mlCoCoA: a machine learning-based congestion control for CoAP

Internet of Things (IoT) is a technological invention that has the potential to impact on how we live and how we work by connecting any device to the Internet. Consequently, a vast amount of novel applications will enhance our lives. Internet Engineering Task Force (IETF) standardized the Constrained Application Protocol (CoAP) to accommodate the application layer and network congestion needs of such IoT networks. CoAP is designed to be very simple where it employs a genuine congestion control (CC) mechanism, named as default CoAP CC leveraging basic binary exponential backoff. Yet efficient, default CoAP CC does not always utilize the network dynamics the best. As a result, CoCoA has been exposed to better utilize the IoT networks. Although CoCoA considers the network dynamics, the RTO calculation of CoCoA is based on constant coefficient values. However, our experiments show that these constant values, in general, do not achieve the best throughput. Inspired by these observations, we propose a new machine learning-based CC mechanism called as mlCoCoA that is a variation of CoCoA. Particularly, mlCoCoA sets retransmission timeout (RTO) estimation parameters of CoCoA adaptively by using a machine learning method. In this study, we applied support vector machines on a self-created dataset to develop new models for improving the throughput of the IoT network with dynamic selection of CoCoA coefficient values. We carried out extensive simulations in Cooja environment coupled with Californium. Our results indicate that compared to the performance of default CoAP CC and CoCoA mechanisms, mlCoCoA has merit in terms of improving the throughput of CoAP applications.

