Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030999
A. Elkholy, E. Sallam
Nowadays, Hadoop is a widely used framework for processing large data. Hadoop scheduler is a critical element which has a big effect on Hadoop performance. Finding a dynamic scheduler which adapts to different nodes computing capabilities and the same node performance is a challenging problem. Most of the current Hadoop schedulers consider the homogeneity of the resources on which Hadoop is running and assign each node in the cluster a fixed capacity over the run time, neglecting the different nodes computing capabilities and the performance of each node over the run time. This causes under/over utilization of resources, poor performance and longer run time. So, we propose a dynamic Hadoop scheduler which adapts to the performance and the computing capabilities of each node separately. The proposed scheduler controls the capacity of each node which represented by the number of tasks that can be processed concurrently at a time. The scheduler extends/shrinks the capacity of each node depending on its available resources and performance over the run time. Our scheduler is implemented on Hadoop and compared by the Hadoop Fair Scheduler. The experimental results show that our scheduler has achieved less average completion time and higher resources utilization.
{"title":"Self adaptive Hadoop scheduler for heterogeneous resources","authors":"A. Elkholy, E. Sallam","doi":"10.1109/ICCES.2014.7030999","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030999","url":null,"abstract":"Nowadays, Hadoop is a widely used framework for processing large data. Hadoop scheduler is a critical element which has a big effect on Hadoop performance. Finding a dynamic scheduler which adapts to different nodes computing capabilities and the same node performance is a challenging problem. Most of the current Hadoop schedulers consider the homogeneity of the resources on which Hadoop is running and assign each node in the cluster a fixed capacity over the run time, neglecting the different nodes computing capabilities and the performance of each node over the run time. This causes under/over utilization of resources, poor performance and longer run time. So, we propose a dynamic Hadoop scheduler which adapts to the performance and the computing capabilities of each node separately. The proposed scheduler controls the capacity of each node which represented by the number of tasks that can be processed concurrently at a time. The scheduler extends/shrinks the capacity of each node depending on its available resources and performance over the run time. Our scheduler is implemented on Hadoop and compared by the Hadoop Fair Scheduler. The experimental results show that our scheduler has achieved less average completion time and higher resources utilization.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121962254","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030961
Amr Hany, M. El-Moursy, H. Fahmy
A comparison between SoC with shared bus medium and NoC using Transaction Level Modeling (TLM) is presented. The router of the NoC is implemented using SystemC. Different traffic patterns and loads are used to evaluate the implementation. Detailed performance evaluation using different metrics such as throughput, latency, number of hops and power consumption is provided. It is shown that the throughput of NoC is higher in addition to its scalability as number of cores in large systems increases. The rate of throughput increase in NoC is higher than the rate of increase of power consumption as compared to SoC as system size increases. SoC could not satisfy the continuous demands of large systems while NoC is highly scalable.
{"title":"Network Of Cores For Large Systems","authors":"Amr Hany, M. El-Moursy, H. Fahmy","doi":"10.1109/ICCES.2014.7030961","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030961","url":null,"abstract":"A comparison between SoC with shared bus medium and NoC using Transaction Level Modeling (TLM) is presented. The router of the NoC is implemented using SystemC. Different traffic patterns and loads are used to evaluate the implementation. Detailed performance evaluation using different metrics such as throughput, latency, number of hops and power consumption is provided. It is shown that the throughput of NoC is higher in addition to its scalability as number of cores in large systems increases. The rate of throughput increase in NoC is higher than the rate of increase of power consumption as compared to SoC as system size increases. SoC could not satisfy the continuous demands of large systems while NoC is highly scalable.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127675722","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030918
Amr A. Mohamed, Amr M. T. Ali-Eldin, A. Saleh
Location management (LM) is how to find a mobile terminal (MT) current location on the move. Location update (LU) and paging must be maintained efficiently to minimize location management cost in personal communication service networks (PCS networks). In this paper we introduce a new location update and paging techniques, the location update is concerned with location tracking which is based on geographical position of the mobile terminal with time aspects. The locations are saved in the mobile cache in means of cell ID and time interval, the tracking process is totally managed by the MT's current visitor location register (VLR), the location data is transferred from the mobile cache to the VLR when the mobile terminal crosses a pre-defined number of cells, or when a pre-defined number of time intervals is reached. The paging is done according to probability of existence for the mobile terminal to the location data saved in VLR. The proposed techniques in this paper reduce location management cost compared to existed location management methods.
