Ciena Corporation

Nortel Networks Corporation

Rockstar Consortium US LP

Rockstar Bidco, LP

Lyndon Y Ong

Loudon Thomas Blair

Michael Y Frankel

Ian Hamish Duncan

Michael Alain Gazier

Christian Bourget

Raghuraman Ranganathan

David W Boertjes

Jamie Gaudette

Tal Isaac Lavian

David Côté

Thomas Triplet

Stephen Lau

Sandeep Bhat

Saikrishna M Kotha

Anurag Prakash

Mohit Chhillar

John K Oltman

Nigel Robert Davis

Vagish Madrahalli

Marian Trnkus

Francois Audet

Neena Aluri

Yalin Wang

Alessandro Fabbri

David Keith Bainbridge

Robert J Dalias

Steven P Curtis

Mahad Ahmed

Rajender Razdan

Magdi Wissa

Jiri Matousek

Mo R Zonoun

Shelly A Bhalla

Artificial Intelligence (AI)-based network control includes obtaining data from a network having a plurality of network elements; analyzing the data with one or more Machine Learning (ML) algorithms to determine one or more actions for network control; analyzing the determined one or more actions to determine any risks associated therewith; and one of allowing, modifying, and blocking the determined one or more actions based on the determined risks to safeguard the network. The risks can be based on one or more of (1) non-deterministic behavior AI inference which is statistical in nature, (2) unbounded uncertainty of the AI inference that can result in arbitrarily large inaccuracy on rare occasions, (3) unpredictable behavior of the AI inference in presence of input data that is different than data in training and testing datasets, and (4) malicious input data.

Safeguarding artificial intelligence-based network control

Systems and methods include receiving information from a governed system having resources; implementing one or more context neutral or specific control applications that each is a pipeline of a plurality of functions to control the resources; utilizing the information as one input to a first function in the plurality of functions; utilizing inputs from one or more control applications as inputs to any of the plurality of functions; and causing actions on the resources based on outputs of a last function in the plurality of functions. The plurality of functions can include sensing, discerning, inferring, deciding, and causing the actions.

Governance and interactions of autonomous pipeline-structured control applications

An Artificial Intelligence (AI)-based network control system includes an AI system configured to obtain data from a network having a plurality of network elements and to determine actions for network control through one or more Machine Learning (ML) algorithms; a controller configured to cause the actions in the network; and a safeguard module between the AI system and the controller, wherein the safeguard module is configured to one of allow, block, and modify the actions from the AI system.

A method, implemented by a slice registration server, for dynamic reservation of network slices includes receiving a first request from a client for a network slice including one or more of networks, compute, and storage resources in one or more networks for a time period; determining availability of the network resources based on the first request and a state of the one or more networks; transmitting a response to the client based on the availability; receiving a second request from the client based on the response; and causing instantiation of the network resources and providing an acknowledgment to the client based thereon.

Dynamic reservation protocol for 5G network slicing

Systems and methods for path computation in an optical network include obtaining optical layer characteristics related to one or more optical paths in the optical network based in part on performance measurements in the optical network; responsive to service establishment or service restoration, determining a path from source to destination based on utilizing the optical layer characteristics to confirm physical validity of the path; and provisioning a service on the determined path from the source to the destination in the optical network.

Path computation based on dynamic performance monitoring systems and methods in optical networks

The present disclosure provides dynamic performance monitoring systems and methods for optical networks to ascertain optical network health in a flexible and accurate manner. The present invention introduces accurate estimations for optical channel performance characteristics based either on existing channels or with a dynamic optical probe configured to measure characteristics on unequipped wavelengths. Advantageously, the dynamic performance monitoring systems and methods introduce the ability to determine physical layer viability in addition to logical layer viability.

