关键词： Deep reinforcement learning   Lyapunov optimization   Mobile edge computing   Task offloading  

摘要： With the arrival of 5G technology and the popularization of the Internet of Things (IoT), mobile edge computing (MEC) has great potential in handling delay-sensitive and compute-intensive (DSCI) applications. Meanwhile, the need for reduced latency and improved energy efficiency in terminal devices is becoming urgent increasingly. However, the users are affected by channel conditions and bursty computational demands in dynamic MEC environments, which can lead to longer task correspondence times. Therefore, finding an efficient task offloading method in stochastic systems is crucial for optimizing system energy consumption. Additionally, the delay due to frequent user-MEC interactions cannot be overlooked. In this article, we initially frame the task offloading issue as a dynamic optimization issue. The goal is to minimize the system's longterm energy consumption while ensuring the task queue's stability over the long term. Using the Lyapunov optimization technique, the task processing deadline problem is converted into a stability control problem for the virtual queue. Then, a novel Lyapunov-guided deep reinforcement learning (DRL) for delay-aware offloading algorithm (LyD2OA) is designed. LyD2OA can figure out the task offloading scheme online, and adaptively offload the task with better network quality. Meanwhile, it ensures that deadlines are not violated when offloading tasks in poor communication environments. In addition, we perform a rigorous mathematical analysis of the performance of Ly2DOA and prove the existence of upper bounds on the virtual queue. It is theoretically proven that LyD2OA enables the system to realize the trade -off between energy consumption and delay. Finally, extensive simulation experiments verify that LyD2OA has good performance in minimizing energy consumption and keeping latency low.

关键词： Ultra-dense heterogeneous network   Mobile edge computing   Wireless resource management   Task offloading   Multi-agent deep deterministic policy gradient  

摘要： With the rapid development of IoT technology, various computation-intensive and latency-sensitive tasks have emerged in large numbers, which impose higher requirements on the processing efficiency of the tasks. In this paper, by fusing mobile edge computing (MEC) and ultra-dense heterogeneous network (UD-HetNet) technologies, we design the scenario of UD-HetNet with MEC to improve the efficiency of computation and communication during task processing. However, how to design a effective task offloading and resource management strategy is still a major challenge in this scenario. Therefore, in this paper, we propose a distributed task offloading and wireless resource management framework that optimizes task offloading, local computation frequency scaling, subchannel allocation, and transmit power regulation strategies to reduce system overhead (weighted sum of delay and energy consumption of task processing) effectively. First, we design a task offloading for multi-base station (BS) collaboration base on priority algorithm and optimize the local computation frequency using convex optimization theory. Following by, we introduce a multi-agent deep deterministic policy gradient (MADDPG) technology to optimize subchannel allocation and transmit power regulation during task offloading to accommodate the dynamic and variable nature of the channel. Finally, user equipment (UE)-edge server (ES), UE-subchannel, and subchannel-power matching are achieved. Simulation results show that our algorithm has significant advantages in balancing the ES load, improving channel utilization, and reducing system overhead.

关键词： mobile edge computing   dynamic matching   D2D   delay constraint   multi-agent reinforcement learning  

摘要： Device-to-device (D2D) is a pivotal technology in the next generation of communication, allowing for direct task offloading between mobile devices (MDs) to improve the efficient utilization of idle resources. This paper proposes a novel algorithm for dynamic task offloading between the active MDs and the idle MDs in a D2D-MEC (mobile edge computing) system by deploying multi-agent deep reinforcement learning (DRL) to minimize the long-term average delay of delay-sensitive tasks under deadline constraints. Our core innovation is a dynamic partitioning scheme for idle and active devices in the D2D-MEC system, accounting for stochastic task arrivals and multi-time-slot task execution, which has been insufficiently explored in the existing literature. We adopt a queue-based system to formulate a dynamic task offloading optimization problem. To address the challenges of large action space and the coupling of actions across time slots, we model the problem as a Markov decision process (MDP) and perform multi-agent DRL through multi-agent proximal policy optimization (MAPPO). We employ a centralized training with decentralized execution (CTDE) framework to enable each MD to make offloading decisions solely based on its local system state. Extensive simulations demonstrate the efficiency and fast convergence of our algorithm. In comparison to the existing sub-optimal results deploying single-agent DRL, our algorithm reduces the average task completion delay by 11.0% and the ratio of dropped tasks by 17.0%. Our proposed algorithm is particularly pertinent to sensor networks, where mobile devices equipped with sensors generate a substantial volume of data that requires timely processing to ensure quality of experience (QoE) and meet the service-level agreements (SLAs) of delay-sensitive applications.

