Multi-user Mobile Edge Computing Research Articles

Deep reinforcement learning-based low-latency task offloading for mobile-edge computing networks

Wireless Mobile Edge Computing (MEC) is an emerging solution to facilitate users’ computing. However, there are still some drawbacks, such as slow learning speed and high task latency. To overcome these difficulties, a deep reinforcement learning (DRL)-based task offloading (DRTO) framework is proposed, taking into account the time-varying nature of wireless channels and the unpredictability of task arrivals in multi-user MEC systems. Many deep neural networks (DNNs) are also used as scalable solutions to quickly determine the best offloading strategy by combining the perceptual capabilities of deep learning with the decision making capabilities of reinforcement learning (RL). Additionally, the concept of a minimum upper bound on the target Q-value is utilized to address the value overestimation problem that occurs during offload policy updates. This approach aims to minimize the latency of offload decisions by considering different channel environments, variable latency constraints among many users, and limited computational resources. Simulation results show that the algorithm reduces computation time and latency while achieving near-optimal performance compared to traditional Deep Deterministic Policy Gradient (DDPG) and Q-learning optimization methods. In addition, DRTO achieves more than 99.6% computational speedup compared to current almost ideal benchmarking techniques. Thus, the DRTO computational offload approach offers great potential for reducing overall system latency and improving the user experience.

Optimization of resource allocation strategy for high-speed railway based on deep reinforcement learning

With the accelerated development of high-speed railway (HSR), the contradiction between the surge of user services and the demand for resource has become increasingly prominent. Mobile edge computing (MEC) has emerged to improve performance, reduce communication delay and ease network load. In this paper, we design a multi-user MEC system framework that aims to solve the joint optimization problem of computation offloading and resource allocation in HSR communication scenario with deep reinforcement learning algorithm. The framework dynamically allocates computation resource and network bandwidth through the real-time distance between users and base station (BS) to achieve optimal resource utilization and maximize user experience. To achieve this goal, we use a deep reinforcement learning based dynamic computation offloading and resource allocation (DDCORA) optimization algorithm. The algorithm minimizes the system cost by sharing state information among different users and making collaborative decisions to rationally allocate spectrum resource and computation resource. Simulation results show that DDCORA algorithm can significantly decrease the system cost while enhancing the overall system performance and user experience.

Joint Task Offloading and Resource Allocation in Multi-User Mobile Edge Computing With Continuous Spectrum Sharing

Joint Task Offloading and Resource Allocation in Multi-User Mobile Edge Computing With Continuous Spectrum Sharing

Priority-aware path planning and user scheduling for UAV-mounted MEC networks: A deep reinforcement learning approach

Owing to the flexibility and controllability, unmanned aerial vehicle (UAV) is frequently integrated into mobile edge computing (MEC) network to improve the system performance. This paper investigates a novel multi-user multi-hotspot MEC network supported by a UAV, where the UAV can help compute the tasks offloaded from end users (EUs) in multiple hotspots. In this network, we consider the task priority and task size are dynamic, due to the EUs’ demands. We then propose a task priority-based system utility model to evaluate the network performance, which considers the priorities of tasks based on the urgent or non-urgent level. We further formulate a utility maximization problem that jointly optimizes the UAV’s access path and the EUs’ offloading strategy, while satisfying the constraints related to the UAV’s battery capacity and UAV’s duration of flight. Since the formulated problem is a NP-hard problem, we present a deep reinforcement learning (DRL) based scheme as a solution. The DRL scheme utilizes principles from reinforcement learning to address the optimization problem effectively, resulting in a dynamic solution. Simulation results demonstrate that the proposed DRL scheme outperforms alternative benchmark schemes in terms of system utility.

