車輛網(wǎng)絡多平臺卸載智能資源分配算法

王汝言; 梁穎杰; 崔亞平

doi:10.11999/JEIT190074

車輛網(wǎng)絡多平臺卸載智能資源分配算法

doi: 10.11999/JEIT190074 cstr: 32379.14.JEIT190074

1.
重慶郵電大學通信與信息工程學院重慶 400065
2.
重慶高校市級光通信與網(wǎng)絡重點實驗室重慶 400065
3.
泛在感知與互聯(lián)重慶市重點實驗室重慶 400065

基金項目: 國家自然科學基金(61801065, 61771082, 61871062)，重慶市高校創(chuàng)新團隊建設計劃(CXTDX201601020)

詳細信息

作者簡介:
王汝言：男，1969年生，教授，主要研究方向為泛在網(wǎng)絡、多媒體信息處理等

梁穎杰：女，1994年生，碩士生，研究方向為車聯(lián)網(wǎng)、移動邊緣計算

崔亞平：男，1986年生，講師，研究方向為毫米波通信、多天線技術、車聯(lián)網(wǎng)等

通訊作者:
梁穎杰　liangyj10111@163.com

中圖分類號: TN919.2
計量
- 文章訪問數(shù): 3064
- HTML全文瀏覽量: 1673
- PDF下載量: 151
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-01-25
- 修回日期: 2019-07-16
- 網(wǎng)絡出版日期: 2019-09-20
- 刊出日期: 2020-01-21

Intelligent Resource Allocation Algorithm for Multi-platform Offloading in Vehicular Networks

1.
School of Communication and Information Engineering, Chongqing University of Posts andTelecommunications, Chongqing 400065, China
2.
Chongqing Key Laboratory of Optical Communication and Networks , Chongqing 400065, China
3.
Chongqing Key Laboratory of Ubiquitous Sensing and Networking, Chongqing 400065, China

Funds: The National Natural Science Foundation of China (61801065, 61771082, 61871062), The Program for Innovation Team Building at Institutions of Higher Education in Chongqing (CXTDX201601020)

摘要

摘要:
為了降低計算任務的時延和系統(tǒng)的成本，移動邊緣計算(MEC)被用于車輛網(wǎng)絡，以進一步改善車輛服務。該文在考慮計算資源的情況下對車輛網(wǎng)絡時延問題進行研究，提出一種多平臺卸載智能資源分配算法，對計算資源進行分配，以提高下一代車輛網(wǎng)絡的性能。該算法首先使用K臨近(KNN)算法對計算任務的卸載平臺(云計算、移動邊緣計算、本地計算)進行選擇，然后在考慮非本地計算資源分配和系統(tǒng)復雜性的情況下，使用強化學習方法，以有效解決使用移動邊緣計算的車輛網(wǎng)絡中的資源分配問題。仿真結(jié)果表明，與任務全部卸載到本地或MEC服務器等基準算法相比，提出的多平臺卸載智能資源分配算法實現(xiàn)了時延成本的顯著降低，平均可節(jié)省系統(tǒng)總成本達80%。
- 車輛網(wǎng)絡 /
- 移動邊緣計算 /
- 資源分配 /
- 強化學習
Abstract:
In order to reduce the delay of computing tasks and the total cost of the system, Mobile Eedge Computing (MEC) technology is applied to vehicular networks to improve further the service quality. The delay problem of vehicular networks is studied with the consideration of computing resources. In order to improve the performance of the next generation vehicular networks, a multi-platform offloading intelligent resource allocation algorithm is proposed to allocate the computing resources. In the proposed algorithm, the K-Nearest Neighbor (KNN) algorithm is used to select the offloading platform (i.e., cloud computing, mobile edge computing, local computing) for computing tasks. For the computing resource allocation problem and system complexity in non-local computing, reinforcement learning is used to solve the optimization problem of resource allocation in vehicular networks using the mobile edge computing technology. Simulation results demonstrate that compared with the baseline algorithms (i.e., all tasks offload to the local or MEC server), the proposed multi-platform offloading intelligent resource allocation algorithm achieves a significant reduction in latency cost, and the average system cost can be saved by 80%.
- Vehicular networks /
- Mobile Edge Computing (MEC) /
- Resource allocation /
- Reinforcement learning

HTML全文

圖 1 網(wǎng)絡模型

下載: 全尺寸圖片幻燈片

圖 2 總成本與距離關系圖

下載: 全尺寸圖片幻燈片

圖 3 總成本與車輛數(shù)關系圖

下載: 全尺寸圖片幻燈片

圖 4 總成本與車輛數(shù)及本地計算能力關系圖

下載: 全尺寸圖片幻燈片

圖 5 總成本與任務數(shù)據(jù)大小關系圖

下載: 全尺寸圖片幻燈片

算法1 多平臺卸載智能資源分配算法
階段1：初始化
(1) 任務${R_i}$的最大延遲${\tau _{{R_i}}}$，任務大小${B_{{R_i}}}$；
(2) 任務的當前位置$P = 1$；
(3) ${{Q}}$矩陣，參數(shù)$\gamma $，獎賞矩陣${{R}}$；
(4) 本地(l)、移動邊緣計算(m)、云計算(c)，各平臺平均延遲${\tau _1},{\tau _2},{\tau _3}$，允許最大任務大小${B_1},{B_2},{B_3}$。
階段2：選擇任務卸載位置
計算(${\tau _{{R_i}}},{B_{{R_i}}}$)和(${\tau _1},{B_1}$)的歐式距離$D$
$D = \sqrt {{{({\tau _{{R_i}}} - {\tau _1})}^2} + {{({B_{{R_i}}} - {B_1})}^2}} ,P = 1$
for j=2, 3 do
計算(${\tau _{{R_i}}},{B_{{R_i}}}$)和(${\tau _j},{B_j}$)的歐式距離${d_j}$
if ${d_j} < D$ then
$D = {d_j},P = j$
end if
end for
if P=1
任務卸載到本地
if P=2 or 3
進行階段3。
階段3：資源分配
if P=3 then
在云計算服務器中計算任務${R_i}$
end if
if P=2 then
for 每次迭代 do
隨機選擇一個狀態(tài)${s_t}$
for 每一步 do
從狀態(tài)${s_t}$的可能動作中隨機選擇動作$a$
執(zhí)行動作$a$，計算獎勵$r$，進入下一狀態(tài)$s'$
計算
$q(s,a) \leftarrow r(s,a) + \gamma \cdot \max [q(s',a')]$
更新狀態(tài)$s \leftarrow s'$
until ${{Q}}$矩陣穩(wěn)定
end for
end for
end if

