面向用户需求的空天地一体化车载网络任务分配策略

doi:10.12305/j.issn.1001-506X.2022.05.35

摘要/Abstract

摘要：

为了提高空天地一体化车载网络(space-air-ground integrated vehicular networks, SAGVN)内用户的网络服务质量体验, 解决不同网络间相互协同的问题, 提出了面向用户需求的SAGVN任务分配策略。基于用户信号强度、时延、网络费用和带宽需求, 利用效用函数理论和层次分析法(analytic hierarchy process, AHP), 构建用户需求和满意度描述框架。将网络任务分配过程抽象为半马尔可夫决策过程(semi Markov decision process, SMDP), 根据用户需求和网络状态, 利用价值迭代算法获得整体用户满意度最大的网络任务分配策略, 利用Q-learning算法得到近似最优策略。实验表明, 相较于传统策略, 所提策略整体用户满意度提高超过30%;在网络拥塞的环境下, 可以有效降低对网络服务需求迫切用户服务请求的拒绝率。

关键词: 空天地一体化车载网络, 无线网络管理, 半马尔可夫决策过程, 用户需求, Q-learning算法

Abstract:

To improve the user network service quality experience in space-air-ground integrated vehicular networks (SAGVN) and solve the problem of collaboration among different networks, a task allocation strategy for SAGVN oriented on user demand is proposed. Based on the user demand of signal strength, delay, network cost and bandwidth, the utility function theory and analytic hierarchy process (AHP) are used to construct the description framework of user demand and satisfaction. The network task allocation process is abstracted as semi Markov decision process (SMDP). According to the user demand and network states, the value iteration algorithm is used to obtain the network task allocation strategy to maximize the overall user satisfaction andthe approximate optimal strategy is obtained by Q-learning algorithm. Experimental results show that compared with the traditional strategy, the overall user satisfaction of the proposed strategy is improved by more than 30%; inthe network congestion environment, it can greatly reduce the rejection rate of the users with urgent network service demand.

Key words: space-air-ground integrated vehicular networks (SAGVN), wireless network management, semi Markov decision process (SMDP), user demand, Q-learning algorithm

中图分类号:

TN92

谭诗翰, 金凤林, 顿聪颖. 面向用户需求的空天地一体化车载网络任务分配策略[J]. 系统工程与电子技术, 2022, 44(5): 1717-1727.

Shihan TAN, Fenglin JIN, Congying DUN. Task assignment strategy for space-air-ground integrated vehicular networks oriented to user demand[J]. Systems Engineering and Electronics, 2022, 44(5): 1717-1727.