Task Scheduling for Federated Learning in Edge Cloud Computing Environments by Using Adaptive-Greedy Dingo Optimization Algorithm and Binary Salp Swarm Algorithm

With the development of computationally intensive applications, the demand for edge cloud computing systems has increased, creating significant challenges for edge cloud computing networks. In this paper, we consider a simple three-tier computational model for multiuser mobile edge computing (MEC) and introduce two major problems of task scheduling for federated learning in MEC environments: (1) the transmission power allocation (PA) problem, and (2) the dual decision-making problems of joint request offloading and computational resource scheduling (JRORS). At the same time, we factor in server pricing and task completion, in order to improve the user-friendliness and fairness in scheduling decisions. The solving of these problems simultaneously ensures both scheduling efficiency and system quality of service (QoS), to achieve a balance between efficiency and user satisfaction. Then, we propose an adaptive greedy dingo optimization algorithm (AGDOA) based on greedy policies and parameter adaptation to solve the PA problem and construct a binary salp swarm algorithm (BSSA) that introduces binary coding to solve the discrete JRORS problem. Finally, simulations were conducted to verify the better performance compared to the traditional algorithms. The proposed algorithm improved the convergence speed of the algorithm in terms of scheduling efficiency, improved the system response rate, and found solutions with a lower energy consumption. In addition, the search results had a higher fairness and system welfare in terms of system quality of service.

Sequential Offloading for Distributed DNN Computation in Multiuser MEC Systems

This paper studies a sequential task offloading problem for a multiuser mobile edge computing (MEC) system. While most of the existing works consider static one-shot offloading optimization with fixed wireless channel conditions and fixed computational tasks, we consider a dynamic optimization approach, which embraces wireless channel fluctuations and random deep neural network (DNN) task arrivals over an infinite horizon. Specifically, we introduce a local CPU workload queue (WD-QSI) and an MEC server workload queue (MEC-QSI) to model the dynamic workload of DNN tasks at each WD and the MEC server, respectively. The transmit power and the partitioning of the local DNN task at each WD are dynamically determined based on the instantaneous channel conditions (to capture the transmission opportunities) and the instantaneous WD-QSI and MEC-QSI (to capture the dynamic urgency of the tasks) to minimize the average latency of the DNN tasks. The joint optimization can be formulated as an ergodic Markov decision process (MDP), in which the optimality condition is characterized by a centralized Bellman equation. However, the brute force solution of the MDP is not viable due to the curse of dimensionality as well as the requirement for knowledge of the global state information. To overcome these issues, we first decompose the MDP into multiple lower dimensional sub-MDPs, each of which can be associated with a WD or the MEC server. Next, we further develop a parametric online Q-learning algorithm, so that each sub-MDP is solved locally at its associated WD or the MEC server. The proposed solution is completely decentralized in the sense that the transmit power for sequential offloading and the DNN task partitioning can be determined based on the local channel state information (CSI) and the local WD-QSI at the WD only. Additionally, no prior knowledge of the distribution of the DNN task arrivals or the channel statistics will be needed for the MEC server. The proposed solution can achieve the superb performance over various state-of-the-art baselines.

Soft Actor–Critic-Based Computation Offloading in Multiuser MEC-Enabled IoT—A Lifetime Maximization Perspective

This paper studies the network lifetime optimization problem in a multi-user mobile edge computing (MEC)-enabled Internet of things (IoT) system comprising an access point (AP), a MEC server, and a set of K mobile devices (MDs) with limited battery capacity. Considering the residual battery energy at the MDs, stochastic task arrivals, and time-varying wireless fading channels, a soft actor-critic (SAC)-based deep reinforcement learning (DRL) lifetime maximization, called DeepLM, is proposed to jointly optimize the task splitting ratio, the local CPU-cycle frequencies at the MDs, the bandwidth allocation, and the CPU-cycle frequency allocation at the MEC server subject to the task queuing backlogs constraint, the bandwidth constraint, and maximum CPU-cycle frequency constraints at the MDs and the MEC server. Our results reveal that DeepLM enjoys a fast convergence rate and a small oscillation amplitude. We also compare the performance of DeepLM with three benchmark offloading schemes, namely, fully edge computing (FEC), fully local computing (FLC), and random computation offloading (RCO). DeepLM increases the network lifetime by 496% and 229% compared to the FLC and RCO schemes. Interestingly, it achieves such a colossal lifetime improvement when its non-backlog probability is 0.99, while that of FEC, FLC, and RCO is 0.69, 0.53, and 0.25, respectively, showing a significant performance gain of 30%, 46%, and 74%.

