Abstract: Methods to achieve bounded router buffer sizes and Quality of Service guarantees for traffic flows in a packet-switched network are described. The network can be an Internet Protocol (IP) network, a Differentiated Services network, an MPLS network, wireless mesh network or an optical network. The routers can use input queueing, possibly in combination with crosspoint queueing and/or output queueing. Routers may schedule QoS-enabled traffic flows to ensure a bounded normalized service lead/lag. Each QoS-enabled traffic flow will buffer O(K) packets per router, where K is an integer bound on the normalized service lead/lag. Three flow-scheduling methods are analysed. Non-work-conserving flow-scheduling methods can guarantee a bound on the normalized service lead/lag, while work-conserving flow-scheduling methods typically cannot guarantee the same small bound.

Abstract: Methods to achieve bounded router buffer sizes and Quality of Service guarantees for traffic flows in a packet-switched network are described. The network can be an Internet Protocol (IP) network, a Differentiated Services network, an MPLS network, wireless mesh network or an optical network. The routers can use input queueing, possibly in combination with crosspoint queueing and/or output queueing. Routers may schedule QoS-enabled traffic flows to ensure a bounded normalized service lead/lag. Each QoS-enabled traffic flow will buffer O(K) packets per router, where K is an integer bound on the normalized service lead/lag. Three flow-scheduling methods are analysed. Non-work-conserving flow-scheduling methods can guarantee a bound on the normalized service lead/lag, while work-conserving flow-scheduling methods typically cannot guarantee the same small bound.

Abstract: Methods to achieve bounded router buffer sizes and Quality of Service guarantees for traffic flows in a packet-switched network are described. The network can be an Internet Protocol (IP) network, a Differentiated Services network, an MPLS network, wireless mesh network or an optical network. The routers can use input queueing, possibly in combination with crosspoint queueing and/or output queueing. Routers may schedule QoS-enabled traffic flows to ensure a bounded normalized service lead/lag. Each QoS-enabled traffic flow will buffer O(K) packets per router, where K is an integer bound on the normalized service lead/lag. Three flow-scheduling methods are analysed. Non-work-conserving flow-scheduling methods can guarantee a bound on the normalized service lead/lag, while work-conserving flow-scheduling methods typically cannot guarantee the same small bound.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. Each crosspoint contains an internal queue (XQ), which can store one or more packets to be routed. Traffic rates between Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each IO pair within a scheduling frame of F time-slots. An algorithm for scheduling N traffic flows with traffic rates is based upon recursive and fair decomposition of a traffic rate vector with N elements. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of XQs to be reduced. A shared column queue may be used in place of the XQs.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. In an embodiment, each crosspoint contains an internal queue (XQ), which can store one or more packets to be routed. Traffic rates to be realized between all Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each IO pair within a scheduling frame of F time-slots. An efficient algorithm for scheduling N traffic flows with traffic rates based upon a recursive and fair decomposition of a traffic rate vector with N elements, is proposed. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of all the XQs to be reduced. To further reduce memory requirements, a shared column queue may be used in place of the XQs.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. In an embodiment, each crosspoint contains an internal queue (XQ), which can store one or more packets to be routed. Traffic rates to be realized between all Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each IO pair within a scheduling frame of F time-slots. An efficient algorithm for scheduling N traffic flows with traffic rates based upon a recursive and fair decomposition of a traffic rate vector with N elements, is proposed. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of all the XQs to be reduced. To further reduce memory requirements, a shared column queue may be used in place of the XQs.

Abstract: Methods to achieve bounded router buffer sizes and Quality of Service guarantees for traffic flows in a packet-switched network are described. The network can be an Internet Protocol (IP) network, a Differentiated Services network, an MPLS network, wireless mesh network or an optical network. The routers can use input queueing, possibly in combination with crosspoint queueing and/or output queueing. Routers may schedule QoS-enabled traffic flows to ensure a bounded normalized service lead/lag. Each QoS-enabled traffic flow will buffer O(K) packets per router, where K is an integer bound on the normalized service lead/lag. Three flow-scheduling methods are analysed. Non-work-conserving flow-scheduling methods can guarantee a bound on the normalized service lead/lag, while work-conserving flow-scheduling methods typically cannot guarantee the same small bound.

