Multi-agent reinforcement learning for resource allocation in IoT networks with edge computing

Liu, Xiaolan; Yu, Jiadong; Zhang, Feng; Gao, Yue

doi:10.23919/jcc.2020.09.017

Cited by 77 publications

(54 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By counting down the time between the user equipment and the edge computing server on the extreme network, it optimizes the MEC computing download strategy, verifies the effectiveness of the strategy, and determines when to download the user's computing tasks to the MEC server. However, this article did not optimize the computer uninstallation strategy on multiple MEC devices [3].…”

Section: Related Work On Digital Media Application Technology For Mobile Terminals Based On Edge Computing and Virtualmentioning

confidence: 99%

“…e fewer the sparks scattered in the space, the larger the explosion radius, and it has a specific global search capability. e suitability value of each firework is calculated according to the objective optimization function t (TA) in formula (3). e fitness value is used to evaluate the quality of fireworks and can be used to calculate the explosion radius A i and the number of S i explosion sparks for each TA i firework.…”

Section: Edge Computing Optimization Delay Computing Offloading Strategy Based On Its Integration and Communicationmentioning

confidence: 99%

See 1 more Smart Citation

Digital Media Application Technology of Mobile Terminals Based on Edge Computing and Virtual Reality

Jiang

2021

Mobile Information Systems

View full text Add to dashboard Cite

With the maturity of the most advanced technology and virtual reality, the application of digital media technology in various fields has become more and more extensive. Digital media technology has greatly promoted the development of all classes of society. Therefore, how to develop digital media technology applications has become a major issue. This article aims to study the digital media application technology of mobile terminals based on edge computing and virtual reality. In this paper, we use edge computing and virtual reality methods to study the digital media application technology of mobile terminals. We used the SD-CEN architecture and FWA in edge computing to conduct simulation experiments and compared the delay time performance of the FWA with that of the PSO-CO algorithm, WRR algorithm, and Pick-KX algorithm. The results of this paper show that it can effectively reduce the response delay of real-time face recognition services and improve user experience. Compared with the traditional cloud computing architecture and a single MEC device, the SD-CEN network architecture based on FWA strategy has more advantages. The latency of the FWA is increased by 61%, 46%, and 17%, respectively, compared with that of the WRR, Pick-KX, and PSO-CO algorithms.

show abstract

Section: Related Work On Digital Media Application Technology For Mobile Terminals Based On Edge Computing and Virtualmentioning

confidence: 99%

Section: Edge Computing Optimization Delay Computing Offloading Strategy Based On Its Integration and Communicationmentioning

confidence: 99%

Digital Media Application Technology of Mobile Terminals Based on Edge Computing and Virtual Reality

Jiang

2021

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Different from some papers on general resource management in edge computing [13][14][15], it is worth noting that this paper applies edge intelligence to distributed grids, but does not consider power flow calculations between microgrids. Along with power consumers' increasing demand for power services, the microgrid framework is increasingly seen as a hot issue in current smart grids.…”

Section: Related Workmentioning

confidence: 99%

Power flow adjustment for smart microgrid based on edge computing and multi-agent deep reinforcement learning

Wang

Cao

et al. 2021

J Cloud Comp

View full text Add to dashboard Cite

In current power grids, a massive amount of power equipment raises various emerging requirements, e.g., data perception, information transmission, and real-time control. The existing cloud computing paradigm is stubborn to address issues and challenges such as rapid response and local autonomy. Microgrids contain diverse and adjustable power components, making the power system complex and difficult to optimize. The existing traditional adjusting methods are manual and centralized, which requires many human resources with expert experience. The adjustment method based on edge intelligence can effectively leverage ubiquitous computing capacities to provide distributed intelligent solutions with lots of research issues to be reckoned with. To address this challenge, we consider a power control framework combining edge computing and reinforcement learning, which makes full use of edge nodes to sense network state and control power equipment to achieve the goal of fast response and local autonomy. Additionally, we focus on the non-convergence problem of power flow calculation, and combine deep reinforcement learning and multi-agent methods to realize intelligent decisions, with designing the model such as state, action, and reward. Our method improves the efficiency and scalability compared with baseline methods. The simulation results demonstrate the effectiveness of our method with intelligent adjusting and stable operation under various conditions.

show abstract

“…Some researchers have paid attention to multi-agent reinforcement learning, looking for a convenient MDP model. Liu et al [23] regarded task offloading as a stochastic game, using independent learning agents to learn offloading strategy for each edge server; Wang et al [24] leveraged multi-agent deep Deterministic Policy Gradient to train UAVs in a MEC architecture; Munir et al [25] considered a microgrid-enabled MEC network, using asynchronous advantage actor-critic algorithm to train agents.…”

Section: Task Offloading In Mecmentioning

confidence: 99%

Decentralized Offloading Strategies Based on Reinforcement Learning for Multi-Access Edge Computing

Shi

et al. 2021

Information

View full text Add to dashboard Cite

Using reinforcement learning technologies to learn offloading strategies for multi-access edge computing systems has been developed by researchers. However, large-scale systems are unsuitable for reinforcement learning, due to their huge state spaces and offloading behaviors. For this reason, this work introduces the centralized training and decentralized execution mechanism, designing a decentralized reinforcement learning model for multi-access edge computing systems. Considering a cloud server and several edge servers, we separate the training and execution in the reinforcement learning model. The execution happens in edge devices of the system, and edge servers need no communication. Conversely, the training process occurs at the cloud device, which causes a lower transmission latency. The developed method uses a deep deterministic policy gradient algorithm to optimize offloading strategies. The simulated experiment shows that our method can learn the offloading strategy for each edge device efficiently.

show abstract

Multi-agent reinforcement learning for resource allocation in IoT networks with edge computing

Cited by 77 publications

References 0 publications

Digital Media Application Technology of Mobile Terminals Based on Edge Computing and Virtual Reality

Digital Media Application Technology of Mobile Terminals Based on Edge Computing and Virtual Reality

Power flow adjustment for smart microgrid based on edge computing and multi-agent deep reinforcement learning

Decentralized Offloading Strategies Based on Reinforcement Learning for Multi-Access Edge Computing

Contact Info

Product

Resources

About