Pub Date : 2018-05-13DOI: 10.1109/CCECE.2018.8447669
A. Tavighi, H. Ahmadi, M. Armstrong, J. Martí
AC interference is a growing concern within the power industry due to the proximity of other utilities (pipelines, railways, etc.) sharing the same right-of-way (ROW) and corresponding safety issues. This paper presents a methodology for determining the optimal phasing of power transmission lines to reduce the interference and improve on safe operation of utilities sharing the same ROW. The induced voltage levels on an adjacent conductor are calculated using various existing methods to compare their accuracy. Several important findings are reported here regarding the AC interference modeling under steady-state condition. The importance of the inherent unbalance in phase currents and the effect of soil resistivity are discussed in detail. The test case in the study is based on a project in BC Hydro to build two 500 k V transmission lines located in the Peace Region area, British Columbia. The results of this study were used in determining the optimal phasing for these transmission lines.
{"title":"Optimal Phasing for Parallel Transmission Lines to Minimize AC Interference","authors":"A. Tavighi, H. Ahmadi, M. Armstrong, J. Martí","doi":"10.1109/CCECE.2018.8447669","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447669","url":null,"abstract":"AC interference is a growing concern within the power industry due to the proximity of other utilities (pipelines, railways, etc.) sharing the same right-of-way (ROW) and corresponding safety issues. This paper presents a methodology for determining the optimal phasing of power transmission lines to reduce the interference and improve on safe operation of utilities sharing the same ROW. The induced voltage levels on an adjacent conductor are calculated using various existing methods to compare their accuracy. Several important findings are reported here regarding the AC interference modeling under steady-state condition. The importance of the inherent unbalance in phase currents and the effect of soil resistivity are discussed in detail. The test case in the study is based on a project in BC Hydro to build two 500 k V transmission lines located in the Peace Region area, British Columbia. The results of this study were used in determining the optimal phasing for these transmission lines.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127482682","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447793
Wafaa Anani, J. Samarabandu
Recurrent neural networks (RNN) shows a remarkable result in sequence learning, particularly in architectures with gated unit structures such as long short-term memory (LSTM). In recent years, several permutations of LSTM architecture have been proposed mainly to overcome the computational complexity of LSTM. In this paper, we present the first study that will empirically investigate and evaluate LSTM architecture variants specifically on a intrusion detection dataset. The investigation is designed to identify the learning time required for each LSTM algorithm and to measure the intrusion prediction accuracy. The results show that each variant exhibit improvement at specific parameters, yet, with a large dataset and short time training, none outperformed the standard LSTM.
{"title":"Comparison of Recurrent Neural Network Algorithms for Intrusion Detection Based on Predicting Packet Sequences","authors":"Wafaa Anani, J. Samarabandu","doi":"10.1109/CCECE.2018.8447793","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447793","url":null,"abstract":"Recurrent neural networks (RNN) shows a remarkable result in sequence learning, particularly in architectures with gated unit structures such as long short-term memory (LSTM). In recent years, several permutations of LSTM architecture have been proposed mainly to overcome the computational complexity of LSTM. In this paper, we present the first study that will empirically investigate and evaluate LSTM architecture variants specifically on a intrusion detection dataset. The investigation is designed to identify the learning time required for each LSTM algorithm and to measure the intrusion prediction accuracy. The results show that each variant exhibit improvement at specific parameters, yet, with a large dataset and short time training, none outperformed the standard LSTM.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125650904","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447635
A. Ahadi, Xiaodong Liang
An important step for generation adequacy evacuation in power system planning involving wind farms is to develop an accurate wind speed model for a site. Auto-regressive Moving Average (ARMA) model is a most common approach for predicting future wind speeds. This method, however, has some drawback, for example, the probability distribution of ARMA model might follow a Normal distribution with negative wind speeds. In this paper, a neural network based approach is proposed for wind speed time series prediction, and three training algorithms, Bayesian Regularization, Levenberg Marquardt, and Scaled Conjugate Gradient, are considered. The wind speed data in St. John's, Newfoundland and Labrador, Canada, are used in the case study to validate the proposed approach. The results obtained from the neural network approach are compared with that from the ARMA model. It is found that the neural network approach provides more accurate wind speed time series prediction.
