loading...
Fair Overload Handling Using Proof-of-Work Functions
Phoenix, Arizona January 23-January 27
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/SAINT.2006.322006 International Symposium on Appli ...
 This Article 
 
PDF
HTML
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Sebastian Golze, Technische Universität Berlin
Gero Mühl, Technische Universität Berlin
Overload can reduce the overall performance of a computer system up to a point where the whole service might collapse. Thus, for example the load on a server must be controlled to achieve optimal system performance. Doing so some requests from clients must be rejected. We show that we can distinguish four different types of user profiles, why micropayments are no suitable solution and how a Proof-of-Work based system can be used to allocate the rare resources slots to those clients that generate the maximal use out of these requests. We then present the new HashCashLin function we developed in order to overcome the poor adjustment possibilities of the classic HashCash function and how such a Proof-of-Work can be augmented. We describe our Proof-of-Work auction system and finally we show the results obtained by running a simulated model of our system.
Citation:
Sebastian Golze, Gero Mühl, "Fair Overload Handling Using Proof-of-Work Functions," saint, pp.14-21, 2006 International Symposium on Applications and the Internet (SAINT'06), 2006
Usage of this product signifies your acceptance of the Terms of Use.