Deep reinforcement learning for RAN optimization and control.

Our work proved the effectiveness of applying deep reinforcement learning to improve network performance in a real RAN network environment. ... Our vendors provide several settings of the eNodeB to optimize the RAN performance, such as media access control scheduler, loading balance, etc. ... Then we exploit recent advances of artificial intelligence and implement a deep reinforcement learning algorithm on the real environment and get satisfactory improvement for the complicated dynamic RAN ...

arXiv:2011.04607v2 fatcat:lplkwvnovvhuxjvba2rjzyjeiy

Multiple Versions

Our work proved the effectiveness of applying deep reinforcement learning to improve network performance in a real RAN network environment. ... Our vendors provide several settings of the eNodeB to optimize the RAN performance, such as media access control scheduler, loading balance, etc. ... Then we exploited recent advances of artificial intelligence and implement a deep reinforcement learning algorithm on the real environment and get satisfactory improvement for the complicated dynamic RAN ...

doi:10.48550/arxiv.2011.04607 fatcat:cw6rgxuxznfxzjnabvip35yzp4

In this paper, we propose a federated deep reinforcement learning algorithm to coordinate multiple independent xAPPs in O-RAN for network slicing. ... Compared with conventional deep reinforcement learning, our proposed algorithm can achieve 11% higher throughput for enhanced mobile broadband (eMBB) slices and 33% lower delay for ultra-reliable low-latency ... Here, we proposed a federated deep reinforcement learning solution to coordinate two xAPPs, power control, and radio resource allocation for network slicing in O-RAN. ...

arXiv:2208.01736v1 fatcat:pl2b6nmyargpnd3phaxpzwxlyu

One important feature introduced by O-RAN is the heavy usage of Machine Learning (ML) techniques, particularly Deep Learning (DL), to foster innovation and ease the deployment of intelligent RAN applications ... In addition, we present two case studies for DL techniques deployment in O-RAN. ... of Service DL Deep Learning RAN Radio Access Network DNN Deep Neural Network RIC RAN Intelligent Controller DQN Deep Q-Network REC Radio Equipment Controller DRL Deep Reinforcement Learning RF Radio Frequency ...

doi:10.1109/ojcoms.2022.3146618 fatcat:3t47unghhza4jlq6yr7fh47f6a

DOAJ

Finally, we identify challenges and open issues to provide a roadmap for researchers in the area of MATL based O-RAN optimization. ... In our view, Multi-Agent Systems (MASs) with MATL can play an essential role in the orchestration of O-RAN controllers, i.e., near-real-time and non-real-time RAN Intelligent Controllers (RIC). ... Sequential multi-agent deep reinforcement learning (SMADRL), Concurrent multiagent deep reinforcement learning (CMADRL) and Team multi-agent deep reinforcement learning (TMADRL) schemes. • SMADRL: In the ...

doi:10.3390/s22145375 pmid:35891055 pmcid:PMC9325199 fatcat:vssoevx23fhnfflevrg7oiyuim

DOAJ

Yvonne-Anne Pignolet, Stefan Schmid, and Gilles Tredan 4756 DeepCC: Multi-Agent Deep Reinforcement Learning Congestion Control for Multi-Path TCP Based on Self-Attention . . . . . . . . ... Mostafa Ibrahim, Umair Sajid Hashmi, Muhammad Nabeel, Ali Imran, and Sabit Ekin 4042 Harnessing UAVs for Fair 5G Bandwidth Allocation in Vehicular Communication via Deep Reinforcement Learning . . . . ...

doi:10.1109/tnsm.2021.3106439 fatcat:ze67mhvuinejfg6olbdsxclpga

In view of this, this study is based on deep reinforcement learning convolutional neural networks, combined with point cloud models, proximal strategy optimization algorithms, and flexible action evaluation ... A seal cutting robot based on deep reinforcement learning has been proposed. ... Section 3 mainly calculates and analyzes the comprehensive utilization of deep reinforcement learning and seal cutting optimization algorithms, and also includes the design and construction of seal cutting ...

doi:10.37965/jait.2024.0453 fatcat:omerypesvzbztjkuccu5sgeyxm

Open Access

Specifically, the decision agents leverage the remold of classical deep reinforcement learning (DRL) algorithm into variational quantum circuits (VQCs) to obtain the optimal cooperative control on slice ... In this intent, we propose a cloud-native federated learning framework based on quantum deep reinforcement learning (QDRL) where distributed decision agents deployed as micro-services at the edge and cloud ... Specifically, the decision agents leverage the remold of classical deep reinforcement learning (DRL) algorithm into variational/parametrized quantum circuits (VQCs or PQCs) to obtain the optimal cooperative ...

