Pub Date : 2017-09-01DOI: 10.1109/ISAP.2017.8071424
A. Sahu, H. N. R. K. Tippanaboyana, Lindsay Hefton, A. Goulart
Advanced Metering Infrastructure (AMI) is an integral part of smart power grids. With advanced computing and communications, cybersecurity has emerged to be a critical issue for AMI networks, which demand confidentiality and integrity. Cyber attackers can employ unauthorized devices, also known as rogue nodes, to steal customers' private information, modify or create wrong data that can financially impact customers, utilities, and the electricity market. To detect rogue nodes in AMI networks, we propose and simulate two Intrusion Detection Systems (IDS). Their goal is to detect man-in-the-middle attacks (MiTM), where the rogue node steals information using Address Resolution Protocol (ARP) cache poisoning. A host-based simplistic IDS for the smart meters and a network-based IDS for the data concentrator, which has a larger computing power, were implemented to detect and stop such MiTM attacks. The proposed IDS system uses a Bayesian-based machine learning technique so that the IDS learns the behavior of the attack and detects future attacks.
{"title":"Detection of rogue nodes in AMI networks","authors":"A. Sahu, H. N. R. K. Tippanaboyana, Lindsay Hefton, A. Goulart","doi":"10.1109/ISAP.2017.8071424","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071424","url":null,"abstract":"Advanced Metering Infrastructure (AMI) is an integral part of smart power grids. With advanced computing and communications, cybersecurity has emerged to be a critical issue for AMI networks, which demand confidentiality and integrity. Cyber attackers can employ unauthorized devices, also known as rogue nodes, to steal customers' private information, modify or create wrong data that can financially impact customers, utilities, and the electricity market. To detect rogue nodes in AMI networks, we propose and simulate two Intrusion Detection Systems (IDS). Their goal is to detect man-in-the-middle attacks (MiTM), where the rogue node steals information using Address Resolution Protocol (ARP) cache poisoning. A host-based simplistic IDS for the smart meters and a network-based IDS for the data concentrator, which has a larger computing power, were implemented to detect and stop such MiTM attacks. The proposed IDS system uses a Bayesian-based machine learning technique so that the IDS learns the behavior of the attack and detects future attacks.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128493850","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071394
S. Nistor, Aftab Khan, M. Sooriyabandara
The uptake of distribution generation on electricity distribution networks imposes the operators to install new measurement devices such as phasor measurement units to achieve network observability. In this paper, we propose a framework for estimating synchronized phasor measurements for a virtual node using the measurements from the other nodes in the network. This system uses a machine learning method, in particular supervised regression models, to provide estimates. We show the performance of the proposed framework comparing two widely used regression methods i.e., Generalized Linear Models and Artificial Neural Networks. We extensively evaluate the proposed approach utilizing a real-world dataset collected from a medium voltage ring feeder. Our results indicate very low error rates; the average error for voltage magnitude was approx. 0.2V while for phase angle was 0.7mrad. Such low errors indicate the potential for reducing the scale of the measuring infrastructure required on distribution networks and increasing their reliability.
{"title":"Phaser measurements estimation on distribution networks using machine learning","authors":"S. Nistor, Aftab Khan, M. Sooriyabandara","doi":"10.1109/ISAP.2017.8071394","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071394","url":null,"abstract":"The uptake of distribution generation on electricity distribution networks imposes the operators to install new measurement devices such as phasor measurement units to achieve network observability. In this paper, we propose a framework for estimating synchronized phasor measurements for a virtual node using the measurements from the other nodes in the network. This system uses a machine learning method, in particular supervised regression models, to provide estimates. We show the performance of the proposed framework comparing two widely used regression methods i.e., Generalized Linear Models and Artificial Neural Networks. We extensively evaluate the proposed approach utilizing a real-world dataset collected from a medium voltage ring feeder. Our results indicate very low error rates; the average error for voltage magnitude was approx. 0.2V while for phase angle was 0.7mrad. Such low errors indicate the potential for reducing the scale of the measuring infrastructure required on distribution networks and increasing their reliability.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126716810","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071374
Choroq. Z El Archi, T. Nasser, Jorge Alvarado
Wind systems connected to a three-phase voltage grid often experience unbalanced voltage conditions, due to differences in the loads in the grid. This issue is particularly important in wind energy conversion systems (WECS) that use the doubly fed induction generator (DFIG). Therefore, it is important to take into account unbalanced conditions when coupling the wind generator with the grid, especially since the stator of the DFIG is directly connected to the grid. In this paper, the DFIG is modeled under low asymmetrical voltage fault in the grid in order to control the power flow between the generator and the grid. A proportional integral (PI) controller is used and simulated in the study using Matlab/Simulink. The results show that the oscillations in the electromagnetic torque and the total active power can be controlled effectively to improve the quality of the power delivered to the grid.
