Abstract Transmission Control Protocol TCP is no doubt most widely used congestion control protocol designed for highly reliable and end-to-end communication over the internet. TCP is not suitable in its standard form for modern and high speed networks. Various TCP variants are solution for this issue. CUBIC is a modern TCP variant designed for high speed and scalable networks. CUBIC is also adopted as default congestion control algorithm in Linux kernel. This survey paper contains a detailed discussion about TCP CUBIC and the directions for further improvements. It describes the CUBIC design architecture with the pseudo code of the algorithm, TCP support in Linux kernel and implementation of CUBIC, Network Simulator 2 and Network Simulator 3 based study of CUBIC along with its class diagram. Finally, the performance of CUBIC is evaluated both in wired and wireless environment under the parameters of goodput and intra-protocol fairness along with TCP NewReno and TCP Compound. The simulation results demonstrate that CUBIC is very suitable for wired and high speed networks but its performance degrades in wireless and low speed networks.

References

[1] A Discrete-Event Network Simulator, ns-3 simulator Tutorial, https://www.nsnam.org/docs/tutorial/html, last Visited, 2016.

[2] Ahmad M., Ngadi A., Nawaz A., Ahmad U., Mustafa T., and Raza A., “A Survey on TCP CUBIC Variant Regarding Performance,” in Proceedings of 15th International Multitopic Conference, Islamabad, pp. 409-412, 2012.

[3] Ahmad N., Shoaib U., and Prinetto P., “Usability of Online Assistance from Semiliterate Users’ Perspective,” International Journal of Human- Computer Interaction, vol. 31, no. 1, pp. 55-64, 2015.

[4] Arianfar S., “TCP’s Congestion Control Implementation in Linux Kernel,” in Proceedings of Seminar on Network Protocols in Operating Systems, pp. 1-6. 2012.

[5] Bisen D. and Sharma D., “Improve Performance of Tcp New Reno over Mobile Ad-Hoc Network Using Abra,” International Journal of Wireless and Mobile Networks, vol. 3, no. 2, pp. 102-111, 2011.

[6] Brakmo L. and Peterson L., “TCP Vegas: End to End Congestion Avoidance on A Global Internet,” IEEE Journal on Selected Areas in Communications, vol. 13, no. 8, pp. 1465-1480, 1995.

[7] Caini C. and Firrincieli R., “TCP Hybla: A TCP Enhancement for Heterogeneous Networks,” International Journal of Satellite Communications and Networking, vol. 22, no. 5, pp. 547-566, 2004.

[8] Casetti C., Gerla M., Mascolo S., Sanadidi M., and Wang R., “TCP Westwood: End-to-End Congestion Control for Wired/Wireless Networks,” Wireless Networks, vol. 8, no. 5, pp. 467-479, 2002.

[9] Floyd S., “High Speed TCP for Large Congestion Windows,” Network Working Group, 2003.

[10] Gharge S. and Valanjoo A., “Simulation Based Performance Evaluation of TCP Variants and Routing Protocols in Mobile Ad-Hoc Networks,” IEEE International Conference on Advances in Engineering and Technology Research, Unnao, pp. 1-8, 2014.

[11] Ha S., Rhee I., and Xu L., “CUBIC: A New TCP- Friendly High-Speed TCP Variant,” ACM SIGOPS Operating Systems Review, vol. 42, no. 5, pp. 64-74, 2008.

[12] Henderson T., Floyd S., Gurtov A., and Nishida Y., “The Newreno Modification to TCP's Fast Recovery Algorithm” Network Working Group, 2012.

[13] Irfan M., Oriat C., and Groz R., “Model Inference and Testing,” Advances in Computers, vol. 89, pp. 89-139, 2013.

[14] Jacobson V., “Berkeley TCP Evolution From 4.3-Tahoe to 4.3-Reno,” in Proceedings of the 18th Internet Engineering Task Force, Vancouver, 1990.

[15] Kozu T., Akiyama Y., and Yamaguchi S., “Improving Rtt Fairness on Cubic Tcp,” in Proceedings of 1st International Symposium on Computing and Networking, Matsuyama, pp. 162-167, 2013.

