Reducing Service Cost Based on the Skewness of Data Popularity for Cloud Storage Systems

Reducing service cost has been a popular topic in recent studies on cloud storage systems. One of the basic techniques is to power down parts of service nodes. However, it will reduce the availability of data objects, which is the overriding concern of users. So we mathematically formulate the problem to close maximum service nodes under the constraint of a given high availability. According to our analysis, this problem is NP complete. In practical systems, few data objects get most accesses while large number of objects get few. So we propose a parallelized greedy algorithm to power down service nodes based on the skew ness of data popularity.