Large-Scale Bandwidth and Power Optimization for Multi-Modal Edge Intelligence Autonomous Driving

Li，Xinrao1; Zhang，Tong2; Wang，Shuai3; Zhu，Guangxu4; Wang，Rui1; Chang，Tsung Hui5

2023

10.1109/LWC.2023.3262573

IEEE Wireless Communications Letters   影响因子和分区

2162-2337

2162-2345

Edge intelligence autonomous driving (EIAD) offers computing resources in autonomous vehicles for training deep neural networks. However, wireless channels between the edge server and the autonomous vehicles are time-varying due to the high-mobility of vehicles. Moreover, the required number of training samples for different data modalities, e.g., images, point-clouds, is diverse. Consequently, when collecting these datasets from vehicles to the edge server, the associated bandwidth and power allocation across all data frames is a large-scale multi-modal optimization problem. This article proposes a highly computationally efficient algorithm that directly maximizes the quality of training (QoT). The key ingredients include a data-driven model for quantifying the priority of data modality and two first-order methods termed accelerated gradient projection and dual decomposition for low-complexity resource allocation. Finally, high-fidelity simulations in Car Learning to Act (CARLA) show that the proposed algorithm reduces the perception error by 3% and the computation time by 98%.

Autonomous driving Autonomous vehicles Bandwidth edge intelligence large-scale optimization Optimization Resource management Servers Task analysis Training

SCI ; EI

英语

第一

Guangdong Basic and Applied Basic Research Foundation["2019B1515130003","2021B1515120008","2021B1515120067","2022A1515010109"] ; National Natural Science Foundation of China[62001310]

Computer Science ; Engineering ; Telecommunications

Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications

WOS:001006038300033

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20231413849268

Bandwidth ; Computing power ; Deep neural networks ; Job analysis ; Large dataset ; Resource allocation

Highway Transportation:432 ; Ergonomics and Human Factors Engineering:461.4 ; Information Theory and Signal Processing:716.1 ; Computer Peripheral Equipment:722.2 ; Digital Computers and Systems:722.4 ; Computer Software, Data Handling and Applications:723 ; Data Processing and Image Processing:723.2 ; Robot Applications:731.6 ; Management:912.2

2-s2.0-85151572965

Scopus

1.Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China
2.College of Information Science and Technology, Jinan University, Guangzhou, China
3.Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
4.Shenzhen Research Institute of Big Data, Shenzhen, China
5.School of Science and Engineering, The Chinese University of Hong Kong Shenzhen and Shenzhen Research Institute of Big Data, China

Li，Xinrao,Zhang，Tong,Wang，Shuai,et al. Large-Scale Bandwidth and Power Optimization for Multi-Modal Edge Intelligence Autonomous Driving[J]. IEEE Wireless Communications Letters,2023,PP(99):1-1.

Li，Xinrao,Zhang，Tong,Wang，Shuai,Zhu，Guangxu,Wang，Rui,&Chang，Tsung Hui.(2023).Large-Scale Bandwidth and Power Optimization for Multi-Modal Edge Intelligence Autonomous Driving.IEEE Wireless Communications Letters,PP(99),1-1.

Li，Xinrao,et al."Large-Scale Bandwidth and Power Optimization for Multi-Modal Edge Intelligence Autonomous Driving".IEEE Wireless Communications Letters PP.99(2023):1-1.