Pub Date : 2020-11-02DOI: 10.1109/igessc50231.2020.9285054
{"title":"IGESSC 2020 Committees","authors":"","doi":"10.1109/igessc50231.2020.9285054","DOIUrl":"https://doi.org/10.1109/igessc50231.2020.9285054","url":null,"abstract":"","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":" 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113950721","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285022
Wencheng Wu, Lei Lin, Beilei Xu, S. Wshah, R. Elmoudi
Numerical models play important roles in power system operation. They are widely used for planning studies to identify and mitigate issues, determine transfer capability, and develop transmission reinforcement plans. These models need to be accurate and updated regularly to serve these purposes faithfully over time. In this paper, we formulate the problem of parameter calibration for machine models in a power system into the framework of reinforcement learning and demonstrate the feasibility of applying Deep Deterministic Policy Gradient (DDPG) for a two-parameter generator model calibration on a 4-bus system. To improve the efficiency and accuracy of DDPG, we introduce memory forgetting mechanism and dynamic range adjustment (DRA) into the original DDPG, i.e., DRA-DDPG. To reduce the parameter estimation errors due to partially observable disturbance states in the power system, we introduce the concept of maximal K-Nearest-Neighbor (KNN) reward to enable our reinforcement learning algorithm to accommodate a finite set (K) of unknown disturbance states in the system. Our experimental results show that the proposed DRA-DDPG outperforms the baseline DDPG in terms of accuracy and efficiency and the proposed maximal KNN reward is well-suited for resolving the uncertainties from partially observable system states.
{"title":"Generator Model Parameter Calibration Using Reinforcement Learning","authors":"Wencheng Wu, Lei Lin, Beilei Xu, S. Wshah, R. Elmoudi","doi":"10.1109/IGESSC50231.2020.9285022","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285022","url":null,"abstract":"Numerical models play important roles in power system operation. They are widely used for planning studies to identify and mitigate issues, determine transfer capability, and develop transmission reinforcement plans. These models need to be accurate and updated regularly to serve these purposes faithfully over time. In this paper, we formulate the problem of parameter calibration for machine models in a power system into the framework of reinforcement learning and demonstrate the feasibility of applying Deep Deterministic Policy Gradient (DDPG) for a two-parameter generator model calibration on a 4-bus system. To improve the efficiency and accuracy of DDPG, we introduce memory forgetting mechanism and dynamic range adjustment (DRA) into the original DDPG, i.e., DRA-DDPG. To reduce the parameter estimation errors due to partially observable disturbance states in the power system, we introduce the concept of maximal K-Nearest-Neighbor (KNN) reward to enable our reinforcement learning algorithm to accommodate a finite set (K) of unknown disturbance states in the system. Our experimental results show that the proposed DRA-DDPG outperforms the baseline DDPG in terms of accuracy and efficiency and the proposed maximal KNN reward is well-suited for resolving the uncertainties from partially observable system states.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"abs/1609.00738 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131582972","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 : 2020-11-02DOI: 10.1109/igessc50231.2020.9284996
{"title":"IGESSC 2020 Ad Page","authors":"","doi":"10.1109/igessc50231.2020.9284996","DOIUrl":"https://doi.org/10.1109/igessc50231.2020.9284996","url":null,"abstract":"","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133637165","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285056
E. Naderi, A. Asrari
This paper approaches the optimal power flow (OPF) to generate a model of false data injection (FDI) cyberattack causing system congestions. In the developed model, hacker takes advantage of a reformulated OPF to optimally manipulate the electric load data such that the system operator is misled and the falsified data injections result in distortions in normal operation of the system. The effectiveness of the developed model from attacker’s standpoint is validated on the IEEE 30-bus system. The simulation results verify that the presented FDI approach via OPF not only leads to tie-line congestions but also negatively affects the optimal generation schedules, which implies its impact on security and economy of the system.