Abstract: Schedule and channel assignment in a wireless mesh network (WMN) includes: forming a representation of a sequence of permutation matrices from an n×n rate matrix. The entries of the rate matrix define the bandwidth of links between nodes of the WMN. Each permutation matrix represents active radio links between nodes. The sequence of permutation matrices defines a sequence of radio links to provide desired bandwidth between nodes. Further, a representation of a sequence of partial permutation matrices corresponding to the sequence of permutation matrices is formed so that each of the permutation matrices can be decomposed into a group of partial permutation matrices. Each partial permutation matrix represents non-interfering radio links between the nodes. In each timeslot, the nodes are configured for radio transmission and reception in accordance with at least one of the partial permutation matrices in each group to transmit traffic between the nodes.

Abstract: Methods to achieve bounded router buffer sizes and Quality of Service guarantees for traffic flows in a packet-switched network are described. The network can be an Internet Protocol (IP) network, a Differentiated Services network, an MPLS network, wireless mesh network or an optical network. The routers can use input queueing, possibly in combination with crosspoint queueing and/or output queueing. Routers may schedule QoS-enabled traffic flows to ensure a bounded normalized service lead/lag. Each QoS-enabled traffic flow will buffer O(K) packets per router, where K is an integer bound on the normalized service lead/lag. Three flow-scheduling methods are analyzed. Non-work-conserving flow-scheduling methods can guarantee a bound on the normalized service lead/lag, while work-conserving flow-scheduling methods typically cannot guarantee the same small bound.

Abstract: Schedule and channel assignment (SCA) in a wireless mesh network (WMN) is disclosed. A method includes: forming a representation of a sequence of permutation matrices from an n×n rate matrix. The entries of the rate matrix define the bandwidth of links between the n nodes of the WMN. Each of the permutation matrices represents active radio links between the n nodes. The sequence of permutation matrices defines a sequence of radio links to provide the desired bandwidth of links between said n nodes. Further, a representation of a sequence of partial permutation matrices corresponding to the sequence of permutation matrices is formed in such a way that each of the permutation matrices can be decomposed into a group of partial permutation matrices. Each of the partial permutation matrices in a group represents non-interfering radio links between the n nodes.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. In an embodiment, each crosspoint contains an internal queue (XQ), which can store one or more packets to be routed. Traffic rates to be realized between all Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each IO pair within a scheduling frame of F time-slots. An efficient algorithm for scheduling N traffic flows with traffic rates based upon a recursive and fair decomposition of a traffic rate vector with N elements, is proposed. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of all the XQs to be reduced. To further reduce memory requirements, a shared column queue may be used in place of the XQs.

Abstract: Schedule and channel assignment (SCA) in a wireless mesh network (WMN) is disclosed. A method includes: forming a representation of a sequence of permutation matrices from an n×n rate matrix. The entries of the rate matrix define the bandwidth of links between the n nodes of the WMN. Each of the permutation matrices represents active radio links between the n nodes. The sequence of permutation matrices defines a sequence of radio links to provide the desired bandwidth of links between said n nodes. Further, a representation of a sequence of partial permutation matrices corresponding to the sequence of permutation matrices is formed in such a way that each of the permutation matrices can be decomposed into a group of partial permutation matrices. Each of the partial permutation matrices in a group represents non-interfering radio links between the n nodes.

Abstract: Methods to achieve bounded router buffer sizes and Quality of Service guarantees for traffic flows in a packet-switched network are described. The network can be an Internet Protocol (IP) network, a Differentiated Services network, an MPLS network, wireless mesh network or an optical network. The routers can use input queueing, possibly in combination with crosspoint queueing and/or output queueing. Routers may schedule QoS-enabled traffic flows to ensure a bounded normalized service lead/lag. Each QoS-enabled traffic flow will buffer O(K) packets per router, where K is an integer bound on the normalized service lead/lag. Three flow-scheduling methods are analysed. Non-work-conserving flow-scheduling methods can guarantee a bound on the normalized service lead/lag, while work-conserving flow-scheduling methods typically cannot guarantee the same small bound.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. In an embodiment, each crosspoint contains an internal queue (XQ), which can store one or more packets to be routed. Traffic rates to be realized between all Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each 10 pair within a scheduling frame of F time-slots. An efficient algorithm for scheduling N traffic flows with traffic rates based upon a recursive and fair decomposition of a traffic rate vector with N elements, is proposed. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of all the XQs to be reduced. To further reduce memory requirements, a shared column queue may be used in place of the XQs.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. In an embodiment, each crosspoint contains an internal queue (XQ), which can store one or more packets to be routed. Traffic rates to be realized between all Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each IO pair within a scheduling frame of F time-slots. An efficient algorithm for scheduling N traffic flows with traffic rates based upon a recursive and fair decomposition of a traffic rate vector with N elements, is proposed. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of all the XQs to be reduced. To further reduce memory requirements, a shared column queue may be used in place of the XQs.