{"title":"Wind Speed Time Series Predicted by Neural Network","authors":"A. Ahadi, Xiaodong Liang","doi":"10.1109/CCECE.2018.8447635","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447635","url":null,"abstract":"An important step for generation adequacy evacuation in power system planning involving wind farms is to develop an accurate wind speed model for a site. Auto-regressive Moving Average (ARMA) model is a most common approach for predicting future wind speeds. This method, however, has some drawback, for example, the probability distribution of ARMA model might follow a Normal distribution with negative wind speeds. In this paper, a neural network based approach is proposed for wind speed time series prediction, and three training algorithms, Bayesian Regularization, Levenberg Marquardt, and Scaled Conjugate Gradient, are considered. The wind speed data in St. John's, Newfoundland and Labrador, Canada, are used in the case study to validate the proposed approach. The results obtained from the neural network approach are compared with that from the ARMA model. It is found that the neural network approach provides more accurate wind speed time series prediction.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126235044","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447597
G. Loganathan, J. Samarabandu, Xianbin Wang
Network intrusions can be modeled as anomalies in network traffic in which the expected order of packets and their attributes deviate from regular traffic. Algorithms that predict the next sequence of events based on previous sequences are a promising avenue for detecting such anomalies. In this paper, we present a novel multi-attribute model for predicting a network packet sequence based on previous packets using a sequence-to-sequence (Seq2Seq) encoder-decoder model. This model is trained on an attack-free dataset to learn the normal sequence of packets in TCP connections and then it is used to detect anomalous packets in TCP traffic. We show that in DARPA 1999 dataset, the proposed multi-attribute Seq2Seq model detects anomalous raw TCP packets which are part of intrusions with 97 % accuracy. Also, it can detect selected intrusions in real-time with 100% accuracy and outperforms existing algorithms based on recurrent neural network models such as LSTM.
{"title":"Sequence to Sequence Pattern Learning Algorithm for Real-Time Anomaly Detection in Network Traffic","authors":"G. Loganathan, J. Samarabandu, Xianbin Wang","doi":"10.1109/CCECE.2018.8447597","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447597","url":null,"abstract":"Network intrusions can be modeled as anomalies in network traffic in which the expected order of packets and their attributes deviate from regular traffic. Algorithms that predict the next sequence of events based on previous sequences are a promising avenue for detecting such anomalies. In this paper, we present a novel multi-attribute model for predicting a network packet sequence based on previous packets using a sequence-to-sequence (Seq2Seq) encoder-decoder model. This model is trained on an attack-free dataset to learn the normal sequence of packets in TCP connections and then it is used to detect anomalous packets in TCP traffic. We show that in DARPA 1999 dataset, the proposed multi-attribute Seq2Seq model detects anomalous raw TCP packets which are part of intrusions with 97 % accuracy. Also, it can detect selected intrusions in real-time with 100% accuracy and outperforms existing algorithms based on recurrent neural network models such as LSTM.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126494418","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447587
R. Jafari, M. Kanabar, T. Sidhu, I. Voloh
Electrical power systems control the ground fault condition and its consequent challenges by proper neutral grounding. The neutral grounding resistors are well-known apparatuses that are widely used in this field of power system engineering. These resistors fail due to vibration, intermittent arcs, corrosion, etc. and cause the danger of system being ungrounded or solidly grounded. The continuity of service of these resistors is very critical to many industries resulting in various neutral grounding resistor monitoring techniques. In this paper, all existing monitoring techniques will be reviewed. Moreover, the understood trend of this art will be used to anticipate the next generation of the existing neutral grounding resistor monitoring techniques. Thereafter, the performance of an existing monitoring method will be analyzed under various conditions considering different configurations of the power system. The situations that the monitoring method fails to monitor correctly will be highlighted followed by a potential solution.
