A system for optimizing network traffic is described. The system includes a quality of service (QoS) engine configured to acquire information regarding a plurality of data packets comprising a plurality of data packet flows operating over a plurality of links. The QoS engine can be further configured to determine a flow priority to the plurality of data packets flows, and to determine TCP characteristics for the plurality of data packet flows. The system further includes a TCP controller configured to acquire the flow priority to the plurality of data packets from the QoS engine. The TCP controller can be configured to obtain queue information associated with the plurality of data packets, and adjust a receive window size based on the flow priority and the queue information.

Technologies for providing shared memory for accelerator sleds includes an accelerator sled to receive, with a memory controller, a memory access request from an accelerator device to access a region of memory. The request is to identify the region of memory with a logical address. Additionally, the accelerator sled is to determine from a map of logical addresses and associated physical address, the physical address associated with the region of memory. In addition, the accelerator sled is to route the memory access request to a memory device associated with the determined physical address.

Technologies for providing shared memory for accelerator sleds includes an accelerator sled to receive, with a memory controller, a memory access request from an accelerator device to access a region of memory. The request is to identify the region of memory with a logical address. Additionally, the accelerator sled is to determine from a map of logical addresses and associated physical address, the physical address associated with the region of memory. In addition, the accelerator sled is to route the memory access request to a memory device associated with the determined physical address.

Disclosed herein are systems and methods for multi-level classification of data traffic flows based on information in a first packet for a data traffic flow. In exemplary embodiments of the present disclosure, a key can be generated from intercepted DNS data to track data traffic flows by application names and destination IP addresses. Based on these keys, patterns can be discerned to infer data traffic information based on only the information in a first packet, such as destination IP address. The determined patterns can be used to predict classifications of future traffic flows with similar key information. In this way, data traffic flows can be classified and steered in a network based on limited information available in a first packet.

Disclosed herein are systems and methods for multi-level classification of data traffic flows based on information in a first packet for a data traffic flow. In exemplary embodiments of the present disclosure, a key can be generated from intercepted DNS data to track data traffic flows by application names and destination IP addresses. Based on these keys, patterns can be discerned to infer data traffic information based on only the information in a first packet, such as destination IP address. The determined patterns can be used to predict classifications of future traffic flows with similar key information. In this way, data traffic flows can be classified and steered in a network based on limited information available in a first packet.

A trust reality service brokering apparatus located on an edge cloud receives a context rule, analyzes event data of at least one physical entity connected to the edge cloud based on the context rule, and transmits an action command to a physical entity or virtual entity corresponding to the event when it is determined that an event has occurred according to an analysis result.

A trust reality service brokering apparatus located on an edge cloud receives a context rule, analyzes event data of at least one physical entity connected to the edge cloud based on the context rule, and transmits an action command to a physical entity or virtual entity corresponding to the event when it is determined that an event has occurred according to an analysis result.

In one embodiment, a network flow sampling system includes packet processing circuitry to process data packets of multiple network flows, and an adaptive policer to, for each one network flow of the multiple network flows compute a quantity of flow-specific sampling credits to be assigned to the one network flow responsively to a quantity of the network flows currently being processed by the packet processing circuitry, assign the flow-specific sampling credits to the one network flow, sample at least one of the data packets of the one network flow responsively to availability of the flow-specific sampling credits of the one network flow yielding sampled data, while applying sampling fairness among the network flows, and remove at least one of the flow-specific sampling credits of the one network flow from availability responsively to sampling the at least one data packet of the one network flow.

In one embodiment, a network flow sampling system includes packet processing circuitry to process data packets of multiple network flows, and an adaptive policer to, for each one network flow of the multiple network flows compute a quantity of flow-specific sampling credits to be assigned to the one network flow responsively to a quantity of the network flows currently being processed by the packet processing circuitry, assign the flow-specific sampling credits to the one network flow, sample at least one of the data packets of the one network flow responsively to availability of the flow-specific sampling credits of the one network flow yielding sampled data, while applying sampling fairness among the network flows, and remove at least one of the flow-specific sampling credits of the one network flow from availability responsively to sampling the at least one data packet of the one network flow.

A Wi-Fi APD is configured to tag internet protocol data with a first priority level and a second priority level that is higher than the first priority level. The network controller contains a memory that contains a channel bandwidth threshold value. The network controller contains a processor configured to execute instructions that cause the network controller to: periodically poll the Wi-Fi APD; periodically receive poll responses from the Wi-Fi APD; determine whether channel bandwidth is greater than the stored channel bandwidth threshold value; determine whether the response time of the poll responses is greater than the polling period; and instruct the Wi-Fi APD to tag internet protocol data with the second priority level when at least one of the channel bandwidth is less than the channel bandwidth threshold value and the response time is greater than the period of the first frequency.