Multi-threads computation for aggregation of time-series data

Time-series data involved applications have become popular with the rapid improvement of smart terminals and wireless networks. For example, in the case of mobile sensing, a sensing user will get a private input in each time period. And during the same period, the aggregator wants to calculate the aggregation statistics from the private inputs of sensing users. The privacy issue becomes much more challenging in the case of an untrusted aggregator. We are trying to increase the computation efficiency of the untrusted aggregator. Multi-cores architecture based CPU has been widely applied for not only personal computers but also servers. And it has been an indispensible field in our everyday life. In this paper, we take advantages of multi-threads computation to a scalable basic aggregation protocol, and improve the computation efficiency of the untrusted aggregator. We conduct some experiments to compare it with the basic protocol. The conducted experiments show the computation efficiency of our proposed protocol. Copyright © 2019 Inderscience Enterprises Ltd.