Workshops

Session AidTSP-TS1: AidTSP Technical Session I Session AidTSP-TS2: AidTSP Technical Session II Session AidTSP-TS3: AidTSP Technical Session III Session AidTSP-TS4: AidTSP Technical Session IV
Session AoI-Open: Opening Session Session AoI-Key: Keynote Session AoI-SCH: Scheduling and Optimization for AoI Session AoI-CBrk: Virtual Coffee Break Session AoI-BEY: Beyond AoI Metrics
Session CNERT-O: Opening Session Session CNERT-K: Keynote Session CNERT-P: Panel Session CNERT-S1: Session 1, Experimentation Enabling Capabilities Session CNERT-S2: Session 2, Services and network design Session CNERT-S3: Session 3, Wireless Session CNERT-D: Demo Session
Session DeepWireless-OS: Opening Session Session DeepWireless-KS1: Keynote Session 1 Session DeepWireless-TS1: Technical Session 1 - Deep Learning for Wireless Security Session DeepWireless-TS2: Technical Session 2 - Deep Learning for Wireless Applications Session DeepWireless-KS2: Keynote Session 2 Session DeepWireless-TS3: Technical Session 3 - Deep Learning for 5G Communications Session DeepWireless-CS: Closing Session
Session DroneCom-TS1: Technical Session I Session DroneCom-KS1: Keynote Session I Session DroneCom-TS2: Technical Session II Session DroneCom-TS3: Technical Session III Session DroneCom-KS2: Keynote Session II Session DroneCom-TS4: Technical Session IV
Session FOGML-S1: Opening Remarks Session FOGML-S2: Federated Learning Session FOGML-S3: Distributed Learning and Edge Computing
Session GI-00: Session#0 - Opening Session with Invited Keynote Session GI-01: Session#1 - Applying Machine Learning to Next Generation Internet Session GI-02: Session#2 - Performance Optimization of Next Generation Internet
Session ICCN-KS1: Security in Wireless Body Area Networks Session ICCN-B1: Virtual Coffee Break Session ICCN-S1: Cloud and Edge Computing Session ICCN-S2: Cloud and Edge Security Session ICCN-B2: Virtual Lunch Break Session ICCN-S3: Cloud and Edge Computing Session ICCN-S4: Cloud and Edge Computing
Session MobiSec-S1: AI & Security (I) Session MobiSec-K: Keynote: AI for Cybersecurity and Security of AI Session MobiSec-S2: AI & Security (II) Session MobiSec-S3: Mobile & Edge Security Session MobiSec-S4: Communication Security
Session NG-OPERA-OS: Opening Session Session NG-OPERA-KS: Keynote Session Session NG-OPERA-PS: Panel Session Session NG-OPERA-Break-1: Break Session NG-OPERA-TS1: Technical Session 1: Machine Learning and Resource Optimization for 6G RANs Session NG-OPERA-Lunch: Lunch Session NG-OPERA-TS2: Technical Session 2: System-level Solutions for Open RANs Session NG-OPERA-Break-2: Break Session NG-OPERA-TS3: Technical Session 3: Non-terrestrial Integration and Posters Session NG-OPERA-ACS: Awards and Closing
Session NetSciQCom-S1: Keynote Talk Session NetSciQCom-S2: Contributed Talks
Session PerAI-6G-Opening: Opening Session Session PerAI-6G-Keynote-1: Keynote Session 1 Session PerAI-6G-Keynote-2: Keynote Session 2 Session PerAI-6G-Session-1: Session 1: AI applications in 6G Session PerAI-6G-Session-2: Session 2: Distributed Learning in 6G Session PerAI-6G-Session-3: Session 3: Digital Twin in 6G Session PerAI-6G-Session-4: Session 4: Resource Management in 6G Session PerAI-6G-Closing: Closing Session
Session WISARN-O: Opening Session WISARN-K1: Keynote Session WISARN-CB: Virtual Coffee Break Session WISARN-S1: Technical Session
Session Wireless-Sec-I: Wireless Security I Session Wireless-Sec-II: Wireless Security II

Session DroneCom-TS1

Technical Session I

Conference
8:00 AM — 9:30 AM EDT
Local
May 20 Sat, 8:00 AM — 9:30 AM EDT

Drone-Assisted Behavior Recognition via Key Frame Extraction for Efficient 5G Communication

