Energy disaggregation techniques, which use smart meter data to infer appliance energy usage, can provide consumers and energy companies valuable insights into energy management. However, these techniques also present privacy risks, such as the potential for behavioral profiling. Local differential privacy (LDP) methods provide strong privacy guarantees with high efficiency in addressing privacy concerns. However, existing LDP methods focus on protecting aggregated energy consumption data rather than individual appliances. Furthermore, these methods do not consider the fact that smart meter data are a form of streaming data, and its processing methods should account for time windows. In this paper, we propose a novel LDP approach (named LDP-SmartEnergy) that utilizes randomized response techniques with sliding windows to facilitate the sharing of appliance-level energy consumption data over time while not revealing individual users' appliance usage patterns. Our evaluations show that LDP-SmartEnergy runs efficiently compared to baseline methods. The results also demonstrate that our solution strikes a balance between protecting privacy and maintaining the utility of data for effective analysis.

翻译：能源分解技术通过智能电表数据推断设备能耗，可为用户和能源公司提供有价值的能源管理洞见。然而，这些技术也带来了隐私风险，例如行为特征分析的可能性。本地差分隐私（LDP）方法在解决隐私问题时能够提供强隐私保障与高效率。然而现有LDP方法侧重于保护聚合能耗数据，而非单个设备数据。此外，这些方法未考虑智能电表数据作为流式数据的特性，其处理方法应考虑时间窗口。本文提出一种新型LDP方案（命名为LDP-SmartEnergy），该方案利用滑动窗口随机响应技术，在随时间共享设备级能耗数据的同时，不泄露个体用户的设备使用模式。评估结果表明，与基线方法相比，LDP-SmartEnergy运行高效。结果同时证明，本方案在隐私保护与数据效用维护之间取得了有效平衡。