基于带宽匹配的软件定义数据中心网络流量节能调度方案

doi:10.12305/j.issn.1001-506X.2024.11.32

摘要/Abstract

摘要：

针对数据中心网络的流调度优化问题, 选用经典的Fat-Tree拓扑结构, 利用软件定义网络集中控制的优势, 提出一种基于带宽匹配的节能路由算法(energy efficient routing algorithm, EERA)。EERA首先对需要传输的数据流按照其截止时间进行排序, 然后对拓扑中的链路权值按照每个排序后的数据流需要传输的数据量进行更新, 删除可用带宽不满足传输数据量的链路, 得到新的拓扑图。在重新定义的拓扑图中, EERA计算源节点和目标节点之间所有可用链路, 从这些可用链路中选取与流传输数据量所需带宽最匹配的链路进行路由。仿真实验表明, 在不增加额外存储开销的前提下, EERA为即将到来的数据流预留了足够的带宽, 减少了网络链路拥塞, 在节省网络能耗的同时实现了网络负载均衡。

关键词: 数据中心网络, 软件定义网络, 流量调度, 负载均衡, 节能路由

Abstract:

To solve the traffic scheduling optimization problem in the data center networks, an energy efficient routing algorithm (EERA) is proposed based on bandwidth matching in the software defined data center networks, and takes the advantage of the software defined network centralized control using classic Fat-Tree topology. EERA sorts the traffic according to their deadlines and traffic sizes and updates the link weights in the topology for each sorted traffic according to the amount of data. Then EERA deletes the links whose available bandwidth does not meet the amount of transmitting data and gets a new topology. In the redefined topology, EERA calculates all the available links between the source node and the target node, then selectes the optimal links from these available links that match the bandwidth required by traffic transmitting. Simulation results show that EERA reserves enough bandwidth for incoming traffic with no additional storage overhead, and reduces the network congestion. At the same time, EERA saves the network energy consumption and achieves the network load balancing.

Key words: data center network, software defined network, traffic scheduling, load balancing, energy efficient routing

中图分类号:

TN92

张朝辉, 周嘉琦. 基于带宽匹配的软件定义数据中心网络流量节能调度方案[J]. 系统工程与电子技术, 2024, 46(11): 3901-3911.

Zhaohui ZHANG, Jiaqi ZHOU. Traffic energy efficient scheduling scheme based on bandwidth matching in software defined data center networks[J]. Systems Engineering and Electronics, 2024, 46(11): 3901-3911.