Hui Li and Tongao Ge (Qingdao University of Science and Technology Qingdao, China); Ruidi Ma (State Oceanic Administration of China Qingdao, China); Ying Guo and Guowei Zhao (Qingdao University of Science and Technology Qingdao, China); Jiaming Pei (University of Sydney Australia Sydney, Australia); Lukun Wang (Shandong University of Science and Technology Qingdao, China); Lingwei Xu (Qingdao University of Science and Technology Qingdao, China)

0
Video behavior recognition based on drone + 5G technology has important research value in public security, intelligent transportation, telemetry and remote sensing, etc. However, the high redundancy of videos taken by drones leads to a large amount of calculation for its auxiliary behavior recognition algorithm, the current drone platform has limited computational power and cannot process data well. Therefore, we propose drone-assisted behavior recognition via key frame extraction for efficient 5G communication (AFVS). Firstly, a video summary algorithm of full convolutional network and attention mechanism, AFCN, is proposed to quickly extract important information from drone video. Secondly, SV-Stream with dual stream architecture is designed to process both video stream and skeleton stream. In the video stream, the fast and slow path network is designed to extract the deep feature information affecting the target behavior and improve the accuracy of behavior recognition. The experimental results show that the proposed algorithm solves the defects of drone behavior recognition algorithm in natural scenes well, and improves the performance of behavior recognition.
Speaker Ying Guo（Qingdao University of Science and Technology）

Ms Guo received her bachelor's degree in Information Science and Technology from Qingdao University of Science and Technology. She is now studying for a master's degree in Electronic Information at the College of Information Science and Technology, Qingdao University of Science and Technology.

Joint User Association, Power Allocation and ABS Deployment Optimization in Air-ground Cooperative Networks

Huan Li and Daosen Zhai (Northwestern Polytechnical University, Xiían, Shaanxi, 710072, China and National Mobile Communications Research Laboratory, Southeast University, Nanjing, Jiangsu, 211189, China); Ruonan Zhang (Northwestern Polytechnical University, Xiían, Shaanxi, 710072, China); Haotong Cao (The Hong Kong Polytechnic University, Hong Kong SAR, China); Wenxin Tang and Zhangjie Cai (Northwestern Polytechnical University, Xiían, Shaanxi, 710072, China)

0
In this paper, we propose an unmanned aerial vehicle (UAV)-assisted air-ground cooperative network scheme to improve system throughput and enhance user fairness by deploying the UAV as aerial base station (ABS) to provide wireless services to cell-edge users. To take full advantage of this scheme, we propose a joint user association, power allocation, and ABS deployment optimization problem to achieve the minimum potential delay fairness. To solve the complex optimization problem, we design an alternating iterative scheme based on branch-and bound (B&B) algorithm and particle swarm optimization (PSO), and use the k-mean algorithm to obtain the initial solution. The simulation results demonstrate that the proposed algorithm further improves the network performance compared with other schemes.
Speaker Huan Li (Northwestern Polytechnical University)

Huan Li received the B.E. degree in telecommunication engineering from the School of Northwestern Polytechnical University, Xi’an, China, in July 2020, where he is currently pursuing the Ph.D in communication and information systems. His research interests include unmanned aerial vehicle communications and resource allocation in wireless communications.(Based on document published on 12 November 2020).

Time-Constrained UAV-aided Data Collection for IoT Networks with Energy Harvesting

Pengfei Du, Fan Xie, Shijia Chen (Engineering Research Center of Intelligent Air-ground Integrated Vehicle and Traffic Control Ministry of Education, Xihua University, Chengdu, 610039, China); Xuejun Zhang (School of Electronic Information and Engineering, Beijing University of Aeronautics and Astronautics, Beijing, 100191, China)

0
This work investigates the time-constrained un manned aerial vehicle (UAV) aided data collection problem for Internet of Thing (IoT) networks, where multiple IoT devices (IoTDs) harvest the solar energy and send their sensed data to the UAV in the uplink by applying the time division multiple access (TDMA) method. Specifically, we propose to maximize the total number of served IoTDs in a finite data gathering period via optimizing the trajectory of UAV, the time allocation and trans mitting power of IoTDs under the UAVís maximum flight speed constraint, and the energy harvesting neutralization constraint of every IoTD. To tackle this non-linear integer programming, we first convert it into an equivalent tractable problem by adding the deductive penalty into the target function, and develop the time-constrained UAV-assisted data collection algorithm (TCDCA) to achieve a sub-optimal solution by exploiting the alternating optimization, successive convex approximation (SCA) and quadratic approximation methods. Subsequently, abundant simulations results are provided to confirm that the TCDCA is able to notably enhance the total number of served IoTDs compared to the conventional scheme with constant trajectory or constant time allocation.
Speaker Fan Xie

He is pursuing a master's degree in Engineering Research Center of Intelligent Air-ground Integrated Vehicle and Traffic Control Ministry of Education, Xihua University.

