Hughes Network Systems, LLC

Amit Arora

John D Kenyon

Archana Gharpuray

Satyajit Roy

Robert James Torres

Jun Xu

Sandeep Ahluwalia

Hanny Kadrichu

Chandrasekhar Sangireddi

Thomas Jagodits

Joseph Sanju George

Kartik Seshadri

Zhao Chan Lin

Sonia Thakur

Namrata Walanj

Sairaj Amberkar

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining availability of network service. In some implementations, a request indicating a location and a communication service level is received. A first subset of service providers or communication technologies is determined based on outputs generated by multiple first machine learning models each trained to predict service availability for different service providers or communication technologies. A second subset is selected from the first subset based on outputs generated by multiple second machine learning models trained to predict availability of different communication service levels for different service providers or communication technologies. At least one service provider or communication technology is selected from the second subset based on output generated by a third machine learning model. A response to the request indicating the selected service provider or communication technology is provided.

Determining availability of network service

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for using machine learning to detect and correct satellite terminal performance limitations. In some implementations, a system retrieves data indicating labels for clusters of network performance anomalies. The system generates a set of training data to train a machine learning model, the set of training data being generated by assigning the labels for the clusters to sets of performance indicators used to generate the clusters. The system trains a machine learning model to predict classifications for communication devices based on input of performance indicators for the communication devices. The system determines a classification for the communication device based on output that the trained machine learning model generates.

Machine learning to enhance satellite terminal performance

Methods and systems for monitoring a communication network using machine-learning techniques are disclosed. In some implementations, a forecasted amount of traffic for a communication network is determined using one or more network traffic forecasting models being configured to generate the forecasted amount of traffic based on data indicating one or more previous amounts of traffic for the communication network. A measure of network health is generated based on a measured amount of traffic and the forecasted amount of traffic. Data indicating one or more characteristics of the communication network is processed using one or more machine learning models to generate a predicted measure of network health for a future time period. An indication of the predicted measure of network health for the future time period is provided.

Monitoring a communication network

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for machine learning models for adjusting communication parameters. In some implementations, data for each device in a set of multiple communication devices is obtained. A machine learning model is trained based on the obtained data. The model can be trained to receive an indication of a geographic location and predict a communication setting capable of providing at least a minimum level of efficiency. After training the machine learning model, an indication of a predicted communication setting for a particular communication device is generated. A determination is then made whether to change a current communication setting for the particular communication device based on the predicted communication setting.

Machine learning models for adjusting communication parameters

Systems and methods are provided to achieve dynamic bandwidth allocation among terminal groups (TGs) with proportional fairness in terms of both throughput and spectrum usage across a network. Quality of service (QoS) metrics for such TGs can be satisfied in terms of maximum throughput and spectrum utilization, while also satisfying QoS metrics such as latency, throughput, and prioritized traffic services for individual terminals within the TGs. A centralized bandwidth manager can be utilized to manage such dynamic bandwidth allocation across multiple Code Rate Organizers (CROs), including environments in which the multiple CROs manage communications across multiple IPGWs for multiple terminal groups. Because, in such environments, a given conventional CRO cannot effectively manage allocations across the entire network, the centralized bandwidth management functionality can be introduced to assess the flows for multiple TGs across multiple CROs and to make bandwidth allocations accordingly.

Dynamic bandwidth management with spectrum efficiency for logically grouped terminals in a broadband satellite network

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning models to classify network traffic as IoT traffic or non-IoT traffic and managing the traffic based on the classification. In some implementations, machine learning parameters of a local machine learning model trained by the edge device is received each of at least a subset of a set of edge devices. The machine learning parameters received from an edge device are parameters of the local machine learning model trained by the edge device based on local network traffic processed by the edge device and to classify the network traffic as Internet of Things (IoT) traffic or non-IoT traffic. A global machine learning model is generated, using the machine learning parameters, to classify network traffic processed by edge devices as IoT traffic or non-IoT traffic.

Managing internet of things network traffic using federated machine learning

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning clustering models to determine conditions a satellite communication system. In some implementations, feature vectors for a time period are obtained. Each feature vector includes feature values that represent properties of a satellite communication system at a respective time during the time period. Each feature vector is provided as input to a machine learning model that assigns the feature vector to a based on the properties of the satellite communication system represented by the feature vector. Each cluster corresponds to a respective potential operating condition of the satellite communication system. Data is generated that indicates a likelihood that each potential operating condition is the actual operating condition based on a quantity of the feature vectors that have been assigned to the cluster corresponding to the potential operating condition during the time period.

Machine learning clustering models for determining the condition of a communication system

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning models to detect problems in a satellite communication system. In some implementations, one or more feature vectors that respectively correspond to different times are obtained. The feature vector(s) are provided as input to one or more machine learning models trained to receive at least one feature vector that includes feature values representing properties of the satellite communication system and output an indication of potential causes of a condition of the satellite communication system based on the properties of the satellite communication system. A particular cause that is indicated as being a most likely cause of the condition of the satellite communication system is determined based on one or more machine learning model outputs received from each of the one or more machine learning models.

Machine learning models for detecting the causes of conditions of a satellite communication system

Systems and method are disclosed and among these is a method for fingerprint based detection of Internet of Things (IoT) devices and classification of IoT device type, and corresponding adaptive allocation of link resources, with monitoring of traffic for flow data, detecting IoT devices and classifying the IoT device types, via machine learning classifiers, real time assigning IoT device type based quality of service (QoS) for IoT device traffic, and corresponding IoT device type based, real time allocating of resources to the link. Optionally, machine classifiers can be centrally instantiated, distributed to what can be large populations of user IoT Internet access terminals, and retrained by same, centrally merged or combined, and then redistributed.

System and method of traffic-based classification of IoT devices and dynamic allocation of link resources to IoT devices

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for machine learning models for adjusting communication parameters. In some implementations, data for each terminal in a set of multiple satellite terminals is obtained. A machine learning model is trained based on the obtained data. The model can be trained to receive an indication of a geographic location and predict a satellite beam capable of providing at least a minimum level of efficiency for communication at the geographic location. After training the machine learning model, an indication of a predicted satellite beam for a particular location is generated for a particular geographic location. A determination is then made whether to change the current satellite beam for a terminal at the particular geographic location based on the predicted satellite beam.

A method of and system for converting domain names to a vector space embedding may include receiving data relating to internet traffic over a network, organizing the data into one or more documents that make up a training dataset, each of the one or more documents including one or more Domain Name Server (DNS) queries, providing the training dataset to a deep neural network to generate at least one vector space embedding for one or more domain names, and providing the vector space embedding as an output.

Intelligent conversion of internet domain names to vector embeddings

Managing Internet of Things network traffic using federated machine learning

Methods and systems for spoken language interface for network management are disclosed. In some implementations, data indicating a transcription of a spoken request from a user of a voice-response interface is received. Status information for a communication system is received. The request is interpreted based on the transcription and the status information for the communication system. A response to the request is generated based on the status information for the communication system, and data for a synthesized speech utterance of the response is provided in response to the spoken request.

Growing community of inventors

Germantown, MD, United States of America

Amit Arora