Pub Date : 2021-09-02DOI: 10.1109/SmartGridComm51999.2021.9632288
R. Sadnan, T. Asaki, A. Dubey
Managing optimal operations for power distribution systems centrally have significant limitations that motivates distributed computational paradigm. However, for managing fast varying phenomena - resulting from highly variable distributed energy resources (DERs), the existing distributed optimization approaches are inefficient. Related online distributed control methods are equally limited in their applications. They require thousands of time-steps to track the network-level optimal solutions, resulting in slow performance. We have previously developed an online distributed controller that leverages the system's radial topology to achieve network-level optimal solutions within a few time steps. However, it requires solving a node-level nonlinear programming problem at each time step. This paper analyzes the solution space for the node-level optimization problem and derives the analytical closed-form solutions for the decision variables. The theoretical analysis of the node-level optimization problem and obtained closed-form optimal solutions eliminate the need for embedded optimization solvers at each distributed agent and significantly reduce the computational time and optimization costs.
{"title":"Online Distributed Optimization in Radial Power Distribution Systems: Closed-Form Expressions","authors":"R. Sadnan, T. Asaki, A. Dubey","doi":"10.1109/SmartGridComm51999.2021.9632288","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9632288","url":null,"abstract":"Managing optimal operations for power distribution systems centrally have significant limitations that motivates distributed computational paradigm. However, for managing fast varying phenomena - resulting from highly variable distributed energy resources (DERs), the existing distributed optimization approaches are inefficient. Related online distributed control methods are equally limited in their applications. They require thousands of time-steps to track the network-level optimal solutions, resulting in slow performance. We have previously developed an online distributed controller that leverages the system's radial topology to achieve network-level optimal solutions within a few time steps. However, it requires solving a node-level nonlinear programming problem at each time step. This paper analyzes the solution space for the node-level optimization problem and derives the analytical closed-form solutions for the decision variables. The theoretical analysis of the node-level optimization problem and obtained closed-form optimal solutions eliminate the need for embedded optimization solvers at each distributed agent and significantly reduce the computational time and optimization costs.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116214640","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 : 2021-09-02DOI: 10.1109/SmartGridComm51999.2021.9632292
Gayathri Krishnamoorthy, A. Dubey
Reinforcement learning algorithms have been found useful in solving optimal power flow (OPF) problems in electric power distribution systems. However, the use of largely model-free reinforcement learning algorithms that completely ignore the physics-based modeling of the power grid compromises the optimizer performance and poses scalability challenges. This paper proposes a novel approach to synergistically combine the physics-based models with learning-based algorithms using imitation learning to solve distribution-level OPF problems. Specifically, we propose imitation learning based improvements in deep reinforcement learning (DRL) methods to solve the OPF problem for a specific case of battery storage dispatch in the power distribution systems. The proposed imitation learning algorithm uses the approximate optimal solutions obtained from a linearized model-based OPF solver to provide a good initial policy for the DRL algorithms while improving the training efficiency. The effectiveness of the proposed approach is demonstrated using IEEE 34-bus and 123-bus distribution feeders with numerous distribution-level battery storage systems.
