Efficient Lossy Compression for IoT Using SZ and Reconstruction with 1D U-Net

Several recent research has centered on maximizing Internet of Things (IoT) devices’ lifetime by deploying data reduction techniques on IoT nodes to reduce data transmission. Data compression methods can be seen as a direct way of achieving energy efficiency. The trade-off between compression ratio and data distortion is usually considered when using a lossy compressor. This paper proposes a light SZ compressor with a maximal compression ratio without considering this trade-off. The proposed approach was tested on ESP Wroom 32 and WiFi LoRa 32 microcontrollers. Given the importance of data quality arriving at the gateway for analysis, the proposed lossy compressor with a high compression ratio can discard important data features and patterns. This paper solves this problem by proposing a method for data enhancement based on the U-Net architecture. Therefore, the contribution of this paper is twofold: (1) Efficient data reduction approach for energy optimization at the level of IoT nodes. (2) 1D U-Net-based data recovery approach at the level of the edge.