Deep Reinforcement Learning for Time-Energy Tradeoff Online Offloading in MEC-Enabled Industrial Internet of Things

Jiao, Xianlong; Ou, Hongjun; Chen, Shiguang; Guo, Songtao; Qu, Yuben; Xiang, Chaocan; Shang, Jiaxing

doi:10.1109/tnse.2023.3263169

Cited by 5 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The payment cost in computational offloading within a MEC network refers to the financial or monetary expenses associated with offloading a task from the user's device to an edge server or cloudlet for execution. This cost vary based on various factors and can impact the decision-making process for task offloading [ 82 , 140 , 142 , 91 , 93 , [190] , [191] , [192] , [193] ].…”

Section: Resultsmentioning

confidence: 99%

“…EUA is a public real-world dataset, which includes the geographical locations of 816 end-users and 125 base stations in Melbourne, Australia [ 219 , [220] , [221] , [222] ]. References [ 180 , [192] , [223] , [224] ] selected this data set as the distribution of MEC base stations and the activity trajectories of mobile devices, and then superimposed specific generated computing tasks to build a verification environment for the offloading mechanism.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A comprehensive review on internet of things task offloading in multi-access edge computing

Dayong,

Bin Abu Bakar,

Isyaku

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

A comprehensive review on internet of things task offloading in multi-access edge computing

Dayong,

Bin Abu Bakar,

Isyaku

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…First, [24] evolves the DROO algorithm from [22] to address the task offloading problem, along with data from EUA dataset [29]. Different from our work, this solution is centralized, so decision-making might be challenging mainly because of the overhead produced in both the network and the MEC server by sending much information, apart from the privacy concerns this could raise [13] and the scalability limitation of RL-based algorithms due to the huge decision space, increasing network congestion and, consequently, latencies [12].LyDROO [7], as another proposal emanated from DROO, applies Lyapunov optimization to decouple the multi-stage stochastic Mixed-Integer Nonlinear Programming (MINLP) and solves each resulting subproblem via DROO algorithm.…”

Section: Ml-based Solutionsmentioning

confidence: 99%

Deep Reinforcement Learning techniques for dynamic task offloading in the 5G edge-cloud continuum

Nieto,

de la Iglesia,

Lopez-Novoa

et al. 2024

J Cloud Comp

View full text Add to dashboard Cite

The integration of new Internet of Things (IoT) applications and services heavily relies on task offloading to external devices due to the constrained computing and battery resources of IoT devices. Up to now, Cloud Computing (CC) paradigm has been a good approach for tasks where latency is not critical, but it is not useful when latency matters, so Multi-access Edge Computing (MEC) can be of use. In this work, we propose a distributed Deep Reinforcement Learning (DRL) tool to optimize the binary task offloading decision, this is, the independent decision of where to execute each computing task, depending on many factors. The optimization goal in this work is to maximize the Quality-of-Experience (QoE) when performing tasks, which is defined as a metric related to the battery level of the UE, but subject to satisfying tasks’ latency requirements. This distributed DRL approach, specifically an Actor-Critic (AC) algorithm running on each User Equipment (UE), is evaluated through the simulation of two distinct scenarios and outperforms other analyzed baselines in terms of QoE values and/or energy consumption in dynamic environments, also demonstrating that decisions need to be adapted to the environment’s evolution.

show abstract

“…Various factors are considered, such as task characteristics (e.g., computation-intensive or data-intensive), network conditions, energy consumption, latency requirements, and the number and capacity of severs. Decision-making techniques, such as optimization algorithms [14][15][16] or machine learning models [17][18][19], are employed to determine the most suitable tasks offloading decision. Once the decision to offload certain tasks is made, the next step is to allocate the necessary resources to perform the offloading and computation of the tasks.…”

Section: Introductionmentioning

confidence: 99%

An Improved Gravitational Search Algorithm for Task Offloading in a Mobile Edge Computing Network with Task Priority

Xu,

Liu,

Fan

et al. 2024

Electronics

View full text Add to dashboard Cite

Mobile edge computing (MEC) distributes computing and storage resources to the edge of the network closer to the user and significantly reduces user task completion latency and system energy consumption. This paper investigates the problem of computation offloading in a three-tier mobile edge computing network composed of multiple users, multiple edge servers, and a cloud server. In this network, each user’s task can be divided into multiple subtasks with serial and parallel priority relationships existing among these subtasks. An optimization model is established with the objective of minimizing the total user delay and processor cost under constraints such as the available resources of users and servers and the interrelationships among the subtasks. An improved gravitational search algorithm (IGSA) is proposed to solve this optimization model. In contrast with the other gravitational search algorithm, the convergence factor is introduced in the calculation of the resultant force and the crossover operation in a genetic algorithm is performed when generating the new particles during each iteration. The simulation results show that the proposed IGSA greatly improves the system performance compared with the existing algorithms.

show abstract

Deep Reinforcement Learning for Time-Energy Tradeoff Online Offloading in MEC-Enabled Industrial Internet of Things

Cited by 5 publications

References 41 publications

A comprehensive review on internet of things task offloading in multi-access edge computing

A comprehensive review on internet of things task offloading in multi-access edge computing

Deep Reinforcement Learning techniques for dynamic task offloading in the 5G edge-cloud continuum

An Improved Gravitational Search Algorithm for Task Offloading in a Mobile Edge Computing Network with Task Priority

Contact Info

Product

Resources

About