Road Travel
.
.
Saman Halgamuge, University of Melbourne, Australia
IEEE Fellow, IET Fellow, AAIA Fellow
Dr.-Ing Saman Halgamuge, Professor of University of Melbourne, Fellow of IEEE and IET, received the Dr.-Ing and Dipl.-Ing in data engineering from the Technical University of Darmstadt, Germany and BSc Engineering degree from University of Moratuwa, Sri Lanka. He is listed as a top 2% most cited researcher for AI and Image Processing in the Stanford database. His previous leadership roles include Head, School of Engineering at Australian National University and Associate Dean of the Engineering and IT at University of Melbourne. He graduated 50 PhD students and mentored 16 postdoctoral fellows in Australia. His research funding includes Australian and International industry and government agencies and philanthropic foundations. He is an honorary professor of ITB and SLIIT.
(Onsite Talk) Speech Title: Emerging Role of AI in Sustainable Energy: From forecasting the solar generation of rooftop solar panels to Energy Management in Electric Vehicles
The energy sector is undergoing a remarkable transition ably supported by AI. This transition is not only driven by the access to increasingly affordable solar and storage solutions, but also due to the increased ability of AI to predict how electricity will be used by consumers, which then can be used to optimize the usage of non-dispatchable energy. The unmistakable presence of Electric Vehicles (EVs) adds to the opportunity for researchers working in the interface between Sustainable Energy and AI. In this keynote, we focus on forecasting the decentralised energy production of rooftop solar while also discussing the energy storage options and the contribution of such renewable energy production towards stabilising the grid that may have to cope with increasing numbers of EVs on the road. Importantly, we answer the questions: Could AI help in accurately forecasting solar generation? Could the charging and discharging policy for EVs be optimised? Could the developing world also benefit from AI applied to Sustainable Energy?
Arumugam Nallanathan, Queen Mary university of London, U.K.
IEEE Fellow, IEEE Distinguished Lecturer
Arumugam Nallanathan is Professor of Wireless Communications and the founding head of the Communication Systems Research (CSR) group in the School of Electronic Engineering and Computer Science at Queen Mary University of London since September 2017. He was with the Department of Informatics at King’s College London from December 2007 to August 2017, where he was Professor of Wireless Communications from April 2013 to August 2017. He was an Assistant Professor in the Department of Electrical and Computer Engineering, National University of Singapore from August 2000 to December 2007. His research interests include 6G Wireless Networks and Internet of Things (IoT). He published nearly 700 technical papers in scientific journals and international conferences. He is a co-recipient of the Best Paper Awards presented at the IEEE International Conference on Communications 2016 (ICC’2016), IEEE Global Communications Conference 2017 (GLOBECOM’2017) and IEEE Vehicular Technology Conference 2017 (VTC’2017). He is a co-receipient of IEEE Communications Society Leonard G. Abraham Prize, 2022.
He is an Editor-at-Large for IEEE Transactions on Communications and a senior editor for IEEE Wireless Communications Letters. He was an Editor for IEEE Transactions on Wireless Communications (2006-2011), IEEE Transactions on Vehicular Technology (2006-2017), IEEE Signal Processing Letters and a Guest Editor for IEEE Journal on Selected Areas in Communications (JSAC). He served as the Chair for the Signal Processing and Computing for Communications (SPCC-TC) of IEEE Communications Society and Technical Program Chair and member of Technical Program Committees in numerous IEEE conferences. He received the IEEE Communications Society SPCE outstanding service award 2012 and IEEE Communications Society RCC outstanding service award 2014. He has been selected as a Web of Science (ISI) Highly Cited Researcher in 2016, 2022 and 2023. He is an IEEE Fellow and IEEE Distinguished Lecturer.
(Onsite Talk) Speech Title: Federated Learning in Wireless Communications
Abstract: Federated learning (FL) is an efficient and privacy-preserving distributed learning paradigm that enables massive edge devices to train machine learning models collaboratively. Although various communication schemes and algorithm designs have been proposed to expedite the FL process in resource-limited wireless networks, the unreliable nature of wireless channels, device heterogeneity, and data heterogeneity are still less explored. In this talk, three solutions will be dicussed for addressing the above practical challenges in wireless FL. Firstly, to tackle the unreliable wireless channels, a novel FL framework, namely FL with gradient recycling (FL-GR), which recycles the historical gradients of unscheduled and transmission-failure devices to improve the learning performance of FL will be discussed. Secondly, to solve the heterogeneity issues, an adaptive model pruning-based FL framework, where the edge server dynamically generates sub-models by pruning the global model for devices' local training to adapt their heterogeneous computation capabilities and time-varying channel conditions will be explained. Thirdly, a semi-asynchronous time trigger protocol to overcome the integration issues with one emerging wireless communication scheme, i.e., over-the-air communications will be provided. Based on our research experience, some open problems of wireless FL will be provided.
