MPTCP Throughput Enhancement by Q-Learning for Mobile Devices

Mobile devices are able to leverage diverse heterogeneous network paths by Multi-Path Transmission Control Protocol (MPTCP); nevertheless, boosting MPTCP throughput in wireless networks is a real bear. Not only the best path(s) should be selected, but also the optimal congestion control mechanism should be chosen. We investigate the impact of different paths and congestion control for different signal quality states. Consequently, we present the novel MPTCP algorithm augmenting the end user throughput by understating the best policy in different situations by Q-learning. The Results reveal a tremendous effect of switching between the different interfaces and changing the congestion control mechanism on throughput and delay. By and large, the proposed framework achieves 10% more throughput compared to base MPTCP.

[1]  Kaoru Ota,et al.  Smart Technologies for Emergency Response and Disaster Management , 2017 .

[2]  Marcelo Bagnulo,et al.  Opportunistic mobility with multipath TCP , 2011, MobiArch '11.

[3]  Mohammad Javad Shamani,et al.  Signal aware multi-path TCP , 2016, 2016 12th Annual Conference on Wireless On-demand Network Systems and Services (WONS).

[4]  Mehdi Esnaashari,et al.  Data Storages in Wireless Sensor Networks to Deal With Disaster Management , 2019, Emergency and Disaster Management.

[5]  Mark Handley,et al.  TCP Extensions for Multipath Operation with Multiple Addresses , 2020, RFC.

[6]  Behnaz Arzani,et al.  Impact of Path Characteristics and Scheduling Policies on MPTCP Performance , 2014, 2014 28th International Conference on Advanced Information Networking and Applications Workshops.

[7]  Mohammad Javad Shamani,et al.  On the Energy Inefficiency of MPTCP for Mobile Computing , 2016, WWIC.

[8]  Mohsen Guizani,et al.  Proactive Multipath TCP for Seamless Handoff in Heterogeneous Wireless Access Networks , 2016, IEEE Transactions on Wireless Communications.

[9]  Yu Cao,et al.  Delay-based Congestion Control for MPTCP , 2017 .

[10]  Ana Galindo-Serrano,et al.  Distributed Q-Learning for Aggregated Interference Control in Cognitive Radio Networks , 2010, IEEE Transactions on Vehicular Technology.

[11]  Mark Handley,et al.  Coupled Congestion Control for Multipath Transport Protocols , 2011, RFC.

[12]  Ji Zhang,et al.  NSSSD: A new semantic hierarchical storage for sensor data , 2016, 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD).

[13]  Jing Wang,et al.  Automatic text summarization using fuzzy inference , 2016, 2016 22nd International Conference on Automation and Computing (ICAC).

[14]  Hamed Kebriaei,et al.  Learning RAT Selection Game in 5G Heterogeneous Networks , 2016, IEEE Wireless Communications Letters.

[15]  Mohsen Ashourian,et al.  An Improved Node Scheduling Scheme for Resilient Packet Ring Network , 2015 .

[16]  Olivier Bonaventure,et al.  MultiPath TCP: From Theory to Practice , 2011, Networking.

[17]  Weiping Zhu,et al.  A Game Theoretic Framework for Multipath Optimal Data Transfer in Multiuser Overlay Networks , 2008, 2008 IEEE International Conference on Communications.

[18]  Mohammad Javad Shamani,et al.  Multi-Path TCP Incomplete Information Repeated Bayesian Game , 2017, 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall).

[19]  Tao Peng,et al.  Collaborative trajectory privacy preserving scheme in location-based services , 2017, Inf. Sci..

[20]  Mark Handley,et al.  TCP Extensions for Multipath Operation with Multiple Addresses , 2011 .

[21]  Md. Zakirul Alam Bhuiyan,et al.  A Survey on Deep Learning in Big Data , 2017, 22017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC).

[22]  Wei Zhang,et al.  MAPP: A Modular Arithmetic Algorithm for Privacy Preserving in IoT , 2017, 2017 IEEE International Symposium on Parallel and Distributed Processing with Applications and 2017 IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC).

[23]  Mehdi Gheisari,et al.  An Evaluation of Proposed Systems of Sensor Datas Storage in Total Data Parameter , 2012 .

[24]  Miroslav Popovic,et al.  MPTCP Is Not Pareto-Optimal: Performance Issues and a Possible Solution , 2013, IEEE/ACM Transactions on Networking.

[25]  Mehdi Gheisari.  Design, Implementation and Evaluation of SemHD: a New Semantic Hierarchical Sensor Data Storage , 2012 .

[26]  Christoph Paasch,et al.  Improving Multipath TCP , 2014 .

[27]  Mihaela van der Schaar,et al.  Learning to Compete for Resources in Wireless Stochastic Games , 2009, IEEE Transactions on Vehicular Technology.

[28]  Yusheng Ji,et al.  A cross-layer approach for improving WiFi performance , 2014, 2014 International Wireless Communications and Mobile Computing Conference (IWCMC).

[29]  Mehdi Gheisari,et al.  Agent programming with object oriented (C++) , 2017, 2017 Second International Conference on Electrical, Computer and Communication Technologies (ICECCT).

[30]  Mehdi Gheisari,et al.  A Comparison with two semantic sensor data storages in total data transmission , 2014, ArXiv.

[31]  Geyong Min,et al.  Performance Enhancement of Multipath TCP for Wireless Communications With Multiple Radio Interfaces , 2016, IEEE Transactions on Communications.

[32]  Steven H. Low,et al.  Balanced Linked Adaptation Congestion Control Algorithm for MPTCP , 2016 .

[33]  Erich M. Nahum,et al.  How green is multipath TCP for mobile devices? , 2014, AllThingsCellular '14.

[34]  Vern Paxson,et al.  TCP Congestion Control , 1999, RFC.

[35]  Injong Rhee,et al.  CUBIC: a new TCP-friendly high-speed TCP variant , 2008, OPSR.

[36]  Hari Balakrishnan,et al.  WiFi, LTE, or Both?: Measuring Multi-Homed Wireless Internet Performance , 2014, Internet Measurement Conference.

[37]  Husheng Li,et al.  Multi-agent Q-learning of channel selection in multi-user cognitive radio systems: A two by two case , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[38]  Erich M. Nahum,et al.  Cross-layer path management in multi-path transport protocol for mobile devices , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[39]  Mehdi Gheisari,et al.  A Comparison with Some Sensor Network Storages , 2011 .

[40]  Mehdi Bennis,et al.  A Q-learning based approach to interference avoidance in self-organized femtocell networks , 2010, 2010 IEEE Globecom Workshops.

[41]  Mehdi Gheisari,et al.  A Comparison with Two Sensor Data Storagesin Energy , 2011 .