关键词： Computation offloading   deep reinforcement learning   environment adaptation   mobile edge computing  

摘要： One of the key issues in mobile edge computing (MEC) is computation offloading, most policies of which are developed based on mathematical programming (MP). Due to the high computational complexity of iterative programming in MP-based policies, recent years have seen a popular trend to develop offloading policies based on deep reinforcement learning (DRL). However, on account of the poor generalization ability of DRL models in MEC environments with different network sizes and settings, it is difficult to directly apply DRL-based offloading policies in unseen MEC environments. Motivated by this, we propose a DRL-based environment-adaptive offloading framework (DEAT), including a size-adaptive scheme (SIED) and setting-adaptive component (SEAL). SIED leverages the idea of 'time division multiplexing' to adapt to varying MEC network sizes and order-unaware feature extraction to mitigate impacts of different size-changing orders. SEAL adopts system dynamics embedding and offloading policy embedding, which guide the finding of the closest pre-training MEC environment and offloading policy, respectively, to achieve fast setting-adaptation with only few exploring interactions in unseen MEC environments. Extensive experiments are conducted via both simulation and testbed to demonstrate the adaptation performance advantages of DEAT in unseen MEC environments compared to the state-of-the-art offloading approaches.

关键词： Mobile edge computing   Ultra-dense network   Offloading   Non-orthogonal multiple access   Deep reinforcement learning  

摘要： To address the current challenge of smart devices in healthcare Internet of things (IoT) struggling to efficiently process intensive applications in real-time, a collaborative cloud-edge offloading model tailored for ultra-dense edge computing (UDEC) networks is developed. While numerous studies have delved into the optimization of offloading in mobile edge computing (MEC), it is imperative to consider non-orthogonal multiple access (NOMA) as a physical technology when addressing the offloading optimization process in MEC. The multiuser sharing of spectrum resources in NOMA can enhance the network spectrum utilization and reduce the computational delay when users transmit computing tasks. Consequently, a model for NOMA-assisted UDEC systems is proposed. The model takes into account joint offloading decisions, computational resources, and sub-channel resources and is modeled as a complex nonlinear mixed-integer programming problem. The aim is to decrease the task execution delay and energy consumption of smart devices while ensuring that users' maximum acceptable delay for processing medical computational tasks is met efficiently and in a timely manner. Deep deterministic policy gradient (DDPG), a deep reinforcement learning method, is employed to solve the joint optimization problem. The final simulation results show that the algorithm converges well. The proposed offloading scheme can reduce the system cost by 54.5 and 69.9% in comparison with scenarios where users solely perform local computations and offload their tasks to the base station (BS). The application of NOMA communication in our offloading scheme boosts network spectrum utilization and trims down the system cost by 87.09% when contrasted with orthogonal multiple access (OMA).

关键词： mobile edge computing   vehicular edge computing   computation offloading   deep reinforcement learning   partial offloading  

摘要： Vehicular Edge Computing (VEC) is a crucial application of Mobile Edge Computing (MEC) in vehicular networks. In VEC networks, the computation tasks of vehicle terminals (VTs) can be offloaded to nearby MEC servers, overcoming the limitations of VTs' processing power and reducing latency caused by distant cloud communication. However, a mismatch between VTs' demanding tasks and MEC servers' limited resources can overload MEC servers, impacting Quality of Service (QoS) for computationally intensive tasks. Additionally, vehicle mobility can disrupt communication with static MEC servers, further affecting VTs' QoS. To address these challenges, this paper proposes a vehicle collaborative partial computation offloading model. This model allows VTs to offload tasks to two types of service nodes: collaborative vehicles and MEC servers. Factors like a vehicle's mobility, remaining battery power, and available computational power are also considered when evaluating its suitability for collaborative offloading. Furthermore, we design a deep reinforcement learning-based strategy for collaborative partial computation offloading that minimizes overall task delay while meeting individual latency constraints. Experimental results demonstrate that compared to traditional approaches without vehicle collaboration, this scheme significantly reduces latency and achieves a significant reduction (around 2%) in the failure rate under tighter latency constraints.