Ahmet Yazıcı, Eskişehir Osmangazi Üniversitesi, Turkey
Ahmet Yazıcı received the Ph.D. degre from Eskisehir Osmangazi University (ESOGU) in control systems in 2005. He was a member of the OSU-ACT Team in 2007 Darpa Urban Challenge. He has been with the Department of Computer Engineering, Eskisehir Osmangazi University since 2005. He is founder of Intelligent Factory and Robotic Laboratory (2016) and ESOGU Center for Intelligent Systems Research (CISAR) (2020).
CISAR has also good cooperation with Large Industries, SMEs and Research Institutions in Turkey and Europe. It provides practical solutions to real world problems and develop commercial-ready products cooperation with industry. As a result, CISAR has been successful in the realization of numerous industry-based research projects with major national and international organizations.
(Onsite Talk) Speech Title: Optimization of Electric Vehicle Autonomy- OPEVA
Abstract: Electric vehicles (EV) are critical components to create a sustainable modern “mobility experience”. To accelerate the deployment of EVs, technological solutions should cover end to end ecosystem. This requires integrations of developments in several subdomains of ecosystems of EVs such as of energy-efficient power train, accurate range prediction techniques, dynamic routing, EV grid integration, efficient charging technologies etc. These will also improve EV market penetration by addressing limiting psychological factors such as range anxiety, high price, limited charging facilities, and duration of charging. The main objective of the OPEVA project is to explore the benefits that can be obtained from the interaction between the multiple actors involved in the modern “mobility experience” in order to optimize the autonomy of electric vehicles in a modern world which also requires consider sustainability and resource optimization.
This presentation focus on developments in OPEVA project that involves 37 partners from 11 European Countries. The project identifies six technology domains, involving 23 key technologies, and four non-technical domains which must be developed to move from conventional EVs to sustainable EVs. The project achievements will be tested in 9 collaborative demonstrators, which include: HiL testing for integrated battery balancing and power electronics, development of Battery Packs with Smart BMS, simulation on HiL system Test and Perform Physical Test with Battery Pack Test Machine, improved sensors for accurate battery monitoring, energy Efficient Route Planning, in-vehicle integration of inductive charging with BMS and power electronics, modular batteries storage based second life EV module variants, GaN-based IoT-enabled surface inductive charging system, and Flexible Charging schedulers.
Kemal Leblebicioğlu, Middle East Technical University, Turkey
Kemal Leblebicioğlu received the Ph.D. degree from the Mathematics Department, Middle East Technical University (METU), Ankara, Turkey, in 1988. His Ph.D. thesis is on optimal control problem with nonlinear elliptic state equations.,He has been a Full Professor with the Electrical and Electronics Engineering Department, METU, since 1999. He has a background in optimization, optimal control theory, computer vision, intelligent systems, flight control, walking robots, and unmanned vehicles. He conducted several research and development projects as a project leader and a researcher, and gave consultancy to several civilian and government research centers. Nowadays, he makes research on decision-making systems and unmanned vehicles, in particular, unmanned air and underwater vehicles. He has been one of the founders of the company DESISTEK, Ankara, Turkey, that produces unmanned underwater and sea-surface vehicles since 2011.
(Onsite Talk) Speech Title: Control Structure Design with Constraints for a Slung Load Quadrotor System
This work presents a study to design a new control structure for a quadrotor carrying a slung load with swing angle constraints. This quadrotor is supposed to pass through the waypoints at specified speeds. The quadrotor with the slung load is an underactuated system. First, a cascaded PID autopilot for the quadrotor is designed, which adaptively gives attention to position and speed requirements as a function of their errors. Its parameters are found from an optimization problem solved using the Particle Swarm Optimization (PSO) algorithm. Second, this controller's performance is improved by adding the Complementary Controller employing an Artificial Neural Network (ANN). This structure is activated when the swing angle constraint is about to be violated. It is trained using optimal control values corresponding to the cases where the swing angle falls in a particular band about the upper swing angle constraint. The combined controller is tested over different challenging scenarios, and results are presented. Simulations are performed in MATLAB/Simulink environment. Finally, some of the simulation results are validated on a physical system.