Overlay networking is one of the perspective solutions to today's Intemet challenges. At basic service level, overlay networks can serve as a supplement and enhancement of existing services, such as routing and ad...Overlay networking is one of the perspective solutions to today's Intemet challenges. At basic service level, overlay networks can serve as a supplement and enhancement of existing services, such as routing and addressing. At high application level, overlay networks can be used for applications, which are difficult to deploy in existing IP architecture with some specific reasons, e.g., they need high-level information, which is hard to obtain by underlying layers. To address the heterogeneity of today's Internet, overlay networks provide ways to service availability and desirable performance while retaining scalability. In contrast to changing the existing network layer, overlay networks allow bootstrapping, which is most important in the development of Internet infrastructure. Various applications of overlay networking are clarified in this paper. Research challenges including routing and searching in overlay networking are also identified.展开更多
Most existing overlay multicast approaches refuse to consider any network layer support no matter whether it is available or not. This design principle greatly increases the complexity of the routing algorithms and ma...Most existing overlay multicast approaches refuse to consider any network layer support no matter whether it is available or not. This design principle greatly increases the complexity of the routing algorithms and makes the overlay topologies incompatible with the underlying network. To address these issues, topology-aware overlay multicast over IP multicast networks (TOMIMN) was proposed as a novel overlay multicast protocol, which exploits the cooperation between end-hosts and IP multicast routers to construct a topology-aware overlay tree. Through a little modification to protocol independent multicast sparse mode (PIM-SM), a multicast router is able to receive registration from nearby group members and redirect passing-by join requests to them. Due to the multicast router's support, TOMIMN organizes its group members into an overlay multicast tree efficiently, which matches the physical network topology well.展开更多
Peer-to-peer (P2P) systems are now very popular. Current P2P systems are broadly of two kinds, structured and unstructured. The tree structured P2P systems used technologies such as distributed hash tables (DHT) and h...Peer-to-peer (P2P) systems are now very popular. Current P2P systems are broadly of two kinds, structured and unstructured. The tree structured P2P systems used technologies such as distributed hash tables (DHT) and hierarchical clustering can search the required target quickly, however, in a tree, the internal node has a higher load and its leave or crash often causes a large population of its offspring's problems, so that in the highly dynamic Internet environment the tree structure may still suffer frequent breaks. On the other hand, most widely used unstructured P2P networks rely on central directory servers or massive message flooding, clearly not scalable. So, we consider both of the above systems' advantages and disadvantages and realize that in the P2P systems one node may fail easily, but that when a number of nodes organized as a set, which we call "super node", the set is robust. Super nodes can be created and updated aware of topology-aware, and used with simple protocol such as flooding or "servers" to exchange information. Furthermore the entire robust super node can be organized into exquisite tree structure. By using this overlay network architecture, P2P systems are robust, efficient, scalable and secure. The simulation results demonstrated that our architecture greatly reduces the alteration time of the structure while decreasing the average delay time, compared to the common tree structure.展开更多
This paper presents a method to model network delay for overlay network application. The network topology measurement technology and network AS information is used to build up model of network delay via AS and geograp...This paper presents a method to model network delay for overlay network application. The network topology measurement technology and network AS information is used to build up model of network delay via AS and geographic distance. Based on global Internet measurement result, we calculated the parameters of the model. Furthermore, the model verification is done by comparing on AS-MMI protocol and HMTP protocol.展开更多
Once deployed, sensor networks are capable of providing a comprehensive view of their environment. However, since the current sensor network paradigm promotes isolated networks that are statically tasked, the full pow...Once deployed, sensor networks are capable of providing a comprehensive view of their environment. However, since the current sensor network paradigm promotes isolated networks that are statically tasked, the full power of the harnessed data has yet to be exploited. In recent years, users have become mobile enti-ties that require constant access to data for efficient and autonomous processing. Under the current limita-tions of sensor networks, users would be restricted using only a subset of the vast amount of data being col-lected;depending on the networks they are able to access. Through reliance on isolated networks, prolifera-tion of sensor nodes can easily occur in any area that has high appeals to users. Furthermore, support for dy-namic tasking of nodes and efficient processing of data is contrary to the general view of sensor networks as subject to severe resource constraints. Addressing the aforementioned challenges requires the deployment of a system that allows users to take full advantage of data collected in the area of interest to their tasks. Such a system must enable interoperability of surrounding networks, support dynamic tasking, and swiftly react to stimuli. In light of these observations, we introduce a hardware-overlay system designed to allow users to efficiently collect and utilize data from various heterogeneous sensor networks. The hardware-overlay takes advantage of FPGA devices and the mobile agent paradigm in order to efficiently collect and process data from cooperating networks. The computational and power efficiency of the prototyped system are herein demonstrated. Furthermore, as a proof-of-concept, we present the implementation of a distributed and autonomous visual object tracker implemented atop the Reconfigurable and Interoperable Sensor Network (RISN) showcasing the network’s ability to support ad-hoc agent networks dedicated to user’s tasks.展开更多