图/表 7

图1

表1

图2

图3

表2

图4

图5

参考文献 46

1	JIANG C W , TSENG C L , WANG Y Z , et al. Optimal pricing strategy for data center considering demand response and renewable energy source accommodation[J]. Journal of Modern Power Systems and Clean Energy, 2023, 11 (1): 345- 354. doi: 10.35833/MPCE.2021.000130
2	XU G , DAI B , HUANG B X , et al. Bandwidth-aware energy efficient flow scheduling with SDN in data center networks[J]. Future Generation Computer Systems, 2017, 68, 163- 174. doi: 10.1016/j.future.2016.08.024
3	左青云, 陈鸣, 王秀磊, 等. 一种基于SDN的在线流量异常检测方法[J]. 西安电子科技大学学报, 2015, 42 (1): 155- 160. doi: 10.3969/j.issn.1001-2400.2015.01.32
	ZUO Q Y , CHEN M , WANG X L , et al. Online traffic anomaly detection method for SDN[J]. Journal of Xidian University, 2015, 42 (1): 155- 160. doi: 10.3969/j.issn.1001-2400.2015.01.32
4	杜鑫乐, 徐恪, 李彤, 等. 数据中心网络的流量控制: 研究现状与趋势[J]. 计算机学报, 2021, 44 (7): 1287- 1309.
	DU X L , XU K , LI T , et al. Traffic control for data center network: state of the art and future research[J]. Chinese Journal of Computers, 2021, 44 (7): 1287- 1309.
5	ALASMAR M , PARISIS G , CROWCROFT J . SCDP: systematic rateless coding for efficient data transport in data centers[J]. IEEE/ACM Trans. on Networking, 2021, 29 (6): 2723- 2736. doi: 10.1109/TNET.2021.3098386
6	LUO S X , YU H F , LI K , et al. Efficient file dissemination in data center networks with priority-based adaptive multicast[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (6): 1161- 1175. doi: 10.1109/JSAC.2020.2986616
7	WANG L , ZHANG F , AROCA J A , et al. GreenDCN: a general framework for achieving energy efficiency in data center networks[J]. IEEE Journal on Selected Areas in Communications, 2013, 32 (1): 4- 15.
8	LI D , YU Y R , HE W , et al. Willow: saving data center network energy for network-limited flows[J]. IEEE Trans. on Pa-rallel and Distributed Systems, 2014, 26 (9): 2610- 2620.
9	YAO Z, WANG Y, BA J H, et al. Deadline-aware and energy-efficient dynamic flow scheduling in data center network[C]//Proc. of the 13th International Conference on Network and Ser-vice Management, 2017.
10	CUI Y , XIAO S H , WANG X , et al. Performance-aware energy optimization on mobile devices in cellular network[J]. IEEE Trans. on Mobile Computing, 2016, 16 (4): 1073- 1089.
11	CHKIRBENE Z , GOUISSEM A , HADJIDJ R , et al. Efficient techniques for energy saving in data center networks[J]. Computer Communications, 2018, 129, 111- 124. doi: 10.1016/j.comcom.2018.07.025
12	GUO Z H , XU Y , LIU Y F , et al. AggreFlow: achieving power efficiency, load balancing, and quality of service in data center networks[J]. IEEE/ACM Trans. on Networking, 2020, 29 (1): 17- 33.
13	HUANG J W , LYU W J , LI W H , et al. Mitigating packet reordering for random packet spraying in data center networks[J]. IEEE/ACM Trans. on Networking, 2021, 29 (3): 1183- 1196. doi: 10.1109/TNET.2021.3056601
14	CHENG Y Y , JIA X H . NAMP: network-aware multipathing in software-defined data center networks[J]. IEEE/ACM Trans. on Networking, 2020, 28 (2): 846- 859. doi: 10.1109/TNET.2020.2971587
15	WANG F , YAO H P , ZHANG Q , et al. Dynamic distributed multi-path aided load balancing for optical data center networks[J]. IEEE Trans. on Network and Service Management, 2021, 19 (2): 991- 1005.
16	WU Z R , DENG Y H , FENG H , et al. Blender: a container placement strategy by leveraging Zipf-like distribution within containerized data centers[J]. IEEE Trans. on Network and Service Management, 2021, 19 (2): 1382- 1398.
17	DESMOUCEAUX Y , ENGUEHARD M , CLAUSEN T H . Joint monitorless load-balancing and autoscaling for zero-wait-time in data centers[J]. IEEE Trans. on Network and Service Management, 2020, 18 (1): 672- 686.
18	崔子熙, 胡宇翔, 兰巨龙, 等. 基于流分类的数据中心网络负载均衡机制[J]. 电子学报, 2021, 49 (3): 559.
	CUI Z X , HU Y X , LAN J L , et al. Load balancing based on flow classification for datacenter network[J]. Acta Electonica Sinica, 2021, 49 (3): 559.
19	赵君, 马中, 刘驰, 等. 一种多目标蚁群优化的虚拟机放置算法[J]. 西安电子科技大学学报, 2015, 42 (3): 173- 178.
	ZHAO J , MA Z , LIU C , et al. Multi-objective ant colony optimization algorithm for virtual machine placement[J]. Journal of Xidian University, 2015, 42 (3): 173- 178.
20	FENG H , DENG Y H , ZHOU Y , et al. Towards heat-recirculation-aware virtual machine placement in data centers[J]. IEEE Trans. on Network and Service Management, 2021, 19 (1): 256- 270.
21	AYOUB O , DE SOUSA A , MENDIETA S , et al. Online virtual machine evacuation for disaster resilience in inter-data center networks[J]. IEEE Trans. on Network and Service Ma-nagement, 2021, 18 (2): 1990- 2001. doi: 10.1109/TNSM.2021.3056766
22	LI B Y , CHENG B , LIU X , et al. Joint resource optimization and delay-aware virtual network function migration in data center networks[J]. IEEE Trans. on Network and Service Management, 2021, 18 (3): 2960- 2974. doi: 10.1109/TNSM.2021.3067883
