Communications Signal Processing Based Solutions for Massive Machine-to-Machine Networks (M3NETs)

Lead Research Organisation: Loughborough University
Department Name: Wolfson Sch of Mech, Elec & Manufac Eng


Future wireless networks should have the capability of serving a wide range of personal wireless devices and appliances with stringent end-to-end delay requirements. These appliances will be equipped with the capabilities to sense various real time events and be able to self-configure via network connections, thereby paving the way for many emerging applications including e-health, intelligent transportation and smart cities. The most important enabling technologies for these applications is seamless machine-to-machine (M2M) wireless communications, which is the key to sustaining large-scale massive interconnections between things. The number of M2M devices has been growing exponentially, and is expected to reach up to 50 billion by 2020. This trend in the market growth for both M2M devices and M2M connectivity segments will further accelerate in the future. Along with it, by 2020, M2M connections will generate 6.7 percent of total mobile traffic-up from 2.7 percent in 2015. As such, M2M communications is envisioned as one of the five disruptive technology directions for fifth generation (5G) wireless networks and beyond.

Despite the importance of machine-type communications, there are many critical challenges that need to be addressed in terms of network congestion and overload due to presence of massive M2M devices with heterogeneous traffic patterns, unprecedented level of inter and intra interference among M2M and human-to-human (H2M) communications, complex resource management due to irregular traffic patterns and energy constraints. The focus of this project is on tackling these critical challenges, by advancing aspects of communications signal processing, stochastic geometry, convex optimizations and game theory. In particular, we will contribute in terms of characterising heterogeneous traffic patterns associated with massive M2M communications, development of distributed random access channel protocols, proposal of convex and game theoretic resource allocation methods and design of energy harvesting constraint based cross-layer optimisation algorithms and protocols. All the concepts and algorithms developed will be integrated and the radio link layer performance will be assessed using a simulation reference system based on LTE-Advanced standards and its evolution towards 5G. Industrial partners will be engaged throughout the project to ensure industrial relevance of our work.
Description This research project has resulted in many novel algorithms and methods that could facilitate specially efficient machine-to-machine (M2M) communications. In particular, we have proposed bockchain technology in combination with artificial intelligence techniques for the autonomous operation of devices in a wireless networks, which has great potential for future generations of wireless networks that will have massive number of connected systems and will require autonomous scheduling, resource allocation, management and operation. We have also proposed new relaying technology based on hybrid reflecting intelligent surface and relay for enhancing coverage of wireless transmissions. We have also investigated vulnerability of AI technology (machine learning) in wireless networks and proposed new adversarial machine learning techniques to mitigate attacks on machine learning-based wireless networks.
Exploitation Route The machine learning and blockchain technology have the potential to make huge impact in the design of future generations of wireless networks. Our current focus is exactly on these topics and we have been disseminating in leading intentional conferences and journals.
Sectors Digital/Communication/Information Technologies (including Software)

Description We have proposed several novel techniques including blockchain technology for autonomous operation of distributed wireless network and nodes, reflective intelligence surfaces for enhancing capacity and coverage of wireless networks and adversarial machine learning for mitigating attacks on machine learning-based wireless networks. These are very timely and emerging research works in wireless networks and our publications have attracted considerable citations and have the potential to make economic impact.
First Year Of Impact 2018
Sector Digital/Communication/Information Technologies (including Software)
Impact Types Economic

Description International academic colloboration 
Organisation University of Genoa
Country Italy 
Sector Academic/University 
PI Contribution Development of new adversarial machine learning algorithms for modulation classification.
Collaborator Contribution Knowledge and expertise in adversarial machine learning.
Impact L. Zhang, S. Lambotharan, G. Zheng, B. AsSadhan and F. Roli, "Countermeasures Against Adversarial Examples in Radio Signal Classification," IEEE Wireless Communications Letters, vol. 10 (8), pp. 1830-1834, August 2021. L. Zhang, S. Lambotharan, G. Zheng, G, Liao, A. Demontis and F. Roli, "A Hybrid Training-time and Run-time Defense Against Adversarial Attacks in Modulation Classification," to appear in IEEE Wireless Communications Letters, 2022 L. Zhang, S. Lambotharan, G. Zheng and F. Roli, "A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification," IEEE Globecom, Madrid, 2021.
Start Year 2020
Description Invited Plenary Talk 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact I have given a plenary talk which included the results from this project and wireless communications research in general at the 18th International Symposium on Advanced Electrical and Communication Technologies (ISAECT), Rabat, Morocco, Nov. 2018. This has attracted significant interests from participants of the conference.
Year(s) Of Engagement Activity 2018