Distributed deep reinforcement learning architecture for task offloading in autonomous IoT systems

Boni, Abdel Kader Chabi Sika; Hablatou, Youssef; Hassan, Hassan; Drira, Khalil

doi:10.1145/3567445.3567454

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Boni et al [26] propose a distributed reinforcement learning architecture for task offloading in autonomous IoT systems. In their architecture, IoT devices correspond to actors, and a cloud node corresponds to a learner; in addition, a smart access point is installed to aggregate information from the IoT devices, while a replay memory is included in the cloud node.…”

Section: Applications Of Distributed Reinforcement Learning For Edge-...mentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Distributed Reinforcement Learning Architecture for Long-Haul Communication Between Actors and Learner

Morishima,

Matsutani

2024

IEEE Access

View full text Add to dashboard Cite

A computing cluster that interconnects multiple compute nodes is used to accelerate distributed reinforcement learning that uses DQN (Deep Q-Network). In distributed reinforcement learning, actor nodes acquire experiences by interacting with a given environment and a learner node optimizes the DQN model. When distributed reinforcement learning is used in practical applications such as robotics, we can assume that actor nodes are located in edge side while the learner node is located in cloud side. In this case, the long-haul communication between them imposes significant communication overheads. However, most prior works simply assume that actors and learner are located closely, and do not take the overheads into account. In this paper, we focus on the practical environment where the actors and learner are located remotely, and they interact via a buffer node that collects information from multiple actor nodes. We implement a prototype system in which the buffer and learner nodes are connected via a 25GbE (Gigabit Ethernet) switch and a 10km optical fiber cable. Although a replay memory functionality is closely associated with the learner side, in this paper we propose to combine the replay memory into the buffer node. In our experiments using the prototype system, the proposed approach is compared with an existing approach in terms of the training efficiency (i.e., training loss) and the transfer efficiency over the long-haul communication (i.e., average priority of transferred experiences). As a result, the training loss of the proposed approach is reduced to 26% of the existing approach, and the average priority is 3.92 times higher than the existing approach after the training loss is converged. These results demonstrate that the proposed approach can improve the training/communication efficiency compared with the existing approach in a practical system that imposes long-haul communication between the actors and learner.

show abstract

Section: Applications Of Distributed Reinforcement Learning For Edge-...mentioning

confidence: 99%

“…The second situation may occur in applications where experiences are collected from larger systems (e.g., multiple LANs) as in [26]- [30]. The proposed approach can address such a situation by adding more buffer nodes each of which has its own experience replay memory.…”

Section: B Effectiveness and Scalability Of Proposed Approach For Rea...mentioning

confidence: 99%

An Efficient Distributed Reinforcement Learning Architecture for Long-Haul Communication Between Actors and Learner

Morishima,

Matsutani

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

Mayfly Taylor Optimization-Based Graph Attention Network for Task Scheduling in Edge Computing

Chen,

Liu

2023

J Grid Computing

View full text Add to dashboard Cite

Digital health in smart cities: Rethinking the remote health monitoring architecture on combining edge, fog, and cloud

et al. 2023

View full text Add to dashboard Cite

Distributed deep reinforcement learning architecture for task offloading in autonomous IoT systems

Cited by 4 publications

References 18 publications

An Efficient Distributed Reinforcement Learning Architecture for Long-Haul Communication Between Actors and Learner

An Efficient Distributed Reinforcement Learning Architecture for Long-Haul Communication Between Actors and Learner

Mayfly Taylor Optimization-Based Graph Attention Network for Task Scheduling in Edge Computing

Digital health in smart cities: Rethinking the remote health monitoring architecture on combining edge, fog, and cloud

Contact Info

Product

Resources

About