关键词： Training   Relays   Data models   Energy consumption   Mobile handsets   Computational modeling   Costs   Federated learning   mobile edge computing   resource management   cooperative networks  

摘要： Federated learning (FL) is a promising training paradigm to achieve ubiquitous intelligence for future 6G communication systems. However, it is challenging to apply FL in 6G-enabled edge system since decentralized training consumes considerable energy and mobile devices are mostly battery-powered and resource-constrained. The intensive computation and communication cost of local updates accumulated by hundreds of global rounds bring about the energy bottleneck, which is exacerbated when the data is non identically and independently distributed (non-IID). To address this issue, we propose FedRelay, a generic multi-flow relay learning framework in which local updates are performed relay-by-relay in the training flow via model propagation. We also present a decentralized relay selection protocol that takes advantage of the diversity of cooperative communication networks. Following that, we investigate a FedRelay optimization problem to simultaneously minimize the energy consumption of local updates and alleviate the global non-IIDness. Technically, an approximation algorithm is proposed to jointly optimize computation frequency and transmission power, thus reducing the local training overhead. We further regulate the training topology of each flow by proposing a greedy relay policy that encourages effective information exchange among devices. Experiment results show that, compared to state-of-the-art federated learning algorithms, our learning framework can save up to 5 times the total energy required to achieve a reasonable global test accuracy.

关键词： Task analysis   Servers   Stability analysis   Optimization   TV   Cloud computing   Trajectory   Computation offloading   deep reinforcement learning   intelligent vehicles   mobile edge computing  

摘要： Computation offloading is considered as a promising method to improve computation performance of Intelligent Vehicles (IVs), where IVs can offload resource-hungry applications to Mobile Edge Computing (MEC) servers. However, due to the dynamic environment of Intelligent Transportation Systems, it's challenging to develop an effective offloading scheme that ensures stable operation of the system. Furthermore, IVs only offload tasks to MEC servers or parked vehicles, how to take full advantage of resources in a random traffic flow is a main challenge. In this paper, we propose a vehicular-cloud-assisted MEC network in urban cities to fully explore the idle resources and ensure the stability of task queue. Specifically, we develop a novel virtual platform based on deep neural network that predicts vehicles trajectory and creates vehicular cloud to integrate computation resources. We then design a vehicular-cloud-assisted offloading scheme that aims to maximize task throughput in continuous time slots subject to multi-constraint. To address the coupling among multiple variables and different time slots, we put forward a lightweight framework to apply the Lyapunov optimization in combination with deep reinforcement learning. In particular, we apply Lyapunov drift-plus-penalty approach to decompose the initial problem into per-slot subproblems and control the long-term task queue stability. To further reduce the computation complexity, we decouple the subproblem into three processes, and the deep Q-network is put forward to solve it. Extensive simulations demonstrate that under different task arrivals, our proposed scheme can achieve the task queue stability within 10 time slots with a low transmission power.

关键词： cooperative beamforming   intelligent reflecting surface   mobile edge computing   partial computation offloading   resource allocation  

摘要： In order to improve the performance of the mobile edge computing (MEC) system, the intelligent reflecting surface (IRS) has recently been included. This paper investigates the computation performance of an IRS-aided MEC system, where an access point services multi-MEC devices by utilizing two distributed IRSs to operate a partial offloading strategy. Through collaboratively constructing the cooperative passive beamforming at the two IRSs, the central processing unit (CPU) frequency, the offloading time allocation, and the transmit power of users, an optimization problem is constructed to maximize the sum computation rate of the proposed system. To tackle this non-convex issue, the authors first illustrate that the design of passive beamforming is independent to optimize other variables and propose to solve it alternatively. Then the joint optimization problem of other parameters is proved to be a convex problem and is resolvable by adopting the Lagrange dual approach. Compared with the benchmark schemes, the simulation outcomes demonstrated that the performance of the proposed system is vastly improved by deploying two distributed IRSs.

