Pub Date : 1900-01-01DOI: 10.1109/ICPADS56603.2022.00093
Hao Ge, Qiongbing Zhang, Xuan Long, Junchao Cui
Load balance technology of web server clusters which assigns customer requests to suitable servers, is a major tool for quality-of-service guarantees. Nginx, a popular frontend web server, is lightweight and requires low-complexity load balancing algorithms. This study proposed a Nginx-based dynamic feedback load balancing algorithm that delivers customer requests to server nodes in accordance with the nodes’ status. Specifically, an adaptive heartbeat detection mechanism that adjusts heartbeat packet transmission in line with the server node status is designed to collect real-time node status information. The simulation study indicates that our algorithm can obtain better load balancing with a considerable reduction in heartbeat packet transmissions compared with baseline algorithms.
{"title":"A Nginx-based Dynamic Feedback Load Balancing Algorithm With Adaptive Heartbeat Detecting","authors":"Hao Ge, Qiongbing Zhang, Xuan Long, Junchao Cui","doi":"10.1109/ICPADS56603.2022.00093","DOIUrl":"https://doi.org/10.1109/ICPADS56603.2022.00093","url":null,"abstract":"Load balance technology of web server clusters which assigns customer requests to suitable servers, is a major tool for quality-of-service guarantees. Nginx, a popular frontend web server, is lightweight and requires low-complexity load balancing algorithms. This study proposed a Nginx-based dynamic feedback load balancing algorithm that delivers customer requests to server nodes in accordance with the nodes’ status. Specifically, an adaptive heartbeat detection mechanism that adjusts heartbeat packet transmission in line with the server node status is designed to collect real-time node status information. The simulation study indicates that our algorithm can obtain better load balancing with a considerable reduction in heartbeat packet transmissions compared with baseline algorithms.","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121140955","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}
The power control problem in the cognitive radio system is studied in this paper with game theory. A cost function based on fairness is designed, a power control algorithm based on SNR cost function is proposed, and a Non-cooperative Power control Game via Fairness Pricing(NPGFP) algorithm is developed. The algorithm proposed in this paper-NPGFP algorithm uses the complete information game method to make each cognitive user dynamically adjust its power parameters by detecting the power and location parameters of other cognitive users and the primary users. The algorithm ensures the system convergence stability and the benefit maximization of each cognitive user by making the transmit power to reach a steady state with iteration. By simulation in three different scenes it is shown that NPGFP algorithm is better than NPGP(Non-cooperative Power control Game model based on Pricing) algorithm in throughput, SNR, cost function of the cognitive user and the stability of the algorithm convergence.
{"title":"Power Control Algorithm Based on SNR Cost Function in Cognitive Radio System","authors":"Yunxiao Zu, Yi-Fei Liu, Shi-Bo Mao, Xue Jia","doi":"10.1109/ICPADS.2012.150","DOIUrl":"https://doi.org/10.1109/ICPADS.2012.150","url":null,"abstract":"The power control problem in the cognitive radio system is studied in this paper with game theory. A cost function based on fairness is designed, a power control algorithm based on SNR cost function is proposed, and a Non-cooperative Power control Game via Fairness Pricing(NPGFP) algorithm is developed. The algorithm proposed in this paper-NPGFP algorithm uses the complete information game method to make each cognitive user dynamically adjust its power parameters by detecting the power and location parameters of other cognitive users and the primary users. The algorithm ensures the system convergence stability and the benefit maximization of each cognitive user by making the transmit power to reach a steady state with iteration. By simulation in three different scenes it is shown that NPGFP algorithm is better than NPGP(Non-cooperative Power control Game model based on Pricing) algorithm in throughput, SNR, cost function of the cognitive user and the stability of the algorithm convergence.","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"330 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115971249","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}
{"title":"Design, Analysis and Performance Evaluation of a New Algorithm for Developing a Fault Tolerant Distributed System","authors":"","doi":"10.1109/ICPADS.2006.33","DOIUrl":"https://doi.org/10.1109/ICPADS.2006.33","url":null,"abstract":"","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116305227","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}
Grid computing provides a computational infrastructure supporting flexible, secure, coordinated resource sharing among dynamic collections of individuals, institutions, and resources. Which means the grid should offer access for users and systems from various places. In order to protect the information and resource from abuse, access control in grid computing is therefore necessary and important. In this paper, a new approach is presented to authorize and administrate grid access requests, in which the requests are obliged to negotiate with a policy enforcement system in order to gain access to the target grid resources. This new method is called semantic access control as it exploits semantic Web technology, and use machine reasoning about the messages and policies at a semantic level.
