Pub Date : 2017-06-19DOI: 10.1109/ISIE.2017.8001537
T. Janarthanan, S. Zargari
Machine learning and data mining techniques have been widely used in order to improve network intrusion detection in recent years. These techniques make it possible to automate anomaly detection in network traffics. One of the major problems that researchers are facing is the lack of published data available for research purposes. The KDD'99 dataset was used by researchers for over a decade even though this dataset was suffering from some reported shortcomings and it was criticized by few researchers. In 2009, Tavallaee M. et al. proposed a new dataset (NSL-KDD) extracted from the KDD'99 dataset in order to improve the dataset where it can be used for carrying out research in anomaly detection. The UNSW-NB15 dataset is the latest published dataset which was created in 2015 for research purposes in intrusion detection. This research is analysing the features included in the UNSW-NB15 dataset by employing machine learning techniques and exploring significant features (curse of high dimensionality) by which intrusion detection can be improved in network systems. Therefore, the existing irrelevant and redundant features are omitted from the dataset resulting not only faster training and testing process but also less resource consumption while maintaining high detection rates. A subset of features is proposed in this study and the findings are compared with the previous work in relation to features selection in the KDD'99 dataset.
近年来，机器学习和数据挖掘技术被广泛用于改进网络入侵检测。这些技术使得在网络流量中自动检测异常成为可能。研究人员面临的主要问题之一是缺乏可用于研究目的的已发表数据。KDD'99数据集被研究人员使用了十多年，尽管该数据集存在一些报道的缺点，并且受到少数研究人员的批评。2009年，Tavallaee M. et al.提出了从KDD'99数据集提取的新数据集(NSL-KDD)，以改进该数据集，使其可用于开展异常检测研究。UNSW-NB15数据集是最新发布的数据集，于2015年创建，用于入侵检测的研究目的。本研究通过采用机器学习技术和探索重要特征(高维诅咒)来分析UNSW-NB15数据集中包含的特征，通过这些特征可以改进网络系统中的入侵检测。因此，从数据集中省略现有的不相关和冗余特征，不仅可以加快训练和测试过程，而且可以减少资源消耗，同时保持较高的检测率。本研究提出了一个特征子集，并将研究结果与KDD'99数据集中的特征选择相关的先前工作进行了比较。
{"title":"Feature selection in UNSW-NB15 and KDDCUP'99 datasets","authors":"T. Janarthanan, S. Zargari","doi":"10.1109/ISIE.2017.8001537","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001537","url":null,"abstract":"Machine learning and data mining techniques have been widely used in order to improve network intrusion detection in recent years. These techniques make it possible to automate anomaly detection in network traffics. One of the major problems that researchers are facing is the lack of published data available for research purposes. The KDD'99 dataset was used by researchers for over a decade even though this dataset was suffering from some reported shortcomings and it was criticized by few researchers. In 2009, Tavallaee M. et al. proposed a new dataset (NSL-KDD) extracted from the KDD'99 dataset in order to improve the dataset where it can be used for carrying out research in anomaly detection. The UNSW-NB15 dataset is the latest published dataset which was created in 2015 for research purposes in intrusion detection. This research is analysing the features included in the UNSW-NB15 dataset by employing machine learning techniques and exploring significant features (curse of high dimensionality) by which intrusion detection can be improved in network systems. Therefore, the existing irrelevant and redundant features are omitted from the dataset resulting not only faster training and testing process but also less resource consumption while maintaining high detection rates. A subset of features is proposed in this study and the findings are compared with the previous work in relation to features selection in the KDD'99 dataset.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"1 1","pages":"1881-1886"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86533936","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001233
Yen-Chih Yeh, M. Tsai
In recent years, the development of electric vehicles has drawn a lot of attention. Locations and pricing strategies can effect a car owner's willingness to park and recharge their cars in a parking lot. Different living habits also result in different parking behavior. Even with the dynamic energy prices, it is still unable to identify the energy demand at different peak times. In order to save the costs of construction or expand substations transformers and conductors in feeders, a smarter system needs to be implemented. The system will analyze the amount of energy required at different peak times and report it back in order to adjust the topology accordingly to improve load factor of the distribution systems. This paper develops a parking lot decision-making system that is able to manage and exchange data by implementing of the Smart Object System. The control of distribution systems and parking lots is optimized through Genetic Algorithm. Analysis of power flow of electric power system is performed by using PowerFactory. To minimize the impact to the existing distribution system operations, line and transformer ampacities as well as voltage profile are considered as constraints such that the operation of car parks does not violate the normal operation of distribution systems. The simulation results show that the proposed system can efficiently minimize the charging time while maintain the voltage current constraints in IEEE 14-bus.