{"title":"Modeling a DFIG based wind system for unbalanced grid voltage condition","authors":"Choroq. Z El Archi, T. Nasser, Jorge Alvarado","doi":"10.1109/ISAP.2017.8071374","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071374","url":null,"abstract":"Wind systems connected to a three-phase voltage grid often experience unbalanced voltage conditions, due to differences in the loads in the grid. This issue is particularly important in wind energy conversion systems (WECS) that use the doubly fed induction generator (DFIG). Therefore, it is important to take into account unbalanced conditions when coupling the wind generator with the grid, especially since the stator of the DFIG is directly connected to the grid. In this paper, the DFIG is modeled under low asymmetrical voltage fault in the grid in order to control the power flow between the generator and the grid. A proportional integral (PI) controller is used and simulated in the study using Matlab/Simulink. The results show that the oscillations in the electromagnetic torque and the total active power can be controlled effectively to improve the quality of the power delivered to the grid.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"1065 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132278595","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071417
J. Soares, Z. Vale, Nuno Borges, F. Lezama, N. Kagan
With the high penetration of renewable generation in Smart Grids (SG), the uncertainty behavior associated with the forecast of weather conditions possesses a new degree of complexity in the Energy Resource Management (ERM) problem. In this paper, a Multi-Objective Particle Swarm Optimization (MOPSO) methodology is proposed to solve ERM problem in buildings with penetration of Distributed Generation (DG) and Electric Vehicles (EVs) and considering the uncertainty of photovoltaic (PV) generation. The proposed methodology aims to maximize profits while minimizing CO2 emissions. The uncertainty of PV generation is modeled with the use of Monte Carlo simulation in the evaluation process of the MOPSO core. Also, a robust optimization approach is adopted to select the best solution for the worst-case scenario of PV generation. A case study is presented using a real building facility from Brazil, to verify the effectiveness of the implemented robust MOPSO.
{"title":"Multi-objective robust optimization to solve energy scheduling in buildings under uncertainty","authors":"J. Soares, Z. Vale, Nuno Borges, F. Lezama, N. Kagan","doi":"10.1109/ISAP.2017.8071417","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071417","url":null,"abstract":"With the high penetration of renewable generation in Smart Grids (SG), the uncertainty behavior associated with the forecast of weather conditions possesses a new degree of complexity in the Energy Resource Management (ERM) problem. In this paper, a Multi-Objective Particle Swarm Optimization (MOPSO) methodology is proposed to solve ERM problem in buildings with penetration of Distributed Generation (DG) and Electric Vehicles (EVs) and considering the uncertainty of photovoltaic (PV) generation. The proposed methodology aims to maximize profits while minimizing CO2 emissions. The uncertainty of PV generation is modeled with the use of Monte Carlo simulation in the evaluation process of the MOPSO core. Also, a robust optimization approach is adopted to select the best solution for the worst-case scenario of PV generation. A case study is presented using a real building facility from Brazil, to verify the effectiveness of the implemented robust MOPSO.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133514744","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071407
Wenlei Bai, I. Eke, Kwang.Y. Lee
The increasing number and types of energy resources and prosumers has complicated the operation in microgrid greatly. Such problem becomes a hard-to-solve or even impossible-to-solve for traditional mathematical algorithms without necessary approximation. However, modern heuristic optimization techniques have proven their efficiency and robustness in complex non-linear, non-convex and large-size problems. In this paper, we propose a comprehensive microgrid which consists of renewables, distributed generators, demand response, marketplace, energy storage system and prosumers, and investigate the behaviors of such system. A novel heuristic method, artificial bee colony, is proposed to solve the day-ahead optimal scheduling of the microgrid. Case studies have shown that such algorithm is able to solve the problem fast, reliable with satisfactory solutions. For the first case, the computational time is 9 minutes compared with 19 hours by a traditional methodical tool which has not taken necessary approximation of the original problem.