Spectral Efficiency of Multi-Pair mMIMO-NOMA UAV-Relaying with Low-Resolution ADCs/DACs

Xingwang Li, Mingyu Zhang, Hui Chen (School of Physics and Electronic Information Engineering, Henan Polytechnic University, Jiaozuo, China); Dinh-Thuan Do (School of Engineering, University of Mount Union, Alliance OH 44601, USA) , Shahid Mumtaz (Instituto de Telecomunicacoes, Aveiro, Portugal), and Arumugam Nallanathan (School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K)

0
In this paper, we propose an unmanned aerial vehicle (UAV)-enabled massive multiple-input multiple-out (MIMO) non-orthogonal multiple access (NOMA) full-duplex (FD) two way relay (TWR) system with low resolution analog-to-digital converters/digital-to-analog converters (ADCs/DACs) architecture. By adopting the additive quantization noise model (AQNM), the spectral efficiency (SE) with imperfect channel state information (CSI), imperfect successive interference cancellation (SIC) and low-precision ADCs/DACs is studied. To evaluate the system SE performance, some asymptotic analyses are presented. Simulation results verify the accuracy of theoretical derivations and illustrate that with low-resolution ADC/DAC architecture, the SE of proposed massive MIMO-NOMA FD TWR system outperforms the corresponding OMA and/or HD system. In addition, the SE loss due to interference and noise can be compensated by utilizing massive MIMO. We also confirm that the impact of ADCs/DACs can be effectively mitigated by adjusting UAV altitude and employing more antennas at the UAV.
Speaker Mingyu Zhang (Henan Polytechnic University)


Dynamic Construction and Adaptation of 3D Virtual Network Topology for UAV-Assisted Data Collection

Chen Qiu, Xianbin Wang, Weiming Shen (Department of Electrical and Computer Engineering, Western University, London, Canada) and Richard Lee (General Dynamics Land Systems, London, Canada)

0
Unmanned aerial vehicles (UAV) assisted data col lection from on ground devices and sensors is becoming more useful in many mission-critical applications. However, meeting the data collection requirements under dynamic channel conditions between the UAV and on ground devices relies on frequent information exchanges, which brings great challenges to the dynamic operation of the integrated UAV network due to its inherent complexity. To rapidly obtain a holistic view in assisting the UAV network operation, we first propose a three dimensional (3D) virtual network topology which helps the UAV to make faster decisions by analyzing refined virtual indicators instead of measuring and processing related physical factors frequently in real time. To improve the efficiency of UAV data collection, dynamic adaptation of the 3D virtual network topology is achieved by a deep deterministic policy gradient (DDPG) based algorithm, where the UAV flying speed and direction, as well as the determination of the target group of on ground devices are optimized under the UAV energy constraint. Simulation results demonstrate that the proposed DDPG-based dynamic adaptation of the 3D virtual network topology can effectively improve the data collection efficiency compared with the benchmark solutions.
Speaker Chen Qiu(Western University)


Session Chair

Xianbin Wang (Western University)

Session DroneCom-KS1

Keynote Session I

Conference
9:30 AM — 10:00 AM EDT
Local
May 20 Sat, 9:30 AM — 10:00 AM EDT

Smart Drones with Pervasive AI

Mohsen Guizani (Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi)

0
TBA
Speaker
Speaker biography is not available.
Session Chair

Sahil Garg (Ultra Communications)

Session DroneCom-TS2

Technical Session II

Conference
10:30 AM — 12:00 PM EDT
Local
May 20 Sat, 10:30 AM — 12:00 PM EDT

Distributionally Robust Chance-Constrained Optimization for Hierarchical UAV-based MEC

Can Cui, Ziye Jia, Chao Dong (The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space, Ministry of Industry and Information Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, 210016, China); Zhuang Ling (College of Communication Engineering, Jilin University, Changchun, Jilin, 130012, China), Jiahao You and Qihui Wu (The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space, Ministry of Industry and Information Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, 210016, China)

