A scalable architecture for concurrent online auctions

Abstract

SUMMARY Online auction systems are characterised by a number of functional and performance management requirements, caused by the potentially very large numbers of distributed concurrent bidders, as well as by the auction rules. Such systems are typically implemented as three tier, thread‐based architectures, whose performance does not scale up well with an increase in the number of concurrent bidders. Nor such systems can take advantage of new Cloud based environments. In this paper, we propose an architectural framework for online auctions developed on top of a soft real‐time platform (Open Telecom Platform) using a concurrent language (Erlang) and an embedded Web server (Yaws). The proposed framework can scale up to hundreds of thousands of concurrent users while its performance can benefit from multicore and symmetric multiprocessing computer architectures. We demonstrate the capabilities of the framework by developing prototypes for two auction types known as ‘unique bid’ and ‘penny’, analyse their performance characteristics and compare them with that of existing auction systems. Copyright © 2013 John Wiley & Sons, Ltd.