Learning Sparse Privacy-Preserving Representations for Smart Meters Data

Fine-grained Smart Meters (SMs) data recording and communication has enabled several features of Smart Grids (SGs) such as power quality monitoring, load forecasting, fault detection, and so on. In addition, it has benefited the users by giving them more control over their electricity consumption. However, it is well-known that it also discloses sensitive information about the users, i.e., an attacker can infer users' private information by analyzing the SMs data. In this study, we propose a privacy-preserving approach based on non-uniform down-sampling of SMs data. We formulate this as the problem of learning a sparse representation of SMs data with minimum information leakage and maximum utility. The architecture is composed of a releaser, which is a recurrent neural network (RNN), that is trained to generate the sparse representation by masking the SMs data, and an utility and adversary networks (also RNNs), which help the releaser to minimize the leakage of information about the private attribute, while keeping the reconstruction error of the SMs data minimum (i.e., maximum utility). The performance of the proposed technique is assessed based on actual SMs data and compared with uniform down-sampling, random (non-uniform) down-sampling, as well as the state-of-the-art in privacy-preserving methods using a data manipulation approach. It is shown that our method performs better in terms of the privacy-utility trade-off while releasing much less data, thus also being more efficient.

[1]  Georgios Kalogridis,et al.  Smart Grid Privacy via Anonymization of Smart Metering Data , 2010, 2010 First IEEE International Conference on Smart Grid Communications.

[2]  H. Vincent Poor,et al.  Optimal demand-side management for joint privacy-cost optimization with energy storage , 2017, 2017 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[3]  Ashish Khisti,et al.  Information-Theoretic Privacy for Smart Metering Systems with a Rechargeable Battery , 2015, IEEE Transactions on Information Theory.

[4]  Silvia Santini,et al.  The ECO data set and the performance of non-intrusive load monitoring algorithms , 2014, BuildSys@SenSys.

[5]  Ning Lu,et al.  Smart-grid security issues , 2010, IEEE Security & Privacy.

[6]  On the Impact of Side Information on Smart Meter Privacy-Preserving Methods , 2020, 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm).

[7]  Deniz Gündüz,et al.  Privacy-cost Trade-off in a Smart Meter System with a Renewable Energy Source and a Rechargeable Battery , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  H. Vincent Poor,et al.  Privacy-Aware Smart Metering: Progress and Challenges , 2018, IEEE Signal Processing Magazine.

[9]  Stefanie Kuenzel,et al.  Privacy-Functionality Trade-Off: A Privacy-Preserving Multi-Channel Smart Metering System , 2020, Energies.

[10]  Jian Weng,et al.  Cost-Friendly Differential Privacy for Smart Meters: Exploiting the Dual Roles of the Noise , 2017, IEEE Transactions on Smart Grid.

[11]  D. Ruppert The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[12]  H. Vincent Poor,et al.  Increasing Smart Meter Privacy Through Energy Harvesting and Storage Devices , 2013, IEEE Journal on Selected Areas in Communications.

[13]  Parv Venkitasubramaniam,et al.  On the privacy-cost tradeoff of an in-home power storage mechanism , 2013, 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[14]  H. Vincent Poor,et al.  Smart Meter Privacy With Renewable Energy and an Energy Storage Device , 2017, IEEE Transactions on Information Forensics and Security.

[15]  Fabrice Labeau,et al.  Privacy-Preserving Adversarial Network (PPAN) for Continuous non-Gaussian Attributes , 2020 .

[16]  Yasin Kabalci,et al.  Introduction to Smart Grid Architecture , 2019 .

[17]  Andreas Reinhardt,et al.  On the Impact of Temporal Data Resolution on the Accuracy of Non-Intrusive Load Monitoring , 2020, BuildSys@SenSys.

[18]  Georgios Kalogridis,et al.  Privacy for Smart Meters: Towards Undetectable Appliance Load Signatures , 2010, 2010 First IEEE International Conference on Smart Grid Communications.

[19]  Daisuke Mashima,et al.  Authenticated down-sampling for privacy-preserving energy usage data sharing , 2015, 2015 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[20]  Dominik Engel,et al.  Influence of Data Granularity on Smart Meter Privacy , 2015, IEEE Transactions on Smart Grid.

[21]  A. Kraskov,et al.  Estimating mutual information. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  Andrey Brito,et al.  A Technique to provide differential privacy for appliance usage in smart metering , 2016, Inf. Sci..

[23]  Vincent W. S. Wong,et al.  Smart Meter Privacy: Exploiting the Potential of Household Energy Storage Units , 2018, IEEE Internet of Things Journal.

[24]  Pablo Piantanida,et al.  Privacy-Cost Management in Smart Meters: An Information-Theoretic Deep Reinforcement Learning Approach , 2020 .

[25]  G. Schwartz,et al.  Privacy-Aware Sampling for Residential Demand Response Programs , 2012 .

[26]  Lawrence Mosley,et al.  A balanced approach to the multi-class imbalance problem , 2013 .

[27]  F. Labeau,et al.  Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning , 2020, 2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe).

[28]  F. Labeau,et al.  Real-Time Privacy-Preserving Data Release for Smart Meters , 2019, IEEE Transactions on Smart Grid.

[29]  H. Vincent Poor,et al.  Smart Meter Privacy: A Theoretical Framework , 2013, IEEE Transactions on Smart Grid.

[30]  Ye Wang,et al.  Privacy-Preserving Adversarial Networks , 2017, 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[31]  Deniz Gündüz,et al.  Smart Meter Privacy for Multiple Users in the Presence of an Alternative Energy Source , 2013, IEEE Transactions on Information Forensics and Security.

[32]  Pablo Piantanida,et al.  Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release , 2019, 2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm).

[33]  Georgios Kalogridis,et al.  ElecPrivacy: Evaluating the Privacy Protection of Electricity Management Algorithms , 2011, IEEE Transactions on Smart Grid.

[34]  Liang Cheng,et al.  Evaluation of utility-privacy trade-offs of data manipulation techniques for smart metering , 2016, 2016 IEEE Conference on Communications and Network Security (CNS).