UAV Trajectory Planning in Wireless Sensor Networks for Energy Consumption Minimization by Deep Reinforcement Learning

Zhu, Botao; Bedeer, Ebrahim; Nguyen, Ha H.; Barton, Robert; Henry, Jérôme

doi:10.1109/tvt.2021.3102161

Cited by 86 publications

(36 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is currently being used as a universal translator between different data types in various areas-from language translation [10] to image recognition [11]. In wireless communication, NN based Deep Learning models are used for channel prediction [12], trajectory planning [13] and resource allocation [14] among others.…”

Section: Our Approachmentioning

confidence: 99%

“…This cyclic process continues unless at the end of a cycle any one of the following two termination conditions gets validated. The first termination flag triggers if the maximum value of the fraction obtained at the current cycle turns out to be less than that obtained in the previous cycle (line 13). It indicates that the cyclic procedure can no longer improve the fraction value.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning based Coverage and Rate Manifold Estimation in Cellular Networks

Mondal¹,

Mankar²,

Das³

et al. 2022

Preprint

View full text Add to dashboard Cite

This article proposes Convolutional Neural Network based Auto Encoder (CNN-AE) to predict location dependent rate and coverage probability of a network from its topology. We train the CNN utilising BS location data of India, Brazil, Germany and the USA and compare its performance with stochastic geometry (SG) based analytical models. In comparison to the best-fitted SGbased model, CNN-AE improves the coverage and rate prediction errors by a margin of as large as 40% and 25% respectively. As an application, we propose a low complexity, provably convergent algorithm that, using trained CNN-AE, can compute locations of new BSs that need to be deployed in a network in order to satisfy pre-defined spatially heterogeneous performance goals.

show abstract

Section: Our Approachmentioning

confidence: 99%

mentioning

confidence: 99%

Deep Learning based Coverage and Rate Manifold Estimation in Cellular Networks

Mondal¹,

Mankar²,

Das³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The power consumed by the UAV to remain afloat in the horizontal moving mode is modeled in [49]. These models have been studied to improve the energy and power efficiency of aerial computing [50]. Moreover, the possibility of aerial computing in terms of energy and power consumption can be realized by integrating aerial computing with emerging technologies in 6G, as discussed in Section III.…”

Section: Network Designmentioning

confidence: 99%

Aerial Computing: A New Computing Paradigm, Applications, and Challenges

Pham,

Ruby,

Fang

et al. 2022

Preprint

View full text Add to dashboard Cite

In existing computing systems, such as edge computing and cloud computing, several emerging applications and practical scenarios are mostly unavailable or only partially implemented. To overcome the limitations that restrict such applications, the development of a comprehensive computing paradigm has garnered attention in both academia and industry. However, a gap exists in the literature owing to the scarce research, and a comprehensive computing paradigm is yet to be systematically designed and reviewed. This study introduces a novel concept, called aerial computing, via the amalgamation of aerial radio access networks and edge computing, which attempts to bridge the gap. Specifically, first, we propose a novel comprehensive computing architecture that is composed of low-altitude computing, high-altitude computing, and satellite computing platforms, along with conventional computing systems. We determine that aerial computing offers several desirable attributes: global computing service, better mobility, higher scalability and availability, and simultaneity. Second, we comprehensively discuss key technologies that facilitate aerial computing, including energy refilling, edge computing, network softwarization, frequency spectrum, multiaccess techniques, artificial intelligence, and big data. In addition, we discuss vertical domain applications (e.g., smart cities, smart vehicles, smart factories, and smart grids) supported by aerial computing. Finally, we highlight several challenges that need to be addressed and their possible solutions.

show abstract

“…Nonetheless, limited battery power of UAV [21] becomes a crucial issue despite the benefits of UAV application in IoT data collection. Some prior works have proposed a trajectory optimization to reduce the energy consumption of UAV, thus expand the flight time [22]- [24]. However, most of the aforementioned works only considered a fixed-altitude scenario in 2D environment with limited action space (e.g.…”

Section: Introductionmentioning

confidence: 99%

Energy-Efficient Multidimensional Trajectory of UAV-Aided IoT Networks With Reinforcement Learning

Silvirianti

Shin

2022

IEEE Internet Things J.

View full text Add to dashboard Cite

This paper proposed a multi-dimensional search space (or directional space) which has larger degree-of-freedom (DOF) to improve energy efficiency of limited-battery-powered UAV in Internet of Things (IoT) data collection scenario. In this paper, the UAV navigates from initial to goal point while collecting data from IoT sensors on the ground. Due to limited battery-power of UAV, optimized trajectory becomes a crucial practical issue. Based on the available directional space, direction of UAV which related to navigation trajectory is optimized using reinforcement learning. The objective of this reinforcement learning is to maximize energy efficiency of UAV as a longterm reward by selecting optimized direction. Moreover, practical energy consumption model and environment are presented in this paper. The simulation results verify the proposed scheme that has larger directional space achieved higher energy efficiency compared to benchmark models.

show abstract

UAV Trajectory Planning in Wireless Sensor Networks for Energy Consumption Minimization by Deep Reinforcement Learning

Cited by 86 publications

References 36 publications

Deep Learning based Coverage and Rate Manifold Estimation in Cellular Networks

Deep Learning based Coverage and Rate Manifold Estimation in Cellular Networks

Aerial Computing: A New Computing Paradigm, Applications, and Challenges

Energy-Efficient Multidimensional Trajectory of UAV-Aided IoT Networks With Reinforcement Learning

Contact Info

Product

Resources

About