IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (IEEE SmartGridComm 2022)

Session K5: Keynote Speech: Retail Electricity Markets and DER-hungry Grid Edge
Session CO3: Operation and Control of Microgrids Session SS: Interplay Between Communication and Computation in Wireless-empowered Smart Grids Session CO4: Scheduling and Optimization in Smart Grids Session SP3: Attack Detection and Localization in Smart Grids Session DAC3: Data Analysis and Computation in Smart Metering Session SP4: Cyber Security, Risk Management and Digital Twins
Session W2: Workshop: Intelligence and Security for Smart Energy Systems Session W3: Workshop: Cybersecurity of Electric Vehicle Charging and Smart Grid Resources

Session W2

Workshop: Intelligence and Security for Smart Energy Systems

Conference
10:30 AM — 12:20 PM +08
Local
Oct 27 Thu, 10:30 PM — 12:20 AM EDT

Invited Talk: Stochastic Energy Management and Cyber-Physical Security in Smart Distribution Systems

Hao Liang, University of Alberta, Canada

0
This talk does not have an abstract.

Vulnerability Assessment of Machine Learning Based Short-Term Residential Load Forecast against Cyber Attacks on Smart Meters

Shichao Liu, Alanoud Alrasheedi, Osarodion Egbomwan and Nowayer Alrashidi (Carleton University, Canada)

0
Short-Term Load Forecast at residential house level plays a critical role in home energy management system. While a variety of machine learning based load forecasting methods have been proposed, their prediction performance have not been assessed against cyber threats on smart meters which have been increasingly reported. This paper investigates the vulnerability of four extensively used machine learning algorithms for residential short-term load forecast against cyberattacks, including Nonlinear Auto Regression with external input (NARX) neural network, support vector machine (SVM), decision tree (DT), and long-short-term memory (LSTM) deep learning. We use the REFIT dataset which collected whole-house aggregated loads at 8-second intervals continuously from 20 houses over a two-year period in the U.K. The results were determined and show the predictions using NARX and LSTM. Four cyberattack models are investigated, including pulse, scale, ramp, and random. The vulnerability assessment results indicate the LSTM provides the most accurate prediction without cyberattacks. However, the prediction accuracy of the LSTM fluctuates when there are cyber attacks. Among the four cyberattacks, the random attack triggered the larges variations on the predication results.

Fault Diagnosis of Microgrids Using Branch Convolution Neural Network and Majority Voting

Zhoubing Li and Meng Zhang (Xi'an Jiaotong University, China); Lin Li (Xi'an Technological University, China); Xiaohong Guan (Xi'an Jiaotong University & Tsinghua University, China)

0
Fault diagnosis is an important guarantee for the stable and safe operation of microgrids, which consists of fault localization and fault detection. However, most current researches separately deal with these two issues, which makes the fault diagnosis results lack of vital information. This paper proposes a solution based on deep learning, namely branch CNN with a majority voting (B-CNN-MV) model, to simultaneously realize fault localization and fault detection through two branches. One of the branches realizes fault localization and the other performs fault detection. Firstly, in each branch, the CNN module extracts the two-dimensional image features of each sample in the spatial dimension and outputs primary classification results. Then, the classification results from the CNN module within one period of data constitute the temporal dimension input for the following majority voting module. Finally, the majority voting modules after each branch employ these temporal dimension inputs to calculate the final fault type and location results. Through this new design, the information on fault location and fault type can be obtained more accurately at the same time. Moreover, the test results also show that the model has a high accuracy even in the case of insufficient data.

Evaluating Synthetic Datasets for Training Machine Learning Models to Detect Malicious Commands

Jia Wei Teo (National University of Singapore, Singapore); Sean Gunawan (Singapore University of Technology and Design, Singapore); Partha P. Biswas (Advanced Digital Sciences Center, Singapore); Daisuke Mashima (Advanced Digital Sciences Center & National University of Singapore, Singapore)

0
Electrical substations in power grid act as the critical interface points for the transmission and distribution networks. Over the years, digital technology has been integrated into the substations for remote control and automation. As a result, substations are more prone to cyber attacks and exposed to digital vulnerabilities. One of the notable cyber attack vectors is the malicious command injection, which can lead to shutting down of substations and subsequently power outages as demonstrated in Ukraine Power Plant Attack in 2015. Prevailing measures based on cyber rules (e.g., firewalls and intrusion detection systems) are often inadequate to detect advanced and stealthy attacks that use legitimate-looking measurements or control messages to cause physical damage. Additionally, defenses that use physics-based approaches (e.g., power flow simulation, state estimation, etc.) to detect malicious commands suffer from high latency. Machine learning serves as a potential solution in detecting command injection attacks with high accuracy and low latency. However, sufficient datasets are not readily available to train and evaluate the machine learning models. In this paper, focusing on this particular challenge, we discuss various approaches for the generation of synthetic data that can be used to train the machine learning models. Further, we evaluate the models trained with the synthetic data against attack datasets that simulates malicious commands injections with different levels of sophistication. Our findings show that synthetic data generated with some level of power grid domain knowledge helps train robust machine learning models against different types of attacks.

