Pub Date : 1999-02-10DOI: 10.1109/PCCC.1999.749415
S. Tragoudas
We examine the problem of transmitting a units of data in the most reliable manner along an (s,t) path of a network N=(V,E,c,d,r,s,t). Each edge of a network is assigned a capacity, a delay and a reliability value. In contrast to the similarly defined shortest path problem, it is shown that for this more complex routing problem the subpaths of an optimal path are not necessarily optimal. However, an optimal polynomial is presented. On acyclic networks with interconnections that operate with the same reliability probability, we present a polynomial time algorithm that computes the best route for each value of /spl sigma/. This is a very useful precomputation when different amount of data need to be transmitted at different time periods.
{"title":"The most reliable data path transmission","authors":"S. Tragoudas","doi":"10.1109/PCCC.1999.749415","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749415","url":null,"abstract":"We examine the problem of transmitting a units of data in the most reliable manner along an (s,t) path of a network N=(V,E,c,d,r,s,t). Each edge of a network is assigned a capacity, a delay and a reliability value. In contrast to the similarly defined shortest path problem, it is shown that for this more complex routing problem the subpaths of an optimal path are not necessarily optimal. However, an optimal polynomial is presented. On acyclic networks with interconnections that operate with the same reliability probability, we present a polynomial time algorithm that computes the best route for each value of /spl sigma/. This is a very useful precomputation when different amount of data need to be transmitted at different time periods.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127920448","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749441
T. Watanabe, A. Mori
When distributed object technology is used in a wide area network, large delay causes inefficient access to an object. For this problem we propose a replicated object relocation protocol called RORP, where the replicated object is relocated to an intermediate site considering communication delay, processing ability of servers, reference frequency of objects, time of object transmission, domain and limited number of replications. The paper describes the protocol and discusses its performance through an implementation of RORP prototype. We evaluate the client oriented replication scheme by processing amount distributed to clients, intermediate sites and servers. In addition the paper shows how RORP enables reduction of a response time and total network traffic including control messages and object retrieval messages.
{"title":"RORP: Distributed object relocation protocol for wide area networks","authors":"T. Watanabe, A. Mori","doi":"10.1109/PCCC.1999.749441","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749441","url":null,"abstract":"When distributed object technology is used in a wide area network, large delay causes inefficient access to an object. For this problem we propose a replicated object relocation protocol called RORP, where the replicated object is relocated to an intermediate site considering communication delay, processing ability of servers, reference frequency of objects, time of object transmission, domain and limited number of replications. The paper describes the protocol and discusses its performance through an implementation of RORP prototype. We evaluate the client oriented replication scheme by processing amount distributed to clients, intermediate sites and servers. In addition the paper shows how RORP enables reduction of a response time and total network traffic including control messages and object retrieval messages.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116750493","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749463
K. Oida, K. Shinjo
This paper deals with a routing problem for a pair of parallel paths connecting a source node and a destination node. The problem is to find the optimal routing that minimizes the average packet delay under the condition that all of the packets' arrival times at the source node as well as all of the packets' sizes are completely deterministic. The numerical solutions of the problem show that the optimal routing assigns most of the short packets to one path and most of the long packets to the other path when the input traffic intensity is high. This new routing assignment is called the fix-queue-based-on-size (FS) policy. It is shown mathematically that the expected average packet delay of the FS policy is smaller than that of the send-to-shortest-delay (SSD) policy if a large number of packets simultaneously arrive at the source node.