To accurately track computer viruses,an overlay network that monitors the activities of viruses is constructed.Identifying and locating nodes infected by virus on network is achieved by a naming system in which a node...To accurately track computer viruses,an overlay network that monitors the activities of viruses is constructed.Identifying and locating nodes infected by virus on network is achieved by a naming system in which a node in the network is mapped to a unique serial number of the hard-drive.By carefully monitoring and recording sensitive communication between local system and remote nodes on the network,and suspicious operations on files that originate from remote nodes and entered via some form of file transfer,activities of viruses in both local and network level are recorded and ready for future analysis.These data can also be used in analysis of the mechanism of a computer virus as well as its spreading mode and pattern.展开更多
Overlay multicast has become one of the most promising multicast solutions for IP network,and Neutral Network(NN) has been a good candidate for searching optimal solutions to the constrained shortest routing path in v...Overlay multicast has become one of the most promising multicast solutions for IP network,and Neutral Network(NN) has been a good candidate for searching optimal solutions to the constrained shortest routing path in virtue of its powerful capacity for parallel computation. Though traditional Hopfield NN can tackle the optimization problem,it is incapable of dealing with large scale networks due to the large number of neurons. In this paper,a neural network for overlay multicast tree com-putation is presented to reliably implement routing algorithm in real time. The neural network is constructed as a two-layer recurrent architecture,which is comprised of Independent Variable Neurons(IDVN) and Dependent Variable Neurons(DVN) ,according to the independence of the decision variables associated with the edges in directed graph. Compared with the heuristic routing algorithms,it is characterized as shorter computational time,fewer neurons,and better precision.展开更多
文摘Overlay networking is one of the perspective solutions to today's Intemet challenges. At basic service level, overlay networks can serve as a supplement and enhancement of existing services, such as routing and addressing. At high application level, overlay networks can be used for applications, which are difficult to deploy in existing IP architecture with some specific reasons, e.g., they need high-level information, which is hard to obtain by underlying layers. To address the heterogeneity of today's Internet, overlay networks provide ways to service availability and desirable performance while retaining scalability. In contrast to changing the existing network layer, overlay networks allow bootstrapping, which is most important in the development of Internet infrastructure. Various applications of overlay networking are clarified in this paper. Research challenges including routing and searching in overlay networking are also identified.
文摘Most existing overlay multicast approaches refuse to consider any network layer support no matter whether it is available or not. This design principle greatly increases the complexity of the routing algorithms and makes the overlay topologies incompatible with the underlying network. To address these issues, topology-aware overlay multicast over IP multicast networks (TOMIMN) was proposed as a novel overlay multicast protocol, which exploits the cooperation between end-hosts and IP multicast routers to construct a topology-aware overlay tree. Through a little modification to protocol independent multicast sparse mode (PIM-SM), a multicast router is able to receive registration from nearby group members and redirect passing-by join requests to them. Due to the multicast router's support, TOMIMN organizes its group members into an overlay multicast tree efficiently, which matches the physical network topology well.
基金Project (Nos. 60502014 and 60432030) supported by the National Natural Science Foundation of China
文摘Peer-to-peer (P2P) systems are now very popular. Current P2P systems are broadly of two kinds, structured and unstructured. The tree structured P2P systems used technologies such as distributed hash tables (DHT) and hierarchical clustering can search the required target quickly, however, in a tree, the internal node has a higher load and its leave or crash often causes a large population of its offspring's problems, so that in the highly dynamic Internet environment the tree structure may still suffer frequent breaks. On the other hand, most widely used unstructured P2P networks rely on central directory servers or massive message flooding, clearly not scalable. So, we consider both of the above systems' advantages and disadvantages and realize that in the P2P systems one node may fail easily, but that when a number of nodes organized as a set, which we call "super node", the set is robust. Super nodes can be created and updated aware of topology-aware, and used with simple protocol such as flooding or "servers" to exchange information. Furthermore the entire robust super node can be organized into exquisite tree structure. By using this overlay network architecture, P2P systems are robust, efficient, scalable and secure. The simulation results demonstrated that our architecture greatly reduces the alteration time of the structure while decreasing the average delay time, compared to the common tree structure.
