless networks is proposed, encompassing the integration of domain knowledge into neural network model selection, neural network model customization, knowledge and data fusion architecture construction, loss function design, and hyperparameter configuration. Based on this taxonomy, literature on knowledge-driven resource allocation and signal processing is thoroughly reviewed. This survey aims to provide an insightful guideline for effectively incorporating domain knowledge into neural networks in the field of wireless communications, ultimately advancing efficient and reliable intelligent 6G networks.

Pre-caching popular videos at base stations (BSs) is a cost-effective way to significantly alleviate the backhaul pressure. With the video caching, the cache placement and the transmission strategy are intertwined with each other and jointly affect the system performance. Furthermore, the cache placement is updated in a much longer timescale than the transmission strategy. In this paper, the long-term transmission-aware cache placement and the short-term transmission strategy are designed to enhance the quality of experience (QoE) for the video streaming in cloud radio access networks (cloud-RANs). Specifically, consider a cache-enabled cloud-RAN, video contents are cached at BSs, and user requests are cooperatively satisfied by multiple BSs via the cooperative beamforming. To improve the weighted sum of users' QoE, the long-term transmission-aware caching problem in the caching phase and the short-term transmission problem in the delivery phase are respectively formulated, taking into account the backhaul capacity constraint, the transmission power constraint, and the storage size constraint. For the caching problem, the sample average approach is first used to approximate the long-term average QoE value. Then, cache placement strategies are devised in both centralized and distributed manner. For the transmission problem, the full-cooperative beamforming scheme is studied with the optimized cache placement, and an iterative algorithm is proposed. Simulation results show that our proposed transmission-aware cache placement and transmission strategies can achieve higher QoE performance than other cache placement and transmission strategies.