Abstract: This disclosure describes techniques for employing a collaborate traffic balancer in communications among network devices. The techniques include dynamic traffic engineering concepts to improve network communications. The techniques may include causing a headend device to establish a secure communication session between a client device and a server in a resource infrastructure supporting the service. The techniques may include selecting a tunnel for the secure communication session to reach the resource infrastructure. The techniques may further include migrating the secure communication session from a current tunnel to a new tunnel where a degradation in quality of the secure communication session is predicted.

Abstract: This disclosure describes techniques for employing a collaborate traffic balancer in communications among network devices. The techniques include dynamic traffic engineering concepts to improve network communications. The techniques may include causing a headend device to establish a secure communication session between a client device and a server in a resource infrastructure supporting the service. The techniques may include selecting a tunnel for the secure communication session to reach the resource infrastructure. The techniques may further include migrating the secure communication session from a current tunnel to a new tunnel where a degradation in quality of the secure communication session is predicted.

Abstract: In one embodiment, a method includes generating, by a controller, intent-based entries. The intent-based entries include information associated with scheduling of service instances. The method also includes receiving, by the controller, feedback from an assurance platform. The feedback is generated by the assurance platform using metrics received from cloud service providers. Each of the cloud service providers is associated with an agent. The method further includes determining, by the controller, updates for the intent-based entries based on the feedback and communicating, by the controller, the updates for the intent-based entries to agents of the cloud service providers.

Abstract: The disclosed technology relates to a process for automating an optimized schedule of future application traffic paths on various Virtual Private Networks (VPN) tunnels using different Key Performance Indicators (KPIs) in order to meet the different applications' Service Level Agreements. The schedule is based on first characterizing the performance of different tunnels observed over a period of time. The past performance of the tunnels is then used to predict future performance of the same tunnels using machine learning. A schedule is then generated based on the prediction to transmit content across the network that best satisfies the SLA criteria of the content. The process lowers overall Operation Expenditure (OPEX) related to the cost (e.g. time and resources) of the overall network, improves data flow, and minimizes interruptions.

Abstract: In one embodiment, a network functions virtualization infrastructure can be managed in a decentralized fashion. A front end can receive a request to provision a virtualized network function. The front end can create service descriptors for the request according to the virtualized network function, the service descriptors comprising a hierarchy of information elements organized based on distributed back-end agents operable to provision and manage the virtualized network function. The front end can store the service descriptors in a distributed data store.

Abstract: In one embodiment, a network functions virtualization infrastructure can be managed in a decentralized fashion. A front end can receive a request to provision a virtualized network function. The front end can create service descriptors for the request according to the virtualized network function, the service descriptors comprising a hierarchy of information elements organized based on distributed back-end agents operable to provision and manage the virtualized network function. The front end can store the service descriptors in a distributed data store.