Abstract: Methods implemented in an electronic device are disclosed for checkpoint and rollback recovery in a SDN system. The method utilizes message identifiers to indicate an order of consistent states of forwarding tables of a plurality of network elements of the SDN system. The SDN controller of the SDN system receives a request to recover the network to a previous state, and identifies a consistent state of forwarding table for each of the plurality of network elements utilizing the message identifiers associated the consistent states, where the identified consistent states represent the previous state of the network without the identified consistent states being captured at the same time at the plurality of network elements. The SDN controller indicates the identified consistent state for each of the plurality of the network elements to a corresponding network element, where the corresponding network element makes its forwarding table consistent with the identified consistent state.

Abstract: A system and method for placing inline services having multiple instances in a service provider network. In one implementation, a topology of the service provider network and services to be placed therein are defined, wherein a network node may include a data forwarding functionality and a control plane functionality. Using service chaining policy requirements, the number of service instances, etc. as input, services and their multiple instances are placed within the network such that an overall network metric is optimized for all subscriber data flows.

Abstract: Embodiments of the present disclosure include a method and apparatus for placing services in a network. The network and a set of services to be placed within the network are defined. A set of requirements for a plurality of subscribers is determined. Each requirement is a sequence of services to traverse for each subscriber. The services are placed such that a total delay or total distance is minimized for all subscribers.

Abstract: A method implemented in a network for placing services in a SDN system is disclosed. The network contains a plurality of network devices managed by a SDN controller and offers a set of services to subscribers. Subsets of the set of services are included in ordered service chains for subscribers. The method starts with determining a list of bandwidth consumption entities of a service for each service, where each bandwidth consumption entity is based on one or more chains of services. Then a weight of each service is calculated based on the list of bandwidth consumption entities of the service and a service with the highest weight within a group of services that have not been placed in the SDN system is selected. The selected service is then placed at a network device based at least partially on calculating bandwidth impacts to the SDN system by the service.

Abstract: A method for placing services at network devices is disclosed. A network contains a plurality of network devices and the network offers a set of services to subscribers. Each subscriber of the network utilizes a subset of the set of service, where an order of the services is not predefined. The method starts with ordering the services from the most utilized service to the least utilized, and selects services from the most utilized to the least utilized. For each service, a network device is selected so that placing the service adds a least sum of additional delay based on services already placed in the network, and a path for each subscriber utilizing the service is updated to include the service, where the path is an ordered chain of services, and where the service is inserted in the path to result in minimum addition to delay to the subscriber.

Abstract: Methods implemented in an electronic device are disclosed for checkpoint and rollback recovery in a SDN system. The method utilizes message identifiers to indicate an order of consistent states of forwarding tables of a plurality of network elements of the SDN system. The SDN controller of the SDN system receives a request to recover the network to a previous state, and identifies a consistent state of forwarding table for each of the plurality of network elements utilizing the message identifiers associated the consistent states, where the identified consistent states represent the previous state of the network without the identified consistent states being captured at the same time at the plurality of network elements. The SDN controller indicates the identified consistent state for each of the plurality of the network elements to a corresponding network element, where the corresponding network element makes its forwarding table consistent with the identified consistent state.

Abstract: A method implemented by a network topology design system, the network topology design system including a processing device. The method to determine placement of a controller within a network with a split architecture where control plane components of the split architecture network are executed by a controller and the control plane components are separate from data plane components of the split architecture network. The placement of the controller is selected to minimize disruption of the split architecture network caused by a link failure, a switch failure or a connectivity loss between the controller and the data plane components.

Abstract: A method implemented in a network for placing services in a SDN system is disclosed. The network contains a plurality of network devices managed by a SDN controller and offers a set of services to subscribers. Subsets of the set of services are included in ordered service chains for subscribers. The method starts with determining a list of bandwidth consumption entities of a service for each service, where each bandwidth consumption entity is based on one or more chains of services. Then a weight of each service is calculated based on the list of bandwidth consumption entities of the service and a service with the highest weight within a group of services that have not been placed in the SDN system is selected. The selected service is then placed at a network device based at least partially on calculating bandwidth impacts to the SDN system by the service.

Abstract: A network element controls congestion in a link of a packet data network. A congested link is identified and a throttle rate is determined for one or more of the traffic groups traversing the congested link. The central controller determines the throttle rates using a weight of the group and the current traffic rate of the group through the link. The throttle rates are sent to switches to throttle traffic for each affected group.

Abstract: A process is performed by a controller in a split-architecture network. The controller monitors congestion of traffic groups across the split-architecture network and executes the process to provide delay based data rate control to alleviate congestion of the traffic groups. The process includes configuring an ingress switch and egress switch for each traffic group to collect delay measurement data for data packets of each traffic group as they arrive at the ingress switch and egress switch. The delay measurement data is received from the ingress switch and egress switch of each traffic group. A check is made whether a minimum data packet delay for any traffic group exceeds a defined threshold value. At least one traffic group is then identified in the split-architecture network to discard in response to the threshold value being exceeded.

