Intelligent Massive NOMA towards 6G: Signal Processing Advances and - PowerPoint PPT Presentation

Intelligent Massive NOMA towards 6G: Signal Processing Advances and Emerging Applications Dr. Yuanwei Liu Queen Mary University of London, UK yuanwei.liu@qmul.ac.uk Sep. 16th, 2020 1 / 63

Outline 1 Power-Domain NOMA Basics 2 Signal Processing Advances for NOMA: A Machine Learning Approach 3 Emerging Applications for NOMA Emerging Applications for NOMA: Interplay Between RIS/IRS and NOMA Networks Emerging Applications for NOMA: Exploiting NOMA in UAV Networks 2 / 63

From OMA to NOMA 1 Question : What is multiple access? 2 Orthogonal multiple access (OMA) : e.g., FDMA, TDMA, CDMA, OFDMA. 3 New requirements in beyond 5G Ultra-high spectrum efficiency. Massive connectivity. Heterogeneous QoS and mobility requirement. 4 Non-orthogonal multiple access (NOMA) : to break orthogonality. 5 Standard and industry developments on NOMA Whitepapers : DOCOMO, METIS, NGMN, ZTE, SK Telecom, etc. LTE Release 13 : a two-user downlink special case of NOMA. Next generation digital TV standard ATSC 3.0 : a variation of NOMA, termed Layer Division Multiplexing (LDM). 3 / 63

Power-Domain NOMA Basics User m Subtract user User n Time detection m ’ s signal detection User n Power SIC BS Superimposed signal of User m User m User m and n detection 0 User m User n Frequency 1 Supports multiple access within a given resource block (time/frequecy/code), using different power levels for distinguishing/separating them [1]. 2 Apply successive interference cancellation (SIC) at the receiver for separating the NOMA users [2]. 3 If their power is similar, PIC is a better alternative. [1] Y. Liu et al. , “Non-Orthogonal Multiple Access for 5G”, Proceedings of the IEEE ; Dec 2017. ( Web of Science Hot paper ) [2] Z. Ding, Y. Liu, et al. (2017), “Application of Non-orthogonal Multiple Access in LTE and 5G Networks”, IEEE Communication Magazine ;( Web of Science Hot paper ). 4 / 63

Power NOMA Basics 1 Question : Why NOMA is a popular proposition for beyond 5G? 2 Consider the following two scenarios. If a user has poor channel conditions The bandwidth allocated to this user via OMA cannot be used at a high rate. NOMA - improves the bandwidth-efficiency . If a user only needs a low data rate, e.g. IoT networks. The use of OMA gives the IoT node more capacity than it needs. NOMA - heterogeneous QoS and massive connectivity . [1] Z. Ding, Y. Liu, et al. (2017), “Application of Non-orthogonal Multiple Access in LTE and 5G Networks”, IEEE Communication Magazine ;( Web of Science Hot paper ). 5 / 63

Power NOMA Basics 1 Question : Why NOMA is a popular proposition for beyond 5G? 2 Consider the following two scenarios. If a user has poor channel conditions The bandwidth allocated to this user via OMA cannot be used at a high rate. NOMA - improves the bandwidth-efficiency . If a user only needs a low data rate, e.g. IoT networks. The use of OMA gives the IoT node more capacity than it needs. NOMA - heterogeneous QoS and massive connectivity . [1] Z. Ding, Y. Liu, et al. (2017), “Application of Non-orthogonal Multiple Access in LTE and 5G Networks”, IEEE Communication Magazine ;( Web of Science Hot paper ). 5 / 63

Power NOMA Basics 1 Question : Why NOMA is a popular proposition for beyond 5G? 2 Consider the following two scenarios. If a user has poor channel conditions The bandwidth allocated to this user via OMA cannot be used at a high rate. NOMA - improves the bandwidth-efficiency . If a user only needs a low data rate, e.g. IoT networks. The use of OMA gives the IoT node more capacity than it needs. NOMA - heterogeneous QoS and massive connectivity . [1] Z. Ding, Y. Liu, et al. (2017), “Application of Non-orthogonal Multiple Access in LTE and 5G Networks”, IEEE Communication Magazine ;( Web of Science Hot paper ). 5 / 63

Power NOMA Basics 1 Question : Why NOMA is a popular proposition for beyond 5G? 2 Consider the following two scenarios. If a user has poor channel conditions The bandwidth allocated to this user via OMA cannot be used at a high rate. NOMA - improves the bandwidth-efficiency . If a user only needs a low data rate, e.g. IoT networks. The use of OMA gives the IoT node more capacity than it needs. NOMA - heterogeneous QoS and massive connectivity . [1] Z. Ding, Y. Liu, et al. (2017), “Application of Non-orthogonal Multiple Access in LTE and 5G Networks”, IEEE Communication Magazine ;( Web of Science Hot paper ). 5 / 63

