Unmanned aerial vehicles (UAVs) have become indispensable tools in logistics, mapping, and disaster response, etc. However, effective cooperation among multiple UAVs remains challenging due to limited direct communication and energy constraints in aerial environments. Conventional device-to-device (D2D) frameworks on the ground are insufficient to cope with the complexity in UAV-assisted networks, such as frequent topology variation, interference fluctuation, and battery power. To overcome these limitations, this paper proposes a semantic-aware cellular D2D communication architecture, namedAirtalking, which integrates semantic encoding and decoding to enable efficient UAV-to-UAV (U2U) data exchange. Unlike traditional bit-level transmission, semantic communication focuses on delivering essential information, thereby reducing payload size and improving time and energy efficiency. We design algorithms to balance latency and energy consumption and simulate with different scheduling policies under varying flight conditions. The results show that the proposed aerial U2U framework can improve communication stability and efficiency, demonstrating the feasibility of deploying semantic communication in practical multi-UAV systems.

With the continuous innovation in manufacturing, Unmanned Aerial Vehicles (UAVs) have gradually become commodities from just professional equipment. As a universal type, quadrotor UAV allows us to see its potential for applications in multiple fields. Moreover, in the brand new field of aerial computing, UAVs have started to play a leading role in providing computing services to mobile users. However, limited by the performance of onboard equipment, we often cannot rely on one UAV to complete complex computing tasks. This paper first carries out a real-world case study and discovers the importance of flying attitude in applying quadcopter UAVs to achieve aerial edge computing. Then in designing the collaboration algorithms, we apply Monte Carlo Tree Search (MCTS) to realize the independent operations of UAVs while assisting each other in accomplishing the common goals. In performance evaluation, we compare the performance of our proposed solution with the existing methods. Finally, the results show that our MCTS-based algorithm can implement efficient collaboration among UAVs while reducing energy consumption and time cost in providing AEC services.

Improving ship classification performance in synthetic aperture radar (SAR) imagery by the methods based on transfer learning (TL) is a newly emerging research topic and has great potential. The existing studies merely address the problem of transfer learning from a single source domain (AIS or ORS) to the target domain (SAR) based on the homogeneous transfer learning (HoTL) which requires all domains are represented by homogeneous features with same dimensions. Our work takes a step forward and attempts to address a more meaningful and challenging problem that transfers knowledge from multiple source domains for the purpose of exploring and exploiting complementarity cross source domains to assist ship classification in the target domain. To this end, our study develops a multi-source heterogeneous transfer learning (MS-HeTL) method which liberates the restriction of utilizing the exact same features for all domains, allows each domain represented by a more appropriate feature and thus improves the ship classification performance even further. Specifically, we first propose multi-source heterogeneous feature augmentation (MS-HFA) to effectively solve the challenges brought by feature heterogeneity and fully exploit the complementarity cross domains. Then a support vector machine (SVM) classification framework is specific-designed to be incorporated with the augmented feature representations in the common space to conduct knowledge transfer cross domains. Extensive experiments on two benchmark datasets, HR-SAR and FUSAR, show that the proposed method outperforms the existing methods, and demonstrates its effectiveness and advantages. All datasets and source codes are available at https://github.com/BUCT-RS-ML/MS-HeTL-via-MS-HFA.

Fog computing provides new ideas for solving big data problems in the Internet of Things (IoT) era. With fog, we can save much time on long-distance transmission, thereby increasing the efficiency of network service. However, to transform fog computing from a technology to a service, we first need to properly handle the trading relationship between users and service provider in fog. In this paper, we design an efficiency-aware dynamic service pricing strategy to optimize the payoffs of both users and provider in fog computing. In the modeling, we design a Stackelberg competition-based model while regarding provider as the market leader, and each individual user as a follower. Users in this model care about how to obtain the most cost-effective services. And provider pays attention to taking full advantage of the geo-distributed characteristic in setting prices with multiple customers. In the performance evaluation part, we carry out experiments using real-world datasets to simulate this continuous negotiation process between supply and demand in fog pricing. The results show that our strategy can solve the dual-objective optimization problem while establishing a stable trading relationship between the two sides.

As one of the most striking research hotspots in both academia and industry, Internet of Things (IoT) has been constantly changing our daily life by joining together nearly all we can imagine. From home furnishings and vehicles to urban facilities, all these smart things need powerful managing and processing capabilities to deal with mass multimedia data in different content forms such as images, audios, and videos. Nowadays, since Moore's Law is no longer applicable, conventional thinking may not be adequate in facing the explosive growing amount of data. Hence, in this paper, we adopt the idea of in-memory processing to solve the problem of real-time multimedia big data computing in IoT. We apply closed-loop feedback in the scheduling method design to integrate in-memory storages of all devices within a 3-tier network structure. In addition, we consider the respective conditions of different real-time required levels and content forms. The analysis results show that our scheduling method can achieve better workload allocation with less latency in comparison of existing methods.

The current boom in the Internet of Things (IoT) is changing daily life in many ways, from wearable devices to connected vehicles and smart cities. We used to regard fog computing as an extension of cloud computing, but it is now becoming an ideal solution to transmit and process large-scale geo-distributed big data. We propose a Byzantine fault-tolerant networking method and two resource allocation strategies for IoT fog computing. We aim to build a secure fog network, called “SIoTFog,” to tolerate the Byzantine faults and improve the efficiency of transmitting and processing IoT big data. We consider two cases, with a single Byzantine fault and with multiple faults, to compare the performances when facing different degrees of risk. We choose latency, number of forwarding hops in the transmission, and device use rates as the metrics. The simulation results show that our methods help achieve an efficient and reliable fog network.

Energy internet is now an industry hot spot which enables the interconnection and sharing of energy just like the Internet. Inspired by the concept of energy internet, this paper will focus on a designed energy distribution network, using city bus lines running Electric Vehicles (EV) to achieve electric power storage and transmission. This network is made of renewable energy sources providing power, charge stations for power exchange and bus lines as delivery, electric buses serving as the carriers of flowing power in network. This paper will mainly discuss and solve the problem of placing charge stations on city bus map to compose the network framework. Our work includes two optimization algorithms using some ideas of graph theory, simulating with real-world transporting data of different city maps and analyzing the results to evaluate efficiency as well as advantages and disadvantages on algorithms and data sets.