Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9961041
C. Krasopoulos, Thanasis G. Papaioannou, G. Stamoulis
Demand flexibility management, often by means of Demand Response (DR), can significantly enhance the stability of the electric grid and reduce the investment cost for infrastructure upgrades in case of dynamic energy mix with renewable sources. However, uncertainty in the consumer response to the DR signals may disrupt this goal. In this paper, we deal with the optimal management of the flexibility offered by residential users under uncertainty. We develop a probabilistic user model to account for the uncertainty in the actual provision of the flexibility by a user in conjunction with incentives' offered thereto, which we subsequently introduce in the Demand Response (DR) targeting process. We consider a suitable optimization framework to enable flexibility maximization and budget minimization as separate single-objective expressions with the appropriate constraints. We define representative problems and solve them numerically for a wide range of user parameters, in order to illustrate the applicability and accuracy of our method, and to extract valuable insights. Finally, we develop techniques to resolve practical issues and to enable real-world implementation of the proposed scheme in pilot sites; namely, a mathematical expression to estimate the confidence intervals of the attained flexibility and a learning algorithm for extracting the individual user parameters according to their participation patterns.
{"title":"Flexibility Management for Residential Users Under Participation Uncertainty","authors":"C. Krasopoulos, Thanasis G. Papaioannou, G. Stamoulis","doi":"10.1109/SmartGridComm52983.2022.9961041","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9961041","url":null,"abstract":"Demand flexibility management, often by means of Demand Response (DR), can significantly enhance the stability of the electric grid and reduce the investment cost for infrastructure upgrades in case of dynamic energy mix with renewable sources. However, uncertainty in the consumer response to the DR signals may disrupt this goal. In this paper, we deal with the optimal management of the flexibility offered by residential users under uncertainty. We develop a probabilistic user model to account for the uncertainty in the actual provision of the flexibility by a user in conjunction with incentives' offered thereto, which we subsequently introduce in the Demand Response (DR) targeting process. We consider a suitable optimization framework to enable flexibility maximization and budget minimization as separate single-objective expressions with the appropriate constraints. We define representative problems and solve them numerically for a wide range of user parameters, in order to illustrate the applicability and accuracy of our method, and to extract valuable insights. Finally, we develop techniques to resolve practical issues and to enable real-world implementation of the proposed scheme in pilot sites; namely, a mathematical expression to estimate the confidence intervals of the attained flexibility and a learning algorithm for extracting the individual user parameters according to their participation patterns.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128965122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Battery Swapping Stations (BSSs) are rapidly ex-panding infrastructures for electric vehicles. However, the in-appropriate battery charging strategy of BSSs will lead to unnecessary charging costs. In this paper, we study the real-time optimal battery charging strategies for every BSSs in a system under a non-cooperative scenario and dynamic electricity pricing environment. We propose a non-cooperative game model to characterize the BSS charging competition. We prove the existence and uniqueness of Nash Equilibrium under arbitrary swapping demands and battery numbers, and an algorithm is proposed to solve the Equilibrium. Numerical results show that our proposed strategy outperforms the benchmark strategies in terms of overall profits.
{"title":"Battery Charging Strategies Design for Battery Swapping Stations: A Game Theoretic Approach","authors":"Huanyu Yan, Chenxi Sun, Huanxin Liao, Xiaoying Tang","doi":"10.1109/SmartGridComm52983.2022.9960987","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9960987","url":null,"abstract":"Battery Swapping Stations (BSSs) are rapidly ex-panding infrastructures for electric vehicles. However, the in-appropriate battery charging strategy of BSSs will lead to unnecessary charging costs. In this paper, we study the real-time optimal battery charging strategies for every BSSs in a system under a non-cooperative scenario and dynamic electricity pricing environment. We propose a non-cooperative game model to characterize the BSS charging competition. We prove the existence and uniqueness of Nash Equilibrium under arbitrary swapping demands and battery numbers, and an algorithm is proposed to solve the Equilibrium. Numerical results show that our proposed strategy outperforms the benchmark strategies in terms of overall profits.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133906592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9961030
J. Lozano, K. Koneru, J. H. Castellanos, A. Cárdenas
Despite the importance of the Generic Object Ori-ented Substation Event (GOOSE) protocol in substation automation, there is very little exploration of its behavior in real-world deployments. Due to the sensitivity of actual data, various analyses are performed only on small testbeds or emulated traffic with designed assumptions of how these systems behave. In this work, we provide a timing characterization of the GOOSE protocol in a real-world substation. We compare the results with a testbed that mimics a real-world power system. We also discuss the insights from the analysis regarding presumed differences between simulated traffic and real-world traffic to understand the actual behavior of the devices.
