The Experts below are selected from a list of 510 Experts worldwide ranked by ideXlab platform
Mo-yuen Chow - One of the best experts on this subject based on the ideXlab platform.
-
Distribution fault diagnosis using a hybrid algorithm of fuzzy classification and artificial immune systems
2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century, 2008Co-Authors: Le Xu, Mo-yuen ChowAbstract:Effective distribution outage cause identification can help expedite the restoration procedure and improve the system availability. The fuzzy classification E-algorithm and the immune system inspired classification algorithm, artificial immune recognition system (AIRS), have demonstrated good capabilities in outage cause identification, especially with the existence of imbalanced data. E-algorithm extracts inference rules but is computational demanding; AIRS has the quick searching capability but is lack of rule extraction capability. In this paper, fuzzy artificial immune recognition system (FAIRS) has been proposed to take advantage of the strengths of E-algorithm and AIRS. FAIRS is applied to Duke Energy outage data for cause identification using three major customer interruption causes (tree, animal, and lightning) as prototypes; and FAIRS achieves comparable fault diagnosis performance with two base algorithms while being able to extract linguistic rules to explain the inference within significantly reduced computing time than E-algorithm.
-
Power Distribution Outage Cause Identification using Fuzzy Artificial Immune Recognition Systems (FAIRS) algorithm
2007 IEEE Power Engineering Society General Meeting, 2007Co-Authors: Le Xu, Mo-yuen Chow, J. TimmisAbstract:Power distribution systems have been significantly affected by many events. Effective outage cause identification can help expedite the restoration procedure and improve the system reliability. Fuzzy classification E-algorithm and biological immune system based AIRS algorithm have demonstrated good capability in outage cause identification especially with imbalanced data, E-algorithm can produce inference rules but is computational demanding; AIRS has the quick searching capability but is lack of rule extraction capability. In this paper, fuzzy artificial immune recognition system (FAIRS) has been proposed to utilize the advantages of both E-algorithm and AIRS. FAIRS is applied to Duke Energy outage data for cause identification using three major causes (tree, animal, and lightning) as prototypes. It is compared with both E-algorithm and AIRS, and the results show that FAIRS achieves comparable performance while being able to extract linguistic rules with rule length flexibility to explain the inference with significantly reduced computing time than E-algorithm.
-
power distribution fault cause identification with imbalanced data using the data mining based fuzzy classification e algorithm
IEEE Transactions on Power Systems, 2007Co-Authors: Le Xu, Mo-yuen Chow, L.s. TaylorAbstract:Power distribution systems have been significantly affected by many outage-causing events. Good fault cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data sets often degrades the fault cause identification performance. In this paper, the E-algorithm, which is extended from the fuzzy classification algorithm by Ishibuchi to alleviate the effect of imbalanced data constitution, is applied to Duke Energy outage data for distribution fault cause identification. Three major outage causes (tree, animal, and lightning) are used as prototypes. The performance of E-algorithm on real-world imbalanced data is compared with artificial neural network. The results show that the E-algorithm can greatly improve the performance when the data are imbalanced
-
Power Distribution Outage Cause Identification With Imbalanced Data Using Artificial Immune Recognition System (AIRS) Algorithm
IEEE Transactions on Power Systems, 2007Co-Authors: Le Xu, Mo-yuen Chow, J. Timmis, Leroy S. TaylorAbstract:Power distribution systems have been significantly affected by many fault causing events. Effective outage cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data often degrades the outage cause identification performance. In this paper, artificial immune recognition system (AIRS), an immune-inspired algorithm for supervised classification task is applied to the Duke Energy outage data for outage cause identification using three major causes (tree, animal, and lightning) as prototypes. The performance of AIRS on these real-world imbalanced data is compared with an artificial neural network (ANN). The results show that AIRS can greatly improve the performance by as much as 163% when the data are imbalanced and achieve comparable performance with ANN for relatively balanced data
-
IEEE Congress on Evolutionary Computation - On the Investigation of Artificial Immune Systems on Imbalanced Data Classification for Power Distribution System Fault Cause Identification
2006 IEEE International Conference on Evolutionary Computation, 2006Co-Authors: Le Xu, Mo-yuen Chow, J. Timmis, L.s. Taylor, A. WatkinsAbstract:Imbalanced data are often encountered in real-world real-world real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm Artificial Immune Recognition System (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an Artificial Neural Network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.
