Throughtput Competitive Advance Reservation Using Polynomial Time

Abstract

Abstract:In response to the high throughput needs of grid and cloud computing applications, several production networks have recently started to support advance reservation of dedicated circuits. An important open problem within this context is to devise advance reservation algorithms that can provide provable throughput performance guarantees independently of the specific network topology and arrival pattern of reservation requests. In this paper, we first show that the throughput performance of greedy approaches, which return the earliest possible completion time for each incoming request, can be arbitrarily worse than optimal. Next, we introduce two new online, polynomial-time algorithms for advance reservation, called BATCH ALL and BATCH LIM. Both algorithms are shown to be throughput-optimal through the derivation of delay bounds for bandwidth augmented networks. The BATCH LIM algorithm has the advantage of returning the completion time of a connection immediately as a request is placed, but at the expense of looser delay performance. The propose system called BATCH ALL+ is a simple approach that limits path dispersion, i.e., the newly arrived batch can be combined with the currently running batch if the destination is same, so time consumption is less when compare to BATCH ALL and BATCH LIM.