{"title":"Impact simulation of PEV parking lots to power distribution systems","authors":"Yen-Chih Yeh, M. Tsai","doi":"10.1109/ISIE.2017.8001233","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001233","url":null,"abstract":"In recent years, the development of electric vehicles has drawn a lot of attention. Locations and pricing strategies can effect a car owner's willingness to park and recharge their cars in a parking lot. Different living habits also result in different parking behavior. Even with the dynamic energy prices, it is still unable to identify the energy demand at different peak times. In order to save the costs of construction or expand substations transformers and conductors in feeders, a smarter system needs to be implemented. The system will analyze the amount of energy required at different peak times and report it back in order to adjust the topology accordingly to improve load factor of the distribution systems. This paper develops a parking lot decision-making system that is able to manage and exchange data by implementing of the Smart Object System. The control of distribution systems and parking lots is optimized through Genetic Algorithm. Analysis of power flow of electric power system is performed by using PowerFactory. To minimize the impact to the existing distribution system operations, line and transformer ampacities as well as voltage profile are considered as constraints such that the operation of car parks does not violate the normal operation of distribution systems. The simulation results show that the proposed system can efficiently minimize the charging time while maintain the voltage current constraints in IEEE 14-bus.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"16 1","pages":"117-122"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88893856","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001278
Zheyuan Cheng, M. Chow, Daebong Jung, Jinyong Jeon
Vehicle speed prediction plays an important role in Data-Driven Intelligent Transportation System (D2ITS) and electric vehicle energy management. Accurately predicting vehicle speed for an individual trip is a challenging topic because vehicle speed is subjected to various factors such as route types, route curvature, driver behavior, weather and traffic condition. A big data based deep learning vehicle speed prediction algorithm featuring big data analytics and Adaptive Neuro-Fuzzy Inference System (ANFIS) is presented in this paper. Big data analytics examines copious amounts of speed related data to identify the pattern and correlation between input factors and vehicle speed. ANFIS model is constructed and configured, based on the analytics. The proposed speed prediction algorithm is trained and evaluated using the actual driving data collected by one test driver. Experiment results indicate that the proposed algorithm is capable of accurately predicting vehicle speed for both freeway and urban traffic networks.
{"title":"A big data based deep learning approach for vehicle speed prediction","authors":"Zheyuan Cheng, M. Chow, Daebong Jung, Jinyong Jeon","doi":"10.1109/ISIE.2017.8001278","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001278","url":null,"abstract":"Vehicle speed prediction plays an important role in Data-Driven Intelligent Transportation System (D2ITS) and electric vehicle energy management. Accurately predicting vehicle speed for an individual trip is a challenging topic because vehicle speed is subjected to various factors such as route types, route curvature, driver behavior, weather and traffic condition. A big data based deep learning vehicle speed prediction algorithm featuring big data analytics and Adaptive Neuro-Fuzzy Inference System (ANFIS) is presented in this paper. Big data analytics examines copious amounts of speed related data to identify the pattern and correlation between input factors and vehicle speed. ANFIS model is constructed and configured, based on the analytics. The proposed speed prediction algorithm is trained and evaluated using the actual driving data collected by one test driver. Experiment results indicate that the proposed algorithm is capable of accurately predicting vehicle speed for both freeway and urban traffic networks.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"2016 1","pages":"389-394"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86645181","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001235
Martin P. Marietta, Bruno Samaniego, F. Guinjoan, G. Velasco, Robert Piqué, H. Valderrama-Blavi
This work suggests an integration procedure for a ESS (Energy Storage System) control algorithm into optimization control strategies minimizing cost functions for a microgrid system. This approach is based on a modification of the optimization strategy for adding absorption and flotation stages after each bulk charge to preserve the battery lifetime. These stages are computed out of the optimization program to reduce both computation complexity and convergence problems. Simulation results have confirmed the feasibility of this procedure at expenses of only a slight cost function increase, which can be assumed to preserve the battery lifetime.
