关键词： Internet of Vehicles   mobile edge computing   object detection   image compression  

摘要： The prevalence of intelligent transportation systems in alleviating traffic congestion and reducing the number of traffic accidents has risen in recent years owing to the rapid advancement of information and communication technology (ICT). Nevertheless, the increase in Internet of Vehicles (IoV) users has led to massive data transmission, resulting in significant delays and network instability during vehicle operation due to limited bandwidth resources. This poses serious security risks to the traffic system and endangers the safety of IoV users. To alleviate the computational load on the core network and provide more timely, effective, and secure data services to proximate users, this paper proposes the deployment of edge servers utilizing edge computing technologies. The massive image data of users are processed using an image compression algorithm, revealing a positive correlation between the compression quality factor and the image's spatial occupancy. A performance analysis model for the ADHOC MAC (ADHOC Medium Access Control) protocol is established, elucidating a positive correlation between the frame length and the number of service users, and a negative correlation between the service user rate and the compression quality factor. The optimal service user rate, within the constraints of compression that does not compromise detection accuracy, is determined by using the target detection result as a criterion for effective compression. The simulation results demonstrate that the proposed scheme satisfies the object detection accuracy requirements in the IoV context. It enables the number of successfully connected users to approach the total user count, and increases the service rate by up to 34%, thereby enhancing driving safety, stability, and efficiency.

关键词： Task analysis   Energy consumption   Optimization   Servers   Reinforcement learning   Performance evaluation   Costs   Mobile edge computing   computation offloading   task characteristics   completion time estimation  

摘要： Edge computing extends computational capabilities to the physical edge of the world, providing faster and more efficient responses to consumer devices such as smart home appliances, smartphones, and wearable devices. However, it raises a critical question: How can we efficiently manage time-sensitive and computationally intensive tasks to meet device performance needs? To address this, we propose a computational cost-driven strategy for computation offloading based on reinforcement learning for consumer devices. Firstly, we convert the problem of minimizing computational costs, including latency and energy consumption, into maximizing the cumulative rewards problem of consumer devices. Second, we design a task completion time estimation method to ensure a favorable user experience. Third, by comprehensively considering the status of the network, computational demands, and task completion times, we employ reinforcement learning techniques to determine the optimal task offload strategy for consumer devices by maximizing cumulative rewards. This ensures efficient task completion with lower computational costs. The simulation results demonstrate that our method achieves the highest rewards in different scenarios. Our method reduces the task discard ratio by 25% compared to the PPO_KLP-based offload strategy.

关键词： Mobile edge computing   base station selection   resource allocation   double auction   revenue maximization  

摘要： In mobile edge computing (MEC), task offloading and resource allocation are two important issues that are inextricably linked. However, existing studies have either ignored the mobility of mobile users (MUs) during task offloading or the allocation of profits between two parties during the allocation of limited resources (i.e., the resource competition). In this paper, we jointly optimized these two problems. First, to reduce the task offloading delay and the service interruption due to movement, we develop a mobility-aware model, based on which we propose the MWBS algorithm to select the appropriate offloading base station (BS) for MUs. Second, considering the resource competition and the delay constraint of the task, we develop a double auction model and then propose the DARA algorithm, which efficiently allocates the BS resources and maximizes the total system revenue (i.e., social welfare) through a multi-session auction. Finally, we combine MWBS and DARA to propose the BS resource allocation algorithm called MD-BSRA in mobile scenarios. Simulation results show that MD-BSRA can effectively improve task offload success rate, total system revenue and resource utilization while reducing offload delay and service interruption.

