Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release
McGill University（麦吉尔大学）；CentraleSupélec（巴黎中央理工-高等电力学院）；CNRS（法国国家科学研究中心）；Université Paris Sud（巴黎第十一大学）；Montreal Institute for Learning Algorithms (Mila)（蒙特利尔学习算法研究所）；Université de Montréal（蒙特利尔大学）
Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida, Fabrice Labeau
备注：
to appear in IEEESmartGridComm 2019. arXiv admin note: substantial text overlap with arXiv:1906.06427
发表信息：
2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2019, pp. 1-7
The explosion of data collection has raised serious privacy concerns in users due to the possibility that sharing data may also reveal sensitive information. The main goal of a privacy-preserving mechanism is to prevent a malicious third party from inferring sensitive information while keeping the shared data useful. In this paper, we study this problem in the context of time series data and smart meters (SMs) power consumption measurements in particular. Although Mutual Information (MI) between private and released variables has been used as a common information-theoretic privacy measure, it fails to capture the causal time dependencies present in the power consumption time series data. To overcome this limitation, we introduce the Directed Information (DI) as a more meaningful measure of privacy in the considered setting and propose a novel loss function. The optimization is then performed using an adversarial framework where two Recurrent Neural Networks (RNNs), referred to as the releaser and the adversary, are trained with opposite goals. Our empirical studies on real-world data sets from SMs measurements in the worst-case scenario where an attacker has access to all the training data set used by the releaser, validate the proposed method and show the existing trade-offs between privacy and utility.
Simultaneous Detection of Multiple Appliances from Smart-meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning
Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study
Northeast Normal University（东北师范大学）；Changchun University of Technology（长春工业大学）；University of Missouri（密苏里大学）；Qinghu Rising Sunshine Data Technology (Beijing) Co., Ltd（清湖旭日阳光数据技术（北京）有限公司）；National Institute Ltd（国家研究院有限公司）
Electrical Load Forecasting over Multihop Smart Metering Networks with Federated Learning
Department of Electrical and Computer Engineering, University of Alabama in Huntsville（阿拉巴马大学亨茨维尔分校电气与计算机工程系）；Computer Science and Mathematics Division, Oak Ridge National Laboratory（橡树岭国家实验室计算机科学与数学 division）；Department of Electrical and Computer Engineering, Kansas State University（堪萨斯州立大学电气与计算机工程系）
The Energy Prediction Smart-Meter Dataset: Analysis of Previous Competitions and Beyond
University of Nottingham（诺丁汉大学）；Universidade de Santiago de Compostela（圣地亚哥德孔波斯特拉大学）；University of Melbourne（墨尔本大学）；University of Granada（格拉纳达大学）；Monash University（莫纳什大学）；IBM Research Europe（IBM欧洲研究院）；E.ON Digital Technology GmbH（E.ON数字技术有限公司）；Honda Research Institute Europe GmbH（本田欧洲研究院有限公司）；National Grid ESO（英国国家电网电力系统运营商）；Coles Group（科尔斯集团）；Amazon（亚马逊）
MARTINI: Smart Meter Driven Estimation of HVAC Schedules and Energy Savings Based on WiFi Sensing and Clustering
The University of Texas at Austin（德克萨斯大学奥斯汀分校）
HVAC系统占建筑物能源使用的很大一部分。夜间挫折调度是一种节能措施，其中冷却和加热设定点在空闲期间分别增加和减少，目的是实现节能。然而，需要了解建筑物的实际占用情况，以使这一措施取得最大成功。此外，需要一种可扩展的方式来估计节能措施的节能潜力，该节能措施不受建筑物特定参数和实验或模拟建模投资的限制。在这里，我们提出了MARTINI，这是一个基于居住者的HVAC时间表和节能的sMART meTer driveN评估，它利用了商业建筑中无处不在的能源智能电表和WiFi基础设施。我们估计的时间表，通过集群WiFi导出的占用配置文件，并通过移动斜升和挫折时间观察到的典型/测量的负载配置文件通过集群智能电表能源配置文件，节省能源。我们的案例研究结果显示，当HVAC系统运行与入住率保持一致时，五座建筑物在七个月内的平均冷冻水节能率为8.1%-10.8%（夏季）和0.2%-5.9%（秋季）。我们验证了我们的方法与结果从建筑能源性能模拟（BEPS），发现估计的平均节省的MARTINI是在0.9%-2.4%的BEPS预测。在没有占用信息的情况下，我们仍然可以通过增加爬坡时间和减少倒退开始时间来估计潜在的节省。在51栋教学楼中，我们发现节省潜力在1%-5%之间。
Dynamic Time Warping Clustering to Discover Socio-Economic Characteristics in Smart Water Meter Data
Norwegian University of Science and Technology（挪威科技大学）；KWR Water Cycle Research Institute（KWR水循环研究所）；University of Cincinnati（辛辛那提大学）；Leiden University（莱顿大学）；Delft University of Technology（代尔夫特理工大学）
Real-Time Privacy-Preserving Data Release for Smart Meters
McGill University（麦吉尔大学）；CentraleSupélec（中央理工-高等电力学院）；CNRS（法国国家科学研究中心）；Université Paris Sud（巴黎第十一大学）；Montreal Institute for Learning Algorithms (Mila)（蒙特利尔学习算法研究所）；Université de Montréal（蒙特利尔大学）
