Abstract
The constrained application protocol (CoAP) is an application layer protocol in IoT, with underlying support for congestion control mechanism. It minimizes the frequent retransmissions, but does not optimize the throughput or adapt dynamic conditions. However, designing an efficient congestion control mechanism over the IoT poses new challenges because of its resource constraint nature. In this context, this article presents a new Intelligent congestion control algorithm (iCoCoA) for constraint devices, motivated by the success of the deep reinforcement learning in various applications. The iCoCoA learns from the various network features to decide the best Retransmission Timeout to mitigate the congestion in the dynamic environments. It also optimizes the throughput, energy, and unnecessary frequent retransmissions compared with the existing models. iCoCoA is developed and tested on the Cooja simulator and compared it with the standard protocols such as CoAP, CoCoA, and CoCoA+ in continuous and burst traffic conditions. The proposed iCoCoA mitigates congestion, outperforms 4–15% in throughput, 3–10% better packet delivery ratio, and 7–16% energy-efficiency with reduced number of retransmissions.
Similar content being viewed by others
Data availability statement
All data generated or analysed during this study are generated randomly during the simulation. The details about data generation is included in this article.
References
Agyemang JO, Kponyo JJ, Gadze JD, Nunoo-Mensah H, Yu D (2022) Lightweight messaging protocol for internet of things devices. Technologies 10(1):21
Aimtongkham P, Horkaew P, So-In C (2021) An enhanced CoAP scheme using fuzzy logic with adaptive timeout for IoT congestion control. IEEE Access 9:58967–58981
Akpakwu GA, Hancke GP, Abu-Mahfouz AM (2020) CACC: context-aware congestion control approach for lightweight CoAP/UDP-based internet of things traffic. Trans Emerg Telecommun Technol 31(2):e3822
Betzler A, Gomez C, Demirkol I, Paradells J (2013) Congestion control in reliable CoAP communication. In: Proceedings of the 16th ACM International Conference on Modeling, analysis & simulation of wireless and mobile systems. ACM, pp 365–372
Betzler A, Gomez C, Demirkol I, Paradells J (2015) CoCoA+: an advanced congestion control mechanism for CoAP. Ad Hoc Netw 33:126–139
Betzler A, Gomez C, Demirkol I, Paradells J (2016a) CoAP congestion control for the Internet of Things. IEEE Commun Mag 54(7):154–160
Betzler A, Isern J, Gomez C, Demirkol I, Paradells J (2016b) Experimental evaluation of congestion control for CoAP communications without end-to-end reliability. Ad Hoc Nets 52:183–194
Bolettieri S, Tanganelli G, Vallati C, Mingozzi E (2018) pCoCoA: a precise congestion control algorithm for CoAP. Ad Hoc Netw 80:116–129
Bormann C, Castellani AP, Shelby Z (2012) CoAP: an application protocol for billions of tiny internet nodes. IEEE Internet Comput 2:62–67
Demir AK, Abut F (2020) mlCoCoA: a machine learning-based congestion control for CoAP. Turk J Electr Eng Comput sci 28(5):1–20
Donta PK, Amgoth T, Annavarapu CSR (2020) Congestion-aware data acquisition with q-learning for wireless sensor networks. In: 2020 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS). IEEE, pp 1–6
Donta PK, Amgoth T, Annavarapu CSR (2021) An extended aco-based mobile sink path determination in wireless sensor networks. J Ambient Intell Humaniz Comput 12(10):8991–9006
Donta PK, Srirama SN, Amgoth T, Annavarapu CSR (2022) Survey on recent advances in iot application layer protocols and machine learning scope for research directions. Digit Commun Netw 8(5):727–744
HoBfeld T, Skorin-Kapov L, Heegaard PE, Varela M (2017) Definition of QoE fairness in shared systems. IEEE Commun Lett 21(1):184–187
Jamshed MA, Ali K, Abbasi QH, Imran MA, Ur-Rehman M (2022) Challenges, applications and future of wireless sensors in internet of things: a review. IEEE Sens J 22(6):5482–5494