{"title":"Characteristics of deterministic optimal routing for a simple traffic control problem","authors":"K. Oida, K. Shinjo","doi":"10.1109/PCCC.1999.749463","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749463","url":null,"abstract":"This paper deals with a routing problem for a pair of parallel paths connecting a source node and a destination node. The problem is to find the optimal routing that minimizes the average packet delay under the condition that all of the packets' arrival times at the source node as well as all of the packets' sizes are completely deterministic. The numerical solutions of the problem show that the optimal routing assigns most of the short packets to one path and most of the long packets to the other path when the input traffic intensity is high. This new routing assignment is called the fix-queue-based-on-size (FS) policy. It is shown mathematically that the expected average packet delay of the FS policy is smaller than that of the send-to-shortest-delay (SSD) policy if a large number of packets simultaneously arrive at the source node.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115829257","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749476
S. Deuty, C. S. Mitter
The push for logic levels of one volt and below creates a need for the development of new power electronic circuits. Today's power electronic circuits can only hope to meet an efficiency of 50% for tomorrow's logic needs. Currently, a DC-DC power converter supply is placed adjacent to every Pentium/sup TM/ processor on every motherboard in order to meet the processor power and regulation requirements. The Intel spec for this DC-DC converter is known as the VRM (Voltage Regulator Module). Entire industries have been formed to meet this need for present motherboards and special power consortiums are forming to meet tomorrow's needs. This has resulted in an explosion of new control ICs and MOSFETs from companies such as Motorola, Harris, TI, Fairchild, National, Linear Technology, Maxim, and International Rectifier. The paper addresses the transistor's role in power needs for present and future logic levels. The subject matter includes powering Pentium processors for desktop PCs (5 VDC to 3.3 VDC converters) as well as the Merced/sup TM/ mainframe processor needs (48 to 3.3 VDC) to the several hundred amp logic levels of tomorrow's mainframes. Included are references to design kits, Websites, and SPICE models for some of these power converters.
{"title":"Transistor paradigm shift required to meet the power demands for microprocessors","authors":"S. Deuty, C. S. Mitter","doi":"10.1109/PCCC.1999.749476","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749476","url":null,"abstract":"The push for logic levels of one volt and below creates a need for the development of new power electronic circuits. Today's power electronic circuits can only hope to meet an efficiency of 50% for tomorrow's logic needs. Currently, a DC-DC power converter supply is placed adjacent to every Pentium/sup TM/ processor on every motherboard in order to meet the processor power and regulation requirements. The Intel spec for this DC-DC converter is known as the VRM (Voltage Regulator Module). Entire industries have been formed to meet this need for present motherboards and special power consortiums are forming to meet tomorrow's needs. This has resulted in an explosion of new control ICs and MOSFETs from companies such as Motorola, Harris, TI, Fairchild, National, Linear Technology, Maxim, and International Rectifier. The paper addresses the transistor's role in power needs for present and future logic levels. The subject matter includes powering Pentium processors for desktop PCs (5 VDC to 3.3 VDC converters) as well as the Merced/sup TM/ mainframe processor needs (48 to 3.3 VDC) to the several hundred amp logic levels of tomorrow's mainframes. Included are references to design kits, Websites, and SPICE models for some of these power converters.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125547970","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749430
M. Bassiouni, Wei Cui, Chun-Chin Fang
The wide deployment of multimedia services in third generation wireless networks will require designs that can simultaneously reduce the blocking probability of handoff requests and decrease the handoff delay. In this paper, we discuss this type of designs for dynamic channel assignment and reassignment strategies in highway cellular networks with a small channel reuse distance. A threshold-based approach to reduce the number of messages exchanged among base stations is presented. The properties of the two real-time schemes covered in this paper are presented and the global balance equations for the first scheme is derived based on the cell decoupling approximation model.
{"title":"Modeling and evaluation of channel management for real-time multimedia connections in highway cellular networks","authors":"M. Bassiouni, Wei Cui, Chun-Chin Fang","doi":"10.1109/PCCC.1999.749430","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749430","url":null,"abstract":"The wide deployment of multimedia services in third generation wireless networks will require designs that can simultaneously reduce the blocking probability of handoff requests and decrease the handoff delay. In this paper, we discuss this type of designs for dynamic channel assignment and reassignment strategies in highway cellular networks with a small channel reuse distance. A threshold-based approach to reduce the number of messages exchanged among base stations is presented. The properties of the two real-time schemes covered in this paper are presented and the global balance equations for the first scheme is derived based on the cell decoupling approximation model.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133975738","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749428
C. E. Chow, J. E. Hedlind
This paper presents a power control and channel assignment tool for wireless network design. It takes the location data of the mobile stations which were generated by a user traffic modeling and simulation tool, computes the operating power levels of the mobile stations, and assigns the mobile stations to the set of base stations with the objective of minimizing the interference. It takes into the consideration of the sector antenna angle overlap and the soft/softer handoff.