{"title":"Timing Analysis of GOOSE in a Real-World Substation","authors":"J. Lozano, K. Koneru, J. H. Castellanos, A. Cárdenas","doi":"10.1109/SmartGridComm52983.2022.9961030","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9961030","url":null,"abstract":"Despite the importance of the Generic Object Ori-ented Substation Event (GOOSE) protocol in substation automation, there is very little exploration of its behavior in real-world deployments. Due to the sensitivity of actual data, various analyses are performed only on small testbeds or emulated traffic with designed assumptions of how these systems behave. In this work, we provide a timing characterization of the GOOSE protocol in a real-world substation. We compare the results with a testbed that mimics a real-world power system. We also discuss the insights from the analysis regarding presumed differences between simulated traffic and real-world traffic to understand the actual behavior of the devices.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116045275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9961037
Abel O. Gomez Rivera, Deepak K. Tosh
Cyber-Physical Systems (CPS) commonly monitor and manage critical cyber-enabled services such as distributed power generation architectures. Traditional CPS consists of heterogeneous devices that monitor physical systems processes generally stochastic and complex to model through state-of-the-art methods such as time-series analysis. Due to the stochas-tic nature, assurance of continuous runtime state integrity is challenging. Furthermore, adversaries exploit the lack of robust security mechanisms to deploy false sequential attacks that target the physical state of system processes. Therefore, this work designs runtime-system-state integrity assurance techniques necessary to enhance the security of critical CPS such as Small Modular Reactors (SMR). In this work, we propose a Reinforce-ment Learning(RL)-based Runtime-system-state Integrity (RRI) framework that aims to enable self-configurable runtime-system-states in SMR. The RRI framework generally addresses false sequential attacks by enabling fine-grained detail continuous runtime state integrity assurance through state-of-the-art RL and Machine Learning (ML) methods. A proof-of-concept of the RRI framework has been evaluated in an emulated SMR. This work demonstrates the RRI framework's performance regarding the RL methods' convergence time. Overall, the state-of-the-art RL methods converge in 1,000 episodes. We implemented the emulated experimental SMR through the open-source OpenAI, scikit-learn, and Stable Baselines3 platforms. The open-source platforms enable the development and comparison of RL and ML methods by enabling standard communication between baselines algorithms and ecosystems. The experimental results discussed in this work provide essential information that help understand complex and stochastic environments. Furthermore, we demon-strated that the RRI framework could provide high-fidelity CPS models that can provide helpful insights into understanding the system-state behavior of complex system processes.
{"title":"Achieving Self-Configurable Runtime State Verification in Critical Cyber-Physical Systems","authors":"Abel O. Gomez Rivera, Deepak K. Tosh","doi":"10.1109/SmartGridComm52983.2022.9961037","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9961037","url":null,"abstract":"Cyber-Physical Systems (CPS) commonly monitor and manage critical cyber-enabled services such as distributed power generation architectures. Traditional CPS consists of heterogeneous devices that monitor physical systems processes generally stochastic and complex to model through state-of-the-art methods such as time-series analysis. Due to the stochas-tic nature, assurance of continuous runtime state integrity is challenging. Furthermore, adversaries exploit the lack of robust security mechanisms to deploy false sequential attacks that target the physical state of system processes. Therefore, this work designs runtime-system-state integrity assurance techniques necessary to enhance the security of critical CPS such as Small Modular Reactors (SMR). In this work, we propose a Reinforce-ment Learning(RL)-based Runtime-system-state Integrity (RRI) framework that aims to enable self-configurable runtime-system-states in SMR. The RRI framework generally addresses false sequential attacks by enabling fine-grained detail continuous runtime state integrity assurance through state-of-the-art RL and Machine Learning (ML) methods. A proof-of-concept of the RRI framework has been evaluated in an emulated SMR. This work demonstrates the RRI framework's performance regarding the RL methods' convergence time. Overall, the state-of-the-art RL methods converge in 1,000 episodes. We implemented the emulated experimental SMR through the open-source OpenAI, scikit-learn, and Stable Baselines3 platforms. The open-source platforms enable the development and comparison of RL and ML methods by enabling standard communication between baselines algorithms and ecosystems. The experimental results discussed in this work provide essential information that help understand complex and stochastic environments. Furthermore, we demon-strated that the RRI framework could provide high-fidelity CPS models that can provide helpful insights into understanding the system-state behavior of complex system processes.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117025711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":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.