{"title":"A probabilistic paging technique for location management in PCS networks","authors":"Amr A. Mohamed, Amr M. T. Ali-Eldin, A. Saleh","doi":"10.1109/ICCES.2014.7030918","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030918","url":null,"abstract":"Location management (LM) is how to find a mobile terminal (MT) current location on the move. Location update (LU) and paging must be maintained efficiently to minimize location management cost in personal communication service networks (PCS networks). In this paper we introduce a new location update and paging techniques, the location update is concerned with location tracking which is based on geographical position of the mobile terminal with time aspects. The locations are saved in the mobile cache in means of cell ID and time interval, the tracking process is totally managed by the MT's current visitor location register (VLR), the location data is transferred from the mobile cache to the VLR when the mobile terminal crosses a pre-defined number of cells, or when a pre-defined number of time intervals is reached. The paging is done according to probability of existence for the mobile terminal to the location data saved in VLR. The proposed techniques in this paper reduce location management cost compared to existed location management methods.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129954415","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030990
A. Sarhan, Ahmed M. Elmogy, S. Ali
The increasing demand for World Wide Web (WWW) services has led to a considerable increase in the amount of Internet traffic. As a result, the network becomes highly prone to congestion which increases the load on servers, resulting in increasing the access times of WWW documents. Thus, Web caching is crucial for reducing the load on network, shorten network latency and improve clients' waiting time. Many web cashing systems and policies have been proposed to determine which objects to evict from the cache memory to accommodate new ones. Most of these systems and policies are mainly based on the enhancement of a well-known scheme called the Least Frequently Used (LFU) scheme. Although most of the proposed schemes could overcome the disadvantages of the LFU, they still have lots of overhead and are difficult to implement. This work proposes replacement approaches with better characteristics as they are easier to be implemented than the previous approaches. The proposed approaches consider the internal requests generated in each Web site. We added this factors to two famous approaches; LFU and Weighting Replacement Policy (WRP) to strength their performance. The experimental results indicate the superiority of the proposed approaches compared to both LFU and WRP, in terms of improvement in cache performance.
{"title":"New Web cache replacement approaches based on internal requests factor","authors":"A. Sarhan, Ahmed M. Elmogy, S. Ali","doi":"10.1109/ICCES.2014.7030990","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030990","url":null,"abstract":"The increasing demand for World Wide Web (WWW) services has led to a considerable increase in the amount of Internet traffic. As a result, the network becomes highly prone to congestion which increases the load on servers, resulting in increasing the access times of WWW documents. Thus, Web caching is crucial for reducing the load on network, shorten network latency and improve clients' waiting time. Many web cashing systems and policies have been proposed to determine which objects to evict from the cache memory to accommodate new ones. Most of these systems and policies are mainly based on the enhancement of a well-known scheme called the Least Frequently Used (LFU) scheme. Although most of the proposed schemes could overcome the disadvantages of the LFU, they still have lots of overhead and are difficult to implement. This work proposes replacement approaches with better characteristics as they are easier to be implemented than the previous approaches. The proposed approaches consider the internal requests generated in each Web site. We added this factors to two famous approaches; LFU and Weighting Replacement Policy (WRP) to strength their performance. The experimental results indicate the superiority of the proposed approaches compared to both LFU and WRP, in terms of improvement in cache performance.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116882219","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030998
Shahinaz R. Hussein, Y. Alkabani, H. K. Mohamed
Cloud computing is offering utility oriented IT services to users worldwide. Based on a pay per use model, it provides a variety of computing resources, enterprise applications while enabling their hosting from consumer, scientific and business domains through a three layered architecture and different cloud types. The proliferation of cloud computing has resulted in the establishment of large-scale data centers around the world containing thousands of computing nodes which consume huge amounts of energy, contributing to high operational costs and carbon footprints to the environment. Energy consumption is not only determined by hardware efficiency, but it also depends on the resource management system deployed on the infrastructure and the efficiency of applications running in the system. The challenge is addressed in finding cloud computing solutions that not only save energy for the environment but also reduce operational costs. Our Fuzzy based contribution improves power efficiency with around 40 % than other policies.
