Two-Level Scheduling Algorithms for Deep Neural Network Inference in Vehicular Networks

计算机科学 调度(生产过程) 能源消耗 推论 算法 火车 实时计算 人工智能 数学优化 工程类 数学 电气工程 地图学 地理
作者
Yalan Wu,Jigang Wu,Mianyang Yao,Bosheng Liu,Long Chen,Siew-Kei Lam
出处
期刊:IEEE Transactions on Intelligent Transportation Systems [Institute of Electrical and Electronics Engineers]
卷期号:24 (9): 9324-9343 被引量:6
标识
DOI:10.1109/tits.2023.3266795
摘要

In vehicular networks, task scheduling at the microarchitecture-level and network-level offers tremendous potential to improve the quality of computing services for deep neural network (DNN) inference. However, existing task scheduling works only focus on either one of the two levels, which results in inefficient utilization of computing resources. This paper aims to fill this gap by formulating a two-level scheduling problem for DNN inference tasks in a vehicular network, with an objective of minimizing total weighted sum of response time and energy consumption for all tasks under the following constraints: per task response time, per vehicle energy consumption, per vehicle storage capacity. We first formulate the problem and prove that it is NP-hard. A group transformation based algorithm, called GTA, is proposed. GTA makes scheduling decisions at the network-level using the group transformation based approach, and at the microarchitecture-level using a greedy strategy. In addition, an algorithm, denoted as DRL, is proposed to decrease total weighted sum of response time and energy consumption for all tasks. DRL trains two models with deep reinforcement learning to achieve two-level scheduling. The proposed algorithms are evaluated on a platform consisting of a desktop, Raspberry Pi, Eyeriss, OSM, SUMO, NS-3. Simulation results show that DRL outperforms the state-of-the-art methods for all cases, while the proposed GTA outperforms the state-of-the-art methods for most cases, in terms of total weighted sum of response time and energy consumption. Compared with four baseline algorithms, GTA and DRL reduce the total weighted sum of response time and energy consumption by 41.49% and 62.38%, on average respectively, for different numbers of tasks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
lobster发布了新的文献求助10
刚刚
亓音完成签到 ,获得积分10
刚刚
junjie完成签到,获得积分10
1秒前
2秒前
dongger完成签到,获得积分10
3秒前
陈向洋发布了新的文献求助30
3秒前
陈向洋发布了新的文献求助10
3秒前
852的应助被范范范采纳,获得10
4秒前
4秒前
seapowerseries完成签到,获得积分10
5秒前
华仔的应助被wg采纳,获得10
5秒前
7秒前
祁林林完成签到,获得积分20
7秒前
wiliiam完成签到,获得积分10
7秒前
7秒前
喜悦翰完成签到,获得积分10
7秒前
7秒前
ke发布了新的文献求助10
8秒前
8秒前
小二郎的应助被开心德地采纳,获得10
8秒前
高大颜演发布了新的文献求助10
8秒前
asadman_W完成签到,获得积分10
8秒前
9秒前
汉堡包的应助被小斻也斻采纳,获得10
10秒前
啥也不会完成签到,获得积分10
11秒前
科研通AI65的应助被从容问柳采纳,获得10
11秒前
11秒前
12秒前
李佳完成签到,获得积分10
13秒前
13秒前
纯情的天思完成签到,获得积分20
13秒前
amiee发布了新的文献求助10
13秒前
asadman_W发布了新的文献求助10
14秒前
14秒前
14秒前
Ll完成签到,获得积分10
15秒前
Agoni发布了新的文献求助10
15秒前
长情可乐发布了新的文献求助10
15秒前
15秒前
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188885
求助须知:如何正确求助?哪些是违规求助? 9576442
关于积分的说明 21847777
捐赠科研通 7786897
什么是DOI,文献DOI怎么找? 3435446
关于科研通互助平台的介绍 2559654
邀请新用户注册赠送积分活动 2482383