关键词： Semantics   Task analysis   Energy consumption   Consumer electronics   Optimization   Resource management   Bandwidth   Mobile edge computing   semantic communication   resilient optimization   deep reinforcement learning  

摘要： In this paper, we investigate a semantic-aware mobile edge computing (MEC) network for sustainable next-G consumer electronics, which leverages advanced semantic communication technology to overcome the limitations of available bandwidth and thereby improve communication efficiency. For this network, consumer electronic devices can offload the semantic information extracted from the task instead of transmitting the whole task in the conventional MEC networks, where the latency and energy consumption can be significantly reduced through proper semantic encoding, offloading, and bandwidth and computation allocation decisions. However, the non-convexity of the issue makes it difficult to obtain the optimal decision. To address this issue, a two-level optimization framework is proposed. Specifically, in the upper-level optimization, a resilient deep reinforcement learning (DRL) approach is utilized to enable adaptive offloading and semantic encoding decisions within a dynamic network. In the lower-level optimization, we design three criteria for allocating bandwidth and computation resources by carefully considering the trade-off between computational complexity and implementation efficiency. Finally, extensive simulations are conducted to validate the effectiveness of our proposed strategy. The findings in this paper can help reduce the energy consumption of consumer electronics, hence supporting the development of sustainable next-G consumer electronics.

关键词： Mobile edge computing   decentralized D2D collaboration   mean field graph   task offloading   dynamic pricing  

摘要： Mobile edge computing (MEC) facilitates computation offloading to edge server and task processing via device-to-device (D2D) collaboration. Existing works mainly focus on centralized network-assisted offloading solutions, which are unscalable to collaborations among massive users. In this paper, we propose a joint framework of decentralized D2D collaboration and task offloading for MEC systems with large populations. Specifically, we utilize the power of two choices for D2D collaboration, which enables users to assist each other in a decentralized manner. Due to short-range D2D communication and user movements, we formulate a mean field model on a finite-degree and dynamic graph to analyze the collaboration state evolution. We derive the existence, uniqueness and convergence of the state stationary point to provide a tractable collaboration performance. Complementing this D2D collaboration, we further build a Stackelberg game to model users' task offloading, where the provider, managing many servers, is the leader to determine service prices, while users are followers to make offloading decisions. By embedding Stackelberg game into Lyapunov optimization, we develop an online offloading and pricing scheme, which can optimize servers' service utility or fairness, and users' system cost simultaneously. Extensive evaluations show that D2D collaboration can mitigate users' workloads by 73.8% and fair pricing can promote servers' utility fairness by 15.87%.

关键词： Predictive models   Data models   Computational modeling   Manufacturing   Adaptation models   Predictive maintenance   Performance evaluation   Machine diagnosis   mobile edge computing   machine learning   predictive maintenance   explainable artificial intelligence  

摘要： As the number of Internet of Things edge devices in smart factories increasing, it is crucial to predict the lifetime of the equipment to keep the production running normally. Although predictive maintenance based on machine learning achieve a better performance, they still face the challenge of black box and time-efficient. This paper propose a stacking-based model called ERF-XGB for predictive maintenance in the edge computing environment. The model first performs initial prediction by integrating the Random Forest model and Extreme Gradient Boosting model, followed by further processing of the initial prediction results using the linear regression model to obtain the final prediction results. In addition, the model incorporates the Shapley Additive exPlanations method, which can enhance the interpretability of the model when performing predictive maintenance. An experimental evaluation of the Predictive and Health Management dataset shows that the ERF-XGB model has an RMSE of 18.271 and an MAE of 13.454, which are the two metrics that perform the best when compared to other comparison models, suggesting that the model has a better predictive performance. Meanwhile, the Shapley Additive exPlanations method visualizes the impact of each edge device on normal operation in the production process, facilitating precise equipment management and maintenance.

关键词： Federated learning   Training   Computational modeling   Data models   Servers   Error compensation   Quantization (signal)   Mobile edge computing   federated learning   machine learning   gradient compression   communication efficiency  

摘要： In this paper, we explore an emerging customer application named federated learning in Mobile Edge Computing (MEC). Federated learning is a machine learning technique that enables data privacy and avoids data silos. However, federated learning tasks with high performance often face large model parameters and high communication costs. To address this challenge, this paper presents FedSQ (Federated Learning with Sparsity and Quantization), a novel sparsity and quantization strategy that reduces communication overhead and enhances model convergence. FedSQ selectively uploads the parameters with large gradient change ratios and uses the old values from the previous round for the parameters with small gradient change ratios. FedSQ also incorporates an error compensation mechanism with correction to mitigate the compression loss and balance the model parameters between the current and previous rounds. We conduct experiments on standard datasets and demonstrate that FedSQ achieves high compression ratio without sacrificing the model accuracy significantly in various federated learning tasks. Across all communication rounds, FedSQ achieved the highest accuracy improvement of 25.74% and the highest compression rate of 97.98%. Our research provides a novel intelligent data-driven model for consumer electronics, which can improve the communication efficiency and model convergence of client applications in MEC.