Le Xu - One of the best experts on this subject based on the ideXlab platform.
-
Distribution fault diagnosis using a hybrid algorithm of fuzzy classification and artificial immune systems
2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century, 2008Co-Authors: Le Xu, Mo-yuen ChowAbstract:Effective distribution outage cause identification can help expedite the restoration procedure and improve the system availability. The fuzzy classification E-algorithm and the immune system inspired classification algorithm, artificial immune recognition system (AIRS), have demonstrated good capabilities in outage cause identification, especially with the existence of imbalanced data. E-algorithm extracts inference rules but is computational demanding; AIRS has the quick searching capability but is lack of rule extraction capability. In this paper, fuzzy artificial immune recognition system (FAIRS) has been proposed to take advantage of the strengths of E-algorithm and AIRS. FAIRS is applied to Duke Energy outage data for cause identification using three major customer interruption causes (tree, animal, and lightning) as prototypes; and FAIRS achieves comparable fault diagnosis performance with two base algorithms while being able to extract linguistic rules to explain the inference within significantly reduced computing time than E-algorithm.
-
Power Distribution Outage Cause Identification using Fuzzy Artificial Immune Recognition Systems (FAIRS) algorithm
2007 IEEE Power Engineering Society General Meeting, 2007Co-Authors: Le Xu, Mo-yuen Chow, J. TimmisAbstract:Power distribution systems have been significantly affected by many events. Effective outage cause identification can help expedite the restoration procedure and improve the system reliability. Fuzzy classification E-algorithm and biological immune system based AIRS algorithm have demonstrated good capability in outage cause identification especially with imbalanced data, E-algorithm can produce inference rules but is computational demanding; AIRS has the quick searching capability but is lack of rule extraction capability. In this paper, fuzzy artificial immune recognition system (FAIRS) has been proposed to utilize the advantages of both E-algorithm and AIRS. FAIRS is applied to Duke Energy outage data for cause identification using three major causes (tree, animal, and lightning) as prototypes. It is compared with both E-algorithm and AIRS, and the results show that FAIRS achieves comparable performance while being able to extract linguistic rules with rule length flexibility to explain the inference with significantly reduced computing time than E-algorithm.
-
power distribution fault cause identification with imbalanced data using the data mining based fuzzy classification e algorithm
IEEE Transactions on Power Systems, 2007Co-Authors: Le Xu, Mo-yuen Chow, L.s. TaylorAbstract:Power distribution systems have been significantly affected by many outage-causing events. Good fault cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data sets often degrades the fault cause identification performance. In this paper, the E-algorithm, which is extended from the fuzzy classification algorithm by Ishibuchi to alleviate the effect of imbalanced data constitution, is applied to Duke Energy outage data for distribution fault cause identification. Three major outage causes (tree, animal, and lightning) are used as prototypes. The performance of E-algorithm on real-world imbalanced data is compared with artificial neural network. The results show that the E-algorithm can greatly improve the performance when the data are imbalanced
-
Power Distribution Outage Cause Identification With Imbalanced Data Using Artificial Immune Recognition System (AIRS) Algorithm
IEEE Transactions on Power Systems, 2007Co-Authors: Le Xu, Mo-yuen Chow, J. Timmis, Leroy S. TaylorAbstract:Power distribution systems have been significantly affected by many fault causing events. Effective outage cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data often degrades the outage cause identification performance. In this paper, artificial immune recognition system (AIRS), an immune-inspired algorithm for supervised classification task is applied to the Duke Energy outage data for outage cause identification using three major causes (tree, animal, and lightning) as prototypes. The performance of AIRS on these real-world imbalanced data is compared with an artificial neural network (ANN). The results show that AIRS can greatly improve the performance by as much as 163% when the data are imbalanced and achieve comparable performance with ANN for relatively balanced data
-
IEEE Congress on Evolutionary Computation - On the Investigation of Artificial Immune Systems on Imbalanced Data Classification for Power Distribution System Fault Cause Identification
2006 IEEE International Conference on Evolutionary Computation, 2006Co-Authors: Le Xu, Mo-yuen Chow, J. Timmis, L.s. Taylor, A. WatkinsAbstract:Imbalanced data are often encountered in real-world real-world real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm Artificial Immune Recognition System (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an Artificial Neural Network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.