0
Multi-access edge computing (MEC) is regarded as a promising technology in the sixth-generation communication. However, the antenna gain is always affected by the environment when unmanned aerial vehicles (UAVs) are served as MEC platforms, resulting in unexpected channel errors. In order to deal with the problem and reduce the power consumption in the UAV-based MEC, we jointly optimize the access scheme and power allocation in the hierarchical UAV-based MEC. Specifically, UAVs are deployed in the lower layer to collect data from ground users. Moreover, a UAV with powerful computation ability is deployed in the upper layer to assist with computing. The goal is to guarantee the quality of service and minimize the total power consumption. We consider the errors caused by various perturbations in realistic circumstances and formulate a distributionally robust chance-constrained optimization problem with an uncertainty set. The problem with chance constraints is intractable. To tackle this issue, we utilize the conditional value at-risk method to reformulate the problem into a semidefinite programming form. Then, a joint algorithm for access scheme and power allocation is designed. Finally, we conduct simulations to demonstrate the efficiency of the proposed algorithm
Speaker Can Cui (NUAA)

She is now studying for her bachelor's degree in College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, majoring in information engineering.

Cloud-Assisted Security Framework for Drone-Enabled Offshore Communications

Anusha Vangala, Raj Maheshwari, and Ashok Kumar Das (Center for Security, Theory and Algorithmic Research, International Institute of Information Technology, Hyderabad 500 032, India); Shantanu Pal (Deakin University, Melbourne Burwood Campus, Melbourne 3125, Australia)

0
Maritime transport industry is a targeted sector for cyber security attacks as due to the inherent risks of transferring sensitive information for its smooth functioning. Digitization of maritime transport systems has led them vulnerable to various cybersecurity attacks. Vulnerable data, such as crew or passenger personal information, vessel location, route, schedule and other information can be obtained by the attackers and misused. To counter this, a novel lightweight authentication protocol has been put forward with the help of the drone technology using the 5th generation mobile network (5G) communication. The proposed scheme is analyzed to show its robustness against various security attacks, while consuming low communication and computation costs and achieving security and functionality requirements of anonymity and untraceability properties. A detailed simulation study using the network simulator (NS3) shows its impact on various network performance parameters.
Speaker Anusha Vangala (IIIT-Hyderabad)

Anusha Vangala is a Ph.D. research scholar in computer science and engineering with the Center for Security, Theory and Algorithmic Research, International Institute of Information Technology, Hyderabad, India. Prior to joining the Ph.D. program with IIIT Hyderabad, she had nearly five years of experience as an Assistant Professor of Computer Science and Engineering at various renowned institutes across India. Her research interests include cryptographic security in cloud computing, wireless sensor networks, the Internet of Things, and blockchain technology. She has authored 19 papers related to cryptographic security for authentication and encryption in wireless sensor networks, IoT, and smart agriculture including blockchain technology.

Deep Reinforcement Learning Based Energy Consumption Minimization for Intelligent Reflecting Surfaces Assisted D2D Users Underlaying UAV Network

Vineet Vishnoi, Prakhar Consul, Ishan Budhiraja and Suneet Gupta (School of Computer Science Engineering and Technology, Bennett University, Greater Noida (U.P.), India); and Neeraj Kumar (Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala, Punjab, India)

0
Device-to-device communication (D2D-C) is a leading-edge technique in 5G and forthcoming 6G networks due to its benefits for enhanced spectrum efficiency and energy efficiency (EE). Despite these potential advantages, co-channel interference, cross-channel interference, and massive connectivity are the major issues in D2D-C. In this study, we explore the uplink RIS-assisted communication system in the presence of deviceñtoñdevice pairs (D2DPs). Reconfigurable intelligent surface (RIS) is introduced into wireless communication networks with the assistance of an unmanned aerial vehicle (UAV) in order to solve the issues of co-channel and cross-channel interference. In order to estimate the UAVís trajectory and RISís phase shift while ensuring that every userís data requirement is met, a centralized declining deep-Q network (C-DDQN) method is proposed. In the C-DDQN method, a central controller acts as an agent. The UAVís trajectory and the RISís phase shift are controlled by a central controller. Numerical outcomes showed that the suggested scheme overcomes state-of-the-art techniques in terms of results.
Speaker Prakhar Consul

Prakhar Consul is currently working as a Ph.D. research scholar in Bennett University, Greater Noida (India). His research interest includes, edge computing, machine learning and device-to-device communication.

