Juniper Networks, Inc.

Hsiuyen Tsai

Jenchieh Tsai

Francois Effendy

Shivaprasad Gali

Sanjeev Kumar Mishra

Sabyasachi Mukhopadhyay

François Effendy

Techniques are described for predicting future behavior of links in a network and generating dynamic thresholds for link metrics for use in path selection. In one example, a computing system receives historical values of a link metric for links of a network. The computing system executes a machine learning system which processes the historical values of the link metric to generate: (1) a predicted future value of the link metric for each link; and (2) a threshold for the link metric indicating whether the predicted future value for each link is anomalous. The computing system computes a path based on the predicted future values of the link metric and the threshold for the link metric. The computing system provisions the computed path, thereby enabling a network device to forward network traffic along the computed path.

Link behavior prediction for use in path selection

A device receives topology data and path data associated with a network that includes network devices. The device determines planned bandwidths for new paths through the network based on the topology data and the path data, and ranks the new paths, based on the planned bandwidths, to generate a ranked list. The device selects information identifying a first new path from the ranked list, wherein the first new path includes a first planned bandwidth. The device determines whether the first new path can be provided via a single route through the network based on the first planned bandwidth, and identifies two or more routes through the network for the first new path when the first new path cannot be provided via the single route. The device causes the first planned bandwidth to be reserved by two or more of the network devices for the two or more routes.

Centralized controller-based dynamic network bandwidth allocation and management

Growing community of inventors

Edison, NJ, United States of America

Hsiuyen Tsai