A good Star Student Project strategy is to find a balance to selectively store appropriate data sets and regenerate the rest when needed; however, current approaches are not highly cost-effective. A minimum cost benchmarking approach for data sets storage has been developed, which can (theoretically) achieve the best tradeoff between computation and storage in the cloud [30]; however, this approach is impractical for runtime storage strategy due to high computation complexity. In Star Student Project, toward achieving the minimum cost benchmark in a practical manner, we propose a novel local optimization- based runtime strategy for storing the generated application data sets in the cloud.
https://www.blogger.com/blogger.g?blogID=4435256300017036823#allposts