A Novel Multi-Layer Framework for BVLoS Drone Operation: A Preliminary Study

Francesco Betti Sorbelli (Department of Computer Science and Mathematics, University of Perugia, Italy); Punyasha Chatterjee (School of Mobile Computing & Communication, Jadavpur University), Federico Coro`( Department of Computer Science and Mathematics, University of Perugia, Italy); and Lorenzo Palazzetti (Department of Computer Science and Mathematics, University of Florence, Italy), and Cristina M. Pinotti (Department of Computer Science and Mathematics, University of Perugia, Italy)

0
Drones have become increasingly popular in a va riety of fields, including agriculture, emergency response, and package delivery. However, most drone operations are currently limited to within Visual Line of Sight (VLoS) due to safety concerns. Flying drones Beyond Visual Line of Sight (BVLoS) presents new challenges and opportunities, but also requires new technologies and regulatory frameworks, not yet implemented, to ensure that the drone is constantly under the control of a remote operator. In this preliminary study, we assume to remotely control the drone using the available ground cellular network infrastructure. We propose to plan BVLoS drone operations using a novel multi-layer framework that includes many layers of constraints that closely resemble real-world scenarios and challenges. These layers include information such as the potential ground risk in the event of a drone failure, the available ground cellular network infrastructure, and the presence of ground obstacles. From the multi-layer framework, a graph is constructed whose edges are weighted with a dependability score that takes into account the information of the multi-layer framework. Then, the planning of BVLoS drone missions is equivalent to solving the Maximum Path Dependability Problem on the constructed graph, which turns out to be solvable by applying Dijkstraís algorithm.
Speaker Francesco Betti Sorbelli (University of Perugia)

I received the Bachelor and Master degrees cum laude in Computer Science from the University of Perugia, Italy, in 2007 and 2010, respectively, and my Ph.D. in Computer Science from the University of Florence, Italy, in 2018.

From November 2018 to October 2019, I was a Post-doctoral researcher at the Department of Computer Science, University of Perugia, under the supervision of Cristina M. Pinotti.

From January 2020 to January 2021, I was a Post-doctoral researcher at the Department of Computer Science, Missouri University of Science and Technology, Rolla, Missouri, USA, under the supervision of Sajal K. Das.

From April 2021 to October 2022, I was a Post-doctoral researcher at the University of Perugia, under the supervision of Cristina M. Pinotti.

From October 2022, I am a tenure-track Assistant Professor at the University of Perugia.

My research interests include algorithms design, combinatorial optimization, unmanned vehicles.

On the Secrecy Performance of RIS-enhanced Aerial Communication under Imperfect CSI

Khawaja Muhammad Hamza, Sarah Basharat and Syed Ali Hassan (School of Electrical Engineering and Computer Science (SEECS), National University of Sciences & Technology (NUST), Islamabad, Pakistan); Haejoon Jung (Electronics and Information Convergence Engineering, Kyung Hee University, Yongin, South Korea)

0
In this paper, we consider the reconfigurable intelligent surface (RIS) enhanced aerial communication system, where an unmanned aerial vehicle (UAV) intends to deliver confidential information to the legitimate user in the presence of an eavesdropper with the aid of an RIS. For accurate performance analysis, we consider the practical constraints of imperfect channel state information (CSI) and discrete phase shifts for the RIS enhanced system. Furthermore, in order to compensate for the secrecy loss due to the practical constraints, we formulate a secrecy rate maximization problem under the target secrecy rate constraint to optimize the number of RIS elements. Our extensive simulation results demonstrate the impact of various factors, namely the channel estimation error, RIS phase shift design, number of RIS elements, and transmit power, on the secrecy performance of the considered system. Moreover, the simulation results reveal that the secrecy performance degrades to a great extent in the case of imperfect channel estimation of the RIS to legitimate userís link
Speaker Khawaja Muhammad Hamza (National University of Science and Technology)


Session Chair

Syed Ali Hassan (National University of Sciences and Technology)

Session DroneCom-TS3

Technical Session III

Conference
1:30 PM — 3:00 PM EDT
Local
May 20 Sat, 1:30 PM — 3:00 PM EDT

Blockchain and DQN Enabled Co-Evolutionary Routing Scheme in UAV Networks

Pengcheng Zhao, Yuxin Lu, Yunkai Wei, and Supeng Leng (Yangtze Delta Region Institute (Quzhou), and School of Information and Communication Engineering, University of Electronic Science and Technology of China, P. R. China)

0
In unmanned aerial vehicle (UAV) networks, the route efficiency is crucial for effective cooperation among the UAVs. However, due to the highly dynamic topology and environment of UAV networks, current routing schemes usually suffer from performance degradation. To address this issue, in this paper we propose a blockchain and deep Q-network (DQN) enabled co-evolutionary routing (BDCoER) scheme for UAV networks. BDCoER includes two phases in real-time routing optimization, namely self-evolution phase and co-evolution phase. In the first phase, each UAV trains its own DQN model to make optimized routing decision adaptive to dynamic network environment. Then, based on blockchain, all UAVs cooperatively select the best evolved DQN model and integrate it with their own models, which realizes route co-evolution of the whole network in the second phase. Simulations are conducted to evaluate the performance of BDCoER. The simulation results show that BDCoER considerably outperforms the benchmark schemes in terms of both the end-to-end delay and the packet delivery ratio.
Speaker Pengcheng Zhao (University of Electronic Science and Technology of China)

Pengcheng Zhao received B.Eng. degree in communication engineering from University of Electronic Science and Technology of China, Chengdu, China, in 2022. He is currently working toward the M.Eng. degree in network engineering at the School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China.

