We give a simple algorithm for the MINIMUM DIRECT-ED MULTICUT problem, and show that it gives an-approximation. This improves on the previous approximation guarantee of ��of Cheriyan, Karloff and Rabani [1], which was obtained by a more sophisticated algorithm. 1

This work addresses a files allocation problem (FAP) in distributed computing systems. This FAP attempts to minimize the expected data transfer time for a specific program that must access several data files from non-perfect computer sites. We assume that communication capacity can be reserved; hence, the data transmission behavior is modeled as a many-to-one multi-commodity flow problem. A new critical-cut method is proposed to solve this reduced multi-commodity flow problem. Based on this method, two algorithms which use branch-and-bound are proposed for this FAP. The proposed algorithms are able to allocate data files having single copies or multiple replicated copies. Simulation results are presented to demonstrate the performance of the algorithms.