Aleksandar Vukojevic - One of the best experts on this subject based on the ideXlab platform.
-
ISGT - Lessons learned from microgrid implementation at electric utility
2018 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2018Co-Authors: Aleksandar VukojevicAbstract:In recent years, the topic of microgrids has become one of the most commonly debated issues at numerous conferences. Microgrids gained even more traction after hurricanes Harvey and Irma knocked out the power to almost 10 million people in southeast US. The development and advances in technology, communications and distributed intelligence during the last decade have enabled the creation of microgrid test beds, that utilize distributed generation (DG) sources such as solar or wind farms, diesel or natural gas generators, batteries, fuel cells, combined heat and power (CHP) and others. Since 2015, Duke Energy's Emerging Technologies Office has engineered, developed, installed, and commissioned three phases of its Mount Holly microgrid in North Carolina, with the main objective of trying to understand and investigate the engineering challenges of design, construction, commissioning and maintenance and operation of the microgrid, along with the development of distributed intelligence platform capabilities associated with microgrid control. This paper reflects the lessons learned from the implementation and operation of Mount Holly microgrid at Duke Energy.
-
Lessons learned from microgrid implementation at electric utility
2018 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2018Co-Authors: Aleksandar VukojevicAbstract:In recent years, the topic of microgrids has become one of the most commonly debated issues at numerous conferences. Microgrids gained even more traction after hurricanes Harvey and Irma knocked out the power to almost 10 million people in southeast US. The development and advances in technology, communications and distributed intelligence during the last decade have enabled the creation of microgrid test beds, that utilize distributed generation (DG) sources such as solar or wind farms, diesel or natural gas generators, batteries, fuel cells, combined heat and power (CHP) and others. Since 2015, Duke Energy's Emerging Technologies Office has engineered, developed, installed, and commissioned three phases of its Mount Holly microgrid in North Carolina, with the main objective of trying to understand and investigate the engineering challenges of design, construction, commissioning and maintenance and operation of the microgrid, along with the development of distributed intelligence platform capabilities associated with microgrid control. This paper reflects the lessons learned from the implementation and operation of Mount Holly microgrid at Duke Energy.
-
ISGT - An integrated utility microgrid test site ecosystem optimized by an open interoperable distributed intelligence platform
2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2015Co-Authors: Aleksandar Vukojevic, Stuart Laval, Jason HandleyAbstract:Microgrid is any subset of a distribution grid that can be islanded from the grid and continue to operate as a distributed Energy resource (DER). Recent advances in technology have enabled the creation of microgrid test beds, with distributed generation (DG) and Energy storage providing sufficient Energy to power the loads within the Microgrids. Duke Energy is developing a new Microgrid test bed at its Mount Holly, NC facility that will not only be a self-sustaining entity when disconnected from the grid, but also for the first time trying to prove the interoperability via the distributed intelligence platform (DIP) by utilizing the publish and subscribe message bus protocols to share the data between all devices within the Microgrid. This concept will provide safe, reliable, and secure power environment that utilizes set of communication technologies, both wired and wireless.
-
An integrated utility microgrid test site ecosystem optimized by an open interoperable distributed intelligence platform
2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2015Co-Authors: Aleksandar Vukojevic, Stuart Laval, Jason HandleyAbstract:Microgrid is any subset of a distribution grid that can be islanded from the grid and continue to operate as a distributed Energy resource (DER). Recent advances in technology have enabled the creation of microgrid test beds, with distributed generation (DG) and Energy storage providing sufficient Energy to power the loads within the Microgrids. Duke Energy is developing a new Microgrid test bed at its Mount Holly, NC facility that will not only be a self-sustaining entity when disconnected from the grid, but also for the first time trying to prove the interoperability via the distributed intelligence platform (DIP) by utilizing the publish and subscribe message bus protocols to share the data between all devices within the Microgrid. This concept will provide safe, reliable, and secure power environment that utilizes set of communication technologies, both wired and wireless.