23	ZU J C , HU G Y , PENG D Y , et al. Fair scheduling and rate control for service function chain in NFV enabled data center[J]. IEEE Trans. on Network and Service Management, 2021, 18 (3): 2975- 2986. doi: 10.1109/TNSM.2021.3070331
24	ALIZADEH M, GREENBERG A, MALT D A, et al. Data center TCP (DCTCP)[C]//Proc. of the ACM SIGCOMM 2010 Conference, 2010: 63-74.
25	ALIZADEH M, KABBANI A, EDSALL T, et al. Less is more: trading a little bandwidth for ultra-low latency in the data center[C]//Proc. of the 9th USENIX Symposium on Networked Systems Design and Implementation, 2012: 253-266.
26	CHENG P, REN F, SHU R, et al. Catch the whole lot in an action: rapid precise packet loss notification in data center[C]//Proc. of the 11th USENIX Symposium on Networked Systems Design and Implementation, 2014: 17-28.
27	PERRY J, OUSTERHOUT A, BALAKRISHNAN H, et al. Fastpass: a centralized "zero-queue" datacenter network[C]//Proc. of the ACM Conference on SIGCOMM, 2014: 307-318.
28	CHO I, JANG K, HAN D. Credit-scheduled delay-dounded congestion control for datacenters[C]//Proc. of the Conference of the ACM Special Interest Group on Data Communication, 2017: 239-252.
29	LI Y, MIAO R, LIU H H, et al. HPCC: high precision congestion control[C]//Proc. of the ACM Special Interest Group on Data Communication, 2019: 44-58.
30	ZHANG T , HUANG J W , CHEN K , et al. Rethinking fast and friendly transport in data center networks[J]. IEEE/ACM Trans. on Networking, 2020, 28 (5): 2364- 2377. doi: 10.1109/TNET.2020.3012556
31	ABDELMONIEM A M , BENSAOU B . T-RACKs: a faster recovery mechanism for TCP in data center networks[J]. IEEE/ACM Trans. on Networking, 2021, 29 (3): 1074- 1087. doi: 10.1109/TNET.2021.3059913
32	ZOU S J , HUANG J W , WANG J X , et al. Flow-aware adaptive pacing to mitigate TCP incast in data center networks[J]. IEEE/ACM Trans. on Networking, 2020, 29 (1): 134- 147.
33	陆一飞, 朱书宏. 数据中心网络下基于SDN的TCP拥塞控制机制研究与实现[J]. 计算机学报, 2017, 40 (9): 2167- 2180.
	LU Y F , ZHU S H . Research and implementation of TCP congestion control mechanism based on SDN in data center network[J]. Chinese Journal of Computers, 2017, 40 (9): 2167- 2180.
34	郭秉礼, 赵宁, 朱志文, 等. 数据中心中面向光互联的流量识别与调度研究[J]. 通信学报, 2018, 39 (9): 122- 128.
	GUO B L , ZHAO N , ZHU Z W , et al. Research on traffic identification and scheduling based on optical interconnection architecture in data center[J]. Journal on Communications, 2018, 39 (9): 122- 128.
35	LIU G Y , GUO S T , XIAO B , et al. SDN-based traffic matrix estimation in data center networks through large size flow identification[J]. IEEE Trans. on Cloud Computing, 2019, 10 (1): 675- 690.
36	YU A , YANG H , NGUYEN K K , et al. Burst traffic scheduling for hybrid E/O switching DCN: an error feedback spiking neural network approach[J]. IEEE Trans. on Network and Service Management, 2020, 18 (1): 882- 893.
37	LIU W X , LU J J , CAI J , et al. DRL-PLink: deep reinforcement learning with private link approach for mix-flow scheduling in software-defined data-center networks[J]. IEEE Trans. on Network and Service Management, 2021, 19 (2): 1049- 1064.
38	ZHOU X , WANG R H , WEN Y G , et al. Joint IT-facility optimization for green data centers via deep reinforcement learning[J]. IEEE Network, 2021, 35 (6): 255- 262. doi: 10.1109/MNET.011.2100101
39	JIANG Y A , KODIALAM M , LAKSHMAN T V , et al. Resource allocation in data centers using fast reinforcement learning algorithms[J]. IEEE Trans. on Network and Service Ma-nagement, 2021, 18 (4): 4576- 4588. doi: 10.1109/TNSM.2021.3100460
40	WANG Y , LI Y T , WANG T , et al. Towards an energy-efficient data center network based on deep reinforcement learning[J]. Computer Networks, 2022, 210, 108939. doi: 10.1016/j.comnet.2022.108939
41	鲁垚光, 王兴伟, 李福亮, 等. 软件定义网络中的动态负载均衡与节能机制[J]. 计算机学报, 2020, 43 (10): 1969- 1982.
	LU Y G , WANG X W , LI F L , et al. Dynamic load balancing and energy saving mechanism in software defined network[J]. Chinese Journal of Computers, 2020, 43 (10): 1969- 1982.
42	BIANZINO A P , CHAUDET C , ROSSI D , et al. A survey of green networking research[J]. IEEE Communications Surveys & Tutorials, 2010, 14 (1): 3- 20.
43	BAGAA M , DUTRA D L C , TALEB T , et al. On SDN-driven network optimization and QoS aware routing using multiple paths[J]. IEEE Trans. on Wireless Communications, 2020, 19 (7): 470- 4714.
44	SHAUKAT M , ALASMARY W , ALANAZI E , et al. Balanced energy-aware and fault-tolerant data center scheduling[J]. Sensors, 2022, 22 (4): 1482. doi: 10.3390/s22041482
45	HE Q , WANG Y , WANG X W , et al. Routing optimization with deep reinforcement learning in knowledge defined networking[J]. IEEE Trans. on Mobile Computing, 2023, 23 (2): 1444- 1455.
46	LI Y , JIAN S J , HSIEH S Y , et al. A weighted optimal sche-duling scheme for congestion control in cloud data center networks[J]. IEEE Trans. on Services Computing, 2023, 16 (4): 2402- 2410.