{"title":"Optimal scheduling of distributed energy resources by modern heuristic optimization technique","authors":"Wenlei Bai, I. Eke, Kwang.Y. Lee","doi":"10.1109/ISAP.2017.8071407","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071407","url":null,"abstract":"The increasing number and types of energy resources and prosumers has complicated the operation in microgrid greatly. Such problem becomes a hard-to-solve or even impossible-to-solve for traditional mathematical algorithms without necessary approximation. However, modern heuristic optimization techniques have proven their efficiency and robustness in complex non-linear, non-convex and large-size problems. In this paper, we propose a comprehensive microgrid which consists of renewables, distributed generators, demand response, marketplace, energy storage system and prosumers, and investigate the behaviors of such system. A novel heuristic method, artificial bee colony, is proposed to solve the day-ahead optimal scheduling of the microgrid. Case studies have shown that such algorithm is able to solve the problem fast, reliable with satisfactory solutions. For the first case, the computational time is 9 minutes compared with 19 hours by a traditional methodical tool which has not taken necessary approximation of the original problem.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131709272","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071389
M. Chamana, B. Mather
A library of load variability classes is created to produce scalable synthetic data sets using historical high-speed raw data. These data are collected from distribution monitoring units connected at the secondary side of a distribution transformer. Because of the irregular patterns and large volume of historical high-speed data sets, the utilization of current load characterization and modeling techniques are challenging. Multi-resolution analysis techniques are applied to extract the necessary components and eliminate the unnecessary components from the historical high-speed raw data to create the library of classes, which are then utilized to create new synthetic load data sets. A validation is performed to ensure that the synthesized data sets contain the same variability characteristics as the training data sets. The synthesized data sets are intended to be utilized in quasi-static time-series studies for distribution system planning studies on a granular scale, such as detailed PV interconnection studies.
{"title":"Variability extraction and synthesis via multi-resolution analysis using distribution transformer high-speed power data","authors":"M. Chamana, B. Mather","doi":"10.1109/ISAP.2017.8071389","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071389","url":null,"abstract":"A library of load variability classes is created to produce scalable synthetic data sets using historical high-speed raw data. These data are collected from distribution monitoring units connected at the secondary side of a distribution transformer. Because of the irregular patterns and large volume of historical high-speed data sets, the utilization of current load characterization and modeling techniques are challenging. Multi-resolution analysis techniques are applied to extract the necessary components and eliminate the unnecessary components from the historical high-speed raw data to create the library of classes, which are then utilized to create new synthetic load data sets. A validation is performed to ensure that the synthesized data sets contain the same variability characteristics as the training data sets. The synthesized data sets are intended to be utilized in quasi-static time-series studies for distribution system planning studies on a granular scale, such as detailed PV interconnection studies.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128633926","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071405
Shi Ruifeng, Yang Yang, Kwang.Y. Lee
Electrification of the transportation sector is gradually becoming a global trend due to the environmental benefits from electric vehicles (EVs). This efficient transport module greatly reduce the pollutant emissions, the burden on fuel expenses and uncertain matters associated with fossil fuel resources, which leads to a great likelihood of increasing the PV penetration levels in the next decades. Public fast EV charging station is definitely one of the essential infrastructures in developing the EV industry. A multi-objective EV charging station layout planning model that considers several potential factors is proposed in this paper, which takes economics, environment and convenience factors into consideration. Besides, an improved Strengthened Pareto Evolutionary Algorithm-II (SPEA-II) optimizer is also studied to obtain a satisfactory Pareto solution for decision maker's choice. Numerical case study shows that the method proposed in this paper can find a satisfactory EV charging station layout planning scheme within an acceptable computational cost.