PDF

___

1] Atzori L, Iera A, Morabito G. The internet of things: a survey. Computer Networks 2010; 54 (15): 2787-2805.
[2] Whitmore A, Agarwal A, Da Xu L. The internet of things–a survey of topics and trends. Information Systems Frontiers 2015; 17 (2): 261-274.
[3] Al-Fuqaha A, Guizani M, Mohammadi M, Aledhari M, Ayyash M. Internet of things: a survey on enabling technologies, protocols, and applications. IEEE Communications Surveys & Tutorials 2015; 17 (4): 2347-2376.
[4] Dunkels A, Gronvall B, Voigt T. Contiki - a lightweight and flexible operating system for tiny networked sensors. In: 29th IEEE International Conference on Local Computer Networks; Tampa, FL, USA; 2004. pp. 455-462.
[5] Kovatsch M, Lanter M, Shelby Z. Californium: scalable cloud services for the Internet of things with CoAP. In: IEEE International Conference on the Internet of Things (IoT); Cambridge, MA, USA; 2014. pp. 1-6.
[6] Kovatsch M, Duquennoy S, Dunkels A. A low-power CoAP for Contiki. In: IEEE International Conference on Mobile Ad-Hoc and Sensor Systems; Valencia, Spain; 2011. pp. 855-860.
[7] Pramanik A, Luhach AK, Batra I, Singh U. A systematic survey on congestion mechanisms of CoAP based Internet of things. In: Advanced Informatics for Computing Research; Jalandhar, India; 2017. pp. 306-317.
[8] Vallati C, Righetti F, Tanganelli G, Mingozzi E, Anastasi G. ECOAP: experimental assessment of congestion control strategies for CoAP using the WiSHFUL platform. In: IEEE International Conference on Smart Computing; Sicily, Italy; 2018. pp. 423-428.
[9] Balandina E, Koucheryavy Y, Gurtov A. Computing the retransmission timeout in CoAP. In: Balandin S, Andreev S, Koucheryavy Y(editors). Internet of Things, Smart Spaces, and Next Generation Networking. Lecture Notes in Computer Science, Vol 8121. Berlin, Germany: Springer, 2013, pp. 352-362.
[10] Ludwig R, Sklower K. The Eifel retransmission timer. ACM SIGCOMM Computer Communication Review 2000; 30 (3): 17-27.
[11] Betzler A, Gomez C, Demirkol I, Kovatsch M. Congestion control for CoAP cloud services. In: IEEE Emerging Technology and Factory Automation (ETFA); Barcelona, Spain; 2014. pp. 1-6.
[12] Lim R, Ferrari F, Zimmerling M, Walser C, Sommer P et al. FlockLab: a testbed for distributed, synchronized tracing and profiling of wireless embedded systems. In: International Conference on Information Processing in Sensor Networks, Part of CPSWeek; New York, NY, USA; 2013. pp. 153-165.
13] Bhalerao R, Subramanian SS, Pasquale J. An analysis and improvement of congestion control in the CoAP Internet- of-things protocol. In: IEEE Annual Consumer Communications & Networking Conference (CCNC); Las Vegas, NV, USA; 2016. pp. 889-894.
[14] Lee JJ, Kim KT, Youn HY. Enhancement of congestion control of Constrained Application Protocol/Congestion Control/Advanced for Internet of Things environment. International Journal of Distributed Sensor Networks 2016; 12 (11): 1-13.
[15] Fleury E, Mitton N, Noël T, Adjih C. FIT IoT-LAB: The largest IoT open experimental testbed. ERCIM News 2015; 101 (14): 1-20.
[16] Sarolahti P, Kuznetsov A. Congestion control in Linux TCP. In: USENIX Annual Technical Conference; Berkeley, CA, USA; 2002. pp. 49-62.
[17] Ekstrom H, Ludwig R. The peak-hopper: a new end-to-end retransmission timer for reliable unicast transport. In: IEEE International Conference on Computer Communications; Hong Kong, China; 2004. pp. 2502-2513.
[18] Jarvinen I, Daniel L, Kojo M. Experimental evaluation of alternative congestion control algorithms for constrained application protocol (CoAP). In: IEEE 2nd World Forum on Internet of Things (WF-IoT); Milan, Italy; 2015. pp. 453-458.
[19] Hemminger S. Network emulation with netem. In: 6th Australia’s National Linux Conference; Sydney, Australia; 2005. pp. 18-23.
[20] Hasan HM, Ahmed AI. A comparative analysis for congestion mechanism in CoAP and CoCoA. Engineering and Technology Journal 2018; 36 (8A): 867-877.
[21] Betzler A, Gomez C, Demirkol I, Paradells J. CoAP congestion control for the Internet of things. IEEE Communi- cations Magazine 2016; 54 (7): 154-160.
[22] Betzler A, Gomez C, Demirkol I, Paradells J. CoCoA+: an advanced congestion control mechanism for CoAP. Ad Hoc Networks 2015; 33: 126-139.
[23] Ancillotti E, Bruno R. Comparison of CoAP and CoCoA+ congestion control mechanisms for different IoT appli- cation scenarios. In: IEEE Symposium on Computers and Communications; Heraklion, Crete, Greece; 2017; pp. 1186-1192.
[24] Ancillotti E, Bruno R, Vallati C, Mingozzi E. Design and evaluation of a rate-based congestion control mechanism in CoAP for IoT applications. In: IEEE 19th International Symposium on ”A World of Wireless, Mobile and Multimedia Networks” (WoWMoM); Chanina, Greece; 2018; pp. 14-15.
[25] Bolettieri S, Tanganelli G, Vallati C, Mingozzi E. pCoCoA: a precise congestion control algorithm for CoAP. Ad Hoc Networks 2018; 80: 116-129.
[26] Gheisari S, Tahavori E. CCCLA: a cognitive approach for congestion control in internet of things using a game of learning automata. Computer Communications 2019; 147: 40-49.
[27] Jiao Z, Zhang B, Li C, Mouftah HT. Backpressure-based routing and scheduling protocols for wireless multihop networks: a survey. IEEE Wireless Communications 2016; 23 (1): 102-110. [28] Castellani AP, Rossi M, Zorzi M. Back pressure congestion control for CoAP/6LoWPAN networks. Ad Hoc Networks 2014; 18: 71-84.
[29] Riley GF, Henderson TR. The ns-3 network simulator. In: Wehrle K, Güneş M, Gross J (editors). Modeling and Tools for Network Simulation. Berlin, Germany: Springer, 2010, pp. 15-34.
[30] Demir AK, Abut F. Comparison of CoAP and CoCoA congestion control mechanisms in grid network topologies. Gümüshane University Journal of Natural Sciences 2018; 1: 153-160.
[31] Demir AK, Abut F. Data-Driven modelling and prediction of CoAP throughput in a grid network topology. El-Cezeri Journal of Science and Engineering 2020; 7 (1): 295-303.
[32] Taheri SM, Hesamian G. A generalization of the Wilcoxon signed-rank test and its applications. Statistical Papers 2012; 54: 457-470