Is Machine Learning in Power Systems Vulnerable?

Recent advances in Machine Learning (ML) have led to its broad adoption in a series of power system applications, ranging from meter data analytics, renewable/load/price forecasting to grid security assessment. Although these data-driven methods yield state-of-the-art performances in many tasks, the robustness and security of applying such algorithms in modern power grids have not been discussed. In this paper, we attempt to address the issues regarding the security of ML applications in power systems. We first show that most of the current ML algorithms proposed in power systems are vulnerable to adversarial examples, which are maliciously crafted input data. We then adopt and extend a simple yet efficient algorithm for finding subtle perturbations, which could be used for generating adversaries for both categorical (e.g., user load profile classification) and sequential applications (e.g., renewables generation forecasting). Case studies on classification of power quality disturbances and forecast of building loads demonstrate the vulnerabilities of current ML algorithms in power networks under our adversarial designs. These vulnerabilities call for design of robust and secure ML algorithms for real world applications.

[1]  Xiyu Wang,et al.  An Unsupervised Deep Learning Approach for Scenario Forecasts , 2018, 2018 Power Systems Computation Conference (PSCC).

[2]  Dan Boneh,et al.  Ensemble Adversarial Training: Attacks and Defenses , 2017, ICLR.

[3]  Yuanyuan Shi,et al.  Modeling and optimization of complex building energy systems with deep neural networks , 2017, 2017 51st Asilomar Conference on Signals, Systems, and Computers.

[4]  Silja Meyer-Nieberg,et al.  Electric load forecasting methods: Tools for decision making , 2009, Eur. J. Oper. Res..

[5]  Ananthram Swami,et al.  Crafting adversarial input sequences for recurrent neural networks , 2016, MILCOM 2016 - 2016 IEEE Military Communications Conference.

[6]  Arturo Garcia-Perez,et al.  Detection and Classification of Single and Combined Power Quality Disturbances Using Neural Networks , 2014, IEEE Transactions on Industrial Electronics.

[7]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[8]  Amin Khodaei,et al.  Machine Learning Based Power Grid Outage Prediction in Response to Extreme Events , 2017, IEEE Transactions on Power Systems.

[9]  Mohammed H. Albadi,et al.  A summary of demand response in electricity markets , 2008 .

[10]  Mukund R. Patel Wind and Solar Power Systems: Design, Analysis, and Operation, Second Edition , 2005 .

[11]  Rong Zheng,et al.  Bad data injection in smart grid: attack and defense mechanisms , 2013, IEEE Communications Magazine.

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Radha Poovendran,et al.  Blocking Transferability of Adversarial Examples in Black-Box Learning Systems , 2017, ArXiv.

[14]  Rob J Hyndman,et al.  Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond , 2016 .

[15]  Pan Li,et al.  A Distributed Online Pricing Strategy for Demand Response Programs , 2017, IEEE Transactions on Smart Grid.

[16]  Peng Ning,et al.  False data injection attacks against state estimation in electric power grids , 2011, TSEC.

[17]  Chongqing Kang,et al.  Deep Learning-Based Socio-Demographic Information Identification From Smart Meter Data , 2019, IEEE Transactions on Smart Grid.

[18]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[19]  Daniel Kirschen,et al.  Model-Free Renewable Scenario Generation Using Generative Adversarial Networks , 2017, IEEE Transactions on Power Systems.

[20]  P. Torcellini,et al.  DOE Commercial Building Benchmark Models , 2008 .

[21]  Carter Lassetter Learning Schemes for Power System Planning and Control , 2017 .