{"title":"Approaching Optimal Power Flow From Attacker’s Standpoint To Launch False Data Injection Cyberattack","authors":"E. Naderi, A. Asrari","doi":"10.1109/IGESSC50231.2020.9285056","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285056","url":null,"abstract":"This paper approaches the optimal power flow (OPF) to generate a model of false data injection (FDI) cyberattack causing system congestions. In the developed model, hacker takes advantage of a reformulated OPF to optimally manipulate the electric load data such that the system operator is misled and the falsified data injections result in distortions in normal operation of the system. The effectiveness of the developed model from attacker’s standpoint is validated on the IEEE 30-bus system. The simulation results verify that the presented FDI approach via OPF not only leads to tie-line congestions but also negatively affects the optimal generation schedules, which implies its impact on security and economy of the system.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"146 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128846047","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285003
T. Toups, A. B. Iglesias
The increase in electrical energy usage in residential homes has caused concerns to the power industry mainly due to the adoption of electric vehicles (EV) and renewable energy sources. A concern for power quality is the unbalanced loading that these EVs and renewable energy sources will induce in feeders. Neighborhoods and house clusters typically connect to a single phase on a feeder. Unfortunately, there is little control on which neighborhoods or houses adopt EVs and renewable energy first. Additionally, the unpredictability of EV charging and renewable energy output raises concerns as there could be times of loading that cause unbalance current in the feeder. This paper describes a method to automatically balance the loading in real time by using mechanical switches controlled with an algorithm to swap single phase loads between the phases of a feeder resulting in a more balanced three phase load current as seen at the substation.
{"title":"Feeder Load Balancing Using Phase Switching at the Load Connection Terminals","authors":"T. Toups, A. B. Iglesias","doi":"10.1109/IGESSC50231.2020.9285003","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285003","url":null,"abstract":"The increase in electrical energy usage in residential homes has caused concerns to the power industry mainly due to the adoption of electric vehicles (EV) and renewable energy sources. A concern for power quality is the unbalanced loading that these EVs and renewable energy sources will induce in feeders. Neighborhoods and house clusters typically connect to a single phase on a feeder. Unfortunately, there is little control on which neighborhoods or houses adopt EVs and renewable energy first. Additionally, the unpredictability of EV charging and renewable energy output raises concerns as there could be times of loading that cause unbalance current in the feeder. This paper describes a method to automatically balance the loading in real time by using mechanical switches controlled with an algorithm to swap single phase loads between the phases of a feeder resulting in a more balanced three phase load current as seen at the substation.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123052725","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285088
Muhammad R. Sami, M. Ibarra, Anamaria C. Esparza, S. Al-Jufout, Mehrdad Aliasgari, M. Mozumdar
In this paper, an Intrusion Detection System (IDS) in the Controller Area Network (CAN) bus of modern vehicles has been proposed. NESLIDS is an anomaly detection algorithm based on the supervised Deep Neural Network (DNN) architecture that is designed to counter three critical attack categories: Denial-of-service (DoS), fuzzy, and impersonation attacks. Our research scope included modifying DNN parameters, e.g. number of hidden layer neurons, batch size, and activation functions according to how well it maximized detection accuracy and minimized the false positive rate (FPR) for these attacks. Our methodology consisted of collecting CAN Bus data from online and in real-time, injecting attack data after data collection, preprocessing in Python, training the DNN, and testing the model with different datasets. Results show that the proposed IDS effectively detects all attack types for both types of datasets. NESLIDS outperforms existing approaches in terms of accuracy, scalability, and low false alarm rates.