{"title":"Integration of a Pb-acid battery management algorithm into optimization control strategies for microgrid systems","authors":"Martin P. Marietta, Bruno Samaniego, F. Guinjoan, G. Velasco, Robert Piqué, H. Valderrama-Blavi","doi":"10.1109/ISIE.2017.8001235","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001235","url":null,"abstract":"This work suggests an integration procedure for a ESS (Energy Storage System) control algorithm into optimization control strategies minimizing cost functions for a microgrid system. This approach is based on a modification of the optimization strategy for adding absorption and flotation stages after each bulk charge to preserve the battery lifetime. These stages are computed out of the optimization program to reduce both computation complexity and convergence problems. Simulation results have confirmed the feasibility of this procedure at expenses of only a slight cost function increase, which can be assumed to preserve the battery lifetime.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"100 1","pages":"128-134"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89922375","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001413
W. A. Khan, Lukasz Wisniewski, Dorota Lang, J. Jasperneite
Industrie 4.0 introduces a concept of digitalized production by allowing agile and flexible integration of new business models while maintaining manufacturing costs and efficiency at the reasonable level. In addition, cloud computing is one of the IT trends that is used nowadays to offer services on demand from a virtual environment in enterprise and office areas. The use of cloud computing in an industrial automation domain in order to offer on-demand services, such as alarm flood management or control as a service, is a promising solution. This study examines how the cloud-based applications can meet the Industrie 4.0 requirements concerning security, communication, self-configuration, reliability, and asset administration shell. Moreover, research challenges and existing gaps that need further investigation are identified and discussed.
{"title":"Analysis of the requirements for offering industrie 4.0 applications as a cloud service","authors":"W. A. Khan, Lukasz Wisniewski, Dorota Lang, J. Jasperneite","doi":"10.1109/ISIE.2017.8001413","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001413","url":null,"abstract":"Industrie 4.0 introduces a concept of digitalized production by allowing agile and flexible integration of new business models while maintaining manufacturing costs and efficiency at the reasonable level. In addition, cloud computing is one of the IT trends that is used nowadays to offer services on demand from a virtual environment in enterprise and office areas. The use of cloud computing in an industrial automation domain in order to offer on-demand services, such as alarm flood management or control as a service, is a promising solution. This study examines how the cloud-based applications can meet the Industrie 4.0 requirements concerning security, communication, self-configuration, reliability, and asset administration shell. Moreover, research challenges and existing gaps that need further investigation are identified and discussed.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"67 1","pages":"1181-1188"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84053822","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001376
Nan Chen, T. Wei, D. Ha
In this paper, a power management circuit with sleep mode for impact-type piezoelectric micro-wind energy harvesting system was proposed. Based on the analysis of the output characteristics of impact-type piezoelectric energy harvester, a new resistive matching impedance strategy was proposed to obtain maximum power. Besides, a low-power oscillator was presented to realize sectionalized frequencies. Finally, experimental results show that the controller for sectionalized matching impedance consumes 9.9% of the harvested power when the input average power is 0.9mW, and only 3.7% when the input average power is 2.1mW. The efficiency of the proposed sectionalized matching impedance energy harvesting circuit is around 76 %, which is increased by 59% and 22% at the strike frequency of 0.5Hz, as compared with the constant resistive matching circuit and with the constant resistive matching circuit having sleep mode, respectively.
{"title":"Circuit design for an impact-type piezoelectric system for micro-wind energy harvesting","authors":"Nan Chen, T. Wei, D. Ha","doi":"10.1109/ISIE.2017.8001376","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001376","url":null,"abstract":"In this paper, a power management circuit with sleep mode for impact-type piezoelectric micro-wind energy harvesting system was proposed. Based on the analysis of the output characteristics of impact-type piezoelectric energy harvester, a new resistive matching impedance strategy was proposed to obtain maximum power. Besides, a low-power oscillator was presented to realize sectionalized frequencies. Finally, experimental results show that the controller for sectionalized matching impedance consumes 9.9% of the harvested power when the input average power is 0.9mW, and only 3.7% when the input average power is 2.1mW. The efficiency of the proposed sectionalized matching impedance energy harvesting circuit is around 76 %, which is increased by 59% and 22% at the strike frequency of 0.5Hz, as compared with the constant resistive matching circuit and with the constant resistive matching circuit having sleep mode, respectively.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"16 1","pages":"964-969"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88197061","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001506
F. Sossan, Konstantina Christakou, M. Paolone, Xiang Gao, Marco Liserre
The Smart Transformer, a solid-state transformer with control and communication functionalities, can be the ideal solution for integrating storage into the grid. By leveraging the knowledge of the grid state of distribution grids thanks to smart meters and/or dedicated remote terminal units, in the paper, it is proposed a control strategy for a MV/LV smart transformer (ST) with integrated storage to achieve: i) dispatched-by-design operation of the LV network by controlling the ST active power set-point on the MV power converter, and ii) voltage regulation of both MV and LV networks by controlling the reactive power injections of both LV and MV converter. The former is achieved by dispatching the active power flow of the LV network according to a profile established the day before the operation, called dispatch plan, with the objective of reducing the amount of regulating power required to operate the grid. It is based on the use of forecast to compute a dispatch plan, and a tracking problem to compensate in real-time the mismatch between realization and dispatch plan by taking advantage of the storage capacity. The latter is achieved by using sensitivity coefficients, which are calculated from the state of the grid and integrating the information on the network topology. The problem formulation is given in the paper, and the proof-of-concept is shown by simulation using the IEEE 34 nodes test feeder and the CIGRE Low Voltage reference network.