{"title":"Semantic Access Control in Grid Computing","authors":"Xiaopeng Wang, Junzhou Luo, Aibo Song, Teng Ma","doi":"10.1109/ICPADS.2005.261","DOIUrl":"https://doi.org/10.1109/ICPADS.2005.261","url":null,"abstract":"Grid computing provides a computational infrastructure supporting flexible, secure, coordinated resource sharing among dynamic collections of individuals, institutions, and resources. Which means the grid should offer access for users and systems from various places. In order to protect the information and resource from abuse, access control in grid computing is therefore necessary and important. In this paper, a new approach is presented to authorize and administrate grid access requests, in which the requests are obliged to negotiate with a policy enforcement system in order to gain access to the target grid resources. This new method is called semantic access control as it exploits semantic Web technology, and use machine reasoning about the messages and policies at a semantic level.","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115708178","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 : 1900-01-01DOI: 10.1109/ICPADS.2007.4447706
L. Ni
{"title":"Message from the general chair","authors":"L. Ni","doi":"10.1109/ICPADS.2007.4447706","DOIUrl":"https://doi.org/10.1109/ICPADS.2007.4447706","url":null,"abstract":"","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129287773","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}
The stringent requirement for the high efficiency of routing protocol on Internet will be satisfied by exploiting the Threaded Border Gateway Protocol (TBGP) on multi-cores. Since the TBGP performance is restricted by a mass of contentions when racing to access the routing table, a highly-efficient parallel access approach is originally proposed to achieve the ultra-high route processing speed. In this paper, a novel routing table structure consisting of two-level tries is presented for fast parallel access, and a heuristic-based divide-and-recombine algorithm is devised to balance the table accesses and release the contentions, thereby accelerating the parallel route update of multi-threading. By modifying the typical table operations such as lookup, insert, etc., the correctness of two-level tries table is validated according to the operation behaviors of traditional routing table. Experimental results on dual quad-core Xeon server show that the parallel access contentions decrease sharply by 92.5% versus traditional routing table, and the maximal update time per thread is obviously reduced by 56.8% on average with little overhead. Then, the throughput of BGP update message is measured to be improved by about 169%, delivering significant performance improvement of BGP.
{"title":"An Improved Parallel Access Technology on Routing Table for Threaded BGP","authors":"L. Gao, Ming-che Lai, Z. Gong","doi":"10.1109/ICPADS.2009.81","DOIUrl":"https://doi.org/10.1109/ICPADS.2009.81","url":null,"abstract":"The stringent requirement for the high efficiency of routing protocol on Internet will be satisfied by exploiting the Threaded Border Gateway Protocol (TBGP) on multi-cores. Since the TBGP performance is restricted by a mass of contentions when racing to access the routing table, a highly-efficient parallel access approach is originally proposed to achieve the ultra-high route processing speed. In this paper, a novel routing table structure consisting of two-level tries is presented for fast parallel access, and a heuristic-based divide-and-recombine algorithm is devised to balance the table accesses and release the contentions, thereby accelerating the parallel route update of multi-threading. By modifying the typical table operations such as lookup, insert, etc., the correctness of two-level tries table is validated according to the operation behaviors of traditional routing table. Experimental results on dual quad-core Xeon server show that the parallel access contentions decrease sharply by 92.5% versus traditional routing table, and the maximal update time per thread is obviously reduced by 56.8% on average with little overhead. Then, the throughput of BGP update message is measured to be improved by about 169%, delivering significant performance improvement of BGP.","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125080375","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}
A handover priority method for cellular systems based on statistical traffic profile estimates is evaluated in this work through simulation. The scheme is of practical interest as it is simple to compute, easy to implement and it provides network operators with a wide operating interval. The method is examined in scenarios with high mobility and large handover (i.e. overlapping) areas because handover policies are very important for providing QoS in these conditions. Handover performance degradation due to mobility is analysed. The implications of the overlapping area - a larger area decreases the probability of forced termination of ongoing calls to a greater extent than it increases the probability of blocking of new calls - are of practical interest, particularly in the presence of heavy traffic and mobility conditions.