Stuart Laval - One of the best experts on this subject based on the ideXlab platform.
-
ISGT - Quantitative Evaluation of Reliability Improvement: Case Study on a Self-healing Distribution System
2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2020Co-Authors: Jiaojiao Dong, Paychuda Kritprajun, Leon M. Tolbert, Joshua C. Hambrick, Kevin P. Schneider, Stuart LavalAbstract:In this work, we develop a methodology and tool to quantitatively evaluate the reliability of a self-healing system that considers practical distribution system features such as the distributed Energy resources, microgrids, and service restoration strategies. Also, this paper addresses various practical issues when being applied to an actual Duke Energy distribution system, including the design of feasible and practical service restoration strategies that are used to identify the customer interruptions after a fault, and the incorporation of the utility's historical reliability indices that are used to calibrate the failure rate and repair time of distribution system components such as overhead lines and underground cables. This case study demonstrates the effectiveness of the proposed method.
-
Quantitative Evaluation of Reliability Improvement: Case Study on a Self-healing Distribution System
2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2020Co-Authors: Jiaojiao Dong, Paychuda Kritprajun, Leon M. Tolbert, Joshua C. Hambrick, Kevin Schneider, Stuart LavalAbstract:In this work, we develop a methodology and tool to quantitatively evaluate the reliability of a self-healing system that considers practical distribution system features such as the distributed Energy resources, microgrids, and service restoration strategies. Also, this paper addresses various practical issues when being applied to an actual Duke Energy distribution system, including the design of feasible and practical service restoration strategies that are used to identify the customer interruptions after a fault, and the incorporation of the utility's historical reliability indices that are used to calibrate the failure rate and repair time of distribution system components such as overhead lines and underground cables. This case study demonstrates the effectiveness of the proposed method.
-
A Distributed Power System Control Architecture for Improved Distribution System Resiliency
IEEE Access, 2019Co-Authors: Kevin P. Schneider, Murali Baggu, John Hart, Stuart Laval, Jacob Hansen, Ronald B. Melton, Leslie Ponder, Joshua Hambrick, Mark Buckner, Kumaraguru PrabakarAbstract:Electric distribution systems around the world are seeing an increasing number of utility-owned and non-utility-owned (customer-owned) intelligent devices and systems being deployed. New deployments of utility-owned assets include self-healing systems, microgrids, and distribution automation. Non-utility-owned assets include solar photovoltaic generation, behind-the-meter Energy storage systems, and electric vehicles. While these deployments provide potential data and control points, the existing centralized control architectures do not have the flexibility or the scalability to integrate the increasing number or variety of devices. The communication bandwidth, latency, and the scalability of a centralized control architecture limit the ability of these new devices and systems from being engaged as active resources. This paper presents a standards-based architecture for the distributed power system controls, which increases operational flexibility by coordinating centralized and distributed control systems. The system actively engages utility and non-utility assets using a distributed architecture to increase reliability during normal operations and resiliency during extreme events. Results from laboratory testing and preliminary field implementations, as well as the details of an ongoing full-scale implementation at Duke Energy, are presented.
-
ISGT - An integrated utility microgrid test site ecosystem optimized by an open interoperable distributed intelligence platform
2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2015Co-Authors: Aleksandar Vukojevic, Stuart Laval, Jason HandleyAbstract:Microgrid is any subset of a distribution grid that can be islanded from the grid and continue to operate as a distributed Energy resource (DER). Recent advances in technology have enabled the creation of microgrid test beds, with distributed generation (DG) and Energy storage providing sufficient Energy to power the loads within the Microgrids. Duke Energy is developing a new Microgrid test bed at its Mount Holly, NC facility that will not only be a self-sustaining entity when disconnected from the grid, but also for the first time trying to prove the interoperability via the distributed intelligence platform (DIP) by utilizing the publish and subscribe message bus protocols to share the data between all devices within the Microgrid. This concept will provide safe, reliable, and secure power environment that utilizes set of communication technologies, both wired and wireless.