Efficient Mobility Management in Mobile Edge Computing Networks: Joint Handover and Service Migration

Mobile edge computing (MEC) has been envisioned as an essential technology for latency-critical applications by providing computing services in close proximity to mobile users. Bringing MEC to come into practice, how to support user mobility remains challenging. In addition to seeking a thorny trade-off between service latency and migration cost, both interactions in space and time exist in mobility management, which requires collaboration among users and perfect prior knowledge, including user mobility and network information. In this paper, we propose an efficient mobility management framework for MEC networks, in which mobility management is operated centered around users’ performance and cost, while radio access and computing service provision are loosely coupled. With a loosely coupled design, the proposed framework exhibits more flexibility and incurs higher complexity. Focusing on multi-user and multi-cell MEC networks, this joint control problem is formulated to maximize the long-term total utility accounting for the service delay and migration cost. Considering the exponential complexity, a distributed mobility management approach is developed, which combines game theory and user-oriented deep reinforcement learning to deal with the interactions in space and time. Simulation results show the efficiency and scalability of the proposed approach.

Joint task offloading and resource allocation for multi-user and multi-server MEC networks: A deep reinforcement learning approach with multi-branch architecture

Mobile Edge Computing (MEC) is a promising computing paradigm in the context of 5G networks, as it enables the migration of workloads from User Equipments (UEs) to nearby MEC servers, thereby providing additional computing resources to UEs. In this paper, we propose a joint optimization approach to offloading decisions and resource allocation in a multi-user and multi-server MEC system, which operates in a time-varying environment. Our objective is to minimize the average task latency and discard rate under the constraints of latency and limited computing resources of the server. While traditional optimization methods have been used to solve computational offloading problems in static environments, these methods are not suitable for time-varying systems. Deep reinforcement learning can be an effective method for solving optimization problems in time-varying environments, as it can be used to adjust strategies in real-time in response to changes in the environment. However, the increased number of UEs in the system leads to a combinatorial increase in the number of possible actions, making it difficult for the algorithm to learn. To address this issue, we propose a multi-branch network based Deep Q Network (DQN) algorithm called Branch Deep Q Network (BDQN), which modifies the action generation network into a multi-branch network structure, each branch generates one-dimensional action. This modification makes the number of network outputs increase linearly. Numerical results show that the BDQN algorithm outperforms other baseline algorithms in terms of average task latency and discard rate.

STAR-RIS-Aided Mobile Edge Computing: Computation Rate Maximization With Binary Amplitude Coefficients

In this paper, simultaneously transmitting and reflecting (STAR) reconfigurable intelligent surface (RIS) is investigated in the multi-user mobile edge computing (MEC) system to improve the computation rate. Compared with traditional RIS-aided MEC, STAR-RIS extends the service coverage from half-space to full-space and provides new flexibility for improving the computation rate for end users. However, the STAR-RIS-aided MEC system design is a challenging problem due to the non-smooth and non-convex binary amplitude coefficients with coupled phase shifters. To fill this gap, this paper formulates a computation rate maximization problem via the joint design of the STAR-RIS phase shifts, reflection and transmission amplitude coefficients, the receive beamforming vectors, and energy partition strategies for local computing and offloading. To tackle the discontinuity caused by binary variables, we propose an efficient smoothing-based method to decrease convergence error, in contrast to the conventional penalty-based method, which brings many undesired stationary points and local optima. Furthermore, a fast iterative algorithm is proposed to obtain a stationary point for the joint optimization problem, with each subproblem solved by a low-complexity algorithm, making the proposed design scalable to a massive number of users and STAR-RIS elements. Simulation results validate the strength of the proposed smoothing-based method and show that the proposed fast iterative algorithm achieves a higher computation rate than the conventional method while saving the computation time by at least an order of magnitude. Moreover, the resultant STAR-RIS-aided MEC system significantly improves the computation rate compared to other baseline schemes with conventional reflect-only/transmit-only RIS.

