关键词： Task analysis   Industrial Internet of Things   Smart manufacturing   Servers   Computational modeling   Energy consumption   Data models   Deep reinforcement learning   differential privacy   federated learning   industrial Internet of Things   mobile edge computing  

摘要： Industry 5.0 facilitates the intelligent upgrade of smart factories in Industrial Internet of Things (IIoT), and also introduces a plethora of data processing challenges. Mobile edge computing offloads data to edge servers for processing, easing the data processing pressure and reducing system cost. However, smart factories contain numerous sensitive information, and offloading them to edge servers directly may pose a risk of data leakage. To address these challenges, we investigate a local-edge collaborative smart factory system. Specifically, we first model the tasks as a directed acyclic graph, and formulate the offloading problem as a Markov decision process, considering the optimization of latency, energy consumption and the number of overtime tasks. Then, we propose a security-aware computation offloading method using federated reinforcement learning in IIoT, named SCOF. SCOF employs federated learning, keeping data for local computation and uploading model parameters to edge servers for aggregation. The data transmission passes through an artificial noise channel to protect against eavesdropping. Meanwhile, SCOF utilizes differential privacy to protect data security and employs deep reinforcement learning for selecting near-optimal offloading decisions. Finally, abundant experiments are conducted under a real dataset. The results show that SCOF has better perfomance than the state-of-the-art baseline algorithms.

关键词： And reliability   data caching   data dissemination   distributed consensus   efficiency   mobile edge computing   And reliability   data caching   data dissemination   distributed consensus   efficiency   mobile edge computing  

摘要： Mobile edge computing (MEC) enables web data caching in close geographic proximity to end users. Popular data can be cached on edge servers located less than hundreds of meters away from end users. This ensures bounded latency guarantees for various latency-sensitive web applications. However, transmitting a large volume of data out of the cloud onto many geographically-distributed web servers individually can be expensive. In addition, web content dissemination may be interrupted by various intentional and accidental events in the volatile MEC environment, which undermines dissemination efficiency and subsequently incurs extra transmission costs. To tackle the above challenges, we present a novel scheme named EdgeDis that coordinates data dissemination by distributed consensus among those servers. We analyze EdgeDis's validity theoretically and evaluate its performance experimentally. Results demonstrate that compared with baseline and state-of-the-art schemes, EdgeDis: 1) is 5.97x - 7.52x faster;2) reduces dissemination costs by 48.21% to 91.87%;and 3) reduces performance loss caused by dissemination failures by up to 97.30% in time and 96.35% in costs.

关键词： Computation offloading   deep learning   mobile edge computing   reinforcement learning   resource allocation  

摘要： We consider a multi-user multi-server mobile edge computing (MEC) system, in which users arrive on a network randomly over time and generate computation tasks, which will be computed either locally on their own computing devices or be offloaded to one of the MEC servers. Under such a dynamic network environment, we propose a novel task offloading policy based on hybrid online-offline learning, which can efficiently reduce the overall computation delay and energy consumption only with information available at nearest MEC servers from each user. We provide a practical signaling and learning framework that can train deep neural networks for both online and offline learning and can adjust its offloading policy based on the queuing status of each MEC server and network dynamics. Numerical results demonstrate that the proposed scheme significantly reduces the average computation delay for a broad class of network environments compared to the conventional offloading methods. It is further shown that the proposed hybrid online-offline learning framework can be extended to a general cost function reflecting both delay- and energy-dependent metrics.