-
An integrated utility microgrid test site ecosystem optimized by an open interoperable distributed intelligence platform
2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2015Co-Authors: Aleksandar Vukojevic, Stuart Laval, Jason HandleyAbstract:Microgrid is any subset of a distribution grid that can be islanded from the grid and continue to operate as a distributed Energy resource (DER). Recent advances in technology have enabled the creation of microgrid test beds, with distributed generation (DG) and Energy storage providing sufficient Energy to power the loads within the Microgrids. Duke Energy is developing a new Microgrid test bed at its Mount Holly, NC facility that will not only be a self-sustaining entity when disconnected from the grid, but also for the first time trying to prove the interoperability via the distributed intelligence platform (DIP) by utilizing the publish and subscribe message bus protocols to share the data between all devices within the Microgrid. This concept will provide safe, reliable, and secure power environment that utilizes set of communication technologies, both wired and wireless.
L.s. Taylor - One of the best experts on this subject based on the ideXlab platform.
-
power distribution fault cause identification with imbalanced data using the data mining based fuzzy classification e algorithm
IEEE Transactions on Power Systems, 2007Co-Authors: Le Xu, Mo-yuen Chow, L.s. TaylorAbstract:Power distribution systems have been significantly affected by many outage-causing events. Good fault cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data sets often degrades the fault cause identification performance. In this paper, the E-algorithm, which is extended from the fuzzy classification algorithm by Ishibuchi to alleviate the effect of imbalanced data constitution, is applied to Duke Energy outage data for distribution fault cause identification. Three major outage causes (tree, animal, and lightning) are used as prototypes. The performance of E-algorithm on real-world imbalanced data is compared with artificial neural network. The results show that the E-algorithm can greatly improve the performance when the data are imbalanced
-
IEEE Congress on Evolutionary Computation - On the Investigation of Artificial Immune Systems on Imbalanced Data Classification for Power Distribution System Fault Cause Identification
2006 IEEE International Conference on Evolutionary Computation, 2006Co-Authors: Le Xu, Mo-yuen Chow, J. Timmis, L.s. Taylor, A. WatkinsAbstract:Imbalanced data are often encountered in real-world real-world real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm Artificial Immune Recognition System (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an Artificial Neural Network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.
-
FUZZ-IEEE - Data Mining Based Fuzzy Classification Algorithm for Imbalanced Data
2006 IEEE International Conference on Fuzzy Systems, 2006Co-Authors: Le Xu, Mo-yuen Chow, L.s. TaylorAbstract:The elegant fuzzy classification algorithm proposed by Ishibuchi et al. (I-algorithm) has achieved satisfactory performance on many well-known test data sets that have usually been carefully preprocessed. However, the algorithm does not provide satisfactory performance for the problems with imbalanced data that are often encountered in real-world applications. This paper presents an extension of the I-algorithm to E-algorithm to alleviate the effect of data imbalance. Both the I-algorithm and the E-algorithm are applied to Duke Energy outage data for power distribution systems fault cause identification. Their performance on this real-world imbalanced data set is presented, compared, and analyzed to demonstrate the improvement of the extended algorithm.
-
On the Investigation of Artificial Immune Systems on Imbalanced Data Classification for Power Distribution System Fault Cause Identification
2006 IEEE International Conference on Evolutionary Computation, 2006Co-Authors: Le Xu, Mo-yuen Chow, J. Timmis, L.s. Taylor, A. WatkinsAbstract:Imbalanced data are often encountered in real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm artificial immune recognition system (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an artificial neural network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.
-
Data Mining Based Fuzzy Classification Algorithm for Imbalanced Data
2006 IEEE International Conference on Fuzzy Systems, 2006Co-Authors: Le Xu, Mo-yuen Chow, L.s. TaylorAbstract:The elegant fuzzy classification algorithm proposed by Ishibuchi et al. (I-algorithm) has achieved satisfactory performance on many well-known test data sets that have usually been carefully preprocessed. However, the algorithm does not provide satisfactory performance for the problems with imbalanced data that are often encountered in real-world applications. This paper presents an extension of the I-algorithm to E-algorithm to alleviate the effect of data imbalance. Both the I-algorithm and the E-algorithm are applied to Duke Energy outage data for power distribution systems fault cause identification. Their performance on this real-world imbalanced data set is presented, compared, and analyzed to demonstrate the improvement of the extended algorithm.
