Energy-Efficient Scheduling and Optimization for Connected and Autonomous Vehicles

DC Field Value Language
dc.contributor.advisor김재현-
dc.contributor.author정소이-
dc.date.accessioned2022-11-29T02:32:42Z-
dc.date.available2022-11-29T02:32:42Z-
dc.date.issued2021-02-
dc.identifier.other30680-
dc.identifier.urihttps://dspace.ajou.ac.kr/handle/2018.oak/20280-
dc.description학위논문(박사)--아주대학교 일반대학원 :전자공학과,2021. 2-
dc.description.tableofcontents1 Introduction 1 1.1 Background and motivation 1 1.2 Contributions 3 1.3 Overview of dissertation 7 2 Related work 8 2.1 UAV mobile networks 9 2.2 Energy-efficiency in UAV and its related work 10 2.3 Deep learning in UAV mobile networks and its related work 11 3 Passive UAV scheduling and charging system 14 3.1 System model 17 3.2 Joint message-passing and convex optimization for UAV scheduling 20 3.2.1 Design concepts 20 3.2.2 MWIS-based UAV scheduling using message passing algorithm 21 3.2.3 Joint optimization for charging matching and wireless energy transfer 25 3.3 Performance evaluation 32 3.3.1 Simulation setup 32 3.3.2 Evaluation results 36 3.4 Concluding remarks 41 4 Active UAV scheduling and deep learning-based charging system 43 4.1 System model 48 4.2 Orchestrated scheduling and MADRL for multi-UAV charging 50 4.2.1 Design concepts 50 4.2.2 Multi-UAV charging scheduling: A convex optimization formulation 52 4.2.3 Cooperative MADRL-based EMS learning 60 4.3 Performance evaluation 72 4.3.1 Evaluation setup 72 4.3.2 Evaluation results 76 4.4 Concluding remarks 84 5 Self-adaptive learning scheduling to distributed big-data outsourcing system 86 5.1 System model 91 5.1.1 Edge-assisted UAV networks 91 5.1.2 60GHzmmWaveMAA systems 93 5.2 Dynamic resource outsourcing for big-data learning in edgeassisted UAV networks 95 5.2.1 Design concepts 95 5.2.2 Contractor scheduling via max-weight scheduling 96 5.2.3 Lyapunov transmit power allocation and min-max data distribution 98 5.3 Performance evaluation 109 5.3.1 Evaluation setup 109 5.3.2 Evaluation results 110 5.4 Concluding remarks 117 6 Conclusion 119 References 122-
dc.language.isoeng-
dc.publisherThe Graduate School, Ajou University-
dc.rights아주대학교 논문은 저작권에 의해 보호받습니다.-
dc.titleEnergy-Efficient Scheduling and Optimization for Connected and Autonomous Vehicles-
dc.typeThesis-
dc.contributor.affiliation아주대학교 일반대학원-
dc.contributor.alternativeNameSoyi Jung-
dc.contributor.department일반대학원 전자공학과-
dc.date.awarded2021. 2-
dc.description.degreeDoctoral-
dc.identifier.localId1218616-
dc.identifier.uciI804:41038-000000030680-
dc.identifier.urlhttp://dcoll.ajou.ac.kr:9080/dcollection/common/orgView/000000030680-
dc.subject.keywordConnected and Autonomous Vehicles-
dc.subject.keywordConvex optimization-
dc.subject.keywordEnergy-Efficient-
dc.subject.keywordLyapunov optimization-
dc.subject.keywordUnmanned Aerial Vehicles-
dc.description.alternativeAbstractIn this dissertation, energy-efficient scheduling and optimization algorithms are proposed for unmanned aerial vehicle (UAV) mobile networks. The design and implementation of scheduling and optimization are challenging especially for the energy-limited UAV networks. Therefore, this dissertation proposes novel algorithms for solving the following three challenging problems in energy-efficient scheduling. First of all, a multi-UAV charging scheduling algorithm is proposed in terms of joint optimization between scheduling and energy delivery. This algorithm computes message-passing based scheduling by deactivating selected surveillance Closed-Circuit Television (CCTV) cameras located in overlapping areas. After this computation, optimal matching between UAVs and charging towers is performed. Second, an algorithm for joint UAV scheduling and deep learning-based active energy sharing among charging facilities is proposed. The cooperative energy sharing among towers is designed via multi-agent deep reinforcement learning, and thus intelligent sharing can be realized. Lastly, an adaptive learning computation outsourcing algorithm is designed in distributed big-data outsourcing systems. In order to make the outsourcing decision when a single UAV cannot conduct deep learning computation alone, the edges which can compute the learning computation instead of the UAV can be scheduled under the concept of max-weight. After the scheduling, Lyapunov-based transmit power allocation is considered for stabilized time-average UAV energy consumption minimization in order to deliver the learning data to scheduled edges. Based on the proposed three energy-efficient scheduling and learning algorithms, UAV mobile networks can extend their lifetime for scalable, flexible, and robust operations.-
Appears in Collections:
Graduate School of Ajou University > Department of Electronic Engineering > 4. Theses(Ph.D)
Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse