Routing Optimization Driven by Fuzzy Swarm Intelligence in Software-Defined Sensor Networks
-
摘要: 无线传感器网络由于基础设施建设等固有因素，必须考虑网络资源有限和资源消耗不均匀的问题。基于群智能模糊控制，将模糊控制引入群智能人工蜂群路由协议，解决软件定义传感器网络下的多径路由规划寻优问题。基于无线传感器网络的软件定义网络（Software Defined Networking for Wireless Sensor Networks，SDN-WISE）架构和群智能算法，通过产生人工蜂群模拟蜜蜂采蜜的过程搜索最优链路。人工蜂群对不同数据传输链路进行调整，利用模糊逻辑判断区域状态，并通过生成适应度函数评价出价值最高的数据链路，产生一个优化路由解决方案。实验结果表明，与经典路由算法对比，本文机制采用SDN-WISE在松耦合的软件定义网络架构下，融合人工蜂群的代理自适应能力与模糊控制的容错逻辑，使得优化路由问题求解过程在能量管理、网络利用率、传输时延和数据包传达率上均有明显的优势。Abstract: Due to inherent factors such as infrastructure construction, wireless sensor networks must consider the problem of limited network resources and uneven resource consumption. In this paper, based on swarm intelligence fuzzy control, fuzzy control is introduced into swarm intelligence artificial bee swarm routing protocol to solve the optimization problem of multipath routing planning in software-defined sensor networks. Based on the SDN-WISE software defined network architecture and swarm intelligence algorithm, and the optimal link was searched by generating artificial bees to simulate the process of honey gathering. Artificial bees adjust different data transmission links, judge regional state through fuzzy logic, and evaluate the data link with the highest value by generating fitness function, generating an optimized routing solution. The experimental results show that, compared with the classical routing algorithms is adopted in this method to optimize the routing problem solving process in the framework of loosely coupled software-defined network by integrating the agent adaptive ability of artificial bees and the fault-tolerant logic of fuzzy control. The experimental results show that, It has obvious advantages in residual energy management, network utilization, transmission delay and packet delivery rate.
-
Key words:
- sensor networks /
- software defined /
- artificial bee /
- fuzzy logic /
- routing protocols
-
图 8 节点规模自适应算法性能对比
Figure 8. Comparison of performance of algorithms with adaption node number
图 9 节点数量和通信距离变化下的平均链路长度
Figure 9. Average link length under the change of node number and communication distance
图 10 通信距离自适应算法性能对比
Figure 10. Comparison of performance of algorithms with adaption communication distance
图 11 智能体数量可调性算法性能对比
Figure 11. Comparison of performance of algorithms with tunable swarm size
图 12 智能体数量可调性FABCR性能指标对比
Figure 12. Comparison of performance of FABCR with tunable swarm size
图 13 隶属函数可变性算法性能指标对比
Figure 13. Comparison of performance of algorithms with variable membership function
图 14 隶属函数可变性FABCR性能指标对比
Figure 14. Comparison of performance of FABCR with variable membership function
表 1 SDN流表内容
Table 1. SDN flow table content
Match rule 1 operation Match rule 2 operation Match rule 3 Action Statistic Type Value TTL Counter Sink node=1 && Source node=15 && Current node=6 … Forward Node 1 12 2 Sink node=1 && Source node=20 && Current node=7 Foward Node 2 10 3 Neighbour node=0 || Buffer=10 / / Drop — 8 6 Energy vulnerability<5 Time vulnerability>8 Space vulnerability>20 Set Report 9 3 
下载: 导出CSV
表 2 模糊控制规则库核心内容
Table 2. Core content of the fuzzy control rule base
Rule Energy vulnerability Time vulnerability Space vulnerability Area vulnerability 1 High High High Very High 2 High Low Low Low 3 Low Medium High Medium 4 Low High High High 5 Low Low Low Very low
下载: 导出CSV
表 3 实验参数
Table 3. Experiment parameters
SDN Swarm Intelligence Fuzzy control Parameter Value Parameter Value Parameter Value Number of network nodes 300—800 Swarm size 10 Number of fuzzy rules 27 Network size 100 m*100 m Food source abandonment criteria 50 cycles Fuzzy membership function Triangle-shape SDN Controller position （50，50） Search termination criteria 250 cycles Fuzzy output space partition number 5 SDN Collection packet size 14 Byte Field scale 1 Fuzzy input space partition number 3 Communication range 7—12 m Number of fitness function parameters 3 Fuzzy Inference Systems Mamdani Node initial energy 10 J Dimension of the solution [5,12] Defuzzification method Centroid Data packet size 12 Byte Energy parameter range [0,10] Fuzzy rule connection And Node buffer size 128 Byte Congestion parameter range [0,10] Energy vulnerability range [0,10] Number of data packet 800 Link parameter range [5,12] Time vulnerability range [0,10] Buffer type Drop tail Vulnerable parameter range [0,10] Space vulnerability range [0,50]
下载: 导出CSV
-
[1] JINO RAMSON S R, MONI D J. Applications of wireless sensor networks: A survey[C]//2017 International Conference on Innovations in Electrical, Electronics, Instrumentation and Media Technology (ICEEIMT). 2017: 325-329 [2] MOHAMED R E, SALEH A I, ABDELRAZZAK M, et al. Survey on wireless sensor network applications and energy efficient routing protocols[J]. Wireless Personal Communications, 2018, 101(2): 1019-1055. doi: 10.1007/s11277-018-5747-9 [3] WANG J, GAO Y, LIU W, et al. An improved routing schema with special clustering using PSO algorithm for heterogeneous wireless sensor network[J]. Sensors, 2019, 19(3): 1-17. doi: 10.1109/JSEN.2018.2879242 [4] BONANNI M, CHITI F, FANTACCI R, et al. Dynamic control architecture based on software defined networking for the internet of things[J]. Future Internet, 2021, 13(5): 1-15. [5] NDIAYE M, HANCKE G P, ABU-MAHFOUZ A M. Software defined networking for improved wireless sensor network management: A survey[J]. sensors, 2017, 17(5): 1-32. doi: 10.1109/JSEN.2017.2655998 [6] ALVES R C A, OLIVEIRA D A G, NUNEZ SEGURA G A, et al. The cost of software-defining things: A scalability study of software-defined sensor networks[J]. IEEE Access, 2019, 7: 115093-115108. doi: 10.1109/ACCESS.2019.2936127 [7] BISWAS A, MISHRA K K, TIWARI S, et al. Physics-inspired optimization algorithms: A survey[J]. Journal of Optimization, 2013, 2013: 1-16. [8] MASOOD M, FOUAD M M, SEYEDZADEH S, et al. Energy efficient software defined networking algorithm for wireless sensor networks[J]. Transportation Research Procedia, 2019, 40: 1481-1488. doi: 10.1016/j.trpro.2019.07.205 [9] GALLUCCIO L, MILARDO S, MORABITO G, et al. SDN-WISE: Design, prototyping and experimentation of a stateful SDN solution for wireless sensor networks[C]//2015 IEEE Conference on Computer Communications (INFOCOM). 2015: 513-521 [10] ABDOLMALEKI N, AHMADI M, MALAZI H T, et al. Fuzzy topology discovery protocol for SDN-based wireless sensor networks[J]. Simulation Modelling Practice and Theory, 2017, 79: 54-68. doi: 10.1016/j.simpat.2017.09.004 [11] ZHENG W, LUO D. Routing in wireless sensor network using artificial bee colony algorithm[C]//2014 International Conference on Wireless Communication and Sensor Network. 