图/表 11

图1

图2

图3

表1

表2

图4

图5

图6

图7

表3

图8

参考文献 30

1	CHENG N , LYU F , CHEN J Y , et al. Big data driven vehicular networks[J]. IEEE Network, 2018, 32 (6): 160- 167. doi: 10.1109/MNET.2018.1700460
2	LU N , CHENG N , ZHANG N , et al. Connected vehicles: solutions and challenges[J]. IEEE Internet of Things Journal, 2014, 1 (4): 289- 299. doi: 10.1109/JIOT.2014.2327587
3	AL-SULTAN S , AL-DOORI M M , AL-BAYATTI A H , et al. A comprehensive survey on vehicular Ad Hoc network[J]. Journal of Network and Computer Applications, 2014, 37, 380- 392. doi: 10.1016/j.jnca.2013.02.036
4	MASEGOSA R M , GOZALVEZ J . LTE-V for sidelink 5G V2X vehicular communications: a new 5G technology for short-range vehicle-to-everything communications[J]. IEEE Vehicular Technology Magazine, 2017, 12 (4): 30- 39. doi: 10.1109/MVT.2017.2752798
5	3GPP. Study on scenarios and requirements for next generation access technologies, technical specification group radio access network, (Release 14), TR 38.913[R]. Technical Spectfication Group Rodio Access Network, 2016.
6	LIANG L , YE H , LI G Y . Spectrum sharing in vehicular networks based on multi-agent reinforcement learning[J]. IEEE Journal on Selected Areas in Communications, 2019, 37 (10): 2282- 2292. doi: 10.1109/JSAC.2019.2933962
7	LIU J J , SHI Y P , FADLULLAH Z M , et al. Space-air-ground integrated network: a survey[J]. IEEE Communications Surveys & Tutorials, 2018, 20 (4): 2714- 2741.
8	ZHANG N , ZHANG S , YANG P , et al. Software defined space-air-ground integrated vehicular networks, challenges and solutions[J]. IEEE Communications Magazine, 2017, 55 (7): 101- 109. doi: 10.1109/MCOM.2017.1601156
9	EL HELOU M , IBRAHIM M , LAHOU S , et al. A network-assisted approach for RAT selection in heterogeneous cellular networks[J]. IEEE Journal on Selected Areas in Communications, 2015, 33 (6): 1055- 1067. doi: 10.1109/JSAC.2015.2416987
10	XIE J L , GAO W J , LI C R . Heterogeneous network selection optimization algorithm based on a Markov decision model[J]. China Communications, 2020, 17 (2): 40- 53. doi: 10.23919/JCC.2020.02.004
11	CHENG N , QUAN W , SHI W S , et al. A comprehensive simu-lation platform for space-air-ground integrated network[J]. IEEE Wireless Communications, 2020, 27 (1): 178- 185. doi: 10.1109/MWC.001.1900072
12	KATO N , FADLULLAH Z M , TANG F X , et al. Optimizing space-air-ground integrated networks by artificial intelligence[J]. IEEE Wireless Communications, 2019, 26 (4): 140- 147. doi: 10.1109/MWC.2018.1800365
13	WU H Q , CHEN J Y , ZHOU C H , et al. Resource management in space-air-ground integrated vehicular networks: SDN control and AI algorithm design[J]. IEEE Wireless Communications, 2020, 27 (6): 52- 60. doi: 10.1109/MWC.001.2000130
14	ZHOU S , WANG G C , ZHANG S , et al. Bidirectional mission offloading for agile space-air-ground integrated networks[J]. IEEE Wireless Communications, 2019, 26 (2): 38- 45. doi: 10.1109/MWC.2019.1800290
15	ALBUQUERQUE M, AYYAGARI A, DORSETT M A, et al. Global information grid (GIG) edge network interface architecture[C]//Proc. of the IEEE Military Comunications Confer-ence, 2007: 4455139.
16	HAMDI M , BOUDRIGA N , OBAIDAT M S . Bandwidth-effective design of a satellite-based hybrid wireless sensor network for mobile target detection and tracking[J]. IEEE Systems, 2008, 2 (1): 74- 82. doi: 10.1109/JSYST.2007.916049
17	BLUMENTHAL S H. Medium earth orbit Ka band satellite communications system[C]//Proc. of the IEEE Military Comunications Conference, 2013: 273-277.
18	XIE J , XIAO S , LIAN Y G , et al. A throughput-aware joint vehicle route and access network selection approach based on SMDP[J]. China Communications, 2020, 17 (5): 243- 265. doi: 10.23919/JCC.2020.05.019
19	GAO Z B , WEN B , HUANG L F , et al. Q-learning-based power control for LTE enterprise femtocell networks[J]. IEEE Systems Journal, 2017, 11 (4): 2699- 2707.
20	GOYAL R K, KAUSHAL S. Network selection using AHP for fast moving vehicles in heterogeneous networks[M]//CHAKI R, CORTESI A, SAEEDK, et al, ed. Advances in Intelligent Systems and Computing. New Delhi: Springer, 2015, 395: 235-243.
21	JIANG D D , HUO L W , LV Z H , et al. A joint multi-criteria utility-based network selection approach for vehicle-to-infrastructure networking[J]. IEEE Trans.on Intelligent Transportation Systems, 2018, 19 (10): 3305- 3319. doi: 10.1109/TITS.2017.2778939
22	TANG T, WU W L, DENG Y N, et al. Access network selection algorithm in heterogeneous multi-cognitive wireless networks coexistence nvironment[C]//Proc. of the International Conference on Logistics Engineering, Management and Computer Science, 2015: 1266-1271.
23	OSBORNE M J . An introduction to game theory[M]. Oxford: Oxford University Press, 2004.
24	YE Y Y . The simplex and policy-iteration methods are strongly polynomial for the Markov decision problem with a fixed discount rate[J]. Mathematics of Operations Research, 2011, 36 (4): 593- 603. doi: 10.1287/moor.1110.0516
25	DHIA I B, BOUHTOU M, EN-NAJJARY T, et al. Dynamic access point selection and resource allocation in multi-technology wireless network[C]//Proc. of the IEEE Wireless Communications and Networking Conferenc, 2019: 8885438.
26	DI B Y , ZHANG H L , SONG L Y , et al. Ultra-dense LEO: integrating terrestrial-satellite networks into 5G and beyond for data offloading[J]. IEEE Trans.on Wireless Communications, 2019, 18 (1): 47- 62. doi: 10.1109/TWC.2018.2875980
27	ZHANG Z J , ZHANG W Y , TSENG F H , et al. Satellite mobile edge computing: improving QoS of high-speed satellite-terrestrial networks using edge computing techniques[J]. IEEE Network, 2019, 33 (1): 70- 76. doi: 10.1109/MNET.2018.1800172
28	ABDERRAHIM W , AMIN O , ALOUINI M , et al. Latency-aware offloading in integrated satellite terrestrial networks[J]. IEEE Open Journal of the Communications Society, 2020, 1 (1): 490- 500.
29	SHAHID S M , SEYOUM Y T , WON S H , et al. Load balanc-ing for 5G integrated satellite-terrestrial networks[J]. IEEE Access, 2020, 8, 132144- 132156. doi: 10.1109/ACCESS.2020.3010059
30	SHWETHA A, SANKAR P. Queue management scheme to control congestion in a vehicular based sensor network[C]//Proc. of the 2nd International Conference on Inventive Systems and Control, 2018: 917-921.

参量	任务类别
参量	NRT	RT	DS
b_max/(Mb/s)	5	4	2
b_min/(Mb/s)	0.2	0.2	0.2
τ_max/ms	500	500	100
λ_l/s^-1	1/3	1/3	1/2
μ_l/min^-1	1/3	1/3	1/2

参量	网段
参量	地面	空中	空间
通信节点数	4	3	1
B_j	20 MHz	10 MHz	L-波段
M_j	150	50	250
时延/ms	100	200	500
费用	0.5	1	1.5

服务类别	参数设置
服务类别	初始参数	对比参数1	对比参数2
NRT	5	2	3
RT	5	5	4
DS	5	8	8