His research interests include routing protocols of mobile ad hoc networks and artificial intelligence.

Intelligent Onion Routing-based Electronic Health Record Sharing Framework for Healthcare 4.0

Nilesh Kumar Jadav, Rajesh Gupta, Riya Kakkar, Sudeep Tanwar (Nirma University, Ahmedabad, 382481, India)

0
Electronic Health Records (EHRs) seem to be an efficient data storage platform for storing patientís sensitive medical data in healthcare 4.0. But, EHRs deployed on the cloud or web that can be easily exploited by malicious attackers, which raises the need for a secure data sharing framework in healthcare 4.0. Thus, this paper proposes a secure and protected unmanned aerial vehicle (UAV)-assisted EHR framework for healthcare 4.0 by adopting the onion routing (OR) network and Artificial Intelligence (AI)-based technique. The incorporated OR network secures the patientís confidential data against various security and anonymity attacks which is being stored in the EHR with the help of UAVs. Moreover, we have combined OR network with an AI-based technique using various machine learning models to perform the classification on Ehrís sensitive data as malicious and non-malicious. Further, the OR network is simulated inside the shadow simulator where different onion nodes are designed to relay the patientís medical data from the sender to the intended receiver, i.e., EHR. Finally, the performance evaluation of an AI and OR-based data sharing framework is evaluated in terms of accuracy, precision, recall, and training time where Boosted Tree (BT) surpasses other machine learning (ML) models with the improved accuracy of 95.6% and OR network maintains the anonymity of the data communication in healthcare 4.0. Moreover, the OR network has lower computational complexity (processing time = 0.002742 s) due to the adoption of ML models.
Speaker Nilesh Kumar Jadav (Nirma University)

Nilesh Kumar Jadav ([email protected]) is a full-Time Ph.D. research Scholar in the Computer science and Engineering Department at Nirma University, Ahmedabad, India, supervised by Sudeep Tanwar. His research interest includes artificial intelligence in IoT applications and network security.

DAAPEO: Detect and avoid path planning for UAV-assisted 5G enabled energy-optimized IoT

Sandeep Verma and Aneek Adhya (G S Sanyal School of Telecommunications, IIT Kharagpur-721302, India)

0
Unmanned Aerial Vehicles (UAVs) have been making an indelible mark on the automation industry by meeting the stringent standards of Fifth Generation (5G) connectivity for seamless data dissemination from Internet of Things (IoT). However, the limited battery resources of IoT Sensor Devices (ISD), collision free flight operation of swarm of UAVs i.e., multiple UAVs flying at the same time, are challenging concerns which need to be given attention. In this work, the proposed work addresses the aforementioned issues by proposing an energy-optimized data dissemination strategy for the IoT and a pre-determined path planning strategy for collision-free UAV flight operation, the proposed work is referred as DAAPEO. The boosted sooty tern optimization is used for selecting the Cluster-Head (CH) in IoT being deployed with a large number of ISDs. Following the selection of the CH, two UAVs are programmed to hover in a pre-determined path, collecting data from the corresponding CHs in their immediate vicinity. The proposed idea is decentralized when it comes to choosing a CH and centralized when it comes to UAVs path planning. For collision avoidance with the UAV or other obstacles, a Light Detection and Ranging (LiDAR) sensor is used for the former, and deterministic path planning is done for the latter. Simulation results showcase the predominance of proposed work (i.e., DAAPEO) over the competitive methods, as it essentially improves the energy efficiency of 5G IoT and also helps in Detect and Avoid (DAA) path planning for avoiding the collision of launched UAVs within themselves or with other objects
Speaker Sandeep Verma (Indian Institute of Technology Kharagpur)

I am currently working as a research associate at IIT Kharagpur, West Bengal, India. I received my PhD from the Dr. BR Ambedkar National Institute of Technology, Jalandhar, in the year 2020 in the area of wireless sensor networks. I have more than 1000 citations to my research work with an h-index of 18. I am a senior member of IEEE and also work as an editor for the IET Wireless Sensor System Journal.

