Edge Intelligence (EI) combines edge computing and artificial intelligence to deliver low-latency and resource-efficient services. Integrated Sensing and Communication (ISAC) further empowers EI by enhancing edge perception and accelerating intelligent model training. However, integrating ISAC into EI complicates the coordination of dynamically varying sensing, communication, and computation resources, especially under device mobility and unpredictable network conditions, leading to degraded service performance. To address these coordination challenges and sustain high-quality service under mobility and dynamics, we aim to design an adaptive service provision framework that tightly couples real-time perception with intelligent decision-making at the edge. Specifically, we propose an adaptive service provision architecture for ISAC-assisted EI, where Digital Twins (DTs) hosted on edge servers represent edge devices and their contexts to enable accurate perception and intelligent decision-making, thereby enhancing the efficiency of ISAC-enabled services. By dynamically migrating DTs across edge servers based on device mobility and resource availability, the system supports continuous decision-making and seamless service delivery. We further integrate convex optimization for efficient multi-resource coordination and a Time-Varying Contextual Bandit (TVCB) algorithm to enable adaptive, context-aware DT migration in dynamic environments. Extensive simulations demonstrate that our approach significantly improves service quality, reliability, and adaptability in ISAC-assisted EI systems, reducing migration oscillations and overhead while achieving lower latency and higher utility compared with representative baselines.

Edge intelligence deploys artificial intelligence models on edge nodes proximal to data sources, and delivers real-time inference support for resource-constrained devices. To realize this vision, inference offloading differs from conventional computation offloading by tailoring offloading strategies to the intrinsic characteristics of AI inference tasks. In this field, existing researchs generally lack fine-grained model partitioning capabilities and long-term resource adaptability, failing to optimize resource utilization and sustain stable performance in mobile environments. To address these issues, we propose an adaptive inference acceleration framework that dynamically partitions inference models into hierarchical subtasks and offloads these subtasks to heterogeneous edge servers. We formulate a joint optimization problem for task partitioning, offloading and resource allocation, which takes queue stability as the constraint and aims to minimize the long-term average task completion time. To realize the optimal trade-off between latency and stability without future state prediction, we adopt Lyapunov optimization to decompose the long-term stochastic optimization into slot-by-slot solvable deterministic subproblems. For these slot-by-slot subproblems, we design a Q-network Mixing (QMIX)-based multi-agent reinforcement learning method to enable collaborative strategy selection across edge servers. Experimental simulations show that, compared with baseline algorithms including the greedy, genetic and MAD2RL methods, our proposed framework achieves a substantial reduction in task completion time while preserving inference accuracy and queue stability.

Edge intelligence enhances the computational capabilities of resource-limited devices by offloading inference tasks to edge servers. Traditional methods either execute the entire model on the device, resulting in slow inference, or fully offload it to the server, incurring communication delays and privacy risks due to raw data transmission. Model partitioning addresses these challenges by splitting the model for execution on both the device and edge server, transmitting only intermediate inference results. However, current model partitioning methods lack consideration of device mobility, resulting in reduced inference efficiency and task interruptions. To address these limitations, we introduce MobiSplit, a novel mobility-aware framework that dynamically partitions inference models between resource-constrained devices and edge servers. MobiSplit adapts to real-time device mobility, fluctuating network conditions, and computational constraints to minimize inference latency and energy consumption while ensuring robust task execution. Additionally, we propose a distributed auction-based algorithm that empowers edge devices to autonomously determine optimal partitioning and offloading strategies in a scalable and adaptive manner. Extensive simulations demonstrate that MobiSplit enhances inference efficiency, achieving a 60% latency reduction and a 20% energy consumption decrease compared to the best-performing baseline across diverse edge scenarios.

Internet of Vehicles (IoV), when empowered by aerial communications, provides vehicles with seamless connections and proximate computing services. The unpredictable network dynamics of aerial-assisted IoV pose challenges to the resource allocation. In this article, dynamic digital twin (DT) of aerial-assisted IoV is established to capture the time-varying resource supply and demands, so that unified resource scheduling and allocation can be performed. We design a two-stage incentive mechanism for resource allocation based on Stackelberg game where DT of vehicles or road side units (RSUs) is deemed as the leader, and the RSUs who provide computing services are as the follower. In the first stage incentive, we determine the computing resources that RSUs are willing to offer according to vehicles’ preferences. To further maximize the satisfaction of vehicles and the overall energy efficiency, a distributed incentive mechanism based on alternating direction method of multipliers (ADMMs) is then designed, in which the resource allocation policy for each vehicle is optimized. Thanks to ADMM, the incentive mechanism can be run at multiple RSUs in parallel to reduce delay and relieve the computational burden of UAVs. Simulation results show that the proposed scheme can improve the satisfaction of vehicles and the energy efficiency at the same time.