{"title":"Enhancing the provision of ancillary services from storage systems using smart transformer and smart meters","authors":"F. Sossan, Konstantina Christakou, M. Paolone, Xiang Gao, Marco Liserre","doi":"10.1109/ISIE.2017.8001506","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001506","url":null,"abstract":"The Smart Transformer, a solid-state transformer with control and communication functionalities, can be the ideal solution for integrating storage into the grid. By leveraging the knowledge of the grid state of distribution grids thanks to smart meters and/or dedicated remote terminal units, in the paper, it is proposed a control strategy for a MV/LV smart transformer (ST) with integrated storage to achieve: i) dispatched-by-design operation of the LV network by controlling the ST active power set-point on the MV power converter, and ii) voltage regulation of both MV and LV networks by controlling the reactive power injections of both LV and MV converter. The former is achieved by dispatching the active power flow of the LV network according to a profile established the day before the operation, called dispatch plan, with the objective of reducing the amount of regulating power required to operate the grid. It is based on the use of forecast to compute a dispatch plan, and a tracking problem to compensate in real-time the mismatch between realization and dispatch plan by taking advantage of the storage capacity. The latter is achieved by using sensitivity coefficients, which are calculated from the state of the grid and integrating the information on the network topology. The problem formulation is given in the paper, and the proof-of-concept is shown by simulation using the IEEE 34 nodes test feeder and the CIGRE Low Voltage reference network.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"58 1","pages":"1715-1720"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89346098","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001517
D. Vinnikov, A. Chub, E. Liivik
In this paper, a novel topology of the high step-up multiphase galvanically isolated impedance-source DC-DC converter is proposed. It was derived by the input-parallel-output-parallel cascading of the asymmetrical quasi-Z-source half-bridge cells. The operating principle of the converter is explained by the steady state analysis. It was also demonstrated how the input current ripple of the converter could be decreased by increasing the number of interleaved phases. To validate our approach experimentally, a two-phase DC-DC converter with the power rating of 300 W was assembled. It was confirmed that the proposed converter is capable of ensuring the six-fold regulation of the input voltage with the maximum DC gain of 40 and peak efficiency of 94.5%.
{"title":"Multiphase galvanically isolated impedance-source DC-DC converter for residential renewable energy applications","authors":"D. Vinnikov, A. Chub, E. Liivik","doi":"10.1109/ISIE.2017.8001517","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001517","url":null,"abstract":"In this paper, a novel topology of the high step-up multiphase galvanically isolated impedance-source DC-DC converter is proposed. It was derived by the input-parallel-output-parallel cascading of the asymmetrical quasi-Z-source half-bridge cells. The operating principle of the converter is explained by the steady state analysis. It was also demonstrated how the input current ripple of the converter could be decreased by increasing the number of interleaved phases. To validate our approach experimentally, a two-phase DC-DC converter with the power rating of 300 W was assembled. It was confirmed that the proposed converter is capable of ensuring the six-fold regulation of the input voltage with the maximum DC gain of 40 and peak efficiency of 94.5%.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"53 1","pages":"1775-1780"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80926952","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001465
Kasun Amarasinghe, Daniel L. Marino, M. Manic
Smartgrids of the future promise unprecedented flexibility in energy management. Therefore, accurate predictions/forecasts of energy demands (loads) at individual site and aggregate level of the grid is crucial. Despite extensive research, load forecasting remains to be a difficult problem. This paper presents a load forecasting methodology based on deep learning. Specifically, the work presented in this paper investigates the effectiveness of using Convolutional Neural Networks (CNN) for performing energy load forecasting at individual building level. The presented methodology uses convolutions on historical loads. The output from the convolutional operation is fed to fully connected layers together with other pertinent information. The presented methodology was implemented on a benchmark data set of electricity consumption for a single residential customer. Results obtained from the CNN were compared against results obtained by Long Short Term Memories LSTM sequence-to-sequence (LSTM S2S), Factored Restricted Boltzmann Machines (FCRBM), “shallow” Artificial Neural Networks (ANN) and Support Vector Machines (SVM) for the same dataset. Experimental results showed that the CNN outperformed SVR while producing comparable results to the ANN and deep learning methodologies. Further testing is required to compare the performances of different deep learning architectures in load forecasting.