{"title":"Vulnerability Assessment of Machine Learning Based Short-Term Residential Load Forecast against Cyber Attacks on Smart Meters","authors":"Alanoud Alrasheedi, Osarodion Emmanuel Egbomwan, Shichao Liu, Nowayer Alrashidi","doi":"10.1109/SmartGridComm52983.2022.9961008","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9961008","url":null,"abstract":"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.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114785068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9960986
D. Sahabandu, Luyao Niu, Andrew Clark, R. Poovendran
Cascade failures, in which the failure of generators or transmission lines causes neighboring generators or lines to trip offline, threaten power system stability. Controlled islanding mitigates cascade failures by deliberately removing a subset of transmission lines in order to partition the system into disjoint, internally stable islands. In this paper, we investigate algorithms for controlled islanding to ensure stability while minimizing power flow disruption and load-generator imbalance. We consider a scenario where there are heterogeneous loads with varying costs of load shedding and formulate a hybrid optimization problem of jointly selecting a set of transmission lines to remove (discrete variables) and how much load to shed at each bus (continuous variables). In order to solve this optimization problem with provable optimality bounds, we propose a new notion of hybrid submodularity. We develop a polynomial-time islanding algorithm that achieves a provable 1/2-optimality bound. We use IEEE 118-bus and ACTIVsg 500-bus case studies to demonstrate that our approach provides better islanding solutions compared to a Mixed-Integer Linear Program (MILP)-based approach.
{"title":"A Hybrid Submodular Optimization Approach to Controlled Islanding with Heterogeneous Loads","authors":"D. Sahabandu, Luyao Niu, Andrew Clark, R. Poovendran","doi":"10.1109/SmartGridComm52983.2022.9960986","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9960986","url":null,"abstract":"Cascade failures, in which the failure of generators or transmission lines causes neighboring generators or lines to trip offline, threaten power system stability. Controlled islanding mitigates cascade failures by deliberately removing a subset of transmission lines in order to partition the system into disjoint, internally stable islands. In this paper, we investigate algorithms for controlled islanding to ensure stability while minimizing power flow disruption and load-generator imbalance. We consider a scenario where there are heterogeneous loads with varying costs of load shedding and formulate a hybrid optimization problem of jointly selecting a set of transmission lines to remove (discrete variables) and how much load to shed at each bus (continuous variables). In order to solve this optimization problem with provable optimality bounds, we propose a new notion of hybrid submodularity. We develop a polynomial-time islanding algorithm that achieves a provable 1/2-optimality bound. We use IEEE 118-bus and ACTIVsg 500-bus case studies to demonstrate that our approach provides better islanding solutions compared to a Mixed-Integer Linear Program (MILP)-based approach.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127396844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9961007
C. M. Adrah, M. K. Katoulaei, Tesfaye Amare, David Palma
The fifth-generation (5G) mobile network promises to offer low latency services. Hence, there is interest in assessing various power distribution grid applications that can be deployed with a 5G infrastructure. This paper presents a smart grid cyber-physical testbed for protection systems. It consists of power system applications deployed on OPAL-RT, a real-time platform, and a 5G communication network modeled in ns-3. The testbed is used to assess the performance of a power system protection application (Permissive Underreaching Transfer Trip (PUTT) protection scheme) deployed over a 5G communication network. The proposed approach enables real-time protection traffic to be analyzed in an emulated 5G network and gives insights into how such a testbed can be used to assess the performance of protection traffic in 5G networks and beyond.