{"title":"POCAT: power control and channel assignment tool for wireless networks","authors":"C. E. Chow, J. E. Hedlind","doi":"10.1109/PCCC.1999.749428","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749428","url":null,"abstract":"This paper presents a power control and channel assignment tool for wireless network design. It takes the location data of the mobile stations which were generated by a user traffic modeling and simulation tool, computes the operating power levels of the mobile stations, and assigns the mobile stations to the set of base stations with the objective of minimizing the interference. It takes into the consideration of the sector antenna angle overlap and the soft/softer handoff.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132652651","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749437
Hyun-Wook Jin, C. Yoo
High-speed networks such as ATM, Myrinet, and Gigabit Ethernet are available today, and many researchers make efforts to enhance the performance of end-to-end communication on these high-speed networks. One of the efforts is to develop new light-weight communication primitives for high-speed network. However the latency of the new primitives has not been characterized thoroughly, partly because existing measurement methodologies do not take into account the features of high-speed networks. Therefore, there are only incomplete comparisons of the new primitives and traditional protocols, and they cannot really prove the usefulness of new primitives. In order to address this issue, this paper suggests a new measurement methodology and uses the methodology to perform a detailed latency analysis of UDP and a light-weight primitive, called BPI, on Myrinet. Our results clearly show the difference of per-byte overhead between BPI and UDP. A surprising result is that BPI is found to be slower than UDP for 4KB or larger data size.
{"title":"Latency analysis of UDP and BPI on Myrinet","authors":"Hyun-Wook Jin, C. Yoo","doi":"10.1109/PCCC.1999.749437","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749437","url":null,"abstract":"High-speed networks such as ATM, Myrinet, and Gigabit Ethernet are available today, and many researchers make efforts to enhance the performance of end-to-end communication on these high-speed networks. One of the efforts is to develop new light-weight communication primitives for high-speed network. However the latency of the new primitives has not been characterized thoroughly, partly because existing measurement methodologies do not take into account the features of high-speed networks. Therefore, there are only incomplete comparisons of the new primitives and traditional protocols, and they cannot really prove the usefulness of new primitives. In order to address this issue, this paper suggests a new measurement methodology and uses the methodology to perform a detailed latency analysis of UDP and a light-weight primitive, called BPI, on Myrinet. Our results clearly show the difference of per-byte overhead between BPI and UDP. A surprising result is that BPI is found to be slower than UDP for 4KB or larger data size.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131261130","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749466
Debashis Saha, D. Sengupta
This paper deals with an optical layer protocol designed for next generation lightwave networks, known as all-optical networks (AONs), where path between end-to-end nodes remains entirely optical. These paths are called lightpaths. Unlike OSI-RM, in the AON architecture, a new layer, called optical layer, has been introduced to manage the lightpath-related-functions. The optical layer lies in between physical layer and data link layer. The objective of this paper is to define a specification for the optical layer protocol for AONs. In order to study the dynamics of the optical layer protocol system, we first employ the communicating finite state machine model to represent the protocol. Then a reachability analysis of the model is performed to verify the protocol. This paper shows how the optical layer protocol can be specified formally and made errorfree by the step-wise refinement of an initial specification where validation is done after each refinement.
