paper-with-me

홈 › Papers

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

2022-10-18 · Xinrao Li, Tong Zhang, Shuai Wang, Guangxu Zhu, Rui Wang, Tsung-Hui Chang

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 $98\%$.

📄 PDF Abstract BibTeX arXiv:2210.09659

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingAutonomous Vehicles

Similar Papers 제목 키워드 기반

HammingMesh: A Network Topology for Large-Scale Deep Learning

2022-09-03 · Torsten Hoefler, Tommaso Bonato, Daniele De Sensi, Salvatore Di Girolamo 외

Numerous microarchitectural optimizations unlocked tremendous processing power for deep neural networks that in turn fueled the AI revolution. With the exhaustion of such optimizations, the growth of modern AI is now gat…

Deep LearningScheduling

Synergizing Hyper-accelerated Power Optimization and Wavelength-Dependent QoT-Aware Cross-Layer Design in Next-Generation Multi-Band EONs

2024-11-05 · Farhad Arpanaei, Mahdi Ranjbar Zefreh, Yanchao Jiang, Pierluigi Poggiolini 외

The extension of elastic optical networks (EON) to multi-band transmission (MB-EON) shows promise in enhancing spectral efficiency, throughput, and long-term cost-effectiveness for telecom operators. However, designing M…

Blockingglobal-optimization

Transformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM)

2022-03-29 · HyunWook Park, Minsu Kim, Seongguk Kim, Keunwoo Kim 외

In this article, for the first time, we propose a transformer network-based reinforcement learning (RL) method for power distribution network (PDN) optimization of high bandwidth memory (HBM). The proposed method can pro…

Reinforcement Learning (RL)

Large-Scale Beam Placement and Resource Allocation Design for MEO-Constellation SATCOM

2023-03-11 · Vu Nguyen Ha, Eva Lagunas, Tedros Salih Abdu, Haythem Chaker 외

This paper presents a centralized framework for optimizing the joint design of beam placement, power, and bandwidth allocation in an MEO satellite constellation to fulfill the heterogeneous traffic demands of a large num…

Clustering

A Fast and Effective Large-Scale Two-Sample Test Based on Kernels

2021-10-07 · Hoseung Song, Hao Chen

Kernel two-sample tests have been widely used and the development of efficient methods for high-dimensional large-scale data is gaining more and more attention as we are entering the big data era. However, existing metho…