Computation bits maximization in data compression-assisted MEC networks

In this article, we study the weighted sum computation bits (WSCB) maximization for a multiuser mobile edge computing (MEC) system while considering data compression at each edge user (EU). Considering the partial offloading scheme and data compression at each EU, we formulate a WSCB maximization problem by jointly optimizing the compression time, the computing and compression frequencies of all the EUs as well as the transmit power and time of EUs when performing task offloading. Since the formulated problem is non-convex and difficult to solve, we first replace the original problem with an equivalent one by using the proof by contradiction. Subsequently we introduce auxiliary variables for transforming the equivalent problem into a convex one that can be optimally solved by using the existing convex tools. Further, we devise the closed-form expressions for the optimal transmit power, compression and computing frequencies at each EU by using Karush-Kuhn–Tucker (KKT) conditions. Simulation results verify that our proposed scheme is better than several baseline schemes from the WSCB perspective.

Joint Task Offloading and Cache Placement for Energy-Efficient Mobile Edge Computing Systems

This letter investigates a cache-enabled multiuser mobile edge computing (MEC) system with dynamic task arrivals, taking into account the impact of proactive cache placement on the system’s overall energy consumption. We consider that an access point (AP) schedules a wireless device (WD) to offload computational tasks while executing the tasks of a finite library in the task caching phase, such that the nearby WDs with the same task request arriving later can directly download the task results in the task arrival and execution phase. We aim for minimizing the system’s weighted-sum energy over a finite-time horizon, by jointly optimizing the task caching decision and the MEC execution of the AP, and local computing as well as task offloading of the WDs at each time slot, subject to caching capacity, task causality, and completion deadline constraints. The formulated design problem is a mixed-integer nonlinear program. Under the assumption of fully predicable task arrivals, we first propose a branch-and-bound (BnB) based method to obtain the optimal offline solution. Next, we propose two low-complexity schemes based on convex relaxation and task-popularity, respectively. Finally, numerical results show the benefit of the proposed schemes over existing benchmark schemes.

QoS-aware offloading based on communication-computation resource coordination for 6G edge intelligence

Driven by the demands of diverse artificial intelligence (AI)-enabled application, Mobile Edge Computing (MEC) is considered one of the key technologies for 6G edge intelligence. In this paper, we consider a serial task model and design a quality of service (QoS)-aware task offloading via communication-computation resource coordination for multi-user MEC systems, which can mitigate the I/O interference brought by resource reuse among virtual machines. Then we construct the system utility measuring QoS based on application latency and user devices' energy consumption. We also propose a heuristic offloading algorithm to maximize the system utility function with the constraints of task priority and I/O interference. Simulation results demonstrate the proposed algorithm's significant advantages in terms of task completion time, terminal energy consumption and system resource utilization.

