Multiagent Deep Reinforcement Learning for Joint Multichannel Access and Task Offloading of Mobile-Edge Computing in Industry 4.0

Cao, Zilong; Zhou, Pan; Li, Ruixuan; Huang, Siqi; Wu, Dapeng

doi:10.1109/jiot.2020.2968951

Cited by 127 publications

(62 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, as the environment changes, new environment models can be established and revised to complete various tasks [2]. As an important tool for future social development, intelligent robot technology plays a prominent role in many fields [3][4][5]. For example, the application of intelligent robots in the manufacturing field can increase output with high efficiency and successfully promote the development of intelligent production systems and the intelligent life of humans in the future.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Optimization of Multi‐Intelligent Robot Control System Based on Wireless Communication Network

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The robot is a very complex multi-input multioutput nonlinear system. It has time-varying, strong coupling, and nonlinear dynamic characteristics, and its control is very complicated. Due to the inaccuracy of measurement and modeling, coupled with changes in the load and the influence of external disturbances, it is actually impossible to obtain an accurate and complete dynamic model of the robot. We must face the existence of various uncertain factors of the robot. This paper analyzes the real-time communication protocol in the wireless network control system and confirms that the main way to improve the real-time performance of the wireless network control system is to implement the real-time media access control (MAC) protocol. This paper studies robots from the perspective of control and mainly discusses how to use artificial immune algorithms to design robust nonlinear proportion integral derivative (PID) controllers. A nonlinear PID controller is used to replace the classic PID controller. The nonlinear link can be adjusted with the change of the error, so as to achieve the purpose of improving the adaptability and robustness to obtain satisfactory tracking performance. We carried out selective compliance assembly robot arm (SCARA) robot remote control experiment, dual robot following experiment, SCARA and ABB robot collisionless motion planning experiment, and multirobot intelligent collaborative assembly experiment. The experimental results show that the C/S mode remote control system has good practicability and can complete remote tasks; the P2P communication system has good information transmission effects and can realize real-time information sharing between robots; the collision-free motion planning algorithm enables the dual robots to complete obstacle avoidance tasks well in complex operating environments; the functional modules of the system can closely cooperate to complete the tasks in coordination, and the multirobot system has a certain degree of intelligence.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] Optimization of Multi‐Intelligent Robot Control System Based on Wireless Communication Network

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Their goal was to minimize the average completion time of tasks under the migration energy budget. On the other hand, Cao et al [29] used multi-agent deep deterministic policy gradients (MADDPG) algorithm [30] to solve the coordination of channel access and task offloading in order to achieve efficient computing.…”

Section: Related Workmentioning

confidence: 99%

DeepEdge: A Deep Reinforcement Learning based Task Orchestrator for Edge Computing

Baris¹,

Baktır²,

Sonmez³

et al. 2021

Preprint

View full text Add to dashboard Cite

The improvements in the edge computing technology pave the road for diversified applications that demand real-time interaction. However, due to the mobility of the end-users and the dynamic edge environment, it becomes challenging to handle the task offloading with high performance. Moreover, since each application in mobile devices has different characteristics, a task orchestrator must be adaptive and have the ability to learn the dynamics of the environment. For this purpose, we develop a deep reinforcement learning based task orchestrator, DeepEdge, which learns to meet different task requirements without needing human interaction even under the heavily-loaded stochastic network conditions in terms of mobile users and applications. Given the dynamic offloading requests and time-varying communication conditions, we successfully model the problem as a Markov process and then apply the Double Deep Q-Network (DDQN) algorithm to implement DeepEdge. To evaluate the robustness of DeepEdge, we experiment with four different applications including image rendering, infotainment, pervasive health, and augmented reality in the network under various loads. Furthermore, we compare the performance of our agent with the four different task offloading approaches in the literature. Our results show that DeepEdge outperforms its competitors in terms of the percentage of satisfactorily completed tasks.

show abstract

“…A number of proposals and approaches for improving particular technology using MEC through ML exist. For example, [306] uses DRL to improve online computing offloading for non-orthogonal multiple access, [307] and [308] use multi-agent RL for cooperative caching and task offloading in MEC, respectively. Authors in [309] propose DRL-based energy-efficient task offloading for machine type communication in the edge.…”

Section: B Ml-based Optimization Of the Edge Infrastructurementioning

confidence: 99%

Machine Learning Meets Communication Networks: Current Trends and Future Challenges

et al. 2020

View full text Add to dashboard Cite

The growing network density and unprecedented increase in network traffic, caused by the massively expanding number of connected devices and online services, require intelligent network operations. Machine Learning (ML) has been applied in this regard in different types of networks and networking technologies to meet the requirements of future communicating devices and services. In this article, we provide a detailed account of current research on the application of ML in communication networks and shed light on future research challenges. Research on the application of ML in communication networks is described in: i) the three layers, i.e., physical, access, and network layers; and ii) novel computing and networking concepts such as Multi-access Edge Computing (MEC), Software Defined Networking (SDN), Network Functions Virtualization (NFV), and a brief overview of ML-based network security. Important future research challenges are identified and presented to help stir further research in key areas in this direction. INDEX TERMS Communication networks, machine learning, physical layer, MAC layer, network layer, SDN, NFV, MEC, security, artificial intelligence (AI) I. INTRODUCTION T HE security, availability and performance demands of new applications, services and devices are increasing at a pace higher than anticipated. Real-time responsiveness in application areas like e-health, traffic, and industry requires communication networks to make real-time decisions autonomously. Such real-time autonomous decision-making requires that the network must react and learn from the environment, and control itself without human interventions. However, communication networks have until now taken a different path. Traditional networks rely on human involvement to respond manually to changes such as traffic variation, updates in network functions and services, security breaches, and faults. Human-machine interactions have resulted in network downtime [1], have opened the network to security vulnerabilities [2], and lead to many other challenges in current communication networks [3], [4]. The requirement for human interaction or manual configuration constitutes a major hindrance for a network to use its past experiences to adapt to changing requirements. The general idea is to predict the (future) behavior of a service, network segment, user or User Equipment (UE), and tune the network at run-time based on this information. For instance, the movement trajectory of a user can be predicted using

show abstract

Multiagent Deep Reinforcement Learning for Joint Multichannel Access and Task Offloading of Mobile-Edge Computing in Industry 4.0

Cited by 127 publications

References 31 publications

[Retracted] Optimization of Multi‐Intelligent Robot Control System Based on Wireless Communication Network

[Retracted] Optimization of Multi‐Intelligent Robot Control System Based on Wireless Communication Network

DeepEdge: A Deep Reinforcement Learning based Task Orchestrator for Edge Computing

Machine Learning Meets Communication Networks: Current Trends and Future Challenges

Contact Info

Product

Resources

About