Lyapunov Meets Thompson: Learning-Based Energy-Efficient UAV Communication with Queuing Stability Constraints

Naresh Babu Kakarla and V. Mahendran (Indian Institute of Technology Tirupati, AP, India)

0
Unmanned Aerial Vehicles UAVs help in extending terrestrial networks (such as cellular connectivity) to remote and difficult-to-reach mountainous terrains. UAV based communications are limited by energy and buffer constraints, due to their light-weight design with small vehicle payload capacity requirement. While state-of-the-art addresses such constraints with idealistic assumptions such as known network conditions, this work for the first time proposes a practical learning based energy-efficient UAV communication framework that meets queuing rate stability constraints, while learning the network conditions on-the-fly. To solve the aforementioned problem, a novel integration of Lyapunov stability with Thompson sampling based Multi Armed Bandit (MAB) learning algorithm is proposed to learn the underlying network condition and simultaneously act on the learnt information to efficiently schedule transmissions. The proposed work is extensively evaluated and shown to provide better energy conservation than heuristic approaches, while meeting the rate stability constraints.
Speaker Naresh Babu Kakarla

I did my masters from Andhra University, AP. Currently I am pursuing my PhD from IIT Tirupati, India. My research interests are UAV Networking, Reinforcement Learning


Trajectory Design for Unmanned Aerial Vehicles via Meta-Reinforcement Learning

Ziyang Lu (Syracuse University, Syracuse, NY), Xueyuan Wang (School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou 213164, China), M. Cenk Gursoy (Syracuse University, Syracuse, NY)

0
This paper considers the trajectory design problem for unmanned aerial vehicles (UAVs) via meta-reinforcement learning. It is assumed that the UAV can move in different directions to explore a specific area and collect data from the ground nodes (GNs) located in the area. The goal of the UAV is to reach the destination and maximize the total data collected during the flight on the trajectory while avoiding collisions with other UAVs. In the literature on UAV trajectory designs, vanilla learning algorithms are typically used to train a task-specific model, and provide near-optimal solutions for a specific spatial distribution of the GNs. However, this approach requires retraining from scratch when the locations of the GNs vary. In this work, we propose a meta reinforcement learning framework that incorporates the method of Model-Agnostic Meta-Learning (MAML). Instead of training task-specific models, we train a common initialization for different distributions of GNs and different channel conditions. From the initialization, only a few gradient descents are required for adapting to different tasks with different GN distributions and channel conditions. Additionally, we also explore when the proposed MAML framework is preferred and can outperform the compared algorithms
Speaker Ziyang Lu (Syracuse University)

Ziyang Lu received the B.S. degree in electrical engineering from the University of Liverpool, Liverpool, U.K., in 2016, and the M.S. degree in electrical engineering in 2018 from Syracuse University, Syracuse, NY, USA, where he is currently working toward the Ph.D. degree with the Department of Electrical Engineering and Computer Science. His research interests include the areas of wireless communication and machine learning.

Session Chair

Waleed Ejaz (Lakehead University)

Session DroneCom-KS2

Keynote Session II

Conference
3:00 PM — 3:30 PM EDT
Local
May 20 Sat, 3:00 PM — 3:30 PM EDT

TBA

Rongxing Lu (University of New Brunswick, Canada)

0
TBA
Speaker
Speaker biography is not available.
Session Chair

Sahil Garg (Ultra Communications)

Session DroneCom-TS4

Technical Session IV

Conference
4:00 PM — 5:00 PM EDT
Local
May 20 Sat, 4:00 PM — 5:00 PM EDT

Resource Allocation for UAV-assisted Two-way Relay System Under Hardware Impairments

Zhengqiang Wang and Zhen Zhang (School of Communication and Information Engineering Chongqing University of Posts and Telecommunications, Chongqing, China and Institute of Next Generation Network, Chongqing University of Posts and Telecommunications, Chongqing, China); Xiaoyu Wan and Zifu Fan (Institute of Next Generation Network, Chongqing University of Posts and Telecommunications, Chongqing, China)

0
Unmanned aerial vehicle (UAV) has the characteristics of flexible deployment and strong maneuverability. In the future 6G network, UAV-assisted communication is considered to be a promising solution to achieve integrated air[1]space-ground coverage. To improve the spectral efficiency of UAV-assisted communication, a full-duplex two-way relay non[1]orthogonal multiple access transmission scheme is proposed in this paper. The sum rate of the system is analyzed under the condition that the transceiver has hardware impairments. By decoupling the original non-convex problem into two subproblems, an iterative algorithm based on the block coordinate descent method is proposed to realize the joint optimization of UAV deployment, power allocation, and successive interference cancellation decoding order. Simulation results show that the proposed algorithm has a higher sum rate compared with the benchmark scheme.
Speaker Zhen Zhang (Chongqing University of Posts and Telecommunications)

Zhen Zhang was born in Chongqing, China, in 1998. He is currently pursuing the master’s degree in electronic information and communication engineering with Chongqing University of Posts and Telecommunications, Chongqing, China. His main research interest includes UAV communication and resource allocation.