由于电动汽车(ev)的环境效益，交通运输部门的电气化正逐渐成为全球趋势。这种高效的运输模块大大减少了污染物排放、燃料费用负担和与化石燃料资源相关的不确定事项，这使得未来几十年光伏普及率很有可能提高。公共电动汽车快速充电站无疑是发展电动汽车产业必不可少的基础设施之一。本文提出了一种考虑经济性、环境性和便利性因素的多目标电动汽车充电站布局规划模型。此外，还研究了一种改进的强化帕累托进化算法- ii (SPEA-II)优化器，以获得决策者选择的满意帕累托解。数值算例研究表明，本文提出的方法能够在可接受的计算成本范围内找到满意的电动汽车充电站布局规划方案。
{"title":"Multi-objective EV charging stations planning based on a two-layer coding SPEA-II","authors":"Shi Ruifeng, Yang Yang, Kwang.Y. Lee","doi":"10.1109/ISAP.2017.8071405","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071405","url":null,"abstract":"Electrification of the transportation sector is gradually becoming a global trend due to the environmental benefits from electric vehicles (EVs). This efficient transport module greatly reduce the pollutant emissions, the burden on fuel expenses and uncertain matters associated with fossil fuel resources, which leads to a great likelihood of increasing the PV penetration levels in the next decades. Public fast EV charging station is definitely one of the essential infrastructures in developing the EV industry. A multi-objective EV charging station layout planning model that considers several potential factors is proposed in this paper, which takes economics, environment and convenience factors into consideration. Besides, an improved Strengthened Pareto Evolutionary Algorithm-II (SPEA-II) optimizer is also studied to obtain a satisfactory Pareto solution for decision maker's choice. Numerical case study shows that the method proposed in this paper can find a satisfactory EV charging station layout planning scheme within an acceptable computational cost.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128415553","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071370
Xian-Chang Guo, J. McCalley
This paper is motivated by infeasibilities in look-ahead economic dispatch with significant wind integration; such infeasibilities result from transmission line constraints that cannot be satisfied within a security constrained economic dispatch. Thus, constraint relaxation is necessary to achieve the dispatch decisions and market solution. The acceptable relaxation margin is determined by assessing the time duration of the thermal overloads in terms of an adaptive transmission rate (ATR). ATR is calculated using the dynamic heat balance equation associated with thermal overloading probability. Furthermore, high wind energy penetration increases variability in circuit flows. We utilize conditional value at risk to evaluate the effects of overloads on system security. We propose a systematic methodology of riskbased constraint relaxation (RBCR) to eliminate the infeasibilities of thermal limits in the stochastic look-ahead SCED problem. Finally, the methodology of RBCR has been verified using an IEEE 6 bus testing system.
{"title":"Risk-based constraint relaxation with high penetration of wind resources","authors":"Xian-Chang Guo, J. McCalley","doi":"10.1109/ISAP.2017.8071370","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071370","url":null,"abstract":"This paper is motivated by infeasibilities in look-ahead economic dispatch with significant wind integration; such infeasibilities result from transmission line constraints that cannot be satisfied within a security constrained economic dispatch. Thus, constraint relaxation is necessary to achieve the dispatch decisions and market solution. The acceptable relaxation margin is determined by assessing the time duration of the thermal overloads in terms of an adaptive transmission rate (ATR). ATR is calculated using the dynamic heat balance equation associated with thermal overloading probability. Furthermore, high wind energy penetration increases variability in circuit flows. We utilize conditional value at risk to evaluate the effects of overloads on system security. We propose a systematic methodology of riskbased constraint relaxation (RBCR) to eliminate the infeasibilities of thermal limits in the stochastic look-ahead SCED problem. Finally, the methodology of RBCR has been verified using an IEEE 6 bus testing system.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127468827","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071415
Po-Chen Chen, M. Kezunovic
The weather impact a major factor in operation of power systems. From the long-term planning perspective, it is not enough to predict whether impacts caused by short-term changes in the atmosphere but one also needs to account for the impact of long-term climate change as well. This paper demonstrates how to utilize the historical weather data and climate change projections in a large (macro) geographical area to predict future load patterns in a relatively small (micro) geographical area. The results show that the impact of temperature rising can have either positive or negative impact on the load, and the deviations may be large depending on the projected climate change data.
