Maximization of Value of Service for Mobile Collaborative Computing Through Situation-Aware Task Offloading

Chen, Ruitao; Wang, Xianbin

doi:10.1109/tmc.2021.3086687

Cited by 9 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both binary ofoading and partial ofoading are common task ofoading methods [13]. Binary ofoading refers to the approach of completely ofoading a task to a local or edge node for processing.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Dual-Agent Approach for Coordinated Task Offloading and Resource Allocation in MEC

Dong,

Pan,

Zheng

et al. 2023

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Multiaccess edge computing (MEC) is a novel distributed computing paradigm. In this paper, we investigate the challenges of task offloading scheduling, communication bandwidth, and edge server computing resource allocation for multiple user equipments (UEs) in MEC. Our primary objective is to minimize system latency and local energy consumption. We explore the binary offloading and partial offloading methods and introduce the dual agent-TD3 (DA-TD3) algorithm based on the deep reinforcement learning (DRL) TD3 algorithm. The proposed algorithm coordinates task offloading scheduling and resource allocation for two intelligent agents. Specifically, agent 1 overcomes the action space explosion problem caused by the increasing number of UEs, by utilizing both binary and partial offloading. Agent 2 dynamically allocates communication bandwidth and computing resources to adapt to different task scenarios and network environments. Our simulation experiments demonstrate that the binary and partial offloading schemes of the DA-TD3 algorithm significantly reduce system latency and local energy consumption compared with deep deterministic policy gradient (DDPG) and other offloading schemes. Furthermore, the partial offloading optimization scheme performs the best.

show abstract

Section: Related Workmentioning

confidence: 99%

“…(11) Store the (ob 2 (t), ac 2 (t), re 1,2 (t), ob 2 (t + 1)) in the replay bufer of agent 2. (12) if batch size < the current capacity of bufer Ten (13) for agent i � 1, 2 do (14) Sample a batch of experiences randomly. (15) Calculate the loss of critic net Q i θ 1,2 according to equation ( 15).…”

Section: Experimental Settingsmentioning

confidence: 99%

A Dual-Agent Approach for Coordinated Task Offloading and Resource Allocation in MEC

Dong,

Pan,

Zheng

et al. 2023

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

A Framework for Collaborative Computing on Top of Mobile Cloud Computing to Exploit Idle Resources

Babu

Upadhayaya²

2022

Ann. Data. Sci.

View full text Add to dashboard Cite

DRL-based dependent task offloading with delay-energy tradeoff in medical image edge computing

Liu,

Tian,

Wang

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

Task offloading solves the problem that the computing resources of terminal devices in hospitals are limited by offloading massive radiomics-based medical image diagnosis model (RIDM) tasks to edge servers (ESs). However, sequential offloading decision-making is NP-hard. Representing the dependencies of tasks and developing collaborative computing between ESs have become challenges. In addition, model-free deep reinforcement learning (DRL) has poor sample efficiency and brittleness to hyperparameters. To address these challenges, we propose a distributed collaborative dependent task offloading strategy based on DRL (DCDO-DRL). The objective is to maximize the utility of RIDM tasks, which is a weighted sum of the delay and energy consumption generated by execution. The dependencies of the RIDM task are modeled as a directed acyclic graph (DAG). The sequence prediction of the S2S neural network is adopted to represent the offloading decision process within the DAG. Next, a distributed collaborative processing algorithm is designed on the edge layer to further improve run efficiency. Finally, the DCDO-DRL strategy follows the discrete soft actor-critic method to improve the robustness of the S2S neural network. The numerical results prove the convergence and statistical superiority of the DCDO-DRL strategy. Compared with other algorithms, the DCDO-DRL strategy improves the execution utility of the RIDM task by at least 23.07, 12.77, and 8.51% in the three scenarios.

show abstract

Maximization of Value of Service for Mobile Collaborative Computing Through Situation-Aware Task Offloading

Cited by 9 publications

References 34 publications

A Dual-Agent Approach for Coordinated Task Offloading and Resource Allocation in MEC

A Dual-Agent Approach for Coordinated Task Offloading and Resource Allocation in MEC

A Framework for Collaborative Computing on Top of Mobile Cloud Computing to Exploit Idle Resources

DRL-based dependent task offloading with delay-energy tradeoff in medical image edge computing

Contact Info

Product

Resources

About