关键词： Internet of vehicles   mobile edge computing   resource allocation  

摘要： Benefiting from its abundant computing resources and low computing latency, mobile edge computing (MEC) is a promising approach for enhancing the computing capacity of the 5G Internet of vehicles (IoV). Because of the high mobility, handover is frequent and inevitable in IoV networks. In this paper, we investigate an edge collaborative task offloading and splitting strategy in MEC-enabled IoV networks, in which the task is splitted on the edge and paralleling executed by each part of the task on several MEC servers when handover is occured. Applications in IoV networks have flexible requirements on latency and energy consumption. To realize the tradeoff between latency and energy consumption, we formulate the task offloading and splitting as an optimization problem with the aim of minimizing the total cost of latency and energy consumption by jointly optimizing the task splitting ratio and uplink transmit power of vehicle terminal (VT). Because the proposed problem is non-smooth and non-convex, we divide the original problem into two convex subproblems, and apply an alternate convex search (ACS) algorithm to obtain the optimized solution with low computational complexity. Numerical simulation results show that the proposed method can adjust the offloading strategy properly according to task preference, and obtain a lower total cost compared with the baseline algorithms.

关键词： Edge computing   Resource management   Task analysis   Optimization   Relays   Probability   Power system reliability   Computation offloading outage probability   min-max fairness   mobile edge computing   reconfigurable intelligent surface  

摘要： Reconfigurable intelligent surface (RIS) is able to enhance the wireless channels, and further improve the performance in terms of outage in the mobile edge computing (MEC) system. Taking the computation offloading outage probability (COOP) as the metric, we investigate the coverage performance of the RIS-assisted MEC system. Specifically, we first obtain the closed-form expression of the COOP. Then we derive an asymptotic COOP expression at the high transmit power region and minimize the COOP in the single-smart device (SD) scenario. Finally, aiming at ensuring fairness among SDs in the multi-SD scenario, we propose an alternating optimization-based COOP min-max fairness (AOCMMF) algorithm to obtain the suboptimal solution of the nonconvex min-max problem. The simulation results verify that our closed-form and asymptotic expressions depict the COOP correctly. The proposed AOCMMF scheme can reduce the maximum COOP by 42.23% compared with the equal edge computing resource scheme, and the min-max fairness among SDs is realized.

关键词： Task analysis   Resource management   Device-to-device communication   Servers   Jamming   Copper   Wireless networks   Device-to-device   mobile edge computing   physical layer security   deep reinforcement learning  

摘要： This paper investigates secure computation offloading in device-collaborative mobile edge computing (MEC) networks, where mobile users (MUs) can process a part of their tasks locally and offload the other part to the MEC server or other idle paired MUs. All the transmission links are exposed to a potential eavesdropper. To prevent information leakage, artificial noise (AN) is employed and the secrecy capacity is considered. For such a system, we formulate a weighted latency-energy-aware cost minimization problem by jointly optimizing the subchannel allocation, the offloading proportions, the MUs' transmit powers, the MUs' and the MEC server's CPU frequencies, and the AN power while guaranteeing the secrecy capacities of all transmission links. Since the variables are multi-dimensional and coupled, the formulated problem is challenging to solve with the traditional optimization method. We first propose a swap-matching-based algorithm to achieve the optimal subchannel allocation. We then propose a two-layer asynchronous advantage actor-critic (A3C) algorithm to optimize the rest of the resource variables. Specifically, in the inner layer, by utilizing the Karush-Kuhn-Tucker conditions, we derive the optimal CPU frequency with semi-closed-form expressions. In the outer layer, we propose an A3C-based algorithm to achieve near-optimal solutions with fast convergence speed based on the obtained optimal CPU frequency. Simulation results demonstrate that our proposed scheme can decrease the latency-energy-aware cost compared with other learning-based algorithms.

关键词： multi-objective optimization   mobile edge computing   unmanned aerial vehicle   differential evolution algorithm  

摘要： The advancement of the Internet of Things (IoT) and the availability of wide cloud services have led to the horizon of edge computing paradigm which demands for processing the data at the edge of the network. The development of 5G technology has led to the increased usage of IoT-based devices and the generation of a large volume of data followed by increased data traffic, which is difficult to process by the mobile edge computing (MEC) platform. The latest inventions related to unmanned aerial vehicles (UAVs) helps to assist and replace the edge servers used for MEC. In the present work, the objective is to develop self-adaptive trajectory optimization algorithm (STO) which is a multi-objective optimization algorithm used to solve the vital objectives associated with the above scenario of a UAV-assisted MEC system. The objectives identified are minimizing the energy consumed by the MEC and minimizing the process emergency indicator, where the process emergency indicator implies the urgency level of a particular process. Finding the optimal values for these conflicting objectives will help to further efficiently apply UAV for MEC systems. A self-adaptive multi-objective differential evolution-based trajectory optimization algorithm (STO) is proposed, where a pool of trial vector generation strategies is extended. The strategies and the crossover rate associated with a differential evolution (DE) algorithm are self-adapted using fuzzy systems to improve the population diversity. The experimentation is planned to be conducted on hundreds of IoT device instances considered to be fixed on the ground level and to evaluate the performance of the proposed algorithm for a single unmanned aerial vehicle-assisted mobile edge computing system.