{"title":"Analysis of a Neutral Grounding Resistor Monitoring Method","authors":"R. Jafari, M. Kanabar, T. Sidhu, I. Voloh","doi":"10.1109/CCECE.2018.8447587","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447587","url":null,"abstract":"Electrical power systems control the ground fault condition and its consequent challenges by proper neutral grounding. The neutral grounding resistors are well-known apparatuses that are widely used in this field of power system engineering. These resistors fail due to vibration, intermittent arcs, corrosion, etc. and cause the danger of system being ungrounded or solidly grounded. The continuity of service of these resistors is very critical to many industries resulting in various neutral grounding resistor monitoring techniques. In this paper, all existing monitoring techniques will be reviewed. Moreover, the understood trend of this art will be used to anticipate the next generation of the existing neutral grounding resistor monitoring techniques. Thereafter, the performance of an existing monitoring method will be analyzed under various conditions considering different configurations of the power system. The situations that the monitoring method fails to monitor correctly will be highlighted followed by a potential solution.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130153759","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447829
Ali Anwar, Xiaoke Deng, Hengbo Ma, Weiyang Lin, Huijun Gao
For the quality inspection task of RRU, it is necessary to insert the testing probes into its power and network ports. In this paper, the problem of alignment of robot's end effector with the power port of remote radio unit (RRU) in 4 degrees of freedom (DoF) has been solved. An image based visual servo (IBVS) controller has been designed to perform the alignment task by using the visual features of the power port in image plane. Decoupled features have been selected which eliminate the need to use image jacobian during the control design. This not only reduces the computational cost but also removes the hassle of dealing with image jacobian singularities during the visual servo. The findings have been validated both by performing simulations and designing an experiment which uses an industrial manipulator.
{"title":"Quality Inspection of Remote Radio Unit (RRU) Power Port Using IBVS","authors":"Ali Anwar, Xiaoke Deng, Hengbo Ma, Weiyang Lin, Huijun Gao","doi":"10.1109/CCECE.2018.8447829","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447829","url":null,"abstract":"For the quality inspection task of RRU, it is necessary to insert the testing probes into its power and network ports. In this paper, the problem of alignment of robot's end effector with the power port of remote radio unit (RRU) in 4 degrees of freedom (DoF) has been solved. An image based visual servo (IBVS) controller has been designed to perform the alignment task by using the visual features of the power port in image plane. Decoupled features have been selected which eliminate the need to use image jacobian during the control design. This not only reduces the computational cost but also removes the hassle of dealing with image jacobian singularities during the visual servo. The findings have been validated both by performing simulations and designing an experiment which uses an industrial manipulator.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115693733","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447637
A. Nassif, H. Yazdanpanahi, R. Torquato
There has been a strong drive to enable Distributed Energy Resources (DERs), such as Photovoltaic generators (PV), Combined Heat and Power (CHP), and Electric Vehicles (EV), in large scale, at a residential level. One notable aspect of these devices is their size. Typical rooftop PV systems are in the range of 5kW-15kW, residential CHPs are in the range of 1kW-20kW, and EVs are in the range of 2kW-15kW. Most these DERs are interfaced by using front-end power converters, which may impact the distribution grid in the form of power quality degradation. To elucidate this concern, this paper presents measurements and analyses of common PV, CHP and EVs deployed in Canada, and compares their electromagnetic compatibility emissions with the limits prescribed by applicable standards. Despite their power electronics topologies and sophisticated switching control, these DERs are expected to have a small impact on the distribution system voltage supply waveform.
