Fereydoon Safai

Self-Adaptive SLA-Driven Capacity Management for Internet Services

This work considers the problem of hosting multiple third-party Internet services in a cost-effective manner so as to maximize a providers business objective. For this purpose, we present a dynamic capacity management framework based on an optimization model, which links a cost model based on SLA contracts with an analytical queuing-based performance model, in an attempt to adapt the platform to changing capacity needs in real time. In addition, we propose a two-level SLA specification for different operation modes, namely, normal and surge, which allows for per-use service accounting with respect to requirements of throughput and tail distribution response time. The cost model proposed is based on penalties, incurred by the provider due to SLA violation, and rewards, received when the service level expectations are exceeded. Finally, we evaluate approximations for predicting the performance of the hosted services under two different scheduling disciplines, namely FCFS and processor sharing. Through simulation, we assess the effectiveness of the proposed approach as well as the level of accuracy resulting from the performance model approximations

Implementing Setup Optimization on the Shop Floor

We develop a model and solution algorithm for sequencing production on a flexible assembly line. The model incorporates the practical considerations of printed circuit board PCB assembly where the goal is to reduce the time spent in setup. We discuss the practical implementation problems of integrating optimization software on the shop floor-both from an operations research and systems perspective. We describe Hewlett-Packards successful use of the software and the limitations of production sequencing in PCB assembly.

Dynamic modeling and forecasting on enterprise revenue with derived granularities

Timely and accurate forecasts are crucial in decision-making processes and have significant impacts on many business aspects. We at HP Labs have developed a complete set of quantitative forecasting methods that can enable the establishment of a reliable predictive reporting system, so that executives can discern as early as possible where the company is heading financially. This paper reports some of our technical developments in building such a predictive reporting system.