Intelligent Delay-Aware Partial Computing Task Offloading for Multiuser Industrial Internet of Things Through Edge Computing

The development of Industrial Internet of Things (IIoT) and Industry 4.0 has completely changed the traditional manufacturing industry. Intelligent IIoT technology usually involves a large number of intensive computing tasks. Resource-constrained IIoT devices often cannot meet the real-time requirements of these tasks. As a promising paradigm, the mobile-edge computing (MEC) system migrates the computation intensive tasks from resource-constrained IIoT devices to nearby MEC servers, thereby obtaining lower delay and energy consumption. However, considering the varying channel conditions as well as the distinct delay requirements for various computing tasks, it is challenging to coordinate the computing task offloading among multiple users. In this article, we propose an autonomous partial offloading system for delay-sensitive computation tasks in multiuser IIoT MEC systems. Our goal is to provide offloading services with minimum delay for better Quality of Service (QoS). Enlighten by the recent advancement of reinforcement learning (RL), we propose two RL-based offloading strategies to automatically optimize the delay performance. Specifically, we first implement the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning algorithm to provide a discrete partial offloading decision. Then, to further optimize the system performance with more flexible task offloading, the offloading decisions are given as continuous based on deep deterministic policy gradient (DDPG). The simulation results show that the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning scheme reduces the delay by 23%, and the DDPG scheme reduces the delay by 30%.

Joint Resource Allocation and Cache Placement for Location-Aware Multi-User Mobile-Edge Computing

With the growing demand for latency-critical and computation-intensive Internet of Things (IoT) services, the IoT-oriented network architecture, mobile-edge computing (MEC), has emerged as a promising technique to reinforce the computation capability of the resource-constrained IoT devices. To exploit the cloud-like functions at the network edge, service caching has been implemented to reuse the computation task input/output data, thus effectively reducing the delay incurred by data retransmissions and repeated execution of the same task. In a multiuser cache-assisted MEC system, users’ preferences for different types of services, possibly dependent on their locations, play an important role in the joint design of communication, computation, and service caching. In this article, we consider multiple representative locations, where users at the same location share the same preference profile for a given set of services. Specifically, by exploiting the location-aware users’ preference profiles, we propose joint optimization of the binary cache placement, the edge computation resource, and the bandwidth (BW) allocation to minimize the expected sum-energy consumption, subject to the BW and the computation limitations as well as the service latency constraints. To effectively solve the mixed-integer nonconvex problem, we propose a deep learning (DL)-based offline cache placement scheme using a novel stochastic quantization-based discrete-action generation method. The proposed hybrid learning framework advocates both benefits from the model-free DL approach and the model-based optimization. The simulations verify that the proposed DL-based scheme saves roughly 33% and 6.69% of energy consumption compared with the greedy caching and the popular caching, respectively, while achieving up to 99.01% of the optimal performance.

Resource Allocation in a Relay-Aided Mobile Edge Computing System

Mobile edge computing (MEC) provides wireless devices (WDs) more computing capability and lower latency by allowing them to offload their computation tasks to a nearby more powerful server. Furthermore, adopting the relaying technique can effectively improve the offloading performance, especially when the wireless channel conditions between WD and MEC server are poor. In this article, we consider a multiuser relay-aided MEC system targeting at minimizing the energy consumption. The relay can either execute the computation task by itself or offload the task to the MEC server. Under the partial computation offloading mode, an energy minimization problem is investigated by jointly optimizing transmit power, offloading time duration, and central processing unit (CPU) frequencies. To solve the nonconvex optimization problem, an iterative algorithm based on successive convex approximation (SCA) is developed. Furthermore, the closed-form expressions for the optimal transmission powers and the CPU frequencies are derived. The simulation results show that the proposed scheme can achieve a lower energy consumption than other benchmark schemes.

Multimodal semantic communication accelerated bidirectional caching for 6G MEC

Mobile Edge Computing (MEC) enables immersive XR with multimodal data by coordinating communication, computation, and caching (3C) resources upcoming 6G. The traditional communication constrained by Shannon’s theorem cannot accommodate the user demands for ultra-reliability and high throughput. In contrast, the semantic communication improves the quality of service and user experience by exploiting the semantic features. This paper constructs a multi-user MEC structure based on multimodal semantic communication for interactive AR/VR games. We construct a bidirectional caching task model to achieve cache-enhanced computing. To minimize the system cost, including the user latency, energy consumption, and storage size, we propose a content popularity-based DQN (CP-DQN) algorithm to make caching decisions. Then the CP-DQN is extended to the cache–computation coordination optimization algorithm (CCCA) to achieve the 3C resources tradeoff. Simulation results demonstrate that the proposed algorithm outperforms existing algorithms in terms of caching hit ratio, computation cost and edge resource utilization.