下載: 導出CSV

參考文獻(17)

WU Dapeng, ZHANG Feng, WANG Honggang, et al. Security-oriented opportunistic data forwarding in mobile social networks[J]. Future Generation Computer Systems, 2018, 87: 803–815. doi: 10.1016/j.future.2017.07.028

LUO Changqing, JI Jinlong, WANG Qianlong, et al. Channel state information prediction for 5G wireless communications: A deep learning approach[J]. IEEE Transactions on Network Science and Engineering, 2018. doi: 10.1109/TNSE.2018.2848960

HUSSAIN R, SON J, EUN H, et al. Rethinking vehicular communications: Merging VANET with cloud computing[C]. The 4th IEEE International Conference on Cloud Computing Technology and Science Proceedings, Taipei, China, 2013: 606–609. doi: 10.1109/CloudCom.2012.6427481.

LI Chunhai, WANG Siming, HUANG Xumin, et al. Parked vehicular computing for energy-efficient Internet of vehicles: A contract theoretic approach[J]. IEEE Internet of Things Journal, 2019, 6(4): 6079–6088. doi: 10.1109/JIOT.2018.2869892

ZHANG Ke, MAO Yuming, LENG Supeng, et al. Optimal delay constrained offloading for vehicular edge computing networks[C]. 2017 IEEE International Conference on Communications, Paris, France, 2017: 1–6. doi: 10.1109/ICC.2017.7997360.

ASHRAF M I, LIU Chenfeng, BENNIS M, et al. Dynamic resource allocation for optimized latency and reliability in vehicular networks[J]. IEEE Access, 2018, 6: 63843–63858. doi: 10.1109/ACCESS.2018.2876548

ZHANG Ke, MAO Yuming, LENG Supeng, et al. Contract-theoretic approach for delay constrained offloading in vehicular edge computing networks[J]. Mobile Networks and Applications, 2019, 24(3): 1003–1014. doi: 10.1007/s11036-018-1032-0

DING Qing, SUN Bo, and ZHNAG Xinming. A traffic-light-aware routing protocol based on street connectivity for urban vehicular Ad Hoc networks[J]. IEEE Communications Letters, 2016, 20(8): 1635–1638. doi: 10.1109/LCOMM.2016.2574708

ZHANG Ke, MAO Yuming, LENG Supeng, et al. Mobile-edge computing for vehicular networks: A promising network paradigm with predictive off-loading[J]. IEEE Vehicular Technology Magazine, 2017, 12(2): 36–44. doi: 10.1109/MVT.2017.2668838

HAN Guangjie, LIU Li, CHAN S, et al. HySense: A hybrid mobile Crowdsensing framework for sensing opportunities compensation under dynamic coverage constraint[J]. IEEE Communications Magazine, 2017, 55(3): 93–99. doi: 10.1109/MCOM.2017.1600658CM

SOOKHAK M, YU F R, HE Ying, et al. Fog vehicular computing: Augmentation of fog computing using vehicular cloud computing[J]. IEEE Vehicular Technology Magazine, 2017, 12(3): 55–64. doi: 10.1109/MVT.2017.2667499

LI Ji, GAO Hui, Lü Tiejun, et al. Deep reinforcement learning based computation offloading and resource allocation for MEC[C]. 2018 IEEE Wireless Communications and Networking Conference, Barcelona, Spain, 2018: 1–6. doi: 10.1109/WCNC.2018.8377343.

HE Ying, ZHAO Nan, and YIN Hongxi. Integrated networking, caching, and computing for connected vehicles: A deep reinforcement learning approach[J]. IEEE Transactions on Vehicular Technology, 2018, 67(1): 44–55. doi: 10.1109/TVT.2017.2760281

LIN Chuncheng, DENG D J, and YAO C C. Resource allocation in vehicular cloud computing systems with heterogeneous vehicles and roadside units[J]. IEEE Internet of Things Journal, 2018, 5(5): 3692–3700. doi: 10.1109/JIOT.2017.2690961

MAO Yuyi, YOU Changsheng, ZHNAG Jun, et al. A survey on mobile edge computing: The communication perspective[J]. IEEE Communications Surveys & Tutorials, 2017, 19(4): 2322–2358. doi: 10.1109/COMST.2017.2745201

ZHAO Pengtao, TIAN Hui, QIN Cheng, et al. Energy-saving offloading by jointly allocating radio and computational resources for mobile edge computing[J]. IEEE Access, 2017, 5: 11255–11268. doi: 10.1109/ACCESS.2017.2710056

ZHANG Ke, MAO Yuming, LENG Supeng, et al. Energy-efficient offloading for mobile edge computing in 5G heterogeneous networks[J]. IEEE Access, 2016, 4: 5896–5907. doi: 10.1109/ACCESS.2016.2597169

施引文獻

資源附件(0)

訪問統(tǒng)計