参数	含义	数值
e₁	交换机休眠状态固定能耗/J	240
e₂	交换机开启状态固定能耗/J	310
e₃	交换机端口满载状态能耗/J	4
e₄	交换机端口空载状态能耗/J	2
C	DCNs链路容量/Mbps	100

算法	f_N₁=100		f_N₁=200		f_N₁=300		f_N₁=400		f_N₁=500
算法	交换机	端口	交换机	端口	交换机	端口	交换机	端口	交换机	端口
HPR	96.92	3.08	96.09	3.91	96.02	3.98	96.08	3.92	96.00	4.00
SPF	96.77	3.23	96.02	3.98	95.95	4.05	95.95	4.05	95.89	4.11
ECMP	96.87	3.13	96.13	3.87	95.94	4.06	95.91	4.09	95.90	4.10
EERA	98.47	1.53	97.88	2.12	97.34	2.66	97.08	2.92	96.82	3.18
EAFT	98.38	1.62	97.62	2.38	97.10	2.90	96.90	3.10	96.60	3.40

[1]	张驰, 陈全, 唐祖平, 魏蛟龙. 基于最小路由代价的巨型星座网络接入策略[J]. 系统工程与电子技术, 2024, 46(5): 1792-1800.
[2]	韩驰, 熊伟, 于荣欢, 刘亚丽, 付婧雨. 基于跳数背压策略的低轨卫星网络负载均衡路由[J]. 系统工程与电子技术, 2024, 46(10): 3557-3566.
[3]	朱宇昂, 赵亚丽, 赫佳峦, 张晨光, 吴朝军, 贾晓晓. 基于分布式SDN的机动通信系统拓扑发现方法[J]. 系统工程与电子技术, 2024, 46(1): 357-365.
[4]	闵晓飞, 李靖, 张朝辉. SDN驱动的网络流量负载均衡路由优化算法[J]. 系统工程与电子技术, 2023, 45(8): 2578-2587.
[5]	邬磊, 刘琚, 高智超, 董郑, 许宏吉. 基于时间敏感软件定义网络的工业互联网时延优化方案[J]. 系统工程与电子技术, 2023, 45(6): 1836-1846.
[6]	赵文文, 孟相如, 康巧燕, 阳勇. 一种域间效能优先的二阶段控制器均衡部署策略[J]. 系统工程与电子技术, 2023, 45(12): 4052-4063.
[7]	程一凡, 洪涛, 丁晓进, 张更新. 低轨卫星物联网场景下基于吸引子选择算法的多星负载均衡算法[J]. 系统工程与电子技术, 2022, 44(4): 1354-1363.
[8]	姚玉坤, 任丽丹, 任智, 冯鑫, 杜文正. MSC中基于SDN的拓扑感知RLNC重传方案[J]. 系统工程与电子技术, 2022, 44(4): 1393-1400.
[9]	陈坤, 吕娜, 朱海峰, 方宇. 基于定时的航空集群机载网络更新方法[J]. 系统工程与电子技术, 2021, 43(9): 2642-2648.
[10]	石晓东, 李勇军, 赵尚弘, 王蔚龙, 王星宇. 基于SDN的卫星网络多QoS目标优化路由算法[J]. 系统工程与电子技术, 2020, 42(6): 1395-1401.
[11]	冉金鹏, 赵尚弘, 王翔, 高航航. 面向SDN的生存性虚拟网络映射算法[J]. 系统工程与电子技术, 2020, 42(5): 1182-1189.
[12]	吕娜, 潘武, 陈柯帆, 刘创. 基于选举的SDN机载网络控制器故障恢复机制[J]. 系统工程与电子技术, 2020, 42(11): 2581-2590.
[13]	吕娜, 邹鑫清, 陈柯帆, 朱海峰. 面向软件定义航空集群机载网络的更新策略[J]. 系统工程与电子技术, 2020, 42(1): 206-216.
[14]	谢浩, 郭爱煌, 宋春林, 焦润泽. LTE-V下基于深度强化学习的基站选择算法[J]. 系统工程与电子技术, 2019, 41(7): 1652-1657.
[15]	吕娜, 曹芳波, 陈柯帆, 刘创, 高维廷. 软件定义航空集群机载网络自适应邻居探测方法[J]. 系统工程与电子技术, 2019, 41(10): 2260-2270.