[16] Kumari D., Tahiliani M., and Shenoy U., “Experimental Analysis of CUBIC TCP in Error Prone Manets,” in Proceedings of 5th International Conference on the Applications of Digital Information and Web Technologies, Bangalore, pp. 256-261, 2014.

[17] Liaqat M., Chang V., Gani A., Hamid H., Toseef M., Shoaib U., and Ali R., “Federated Cloud Resource Management: Review and Discussion,” Journal of Network and Computer Applications, vol. 77, pp. 87-105, 2017.

[18] Liu S., Başar T., and Srikant R., “TCP-Illinois: A Loss-And Delay-Based Congestion Control Algorithm for High-Speed Networks,” Performance Evaluation, vol. 65, no. 6, pp. 417- 440, 2008.

[19] Monowar M., Rahman O., Pathan A., and Hong C., “Prioritized Heterogeneous Traffic-Oriented Congestion Control Protocol for Wsns,” The International Arab Journal of Information Technology, vol. 9, no. 1, pp. 39-48, 2012.

[20] Prinetto P., Shoaib U., and Tiotto G., “The Italian Sign Language Sign Bank: Using Wordnet for Sign Language Corpus Creation,” in Proceedings of International Conference on Communications and Information Technology, Aqaba, pp. 134- 137, 2011.

[21] Rahman A., Sarfraz S., Shoaib U., Abbas G., and Sattar M., “Cloud based E-Learning, Security Threats and Security Measures,” Indian Journal of Science and Technology, vol. 9, no. 48, 2016.

[22] Riley G., and Henderson T., “The Ns-3 Network Simulator,” in Proceedings of Modeling and Tools for Network Simulation, Berlin, pp. 15-34, 2010.

[23] Šošić M. and Stojanović V., “Resolving Poor TCP Performance on High-Speed Long Distance Links-Overview and Comparison of BIC, CUBIC and Hybla,” in Proceedings of IEEE 11th A Comprehensive Study of Modern and High Speed TCP-Variant in Linux Kernel: TCP CUBIC 1035 International Symposium on Intelligent Systems and Informatics, Subotica, pp. 26-28, 2013.

[24] Tan K., Song J., Zhang Q., and Sridharan M., “A Compound TCP Approach For High-Speed and Long Distance Networks,” in Proceedings of IEEE INFOCOM 25th IEEE International Conference on Computer Communications, Barcelona, 2006.

[25] Wang Z. and Crowcroft J., “Eliminating Periodic Packet Losses in the 4.3-Tahoe BSD TCP Congestion Control Algorithm,” ACM SIGCOMM Computer Communication Review, vol. 22, no. 2, pp. 9-16, 1992.

[26] Wei D., Jin C., Low S., and Hegde S., “FAST TCP: Motivation, Architecture, Algorithms, Performance,” IEEE/ACM Transactions on Networking, vol. 14, no. 6, pp. 1246-1259, 2006.

[27] Xu L., Harfoush K., and Rhee I., “Binary Increase Congestion Control For Fast Long- Distance Networks,” in Proceedings of IEEE INFOCOM 23rd Annual Joint Conference on Computer and Communications Societies, Hong Kong, pp. 2514-2524, 2004. Abrar Khan received his master degree in Information Technology from University of the Punjab, Gujranwala Campus and M.Phil (IT) from University of Gujrat, Pakistan. His research interests include TCP variants, cloud computing and big data analysis. Umar Shoaib did his PhD in Department of Computer and Control Engineering Politecnico di Torino, Italy. His current research interests include Machine Learning, Robotics, Artificial Intelligence, Scalable Networks, Cloud Computing, Natural Language Processing, Text mining and Internet of Things. Muhammad Sarfraz received his Ph.D in Remote Sensing & GIS from Asian Institute of Technology, Thailand. He is Associate Professor at University of Gujrat, Pakistan. He is members of numerous international societies like Telecoms Sans Frontiers for emergency response in Asia-Pacific, ISPRS Health and Geological Society of America. His research interests include Remote sensing, Geospatial analysis, Scalable networks and Digital image processing.