Abstract: The invention is a routing algorithm characteristic that minimizes the weight, meaning that the probability that a node is disconnected from the controller in case of a failure in the network is minimized. The first algorithm used in the invention is an approximation algorithm for finding the controller routing tree that provides maximum resilience in the network. The algorithm is referred to herein as the Maximum Resilience (MR) algorithm. The heuristic MR algorithm selects a shortest-path tree as a starting point and modifies the tree in order to improve resilience. The output of the MR algorithm is not necessarily a shortest-path tree, but provides more resilience compared to the initial tree. The RASP algorithm provides a shortest-path tree with improved network resilience compared to other possible shortest-path trees.

Abstract: A control plane device in a cloud computing system executes a plurality of virtual machines for implementing network function virtualization (NFV). The control plane device is operable to manage implementation of a general packet radio service (GPRS) tunnel protocol (GTP) in a packet core (PC) of a third generation (3G) network having a split architecture where a control plane of the PC of the 3G network is in the cloud computing system. The control plane communicates with a data plane of the PC through a control plane protocol. The data plane is implemented in a plurality of network devices of the 3G network. The control plane device and the plurality of virtual machines are operable to communicate with other control plane devices in the cloud computing system and with the plurality of network devices of the data plane.

Abstract: A method and apparatus for optimizing the resilience of a network using a combination of in-band and out-of-band signaling is disclosed. The metric used in the embodiment's algorithm to determine resilience is the maximum number of protected neighbors. Nodes closer to the controller are assigned a higher weight than those further from the controller because if their connection to the network is interrupted, all their downstream nodes will be affected and disconnected. Therefore, when determining a path to the controller, switches with alternate paths to the controller are preferred. Dedicated connections using out-of-band signaling are assigned to convert unprotected nodes to protected nodes thus improving the resilience of the network.

Abstract: A method implemented in a network for placing services at network devices is disclosed. The network contains a plurality of network devices and offers a set of services to subscribers. Subsets of the set of services are included in ordered service chains for subscribers. The method starts with determining a list of bandwidth consumption entities of a service for each service within the set of services, where each bandwidth consumption entity is based on one or more chains of services. Then a weight of each service is calculated based on the list of bandwidth consumption entities of the service and a service with a highest weight within the group of one or more services that have not been placed is selected. The selected service is then placed at a network device based at least partially on calculating bandwidth impacts to the network by the service.

Abstract: A network element controls congestion in a link of a packet data network. A congested link is identified and a throttle rate is determined for one or more of the traffic groups traversing the congested link. The central controller determines the throttle rates using a weight of the group and the current traffic rate of the group through the link. The throttle rates are sent to switches to throttle traffic for each affected group.

Abstract: A method implemented by a network topology design system, the network topology design system including a processing device. The method to determine placement of a controller within a network with a split architecture where control plane components of the split architecture network are executed by a controller and the control plane components are separate from data plane components of the split architecture network. The placement of the controller is selected to minimize disruption of the split architecture network caused by a link failure, a switch failure or a connectivity loss between the controller and the data plane components.

Abstract: A method implemented by a network topology design system, the network topology design system including a processing device. The method to determine placement of a controller within a network with a split architecture where control plane components of the split architecture network are executed by a controller and the control plane components are separate from data plane components of the split architecture network. The placement of the controller is selected to minimize disruption of the split architecture network caused by a link failure, a switch failure or a connectivity loss between the controller and the data plane components.

Abstract: A method for placing services at network devices is disclosed. A network contains a plurality of network devices and the network offers a set of services to subscribers. Each subscriber of the network utilizes a subset of the set of service, where an order of the services is not predefined. The method starts with ordering the services from the most utilized service to the least utilized, and selects services from the most utilized to the least utilized. For each service, a network device is selected so that placing the service adds a least sum of additional delay based on services already placed in the network, and a path for each subscriber utilizing the service is updated to include the service, where the path is an ordered chain of services, and where the service is inserted in the path to result in minimum addition to delay to the subscriber.

Abstract: A process is performed by a controller in a split-architecture network. The controller monitors congestion of traffic groups across the split-architecture network and executes the process to provide delay based data rate control to alleviate congestion of the traffic groups. The process includes configuring an ingress switch and egress switch for each traffic group to collect delay measurement data for data packets of each traffic group as they arrive at the ingress switch and egress switch. The delay measurement data is received from the ingress switch and egress switch of each traffic group. A check is made whether a minimum data packet delay for any traffic group exceeds a defined threshold value. At least one traffic group is then identified in the split architecture network to discard in response to the threshold value being exceeded.

Abstract: A network element controls congestion in a link of a packet data network. A congested link is identified and a throttle rate is determined for one or more of the traffic groups traversing the congested link. The central controller determines the throttle rates using a weight of the group and the current traffic rate of the group through the link. The throttle rates are sent to switches to throttle traffic for each affected group.