{"title":"Rapid, Multi-vehicle and Feed-forward Neural Network based Intrusion Detection System for Controller Area Network Bus","authors":"Muhammad R. Sami, M. Ibarra, Anamaria C. Esparza, S. Al-Jufout, Mehrdad Aliasgari, M. Mozumdar","doi":"10.1109/IGESSC50231.2020.9285088","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285088","url":null,"abstract":"In this paper, an Intrusion Detection System (IDS) in the Controller Area Network (CAN) bus of modern vehicles has been proposed. NESLIDS is an anomaly detection algorithm based on the supervised Deep Neural Network (DNN) architecture that is designed to counter three critical attack categories: Denial-of-service (DoS), fuzzy, and impersonation attacks. Our research scope included modifying DNN parameters, e.g. number of hidden layer neurons, batch size, and activation functions according to how well it maximized detection accuracy and minimized the false positive rate (FPR) for these attacks. Our methodology consisted of collecting CAN Bus data from online and in real-time, injecting attack data after data collection, preprocessing in Python, training the DNN, and testing the model with different datasets. Results show that the proposed IDS effectively detects all attack types for both types of datasets. NESLIDS outperforms existing approaches in terms of accuracy, scalability, and low false alarm rates.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126121599","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285092
Max K. Gutierrez, David Choi, H. Jula
The purpose of this paper is to develop a methodology for using a Genetic Algorithm (GA) to tune a PID controller, which will stabilize a ball-and-beam system. A brief overview of GAs will be given followed by a short introduction of the ball-and-beam system, to which a GA will be applied. Next, the method of applying a GA to a PID controller for optimization is discussed. A conventional PID controller and an LQR controller will be designed for the purpose of evaluating the cost associated with these controllers against the cost associated with the GA optimized PID controller. The final results show that a PID controller tuned using the GA is more cost efficient than a conventionally tuned PID controller, but less cost efficient than a conventionally tuned LQR controller.
{"title":"Using Genetic Algorithms to Optimize Control of a Ball-and-Beam System","authors":"Max K. Gutierrez, David Choi, H. Jula","doi":"10.1109/IGESSC50231.2020.9285092","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285092","url":null,"abstract":"The purpose of this paper is to develop a methodology for using a Genetic Algorithm (GA) to tune a PID controller, which will stabilize a ball-and-beam system. A brief overview of GAs will be given followed by a short introduction of the ball-and-beam system, to which a GA will be applied. Next, the method of applying a GA to a PID controller for optimization is discussed. A conventional PID controller and an LQR controller will be designed for the purpose of evaluating the cost associated with these controllers against the cost associated with the GA optimized PID controller. The final results show that a PID controller tuned using the GA is more cost efficient than a conventionally tuned PID controller, but less cost efficient than a conventionally tuned LQR controller.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128226889","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285101
Sainesh Karan, H. Yeh
In this work, two neural network models i.e. Long - Short Term Memory (LSTM) Networks and Convolutional Neural Networks (CNN) are employed to classify faults in microgrids. We used Matlab/Simulink to model a modified IEEE-13 bus feeder and simulate 11 types of faults to generate training and testing data. Additive White Gaussian Noise (AWGN) and Additive Impulsive Gaussian Noise (AIGN) are added to the data to make it closer to real-world data. The data is pre-processed using Discrete Wavelet Transform (DWT) and Multi-Resolution Analysis (MRA). The investigation showed that the LSTM network out-performed the CNN classifier and achieved high accuracy in classifying the faults using only one signal cycle of post fault voltage.