关键词： Servers   Autonomous aerial vehicles   Energy consumption   Dispatching   Base stations   Heuristic algorithms   Optimization   Mobile edge computing   server placement   Unmanned Aerial Vehicle (UAV)   path planning   Internet of Vehicles (IoV)  

摘要： In future Internet of Vehicles (IoV), edge servers will be deployed to the proximity of vehicles on road to offer realtime computation offloading services. However, servers deployed at fixed sites are static, while the traffic load on road is highly dynamic, incurring the mismatch between the demand and supply from time to time. In this paper, we study using multiple Unmanned Aerial Vehicles (UAVs) to act as edge servers for the IoV in a city-wide area. We first build a model on how to dispatch multiple UAVs to multiple hovering locations where they can cover a maximum number of user requests on discretized time slots. As the problem is NP-hard, we design a heuristic algorithm to solve it in polynomial time, namely the UAV pie-eating dispatching algorithm. Next, we propose a matching-based strategy to reduce the total travel distance of the UAVs when they move between the hovering locations, with the purpose of saving energy. We run extensive trace-driven experiments on the trajectory data of the taxicabs in Shanghai. The results verify that our UAV pie-eating algorithm effectively dispatches the UAVs to different locations at different time to adapt to the spatio-temporal demand variation, and our matching-based path planning strategy also reduces the total travel distance significantly compared with other popular strategies.

关键词： Energy efficiency   Deep reinforcement learning   Computation offloading   Mobile edge computing   Unmanned aerial vehicles  

摘要： Industrial Internet of Things (IIoT) has been envisioned as a killer application of 5G and beyond. However, due to the shortness of computation ablility and batery capacity, it is challenging for IIoT devices to process latency-sensitive and resource-sensitive tasks. Moblie Edge Computing (MEC), as a promising paradigm for handling tasks with high quality of service (QoS) requirement and for energy-constrained IIoT devices, allows IIoT devices to offload their tasks to MEC servers, which can significantly reduce the task process delay and energy consumptions. However, the deployment of the MEC servers rely heavily on communication infrastructure, which greatly reduce the flexibility. Toward this end, in this paper, we consider multiple Unmanned Aerial Vehicles (UAV) eqqipped with transceivers as aerial MEC servers to provide IIoT devices computation offloading opportunities due to their high controbility. IIoT devices can choose to offload the tasks to UAVs through air-ground links, or to offload the tasks to the remote cloud center through ground cellular network, or to process the tasks locally. We formulate the multi-UAV-Enabled computation offloading problem as a mixed integer non-linear programming (MINLP) problem and prove its NP-hardness. To obtain the energy-efficient and low complexity solution, we propose an intelligent computation offloading algorithm called multi-agent deep Q-learning with stochastic prioritized replay (MDSPR). Numerical results show that the proposed MDSPR converges fast and outperforms the benchmark algorithms, including random method, deep Q-learning method and double deep Q-learning method in terms of energy efficiency and task successful rate.

关键词： Sensors   Radar   Reliability   Interference   Performance evaluation   Wireless communication   Resource management   Mobile edge computing   integrated sensing and communication   short-packet transmissions  

摘要： Integrated sensing and communication (ISAC) provides an emerging paradigm for enabling a variety of next-generation wireless services and applications. Due to the limited computation resources on ISAC devices and the latency as well as the reliability requirements, we propose a paradigm of mobile edge computing (MEC) aided ISAC with short-packet transmissions, where multiple ISAC devices adopt short-packet transmissions to offload their sensed radar data to an edge-server for analysis. We adopt the mutual information to measure the performance of radar sensing and quantify the reliability and latency performances for analyzing the radar-data via edge computing. We formulate an energy minimization problem that jointly optimizes the size of each short packet, the duration of each short packet, the computing-capacity allocations of edge-server, the beamforming of the radar sensing and the offloading transmission, while providing guaranteed performances for the radar sensing, the latency for radar-data analysis, and the reliability of offloading transmission. We identify the hierarchical structure of the formulated problem and divide the problem into three subproblems. For both the bottom-layer problem optimizing the computing-capacity allocations of the edge-server and the middle-layer problem optimizing the size of each short packet and the duration of each short packet, we derive their solutions analytically. Finally, for the top-layer problem optimizing the beamforming of the radar sensing and the offloading transmission, we transform it into a difference of convex (DC) problem which can be efficiently solved. We show the performance advantages of our proposed scheme. The simulation results show that our proposed algorithm can outperform the benchmark algorithms.

