Differentially Private Publication of Electricity Time Series Data in Smart Grids
Sina Shaham, Gabriel Ghinita, Bhaskar Krishnamachari, Cyrus Shahabi
TL;DR
This work tackles privacy-preserving publication of electricity time series in smart grids by jointly modeling spatio-temporal patterns and applying differential privacy. The authors introduce STPT, a two-phase framework that first privately learns pattern representations via a spatio-temporal RNN trained on a quadtree-partitioned training set, then sanitizes the data through a k-quantized partitioning of pattern estimates with optimally allocated Laplace noise. The method achieves a favorable privacy-utility trade-off, demonstrating substantial utility gains over state-of-the-art baselines across real and synthetic datasets under a fixed privacy budget. The approach leverages macro and micro trend capture and adaptive partitioning to maintain high data utility for range queries, with potential applicability to other distributed sensing domains beyond electricity consumption.
Abstract
Smart grids are a valuable data source to study consumer behavior and guide energy policy decisions. In particular, time-series of power consumption over geographical areas are essential in deciding the optimal placement of expensive resources (e.g., transformers, storage elements) and their activation schedules. However, publication of such data raises significant privacy issues, as it may reveal sensitive details about personal habits and lifestyles. Differential privacy (DP) is well-suited for sanitization of individual data, but current DP techniques for time series lead to significant loss in utility, due to the existence of temporal correlation between data readings. We introduce {\em STPT (Spatio-Temporal Private Timeseries)}, a novel method for DP-compliant publication of electricity consumption data that analyzes spatio-temporal attributes and captures both micro and macro patterns by leveraging RNNs. Additionally, it employs a partitioning method for releasing electricity consumption time series based on identified patterns. We demonstrate through extensive experiments, on both real-world and synthetic datasets, that STPT significantly outperforms existing benchmarks, providing a well-balanced trade-off between data utility and user privacy.