Graph Neural Network Based Prediction of Data Traffic in Cyber-Physical Smart Power Grids

Md Aminul Islam (Tennessee Technological University, USA); Muhammad Ismail (Tennessee Tech University, USA); Osman Boyaci (Texas A&M University, USA); Rachad Atat (Texas AM University at Qatar, Qatar); Susmit Shannigrahi (Tennessee Technological University, USA)

0
Smart power grids rely on tight integration of physical and cyber layers. Event-driven (ED) data packets are generated in the cyber layer in response to emergency conditions in the grid such as weather conditions, physical sabotage, cyber-attacks, etc. For proper management of the resources at the cyber layer, and hence, timely delivery of ED packets, efficient prediction of ED traffic conditions is required. Since the stochastic arrival process of ED packets is attributed to several factors, a data-driven prediction approach is appealing. However, this is challenged by: (a) unavailability of datasets capturing ED packet arrivals and departures at the cyber layer of the power grid, which are needed to train and test the data-driven models, (b) sparsity of the ED traffic data as emergency conditions are rare, and such sparsity impedes the learning process of data-driven models based on gradient descent, and (c) inability of traditional models, e.g., multilayer perceptron (MLP), long short-term memory (LSTM), convolutional neural networks (CNNs), to present accurate prediction as they fail to capture the interactions among the routers within the cyber layer. To address these challenges, this paper: (a) proposes a method to generate ED traffic based on real emergency reports in the U.S. power grid, (b) proposes a pre-processing method to convert the sparse ED traffic data into dense data, and (c) proposes a topology-aware prediction model based on graph neural network (GNN) to accurately predict the network condition. Our results demonstrate the superior performance of the proposed GNN-based approach.
Session Chair and Room

Room TT4-5

Session W3

Workshop: Cybersecurity of Electric Vehicle Charging and Smart Grid Resources

Conference
2:00 PM — 5:30 PM +08
Local
Oct 28 Fri, 2:00 AM — 5:30 AM EDT

Invited Talk: Security by Design in Cybersecurity of Car Accessories Control

Dmitry Mikhaylov, Reperion, Singapore

0
This talk does not have an abstract.

Invited Talk: Formal Abstractions for Safe Integration of Responsive Loads in Smart Grids

Sadegh Soudjani, Newcastle University, United Kingdom

0
This talk does not have an abstract.

On the Security of Wireless Electric Vehicle Charging Communication

Sebastian Köhler, Simon Birnbach, Richard Baker and Ivan Martinovic (University of Oxford, United Kingdom (Great Britain))

0
The adoption of fully Electric Vehicles (EVs) is happening at a rapid pace. To make the charging as fast and convenient as possible, new charging approaches are developed constantly. One such approach is wireless charging, also known as Wireless Power Transfer (WPT). Instead of charging an EV via a charging cable, the battery is charged wirelessly. For safety and efficiency reasons, the vehicle and the charging station continuously exchange critical information about the charging process. This includes, e.g., the maximum voltage and current, battery temperature, and State of Charge (SoC). Since there is no physical connection between the vehicle and the charging station, this necessary control communication has to be implemented as a wireless connection. However, if the communication is interrupted, the charging process is aborted for safety reasons.

In this paper, we analyze the attack surface of EV charging standards that use such a wireless control communication. More specifically, we discuss potential wireless attacks that can violate the availability and analyze the implemented security features of a real-world wireless charging station that has already been deployed. We found that the tested charging station does not implement even simple security measures, such as IEEE 802.11w, that can protect the communication from denial-of-service attacks. Finally, we discuss potential countermeasures, and give recommendations to improve the security and increase the resilience of wireless charging.

Security Threats in Electric Vehicle Charging

Sridhar Adepu (University of Bristol, United Kingdom (Great Britain)); Anchal Ahalawat (Reperion, Singapore); Joseph Gardiner (University of Bristol, United Kingdom (Great Britain))

0
The electric vehicle (EV) charging system plays a significant role in the future energy system. The widespread adoption of operating EV charging is greatly accelerating the integration of transmission and distribution systems, which help to accommodate a clean atmosphere, drop conventional fuel dependence etc. An EV interact with different objects in the charging station to recharge during the charging process. EV is not the only part of the growing EV industry that can be hacked and remotely accessed. The charging stations that power up such vehicles can also be connected to the internet, making them vulnerable to malicious attacks. Thus, this technology has caught the attention of many researchers who have proposed authentication protocols to provide a secure connection for exchanging information between electric vehicles and the charging station. This article discusses the comprehensive security threats of the EV charging system. Moreover, it review the architecture of the charging station system and the protocols between electric vehicles and charging stations.
Session Chair and Room

Room TT4-5

Made with in Toronto · Privacy Policy · SmartGridComm 2020 · SmartGridComm 2021 · © 2022 Duetone Corp.