{"title":"An optical layer protocol for lightpath management in WDM networks","authors":"Debashis Saha, D. Sengupta","doi":"10.1109/PCCC.1999.749466","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749466","url":null,"abstract":"This paper deals with an optical layer protocol designed for next generation lightwave networks, known as all-optical networks (AONs), where path between end-to-end nodes remains entirely optical. These paths are called lightpaths. Unlike OSI-RM, in the AON architecture, a new layer, called optical layer, has been introduced to manage the lightpath-related-functions. The optical layer lies in between physical layer and data link layer. The objective of this paper is to define a specification for the optical layer protocol for AONs. In order to study the dynamics of the optical layer protocol system, we first employ the communicating finite state machine model to represent the protocol. Then a reachability analysis of the model is performed to verify the protocol. This paper shows how the optical layer protocol can be specified formally and made errorfree by the step-wise refinement of an initial specification where validation is done after each refinement.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114055074","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749418
G. Cao, M. Singhal
There are two approaches to design a distributed channel allocation algorithm: Search and Update. The update approach has shorter acquisition delay and lower call blocking rate, but higher message complexity. On the other hand, the search approach has lower message complexity, but longer acquisition delay and higher call blocking rate. In this paper, we propose a novel distributed acquisition algorithm, which has similar message complexity as the search approach and similar acquisition delay as the update approach. Also, we propose a channel selection algorithm, which has low call blocking rate and low intra-handoff overhead. By integrating the channel selection algorithm into our channel acquisition algorithm, we get a complete distributed channel allocation algorithm. By keeping the borrowed channels, our channel allocation algorithm adapts to the network traffic; i.e., free channels are transferred to hot cells to achieve load balance. Simulation results show that our algorithm significantly outperforms the search approach and the update approach in terms of call blocking rate, message complexity, and acquisition delay.
{"title":"An adaptive distributed channel allocation strategy for mobile cellular networks","authors":"G. Cao, M. Singhal","doi":"10.1109/PCCC.1999.749418","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749418","url":null,"abstract":"There are two approaches to design a distributed channel allocation algorithm: Search and Update. The update approach has shorter acquisition delay and lower call blocking rate, but higher message complexity. On the other hand, the search approach has lower message complexity, but longer acquisition delay and higher call blocking rate. In this paper, we propose a novel distributed acquisition algorithm, which has similar message complexity as the search approach and similar acquisition delay as the update approach. Also, we propose a channel selection algorithm, which has low call blocking rate and low intra-handoff overhead. By integrating the channel selection algorithm into our channel acquisition algorithm, we get a complete distributed channel allocation algorithm. By keeping the borrowed channels, our channel allocation algorithm adapts to the network traffic; i.e., free channels are transferred to hot cells to achieve load balance. Simulation results show that our algorithm significantly outperforms the search approach and the update approach in terms of call blocking rate, message complexity, and acquisition delay.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114291017","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749464
Shigang Chen, K. Nahrstedt
Distributed multimedia applications have quality-of-service (QoS) requirements specified in terms of constraints on various metrics such as bandwidth and delay. The task of QoS routing is to find a path from the source node to the destination node with sufficient resources to support the required end-to-end QoS. We propose several distributed algorithms for the bandwidth-constrained routing and the delay constrained routing. The algorithms are presented in the form of distributed recursive computation (DRC). DRC computes the global routing state in a distributed, recursive fashion and often leaves useful information at intermediate nodes during the process. An information-reuse scheme is studied to utilize such information in order to reduce the overall overhead. Our simulation shows that the overhead of the proposed algorithms is modest and stable.
{"title":"Routing by distributed recursive computation and information reuse","authors":"Shigang Chen, K. Nahrstedt","doi":"10.1109/PCCC.1999.749464","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749464","url":null,"abstract":"Distributed multimedia applications have quality-of-service (QoS) requirements specified in terms of constraints on various metrics such as bandwidth and delay. The task of QoS routing is to find a path from the source node to the destination node with sufficient resources to support the required end-to-end QoS. We propose several distributed algorithms for the bandwidth-constrained routing and the delay constrained routing. The algorithms are presented in the form of distributed recursive computation (DRC). DRC computes the global routing state in a distributed, recursive fashion and often leaves useful information at intermediate nodes during the process. An information-reuse scheme is studied to utilize such information in order to reduce the overall overhead. Our simulation shows that the overhead of the proposed algorithms is modest and stable.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116775084","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：