arXiv:2212.11755v1 fatcat:kth3nhn245fjdjia5ngk7nwhje

For each RAN slicing level, we model the resource slicing problem as a single-agent Markov decision process and design a deep reinforcement learning algorithm to solve it. ... In addition, the open radio access network (O-RAN) architecture paves the way for flexible sharing of network resources by introducing more programmability into the RAN. ... ACKNOWLEDGMENTS The authors would like to thank the Natural Sciences and Engineering Research Council of Canada, for the financial support of this research. ...

arXiv:2202.06439v1 fatcat:64v7vjwvnfek5k2unkqrxzqem4

Open Access

The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions ... to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. ... To that end, we ran Dropout-DQN and DQN on one of the classic control environments to express the effect of Dropout on Variance and the learned policies quality. ...

arXiv:1910.05983v2 fatcat:ucy245f55bhyhjcewlmd523ise

Multiple Versions

The widely different requirements of 5G emerging use-cases such as Internet of things (IoT), augmented/virtual reality (AR/VR), vehicle-to-everything (V2X)communication, exacerbate the need for orchestration ... Enabled by the network slicing technology, multiple and independent virtual networks can now be instantiated and customized to meet heterogeneous service requirements over 5G network deployments. ... Fig. 1 presents the envisioned framework, wherein multiple deep reinforcement learning (DRL) agents optimally allocate radio resources to each slice, while a federation layer enables a periodical exchange ...

doi:10.5281/zenodo.6482484 fatcat:ibpsnfseh5apfamlnahhmiwqne

Open Access

Since the recent advent of deep reinforcement learning for game play and simulated robotic control, a multitude of new algorithms have flourished. ... Yet these algorithms share a great depth of common deep reinforcement learning machinery. ... Thanks to Steven Kapturowski for clarification of several implementation details of R2D2, and to Josh Achiam and Wilson Yan for help debugging SAC. ...

arXiv:1909.01500v2 fatcat:mamzoq3bcrd3pi3tgzalt4jwoa

Multiple Versions

In this paper, we model the handoff in RAN slicing as a Markov decision process and resort to deep reinforcement learning to pursue long-term performance improvement in terms of user quality of service ... and network throughput. ... Acknowledgements The authors acknowledged the anonymous reviewers and editors for their efforts in constructive and generous feedback. ...

doi:10.1186/s13638-021-01939-x fatcat:fjg4lrf4mbbjbnk2njqhf6unoe

DOAJ

Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name. ... The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, and inclusive pagination. ... ., +, OJVT 2021 448-470 Control engineering computing Deep Reinforcement Learning Based Energy Efficient Multi-UAV Data Collection for IoT Networks. ...

doi:10.1109/ojvt.2022.3151527 fatcat:4i6zsziyc5eajlo3zyldcmuflu

DOAJ

In the article "Resource optimization for delay-tolerant data in blockchain-enabled IoT with edge computing: A deep reinforcement learning approach," Li et al. proposed a joint optimization framework about ... In the article "Joint DNN partition deployment and resource allocation for delay-sensitive deep learning inference in IoT," He et al. studied joint optimization of partition deployment and resource allocation ...

doi:10.1109/jiot.2020.3019948 fatcat:mogalqnhnnaqpbxb7zivzdhvry

Deep reinforcement learning for RAN optimization and control [article]

Preserved Fulltext

Deep reinforcement learning for RAN optimization and control [article]

Preserved Fulltext

Federated Deep Reinforcement Learning for Resource Allocation in O-RAN Slicing [article]

Preserved Fulltext

Deep Learning for B5G Open Radio Access Network: Evolution, Survey, Case Studies, and Challenges

Preserved Fulltext

Multi-Agent Team Learning in Virtualized Open Radio Access Networks (O-RAN)

Preserved Fulltext

Table of contents

Preserved Fulltext

Reinforcement Learning-Based Simulation of Seal Engraving Robot in the Context of Artificial Intelligence

Preserved Fulltext

Towards Quantum-Enabled 6G Slicing [article]

Preserved Fulltext

Communication and Computation O-RAN Resource Slicing for URLLC Services Using Deep Reinforcement Learning [article]

Preserved Fulltext

On the Reduction of Variance and Overestimation of Deep Q-Learning [article]

Preserved Fulltext

A Federated Deep Reinforcement Learning Approach for Distributed Network Slicing Orchestration

Preserved Fulltext

rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch [article]

Preserved Fulltext

Other Versions

Dynamic handoff policy for RAN slicing by exploiting deep reinforcement learning

Preserved Fulltext

2021 Index IEEE Open Journal of Vehicular Technology Vol. 2

Preserved Fulltext

Special Issue on Artificial-Intelligence-Powered Edge Computing for Internet of Things

Preserved Fulltext