Software Defined Networking systems and methods are described via a Path Computation and Control Element (PCCE) that is based in part on a Path Computation Element (PCE). A common, simple interface is designed based on an existing PCE interface that allows a centralized entity (i.e., a Path Computation and Control Element or PCCE) to control the initiation of new connections or tunnels and by default to manage the state of these connections or tunnels once established. In particular, the systems and methods create an extension to the PCE architecture to allow a centralized application or applications to control the creation, rerouting and deletion of connections within a network.

Software defined networking systems and methods via a path computation and control element

Coherent probe and optical service channel systems and methods for optical networks

A method and system for path computation in a communications network having multiple domains are disclosed. According to one aspect, a method of path computation across multiple domains includes identifying a plurality of border nodes at borders of a plurality of domains, each domain having at least one border node. The method includes providing a path computation element at each of the plurality of border nodes of the domains of the network. The locations of the path computation elements are known to be at the border nodes prior to determining a path in response to a path computation request.

Method for discovery and load balancing of path computation elements based on transport plane link metrics

Photonic link information collection and advertisement systems and methods enable photonic nodes (e.g., optical amplifiers) to operate within a control plane system in a distributed and real-time manner. For example, the photonic nodes may not require full control plane protocol stacks at each photonic node. In particular, the systems and methods provide a distributed discovery method for photonic links without requiring full participation in the control plane at the photonic nodes. Additionally, the systems and methods include network databases with amplifier configuration information in a control plane enabled network.

Photonic link information collection and advertisement systems and methods

A distributed network address translation (NAT) system is used to transport data packets between private and public network domains. A packet modifier substitutes public and private network address information in packets that are crossing between public and private domains to and from the end system. A network application server has an address mapping table and communicates with the packet modifier over a control protocol. The network application server generates address mappings which the packet modifier uses for modification of data packets passing through it.

Distributed network address translation control

The present invention utilizes control plane signaling to dynamically configure flexible, existential ports. The ports are referred to as existential as their nature can change over time depending on the present need of the network, and because the ports are flexible and reconfigurable to a plurality of bit rates and protocols. The present invention removes the constraints of provisioning individual ports and connections, such as from a network management system, and integrates the concept of flexible ports with signaling and control plane methods utilized for routing in modern networks. Advantageously, the present invention extends service providers' investments in equipment, and reduces operating expenses in providing systems that are able to dynamically deal with various network configurations and with low touch by automatically performing provisioning. The methods and systems of the present invention can be extended to other networks utilizing flexible ports, such as wireless radios and the like.

Methods and systems for existential provisioning of flexible line modules using distributed control

The present invention provides a mechanism for distributing client Virtual Private Network (VPN)-related information within a network using a source-independent distributed advertisement that includes incorporating client VPN-related information related to a node of a network into a source-independent distributed advertisement associated with a routing protocol, distributing the source-independent distributed advertisement from the node of the network to at least one other node of the network, or from another node of the network or a centralized management system to the at least one other node of the network, and updating other VPN-related information with the client VPN-related information related to the node of the network at the at least one other node of the network, wherein the client VPN-related information related to the node of the network is distributed to the at least one other node of the network without requiring the establishment of a Transmission Control Protocol (TCP) session specifically for the distribution of the client VPN-related information.

Flexible mechanism for supporting virtual private network services based on source-independent distributed advertisements

The present disclosure provides virtual router/switch systems and methods with a domain of optical switches operating as a single, virtualized router using a control plane design combining centralized control of higher layer packet switching functions with distributed control over transport switching functions. The virtual router systems and methods simplify and reduce cost of Internet Protocol (IP) networks by removing the core routers, replacing them with lower cost, high capacity optical switches which are Packet Optical Transport Systems (POTS). The virtual router systems and methods avoids full mesh connectivity of the edge routers and the associated need to maintain routing adjacencies to each of the other edge routers. The virtual router systems and methods include a centralized IP layer management. Further, the virtual router systems and methods include distributed control of the optical layers.

Growing community of inventors

Sunnyvale, CA, United States of America

Lyndon Y Ong