Research Topics

6G Networks: Characterisation of human-to-machine (H2M) traffic

Collaborators: Prof Martin Maier (Institut National de la Recherche Scientifique (INRS)), Canada Dr. Sourav Mondal (Trinity College Dublin) Dr. Lihua Ruan (Chinese University of Hong Kong)
Keywords: human-to-machine (H2M) communication networks; low-latency communication networks; Tactile Internet; traffic characterisation
Disciplines: Electrical & Electronic Engineering and Computer Science

OVERVIEW

Future 6G networks, which harnesses real-time and remotely-controlled human-to-machine (H2M) applications such as extended reality and the Internet of Senses will need to be supported by communication infrastructures that incur very low and stringent end-to-end communication latency of approximately 1 to 10 ms. Addressing this latency challenge through novel AI-assisted resource allocation strategies necessitates a deep understanding of H2M traffic. The main challenge has been the scarcity of real H2M traffic traces, despite the recent interests from both academia and industry. Consequently H2M traffic characteristics/statistics are relatively unknown.  This project aims to establish experiments that emulate H2M applications and to develop analytical models for H2M traffic.  The key outcome is a deep understanding of the characteristics of H2M traffic and hence its latency and reliability requirements.

This project is presently recruiting PhD candidate(s) with a background in Electrical and Electronic Engineering and/or Computer Science. Interested candidates with a keen interest in experimental investigation and analytical modelling, are encouraged to contact Prof. Wong. The successful candidate(s) will be mentored by a team of leading experts with pioneering contributions in broadband access networks, converged fibre-wireless networks, human-to-machine communication networks, 6G networks, Internet-of-Things, optical wireless networks, and the Tactile Internet.

RELEVANT RESEARCH PAPERS

  1. S. Mondal, L. Ruan, M. Maier, D. Larrabeiti, G. Das and E. Wong, “Enabling Remote Human-to-Machine Applications With AI-Enhanced Servers Over Access Networks,” EEE Open Journal of the Communications Society, vol. 1, pp. 889-899, 2020, doi: 10.1109/OJCOMS.2020.3009023.
  2. L. Ruan, M. P. I. Dias and E. Wong, “Achieving Low-Latency Human-to-Machine (H2M) Applications: An Understanding of H2M Traffic for AI-facilitated Bandwidth Allocation,” IEEE Internet of Things Journal, vol. 8, issue 1, pp. 626-635, 2021. doi: 10.1109/JIOT.2020.3007947.

6G Networks: Improving resiliency for human-to-machine (H2M) applications

Keywords: 6G Networks, Internet-of-Senses, fast-responding fault detection; human-to-machine communication networks; network protection switching; network survivability; Tactile Internet
Disciplines: Electrical & Electronic Engineering and Computer Science

Future 6G communication networks are expected to support mission-critical human-to-machine (H2M) applications, e.g. tele-surgery and coordinated driving, that require a 99.999% network reliability. This is equivalent to at most 0.86 seconds of downtime per day. The future-proofing of existing communication networks to rapidly detect failures and to support H2M traffic with minimal disruption, has yet to be critically investigated.

The primary goals of the project are to design, characterise, and implement fast-responding fault detection techniques and resilient network architectures that meet a network reliability ranging from 99.9% (only 86 seconds of downtime/day) to 99.999% (only 0.86 seconds of downtime/day), depending on the H2M application supported. The performance of these resilient networks are to be evaluated through connection availability and failure-impact-factor measures, with the focus on serving and protecting networks of real cities and towns. Optimal placement of control servers, cloudlets, redundant components and network paths encompassing optical transport, optical x-haul, radio access network through to indoor wireless access networks, to meet reliability and latency demands of different H2M applications, are also to be investigated.

This project is presently recruiting PhD candidate(s) with a background in Electrical and Electronic Engineering and/or Computer Science. Interested candidates with a keen interest in experimental investigation and analytical modelling, are encouraged to contact Prof. Wong. Successful candidate(s) will be mentored by a team of leading experts with pioneering contributions in survivable communication network design and protection switching, converged fibre-wireless networks, Internet-of-Things, and the Tactile Internet.

RELEVANT RESEARCH PAPERS

  • E. Wong, S. Edirisinghe, C. Ranaweera, C. Lim and A. Nirmalathas, “Data and Control Plane Separation for Interoperable Indoor Wireless Access Connectivity”, (Invited Talk), Proc. of ECOC 2020, paper Tu2G.1, 2020.
  • E. Wong, E. Grigoreva, L. Wosinska, and C. Mas Machuca, “Enhancing the Survivability and Power Savings of 5G Transport Networks Based on DWDM Rings,” IEEE J. Opt. Commun. Netw., vol. 9, no. 9, pp. D74-D85, 2017.
  • E. Grigoreva, E. Wong, M. Furdek, L. Wosinka, and C. Mas Machuca, “Energy Consumption and Reliability Performance of Survivable Passive Optical Converged Networks: Public ITS Case Study,” IEEE J. Opt. Commun. Netw., vol. 9, no. 4, pp. C98-C108, 2017.
  • Y. Yu, C. Ranaweera, C. Lim, L. Guo, Y. Liu, A. Nirmalathas, and E. Wong, “Hybrid Fiber-Wireless Network: An Optimization Framework for Survivable Deployment” IEEE J. Opt. Commun. Netw., vol. 9 no. 6, pp. 466-478, 2017.