关键词： Mobile edge computing  

摘要： With the rapid advancement of large models and mobile edge computing, transfer learning, particularly through fine-tuning, has become crucial for adapting models to downstream tasks. Traditionally, this requires users to share their data with model owners for fine-tuning, which is not only costly but also raises significant privacy concerns. Furthermore, fine-tuning large-scale models is computationally intensive and often impractical for many users. To tackle these challenges, we introduce a system that combines offsite-tuning with physical-layer security, which provides local data owners with a lightweight adapter and a compressed emulator. Data owners then fine-tune the adapter locally and securely send it back to the model owners through a confidential channel for integration, ensuring privacy and resource conservation. Our paper focuses on optimizing computational resource allocation among data owners and the large model owner deployed on edge, and on the compression ratio of adapters. We incorporate a secrecy uplink channel to maximize the utility that we defined while minimizing system costs like energy consumption and delay. The optimization uses the Dinkelbach algorithm, fractional programming, successive convex approximation and alternating optimization. Experiments demonstrate our algorithm’s superiority over existing methods. © 2024, CC BY.

关键词： Mobile edge computing  

摘要： We study the problem of decentralized task offloading and load-balancing in a dense network with numerous devices and a set of edge servers. Solving this problem optimally is complicated due to the unknown network information and random task sizes. The shared network resources also influence the users' decisions and resource distribution. Our solution combines the mean field multi-agent multi-armed bandit (MAB) game with a load-balancing technique that adjusts the servers' rewards to achieve a target population profile despite the distributed user decision-making. Numerical results demonstrate the efficacy of our approach and the convergence to the target load distribution. Copyright © 2024, The Authors. All rights reserved.

关键词： Mobile edge computing  

摘要： Accommodating services at the network edge is favorable for time-sensitive applications. However, maintaining service usability is resource-consuming in terms of pulling service images to the edge, synchronizing databases of service containers, and hot updates of service modules. Accordingly, it is critical to determine which service to place based on the received user requests and service refreshing (maintaining) cost, which is usually neglected in existing studies. In this work, we study how to cooperatively place timely refreshing services and offload user requests among edge servers to minimize the backhaul transmission costs. We formulate an integer non-linear programming problem and prove its NP-hardness. This problem is highly non-tractable due to the complex spatial-and-temporal coupling effect among service placement, offloading, and refreshing costs. We first decouple the problem in the temporal domain by transforming it into a Markov shortest-path problem. We then propose a light-weighted Discounted Value Approximation (DVA) method, which further decouples the problem in the spatial domain by estimating the offloading costs among edge servers. The worst performance of DVA is proved to be bounded. 5G service placement testbed experiments and real-trace simulations show that DVA reduces the total transmission cost by up to 59.1% compared with the state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Low-power task scheduling   Mobile edge computing   Power consumption modeling   Energy consumption optimization   Particle swarm optimization  

摘要： In today's increasingly popular Internet of Things (IoT) technology, its energy consumption issue is also becoming increasingly prominent. Currently, the application of Mobile Edge Computing (MEC) in IoT is becoming increasingly important, and scheduling its tasks to save energy is imperative. To address the aforementioned issues, we propose a Multi-User Multi-Server (MUMS) scheduling framework aimed at reducing the energy consumption in MEC. The framework starts with a model definition phase, detailing multi-user multi-server systems through four fundamental models: communication, offloading, energy, and delay. Then, these models are integrated to construct an energy consumption optimization model for MUMS. The final step involves utilizing the proposed L1_PSO (an enhanced version of the standard particle swarm optimization algorithm) to solve the optimization problem. Experimental results demonstrate that, compared to typical scheduling algorithms, the MUMS framework is both reasonable and feasible. Notably, the L1_PSO algorithm reduces energy consumption by 4.6 % compared to Random Assignment and by 2.3 % compared to the conventional Particle Swarm Optimization algorithm.