文摘This paper presents a method to model network delay for overlay network application. The network topology measurement technology and network AS information is used to build up model of network delay via AS and geographic distance. Based on global Internet measurement result, we calculated the parameters of the model. Furthermore, the model verification is done by comparing on AS-MMI protocol and HMTP protocol.
文摘Once deployed, sensor networks are capable of providing a comprehensive view of their environment. However, since the current sensor network paradigm promotes isolated networks that are statically tasked, the full power of the harnessed data has yet to be exploited. In recent years, users have become mobile enti-ties that require constant access to data for efficient and autonomous processing. Under the current limita-tions of sensor networks, users would be restricted using only a subset of the vast amount of data being col-lected;depending on the networks they are able to access. Through reliance on isolated networks, prolifera-tion of sensor nodes can easily occur in any area that has high appeals to users. Furthermore, support for dy-namic tasking of nodes and efficient processing of data is contrary to the general view of sensor networks as subject to severe resource constraints. Addressing the aforementioned challenges requires the deployment of a system that allows users to take full advantage of data collected in the area of interest to their tasks. Such a system must enable interoperability of surrounding networks, support dynamic tasking, and swiftly react to stimuli. In light of these observations, we introduce a hardware-overlay system designed to allow users to efficiently collect and utilize data from various heterogeneous sensor networks. The hardware-overlay takes advantage of FPGA devices and the mobile agent paradigm in order to efficiently collect and process data from cooperating networks. The computational and power efficiency of the prototyped system are herein demonstrated. Furthermore, as a proof-of-concept, we present the implementation of a distributed and autonomous visual object tracker implemented atop the Reconfigurable and Interoperable Sensor Network (RISN) showcasing the network’s ability to support ad-hoc agent networks dedicated to user’s tasks.
基金Project is supported by the National Nature Science Foundation of China(Grant No.60672142,60772053,90304005)New architecture and technology for the Internet information sharing,The relation and Countermeasure of Application Layer Behavior and Collective Performance of Internet,Forecast of Traffic Model on Internet+1 种基金Supported by National Basic Research Program of China,(Grant No.2007CB307100,Project No.2007CB307105)The Theory of Mobility and Sensor Network under The Integrated Network and the Universal Ap-plicable Service System
文摘To accurately track computer viruses,an overlay network that monitors the activities of viruses is constructed.Identifying and locating nodes infected by virus on network is achieved by a naming system in which a node in the network is mapped to a unique serial number of the hard-drive.By carefully monitoring and recording sensitive communication between local system and remote nodes on the network,and suspicious operations on files that originate from remote nodes and entered via some form of file transfer,activities of viruses in both local and network level are recorded and ready for future analysis.These data can also be used in analysis of the mechanism of a computer virus as well as its spreading mode and pattern.
基金the High-tech Project of Jiangsu Province (No.BG2003001).
文摘Overlay multicast has become one of the most promising multicast solutions for IP network,and Neutral Network(NN) has been a good candidate for searching optimal solutions to the constrained shortest routing path in virtue of its powerful capacity for parallel computation. Though traditional Hopfield NN can tackle the optimization problem,it is incapable of dealing with large scale networks due to the large number of neurons. In this paper,a neural network for overlay multicast tree com-putation is presented to reliably implement routing algorithm in real time. The neural network is constructed as a two-layer recurrent architecture,which is comprised of Independent Variable Neurons(IDVN) and Dependent Variable Neurons(DVN) ,according to the independence of the decision variables associated with the edges in directed graph. Compared with the heuristic routing algorithms,it is characterized as shorter computational time,fewer neurons,and better precision.
基金Supported by the High Technology Research and Development Programme of China （No. 2003AA121220） and the National Natural Science Foundation of China （No. 60472067）.