{"title":"A real-time cyber-physical testbed to assess protection system traffic over 5G networks","authors":"C. M. Adrah, M. K. Katoulaei, Tesfaye Amare, David Palma","doi":"10.1109/SmartGridComm52983.2022.9961007","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9961007","url":null,"abstract":"The fifth-generation (5G) mobile network promises to offer low latency services. Hence, there is interest in assessing various power distribution grid applications that can be deployed with a 5G infrastructure. This paper presents a smart grid cyber-physical testbed for protection systems. It consists of power system applications deployed on OPAL-RT, a real-time platform, and a 5G communication network modeled in ns-3. The testbed is used to assess the performance of a power system protection application (Permissive Underreaching Transfer Trip (PUTT) protection scheme) deployed over a 5G communication network. The proposed approach enables real-time protection traffic to be analyzed in an emulated 5G network and gives insights into how such a testbed can be used to assess the performance of protection traffic in 5G networks and beyond.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124875105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9961022
M. Khan, J. Giraldo, M. Parvania
This paper introduces a novel framework for cyber-physical analysis of power distribution systems using a real-time digital twin. The proposed architecture utilizes a digital twin as a real-time reference model that replicates the complex behavior of a power distribution system in order to perform real-time cyber-physical analysis such as detection of potential malicious data manipulations, verification of control actions before being applied to the physical system, and monitoring of the status of the power grid in locations where physical measurements are not available. The implementation in a hardware-in-the-Ioop (HIL) testbed is introduced for power distribution systems that integrate a variety of devices such as protection relays, distributed energy resources, and energy storage. Finally, results in a modified IEEE 13 node test feeder illustrate that the proposed structure is capable of detecting and mitigating cyber attacks, and also validate control commands before being executed.
{"title":"Real-Time Cyber-Physical Analysis of Distribution Systems Using Digital Twins","authors":"M. Khan, J. Giraldo, M. Parvania","doi":"10.1109/SmartGridComm52983.2022.9961022","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9961022","url":null,"abstract":"This paper introduces a novel framework for cyber-physical analysis of power distribution systems using a real-time digital twin. The proposed architecture utilizes a digital twin as a real-time reference model that replicates the complex behavior of a power distribution system in order to perform real-time cyber-physical analysis such as detection of potential malicious data manipulations, verification of control actions before being applied to the physical system, and monitoring of the status of the power grid in locations where physical measurements are not available. The implementation in a hardware-in-the-Ioop (HIL) testbed is introduced for power distribution systems that integrate a variety of devices such as protection relays, distributed energy resources, and energy storage. Finally, results in a modified IEEE 13 node test feeder illustrate that the proposed structure is capable of detecting and mitigating cyber attacks, and also validate control commands before being executed.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131745062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9961034
M. Nafees, N. Saxena, P. Burnap
The Automatic Generation Control (AGC), a fundamental frequency control system, is vulnerable to cyber-physical attacks. Coordinated false data injection attack, aiming to generate fake transient measurements, typically precedes unwarranted actions, inducing frequency excursion, leading to electromechanical swings between generators, blackouts, and costly equipment damage. Unlike other works that focus on point anomaly detection, this work focuses on contextual detection of stealthy cyber-attacks against AGC by utilizing prior information, which is essential for power system operation and situational awareness. More specifically, we depart from the traditional deep learning anomaly detection that is thoroughly driven by black-box detection; instead, we envision an approach based on physics-informed hybrid deep learning detection 'CLDPhy,’ which utilizes the combination of prior knowledge of physics and system metrics. Our method, to the extent of our knowledge, is the first context-based anomaly detection for stealthy cyber-physical attacks against the AGC system. We evaluate our approach on an industrial high-class PowerWorld simulated dataset - based on the IEEE 37-bus model. Our experiments observe a 36.4% improvement in accuracy for coordinated attack detection with contextual information, and our approach clearly demonstrates the superiority in comparison with other baselines.