Adapting communication networks for low-latency human-to-machine (H2M) applications

Collaborators: Dr Lihua Ruan (Chinese University of Hong Kong) Dr. Sourav Mondal (Trinity College Dublin) Dr. Imali Dias (Deakin University) Prof Vincent Chan (Massachusetts Institute of Technology (MIT), USA)
Keywords: human-to-machine communication networks; low-latency communication networks; Tactile Internet
Disciplines: Electrical & Electronic Engineering and Computer Science

OVERVIEW

Future real-time and remotely-controlled human-to-machine (H2M) applications such as teleoperation and telemedicine will need to be supported by communication infrastructures that incur very low and stringent end-to-end communication latency of approximately 1 to 10 ms. Addressing this latency challenge necessitates a strategic rethink on how network resource is allocated and managed. In supporting H2M communications, converged optical fiber and wireless networks have been considered as a promising network infrastructure. In the uplink direction, machines contend for uplink bandwidth. Typically, in order to avoid uplink bandwidth collisions, uplink bandwidth is allocated to each machine by a central office through a process known as dynamic bandwidth allocation. In remotely-controlled H2M applications, adaptive allocation will promote flexibility and real-time response, thus ensuring that the latency constaint is always satisfied. This project therefore focuses on adaptive allocation schemes based on machine learning techniques such as federated and transfer learning.

This project is presently recruiting PhD candidate(s) with a background in Electrical and Electronic Engineering and/or Computer Science. Interested candidates with a keen interest in experimental investigation and analytical modelling, are encouraged to contact Prof. Wong. The successful candidate(s) will be mentored by a team of leading experts with pioneering contributions in broadband access networks, 5G and beyond transport networks, converged fibre-wireless networks, human-to-machine communication networks, Internet-of-Things, optical wireless networks, and the Tactile Internet.

RELEVANT RESEARCH PAPERS

  • S. Mondal, L. Ruan, M. Maier, D. Larrabeiti, G. Das and E. Wong, “Enabling Remote Human-to-Machine Applications With AI-Enhanced Servers Over Access Networks,” in IEEE Open Journal of the Communications Society, vol. 1, pp. 889-899, 2020, doi: 10.1109/OJCOMS.2020.3009023.
  • L. Ruan, M.P.I. Dias and E. Wong, “Achieving Low-Latency Human-to-Machine (H2M) Applications: An Understanding of H2M Traffic for AI-facilitated Bandwidth Allocation,” IEEE Internet of Things Journal, vol. 8, issue 1, pp. 626-635, 2021. doi: 10.1109/JIOT.2020.3007947.
  • L. Ruan, M. P. I. Dias & E. Wong, “Enhancing latency performance through intelligent bandwidth allocation decisions: a survey and comparative study of machine learning techniques,” IEEE Journal of Optical Communications and Networking, vol. 12, no. 4, pp. B20, 2020, doi:10.1364/jocn.379715
  • L. Ruan, M.P.I. Dias, and E. Wong, “Machine Learning-based Bandwidth Prediction for Low-Latency H2M Applications,” IEEE Internet of Things Journal, vol. 6, no. 2, pp. 3743-3752, 2019.
  • E. Wong, M.P.I. Dias, and L. Ruan, “Predictive Resource Allocation for Tactile Internet Capable Passive Optical LANs,” J. Lightw. Technol., vol. 35, no. 13, pp. 2629 – 2641, July 2017.

 

Cloudlets for secure human-to-machine (H2M) applications

Collaborators: Dr. Sourav Mondal (Trinity College Dublin) Prof. Goutam Das (Indian Institute of Technology – Khragpur)
Keywords: artificial intelligence; distributed and cloud computing; optical networks; reinforcement learning
Disciplines: Electrical & Electronic Engineering and and Computer Science

OVERVIEW

Future real-time and remotely-controlled human-to-machine (H2M) applications such as teleoperation and telemedicine will need to be supported by communication infrastructures that incur very low and stringent end-to-end communication latency of approximately 1 to 10 ms. Cloudlets, part of the multi-access edge computing paradigm, are distributed computing/storage resources placed close to end-users to relieve computation/storage pressures of their mobile devices while maintaining satisfactory quality-of-experience for users. The utlisation of cloudlets in H2M supported communication networks are being explored to reduce the communication latency. So far, there has been very little insight into computation offload algorithms and/or optimised cloudlet network planning for the purpose of enhancing latency performance.

This project is presently recruiting PhD candidate(s) with a background in Electrical and Electronic Engineering and/or Computer Science. Interested candidates with a keen interest in experimental investigation and analytical modelling, are encouraged to contact Prof. Wong. The successful candidate(s) will be mentored by a team of leading experts with pioneering contributions in broadband access networks, game theory, converged fibre-wireless networks, human-to-machine communication networks, Internet-of-Things, optical wireless networks, and the Tactile Internet.

RELEVANT RESEARCH PAPERS

  • S. Mondal, G. Das & E. Wong 2020, “A Game-Theoretic Approach for Non-cooperative Load Balancing among Competing Cloudlets,”IEEE Open Journal of the Communications Society, pp. 1–1, doi:10.1109/ojcoms.2020.2971613
  • S. Mondal, G. Das, and E. Wong, “Efficient cost-optimization frameworks for hybrid cloudlet placement over fiber-wireless networks,” IEEE Journal of Optical Communications and Networking, vol. 11, no. 8, pp. 437, 2019. doi:10.1364/jocn.11.000437
  • S. Mondal, G. Das, and E. Wong, “Computation Offloading in Optical Access Cloudlet Networks: A Game-Theoretic Approach,” IEEE Communications Letters, 22 (8), 1564-1567, 2018.
  • S. Mondal, G. Das, and E. Wong, “CCOMPASSION: A Hybrid Cloudlet Placement Framework over Passive Optical Access Network,” in Proc. of IEEE IEEE Conference on Computer Communications (INFOCOM 2018), 216-224, 2018.