{"title":"Deep neural networks for energy load forecasting","authors":"Kasun Amarasinghe, Daniel L. Marino, M. Manic","doi":"10.1109/ISIE.2017.8001465","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001465","url":null,"abstract":"Smartgrids of the future promise unprecedented flexibility in energy management. Therefore, accurate predictions/forecasts of energy demands (loads) at individual site and aggregate level of the grid is crucial. Despite extensive research, load forecasting remains to be a difficult problem. This paper presents a load forecasting methodology based on deep learning. Specifically, the work presented in this paper investigates the effectiveness of using Convolutional Neural Networks (CNN) for performing energy load forecasting at individual building level. The presented methodology uses convolutions on historical loads. The output from the convolutional operation is fed to fully connected layers together with other pertinent information. The presented methodology was implemented on a benchmark data set of electricity consumption for a single residential customer. Results obtained from the CNN were compared against results obtained by Long Short Term Memories LSTM sequence-to-sequence (LSTM S2S), Factored Restricted Boltzmann Machines (FCRBM), “shallow” Artificial Neural Networks (ANN) and Support Vector Machines (SVM) for the same dataset. Experimental results showed that the CNN outperformed SVR while producing comparable results to the ANN and deep learning methodologies. Further testing is required to compare the performances of different deep learning architectures in load forecasting.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"78 1","pages":"1483-1488"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76786591","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 : 2017-06-19DOI: 10.1109/ISIE.2017.8001383
M. Räber, D. Abdeslam, Andreas Heinzelmann, Andres Ramirez
Active charge balancing is an approved technique to implement more energy-efficient and eco-friendly lithium-ion battery systems. The theoretical analysis presented in this paper provides a method to estimate the benefits of a cell-to-cell-type active charge balancing circuit in comparison to a passive balancing solution concerning energy savings and capacity gain. The calculation's variable parameters are the battery system configuration and the cell capacity distribution properties. Their validity is limited to applications with normally distributed cell capacities, limited maximum and minimum cell capacity and full cycle usage. The losses related to passive balancing in an nSmP battery system are calculated as well as the overall energy savings achievable with cell-to-cell based active balancing. The capacity gain factor of an actively balanced battery system related to a passive one is found to be in a range between 1.06 and 1.01 depending on the cell parameters and the system configuration. The derived formulas are verified by numeric simulations. Based on the results, several options are identified to increase the energy efficiency of conventional passive balancing systems. The findings can be used during the design process of new battery systems or to analyze and optimize any existing lithium-ion battery system.
{"title":"Performance estimation of a cell-to-cell-type active balancing circuit for lithium-ion battery systems","authors":"M. Räber, D. Abdeslam, Andreas Heinzelmann, Andres Ramirez","doi":"10.1109/ISIE.2017.8001383","DOIUrl":"https://doi.org/10.1109/ISIE.2017.8001383","url":null,"abstract":"Active charge balancing is an approved technique to implement more energy-efficient and eco-friendly lithium-ion battery systems. The theoretical analysis presented in this paper provides a method to estimate the benefits of a cell-to-cell-type active charge balancing circuit in comparison to a passive balancing solution concerning energy savings and capacity gain. The calculation's variable parameters are the battery system configuration and the cell capacity distribution properties. Their validity is limited to applications with normally distributed cell capacities, limited maximum and minimum cell capacity and full cycle usage. The losses related to passive balancing in an nSmP battery system are calculated as well as the overall energy savings achievable with cell-to-cell based active balancing. The capacity gain factor of an actively balanced battery system related to a passive one is found to be in a range between 1.06 and 1.01 depending on the cell parameters and the system configuration. The derived formulas are verified by numeric simulations. Based on the results, several options are identified to increase the energy efficiency of conventional passive balancing systems. The findings can be used during the design process of new battery systems or to analyze and optimize any existing lithium-ion battery system.","PeriodicalId":6597,"journal":{"name":"2017 IEEE 26th International Symposium on Industrial Electronics (ISIE)","volume":"58 1","pages":"1005-1010"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90616736","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：