In this paper, we study the distributed relay assignment problem in multi-channel multi-radio unmanned aerial vehicle (UAV) communication networks. Multi-UAVs are driven by the overall task and fly in certain formation, where drones with different tasks have various transmission requirements. Source UAVs equipped with multi-radio can select more than one relay radios to achieve high data rate, and each relay radio can be shared by multiple source UAVs. We construct distributed game models to promote the global transmission performance by self-organizing coordination among UAVs. Specifically, the channel competition relationship between relay UAVs is modeled as a congestion game model, while the task-driven relay selection among UAVs is modeled as a many-to-many matching market without substitutability. With the proposed game models, the optimizing of local optimized process will lead to the improvement of global transmission results. After that, we design algorithms for the stable and changeable topology structures, respectively. Based on the given formation shape of UAVs, a learning matching algorithm is proposed to reach the optimum result with a large probability. A fast potential matching algorithm is propose to deal with the topological change of UAV networks. We prove that two proposed algorithms can both achieve the stable matching results. Simulation results show that the proposed relay assignment approaches yield good performances in terms of the global transmission satisfaction and fairness. Particularly, the result of the learning algorithm is close to the global optimum and the fast potential matching approach is robust to the perturbation of UAV networks.

In this paper, we study the multi-task cooperation problem for unmanned aerial vehicle (UAV) swarms, where the UAV energy consumption is taken into consideration during location scheduling and task implementation. One task may need the cooperation of several UAVs with specific capabilities. To avoid unreasonable task allocation, we quantify the mission properties of UAVs and task areas. We comprehensively consider the overlapping and complementary relationship of the UAV’s task types, so that UAVs can form corresponding collective execution tasks according to the task attributes. Based on the coalition game theory, we model the distributed task assignment problem of UAVs as a coalition formation game (CFG). We propose a task allocation algorithm, and then prove that it can achieve the joint optimization of energy and task completion by decision-making of UAVs in finite iterations. With the equilibrium properties of coalition formation in UAV networks, we further optimize the position of UAVs to minimize the network energy consumption. Simulation results verify that the proposed method can reduce the flight loss with high task completion degree.

In this paper, we consider a social-aware unmanned aerial vehicle (UAV) assisted mobile crowd sensing (MCS) system for disaster relief networks, and investigate how to recruit suitable UAVs to perform sensing tasks in stochastic and dynamic environments (both UAVs and tasks arrive stochastically). We formulate the task assignment problem into a dynamic matching problem, and propose a multiple-waitlist based task assignment (MWTA) algorithm to find the stable matching in time-varying environment. We prove that MWTA can achieve the dynamic stability containing the strategy-proofness, efficiency, and envy-freeness. Simulation results demonstrate the performance improvement of our proposed scheme compared with the traditional matching algorithm applied to deterministic matching model in stochastic setting.

In this paper, we study the unmanned aerial vehicle (UAV)-enabled opportunistic data collection in wireless sensor networks (WSNs). The UAV performing remote missions is expected to collect data from the WSN during the return flights. Due to the specified task and safety restrictions, flight trajectory and time of the UAV are strictly constrained, resulting in the limited coverage ability in the data collection process. Moreover, the unknown distribution of active sensors makes it difficult for ground sensors and the UAV to complete the off-line optimization of flight mode and transmission. To tackle these problems, we develop an air-ground collaborative online planning method. On one hand, ground sensors actively form terrestrial transmission clusters to improve the data upload efficiency. After analyzing the line-of-sight (LoS) reliability and transmission correlation, we construct a coalition formation game model for the clustering of ground sensors. We discuss the equilibrium property of the game model, which can be achieved by the proposed distributed coalition formation algorithm. On the other hand, to avoid conflicts during the data collection, a data upload protocol is designed. We further discuss various flight speed planning schemes based on different detection capabilities of the UAV. The simulation results show that the performance of ground coalition-based air-ground collaborative online optimization is much better than that of the unilateral data collection by the UAV. Moreover, UAV flight online planning can further improve data uploading efficiency.

With the development of access technologies and artificial intelligence, a deep reinforcement learning (DRL) algorithm is proposed into channel accessing and anti-jamming. Assuming the jamming modes are sweeping, comb, dynamic and statistic, the DRL-based method through training can almost perfectly avoid jamming signal and communicate successfully. Instead, in this paper, from the perspective of jammers, we investigate the performance of a DRL-based anti-jamming method. First of all, we design an intelligent jamming method based on reinforcement learning to combat the DRL-based user. Then, we theoretically analyze the condition when the DRL-based anti-jamming algorithm cannot converge, and provide the proof. Finally, in order to investigate the performance of DRL-based method, various scenarios where users with different communicating modes combat jammers with different jamming modes are compared. As the simulation results show, the theoretical analysis is verified, and the proposed RL-based jamming can effectively restrict the performance of DRL-based anti-jamming method.

In this paper, we investigate the problem of opportunistic UAV transmission in D2D communication networks. UAVs are supposed to help transmissions of D2D users when they are employed to perform flying missions with given trajectories. On one hand, users can select appropriate UAVs as real-time relays according to the topology in the sky at different moments. On the other hand, due to flight characteristics, UAVs can receive the uploading data when they are approaching transmitters, and then offload the data to corresponding receivers in the appropriate later time. Users need to select and adjust transmission modes dynamically, including multi-UAV selection, time allocation of data loading and offloading, as well as the competition of channel access. We design a hierarchical game model to analyze the complicated relationship among devices. Specifically, a predictable dynamic matching market is constructed to address the issue of UAV selection and time allocation, while the problem of channel access is studied by the congestion game. After that, distributed algorithms are proposed and the properties of convergence are discussed. Simulation results confirm that the effective opportunistic UAV transmission approach can improve the global network significantly, while unreasonable optimization approaches may lead to the decline of the transmission performance.