{"title":"Harmonic Characterization of Modern Residential Distributed Energy Resources","authors":"A. Nassif, H. Yazdanpanahi, R. Torquato","doi":"10.1109/CCECE.2018.8447637","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447637","url":null,"abstract":"There has been a strong drive to enable Distributed Energy Resources (DERs), such as Photovoltaic generators (PV), Combined Heat and Power (CHP), and Electric Vehicles (EV), in large scale, at a residential level. One notable aspect of these devices is their size. Typical rooftop PV systems are in the range of 5kW-15kW, residential CHPs are in the range of 1kW-20kW, and EVs are in the range of 2kW-15kW. Most these DERs are interfaced by using front-end power converters, which may impact the distribution grid in the form of power quality degradation. To elucidate this concern, this paper presents measurements and analyses of common PV, CHP and EVs deployed in Canada, and compares their electromagnetic compatibility emissions with the limits prescribed by applicable standards. Despite their power electronics topologies and sophisticated switching control, these DERs are expected to have a small impact on the distribution system voltage supply waveform.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122360433","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447732
Isabela Albuquerque, João Monteiro, T. Falk, Vuk Pavlovic, Ferdin Ephrem, Diana Lucaci
In this work we investigate the capacity of evaluating human innovation perception from psycophysiological data, including electroencephalography (EEG), electrocardiography (ECG), and eye-gaze, measured with a wearable eye tracking device and an EEG headset. In order to do so, a dataset was collected while 36 participants watched video clips of the exterior and interior of four different car models, one of which was a futuristic concept car, under two different scenarios. The first involved a “first impressions”, unguided period and the second a guided period where participants were explicitly asked to attend to innovative areas of interest (AOI) in the vehicles. In both cases, participants reported their perceived level of innovation of the different AOIs. Experimental results showed that three metrics used for cognitive state assessment stood out for innovation perception assessment on a per-car basis, namely gaze average fixation duration, measured from the eye tracker, arousal (measured from ECG), and motivation (EEG). When averaging over cars and focusing on AOIs, in turn, cognitive load (EEG) showed importance. Lastly, while the guided protocol showed higher correlation when analyzing responses per-vehicle, the opposite behavior was observed when focusing only on AOIs, irrespective of the vehicle. In this scenario, the unguided condition resulted in higher correlation for the majority of the tested metrics.
{"title":"Multimodal Assessment of Human Innovation Perception Based on Eye Tracking, Electroencephalography and Electrocardiography","authors":"Isabela Albuquerque, João Monteiro, T. Falk, Vuk Pavlovic, Ferdin Ephrem, Diana Lucaci","doi":"10.1109/CCECE.2018.8447732","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447732","url":null,"abstract":"In this work we investigate the capacity of evaluating human innovation perception from psycophysiological data, including electroencephalography (EEG), electrocardiography (ECG), and eye-gaze, measured with a wearable eye tracking device and an EEG headset. In order to do so, a dataset was collected while 36 participants watched video clips of the exterior and interior of four different car models, one of which was a futuristic concept car, under two different scenarios. The first involved a “first impressions”, unguided period and the second a guided period where participants were explicitly asked to attend to innovative areas of interest (AOI) in the vehicles. In both cases, participants reported their perceived level of innovation of the different AOIs. Experimental results showed that three metrics used for cognitive state assessment stood out for innovation perception assessment on a per-car basis, namely gaze average fixation duration, measured from the eye tracker, arousal (measured from ECG), and motivation (EEG). When averaging over cars and focusing on AOIs, in turn, cognitive load (EEG) showed importance. Lastly, while the guided protocol showed higher correlation when analyzing responses per-vehicle, the opposite behavior was observed when focusing only on AOIs, irrespective of the vehicle. In this scenario, the unguided condition resulted in higher correlation for the majority of the tested metrics.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127500280","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447574
Ali M. Saleh, N. Le, A. Sesay
Inter-Cell Interference Coordination (ICIC) using frequency reuse schemes in Orthogonal Frequency Division Multiple Access (OFDMA) cellular networks is one of the most promising approaches to reduce the effect of interference and to improve the system performance. Fractional Frequency Reuse (FFR) schemes are efficient interference mitigation techniques that have been used to improve system performance in multirelay multi-cell OFDMA cellular networks, especially for the cell edge users. The purpose of FFR design is to deploy frequency patterns (sets) in such a way that a Mobile Station (MS) user can reduce interference from adjacent cells. The Frequency Reuse Factor (FRF) of 7/3 with frequency reuse pattern (7, 3, 1) is used to improve the system performance of FRF=1 and FRF=3. This paper proposes a new frequency pattern and deploys frequency sets with Amplify and Forward (AF) fixed relays to improve the performance of the system. Simulation results show that the proposed pattern achieves significant Inter-Cell Interference (ICI) reduction when compared to other cooperative and noncooperative schemes.