{"title":"On The Efficacy of Physics-Informed Context-Based Anomaly Detection for Power Systems","authors":"M. Nafees, N. Saxena, P. Burnap","doi":"10.1109/SmartGridComm52983.2022.9961034","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9961034","url":null,"abstract":"The Automatic Generation Control (AGC), a fundamental frequency control system, is vulnerable to cyber-physical attacks. Coordinated false data injection attack, aiming to generate fake transient measurements, typically precedes unwarranted actions, inducing frequency excursion, leading to electromechanical swings between generators, blackouts, and costly equipment damage. Unlike other works that focus on point anomaly detection, this work focuses on contextual detection of stealthy cyber-attacks against AGC by utilizing prior information, which is essential for power system operation and situational awareness. More specifically, we depart from the traditional deep learning anomaly detection that is thoroughly driven by black-box detection; instead, we envision an approach based on physics-informed hybrid deep learning detection 'CLDPhy,’ which utilizes the combination of prior knowledge of physics and system metrics. Our method, to the extent of our knowledge, is the first context-based anomaly detection for stealthy cyber-physical attacks against the AGC system. We evaluate our approach on an industrial high-class PowerWorld simulated dataset - based on the IEEE 37-bus model. Our experiments observe a 36.4% improvement in accuracy for coordinated attack detection with contextual information, and our approach clearly demonstrates the superiority in comparison with other baselines.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131847521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-25DOI: 10.1109/SmartGridComm52983.2022.9960966
Guihai Zhang, B. Sikdar
Demand Response (DR) mechanisms aim to balance power supply and demand in smart grids by modulating consumers' demand and adjusting electric price based on power consumption patterns and forecasts. Deep Learning (DL) networks have been proved to have better detection of False Data Injection (FDI) attacks in such DR system than traditional statistical methods. Adversarial Machine Learning (AML) attacks can generate finely perturbed data that can mislead or disrupt the normal performance of a DL network and bypass DL-based attack detection in DR systems. However, existing AML attack methods in DR systems require a substitute model to generate the adversarial data and rely on the transferability of the data to attack the target DL models or the others. In this paper, a novel attack method called Ensemble and Transfer Adversarial Attack (ETAA) is proposed to improve the transferability of adversarial attacks across different DL models. This method has a general framework and is able to work with various existing gradient-based attacks. Moreover, to reduce the power company's awareness of FDI attack in the demand data, a zero-mean plane projection is applied to limit the perturbations during adversarial data generation. The evaluation results show that the proposed ETAA method can achieve higher attack success rate across different models and the zero-mean projection method can keep the final total adversarial power demand to be closer to the original normal demand.
{"title":"Ensemble and Transfer Adversarial Attack on Smart Grid Demand-Response Mechanisms","authors":"Guihai Zhang, B. Sikdar","doi":"10.1109/SmartGridComm52983.2022.9960966","DOIUrl":"https://doi.org/10.1109/SmartGridComm52983.2022.9960966","url":null,"abstract":"Demand Response (DR) mechanisms aim to balance power supply and demand in smart grids by modulating consumers' demand and adjusting electric price based on power consumption patterns and forecasts. Deep Learning (DL) networks have been proved to have better detection of False Data Injection (FDI) attacks in such DR system than traditional statistical methods. Adversarial Machine Learning (AML) attacks can generate finely perturbed data that can mislead or disrupt the normal performance of a DL network and bypass DL-based attack detection in DR systems. However, existing AML attack methods in DR systems require a substitute model to generate the adversarial data and rely on the transferability of the data to attack the target DL models or the others. In this paper, a novel attack method called Ensemble and Transfer Adversarial Attack (ETAA) is proposed to improve the transferability of adversarial attacks across different DL models. This method has a general framework and is able to work with various existing gradient-based attacks. Moreover, to reduce the power company's awareness of FDI attack in the demand data, a zero-mean plane projection is applied to limit the perturbations during adversarial data generation. The evaluation results show that the proposed ETAA method can achieve higher attack success rate across different models and the zero-mean projection method can keep the final total adversarial power demand to be closer to the original normal demand.","PeriodicalId":252202,"journal":{"name":"2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123382833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：