关键词： Reinforcement learning   collaborative caching   content popularity   mobile edge computing  

摘要： With the enormous growth in mobile data traffic over the 5G environment, Adaptive BitRate (ABR) video streaming has become a challenging problem. Recent advances in Mobile Edge Computing (MEC) technology make it feasible to use Base Stations (BSs) intelligently by network caching, popularity-based video streaming, and more. Additional computing resources on the edge node offer an opportunity to reduce network traffic on the backhaul links during peak traffic hours. More recently, it has been found in the literature that collaborative caching strategies between neighbouring BSs (i.e., MEC servers) make it more efficient to reduce backhaul traffic and network congestion and thus improve the viewer experience substantially. In this work, we propose a Reinforcement Learning (RL)-based collaborative caching mechanism in which the edge servers cooperate to serve the requested content from the end-users. Specifically, this research aims to improve the overall cache hit rate at the MEC, where the edge servers are clustered based on their geographic locations. This task is modelled as a multi-objective optimization problem and solved using an RL framework. In addition, a novel cache admission and eviction policy is defined by calculating the priority score of video segments in the clustered MEC mesh network.

关键词： Task analysis   Wireless communication   Energy consumption   Communication system security   Resource management   Reliability   Servers   Mobile edge computing   user-centric networks   blockchain   task offloading   alternating direction method of multipliers  

摘要： In the traditional mobile edge computing (MEC) system, the availability of MEC services is greatly limited for the edge users of the cell due to serious signal attenuation and inter-cell interference. User-centric MEC (UC-MEC) can be seen as a promising solution to address this issue. In UC-MEC, each user is served by a dedicated access point (AP) cluster enabled with MEC capability instead of a single MEC server, however, at the expense of more energy consumption and greater privacy risks. To achieve efficient and reliable resource utilization with user-centric services, we propose an energy-efficient blockchain-enabled UC-MEC system where blockchain operations and resource optimization are jointly performed. Firstly, we design a resource-aware, reliable, replicated, redundant, and fault-tolerant (R-RAFT) consensus mechanism to implement secure and reliable resource trading. Then, an optimization framework based on alternating direction method of multipliers (ADMM) is proposed to minimize the total energy consumed by wireless transmission, consensus, and task computing, where AP clustering, computing resource allocation, and bandwidth allocation are jointly considered. Simulation results show the superiority of the proposed UC-MEC system over reference schemes, with at most 33.96% reduction in the total delay and 48.77% reduction in the total energy consumption.

关键词： Wireless power transfer   Secure communication   Mobile edge computing   Resource allocation  

摘要： Unmanned aerial vehicles (UAVs) equipped with mobile edge computing (MEC) servers and featuring flexible deployment capabilities can help to reduce the computing pressure on ground user networks. However, the majority of ground users are hindered by their limited battery life, preventing them from working without interruption. To maximize the service lifetime of ground users, UAVs transmit energy to them first and then collect offload tasks afterwards. This approach allows users to work without interruption while transmitting UAVs with computing tasks which can then be processed with the help of MEC servers. This helps to reduce the pressure on ground user networks, ensuring that they remain reliable and efficient. Therefore, we propose an optimization problem that aims to maximize the minimum security offloading rate of the system. This problem involves multiple variables, so conventional methods are not suitable for solving it. Our proposed scheme utilizes block coordinate descent (BCD) and successive convex approximation (SCA) algorithms, which can better optimize the user offloading decision, energy transfer duration, and user transmit power. Numerical results demonstrate that our scheme is more effective than the two benchmark schemes in improving the system performance.