{"title":"Load consumption prediction utilizing historical weather data and climate change projections","authors":"Po-Chen Chen, M. Kezunovic","doi":"10.1109/ISAP.2017.8071415","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071415","url":null,"abstract":"The weather impact a major factor in operation of power systems. From the long-term planning perspective, it is not enough to predict whether impacts caused by short-term changes in the atmosphere but one also needs to account for the impact of long-term climate change as well. This paper demonstrates how to utilize the historical weather data and climate change projections in a large (macro) geographical area to predict future load patterns in a relatively small (micro) geographical area. The results show that the impact of temperature rising can have either positive or negative impact on the load, and the deviations may be large depending on the projected climate change data.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129774456","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 : 2017-09-01DOI: 10.1109/ISAP.2017.8071402
Z. Nie, Duotong Yang, V. Centeno, Kevin D. Jones
According to the proposed definition and classification of power system stability addressed by IEEE and CIGRE Task Force, voltage stability refers to the stability of maintaining the steady voltage magnitudes at all buses in a power system when the system is subjected to a disturbance from a given operating condition (OC). Cascading outage due to voltage collapse is a probable consequence during insecure voltage situations. In this regard, fast responding and reliable voltage security assessment (VSA) is effective and indispensable for system to survive in conceivable contingencies. This paper aims at establishing an online systematic framework for voltage security assessment with high-speed data streams from synchrophasors and phasor data concentrators (PDCs). Periodically updated decision trees (DTs) have been applied in different subjects of security assessments in power systems. However, with a training data set of operating conditions that grows rapidly, re-training and restructuring a decision tree becomes a time-consuming process. Hoeffding-tree-based method constructs a learner that is capable of memory management to process streaming data without retaining the complete data set for training purposes in real-time and guarantees the accuracy of learner. The proposed approach of voltage security assessment based on Very Fast Decision Tree (VFDT) system is tested and evaluated by the IEEE 118-bus standard system.
{"title":"A PMU-based voltage security assessment framework using hoeffding-tree-based learning","authors":"Z. Nie, Duotong Yang, V. Centeno, Kevin D. Jones","doi":"10.1109/ISAP.2017.8071402","DOIUrl":"https://doi.org/10.1109/ISAP.2017.8071402","url":null,"abstract":"According to the proposed definition and classification of power system stability addressed by IEEE and CIGRE Task Force, voltage stability refers to the stability of maintaining the steady voltage magnitudes at all buses in a power system when the system is subjected to a disturbance from a given operating condition (OC). Cascading outage due to voltage collapse is a probable consequence during insecure voltage situations. In this regard, fast responding and reliable voltage security assessment (VSA) is effective and indispensable for system to survive in conceivable contingencies. This paper aims at establishing an online systematic framework for voltage security assessment with high-speed data streams from synchrophasors and phasor data concentrators (PDCs). Periodically updated decision trees (DTs) have been applied in different subjects of security assessments in power systems. However, with a training data set of operating conditions that grows rapidly, re-training and restructuring a decision tree becomes a time-consuming process. Hoeffding-tree-based method constructs a learner that is capable of memory management to process streaming data without retaining the complete data set for training purposes in real-time and guarantees the accuracy of learner. The proposed approach of voltage security assessment based on Very Fast Decision Tree (VFDT) system is tested and evaluated by the IEEE 118-bus standard system.","PeriodicalId":257100,"journal":{"name":"2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)","volume":"18 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133237900","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：