{"title":"Inter-Cell Interference Coordination Using Fractional Frequency Reuse Scheme in Multi-Relay Multi-Cell OFDMA Systems","authors":"Ali M. Saleh, N. Le, A. Sesay","doi":"10.1109/CCECE.2018.8447574","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447574","url":null,"abstract":"Inter-Cell Interference Coordination (ICIC) using frequency reuse schemes in Orthogonal Frequency Division Multiple Access (OFDMA) cellular networks is one of the most promising approaches to reduce the effect of interference and to improve the system performance. Fractional Frequency Reuse (FFR) schemes are efficient interference mitigation techniques that have been used to improve system performance in multirelay multi-cell OFDMA cellular networks, especially for the cell edge users. The purpose of FFR design is to deploy frequency patterns (sets) in such a way that a Mobile Station (MS) user can reduce interference from adjacent cells. The Frequency Reuse Factor (FRF) of 7/3 with frequency reuse pattern (7, 3, 1) is used to improve the system performance of FRF=1 and FRF=3. This paper proposes a new frequency pattern and deploys frequency sets with Amplify and Forward (AF) fixed relays to improve the performance of the system. Simulation results show that the proposed pattern achieves significant Inter-Cell Interference (ICI) reduction when compared to other cooperative and noncooperative schemes.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"257 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132510972","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 : 2018-05-13DOI: 10.1109/CCECE.2018.8447646
H. Salehinejad, S. Rahnamayan, H. Tizhoosh
Differential Evolution (DE) is a popular global optimization algorithm, mostly due to its high performance, easy implementation, and utilization of a few control parameters. The mutation scheme is one of the important steps of DE, which selects a number of individuals from the population as parents to generate the next population during its evolutionary process. The parents are traditionally selected randomly and in some mutation schemes the best member of population is selected as one of the parents. In this paper, we propose the centroid-based differential evolution (CenDE) algorithm, which uses the centroid of top three individuals in the population in terms of objective function value performance as the base parent. The experiments are conducted for high and low dimensional problems with small and standard population sizes on CEC Black-Box Optimization Benchmark problems 2015 (CEC-BBOB 2015). Our experiments show that the center of best three individuals plays an important role in generating candidate individuals with better objective values for the next generation, resulting in a faster convergence of the DE algorithm.
{"title":"CenDE: Centroid-Based Differential Evolution","authors":"H. Salehinejad, S. Rahnamayan, H. Tizhoosh","doi":"10.1109/CCECE.2018.8447646","DOIUrl":"https://doi.org/10.1109/CCECE.2018.8447646","url":null,"abstract":"Differential Evolution (DE) is a popular global optimization algorithm, mostly due to its high performance, easy implementation, and utilization of a few control parameters. The mutation scheme is one of the important steps of DE, which selects a number of individuals from the population as parents to generate the next population during its evolutionary process. The parents are traditionally selected randomly and in some mutation schemes the best member of population is selected as one of the parents. In this paper, we propose the centroid-based differential evolution (CenDE) algorithm, which uses the centroid of top three individuals in the population in terms of objective function value performance as the base parent. The experiments are conducted for high and low dimensional problems with small and standard population sizes on CEC Black-Box Optimization Benchmark problems 2015 (CEC-BBOB 2015). Our experiments show that the center of best three individuals plays an important role in generating candidate individuals with better objective values for the next generation, resulting in a faster convergence of the DE algorithm.","PeriodicalId":181463,"journal":{"name":"2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121292279","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：