{"title":"Reinforcement Learning for Battery Energy Storage Dispatch augmented with Model-based Optimizer","authors":"Gayathri Krishnamoorthy, A. Dubey","doi":"10.1109/SmartGridComm51999.2021.9632292","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9632292","url":null,"abstract":"Reinforcement learning algorithms have been found useful in solving optimal power flow (OPF) problems in electric power distribution systems. However, the use of largely model-free reinforcement learning algorithms that completely ignore the physics-based modeling of the power grid compromises the optimizer performance and poses scalability challenges. This paper proposes a novel approach to synergistically combine the physics-based models with learning-based algorithms using imitation learning to solve distribution-level OPF problems. Specifically, we propose imitation learning based improvements in deep reinforcement learning (DRL) methods to solve the OPF problem for a specific case of battery storage dispatch in the power distribution systems. The proposed imitation learning algorithm uses the approximate optimal solutions obtained from a linearized model-based OPF solver to provide a good initial policy for the DRL algorithms while improving the training efficiency. The effectiveness of the proposed approach is demonstrated using IEEE 34-bus and 123-bus distribution feeders with numerous distribution-level battery storage systems.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122646608","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 : 2021-08-09DOI: 10.36227/techrxiv.15124416.v1
Ardiansyah Musa Efendi, Yeonghyeon Kim, Deokjai Choi
Battery energy storage (BES) participation in the grid ancillary services markets is increasing rapidly in recent years. To facilitate optimal participation, the need for accurate BES state-of-charge (SOC) forecasting is indispensable. In grid ancillary services, the development of SOC forecasting models should deal with uncertainties and corresponding stochastic processes that determine the BES SOC periodically. Several traditional and state-of-the-art machine learning (ML) techniques, ranging from decision-tree to deep learning methods, were used to solve this problem. However, developing a multi-step SOC forecasting model remains a challenge in this subject that is essential for optimal BES economic dispatch and unit commitment. Taking advantage of the Long short-term memory (LSTM) deep learning and its variants techniques which are proven to be a robust method for predicting sequentially dependent data in the time-series domain, this paper proposes LSTM-based multi-step SOC forecasting for BES operating in frequency regulation. Various developed models, i.e., Vanilla-LSTM, Vanilla-Gated Recurrent Units (GRU), Bidirectional-LSTM (Bi-LSTM), and Bi-GRU, are evaluated using real-world datasets. The evaluation results show that the developed models outperform the existing methods in terms of root mean square error (RMSE) and mean absolute error (MAE) evaluation metrics.
{"title":"LSTM-based Multi-Step SOC Forecasting of Battery Energy Storage in Grid Ancillary Services","authors":"Ardiansyah Musa Efendi, Yeonghyeon Kim, Deokjai Choi","doi":"10.36227/techrxiv.15124416.v1","DOIUrl":"https://doi.org/10.36227/techrxiv.15124416.v1","url":null,"abstract":"Battery energy storage (BES) participation in the grid ancillary services markets is increasing rapidly in recent years. To facilitate optimal participation, the need for accurate BES state-of-charge (SOC) forecasting is indispensable. In grid ancillary services, the development of SOC forecasting models should deal with uncertainties and corresponding stochastic processes that determine the BES SOC periodically. Several traditional and state-of-the-art machine learning (ML) techniques, ranging from decision-tree to deep learning methods, were used to solve this problem. However, developing a multi-step SOC forecasting model remains a challenge in this subject that is essential for optimal BES economic dispatch and unit commitment. Taking advantage of the Long short-term memory (LSTM) deep learning and its variants techniques which are proven to be a robust method for predicting sequentially dependent data in the time-series domain, this paper proposes LSTM-based multi-step SOC forecasting for BES operating in frequency regulation. Various developed models, i.e., Vanilla-LSTM, Vanilla-Gated Recurrent Units (GRU), Bidirectional-LSTM (Bi-LSTM), and Bi-GRU, are evaluated using real-world datasets. The evaluation results show that the developed models outperform the existing methods in terms of root mean square error (RMSE) and mean absolute error (MAE) evaluation metrics.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127119072","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 : 2021-07-17DOI: 10.1109/SmartGridComm51999.2021.9632285
Mohammadhadi Shateri, Francisco Messina, P. Piantanida, F. Labeau
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.
{"title":"Learning Sparse Privacy-Preserving Representations for Smart Meters Data","authors":"Mohammadhadi Shateri, Francisco Messina, P. Piantanida, F. Labeau","doi":"10.1109/SmartGridComm51999.2021.9632285","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9632285","url":null,"abstract":"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.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114476224","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 : 2021-06-30DOI: 10.1109/SmartGridComm51999.2021.9631995
Jochen Stiasny, Samuel C. Chevalier, Spyros Chatzivasileiadis
In order to drastically reduce the heavy computational burden associated with time-domain simulations, this paper introduces a Physics-Informed Neural Network (PINN) to directly learn the solutions of power system dynamics. In contrast to the limitations of classical model order reduction approaches, commonly used to accelerate time-domain simulations, PINNs can universally approximate any continuous function with an arbitrary degree of accuracy. One of the novelties of this paper is that we avoid the need for any training data. We achieve this by incorporating the governing differential equations and an implicit Runge-Kutta (RK) integration scheme directly into the training process of the PINN; through this approach, PINNs can predict the trajectory of a dynamical power system at any discrete time step. The resulting Runge-Kutta-based physics-informed neural networks (RK-PINNs) can yield up to 100 times faster evaluations of the dynamics compared to standard time-domain simulations. We demonstrate the methodology on a single-machine infinite bus system governed by the swing equation. We show that RK-PINNs can accurately and quickly predict the solution trajectories.