关键词： Mobile edge computing   Vehicular fog computing   Urban intelligent video systems   Task placement   ICVs  

摘要： With the development of Mobile Edge Computing, driverless, 5 G, and related techniques, Edge-Cloud based Urban Intelligent Video Systems are extremely promising to support public safety through powerful analysis and timely response. Furtherly, flexible Unmanned Ground Vehicles(UGVs), which are equipped with edge devices, can enhance these edge systems to withstand these abnormalities: natural disasters, abnormal crowd flows, and other emergencies. In this regard, as a critical issue in edge systems, task placement in these systems needs to consider these "mobile" edge nodes: ICVs(UGVs). Therefore, a novel and effective framework named Optimized Centroids K-means based Task Placement framework is proposed: we firstly involve the clustering approach to optimize initial centroids as the positions of ICVs in terms of Edge Nodes, various typical optimization methods can be utilized to place related edge tasks effectively. The experimental results demonstrate that our novel framework has a great improvement over several existing typical strategies and supports multiple optimization methods well in this paper.

关键词： Convex optimization   Energy efficient   Mobile edge computing   Task offloading   Unmanned aerial vehicles  

摘要： The utilization of unmanned aerial vehicles (UAVs) as aerial mobile edge computing (MEC) servers presents an effective approach for mitigating the computational limitations of intelligent mobile devices. However, the limited battery capacity of UAVs poses a significant challenge in ensuring sustained service provision. To counter this obstacle and enhance energy efficiency, we introduce a partial offloading MEC scheme assisted by layered UAVs (POAL). Our objective is to minimize the total energy consumption of UAVs by jointly optimizing several factors, including wireless channels, transmit power, task partition, computing power, and UAV trajectories. Due to the non-convexity of the problem, we decompose it into three sub-problems and address them iteratively. Firstly, we employ the CVX optimization tool to allocate wireless channels and utilize Lagrangian duality to determine the optimal transmit power. Secondly, leveraging the monotonicity of the optimization objective, we derive the optimal computing power. Lastly, we employ the successive convex approximation (SCA) technique to tackle the trajectory planning sub-problem. Numerical results demonstrate that the proposed algorithm can effectively position UAVs within 15 iterations. Furthermore, our layered scheme significantly reduces overall energy consumption.

关键词： Mobile edge computing  

摘要： Clients can increase or decrease the number of resources they use dynamically over time due to the elasticity of cloud resources. As a result, variations in resource demands and predefined VM sizes result in a lack of resource utiliation, load imbalances, and excessive power consumption. A framework of efficient resource management is proposed to address these issues, balancing the load accordingly and anticipating the resource utilization of the servers. By optimizing resource utilization and minimizing the number of active servers, this technique facilitates power savings. Under/overloaded servers reduce energy consumption, execution delay, and performance degradation through a resource prediction system that is deployed at the CPU. Moreover, OCL-MEC load-balancing and resource allocation algorithms are proposed to reduce data center network traffic and power consumption. Experiments on real-world workload datasets, namely Bitsbrain VM traces, are conducted to evaluate the proposed framework. Different performance metrics demonstrate the superiority of the proposed framework over state-of-the-art approaches. Power savings of up to 98 % can be achieved by the OCL-MEC framework using a decision tree load balancing model based on HMM prediction systems. © 2024 The Authors

关键词： Mobile edge computing   Service caching   Task offloading  

摘要： With the development of Internet of Things (IoT) networks and Mobile Edge Computing (MEC), many computing -intensive applications have been developed in large quantities. Due to the heterogeneity of tasks, different application services are required to perform each task. Caching application services and related data in edge servers is challenging. Hence, we study the service cache placement and task offloading problem in IoT networks. Since IoT devices and edge servers with limited storage resources can only cache a few services at the same time, we formulate the service cache placement and task offloading of IoT devices problem to minimize task service delay with long-term energy constraint of IoT devices, which is a mixed integer nonlinear programming problem. To solve this problem, an online Deep Reinforcement Learning guided by the Lyapunov optimization framework algorithm (LYADRL) is proposed. We first build a virtual queue model to decouple the problem by Lyapunov optimization technique to transform the problem into a single time slot optimization problem. Then, we use Deep Reinforcement Learning techniques to find the optimal edge service caching and task offloading policies for each time slot. Simulation results show that our algorithm can reduce the service delay compared with other benchmark algorithms.