{"title":"Fault Classification in Microgrids using Deep Learning","authors":"Sainesh Karan, H. Yeh","doi":"10.1109/IGESSC50231.2020.9285101","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285101","url":null,"abstract":"In this work, two neural network models i.e. Long - Short Term Memory (LSTM) Networks and Convolutional Neural Networks (CNN) are employed to classify faults in microgrids. We used Matlab/Simulink to model a modified IEEE-13 bus feeder and simulate 11 types of faults to generate training and testing data. Additive White Gaussian Noise (AWGN) and Additive Impulsive Gaussian Noise (AIGN) are added to the data to make it closer to real-world data. The data is pre-processed using Discrete Wavelet Transform (DWT) and Multi-Resolution Analysis (MRA). The investigation showed that the LSTM network out-performed the CNN classifier and achieved high accuracy in classifying the faults using only one signal cycle of post fault voltage.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122938553","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9284999
M. Arifujjaman, R. Salas, A. Johnson, J. Araiza, J. Mauzey
Southern California Edison (SCE) is in the development stages on various microgrid (MG) projects aimed at improving resiliency while maintaining grid reliability and safety during planned and unplanned outages, including Public Safety Power Shutoffs (PSPS). This paper aims to recognize the impact of negative-sequence voltage on an inverter for a photovoltaic (PV) based distributed generation connected in an islanded MG. A comprehensive mathematical model of the inverter along with the PV and boost converter is proposed to perform the analytical simulation in Matlab environment. It is established that the inverter design capacity is required to be significantly higher in order to meet the imbalance current caused by only a 2% negative-sequence voltage. Thus, an adequate design of the inverter that meets SCE’s needs is crucial; otherwise, the inverter will shut down prematurely due to the imposed design constraint by the manufacturer. This will hinder the success of current and future SCE-led MG projects.
{"title":"Impact of Negative-Sequence Voltage on Inverter in an Islanded Microgrid","authors":"M. Arifujjaman, R. Salas, A. Johnson, J. Araiza, J. Mauzey","doi":"10.1109/IGESSC50231.2020.9284999","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9284999","url":null,"abstract":"Southern California Edison (SCE) is in the development stages on various microgrid (MG) projects aimed at improving resiliency while maintaining grid reliability and safety during planned and unplanned outages, including Public Safety Power Shutoffs (PSPS). This paper aims to recognize the impact of negative-sequence voltage on an inverter for a photovoltaic (PV) based distributed generation connected in an islanded MG. A comprehensive mathematical model of the inverter along with the PV and boost converter is proposed to perform the analytical simulation in Matlab environment. It is established that the inverter design capacity is required to be significantly higher in order to meet the imbalance current caused by only a 2% negative-sequence voltage. Thus, an adequate design of the inverter that meets SCE’s needs is crucial; otherwise, the inverter will shut down prematurely due to the imposed design constraint by the manufacturer. This will hinder the success of current and future SCE-led MG projects.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115676171","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285096
I. Rivera, S. Kwon
Satellite communication and cellular communication systems have not been cooperative for use cases during the past two decades. However, recent research seriously takes into account consolidating satellite and cellular communication systems in 5th and 6th generation (5G and 6G) wireless communications. This paper analyzes the potential symbol error rate (SER) performance considering 5G coordinated multi-point (CoMP) transmission with the satellite and next-generation Node B (gNB), considering adaptive modulation in satellite communication downlink. The comprehensive simulations consider higher-order modulation schemes than those conventionally supported by the satellite in a variety of scenarios in terms of phase noise, modulation order, and altitude of satellite or unmanned aerial vehicle (UAV). The simulation results exhibit that satellites or UAVs need to adaptively change their modulation schemes.
{"title":"5G Satellite-Cellular Coexistence: SER Analysis toward Coordinated Adaptive Modulation","authors":"I. Rivera, S. Kwon","doi":"10.1109/IGESSC50231.2020.9285096","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285096","url":null,"abstract":"Satellite communication and cellular communication systems have not been cooperative for use cases during the past two decades. However, recent research seriously takes into account consolidating satellite and cellular communication systems in 5th and 6th generation (5G and 6G) wireless communications. This paper analyzes the potential symbol error rate (SER) performance considering 5G coordinated multi-point (CoMP) transmission with the satellite and next-generation Node B (gNB), considering adaptive modulation in satellite communication downlink. The comprehensive simulations consider higher-order modulation schemes than those conventionally supported by the satellite in a variety of scenarios in terms of phase noise, modulation order, and altitude of satellite or unmanned aerial vehicle (UAV). The simulation results exhibit that satellites or UAVs need to adaptively change their modulation schemes.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124795886","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：