TCP Performance over Current Cellular Access: A Comprehensive Analysis Eneko Atxutegi 1(B ) , ˚ Ake Arvidsson 2 , Fidel Liberal 1 , Karl-Johan Grinnemo 3 , and Anna Brunstrom 3 1 University of the Basque Country (UPV/EHU), Bilbao, Spain {eneko.atxutegi,fidel.liberal}@ehu.eus 2 Kristianstad University, Kristianstad, Sweden ake.arvidsson@hkr.se 3 Karlstad University, Karlstad, Sweden {karl-johan.grinnemo,anna.brunstrom}@kau.se Abstract. Mobile Internet usage has increased significantly over the last decade and it is expected to grow to almost 4 billion users by 2020. Even after the great effort dedicated to improving the performance, there still exist unresolved questions and problems regarding the interaction between TCP and mobile broadband technologies such as LTE. This chapter presents a thorough investigation of the behavior of distinct TCP implementation under various network conditions in different LTE deploy- ments including to which extent TCP is capable of adapting to the rapid variability of mobile networks under different network loads, with dis- tinct flow types, during start-up phase and in mobile scenarios at different speeds. Loss-based algorithms tend to completely fill the queue, creating huge standing queues and inducing packet losses both under stillness and mobility circumstances. On the other side delay-based variants are capa- ble of limiting the standing queue size and decreasing the amount of pack- ets that are dropped in the eNodeB, but under some circumstances they are not able to reach the maximum capacity. Similarly, under mobility in which the radio conditions are more challenging for TCP, the loss-based TCP implementations offer better throughput and are able to better uti- lize available resources than the delay-based variants do. Finally, CUBIC under highly variable circumstances usually enters congestion avoidance phase prematurely, provoking a slower and longer start-up phase due to the use of Hybrid Slow-Start mechanism. Therefore, CUBIC is unable to efficiently utilize radio resources during shorter transmission sessions. Keywords: TCP adaptability · LTE · Flow size · Slow-Start Mobility 1 Introduction Mobile Internet usage has increased significantly over the last decade, growing almost 18-fold over the past 5 years and more than half a million new mobile devices and connections in 2016 [1]. The following years are expected to be c  The Author(s) 2018 I. Ganchev et al. (Eds.): Autonomous Control for a Reliable Internet of Services, LNCS 10768, pp. 371–400, 2018. https://doi.org/10.1007/978-3-319-90415-3_14