Customer Load Data Synthesis for Privacy to Provide Demand Response Service

With advancements in information and communication technology (ICT), the use of big data has become increasingly prevalent, particularly in the power industry. This study proposes a novel data synthesis methodology to enable the secure sharing and utilization of data containing personal information while retaining the utility of the original data. To model the key components of electricity consumption data, a segmented seasonal trend decomposition using loess (STL) synthesis methodology is proposed, focusing on capturing temporal patterns and characteristics. Segmented STL synthesizes electricity consumption data by segmenting into smaller units and using Gaussian process regression (GPR) and generalized extreme value (GEV) models to effectively capture temporal patterns while enhancing privacy protection. A comparative analysis was conducted on row-wise shuffling, segment-unit row-wise shuffling, and the proposed model. The effectiveness of the proposed method was evaluated using various metrics, including population stability index (PSI), principal component analysis (PCA), and t-distributed stochastic neighbor embedding (t-SNE). In addition, a case study was conducted to determine whether the proposed method properly estimates the potential of a demand response service. The experimental results demonstrate that the proposed methodology effectively reflects the time-series characteristics and electricity usage patterns of the actual data with an error margin within 0.1% while providing a high level of privacy protection.