2014: 280-284 [12] AMIRI E, KESHAVARZ H, ALIZADEH M, et al. Energy efficient routing in wireless sensor networks based on fuzzy ant colony optimization[J]. International Journal of Distributed Sensor Networks, 2014, 10(7): 1-17. [13] RAGAVAN P S, RAMASAMY K. Optimized routing in wireless sensor networks by establishing dynamic topologies based on genetic algorithm[J]. Cluster Computing, 2019, 22(5): 12119-12125. [14] SAMPATHKUMAR A, MULERIKKAL J, SIVARAM M. Glowworm swarm optimization for effectual load balancing and routing strategies in wireless sensor networks[J]. Wireless Networks, 2020, 26(6): 4227-4238. doi: 10.1007/s11276-020-02336-w [15] ZOU Z, QIAN Y. Wireless sensor network routing method based on improved ant colony algorithm[J]. Journal of Ambient Intelligence and Humanized Computing, 2019, 10(3): 991-998. doi: 10.1007/s12652-018-0751-1 [16] GALLUCCIO L, MILARDO S, MORABITO G, et al. Reprogramming wireless sensor networks by using SDN-WISE: A hands-on demo[C]//2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). 2015: 19-20 [17] MOSTAFAEI H, MENTH M. Software-defined wireless sensor networks: A survey[J]. Journal of Network and Computer Applications, 2018, 119: 42-56. doi: 10.1016/j.jnca.2018.06.016 [18] KOBO H I, ABU-MAHFOUZ A M, HANCKE G P. A survey on software-defined wireless sensor networks: Challenges and design requirements[J]. IEEE Access, 2017, 5: 1872-1899. doi: 10.1109/ACCESS.2017.2666200 [19] AKBARI R, HEDAYATZADEH R, ZIARATI K, et al. A multi-objective artificial bee colony algorithm[J]. Swarm and Evolutionary Computation, 2012, 2: 39-52. doi: 10.1016/j.swevo.2011.08.001 [20] KARABOGA D, AKAY B. A comparative study of artificial bee colony algorithm[J]. Applied Mathematics and Computation, 2009, 214(1): 108-132. doi: 10.1016/j.amc.2009.03.090 [21] KARABOGA D, BASTURK B. On the performance of artificial bee colony (ABC) algorithm[J]. Applied Soft Computing, 2008, 8(1): 687-697. doi: 10.1016/j.asoc.2007.05.007 [22] CAI X, DUAN Y, HE Y, et al. Bee-Sensor-C: An energy-efficient and scalable multipath routing protocol for wireless sensor networks[J]. International Journal of Distributed Sensor Networks, 2015, 11(3): 1-14. [23] 宁爱平, 张雪英. 人工蜂群算法的收敛性分析[J]. 控制与决策. 2013, 28(10): 1554-1558. [24] BOHLOULZADEH A, RAJAEI M. A survey on congestion control protocols in wireless sensor networks[J]. International Journal of Wireless Information Networks, 2020, 27(3): 365-384. doi: 10.1007/s10776-020-00479-3 [25] BARADARAN A A, NAVI K. HQCA-WSN: High-quality clustering algorithm and optimal cluster head selection using fuzzy logic in wireless sensor networks[J]. Fuzzy Sets and Systems, 2020, 389: 114-144. doi: 10.1016/j.fss.2019.11.015 [26] DUTT S, AGRAWAL S, VIG R. Delay-sensitive, reliable, energy-efficient, adaptive and mobility-aware (dream) routing protocol for WSNs[J]. Wireless Personal Communications, 2021, 120(2): 1675-1703. doi: 10.1007/s11277-021-08528-7 [27] KAUR T, KUMAR D. MACO-QCR: Multi-objective aco-based qos-aware cross-layer routing protocols in WSN[J]. IEEE Sensors Journal, 2021, 21(5): 6775-6783. doi: 10.1109/JSEN.2020.3038241 [28] AGARKHED J, KADROLLI V, PATIL S. Fuzzy based multi-level multi-constraint multi-path reliable routing in wireless sensor network[J]. International Journal of Information Technology, 2020, 12(4): 1133-1146. doi: 10.1007/s41870-020-00476-y -
点击查看大图
计量
- 文章访问数: 81
- HTML全文浏览量: 108
- PDF下载量: 7
- 被引次数: 0