Abstract: Methods to achieve bounded router buffer sizes and Quality of Service guarantees for traffic flows in a packet-switched network are described. The network can be an Internet Protocol (IP) network, a Differentiated Services network, an MPLS network, wireless mesh network or an optical network. The routers can use input queueing, possibly in combination with crosspoint queueing and/or output queueing. Routers may schedule QoS-enabled traffic flows to ensure a bounded normalized service lead/lag. Each QoS-enabled traffic flow will buffer O(K) packets per router, where K is an integer bound on the normalized service lead/lag. Three flow-scheduling methods are analysed. Non-work-conserving flow-scheduling methods can guarantee a bound on the normalized service lead/lag, while work-conserving flow-scheduling methods typically cannot guarantee the same small bound.

Abstract: Schedule and channel assignment in a wireless mesh network (WMN) includes: forming a representation of a sequence of permutation matrices from an n×n rate matrix. The entries of the rate matrix define the bandwidth of links between nodes of the WMN. Each permutation matrix represents active radio links between nodes. The sequence of permutation matrices defines a sequence of radio links to provide desired bandwidth between nodes. Further, a representation of a sequence of partial permutation matrices corresponding to the sequence of permutation matrices is formed so that each of the permutation matrices can be decomposed into a group of partial permutation matrices. Each partial permutation matrix represents non-interfering radio links between the nodes. In each timeslot, the nodes are configured for radio transmission and reception in accordance with at least one of the partial permutation matrices in each group to transmit traffic between the nodes.

Abstract: Schedule and channel assignment (SCA) in a wireless mesh network (WMN) is disclosed. A method includes: forming a representation of a sequence of permutation matrices from a n×n rate matrix. The entries of the rate matrix define the bandwidth of links between the n nodes of the WMN. Each of the permutation matrices represents active radio links between the n nodes. The sequence of permutation matrices defines a sequence of radio links to provide the desired bandwidth of links between said n nodes. Further, a representation of a sequence of partial permutation matrices corresponding to the sequence of permutation matrices is formed in such a way that each of the permutation matrices can be decomposed into a group of partial permutation matrices. Each of the partial permutation matrices in a group represents non-interfering radio links between the n nodes.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. In an embodiment, each crosspoint contains an internal queue (XQ), which can store one or more packets to be routed. Traffic rates to be realized between all Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each IO pair within a scheduling frame of F time-slots. An efficient algorithm for scheduling N traffic flows with traffic rates based upon a recursive and fair decomposition of a traffic rate vector with N elements, is proposed. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of all the XQs to be reduced. To further reduce memory requirements, a shared column queue may be used in place of the XQs.

Abstract: A crossbar switch has N input ports, M output ports, and a switching matrix with N×M crosspoints. In an embodiment, each crosspoint contains an internal queue (XQ), which can store one or more packets to be touted. Traffic rates to be realized between all Input/Output (IO) pairs of the switch are specified in an N×M traffic rate matrix, where each element equals a number of requested cell transmission opportunities between each IO pair within a scheduling frame of F time-slots. An efficient algorithm for scheduling N traffic flows with traffic rates based upon a recursive and fair decomposition of a traffic rate vector with N elements, is proposed. To reduce memory requirements a shared row queue (SRQ) may be embedded in each row of the switching matrix, allowing the size of all the XQs to be reduced. To further reduce memory requirements, a shared column queue may be used in place of the XQs.