{"title":"Performance of a Traffic-Based Handover Method in High-Mobility Scenarios","authors":"Natalia Vesselinova-Vassileva, F. Barceló","doi":"10.1109/ICPADS.2008.41","DOIUrl":"https://doi.org/10.1109/ICPADS.2008.41","url":null,"abstract":"A handover priority method for cellular systems based on statistical traffic profile estimates is evaluated in this work through simulation. The scheme is of practical interest as it is simple to compute, easy to implement and it provides network operators with a wide operating interval. The method is examined in scenarios with high mobility and large handover (i.e. overlapping) areas because handover policies are very important for providing QoS in these conditions. Handover performance degradation due to mobility is analysed. The implications of the overlapping area - a larger area decreases the probability of forced termination of ongoing calls to a greater extent than it increases the probability of blocking of new calls - are of practical interest, particularly in the presence of heavy traffic and mobility conditions.","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"114 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126065505","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 : 1900-01-01DOI: 10.1109/ICPADS.2004.10001
Kwei-Jay Lin, Hao-Hua Chu
Held also regular and visiting positions in Serbia (Institute of Mathematics, University of Novi Sad, 1980-1987), Japan (Electrotechnical Laboratory, Tsukuba, 1985/86), USA (Washington State University, Pullman, WA, and University of Miami, FL, 1987/88), Canada, France (Amiens 1998, Lille 2002-2008, Orsay 2008), Spain (Murcia, 2005) and Mexico (DISCA, IIMAS, Universidad Nacional Autonoma de Mexico, 2000/02).
{"title":"Preface: ICPADS 2004 QoS and Dynamic Systems Workshop","authors":"Kwei-Jay Lin, Hao-Hua Chu","doi":"10.1109/ICPADS.2004.10001","DOIUrl":"https://doi.org/10.1109/ICPADS.2004.10001","url":null,"abstract":"Held also regular and visiting positions in Serbia (Institute of Mathematics, University of Novi Sad, 1980-1987), Japan (Electrotechnical Laboratory, Tsukuba, 1985/86), USA (Washington State University, Pullman, WA, and University of Miami, FL, 1987/88), Canada, France (Amiens 1998, Lille 2002-2008, Orsay 2008), Spain (Murcia, 2005) and Mexico (DISCA, IIMAS, Universidad Nacional Autonoma de Mexico, 2000/02).","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122788407","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 : 1900-01-01DOI: 10.1109/ICPADS.2016.0059
H. Zhu, Lei Zhang, Weimiao Feng, Chunguang Ma
In location based services (LBSs) of snapshot query, both of query and location privacy should be preserved. Most preceding schemes usually employed a trusted third party (TTP) to achieve k-anonymity, and perturb the real query and location with other k-1 users, but this scheme may be influenced by the single point failure and performance bottleneck. In order to solve this problem, another scheme to achieve k-anonymity with collaborative users through short-range communication was proposed. After deeply analyzing the inherent drawbacks of existing schemes of this type, we have found that most of them mainly focus the location privacy and usually neglect the correlation between query and location. In order to preserve the query privacy, based on the user collaborative scheme, we propose a scheme with query information divide and exchange with random users (short for QDER). This scheme can provide preserving service for both query and location privacy simultaneously. Then we analyze the attack from passive and active adversaries and use entropy to measure the privacy level. Finally, security analysis and experimental evaluations further verify the effectiveness and efficiency.
