Load Balancing Strategy for Data Center Networks Based on SDN
(1.College of Computer Science and Technology, Qingdao University, Qingdao 266071, China; 2.Qingdao Academy of Transportation Sciences, Qingdao 266000, China)
Abstract
Aiming at the problems of current load balancing algorithms in dealing with traffic in data center networks, such as lack of global perspective and dynamic adaptability, dynamic changes of path state, and too complicated calculation, a load balancing strategy is proposed based on the idea of separation of control and forwarding proposed by SDN. The strategy distinguishes between large and small flows. Large flows use the perception ability of SDN to calculate the path set with the fewest hops between the source host and the destination host and the load of the path set. The fuzzy inference algorithm is used to calculate the score of each path, and the flow table is issued to guide the forwarding of data packets on the path with the highest score. Small flows are forwarded according to the forwarding principle of Equal-Cost Multi-Path. The experimental results show that in the Fat-Tree topology, the network throughput and link utilization are improved compared with ECMP and Hedera.
Keywords
data center network; SDN; load balancing; fuzzy logic
References
- [1] AL-FARES M,LOUKISSAS A,VAHDAT A. A Scalable, Commodity Data Center Network Architecture [J].ACM SIGCOMM Computer Communication Review,2008,38(4):63-74.
- [2] MCKEOWN N,ANDERSON T,BALAKRISHNAN H,et al. OpenFlow: Enabling Innovation in Campus Networks [J].ACM SIGCOMM Computer Communication Review,2008,38(2):69-74.
- [3] NEGHABI A A,NAVIMIPOUR N J,HOSSEINZADEH M,et al. Load Balancing Mechanisms in the Software Defined Networks: A Systematic and Comprehensive Review of the Literature [J].IEEE Access,2018,6:14159-14178.
- [4] CHOU L D,YANG Y T,HONG Y M,et al. A Genetic-based Load Balancing Algorithm in Openflow Network [C]// Advanced Technologies, Embedded and Multimedia for Human-centric Computing: HumanCom and EMC 2013. Dordrecht:Springer,2014:411-417.
- [5] AL-FARES M,RADHAKRISHNAN S,RAGHAVAN B,et al. Hedera: Dynamic Flow Scheduling for Data Center Networks [C]//7th USENIX Symposium on Networked Systems Design and Implementation.San Jose:USENIX Association,2010:281-296.
- [6] CURTIS A R,MOGUL J C,TOURRILHES J,et al.DevoFlow: Scaling Flow Management for High-performance Networks [C]//Proceedings of the ACM SIGCOMM 2011 Conference.Toronto:ACM,2011:254-265.
- [7] Peng Daqin, Lai Xiangwu, Liu Yanlin Multi path routing algorithm for fat tree data center network based on SDN [J]. Computer Engineering, 2018, 44 (4): 41-45+65
- [8] Fu Yinghui, Liu Biguo, and Shu Yong'an Research on Multi Path Load Balancing Algorithm for Fat Tree Data Center Network Based on SDN [J]. Computer Applications and Software, 2017, 34 (9): 147-152
- [9] Cai Yueping, Wang Changping Software Defined Data Center Network Hybrid Routing Mechanism [J]. Journal of Communications, 2016, 37 (4): 44-52
- [10] Wang Lingjiao, Li Wen, Guo Hua Research on Load Balancing of Data Center Network Traffic Based on SDN [J]. Journal of Yunnan University: Natural Science Edition, 2024, 46 (1): 45-52
- [11] Yang Yaozhong, Liu Baojun, Duan Hongjie, etc SDN based data center traffic load balancing [J]. Computer Applications and Software, 2022, 39 (11): 130-135+147
- [12] MITTAL K,JAIN A,VAISLA K S,et al. A Comprehensive Review on Type 2 Fuzzy Logic Applications: Past, Present and Future [J].Engineering Applications of Artificial Intelligence,2020,95:103916.
- [13] Yang Xu Research on Congestion Control Strategies for Software Defined Data Center Networks [D]. Beijing: Beijing University of Posts and Telecommunications, 2021
- [14] Du Qin, Cui Xin, Chen Xiangxiao, etc Research on Load Balancing of Data Centers Based on Fuzzy Discrete Particle Swarm Optimization [J]. Journal of Shandong University of Technology: Natural Science Edition, 2024, 38 (5): 61-68
- [15] Zuo Qingyun, Chen Ming, Zhao Guangsong, etc Research on SDN Technology Based on OpenFlow [J]. Journal of Software, 2013, 24 (5): 1078-1097
- [16] ASLAN M,MATRAWY A. On the Impact of Network State Collection on the Performance of SDN Applications [J].IEEE Communications Letters,2015,20(1):5-8.
- [17] BENSON T,ANAND A,AKELLA A,et al. Understanding Data Center Traffic Characteristics [J].ACM SIGCOMM Computer Communication Review,2010,40(1):92-99.
- [18] Wang Feiyue, Mo Hong Some Basic Issues on Type-2 Fuzzy Sets [J]. Journal of Automation, 2017, 43 (7): 1114-1114
- [19] Wu Dongrui, Zeng Zhigang, Mo Hong, etc Interval Type-2 Fuzzy Sets and Fuzzy Systems: Overview and Prospects [J]. Journal of Automation, 2020, 46 (8): 1539-1556
- [20] Chen Yang, Wang Tao Interval Type-2 Fuzzy Set Centroid Calculation Based on Weighted Karnik Mendel Algorithm [J]. Fuzzy Systems and Mathematics, 2020, 34 (3): 98-110
- [21] Li Long, Fu Binzhang, Chen Mingyu, etc Nimble: A Fast Flow Scheduling Strategy for OpenFlow Networks [J]. Journal of Computer Science, 2015, 38 (5): 1056-1068
- [22] Du Xinle, Xu Ke, Li Tong, etc Traffic Control in Data Center Networks: Research Status and Trends [J]. Journal of Computer Science, 2021, 44 (7): 1287-1309
Funding
Collaborative Education Project of the Ministry of Education - Reform Practice of SDN based Network Principles Course Design (220705841293829), Key Project of Higher Education Reform in Shandong Province (Z2023238), Key Technology Research and Application Demonstration of Spinning Full Process Intelligent Control Management System in Qingdao City (22-3-2-qljh-8-gx)
About the authors
Dan Kai (1997-), male, Han ethnicity, from Weihai, Shandong, currently pursuing a master's degree in software defined networks; Corresponding author: Yun Hongyan (1971-), female, Han ethnicity, from Yumen, Gansu Province, professor, senior member of CFF (33877S), PhD, research direction: computer networks, semantic web and ontology engineering, big data integration applications; Liu Tiantian (1998-), female, Han ethnicity, from Qingdao, Shandong, is currently pursuing a master's degree in software defined networks.