{"title":"Green cloud computing: Datacenters power management policies and algorithms","authors":"Shahinaz R. Hussein, Y. Alkabani, H. K. Mohamed","doi":"10.1109/ICCES.2014.7030998","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030998","url":null,"abstract":"Cloud computing is offering utility oriented IT services to users worldwide. Based on a pay per use model, it provides a variety of computing resources, enterprise applications while enabling their hosting from consumer, scientific and business domains through a three layered architecture and different cloud types. The proliferation of cloud computing has resulted in the establishment of large-scale data centers around the world containing thousands of computing nodes which consume huge amounts of energy, contributing to high operational costs and carbon footprints to the environment. Energy consumption is not only determined by hardware efficiency, but it also depends on the resource management system deployed on the infrastructure and the efficiency of applications running in the system. The challenge is addressed in finding cloud computing solutions that not only save energy for the environment but also reduce operational costs. Our Fuzzy based contribution improves power efficiency with around 40 % than other policies.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130297245","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030997
Hend A. Selmy, Y. Alkabani, H. K. Mohamed
Cloud computing is a highly scalable and cost - effective infrastructure for running High Performance Computing, enterprise and Web applications. However, the growing demand of Cloud infrastructure has drastically increased the energy consumption of data centers, which has become a critical issue. Hence, energy efficient solutions are required to minimize this energy consumption. The energy efficient solutions aim at lowering the energy usage of data centers because computing applications and data are growing so quickly that increasingly larger servers and disks are needed to process them fast enough within the required time period so here we reduce the energy consumption by an average of 40% over previously introduced methods. So in datacenters, the number of physical machines can be reduced using virtualization by consolidating virtual machines onto shared servers and enabling them to migrate according to migration policy. This paper presents virtual machines migration and selection policies to boost Cloud Computing Environment energy efficiency and performance.
{"title":"Energy efficient resource management for Cloud Computing Environment","authors":"Hend A. Selmy, Y. Alkabani, H. K. Mohamed","doi":"10.1109/ICCES.2014.7030997","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030997","url":null,"abstract":"Cloud computing is a highly scalable and cost - effective infrastructure for running High Performance Computing, enterprise and Web applications. However, the growing demand of Cloud infrastructure has drastically increased the energy consumption of data centers, which has become a critical issue. Hence, energy efficient solutions are required to minimize this energy consumption. The energy efficient solutions aim at lowering the energy usage of data centers because computing applications and data are growing so quickly that increasingly larger servers and disks are needed to process them fast enough within the required time period so here we reduce the energy consumption by an average of 40% over previously introduced methods. So in datacenters, the number of physical machines can be reduced using virtualization by consolidating virtual machines onto shared servers and enabling them to migrate according to migration policy. This paper presents virtual machines migration and selection policies to boost Cloud Computing Environment energy efficiency and performance.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"939 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127001917","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030949
Fatma Mohamed, R. Ismail, N. Badr, M. Tolba
Most of query optimizers choose a single query plan for processing all the data based on the average data statistics. But this plan is usually not efficient with the uncertain stream datasets of modern applications as network monitoring, sensor networks and financial applications; where these data have continuous variations over time. In this paper we propose an optimized query mesh for data stream (OQMDS) frameworks. In which, process data streams over multiple query plans, each of them is optimal for the sub-set of data with the same statistics. The OQMDS solution depends on preparing multiple query plans and continuously chooses the best execution plan for each sub-set of incoming data streams based on their statistics. We also propose two optimization algorithms called Optimized Iterative Improvement Query Mesh (OII-QM) and Non-Search based Query Mesh (NS-QM) algorithms, to efficiently generate the multiple plans (the optimized QM solution) which are used to process the online data streams. Our experimental results show that, the proposed solution OQMDS improves the overall performance of data stream processing.
