Data Reduction as a Service in Smart City Architecture

A wide range of crowdsensing smart city applications utilize cloud computing to send, store and publish data. The amount of data sent to the cloud is relatively large and this introduces bandwidth, network and storage challenges. In this paper, we offer a smart city architecture that includes a data reduction service located in the proximity of the crowd. In this data reduction service, we propose a lossless compression step for single-precision floating-point data received from the crowd, such as accelerometer readings and GPS coordinates. Floating-point compression has proved to reduce the cost of transmitting a large amount of data. Our compression method was evaluated and achieved a good compression ratio.