What will NOMA for 6G be? Intelligent (AI) + Massive (Grant-Free) + Nonorthogonal (Power/Code Domain)+ Compatibility (New techniques) 6 / 63

My Previous Research Contributions in NOMA Compatibility NOMA for 5G Security Sustainability http://www.eecs.qmul.ac.uk/ ∼ yuanwei/Publications.html 7 / 63

Signal Processing Advances for NOMA: A Machine Learning Approach Raw Data Sets Proposed Unified Machine Learning Framework Applications Periodically UAV comunication Live streaming update Features Prediction/ Prediction/ Feature Data Data data online online extraction modelling modelling Raw Refinement Refinement Predicted input behaviors Social media AD control data MENs provisioning Neural networks Reinforcement learning Fig.: Artificial intelligent algorithms for wireless communications. [1] Y. Liu , S. Bi, Z. Shi, and L. Hanzo, “When Machine Learning Meets Big Data: A Wireless Communication Perspective”, IEEE Vehicular Communication Magazine, vol. 15, no. 1, pp. 63-72, March 2020 , https://arxiv.org/abs/1901.08329 . 8 / 63

Discussions for Applying Machine Learning in Wireless Communications � Two most successful applications for ML Computer Vision and Natural Language Processing � Why and what are the key differences? Dataset: CV and NLP are data oriented/driven and exist rich dataset Well established mathematical models in wireless communications � Before Problem formulation Can this problem be solved by conventional optimization approach? If yes, what is the key advantages of using machine learning? 9 / 63

Motivation and challenge of AI for NOMA networks � Motivation Conventional optimization based methods break down the problem into isolated resource allocation decisions at each time step without considering the long-term effect Reinforcement learning (RL) addresses sequential decision making via maximizing a numeric reward signal while interacting with the unknown environment Offline Resource Allocation RL provides a long-term solution for stochastic optimization problem through exploration (of unknown environment) and exploitation (of known environment). � Challenges The hidden relationship between history and future information has no concrete mathematical expressions . Resource allocation for massive user and base station (BS) connection has high computational complexity. 10 / 63

Case Study: Cache-Aided NOMA MEC Multiple users are served by User 1 x 1 AP x one MEC server. 2 User 2 MEC server The computation tasks are x - User N u -1 N 1 u capable of being computed Task computation x N results caching storage u locally at the mobile devices NOMA uplink or in the MEC server. User N u Step 1: Task Step 2: Task Step 3: Task computation The computation results are offloading decision computing results caching selectively cached in the é N t ù ù ù = ë é ù ù ù = ë é ù ù ù Z = ë z , z , , , , , z z X x x , , , , , , x x x Y y y , , , , , , , y y y û û û û û û 1 2 N N 1 2 N u N N 1 2 N N N u t t u u u u storage of the MEC server. Fig.: An illustration of a multi-user cache-aided MEC. [1] Z. Yang, Y. Liu , Y. Chen, N. Al-Dhahir, “Cache-Aided NOMA Mobile Edge Computing: A Reinforcement Learning Approach”, IEEE Transactions on Wireless Communications , https://arxiv.org/abs/1906.08812 . 11 / 63

System Model: Communication Model The user with higher channel gain is decoded first, the signal-to-interference-plus-noise ratio (SINR) for user i at time t can be given by     ρ i ( t ) | h i ( t ) | 2     R i ( t ) = B log 2 1 + (1) ,   N up �  ρ l ( t ) | h l ( t ) | 2 + σ 2  l = i + 1 Accordingly, the offloading time for task j with input size π j at time t is π j T offload ( t ) = (2) R i ( t ) . i , j Meanwhile, the transmit energy consumption of offloading at time t is given by π j E offload ( t ) = ρ i (3) R i ( t ) . i , j 12 / 63

System Model: Computation Model Local Computing: The computing time T loc i , j and energy consumption E loc i , j for task j with computational requirement ω j are i , j = ω j T loc (4) . ω loc : the local computing ω loc i i capability, ω j E loc i , j = P loc . (5) P loc : the energy consumption i ω loc i i per second. MEC Computing: The computing time T mec ( t ) and energy i , j consumption E mec ( t ) are i , j y i : the proportion of the ω j T mec ( t ) = (6) . computing resources allocated i , j y i ( t ) C MEC from the MEC server, ω j E mec ( t ) = P mec . (7) P mec : the energy consumption i , j y i ( t ) C MEC per second at MEC server. 13 / 63