|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
A reciprocation-based economy for multiple services in P2P grids
If you have a question about this talk, please contact Saar Drimer.
Designers of peer-to-peer grids aim to construct computational grids encompassing thousands of sites. To achieve this scale, the systems cannot rely on trust or off-line negotiations among participants. Moreover, without incentives for donation, there is a danger that free riding will prevail, leading the grid to collapse. Reciprocation-based incentive mechanisms have been proposed to deal with this problem. However, they have only been studied for the case in which a single service – processing power – is shared. In this paper we give a reciprocation-based mechanism for the case when multiple services, such as processing power and data transfers, are shared. In simulations of scenarios in which the services shared are combinations of two different basic services, the mechanism performs very well, even when the cost to peers of donating a service is nearly as large as the utility gained by receiving it.
Mini-bio: Miranda Mowbray is a Technical Contributor at Hewlett-Packard Laboratories, Bristol. She studied political philosophy in the United States before obtaining an MA in Mathematics from Cambridge University and a PhD in Algebra from London University. She co-founded e-mint, the UK Association of Online Community Professionals. Miranda is at present a principal investigator for peer-to-peer technologies at HP Labs.
This talk is part of the Computer Laboratory Security Seminar series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsCU Palestine Society All Faculty of Education Seminars Clinical ID talks
Other talksFurther Thoughts on the Undivided Past Gandhi’s Realism: Means and Ends in Politics: Symposium & Lecture Drug Discovery Today – Inventing new medicines through a complex interplay of diverse scientific disciplines with medicinal chemistry at the core Familial thrombocytopenias with predisposition to leukemia: RUNX1 targets Performance Data Recorders Identifiability conditions for partially-observed Markov chains