{"title":"Efficient optimized query mesh for data streams","authors":"Fatma Mohamed, R. Ismail, N. Badr, M. Tolba","doi":"10.1109/ICCES.2014.7030949","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030949","url":null,"abstract":"Most of query optimizers choose a single query plan for processing all the data based on the average data statistics. But this plan is usually not efficient with the uncertain stream datasets of modern applications as network monitoring, sensor networks and financial applications; where these data have continuous variations over time. In this paper we propose an optimized query mesh for data stream (OQMDS) frameworks. In which, process data streams over multiple query plans, each of them is optimal for the sub-set of data with the same statistics. The OQMDS solution depends on preparing multiple query plans and continuously chooses the best execution plan for each sub-set of incoming data streams based on their statistics. We also propose two optimization algorithms called Optimized Iterative Improvement Query Mesh (OII-QM) and Non-Search based Query Mesh (NS-QM) algorithms, to efficiently generate the multiple plans (the optimized QM solution) which are used to process the online data streams. Our experimental results show that, the proposed solution OQMDS improves the overall performance of data stream processing.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129459827","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030977
Wafaa S. El-Kassas, Bassem A. Abdullah, A. Yousef, A. Wahba
In these days, smartphones become much more used than the personal computers because of the various categories of applications downloadable from the store. The vendors of smartphones support different platforms hence to reach as many users as possible, the developer has to develop the same application for all these platforms using the different tools and programming languages provided by each platform vendor. Therefore the cross-platform mobile applications development solutions were introduced to develop the application once and run it everywhere. The cross-platform solutions use different approaches for native development such as cross-compilation, Model-Driven Development ...etc. None of these approaches claim that it provides a complete solution as they are still under research and development. This paper introduces a new integrated cross-platform mobile development solution that merges between different approaches to benefit from the advantages and minimize the drawbacks of each approach. The main contributions include: explore the approaches used in designing the new solution, explain the research methodology and the new solution architecture along with the implementation, and evaluate the limitations of the new proposed architecture and implementation compared to known solutions. The results show substantial improvement over existing solutions.
{"title":"ICPMD: Integrated cross-platform mobile development solution","authors":"Wafaa S. El-Kassas, Bassem A. Abdullah, A. Yousef, A. Wahba","doi":"10.1109/ICCES.2014.7030977","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030977","url":null,"abstract":"In these days, smartphones become much more used than the personal computers because of the various categories of applications downloadable from the store. The vendors of smartphones support different platforms hence to reach as many users as possible, the developer has to develop the same application for all these platforms using the different tools and programming languages provided by each platform vendor. Therefore the cross-platform mobile applications development solutions were introduced to develop the application once and run it everywhere. The cross-platform solutions use different approaches for native development such as cross-compilation, Model-Driven Development ...etc. None of these approaches claim that it provides a complete solution as they are still under research and development. This paper introduces a new integrated cross-platform mobile development solution that merges between different approaches to benefit from the advantages and minimize the drawbacks of each approach. The main contributions include: explore the approaches used in designing the new solution, explain the research methodology and the new solution architecture along with the implementation, and evaluate the limitations of the new proposed architecture and implementation compared to known solutions. The results show substantial improvement over existing solutions.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133886744","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030937
Pakinam Elamein Abd Elaziz, M. Sobh, H. K. Mohamed
The procedure of detecting any violation or trespass on the level of information in a database depends on placing the normal behaviors and practices of operations done by a transaction Afterwards, any identified pattern or behavior other than those normal patterns could be of high potential of being considered as an intrusion or violation. One of the known problems in this process is that, the accuracy of the process of detecting the frequent patterns in the database, as the algorithm applied may not detect all the patterns and this would affect in two ways. First, the database of the normal patterns would be missing. Second, some new patterns would be missed in the detection process. This paper studies and implements different sequential data mining techniques, and then proposes a new enhanced algorithm. The proposed algorithm increases the accuracy of the process and the number of detected patterns. Finally, the paper proposes a model for database intrusion detection based on the modified algorithm. The paper uses a realistic huge database for evaluating the performance and the accuracy.
