Technologies for scheduling time-sensitive cyclical network traffic in real-time include an internet-of-things (IoT) device that includes at least one sensor for collecting sensor data. The IoT device is configured to store the collected sensor data in a data buffer, allocate a packet descriptor for the sensor data, and populate the allocated packet descriptor with a cyclic data port pointer indicative of a location of the data buffer. The IoT device is additionally configured to queue the packet descriptor into a media access control (MAC) unit transmit direct memory access (DMA) of the IoT device, fetch the sensor data, and packetize the fetched data to form a network packet. Further, the IoT device is configured to transmit the network packet to a target computing device based on a launch time, update the launch time, and requeue the packet descriptor into the MAC unit transmit DMA. Other embodiments are described herein.

This application describes a network device, a controller, a queue management method, and a traffic management chip. The method may be applied to a traffic management chip that uses an HQoS technology, and can include receiving a queue management instruction sent by a controller, where the queue management instruction includes an identifier of a first scheduler and an identifier of a first queue, and the first scheduler is one of multiple first-level schedulers. The method may also include controlling, according to the queue management instruction, scheduling of the first queue by the first scheduler, where a queue scheduled by the first scheduler belongs to a queue resource pool of the TM chip, and the queue resource pool includes at least one to-be-allocated queue. In this application, decoupling between queue allocation and the first-level schedulers is implemented, flexibility of queue allocation is improved, and utilization of queue resources is improved.

A resource-access management system detects whether a user is authorized to access resources. The system may include a user device being configured to include a sensor that detects sensor data associated with the user. Further, the system includes a client qualification engine that determines whether or not a client is authorized to access the resources by comparing the sensor data with a plurality of patterns for evaluating whether or not the user is an authorized user. User scores are generated based on the compared sensor data and the plurality of patterns. Further, a composite score corresponding to the user is generated using the sensor data, plurality of patterns, and one or more additional criteria. Whether the user is granted access to the resources, presented with unauthorized user tests, or blocked from access to the resources depends on the composite score and threshold values.

A communication system may be configured to transmit information from one or more information sources to a plurality of users over limited capacity media while enforcing one or more Quality of Service policies, such as maximum information rate (MIR) policies. Methods are presented herein for enforcing maximum information rate on two or more levels in a hierarchal and extendable manner, for at least the purposes of maximizing utilization of available capacity over said media and of fair distributing said capacity between all users. Also presented herein is a method for estimating load over said media.

This application describes a network device, a controller, a queue management method, and a traffic management chip. The method may be applied to a traffic management chip that uses an HQoS technology, and can include receiving a queue management instruction sent by a controller, where the queue management instruction includes an identifier of a first scheduler and an identifier of a first queue, and the first scheduler is one of multiple first-level schedulers. The method may also include controlling, according to the queue management instruction, scheduling of the first queue by the first scheduler, where a queue scheduled by the first scheduler belongs to a queue resource pool of the TM chip, and the queue resource pool includes at least one to-be-allocated queue. In this application, decoupling between queue allocation and the first-level schedulers is implemented, flexibility of queue allocation is improved, and utilization of queue resources is improved.

Embodiments relate to allocating resources of computing devices for providing information service in a network. The computing devices may be hierarchically structured and may include, for instance, cloud servers, telecommunication servers, edge edges, gateways, and client devices. A system environment may include a hierarchical orchestrator coordinating with one or more local orchestrators to allocate service components (for example, a discrete functional software or hardware component) to computing devices. The orchestrators can automatically reallocate resources responsive to detecting update events such as a change in traffic or payload on the network.

Methods, systems, and apparatus for transferring data are described. A list of recipients of the data is obtained and one or more paths to each recipient of the data is determined. An overall transfer cost of each path is computed and one or more transfer paths for each recipient are selected based on a corresponding overall transfer cost. Then a packet of data is transferred to a client device associated with each transfer path.

Described herein include systems, methods, and apparatuses for the scheduling of data over a network (e.g., a wired or wireless network). A scheduler may be configured to receive a portion of packets at a receiving buffer and classify the packets into real time packets or non-real time packets using associated first and second queues. Further, a first re-transmission component may receive the real time packets from the first queue, and a second re-transmission component may receive the non-real time packets from the second queue. The real time packets may be received, by a transmission component, from the first re-transmission component; the transmission component may also receive non-real time packets from the second re-transmission component. The scheduler may then transmit at least one real time packet or non-real time packet to another device over a network using any suitable scheduling algorithm.

Methods, systems, and apparatus for transferring data are described. A list of recipients of the data is obtained and one or more paths to each recipient of the data is determined. An overall transfer cost of each path is computed and one or more transfer paths for each recipient are selected based on a corresponding overall transfer cost. Then a packet of data is transferred to a client device associated with each transfer path.

A traffic scheduling method includes determining, by a first network device, first traffic scheduling information and a transmission path of a first data stream based on a first talker attribute message received from a talker device and a listener attribute message received from a listener device, and then sending, by the first network device, a first traffic scheduling message to a network device on the transmission path. The first traffic scheduling message includes the first traffic scheduling information. The first traffic scheduling information indicates the network device on the transmission path to generate a gate control list. The gate control list indicates the network device on the transmission path to control, based on the gate control list, a state of a port used to transmit the first data stream.