Jay N, Rotman N, Godfrey B, Schapira M, Tamar A (2019) A deep reinforcement learning perspective on internet congestion control. In: International Conference on machine learning, pp 3050–3059
Kaur N, Sood SK (2017) An energy-efficient architecture for the internet of things. IEEE Syst J 11(2):796–805
Kim M, Lee S, Khan MTR, Seo J, Bae Y, Jeong Y, Kim D (2019) A new CoAP congestion control scheme using message loss feedback for IoUT. In: Proceedings of the 34th ACM/SIGAPP Symposium on applied computing. SAC ’19. ACM, pp 2385–2390
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Lippmann R (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4(2):4–22
Mahajan N, Chauhan A, Kumar H, Kaushal S, Sangaiah AK (2022) A deep learning approach to detection and mitigation of distributed denial of service attacks in high availability intelligent transport systems. Mob Netw Appl 20:1–21
Martinez B, Monton M, Vilajosana I, Prades JD (2015) The power of models: Modeling power consumption for IoT devices. IEEE Sens J 15(10):5777–5789
Mišić J, Ali MZ, Mišić VB (2018) Architecture for IoT domain with CoAP observe feature. IEEE Internet Things J 5(2):1196–1205
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529
Nie X, Zhao Y, Li Z, Chen G, Sui K, Zhang J, Ye Z, Pei D (2019) Dynamic TCP initial windows and congestion control schemes through reinforcement learning. IEEE J Sel Areas Commun 37(6):1231–1247
Praveen Kumar D, Tarachand A, Rao ACS (2019) Machine learning algorithms for wireless sensor networks: a survey. Inf Fusion 49:1–25
Rathod V, Jeppu N, Sastry S, Singala S, Tahiliani MP (2019) CoCoA++: delay gradient based congestion control for Internet of Things. Future Gener Comput Syst 100:1053–1072
Salkuti SR (2018) Congestion management using optimal transmission switching. IEEE Syst J 12(4):3555–3564
Sandell M, Raza U (2019) Application layer coding for IoT: benefits, limitations, and implementation aspects. IEEE Syst J 13(1):554–561
Sangaiah AK, Ramamoorthi JS, Rodrigues JJ, Rahman MA, Muhammad G, Alrashoud M (2020) LACCVoV: linear adaptive congestion control with optimization of data dissemination model in vehicle-to-vehicle communication. IEEE Trans Intell Transp Syst 22(8):5319–5328
Sargent M, Allman M, Paxson V (2011) Computing TCP’s retransmission timer. Computing
Sun X, Ansari N (2018) Traffic load balancing among brokers at the IoT application layer. IEEE Trans Netw Serv Manag 15(1):489–502
Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT Press
Suwannapong C, Khunboa C (2019) Congestion control in CoAP observe group communication. Sensors 19(15):3433
Suwannapong C, Khunboa C (2021) EnCoCo-RED: enhanced congestion control mechanism for CoAP observe group communication. Ad Hoc Netw 112:102377
Uroz D, Rodríguez RJ (2022) Characterization and evaluation of IoT protocols for data exfiltration. IEEE Internet of Things J 9(19):19062–19072
Xiao K, Mao S, Tugnait JK (2019) TCP-Drinc: smart congestion control based on deep reinforcement learning. IEEE Access 7:11892–11904
Yadav RK, Singh N, Piyush P (2020) Genetic CoCoA++: genetic algorithm based congestion control in CoAP. In: 2020 4th International Conference on intelligent computing and control systems (ICICCS). IEEE, pp 808–813
Zhang S, You X, Zhang P, Huang M, Li S (2022) A UCB-based dynamic CoAP mode selection algorithm in distribution IoT. Alex Eng J 61(1):719–727
Acknowledgements
This work was supported by the Archimedes Foundation under the Dora plus Grant 11-15/OO/11476 and SERB, India, through grant CRG/2021/003888. We also thank financial support to UoH-IoE by MHRD, India (F11/9/2019-U3(A)).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no potential conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Donta, P.K., Srirama, S.N., Amgoth, T. et al. iCoCoA: intelligent congestion control algorithm for CoAP using deep reinforcement learning. J Ambient Intell Human Comput 14, 2951–2966 (2023). https://doi.org/10.1007/s12652-023-04534-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-023-04534-8