关键词： Mobile edge computing   Proactive replicas pre-deployment   Reactive service migration   Reinforcement learning algorithm   Time-sensitive  

摘要： Mobile edge computing (MEC) integrated with the Network Functions Virtualization (NFV) technique has been regarded as a promising solution for flexible services provision and user service experience improvement. However, existing service placement in such systems still faces the challenge of satisfying computing tasks with strict latency requirements, especially when massive mobile users roam around different coverage areas of edge servers. For this purpose, we first adopt a novel service placement framework that combines proactive replicas pre -deployment and reactive service migration. Based on this, we investigate the dynamic placement problem of multiple types of services achieved by the various virtualized network functions (VNFs) to minimize long-term redeployment costs in MEC -assisted systems, subject to the completion deadline of tasks and limited computing resources of edge servers. Considering that the update timescale of VNF replicas pre -deployment is different, we design a novel two-timescale multi -agent graph convolutional network -based reinforcement learning algorithm (TMAGRL) by invoking a long-timescale training layer for proactive VNF replicas placement and a short-timescale training layer for reactive VNF migration. Extensive numerical results reveal that TMAGRL, based on the designed hybrid framework, can learn a VNF placement strategy to adapt to the dynamics of the system without any prior information. Moreover, we verify its superior performance in terms of average service response latency and overall redeployment cost by comparing it with baselines.

关键词： Satellites   Low earth orbit satellites   Delays   Orbits   Internet of Things   Approximation algorithms   Low latency communication   Approximation and online algorithms   mobile edge computing   network function chaining   satellite edge network  

摘要： Satellite-terrestrial networks are emerging as the next-generation networking paradigm for Beyond-5 G (B5G) and 6 G networks. Meanwhile, Mobile Edge Computing (MEC) is envisioned as the key technology to provide network services within the proximity of users, by deploying computing resource in ground locations that are close to users. With the fast deployment of Low-Earth-Oribt (LEO) satellites, a new paradigm of MEC is emerging by enabling LEO satellites serving as edge servers in lower orbits that are close to ground users. In this way, the ground users can be further served by LEO satellites in lower orbits instead of conventional high-orbit satellites. Also, since LEO satellites provide shorter paths from users to services, the performance is enhanced compared with ground MEC networks. In this paper, we aim to enable low-latency network services in a Satellite Edge Computing (SEC) network that integrates the MEC and satellite-terrestrial networks. In particular, we consider that each network service is composed of a sequence of Virtualized Network Functions (VNFs), where the traffic of user requests has to be processed by the VNFs in a service chain in the specified order before reaching its destination. To this end, we first formulate a delay-aware service chaining problem in an SEC network to minimize the average delay of implementing a user request, by jointly placing VNFs to LEO satellites in the SEC network and routing the traffic of each user request from its source to destination. We then devise an approximation algorithm with an approximation ratio for the problem in an SEC network with a single user request, by devising a novel concept of chaining orbit and auxiliary graph construction technique. We also design an online algorithm for the online delay-aware service chaining problem in an SEC network, if user requests arrive into the system without the knowledge of their arrivals and the network delays are uncertain. We finally evaluate the performance o

关键词： Epoch adjustment   mobile edge computing   model reliability   federated learning  

摘要： As a distributed learning paradigm, federated learning (FL) can be applied in mobile edge computing (MEC) to support real-time artificial intelligence by leveraging edge computation resources while preserving data privacy in the end devices. However, the unpredictable wireless connections between end devices and edge servers in MEC (e.g., frequent handovers and unstable wireless channels) may result in the loss of important model parameters, which slows down the FL training process and degrades the quality of the global model. In this paper, we propose an adaptive collaborative federated learning (ACFL) scheme to accelerate the convergence and improve model reliability by mitigating communication-based parameter loss under a three-layer MEC architecture. First, a dynamic epoch adjustment method is proposed to reduce communication rounds by dynamically adjusting the training epochs in end devices. In addition, to accelerate the FL convergence, we present an edge server collaborative training scheme by leveraging a multi-layer computing architecture, where edge servers utilize their maintained data to collaboratively train models with end devices. Finally, extensive simulations are conducted and show that ACFL can efficiently improve model reliability and accelerate the convergence of the FL process in MEC.

关键词： mobile edge computing   edge caching   green communication   mobile communication   greedy algorithm  

摘要： In the context of the rapid development of the Internet of Vehicles, virtual reality, automatic driving and the industrial Internet, the terminal devices in the network show explosive growth. As a result, more and more information is generated from the edge of the network, which makes the data throughput increase dramatically in the mobile communication network. As the key technology of the fifth-generation mobile communication network, mobile edge caching technology which caches popular data to the edge server deployed at the edge of the network avoids the data transmission delay of the backhaul link and the occurrence of network congestion. With the growing scale of the network, distributing hot data from cloud servers to edge servers will generate huge energy consumption. To realize the green and sustainable development of the communication industry and reduce the energy consumption of distribution of data that needs to be cached in edge servers, we make the first attempt to propose and solve the problem of edge caching data distribution with minimum energy consumption (ECDDMEC) in this paper. First, we model and formulate the problem as a constrained optimization problem and then prove its NP-hardness. Subsequently, we design a greedy algorithm with computational complexity of O(n2) to solve the problem approximately. Experimental results show that compared with the distribution strategy of each edge server directly requesting data from the cloud server, the strategy obtained by the algorithm can significantly reduce the energy consumption of data distribution.