The Internet of Things (IoT), while providing comprehensive interconnection and ubiquitous services, poses security issues by enabling resources sharing among various devices from different untrusted authorities. Blockchain, as a distributed ledger, provides a traceable and verifiable platform to ensure the secure access control in IoT. The existing works based on blockchain may bring up intolerable computing overhead and delay to the lightweight IoT devices. In this article, we propose a dynamic and lightweight attribute-based access control framework for blockchain-empowered IoT, to achieve secure and fine-grained authorization. The proposed scheme allows access to resources by evaluating attributes, operations, and the environment relevant to a request. The access policy is executed through smart contract in blockchain for security and flexibility. To further adapt to IoT device constraints, we design a access control framework based on decentralized application (DApp), which can maintain tamper proof in a timely manner and be adapt to the delay-intolerant application. When delay-intolerant access is required, access can be allowed according to local replica of the blockchain, without a consensus of blockchain network. Considering the time-varying attributes of IoT devices, a trust management scheme is proposed based on the Markov chain to resist the security fluctuation caused by the vulnerability of IoT devices. In the experiments, we deploy our system prototype on Ethereum to evaluate the feasibility and effectiveness of the scheme. The results show the proposed scheme can achieve secure, high throughput, and flexible access control in IoT.

Internet of Vehicles (IoV) can realize seamless communication connection and computing offloading services with the assistance of air communication. Limited by the high network dynamics of the air-assisted IoV, resource allocation faces great challenges. In this paper, dynamic digital twin of air-assisted IoV is established to capture the time-varying resource supply and demands, so that unified resource scheduling and allocation can be performed. We designed an incentive mechanism for resource allocation based on Stackelberg games to maximize vehicle satisfaction and overall energy efficiency. In the game, the digital twin of air-assisted IoV within the coverage of unmanned aerial vehicles (UAV) are regarded as leaders, while RSUs that provide computing services are followers. At the same time, in order to reduce the delay and reduce the computational burden of the UAV, a distributed incentive mechanism based on the Alternating Direction Multiplier Method (ADMM) was designed to optimize the resource allocation strategy of each RSU. Simulation results show that the proposed scheme can improve the satisfaction of vehicles and the energy efficiency at the same time.

Mobile edge computing (MEC), as a promising technology, provides proximate and prompt computing service for mobile users on various applications. With appropriate incentives, profit-driven users can offload multi-task requests across heterogeneous edge servers. However, such incentive trade lacks a trustworthy platform. Due to the decentralized nature of MEC, trading information from players is easily tampered with by edge servers, which poses a threat to cross-server resource allocation. In this paper, we jointly consider incentives and cross-server resource allocation in blockchain-driven MEC, where the blockchain prevents malicious edge servers from tampering with player information by maintaining a continuous tamper-proof ledger database. Particularly, we propose two double auction mechanisms, namely a double auction mechanism based on breakeven (DAMB) and a more efficient breakeven-free double auction mechanism (BFDA), in which users request multi-task service with claimed bids and edge servers cooperate with each other to serve users. A delegated proof of stake (DPoS) based blockchain technology is leveraged to realize decentralized, untampered, safe and fair resource allocation consensus mechanism. The simulation results show that the proposed DAMB and BFDA can significantly improve the system efficiency of MEC.

In IoT, a flexible and trustworthy access control framework is of significance to ensure the security of lightweight IoT devices. The conventional centralized access control framework is no longer fit for the open and large-scale IoT environments. In this paper, we propose an attribute-based distributed access control framework (ADAC) for IoT using blockchain technology. The attributes, such as manufacturer and object-specified attribute, are considered in the proposed ADAC for more fine-grained access control in the open and lightweight IoT devices. Particularly, we design a smart contract system, which includes a subject contract (SC), an object contract (OC), an access control contract (ACC) and multiple policy contracts (PCs), to manage and access attributes of IoT devices for distributed and trustworthy access control (DTAC). SC and OC are responsible for managing subject attribute and object attribute information, respectively. PCs are used to manage access control policies. ACC performs authorization judgment by accessing attributes and policies. Finally, a case study is performed to demonstrate the workflow and show that ADAC could achieve fine-grained and flexible access control for IoT.