Machine Learning for Predictive Deployment of UAVs with Rate Splitting Multiple Access

Lu, Linyan; Hu, Ye; Zhang, Yirun; Jia, Guangyu; Nie, Jiangtian; Shikh-Bahaei, Mohammad

doi:10.1109/gcwkshps50303.2020.9367523

Cited by 13 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of ML in RSMA-assisted network has been investigated to design power control algorithms without any prior information of the CSI and rate performance gain over SDMA-assisted network was achieved [20]. [21] is another instance where integration of RSMA and ML allowed better deployment of UAVs thereby reducing transmit power levels compared to OMA in UAV-assisted networks. For future research, the only caveat to keep in mind is that the integration of RSMA and ML must not be restricted to the PHY layer only, instead the focus should be on cross-layer design such as aiding network orchestration, to truly assist wireless communication for intelligent 6G.…”

Section: Applications and Future Workmentioning

confidence: 99%

Rate-Splitting Multiple Access for 6G -- Part I: Principles, Applications and Future Works

Mishra,

Mao,

Dizdar

et al. 2022

Preprint

View full text Add to dashboard Cite

This letter is the first part of a three-part tutorial focusing on rate-splitting multiple access (RSMA) for 6G. As Part I of the tutorial, the letter presents the basics of RSMA and its applications in light of 6G. To begin with, we first delineate the design principle and basic transmission frameworks of downlink and uplink RSMA. We then illustrate the applications of RSMA for addressing the challenges of various potential enabling technologies and use cases, consequently making it a promising next generation multiple access (NGMA) scheme for future networks such as 6G and beyond. We briefly discuss the challenges of RSMA and conclude the letter. In continuation of Part I, we will focus on the interplay of RSMA with integrated sensing and communication, and reconfigurable intelligent surfaces, respectively in Part II and Part III of this tutorial.

show abstract

Section: Applications and Future Workmentioning

confidence: 99%

Rate-Splitting Multiple Access for 6G -- Part I: Principles, Applications and Future Works

Mishra,

Mao,

Dizdar

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The i-th transition pair of the minibatch, mean squared Bellman error is calculated with target value y i and Q(s i , a i |θ Q ) to update the critic network (line 12) [31]. The parameters of the actor network, i.e., θ µ , are updated via gradient-based optimization (line [13][14]. (iii) After updating the parameters of actor and critic, i.e., θ µ and θ Q , the target parameters θ Q and θ μ are updated (line 15).…”

Section: Algorithm For Learning Cooperationmentioning

confidence: 99%

“…Compared to the conventional optimization approaches, various ML techniques have been applied to improve the performance of UAV-based computing, including an ML-based approach for autonomous trajectory optimization [12] and the optimization of UAV location in a downlink system with a joint K-means and expectation maximization (EM) based on a Gaussian mixture model (GMM) [13], dynamic optimization of the locations of UAVs in a VLC-enabled UAV based network for minimizing the transmit power [14], among others. There are some studies that utilize DRL methods in UAV network systems, including the meta-reinforcement learningbased path-planning for UAVs in dynamic and unknown wireless network environments [15], a Q-learning methodbased dynamic location planning of UAVs in a non-orthogonal multiple access (NOMA) based wireless network [16], and the optimization for UAV optimal energy consumption control considering communication coverage, fairness, and connectivity.…”

Section: Introductionmentioning

confidence: 99%

Cooperative Multi-Agent Deep Reinforcement Learning for Reliable Surveillance via Autonomous Multi-UAV Control

Yun,

Park,

Kim

et al. 2022

Preprint

View full text Add to dashboard Cite

CCTV-based surveillance using unmanned aerial vehicles (UAVs) is considered a key technology for security in smart city environments. This paper creates a case where the UAVs with CCTV-cameras fly over the city area for flexible and reliable surveillance services. UAVs should be deployed to cover a large area while minimize overlapping and shadow areas for a reliable surveillance system. However, the operation of UAVs is subject to high uncertainty, necessitating autonomous recovery systems. This work develops a multi-agent deep reinforcement learning-based management scheme for reliable industry surveillance in smart city applications. The core idea this paper employs is autonomously replenishing the UAV's deficient network requirements with communications. Via intensive simulations, our proposed algorithm outperforms the state-of-the-art algorithms in terms of surveillance coverage, user support capability, and computational costs.

show abstract

“…In this section, we briefly review several recent applications of machine learning and artificial intelligence to UAVs, mainly focusing on energy efficiency. In [12], the authors present a long short-term memory (LSTM) inference algorithm to predict future mobile traffic using back-propagation-based neural network training. They proposed the division of the entire coverage area into clusters using a joint k-means and an EM algorithm of a Gaussian mixture model.…”

Section: Energy-efficient Machine Learning Approaches For Uavsmentioning

confidence: 99%

Energy-Efficient Inference on the Edge Exploiting TinyML Capabilities for UAVs

Raza

Osman

Ferrini

et al. 2021

Drones

View full text Add to dashboard Cite

In recent years, the proliferation of unmanned aerial vehicles (UAVs) has increased dramatically. UAVs can accomplish complex or dangerous tasks in a reliable and cost-effective way but are still limited by power consumption problems, which pose serious constraints on the flight duration and completion of energy-demanding tasks. The possibility of providing UAVs with advanced decision-making capabilities in an energy-effective way would be extremely beneficial. In this paper, we propose a practical solution to this problem that exploits deep learning on the edge. The developed system integrates an OpenMV microcontroller into a DJI Tello Micro Aerial Vehicle (MAV). The microcontroller hosts a set of machine learning-enabled inference tools that cooperate to control the navigation of the drone and complete a given mission objective. The goal of this approach is to leverage the new opportunistic features of TinyML through OpenMV including offline inference, low latency, energy efficiency, and data security. The approach is successfully validated on a practical application consisting of the onboard detection of people wearing protection masks in a crowded environment.

show abstract

Machine Learning for Predictive Deployment of UAVs with Rate Splitting Multiple Access

Cited by 13 publications

References 15 publications

Rate-Splitting Multiple Access for 6G -- Part I: Principles, Applications and Future Works

Rate-Splitting Multiple Access for 6G -- Part I: Principles, Applications and Future Works

Cooperative Multi-Agent Deep Reinforcement Learning for Reliable Surveillance via Autonomous Multi-UAV Control

Energy-Efficient Inference on the Edge Exploiting TinyML Capabilities for UAVs

Contact Info

Product

Resources

About