Multi-Agent Reinforcement Learning for Distributed Joint Communication and Computing Resource Allocation over Cell-Free Massive MIMO-enabled Mobile Edge Computing Network

Tilahun, Fitsum Debebe; Abebe, Ameha T.; Kang, Chung G.

doi:10.48550/arxiv.2201.09057

Cited by 3 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…State: The full system observation comprises the channel vector of a single vehicle user and the queue length of the task buffer. We presume that each user agent's status is only observed locally by its system 10 . On this principle, each user will choose to operate autonomously from other users.…”

Section: Modeling Based On Maddpg Algorithmmentioning

confidence: 99%

IoV mobile edge computing task offloading based on MADDPG algorithm

Jin,

Lv,

Wang

2023

Third International Conference on Digital Signal and Computer Communications (DSCC 2023)

View full text Add to dashboard Cite

The Internet of Vehicles has become a crucial component of contemporary transportation as a significant subset of the Internet of Things. The demand for periphery computing is increasing as vehicle intelligence and connectivity continues to advance. However, the task unloading of onboard edge computing encounters several obstacles, including limited computing power, communication delay, etc. This paper proposes a task discharge scheme for Internet of Vehicles edge computing based on the MADDPG algorithm to address these issues. The scheme employs a multi-agent reinforcement learning algorithm to accomplish cooperation and communication between vehicles and optimizes the task allocation strategy to improve the efficiency and performance of onboard edge computing. Simulation results indicate that, in comparison to other algorithms, this algorithm can significantly reduce the system's overall execution latency and possesses strong adaptability.

show abstract

Section: Modeling Based On Maddpg Algorithmmentioning

confidence: 99%

IoV mobile edge computing task offloading based on MADDPG algorithm

Jin,

Lv,

Wang

2023

Third International Conference on Digital Signal and Computer Communications (DSCC 2023)

View full text Add to dashboard Cite

show abstract

“…Simulation results show that the proposed scheme by the author is superior to other benchmark schemes in terms of latency and energy consumption metrics. Tilahun et al [91] proposed a JCCRA problem and a MADDPG algorithm, which solves the task to minimize the user's energy consumption while satisfying tight delay constraints. Simulation results show that the authors' proposed scheme significantly outperforms the heuristic baseline in terms of energy consumption.…”

Section: ) Resource Provisioningmentioning

confidence: 99%

A Survey of State-of-the-art on Edge Computing: Theoretical Models, Technologies, Directions, and Development Paths

Liu

Luo

Chen³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

In order to describe the roadmap of current edge computing research activities, we first gave a brief overview of the most advanced edge computing surveys published in the last six years. We found that edge computing has been adaptively integrated into growing number of applications. Edge computing theory and technology will bring substantial innovation and incentive, as well as a large number of application scenarios in different fields, such as edge computing assisted smart city, Internet of Vehicles(IoV), Industrial Internet and many other different fields. However, we believe that a comprehensive investigation of the essence of edge computing is still missing by using the most advanced theoretical models, technologies, directions and development paths. To fill this gap, we have conducted an in-depth survey by identifying and classifying the latest high-quality research results related to theoretical discoveries in edge computing, as well as edge convergence technologies that intersect with the frontiers of Information and Communication Technology (ICT). Finally, we also summarize several promising open issues as future research directions. We hope that this survey report will attract much more attention, stimulate fruitful discussions, and provide ideas and useful guidance for further research on the theoretical models, technologies, directions and development paths of edge computing.

show abstract

“…For instance, in [10], a MARL-based optimization of pilot assignment for mitigating pilot contamination was proposed, which can effectively reduce the computational complexity. Also, in [11], the joint communication and computing resource allocation problem was solved by the fully distributed MARL-based method. Unfortunately, for largescale MARL, the joint learning is unlikely to be implemented in practical application scenarios due to its high computational complexity.…”

Section: Introductionmentioning

confidence: 99%

Uplink Power Control for Extremely Large-Scale MIMO with Multi-Agent Reinforcement Learning and Fuzzy Logic

Liu¹,

Liu²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, we investigate the uplink transmit power optimization problem in cell-free (CF) extremely largescale multiple-input multiple-output (XL-MIMO) systems. Instead of applying the traditional methods, we propose two signal processing architectures: the centralized training and centralized execution with fuzzy logic as well as the centralized training and decentralized execution with fuzzy logic, respectively, which adopt the amalgamation of multi-agent reinforcement learning (MARL) and fuzzy logic to solve the design problem of power control for the maximization of the system spectral efficiency (SE). Furthermore, the uplink performance of the system adopting maximum ratio (MR) combining and local minimum meansquared error (L-MMSE) combining is evaluated. Our results show that the proposed methods with fuzzy logic outperform the conventional MARL-based method and signal processing methods in terms of computational complexity. Also, the SE performance under MR combining is even better than that of the conventional MARL-based method.

show abstract

Multi-Agent Reinforcement Learning for Distributed Joint Communication and Computing Resource Allocation over Cell-Free Massive MIMO-enabled Mobile Edge Computing Network

Cited by 3 publications

References 34 publications

IoV mobile edge computing task offloading based on MADDPG algorithm

IoV mobile edge computing task offloading based on MADDPG algorithm

A Survey of State-of-the-art on Edge Computing: Theoretical Models, Technologies, Directions, and Development Paths

Uplink Power Control for Extremely Large-Scale MIMO with Multi-Agent Reinforcement Learning and Fuzzy Logic

Contact Info

Product

Resources

About