关键词： Routing   Process control   Distributed databases   Cloud computing   Optimization   Metaverse   Data models   Data-intensive services   virtual reality   augmented reality   metaverse   distributed cloud   mobile edge computing   fog computing   caching   network control   stream processing  

摘要： Data-intensive augmented information (AgI) services (e.g., metaverse applications such as virtual/augmented reality), designed to deliver highly interactive experiences resulting from the real-time combination of live data-streams and pre-stored digital content, are accelerating the need for distributed compute platforms with unprecedented storage, computation, and communication requirements. To this end, the integrated evolution of next-generation networks (5G/6G) and distributed cloud technologies (mobile/edge/cloud computing) have emerged as a promising paradigm to address the interaction- and resource-intensive nature of data-intensive AgI services. In this paper, we focus on the design of control policies for the joint orchestration of compute, caching, and communication (3C) resources in next-generation 3C networks for the delivery of data-intensive AgI services. We design the first throughput-optimal control policy that coordinates joint decisions around (i) routing paths and processing locations for live data streams, with (ii) cache selection and distribution paths for associated data objects. We then extend the proposed solution to include a max-throughput data placement policy and two efficient replacement policies. Numerical results demonstrate the superior performance obtained via the novel multi-pipeline flow control and 3C resource orchestration mechanisms of the proposed policy, compared with state-of-the-art algorithms that lack full 3C integrated control.

关键词： Deep reinforcement learning   Mobile edge computing   Internet of vehicles   Task offloading   Asynchronous advantage actor-critic  

摘要： Adopting Internet of Vehicles (IoV) technology has led to many new uses to improve traffic control, safety, and entertainment services. Still, the increasing amount of information these applications produce poses significant obstacles regarding response time, power usage, and other related issues. To enhance the functionality of IoV systems, this paper introduces a new way that utilizes Deep Reinforcement Learning (DRL) and Mobile Edge Computing (MEC) to improve its performance. Specifically, our DRL framework employs a convolutional neural network-based Asynchronous Advantage Actor-Critic (A3C) algorithm, chosen for its efficacy in processing spatial data relevant to IoV systems such as vehicle locations and speeds. The optimization problem considers the vehicle's location and speed, the MEC server's resources, and the IoV application's requirements by formulating it as a Markov Decision Process (MDP). Utilizing the A3C approach, our Deep Neural Network (DNN) method infers an optimal offloading policy. We optimized the proposed algorithm with strategies that include adaptive learning rate, gradient clipping, entropy regularization, and generalized advantage estimation. The optimized algorithm considers factors such as distance, bandwidth, and communication requirements to provide efficient task-offloading solutions, leading to better system utility and performance. The proposed strategy outperforms comparable models through comprehensive simulations, providing an average enhancement of 20.50% in energy consumption, 15.86% in latency, and 11.94% in execution time, emphasizing the effectiveness and superiority of the suggested algorithm in dealing with various workloads while reducing energy consumption, latency, and execution times.

关键词： reconfigurable intelligent surfaces   mobile edge computing   double-deep Q-network   time division multiple access  

摘要： Unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) are increasingly employed in mobile edge computing (MEC) systems to flexibly modify the signal transmission environment. This is achieved through the active manipulation of the wireless channel facilitated by the mobile deployment of UAVs and the intelligent reflection of signals by RISs. However, these technologies are subject to inherent limitations such as the restricted range of UAVs and limited RIS coverage, which hinder their broader application. The integration of UAVs and RISs into UAV-RIS schemes presents a promising approach to surmounting these limitations by leveraging the strengths of both technologies. Motivated by the above observations, we contemplate a novel UAV-RIS-aided MEC system, wherein UAV-RIS plays a pivotal role in facilitating communication between terrestrial vehicle users and MEC servers. To address this challenging non-convex problem, we propose an energy-constrained approach to maximize the system's energy efficiency based on a double-deep Q-network (DDQN), which is employed to realize joint control of the UAVs, passive beamforming, and resource allocation for MEC. Numerical results demonstrate that the proposed optimization scheme significantly enhances the system efficiency of the UAV-RIS-aided time division multiple access (TDMA) network.