Two UC Berkeley students are working with our research initiatives team this summer on manipulation-resistant mechanisms for cloud computing. They will work with ICSI researchers Eric Friedman and Scott Shenker and UC Berkeley's Ali Ghodsi and Ion Stoica.

In clouds, computing resources or individual machines are allocated to users based on the requirements of the jobs they want to run. Users can manipulate allocations by misreporting their requirements. To combat this, researchers are designing algorithms that are less susceptible to such manipulation. They will also use algorithmic mechanism design and game theory to develop general procedures for converting protocols so that they can't be manipulated. Ali Ghodsi, who has a background in systems, provides constant analysis of the real-world implications of the mechanisms they are exploring. The ultimate goal is to reduce the cost and energy usage of clouds and datacenters.

Alexandros Psomas, one of the students working on this project this summer, just finished his first year as a PhD student in the theory group of the UC Berkeley computer science division. Originally from Greece, he received his bachelor's degree at the Athens University of Economics and Business and his master's in logic and algorithms at the University of Athens. At UC Berkeley, he works with Christos Papadimitriou, an EECS professor and ICSI faculty associate, on issues related to dynamic auctions. In dynamic auctions, bidders constantly change their bids, and the seller must determine items' prices based on the probability of selling them.

Alex is joined by Albert Wu, an undergraduate who just finished his second year as a double major in computer science and economics. In addition to working on this project this summer, he is a teacher's assistant in CS61A, UC Berkeley's introductory computer science course. He is interested in game theory and is considering grad school in a program that will allow him to combine game theory and economics. He is originally from San Jose. This summer is his first time performing research.