{"title":"Learning without Data: Physics-Informed Neural Networks for Fast Time-Domain Simulation","authors":"Jochen Stiasny, Samuel C. Chevalier, Spyros Chatzivasileiadis","doi":"10.1109/SmartGridComm51999.2021.9631995","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9631995","url":null,"abstract":"In order to drastically reduce the heavy computational burden associated with time-domain simulations, this paper introduces a Physics-Informed Neural Network (PINN) to directly learn the solutions of power system dynamics. In contrast to the limitations of classical model order reduction approaches, commonly used to accelerate time-domain simulations, PINNs can universally approximate any continuous function with an arbitrary degree of accuracy. One of the novelties of this paper is that we avoid the need for any training data. We achieve this by incorporating the governing differential equations and an implicit Runge-Kutta (RK) integration scheme directly into the training process of the PINN; through this approach, PINNs can predict the trajectory of a dynamical power system at any discrete time step. The resulting Runge-Kutta-based physics-informed neural networks (RK-PINNs) can yield up to 100 times faster evaluations of the dynamics compared to standard time-domain simulations. We demonstrate the methodology on a single-machine infinite bus system governed by the swing equation. We show that RK-PINNs can accurately and quickly predict the solution trajectories.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123720640","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 : 2021-06-28DOI: 10.1109/SmartGridComm51999.2021.9632308
Rahul Nellikkath, Spyros Chatzivasileiadis
Physics-informed neural networks exploit the existing models of the underlying physical systems to generate higher accuracy results with fewer data. Such approaches can help drastically reduce the computation time and generate a good estimate of computationally intensive processes in power systems, such as dynamic security assessment or optimal power flow. Combined with the extraction of worst-case guarantees for the neural network performance, such neural networks can be applied in safety-critical applications in power systems and build a high level of trust among power system operators. This paper takes the first step and applies, for the first time to our knowledge, Physics-Informed Neural Networks with Worst-Case Guarantees for the DC Optimal Power Flow problem. We look for guarantees related to (i) maximum constraint violations, (ii) maximum distance between predicted and optimal decision variables, and (iii) maximum sub-optimality in the entire input domain. In a range of PGLib-OPF networks, we demonstrate how physics-informed neural networks can be supplied with worst-case guarantees and how they can lead to reduced worst-case violations compared with conventional neural networks.
{"title":"Physics-Informed Neural Networks for Minimising Worst-Case Violations in DC Optimal Power Flow","authors":"Rahul Nellikkath, Spyros Chatzivasileiadis","doi":"10.1109/SmartGridComm51999.2021.9632308","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9632308","url":null,"abstract":"Physics-informed neural networks exploit the existing models of the underlying physical systems to generate higher accuracy results with fewer data. Such approaches can help drastically reduce the computation time and generate a good estimate of computationally intensive processes in power systems, such as dynamic security assessment or optimal power flow. Combined with the extraction of worst-case guarantees for the neural network performance, such neural networks can be applied in safety-critical applications in power systems and build a high level of trust among power system operators. This paper takes the first step and applies, for the first time to our knowledge, Physics-Informed Neural Networks with Worst-Case Guarantees for the DC Optimal Power Flow problem. We look for guarantees related to (i) maximum constraint violations, (ii) maximum distance between predicted and optimal decision variables, and (iii) maximum sub-optimality in the entire input domain. In a range of PGLib-OPF networks, we demonstrate how physics-informed neural networks can be supplied with worst-case guarantees and how they can lead to reduced worst-case violations compared with conventional neural networks.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"254 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115630688","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 : 2021-06-19DOI: 10.1109/SmartGridComm51999.2021.9631993
Y. Lu, Ilgiz Murzakhanov, Spyros Chatzivasileiadis
With the rapid growth of renewable energy, lots of small photovoltaic (PV) prosumers emerge. Due to the uncertainty of solar power generation, there is a need for aggregated prosumers to predict solar power generation and whether solar power generation will be larger than load. This paper presents two interpretable neural networks to solve the problem: one binary classification neural network and one regression neural network. The neural networks are built using TensorFlow. The global feature importance and local feature contributions are examined by three gradient-based methods: Integrated Gradients, Expected Gradients, and DeepLIFT. Moreover, we detect abnormal cases when predictions might fail by estimating the prediction uncertainty using Bayesian neural networks. Neural networks, which are interpreted by the gradient-based methods and complemented with uncertainty estimation, provide robust and explainable forecasting for decision-makers.
