Grant: Discovery Grants Program - Individual
University of Toronto
$43,300.00
Self-evolving and high-performance overlay architectures
EF 2007-08
Résumé
The current Internet faces many fundamental challenges, including the lack of support for emerging applications such as multimedia streaming, the lack of trust and security, and the emergence of mobile and sensor networks at the edge. The Internet has increasingly become a hybrid network, with a myriad of networking technologies connecting mobile devices, sensors, and set-top boxes. In this proposal, we argue that most of such challenges in the current Internet are amenable to the treatment of a new self-evolving, self-healing, and high-performance overlay architecture, that is well designed and responsive to changes at all time scales. Such a new self-evolving overlay is to be implemented in the application layer, without changes to the Internet Protocol (IP) architecture. Specifically, we propose to design a new overlay that bring higher performance, better scalability, better robustness, better immunity to malicious traffic, and more flexibility. This new overlay will serve as the foundation of the new wireless Internet. The new overlay not only takes advantage of the idle upload capacities at the edge computer systems, but also constantly evolves its network topologies to adapt to network dynamics, and to converge to the highest possible performance. To provide better immunity to malicious traffic, we apply principles of machine learning and bayesian networks to design a mesh of filters in the application layer, such that malicious traffic and attacks may be recognized, learned and filtered over time. To accomodate edge heterogeneity, we propose to study new overlay mechanisms to provide seamless integration and optimal resource allocation in a hybrid Internet with mobile and sensor devices. To support a new array of multimedia applications, we construct a set of overlay algorithms specifically tailored to the needs of large-scale multimedia streaming and conferencing. We plan to realize our vision of such a new self-evolving and high-performance overlay with large-scale emulations and a real-world implementation.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
238994-2006
Name nom
Li, Baochun
Department département
Electrical and Computer Engineering
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2007
Competition year année de concours
2006
Award amount
43300
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
334
Committee name en
Commun.,Computers & Components
Committee name fr
Communic.,ordin. et composants
Area of application code
803
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer communications
Area of application fr
Téléinformatique
Research subject code
2508
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Communications networks
Research subject fr
Réseaux de télécommunications
Partie
2
Nb partie
5
Application title
Self-evolving and high-performance overlay architectures
Keyword
NA
Application summary
The current Internet faces many fundamental challenges, including the lack of support for emerging applications such as multimedia streaming, the lack of trust and security, and the emergence of mobile and sensor networks at the edge. The Internet has increasingly become a hybrid network, with a myriad of networking technologies connecting mobile devices, sensors, and set-top boxes. In this proposal, we argue that most of such challenges in the current Internet are amenable to the treatment of a new self-evolving, self-healing, and high-performance overlay architecture, that is well designed and responsive to changes at all time scales. Such a new self-evolving overlay is to be implemented in the application layer, without changes to the Internet Protocol (IP) architecture. Specifically, we propose to design a new overlay that bring higher performance, better scalability, better robustness, better immunity to malicious traffic, and more flexibility. This new overlay will serve as the foundation of the new wireless Internet. The new overlay not only takes advantage of the idle upload capacities at the edge computer systems, but also constantly evolves its network topologies to adapt to network dynamics, and to converge to the highest possible performance. To provide better immunity to malicious traffic, we apply principles of machine learning and bayesian networks to design a mesh of filters in the application layer, such that malicious traffic and attacks may be recognized, learned and filtered over time. To accomodate edge heterogeneity, we propose to study new overlay mechanisms to provide seamless integration and optimal resource allocation in a hybrid Internet with mobile and sensor devices. To support a new array of multimedia applications, we construct a set of overlay algorithms specifically tailored to the needs of large-scale multimedia streaming and conferencing. We plan to realize our vision of such a new self-evolving and high-performance overlay with large-scale emulations and a real-world implementation.