Multi-Objective Particle Swarm Optimization-Based Data Compression Algorithm for Public Datasets in Smart Grid Applications

ABSTRACT In smart grid applications, a large amount of data is generated. This data is produced by intelligent devices, smart monitors, and measurement equipment, leading to substantial challenges in storage, computing, and transmission. Consequently, managing this vast amount of data contributes to the smart grid system becoming significantly more complex. To address these challenges, a data compression strategy is essential for enhancing the reliability and storage efficiency of the smart grid system when dealing with large amount of data. In response to this need, this paper proposes a novel data compression method specifically designed for smart grid data. The proposed approach leverages a unique combination of wavelet transform (WT) and multi-objective particle swarm optimization (MO-PSO) to achieve efficient data reduction. To validate the effectiveness of this technique, DRED (Dutch Residential Energy Datasets) datasets are utilized. The evaluation results demonstrate that the MO-PSO-based data compression algorithm outperforms traditional computation methods, offering superior performance in data compression for smart grid applications.