Collaborative inference (CI) has emerged as a promising paradigm in mobile edge computing, where deep neural network (DNN) models are split and collaboratively processed by wireless devices and edge servers to reduce communication overhead and improve inference efficiency. Unmanned aerial vehicles (UAVs) with agile mobility present significant potential as edge servers in such systems. However, the limited computation resources of UAV servers and the inherent security vulnerabilities of ground-to-air channels pose challenges to UAV-assisted CI. To address these issues, this paper proposes a novel UAV-assisted CI framework via multi-exit DNNs and cooperative jamming. Specifically, this framework integrates an early-exit (EE) mechanism to alleviate computational burdens and employs a cooperative UAV jammer to transmit jamming signals to ensure secure split offloading. Our objective is to minimize total energy consumption while maximizing inference accuracy, subject to inference delay requirements and secure offloading rate constraints by jointly optimizing dual-UAV trajectories, EE selection, DNN partitioning, and computation resource allocation. To solve the formulated mixed-integer nonlinear programming problem, we first derive a closed-form solution for computation resource allocation and reformulate the optimization problem accordingly. We then develop an efficient alternating optimization algorithm that employs the successive convex approximation method for UAVs’ trajectory design and a discrete whale optimization algorithm for EE selection and DNN partitioning. Extensive simulation results demonstrate that the proposed scheme outperforms baselines.
Meng-Ru Wu, Hao-Nan Wu, Weidang Lu et al.· IEEE Transactions on Mobile...· 4 citations
Through bypassing the long-distance transmission of cloud services, Mobile Edge Computing (MEC) reduces response delay and ensures Quality-of-Service (QoS). In resource-constrained MEC, due to the strong coupling between service provisioning and task execution, reasonable service caching and resource allocation face many challenges on 1) coordinating the limited storage resources to improve cache hit rate, 2) allocating limited computing resources under delay constraints, and 3) sample collection and model training in dynamic environments. To address these important challenges, we propose CAMART, a novel service Caching and resource Allocation framework via Multi-Agent Reinforcement learning (MARL) with hierarchical knowledge Transfer in Digital Twin (DT) empowered Cloud-Edge Networks (DTCEN). Specifically, we first construct a new DTCEN to realize the mapping from physical to virtual networks. Next, we decouple the joint optimization of service caching and resource allocation into two sub-problems. For the service caching sub-problem, we design an improved MARL-based method to capture global information via a shared-feature extraction network and optimize caching and offloading decisions via a dual-head feature processing network. For the resource allocation sub-problem, we convert it into 0-1 integer programming and design an improved branch-and-bound-based method to reduce computational complexity while guaranteeing a high-quality solution set. Finally, we develop an original DT-driven hierarchical knowledge transfer mechanism to realize cross-scenario knowledge reuse and convergence acceleration. Using real-world datasets, extensive experiments are conducted to validate the superiority of the proposed CAMART. Compared to the state-of-the-art methods, CAMART achieves higher rewards, task completion rate, and cache hit rate in different scenarios.
Zheyi Chen, Jia-Yun Zheng, Hong-Ju Cheng et al.· IEEE Transactions on Mobile...· 1 citation
The rapid proliferation of Uncrewed Aerial Vehicles (UAVs) introduces significant challenges to low-altitude airspace security, particularly from unauthorized intrusions. To address these vulnerabilities, Integrated Sensing and Communication (ISAC) has emerged as a key enabler for anti-UAV systems. However, existing studies focusing on cellular networks with fixed base stations are ill-suited for the continuous movement of target UAVs, thus failing to meet the dual demands of flexible sensing and reliable positioning. To address this, we propose an ISAC-enabled anti-UAV scheme solely based on cooperative UAVs. Specifically, we first derive the optimal transmit power under the constraint of space-air transmission outage probability tolerance. Subsequently, we deduce the sensing Fisher information matrix and Cramér-Rao Bound (CRB) by incorporating the position uncertainty of the target UAV. Then, we formulate a long-term CRB minimization problem to enhance cooperative sensing performance. To tackle this NP-hard problem, we design a robust optimization algorithm that jointly optimizes transmit-receive beamforming, association scheduling, and UAV trajectory, by transforming the structurally complex CRB matrix into a set of semi-definite constraints, and resolving the inherent position uncertainty. Numerical results demonstrate that our proposed algorithm outperforms representative algorithms in terms of sensing accuracy and robustness.
Xiaojie Wang, Lingfei Li, Zhaolong Ning et al.· IEEE Transactions on Wireles...· 1 citation
Integrated Sensing, Communication, and Power Transfer (ISCPT) is a key enabler for sixth-generation networks, enhancing resource utilization to support massive low-power devices. However, existing research has predominantly focused on a single Uncrewed Aerial Vehicle (UAV) in communication and power transfer, lacking the capability to facilitate joint sensing and power transfer of multi-UAVs for moving targets considering estimation errors. To tackle the above challenge, we propose for the first time a multi-UAV-assisted ISCPT algorithm serving both multiple Communication Users (CUs) and Energy Receivers (ERs), featuring a sensing-assisted Wireless Power Transfer (WPT) framework. Specifically, we first derive the Fisher information matrix and Cramér–Rao bound for multi-ER positioning under location uncertainty. Then, we formulate a two-phase optimization problem where sensing directly refines location estimation to achieve robust WPT efficiency maximization. To solve the formulated NP-hard problems, we design a two-phase algorithm by jointly optimizing association scheduling with CUs and ERs, beamforming and trajectory design for UAVs, based on generalized Petersen’s sign-definiteness lemma, Lagrangian relaxation and S-procedure. Numerical results validate that the proposed algorithm achieves a maximum WPT efficiency improvement of 42.3% compared with several representative baseline schemes, demonstrating strong practicality for multi-UAV-assisted ISCPT networks.
Zhaolong Ning, Lingfei Li, Xiaojie Wang et al.· IEEE Journal on Selected Are...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