{"title":"A Users Collaborative Scheme for Location and Query Privacy","authors":"H. Zhu, Lei Zhang, Weimiao Feng, Chunguang Ma","doi":"10.1109/ICPADS.2016.0059","DOIUrl":"https://doi.org/10.1109/ICPADS.2016.0059","url":null,"abstract":"In location based services (LBSs) of snapshot query, both of query and location privacy should be preserved. Most preceding schemes usually employed a trusted third party (TTP) to achieve k-anonymity, and perturb the real query and location with other k-1 users, but this scheme may be influenced by the single point failure and performance bottleneck. In order to solve this problem, another scheme to achieve k-anonymity with collaborative users through short-range communication was proposed. After deeply analyzing the inherent drawbacks of existing schemes of this type, we have found that most of them mainly focus the location privacy and usually neglect the correlation between query and location. In order to preserve the query privacy, based on the user collaborative scheme, we propose a scheme with query information divide and exchange with random users (short for QDER). This scheme can provide preserving service for both query and location privacy simultaneously. Then we analyze the attack from passive and active adversaries and use entropy to measure the privacy level. Finally, security analysis and experimental evaluations further verify the effectiveness and efficiency.","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116161443","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 : 1900-01-01DOI: 10.1109/ICPADS.2002.1183412
Hyun-Chul Kim, Myong-Soon Park
With the proliferation of mobile and wireless computing devices, the demand for continuous network connectivity exists for various wired-and-wireless-integrated networks. Since TCP is the standard network protocol stack for communication on the Internet, its use over the networks is a certainty because it allows seamless integration with the fixed infrastructure. Transmission Control Protocol (TCP) assumes a relatively reliable underlying where most packet losses are due to congestion. In a wireless network, however, packet losses will occur more often due to unreliable wireless links than due to congestion. When using TCP over wireless links, each packet loss on the wireless link results in congestion control measures being invoked at the source. This causes severe performance degradation. We propose a new TCP scheme for the various wireless-integrated network topology. The scheme distinguishes wireless losses from packet losses regardless of the location of wireless links on the networks. This solves the severe performance degradation because of the miss notification of transmission loss. Experiments are performed using the Network Simulator (NS-II) from Lawrence Berkeley Labs. The simulator has been extended to incorporate wireless link characteristics.
{"title":"A New Scheme for Improving Performance of TCP over Network including Wireless Links","authors":"Hyun-Chul Kim, Myong-Soon Park","doi":"10.1109/ICPADS.2002.1183412","DOIUrl":"https://doi.org/10.1109/ICPADS.2002.1183412","url":null,"abstract":"With the proliferation of mobile and wireless computing devices, the demand for continuous network connectivity exists for various wired-and-wireless-integrated networks. Since TCP is the standard network protocol stack for communication on the Internet, its use over the networks is a certainty because it allows seamless integration with the fixed infrastructure. Transmission Control Protocol (TCP) assumes a relatively reliable underlying where most packet losses are due to congestion. In a wireless network, however, packet losses will occur more often due to unreliable wireless links than due to congestion. When using TCP over wireless links, each packet loss on the wireless link results in congestion control measures being invoked at the source. This causes severe performance degradation. We propose a new TCP scheme for the various wireless-integrated network topology. The scheme distinguishes wireless losses from packet losses regardless of the location of wireless links on the networks. This solves the severe performance degradation because of the miss notification of transmission loss. Experiments are performed using the Network Simulator (NS-II) from Lawrence Berkeley Labs. The simulator has been extended to incorporate wireless link characteristics.","PeriodicalId":281075,"journal":{"name":"International Conference on Parallel and Distributed Systems","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121163002","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：