Research on Offloading Strategy for Mobile Edge Computing Based on Improved Grey Wolf Optimization Algorithm

Zhang, Wenzhu; Tuo, Kaihang

doi:10.3390/electronics12112533

Cited by 6 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decision and resource allocation for offloading in vehicular edge computing has become a research hotspot in recent years, attracting widespread attention. [17] proposed an adaptive joint offloading strategy for vehicular edge computing without needing cloud computing support using an improved grey wolf algorithm. The strategy establishes a task offloading and computation model with constraints on task computation latency, computation energy consumption, and MEC server computation resources.…”

Section: Related Workmentioning

confidence: 99%

Digital Twin-Assisted Vehicles Edge Network Computing Offloading Scheme

Zhu,

Tan,

2023

Preprint

View full text Add to dashboard Cite

Traditional vehicle edge computing research has not fully considered the differences between vehicle tasks and edge server computing resources while often ignoring the use of deep reinforcement learning (DRL), which requires a large amount of training data, and DRL is easy to fall into the problem of local optimality. Therefore, this paper proposed a digital twin (DT) -assisted vehicle edge network computation offloading method. For the problem of DRL requiring a large amount of training data, a real-time data acquisition method based on DT is proposed for vehicle tasks and edge nodes. The differentiability of computing resources proposed a computing model based on deep neural network (DNN) partitioning and early exit mechanism, making full use of the computing resources of edge servers and vehicles, reducing the computation delay and transmission delay of tasks, Aiming at the problem that the asynchronous dominant actor-critic (A3C) algorithm in DRL is easy to fall into the local optimal solution, the dynamic baseline and ε-greedy policy are introduced based on A3C and used to select the channel to reduce the transmission delay further. Experimental results show that this scheme outperforms other comparative methods and can effectively reduce the delay of task offloading in vehicular edge computing.

show abstract

Section: Related Workmentioning

confidence: 99%

Digital Twin-Assisted Vehicles Edge Network Computing Offloading Scheme

Zhu,

Tan,

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In these studies, the cost is usually minimized by computation offloading and resource allocation or task scheduling. In [16], the authors developed an improved gray-wolf optimization algorithm to optimize the computation offloading so as to reduce the system cost. In [17], the system cost of the MEC-assisted UDN was reduced through computation offloading strategies, subchannel assignments and power allocation.…”

Section: Introductionmentioning

confidence: 99%

Residual Energy-Based Computation Efficiency Maximization in Dense Edge Computing Systems

Wu,

Li,

Dong

et al. 2023

Electronics

View full text Add to dashboard Cite

With the rapid development of 5G, artificial intelligence, the internet of things (IoT) and other technologies, the number of intelligent terminal devices is growing explosively, bringing huge challenges to the existing communication network and cloud computing service mode. The dense edge computing system (DECS), which combines mobile edge computing (MEC) with an ultra-dense network (UDN), has the potential to significantly improve low latency of communications and enhance the quality of experience (QoE) of user equipments (UEs). In this paper, to achieve energy-efficient MEC, computation efficiency (CE) is maximized by jointly optimizing computation offloading, subchannel allocation and power allocation, which yields a challenging non-convex problem. Specially, due to the heterogeneity of UE battery capacities and residual energy, the residual energy of UEs should be taken into consideration in order to achieve better QoE. Therefore, we develop a residual energy-based computation efficiency (RECE) optimization scheme to maximize CE, where the optimization problem is divided into three subproblems. Firstly, the computation offloading subproblem is addressed by a many-to-one matching strategy. Secondly, the subchannel allocation subproblem is dealt with by adopting the graph coloring algorithm. Finally, the power allocation subproblem is solved by the concave–convex procedure (CCCP) method. The numerical results illustrate that UEs’ CE can be optimized based on their residual energy in the proposed RECE scheme. Additionally, compared to a scheme without considering UE residual energy, the system CE can be much enhanced, and the UE energy consumption can be significantly reduced in the RECE scheme.

show abstract