Communications Signal Processing Based Solutions for Massive Machine-to-Machine Networks (M3NETs)
Lead Research Organisation:
Queen Mary University of London
Department Name: Sch of Electronic Eng & Computer Science
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Publications
Ahsan W
(2021)
Resource Allocation in Uplink NOMA-IoT Networks: A Reinforcement-Learning Approach
in IEEE Transactions on Wireless Communications
Ahsan W
(2022)
A Reliable Reinforcement Learning for Resource Allocation in Uplink NOMA-URLLC Networks
in IEEE Transactions on Wireless Communications
Bai T
(2021)
Resource Allocation for Intelligent Reflecting Surface Aided Wireless Powered Mobile Edge Computing in OFDM Systems
in IEEE Transactions on Wireless Communications
Bai T
(2020)
Latency Minimization for Intelligent Reflecting Surface Aided Mobile Edge Computing
in IEEE Journal on Selected Areas in Communications
Chen Z
(2022)
Dynamic Task Software Caching-Assisted Computation Offloading for Multi-Access Edge Computing
in IEEE Transactions on Communications
Fayaz M
(2021)
Transmit Power Pool Design for Grant-Free NOMA-IoT Networks via Deep Reinforcement Learning
in IEEE Transactions on Wireless Communications
Hong S
(2020)
Artificial-Noise-Aided Secure MIMO Wireless Communications via Intelligent Reflecting Surface
in IEEE Transactions on Communications
Hong S
(2021)
Robust Transmission Design for Intelligent Reflecting Surface-Aided Secure Communication Systems With Imperfect Cascaded CSI
in IEEE Transactions on Wireless Communications
Jiang N
(2018)
Analyzing Random Access Collisions in Massive IoT Networks
in IEEE Transactions on Wireless Communications
| Description | NarrowBand-Internet of Things (NB-IoT) is an emerging cellular-based radio access technology, which offers a range of flexible configurations for different coverage enhancement (CE) groups to provide reliable uplink connections for massive IoT devices with diverse data traffic. To optimize the number of served IoT devices, the uplink resource configurations need to be adjusted in real-time according to the dynamic traffic, this brings the challenge of how to select the configurations at the Evolved Node B (eNB) in the multiple CE groups scenario with high-dimension and interdependency. We developed deep reinforcement learning based dynamic optimization schemes for NB-IoT. The developed schemes can solve the current main problem of random access under bursty traffic condition. These findings highly useful for the next generation artificial intelligence enabled wireless systems. Further more, in Framed-ALOHA networks, assuming no prior information about the traffic model, apart from a bound on its temporal memory, we developed an online learning-based adaptive traffic load prediction method that is based on Recurrent Neural Networks (RNN) and specifically on the Long Short-Term Memory (LSTM) architecture. Along with the line of 3GPP standard (Release 16), we developed machine learning based Grant-Free Non Orthogonal Multiple Access (NOMA) with Multiple Configured-Grants for massive Ultra Reliable Low Latency Communications (mURLLC). Developed machine learning based multiple configured-Grants mURLLC is a potential solution to meet the latency constraint of 6G new use case under bursty traffic scenario. |
| Exploitation Route | We planned to organize a workshop on artificial intelligence in Industrial IoT such that these findings can be disseminated to industries. But, we were unable to organize due to Covid-19 pandemic. We extended this work for UAV enabled IoT networks. We have been able to secure two new grants on machine learning enabled cellular connected UAV networks and federated learning based resource optimisation for 6G wireless communications. |
| Sectors | Agriculture, Food and Drink,Creative Economy,Digital/Communication/Information Technologies (including Software),Environment,Leisure Activities, including Sports, Recreation and Tourism,Manufacturing, including Industrial Biotechology,Transport |
| Description | NarrowBand-Internet of Things (NB-IoT) is an emerging cellular-based radio access technology in 5G and Beyond, which offers a range of flexible configurations for different coverage enhancement (CE) groups to provide reliable uplink connections for massive IoT devices with diverse data traffic. To optimize the number of served IoT devices, the uplink resource configurations need to be adjusted in real-time according to the dynamic traffic, this brings the challenge of how to select the configurations at the Evolved Node B (eNB) in the multiple CE groups scenario with high-dimension and interdependency. We developed deep reinforcement learning based dynamic optimization schemes for NB-IoT. The developed schemes can solve the current main problem of random access under bursty traffic condition. These findings highly useful for the next generation artificial intelligence enabled wireless systems. We have also developed resource allocation algorithms for Ultra Reliable Low Latency Communications (URLLC) enabled Industrial Internet of Things (IIoT) Networks. We extended this work for UAV enabled IoT networks as well as for new 6G use case of mURLLC. Our findings in this project have been disseminated in numerous top IEEE journals and IEEE Flagship conferences and attracted the interest of non-academic industries. These finding also used to secure two follow up EPSRC standard grants as well as one Industrial project on machine learning enabled 6G. |
| First Year Of Impact | 2018 |
| Sector | Digital/Communication/Information Technologies (including Software),Education |
| Impact Types | Economic |