关键词： Mobile edge computing   Unmanned aerial vehicle   Deep reinforcement learning   Offload pairing  

摘要： Dynamically moving Unmanned Aerial Vehicles (UAVs) have emerged as an effective means to significantly enhance the flexibility and transmission performance of mobile edge computing (MEC). However, in practical scenarios, UAVs often face limitations in terms of data storage capacity and computational power. In this paper, a UAV-enabled MEC network with multiple users and multiple edge computing servers is proposed, where the UAV is equipped with limited-size buffers. An optimization problem is formulated to jointly optimize UAV flight trajectories, offload server pairings, task offload ratios, and UAV transmit power to minimize transmission delay, computation delay, and system energy consumption. To tackle the intractable non-convex optimization issue, an intelligent optimization algorithm based on Deep Dueling Double Q-Network (D3QN)-Twin Delayed Deep Deterministic Policy Gradient (TD3) is proposed, which is able to efficiently determine the optimal solution. Simulation results demonstrate that our proposed intelligent algorithm exhibits good convergence and achieves a favorable balance between delay and energy consumption.

关键词： Deep learning   point cloud video   dual-scale pruning   mobile edge computing   transformer  

摘要： 3D point cloud videos are widely used in edge computing scenarios to achieve seamless connectivity and extremely low latency in applications such as autonomous driving. It faces difficulties primarily because point cloud data is often voluminous and contains redundancies. These issues can lead to significant drawbacks in practical applications, causing inference delays and reducing accuracy. To tackle these challenges, we propose a novel approach: a transformer-based spatio-temporal pruning method designed specifically for point cloud videos. Our goal is to expedite network inference. Initially, we utilize the attention mechanism of the transformer to calculate importance scores for different frames and tokens within 3D point cloud videos. To capture the temporal context of each point cloud token, we introduce a frame-wise relation matrix for importance score computation. Subsequently, we use these importance scores as criteria for pruning at both frame and token levels. The experimental results indicate that our approach outperforms other methods. For example, on NTU RGB+D 60 dataset, it shows improvement in accuracy by 0.5% and the average inference time decrease by 28%, while memory consumption is reduced by 28%.

关键词： Secure video offloading   Industrial Internet of Things   resource orchestration   mobile edge computing   multi-cell federated deep reinforcement learning  

摘要： Wireless video offloading in mobile-edge-computing (MEC)-enabled Industrial Internet of Things imposes a risk of exposing users' private data to eavesdroppers. It is difficult for existing secure video offloading schemes to simultaneously guarantee security, reduce latency and energy consumption in privacy-sensitive multi-cell scenarios where users are unwilling to offload data to other cells. In this paper, a secure video offloading scheme based on multi-cell federated deep reinforcement learning (DRL) is proposed to facilitate a secure, real-time and efficient MEC network by efficient orchestration of limited resources. We formulate a collaborative optimization problem of video frame resolution and resources to minimize latency and energy consumption while maximizing the security rate subject to analytic accuracy and limited resources. To solve the formulated NP-hard problem, a multi-cell federated DRL algorithm based on the frameworks of multi-cell horizontal federated learning (FL) and hierarchical reward function-based twin delayed deep deterministic policy gradient (TD3) is proposed. First of all, hierarchical reward function-based TD3 is employed to solve the collaborative optimization NP-hard problem formulated for each single cell, where the optimal solution can be efficiently approached by the agent under the guidance of the innovatively designed hierarchical reward function. Then, multi-cell horizontal FL is applied on TD3 to obtain a model with higher model quality by averagely aggregating multiple individual TD3 models. Simulation results reveal that the proposed algorithm outperforms comparison algorithms in terms of utility, cost, latency, energy consumption and security rate.