{"title":"Database intrusion detection using sequential data mining approaches","authors":"Pakinam Elamein Abd Elaziz, M. Sobh, H. K. Mohamed","doi":"10.1109/ICCES.2014.7030937","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030937","url":null,"abstract":"The procedure of detecting any violation or trespass on the level of information in a database depends on placing the normal behaviors and practices of operations done by a transaction Afterwards, any identified pattern or behavior other than those normal patterns could be of high potential of being considered as an intrusion or violation. One of the known problems in this process is that, the accuracy of the process of detecting the frequent patterns in the database, as the algorithm applied may not detect all the patterns and this would affect in two ways. First, the database of the normal patterns would be missing. Second, some new patterns would be missed in the detection process. This paper studies and implements different sequential data mining techniques, and then proposes a new enhanced algorithm. The proposed algorithm increases the accuracy of the process and the number of detected patterns. Finally, the paper proposes a model for database intrusion detection based on the modified algorithm. The paper uses a realistic huge database for evaluating the performance and the accuracy.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134018384","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 : 2014-12-01DOI: 10.1109/ICCES.2014.7030950
D. N. Vishwakarma, H. Balaga, Harshit Nath
The proposed work presents the use of Artificial Neural Network (ANN) as a pattern classifier for differential protection of power transformer, which makes the discrimination among normal, magnetizing inrush, over-excitation and internal fault currents. This scheme has been realized through two separate customized Parallel-Hidden Layered ANN architectures which work in Master-slave mode. The Back Propagation Neural Network (BP) Algorithm and Genetic Algorithm (GA) are used to train the multi-layered feed forward neural network and their simulated results are compared. The neural network trained by Genetic algorithm gives more accurate results (in terms of mean square error) than that trained by Back Propagation Algorithm. Relaying signals under different fault conditions are obtained by simulating the system using MATLAB Simulink and SimPowerSystem toolbox. Simulated data are used as an input to the algorithm to verify the correctness of the algorithm. The GA trained ANN based differential protection scheme provides faster, accurate, more secured and dependable results for power transformers.
{"title":"Application of genetic algorithm trained masterslave Neural Network for differential protection of power transformer","authors":"D. N. Vishwakarma, H. Balaga, Harshit Nath","doi":"10.1109/ICCES.2014.7030950","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030950","url":null,"abstract":"The proposed work presents the use of Artificial Neural Network (ANN) as a pattern classifier for differential protection of power transformer, which makes the discrimination among normal, magnetizing inrush, over-excitation and internal fault currents. This scheme has been realized through two separate customized Parallel-Hidden Layered ANN architectures which work in Master-slave mode. The Back Propagation Neural Network (BP) Algorithm and Genetic Algorithm (GA) are used to train the multi-layered feed forward neural network and their simulated results are compared. The neural network trained by Genetic algorithm gives more accurate results (in terms of mean square error) than that trained by Back Propagation Algorithm. Relaying signals under different fault conditions are obtained by simulating the system using MATLAB Simulink and SimPowerSystem toolbox. Simulated data are used as an input to the algorithm to verify the correctness of the algorithm. The GA trained ANN based differential protection scheme provides faster, accurate, more secured and dependable results for power transformers.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124788799","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：