{"title":"Neural network interpretability for forecasting of aggregated renewable generation","authors":"Y. Lu, Ilgiz Murzakhanov, Spyros Chatzivasileiadis","doi":"10.1109/SmartGridComm51999.2021.9631993","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9631993","url":null,"abstract":"With the rapid growth of renewable energy, lots of small photovoltaic (PV) prosumers emerge. Due to the uncertainty of solar power generation, there is a need for aggregated prosumers to predict solar power generation and whether solar power generation will be larger than load. This paper presents two interpretable neural networks to solve the problem: one binary classification neural network and one regression neural network. The neural networks are built using TensorFlow. The global feature importance and local feature contributions are examined by three gradient-based methods: Integrated Gradients, Expected Gradients, and DeepLIFT. Moreover, we detect abnormal cases when predictions might fail by estimating the prediction uncertainty using Bayesian neural networks. Neural networks, which are interpreted by the gradient-based methods and complemented with uncertainty estimation, provide robust and explainable forecasting for decision-makers.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134180787","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 : 2021-06-16DOI: 10.36227/techrxiv.14781489
Dino Živojević, Muhamed Delalic, Darijo Raca, D. Vukobratović, M. Cosovic
Estimating the system state is a non-trivial task given a large set of measurements, fuelling the ongoing research attempts to find efficient, scalable and fast state estimation (SE) algorithms. The centralised SE becomes impractical for large-scale systems, particularly if the measurements are spatially distributed across wide geographical areas. Dividing the large-scale systems into clusters (i.e., subsystems) and distributing the computation across clusters, solves the constraints of a centralised based approach. In such scenarios, using distributed SE methods brings many advantages over the centralised approaches. In this paper, we propose a novel distributed method to solve the linear SE model by combining local solutions obtained by applying weighted least-squares (WLS) of the given subsystems with the Gaussian belief propagation (GBP) algorithm. The proposed method is based on the factor graph operating without a central coordinator, where subsystems exchange only “beliefs”, thus preserving the privacy of the measurement data and state variables. Further, we propose an approach to speed-up evaluation of the local solutions upon arrival of new information to the subsystem. Finally, the proposed algorithm reaches the accuracy of the centralised WLS solution in a few iterations and outperforms the vanilla GBP algorithm with respect to its convergence properties.
{"title":"Distributed Weighted Least-Squares and Gaussian Belief Propagation: An Integrated Approach","authors":"Dino Živojević, Muhamed Delalic, Darijo Raca, D. Vukobratović, M. Cosovic","doi":"10.36227/techrxiv.14781489","DOIUrl":"https://doi.org/10.36227/techrxiv.14781489","url":null,"abstract":"Estimating the system state is a non-trivial task given a large set of measurements, fuelling the ongoing research attempts to find efficient, scalable and fast state estimation (SE) algorithms. The centralised SE becomes impractical for large-scale systems, particularly if the measurements are spatially distributed across wide geographical areas. Dividing the large-scale systems into clusters (i.e., subsystems) and distributing the computation across clusters, solves the constraints of a centralised based approach. In such scenarios, using distributed SE methods brings many advantages over the centralised approaches. In this paper, we propose a novel distributed method to solve the linear SE model by combining local solutions obtained by applying weighted least-squares (WLS) of the given subsystems with the Gaussian belief propagation (GBP) algorithm. The proposed method is based on the factor graph operating without a central coordinator, where subsystems exchange only “beliefs”, thus preserving the privacy of the measurement data and state variables. Further, we propose an approach to speed-up evaluation of the local solutions upon arrival of new information to the subsystem. Finally, the proposed algorithm reaches the accuracy of the centralised WLS solution in a few iterations and outperforms the vanilla GBP algorithm with respect to its convergence properties.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123142245","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 : 2021-06-14DOI: 10.1109/SmartGridComm51999.2021.9632335
Johannes Kruse, B. Schäfer, D. Witthaut
Deterministic frequency deviations (DFDs) critically affect power grid frequency quality and power system stability. A better understanding of these events is urgently needed as frequency deviations raise the need for substantial control actions and thereby increase cost of operation. DFDs are partially explained by the rapid adjustment of power generation following the intervals of electricity trading, but this intuitive picture fails especially before and around noonday. In this article, we provide a detailed analysis of DFDs and their relation to external features using methods from eXplainable Artificial Intelligence. We establish a machine learning model that well describes the daily cycle of DFDs and elucidate key interdependencies using SHapley Additive exPlanations. Thereby, we identify solar ramps as critical to explain patterns in the Rate of Change of Frequency (RoCoF).
