Differential privacy and distributed online learning for wireless big data

Distributed sensor networks (DSN) have been widely applied in daily life. Many sensor network applications can be regarded as big-data optimization, since the sensor nodes collect large volume of data in a long time. However, subject to limited computation and communication capabilities of sensor nodes, how we process such a large scale of data is a great challenge. In this paper, we give the sensor nodes the ability of online learning, which reduces the size of data storage by “using” the data. Then, each sensor node is able to save much flash memory to handle more data. Furthermore, the communications among sensor nodes may lead to privacy breaches. Hence, we use differential privacy to solve the privacy-preserving problem. Numeric results show the performance of our proposed differentially private distributed online learning algorithm used in DSN.