关键词： Mobile edge computing   Deep reinforcement learning   DDPG   Microservice selection   Cloud-edge collaboration  

摘要： In mobile edge computing environment, due to resources constraints of edge devices, when user locations continue changing, the network will be delayed or interrupted, which affects the quality of user's service access. Previous studies have shown that deploying multiple microservice instances with the same function on multiple edge servers through container technology can solve this problem. However, how to choose the optimal microservice instance from multiple servers in a cloud-edge hybrid environment needs to be further investigated. This paper studies the selection of microservices problem based on the dynamic and heterogeneous characters of the cloud-edge collaborative environment, which is defined as a microservice selection and scheduling optimization problem (MSSP) to minimize users' service access delay. To cope with the complexity of cloud-edge collaborative environment and improve learning efficiency, MSSP is regarded as a Markov decision-making process, a Deep Deterministic Policy Gradient algorithm for microservice selection called MS_DDPG is then proposed to solve this problem, and the microservice selection strategy experience pool is established in MS_DDPG. Performance evaluations of MS_DDPG based on a real dataset and some synthetic dataset have been conducted, and the results show that MS_DDPG outperforms the other three baseline algorithms. In terms of average access delay, MS_DDPG is reduced by 23.82%. We also validate the performance of MS_DDPG by increasing the number of user requests, and the results also show that MS_DDPG obtains better performance in scalability.

关键词： Automatic speech analysis   deep learning   edge-cloud computing   mobile edge computing   task offloading  

摘要： With the explosive growth of mobile multimedia services and artificial intelligence applications involving automatic speech analysis (ASA), mobile devices are increasingly unable to handle these computation-intensive tasks generated by users due to the limited computing resource. Besides, the existing cloud computing paradigm is not capable of processing such real-time and delaysensitive ASA tasks. In this paper, by leveraging mobile edge computing and deep learning (DL), we investigate task offloading for DLempowered ASA in mobile edge-cloud computing networks to minimize the total time for processing ASA tasks, thereby providing an agile service response. Specifically, to accelerate the processing of ASA tasks, we decompose a convolutional neural network based encoder-decoder model and deploy the encoder at edge servers to extract the features of ASA tasks. Moreover, edge servers derive the user tolerance limit by using a linear regression model for further enhancing the quality of experience of users. Based on some certain network constraints (i.e., user association and edge servers' storage/computing capacity), we propose a low-complexity and distributed offloading framework to solve the formulated complex problem. Evaluation results demonstrate the effectiveness of the proposed framework on reducing the total time and improving the satisfaction rate of users.

关键词： Mobile edge computing   task offloading   privacy preservation   deep reinforcement learning   computation rate  

摘要： Multi-access Edge Computing (MEC) enables mobile users to run various delay-sensitive applications via offloading computation tasks to MEC servers. However, the location privacy and the usage pattern privacy are disclosed to the untrusted MEC servers. The most related work concerning privacy-preserving offloading schemes in MEC either consider an impractical MEC scenario consisting of a single user or take a large amount of computation and communication cost. In this article, we propose a deep reinforcement learning based joint optimization of delay and privacy preservation during offloading for multiple-user wireless powered MEC systems, preserving users' both location privacy and usage pattern privacy. The main idea is that, to protect both the two kinds of privacy, we propose to disguise users' offloading decisions and deliberately offloading redundant tasks along with the actual tasks to the MEC servers. On this basis, we further formalize the task offloading as an optimization problem of computation rate and privacy preservation. Then, we design a deep reinforcement learning based offloading algorithm to solve such an non-convex problem, aiming to obtain the better tradeoff between the computation rate and the privacy preservation. Finally, extensive simulation results demonstrate that our algorithm can maintain a high level of computation rate while protecting users' usage pattern privacy and location privacy, compared with two learning-based methods and two Baselines.