Q-Learning for Sum-Throughput Optimization in Wireless Visible-Light UAV Networks

Yuwei Long and Nan Cen (Missouri University of Science and Technology, Rolla, MO)

0
Unmanned aerial vehicles (UAVs) have been adopted as aerial base stations (ABSs) to provide wireless connectivity to ground users in events of increased network demand, and points of-failure infrastructure (such as in disasters). However, with the existing crowded radio frequency (RF) spectrum, UAV ABSs cannot provide high-data-rate communication required in 5G and beyond. To address this challenge, visible light communication (VLC) is proposed to be equipped on UAVs to take advantage of the flexible and on-demand deployment feature of the UAV, and the high-data-rate communication of the VLC. However, VLC has strong alignment requirements between transceivers, therefore, how to determine the position and orientation of the UAV is critically important for sum-throughput improvement. In this paper, we propose two Q-learning based methods to maximize the sum throughput of the wireless visible-light UAV network by jointly controlling the position and orientation of the UAV. The results show that the proposed approaches can achieve a network wide data rate very close to the optimal solution obtained by exhaustive search and outperform up to 18% compared with the intuitive centroid-based method. Computation complexity is also evaluated, where results showing that the proposed two Q learning based methods can both consume less computational time, i.e., approximately 9 times and 210 times less on average than that of the exhaustive search approach.
Speaker Yuwei Long (Missouri University of Science and Technology)


Strategic Unmanned Aerial Vehicle (UAV) Routing: An Energy-Efficient Approach

Gabriel Avelino Sampedro (Kumoh National Institute of Technology, Gumi, South Korea); Franklin Danas Jr. (Research and Development Center, Philippine Coding Camp, Manila, Philippines); Mideth Abisado (National University - Manila, Manila, Philippines); Dong-Seong Kim and Jae-Min Lee (Kumoh National Institute of Technology, Gumi, South Korea)

0
In this digital age, network connectivity is no longer a luxury but a necessity. Adopting fifth-generation (5G) wireless networks, inefficient communication systems prevail, but not all areas are 5G-ready. Network connectivity has been a long-running issue, especially in areas with limited signal towers. Recently, drones or unmanned aerial vehicles (UAVs) are gaining traction as a viable solution to extend the reach of signal towers. Research is being conducted to adopt this technology in developing flying base stations (FBS). The application of FBS can potentially minimize the gap between regions where a cellular connection is limited or may not reach. However, the energy consumption of FBS is one of the critical factors for its long-term success. Given the limited battery capacity of UAVs, it is essential to minimize energy consumption during operational use. This research aims to explore the application of Low Energy Adaptive Clustering Hierarchy (LEACH), improved LEACH (ILEACH), and optimized heuristic ILEACH (OHILEACH) algorithms in a fleet of UAVs intending to minimize energy consumption. Furthermore, a comparative analysis of the performance of the three LEACH algorithms is explored in terms of energy retention. After a thorough comparative analysis, the application of OHILEACH proved to be the most energy efficient
Speaker Gabriel Avelino Sampedro (University of the Philippines / Kumoh National Institute of Technology)

Gino Sampedro received his B.S. and M.S. degree in Computer Engineering from Mapúa University in the City of Manila, Philippines, earned in 2018. Currently, Gabriel is an Assistant Professor at the Faculty of Information and Communication Studies at the University of the Philippines - Open University. Furthermore, Gabriel is pursuing his Ph.D. in IT Convergence Engineering, where he is a doctorate researcher at the Network Systems Laboratory at Kumoh National Institute of Technology. Gabriel's research interests focus on real-time systems, embedded systems, robotics, and biomedical engineering.

Session Chair

Kuljeet Kaur (…cole de technologie supÈrieure)


Gold Sponsor


Gold Sponsor


Bronze Sponsor


Student Travel Grants


Student Travel Grants


Local Organizer

Made with in Toronto · Privacy Policy · INFOCOM 2020 · INFOCOM 2021 · INFOCOM 2022 · © 2023 Duetone Corp.