{"title":"Exploring deterministic frequency deviations with explainable AI","authors":"Johannes Kruse, B. Schäfer, D. Witthaut","doi":"10.1109/SmartGridComm51999.2021.9632335","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9632335","url":null,"abstract":"Deterministic frequency deviations (DFDs) critically affect power grid frequency quality and power system stability. A better understanding of these events is urgently needed as frequency deviations raise the need for substantial control actions and thereby increase cost of operation. DFDs are partially explained by the rapid adjustment of power generation following the intervals of electricity trading, but this intuitive picture fails especially before and around noonday. In this article, we provide a detailed analysis of DFDs and their relation to external features using methods from eXplainable Artificial Intelligence. We establish a machine learning model that well describes the daily cycle of DFDs and elucidate key interdependencies using SHapley Additive exPlanations. Thereby, we identify solar ramps as critical to explain patterns in the Rate of Change of Frequency (RoCoF).","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133878253","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 : 2021-03-25DOI: 10.1109/SmartGridComm51999.2021.9632000
Xiaorui Liu, Yaodan Hu, Charalambos Konstantinou, Yier Jin
The reliable operation of power grid is supported by energy management systems (EMS) that provide monitoring and control functionalities. Contingency analysis is a critical application of EMS to evaluate the impacts of outages and prepare for system failures. However, false data injection attacks (FDIAs) have demonstrated the possibility of compromising sensor measurements and falsifying the estimated power system states. As a result, FDIAs may mislead system operations and other EMS applications including contingency analysis and optimal power flow. In this paper, we assess the effect of FDIAs and demonstrate that such attacks can affect the resulted number of contingencies. In order to mitigate the FDIA impact, we propose CHIMERA, a hybrid attack-resilient state estimation approach that integrates model-based and data-driven methods. CHIMERA combines the physical grid information with a Long Short Term Memory (LSTM)-based deep learning model by considering a static loss of weighted least square errors and a dynamic loss of the difference between the temporal variations of the actual and the estimated active power. Our simulation experiments based on the load data from New York state demonstrate that CHIMERA can effectively mitigate 91.74% of the cases in which FDIAs can maliciously modify the contingencies.
{"title":"CHIMERA: A Hybrid Estimation Approach to Limit the Effects of False Data Injection Attacks","authors":"Xiaorui Liu, Yaodan Hu, Charalambos Konstantinou, Yier Jin","doi":"10.1109/SmartGridComm51999.2021.9632000","DOIUrl":"https://doi.org/10.1109/SmartGridComm51999.2021.9632000","url":null,"abstract":"The reliable operation of power grid is supported by energy management systems (EMS) that provide monitoring and control functionalities. Contingency analysis is a critical application of EMS to evaluate the impacts of outages and prepare for system failures. However, false data injection attacks (FDIAs) have demonstrated the possibility of compromising sensor measurements and falsifying the estimated power system states. As a result, FDIAs may mislead system operations and other EMS applications including contingency analysis and optimal power flow. In this paper, we assess the effect of FDIAs and demonstrate that such attacks can affect the resulted number of contingencies. In order to mitigate the FDIA impact, we propose CHIMERA, a hybrid attack-resilient state estimation approach that integrates model-based and data-driven methods. CHIMERA combines the physical grid information with a Long Short Term Memory (LSTM)-based deep learning model by considering a static loss of weighted least square errors and a dynamic loss of the difference between the temporal variations of the actual and the estimated active power. Our simulation experiments based on the load data from New York state demonstrate that CHIMERA can effectively mitigate 91.74% of the cases in which FDIAs can maliciously modify the contingencies.","PeriodicalId":378884,"journal":{"name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121656559","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：