To develop a global telecommunications infrastructure, one of the main challenges for 5G services is to ensure reliable communication in high- mobility environments such as vehicle- to- vehicle (V 2 V) communications with relative speeds of up to 220 km/h, MCA with 900 km/h, and even faster speeds with low- earth- orbit satellites (LEOS) [1]. Additionally, research into underwater acoustic (UWA) communication is rapidly advancing due to its vital role in various fields such as underwater exploration, marine biology, and oceanography. Underwater channel conditions present challenges like temperature, salinity, pressure, noise, and currents, making communication complex and unpredictable [2].
Wireless communication in these high- mobility and underwater environments faces severe Doppler spread effects caused by the relative movement of transceivers. This results in significant, dynamic, and rapid channel variations through fast fading. Doubly dispersive channels, typical in high- mobility scenarios, involve multipath delays causing time dispersion and Doppler shifts leading to frequency dispersion [3]. Consequently, transmitted signals experience serious inter- carrier interference (ICI) from Doppler spread and inter- symbol interference (ISI) from delays. Conventional orthogonal frequency division multiplexing (OFDM), widely used in 4 G/5 G cellular systems, may become unreliable because it is highly vulnerable to ICI, and high Doppler spreads can disrupt orthogonality in OFDM waveforms.
To address these issues, a newer orthogonal time frequency space (OTFS) modulation technique shows promise for enabling next- generation wireless communications in such high- mobility settings [3]. Implementing an OTFS receiver requires an efficient channel estimation algorithm that operates with similar energy efficiency to current OFDM channel estimation methods. The goal of this project is to develop an energy- efficient receiver algorithm using a machine learning framework that can accurately estimate the fast- changing, time- varying channels in OTFS signals [4]. The energy- efficient nature of this algorithm would allow deployment across various low- power wireless devices, including mobile phones and Internet- of- Things (iot) gadgets. Furthermore, underwater acoustic communication channels offer a valuable platform to test an effective channel estimation algorithm [5]. The presence of multipath propagation, severe Doppler effects, and spreading in underwater acoustic channels makes it comparable to the challenges faced in high- mobility wireless environments [6]. The energy efficiency requirements of the channel estimation algorithm are particularly relevant here, as underwater transmission usually involves portable, battery- powered equipment.
School
Electrical Engineering and Telecommunications
Research Area
Electrical engineering | Underwater acoustic systems | Wireless communications | Signal processing | Computer communications networks | Optimisation | Machine learning
Suitable for recognition of Work Integrated Learning (industrial training)?
No
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
This project involves developing new channel estimation and modulation designs to greatly enhance data rate, reliability, and robustness of high-mobility communications for future mobile services, including underwater acoustic communication systems. The main goal is to create energy-efficient receiver algorithms using a machine learning framework [7] that can effectively estimate rapidly changing fading channels and reliably detect data symbols to ensure dependable communication in high-mobility and underwater acoustic environments. The student should be proficient in MATLAB programming and have a basic understanding of wireless communications, signal processing, and machine learning. We will offer lectures to introduce advanced concepts that will be part of their training for this project. Additionally, the student will join our research team, which includes undergraduate, postgraduate, MPhil, and PhD students. They will have access to all lab resources, workspaces, software, and research facilities, just like other research scholars, to support their work efficiently and effectively.
- One short paper in a tier-1 IEEE communication conference with an undergraduate student. A poster presentation and a short video highlighting the key results will also be provided.
- One full transaction-type journal paper based on the extension of the conference paper to be led by me within two months after the end of this project.
- Training of an undergraduate student and motivating them to join higher degree research MPhil/PhD programs.
- D. Soldani, M. Shore, J. Mitchell, M. Gregory, ""The 4G to 5G network architecture evolution in Australia,"" Australian Journal of Telecoms and Digital Economy, Vol. 6, N. 4, Dec. 2018.
- M. Lanzagorta, “Underwater communications,” Synthesis lectures on communications, vol. 5, no. 2, pp. 1–129, 2012
- Z. Wei et al., ""Orthogonal Time-Frequency Space Modulation: A Promising Next-Generation Waveform,"" in IEEE Wireless Communications, vol. 28, no. 4, pp. 136-144, August 2021
- Y. K. Enku et al., ""Two-Dimensional Convolutional Neural Network-Based Signal Detection for OTFS Systems,"" in IEEE Wireless Communications Letters, vol. 10, no. 11, pp. 2514-2518, Nov. 2021
- R. A. McCarthy and A. Sengupta, ""Underwater channel estimation exploiting multipath feature morphology"", The Journal of the Acoustical Society of America, vol. 149, pp 983-996, 2021
- N. Ansari, A. S. Gupta and A. Gupta, ""Underwater acoustic channel estimation via CS with prior information,"" OCEANS 2017 - Aberdeen, 2017, pp. 1-5, doi: 10.1109/OCEANSE.2017.8084965.
- Y. Fu, S. Wang, C. Wang, X. Hong, and S. McLaughlin, ""Artificial intelligence to manage network traffic of 5G wireless networks,"" IEEE/ACM Trans. Netw., vol. 32, no. 6, pp. 58–64, Nov./Dec. 2018.