Joint Offloading and Resource Allocation Using Deep Reinforcement Learning in Mobile Edge Computing

Mobile edge computation offloading (MECO) has recently emerged as a promising method to support computation-intensive and latency-sensitive applications, significantly saving the battery energy of smart mobile devices (SMDs). However, on the one hand, the energy consumption depends on both the SMD and the MEC server, which makes it necessary to consider these two entities to achieve energy sustainability jointly. On the other hand, for a real-time mobile edge computing (MEC) system, efficient optimization algorithms based on binary offloading have received significant attention, while efficient algorithms for partial offloading under time-varying channels are seldom investigated. In this paper, we propose an energy-efficient algorithm based on deep reinforcement learning to optimize the overall energy cost in a real-time multi-user MEC system. We decompose the energy minimization problem into two sub-problems, where a deep neural network learns the optimal mapping between wireless channels and offloading ratios, and a closed-form solution for the optimal local frequency and a convex optimization algorithm are used to solve the resource allocation sub-problem. Finally, the extensive experiments demonstrate the effectiveness of our proposed algorithm in reducing the total energy consumption of the MECO system against several offloading schemes and achieving low processing latency fit to the time-varying wireless channels.

Task offloading for vehicular edge computing with imperfect CSI: A deep reinforcement approach

This article examines a multi-user mobile edge computing (MEC) system for the Internet of Vehicle (IoV), where one edge point (EP) nearby the vehicles can help assist in processing the compute-intensive tasks. For the MEC networks, the majority of existing works concentrate on the minimization of system cost of task offloading under the perfect channel estimation, which however fails to consider the practical limitation of imperfect channel estimation (CSI) because of vehicles’ high-mobility. Therefore, the goal of our study is to reduce the delay as well as energy consumption (EC) of computation and communication with imperfect CSI, which are the two significant performance metrics of MEC network. With this aim, we first express the system cost as a form of the linear combination of the delay and EC, and then formulate the optimization problem for the system cost. Moreover, a novel deep approach is proposed, which is integrated by deep reinforcement learning (DRL) with the Lagrange multiplier to jointly minimize the system cost. In particular, the DRL algorithm is employed to obtain the capable offloading strategy, while the Lagrange multiplier is used to obtain the bandwidth allocation. The simulated results are finally presented to show that the devised approach outperforms the traditional ones.

Users' experience matter: Delay sensitivity-aware computation offloading in mobile edge computing

As a promising computing paradigm, Mobile Edge Computing (MEC) provides communication and computing capability at the edge of the network to address the concerns of massive computation requirements, constrained battery capacity and limited bandwidth of the Internet of Things (IoT) systems. Most existing works on mobile edge task ignores the delay sensitivities, which may lead to the degraded utility of computation offloading and dissatisfied users. In this paper, we study the delay sensitivity-aware computation offloading by jointly considering both user's tolerance towards delay of task execution and the network status under computation and communication constraints. Specifically, we use a specific multi-user and multi-server MEC system to define the latency sensitivity of task offloading based on the analysis of delay distribution of task categories. Then, we propose a scoring mechanism to evaluate the sensitivity-dependent utility of task execution and devise a Centralized Iterative Redirection Offloading (CIRO) algorithm to collect all information in the MEC system. By starting with an initial offloading strategy, the CIRO algorithm enables IoT devices to cooperate and iteratively redirect task offloading decisions to optimize the offloading strategy until it converges. Extensive simulation results show that our method can significantly improve the utility of computation offloading in MEC systems and has lower time complexity than existing algorithms.