The intelligent reflecting surface (IRS) and unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) system is widely used in temporary and emergency scenarios. Our goal is to minimize the energy consumption of the MEC system by jointly optimizing UAV locations, IRS phase shift, task offloading, and resource allocation with a variable number of UAVs. To this end, we propose a flexible resource scheduling (FRES) framework by employing a novel deep progressive reinforcement learning that includes the following innovations. First, a novel multitask agent is presented to deal with the mixed integer nonlinear programming (MINLP) problem. The multitask agent has two output heads designed for different tasks, in which a classified head is employed to make offloading decisions with integer variables while a fitting head is applied to solve resource allocation with continuous variables. Second, a progressive scheduler is introduced to adapt the agent to the varying number of UAVs by progressively adjusting a part of neurons in the agent. This structure can naturally accumulate experiences and be immune to catastrophic forgetting. Finally, a light taboo search (LTS) is introduced to enhance the global search of the FRES. The numerical results demonstrate the superiority of the FRES framework, which can make real-time and optimal resource scheduling even in dynamic MEC systems.

This paper investigates a dynamic game framework for physical layer security (PLS)-aware wireless network with third-party collaborative users (TCUs). In the considered system, legitimate users (LUs) aim to transmit secret signals under the threat of eavesdroppers (EVs). There exists TCUs rationally selecting to form coalitions with LUs or EVs, strategically enhancing the secrecy transmission rates for LUs or increasing eavesdropping rates for EVs to obtain rewards. Due to the unpredictability of wireless systems (e.g., time-varying channel conditions, user mobility), coalitions among the three parties may be unfixed and dynamically changing. A hierarchical game integrating a matching subgame with a coalition formation subgame is formulated to model the interactions among LUs, EVs, and TCUs. In order to derive the optimal long-term strategies while solving the equilibrium of the hierarchical game, we first introduce a constrained Gale-Shapley algorithm which determines the optimal power, mode, and channel selections of TCUs with the known coalition partition, and then propose a coalition selection algorithm for reaching the stability of coalition partitions. Moreover, we develop a deep reinforcement learning (DRL)-based solution to concatenate the aforementioned algorithms, producing the long-term optimal strategies for LUs, EVs and TCUs over multiple time slots. Simulations evaluate the performance of the proposed scheme, and demonstrate its superiority over counterparts.

In intelligent transportation systems (ITSs), integrating pedestrians and vehicles into traffic management models is essential for developing realistic and safe solutions. However, current systems often fail to simulate complex, real-world scenarios due to the absence of a comprehensive digital twin framework across diverse traffic environments and effective modeling of pedestrian-vehicle interactions. In this article, we propose a surveillance video-assisted federated digital twin (SV-FDT) framework to enhance ITSs by incorporating pedestrians and vehicles into the control loop. SV-FDT improves computational efficiency and communication performance by transmitting only semantic data and agent parameters, rather than raw video streams. The proposed framework adopts three-layer architecture and constructs detailed pedestrian-vehicle interaction models using multi-source traffic surveillance videos. The three-layer architecture includes: (i) an end layer that collects surveillance videos from multiple sources; (ii) an edge layer that performs self-supervised semantic segmentation to extract interactions, converts them into executable traffic codes, and generates local digital twin systems (LDTSs) for regional traffic modeling; and (iii) a cloud layer that integrates LDTSs into a real-time global digital twin model. Key design considerations, challenges, and practical implementation guidelines are discussed for SV-FDT, and a testbed evaluation is used to show that SV-FDT improves traffic flow, reduces mirroring delay, and enhances recognition accuracy and system efficiency compared to traditional terminal-server frameworks. Finally, we outline open challenges and potential directions for future research in digital twin-enabled ITS.

In this paper, we study the energy-efficient unmanned aerial vehicle (UAV) swarm assisted mobile edge computing (MEC) with dynamic clustering and scheduling. In the considered system model, UAVs are divided into multiple swarms, with each swarm consisting of a leader UAV and several follower UAVs. These UAVs serve as mobile edge servers, providing computing services to their covered ground end-users. Unlike existing works, we allow UAVs to dynamically cluster into different swarms, in other words, each follower UAV can change its leader based on the time-varying spatial positions, updated application placement, etc. in a dynamic manner. With the objective of maximizing the long-term energy efficiency of the UAV swarm assisted MEC system, a joint optimization problem of UAV swarm dynamic clustering and scheduling is formulated. Considering the inherent cooperation and competition among intelligent UAVs, we further reformulate this problem as a combination of a series of strongly interconnected multi-agent stochastic games, and theoretically prove the existence of the corresponding Nash Equilibrium (NE). Then, we propose a novel reinforcement learning based UAV swarm dynamic coordination (RLDC) algorithm for obtaining such an equilibrium. Furthermore, the convergence and complexity of the RLDC algorithm are analyzed. Simulations are performed to evaluate the performance of RLDC and illustrate its superiority compared to existing approaches.