A QoE-aware dynamic bandwidth allocation algorithm based on game theory

Quality of Experience (QoE) is a wide concept including user perception, behavior and expectations as well as application and network performances. The Internet of the future should be able to increase the QoE offered to the users, also in relationship with their commercial profiles. This paper presents an innovative approach, based on game theory, which, according to the feedback of QoE, is able to dynamically assign the available bandwidth of a shared technology (e.g. a WLAN, a cell) to the running flows, in order to maximize the QoE of the users and to guarantee fairness. Moreover, flows could be prioritized, according to commercial profiles (e.g., flows for which users pay more must be served with higher quality). The proposed approach is independent of the way the feedback of QoE is computed (it could be given by a direct user quality expression, estimated from the QoS measurements, from the user's behavior, etc.): the only assumption is that the QoE is a non-decreasing continuous function of the bandwidth allocated to the application. Simulations, considering audio flows with different codecs for which the IQX hypothesis (i.e., exponential interdependency of QoE and QoS) holds, show high performances and fairness/prioritization properties.

[1]  Scott Shenker,et al.  Integrated Services in the Internet Architecture : an Overview Status of this Memo , 1994 .

[2]  R. Braden,et al.  Resource reSer Vation Protocol (RSVP) , 1997 .

[3]  Zheng Wang,et al.  An Architecture for Differentiated Services , 1998, RFC.

[4]  David L. Black,et al.  An Architecture for Differentiated Service , 1998 .

[5]  Francesco Delli Priscoli.  Design and implementation of a simple and efficient medium access control for high-speed wireless local area networks , 1999, IEEE J. Sel. Areas Commun..

[6]  Kee Chaing Chua,et al.  A flexible quality of service model for mobile ad-hoc networks , 2000, VTC2000-Spring. 2000 IEEE 51st Vehicular Technology Conference Proceedings (Cat. No.00CH37026).

[7]  Roberto Cusani,et al.  A novel MAC and scheduling strategy to guarantee QoS for-the new-generation WIND-FLEX wireless LAN , 2002, IEEE Wireless Communications.

[8]  Antonio Pietrabissa,et al.  Load-adaptive bandwidth-on-demand protocol for satellite networks , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[9]  Antonio Pietrabissa,et al.  Control-theoretic bandwidth-on-demand protocol for satellite networks , 2002, Proceedings of the International Conference on Control Applications.

[10]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[11]  Edjair de Souza Mota,et al.  An E-model implementation for speech quality evaluation in VoIP systems , 2005, 10th IEEE Symposium on Computers and Communications (ISCC'05).

[12]  Berthold Vöcking,et al.  Fast convergence to Wardrop equilibria by adaptive sampling methods , 2006, STOC '06.

[13]  Jiann-Liang Chen,et al.  QoS management in heterogeneous home networks , 2007, Comput. Networks.

[14]  Johanne Cohen,et al.  Distributed Learning of Wardrop Equilibria , 2008, UC.

[15]  Markus Fiedler,et al.  Testing the IQX Hypothesis for Exponential Interdependency between QoS and QoE of Voice Codecs iLBC and G.711 , 2008 .

[16]  Bo Li,et al.  The disparity between P2P overlays and ISP underlays: issues, existing solutions, and challenges , 2010, IEEE Network.

[17]  Markus Fiedler,et al.  A generic quantitative relationship between quality of experience and quality of service , 2010, IEEE Network.

[18]  Vincenzo Suraci,et al.  Admission Control and Drop strategies in a UPnP-QoS controlled home network , 2010, 21st Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications.

[19]  Vincenzo Suraci,et al.  A Cognitive Future Internet Architecture , 2011, Future Internet Assembly.

[20]  Abdelhamid Mellouk,et al.  Real-Time state-dependent routing based on user perception , 2011, 2011 International Conference on Communications and Information Technology (ICCIT).

[21]  Vincenzo Suraci,et al.  Modelling quality of experience in future internet networks , 2012, 2012 Future Network & Mobile Summit (FutureNetw).

[22]  A. Pietrabissa,et al.  A proactive link-failure resilient routing protocol for MANETs based on reinforcement learning , 2012, 2012 20th Mediterranean Conference on Control & Automation (MED).

[23]  Partha Dutta,et al.  InSite: QoE-aware video delivery from cloud data centers , 2012, 2012 IEEE 20th International Workshop on Quality of Service.

[24]  Antonio Pietrabissa,et al.  A distributed multi-path algorithm for wireless ad-hoc networks based on Wardrop routing , 2013, 21st Mediterranean Conference on Control and Automation.

[25]  Vincenzo Suraci,et al.  A dynamic load balancing algorithm for Quality of Service and mobility management in next generation home networks , 2013, Telecommun. Syst..

[26]  Barry G. Evans,et al.  Designing a QoE aware intelligent home gateway for future smart homes , 2013, 2013 Future Network & Mobile Summit.

[27]  Antonio Pietrabissa,et al.  MQ-Routing: Mobility-, GPS- and energy-aware routing protocol in MANETs for disaster relief scenarios , 2013, Ad Hoc Networks.

[28]  Vincenzo Suraci,et al.  A decentralized load balancing algorithm for heterogeneous wireless access networks , 2014 .

[29]  Andrea Lanna,et al.  Electric Vehicles charging control based on future internet generic enablers , 2014, 2014 IEEE International Electric Vehicle Conference (IEVC).

[30]  Alessandro Di Giorgio,et al.  Electric vehicles charging load reprofiling , 2014, 22nd Mediterranean Conference on Control and Automation.

[31]  Battilotti Stefano,et al.  A multi-agent reinforcement learning based approach to Quality of Experience control in Future Internet networks , 2015, CCC 2015.

[32]  Delli Priscoli Francesco,et al.  Future internet architecture: Control-based perspectives related to Quality of Experience (QoE) management , 2015, 2015 34th Chinese Control Conference (CCC).

[33]  S. Monaco,et al.  A reinforcement learning approach for QoS/QoE model identification , 2015, 2015 34th Chinese Control Conference (CCC).

[34]  Vincenzo Suraci,et al.  A multi-agent reinforcement learning based approach to Quality of Experience control in Future Internet networks , 2015, 2015 34th Chinese Control Conference (CCC).

[35]  Antonio Pietrabissa,et al.  Quality of Experience Provision in the Future Internet , 2016, IEEE Systems Journal.

[36]  Gerard Roca Mallofre.  Resource Reservation Protocol ( RSVP ) , 2022 .