Citrix Systems, Inc.

Anup Lal Gupta

Praveen Raja Dhanabalan

Akshata Bhat

Jaskirat Chauhan

Marco Murgia

James Roy Bulpin

Saurabh Pant

The systems and methods of the present disclosure are directed towards a dynamic system that is configured to identify and map networked traffic, such as that of video, voice, file transfer, and web based applications to predetermined Quality of Service (QoS) classes. The different QoS classes can be associated with different traffic priorities. The networked traffic can be encrypted, which can prevent an intermediate device from processing or otherwise reading the packet headers of the traffic. The systems and methods of the present disclosure can predict QoS classes for encrypted traffic based on traffic patterns and other characteristics of the encrypted traffic.

Learning technique for QoS based classification and prioritization of SAAS applications

This disclosure is directed to embodiments of systems and methods for performing compression of data in a queue. A device intermediary between a client and a server may determine that a length of time to move existing data maintained in a queue from the queue exceeds a predefined threshold. The device may identify, responsive to the determination, a first quantity of the existing data to undergo compression, and a second quantity of the existing data according to a compression ratio of the compression. The device may reserve, according to the second quantity, a first portion of the queue that maintained the first quantity of the existing data, to place compressed data obtained from applying the compression on the first quantity of the existing. The device may place incoming data into the queue beyond the reserved first portion of the queue.

Application and network aware adaptive compression for better QoE of latency sensitive applications

Disclosed embodiments describe systems and methods for predicting health of a link. A device in communication with a link can identify profile information of a stream of network traffic traversing the link. The device can determine a first prediction of health of the link by applying one or more rules to the plurality of parameters of the profile information. The device can determine a second prediction of health of the link by applying a classifier to one or more timed sequences of the plurality of parameters of the profile information. The device can establishes a respective weight for each of the first prediction of health and the second prediction of heath. The device can select, using the respective weight, between the first prediction of health and the second prediction of health to provide a predictor of the health of the link.

Proactive link load balancing to maintain quality of link

An Internet of Things (IoT) topology analyzer includes an input to passively receive packets exchanged between IoT devices operating within a network and at least one IoT server connected to the network. A processor is coupled to the input and is configured to determine a number of IoT devices operating within the network based on the received packets, with the number of IoT devices used to define an IoT topology of the network.

IoT topology analyzer defining an IoT topology and associated methods

Techniques proactively deploy analytics to a computerized edge device. The techniques involve receiving data from the edge device. The data is conveyed through the edge device from a set of sensors disposed at a particular location. The techniques further involve performing analytics on the data to identify a set of edge device rules that defines a set of actions for the edge device to carry out under a set of predefined conditions potentially sensed by the set of sensors. The techniques further involve providing a command to the edge device. The command (i) includes the set of edge device rules and (ii) directs the edge device to, at a future time, start operating according to the set of edge device rules to protect against unsuccessful deployment of the command to the edge device due to subsequent delayed communication between the processing circuitry and the edge device.

Proactively deploying analytics to a computerized edge device

Methods and systems described herein are directed towards using artificial intelligence to recommend network features to add to networks. A network configuration system may determine the network components and usage characteristics for a network within a plurality of networks. The network configuration system may use an ensemble to generate recommendations based on the network components and usage characteristics of the plurality of networks. The ensemble may include one or more machine learning based recommenders. The ensemble may also include a non-personalized recommender that generates recommendations based on known compatibility between network features. The network configuration system may weight recommendations from each recommender to create a ranked ordering of the recommendations. The network configuration system may modify (e.g., add or remove network features) one or more networks based on the recommendations and/or user input. As networks are modified, the network configuration system may train each recommender to provide better recommendations.

Network configuration system

Systems and methods for identifying a new device in an internet of things (IoT) network comprising a plurality of devices. The method includes, by a processor: detecting that a new device has been added to the IoT network; receiving identification data corresponding to the new device; determining a first device identification using a deep learning algorithm; determining a second device identification using a clustering algorithm; determining a third device identification based on a reference table; determining a fourth device identification by analyzing one or more values included in the identification data. The method further includes selecting, at least one of the first device identification, the second device identification, the third device identification, or the fourth device identification, as a final device identification by performing a weighted selection.

Systems and methods for inventory discovery in a network

The present disclosure discloses a system that automatically identifies the most efficient times to upgrade software associated with an IoT device. The system employs machine-learning mechanisms to precisely identify the specific time interval where there will be the least impact on the functionality of the IoT device or a cluster of IoT devices.

Systems and methods for managing lifecycle and reducing power consumption by learning an IoT device

A device for an Internet of Things (IoT) workspace monitors the IoT workspace to determine a change in a number of IoT devices operating within the IoT workspace. A respective topology of the IoT workspace is determined based the number of IoT devices operating in the IoT workspace. The IoT devices based on each topology are mapped, with each map identifying locations of the IoT devices within the IoT workspace. Relationships and dependencies are determined between the IoT devices for each map. A weight is assigned to each IoT device based on the determined relationships and dependencies for each map. The assigned weights of the changed number of IoT devices are compared to the assigned weights of the IoT devices operating before the change so as to quantify an impact of the change in the IoT workspace.

Change criticality quantifier for an IoT workspace and associated methods

The systems and methods discussed herein provide for a predictive monitoring technique to suppress data exchange between the client device or devices and the monitoring device or devices. Regression-based intelligent predictions systems executed both by the client device or devices and the monitoring device or devices perform identical prediction algorithms. If the predicted metric values and the actual measured metric values on the client device are very close, then the client device may skip transmitting the measured metric values to the monitoring device; similarly, if a measured metric value is not received by the monitoring device, then the monitoring device knows that the measured metric was similar to the predicted metric on the client device, and accordingly may utilize the predicted metric on the monitoring device. Because transmission of the measured metric values may be skipped, network traffic and interface and processor utilization is significantly decreased.

Growing community of inventors

Bengaluru, India

Anup Lal Gupta