Abstract: A network infrastructure management console configures one or more network switch stacks each comprising a plurality of switches. A monitoring component monitors a current conductor switch of the stack. A user interface (UI) backend component comprises a cache memory and receives a user request to configure the stack. The UI backend component receives from the monitoring component notification of the current conductor and stores in a cache memory segment associated with the current conductor the requested configuration changes. If the current conductor switch of the stack has changed due to a failover event, the configuration changes stored in the cache memory segment associated with the previous current conductor are written to a cache memory segment associated with the new current conductor. A configuration push component receives the configuration changes and transmits the configuration changes to the network switch stack.

Abstract: Example implementations relate to edge acceleration by offloading network dependent applications to a hardware accelerator. According to one embodiment, queries are received at a cluster of a container orchestration platform. The cluster includes a host system and a hardware accelerator, each serving as individual worker machines of the cluster. The cluster further includes multiple worker nodes and a master node executing on the host system or the hardware accelerator. A first worker node executes on the hardware accelerator and runs a first instance of an application. A distribution of the queries is determined among the worker machines based on a queuing model that takes into consideration the respective compute capacities of the worker machines. Responsive to receipt of the queries by the host system or the hardware accelerator, the queries are directed to the master node or one of the worker nodes in accordance with the distribution.

Abstract: Systems and methods are provided for measuring available bandwidth available in a black box network by determining a probing rate of packet transmissions between a sender and receiver. The optimal probing rate and bandwidth estimate may be determined. Additional actions may be performed, like automatically rerouting packets and/or load balancing network traffic after the probing rate is determined.

Abstract: Examples disclosed herein relate to a method for defining an ingress access policy at an ingress network device based on instructions from an egress network device. The egress network device receives data packets directed to a first entity from a second entity connected to an ingress network device. Each data packet transmitted includes a source role tag corresponding to the second entity. At the egress network device, the data packets may be dropped based on the enforcement of an egress access policy. When the number of data packets that are being dropped increases beyond a pre-defined threshold, the egress network device transmits a command to the ingress network device instructing the ingress network device to create a restriction on the transmission of subsequent data packets. The command is transmitted in a Border Gateway Protocol (BGP) Flow Specification (FlowSpec) route.

Abstract: Decentralized machine learning to build models is performed at nodes where local training datasets are generated. A blockchain platform may be used to coordinate decentralized machine learning (ML) over a series of iterations. For each iteration, a distributed ledger may be used to coordinate the nodes communicating via a blockchain network. A node can include self-healing features to recover from a fault condition within the blockchain network in manner that does not negatively impact the overall learning ability of the decentralized ML system. During self-healing, the node can determine that a local ML state is not consistent with the global ML state and trigger a corrective action to recover the local ML state. Thereafter, the node can generate a blockchain transaction indicating that it is in-sync with the most recent iteration of training, and informing other nodes to reintegrate the node into ML.

Abstract: A method of certifying a state of a platform includes receiving one or more software elements of a software stack of the platform by an authentication module and performing a hash algorithm on the software stack to generate one or more hash values. The software stack uniquely determines a software state of the platform. The method includes generating creation data, a creation hash, and a creation ticket, corresponding to the hash values and sending the creation ticket to the platform. The method also includes receiving the creation ticket by the authentication module and certifying the creation data and the creation hash based on the creation ticket. The method further includes generating a certified structure based on the creation data and performing the hash algorithm on the certified structure to generate a hash of the certified structure. The certified structure uniquely determines the software state of the platform.

Abstract: Systems and methods are provided for leveraging blockchain technology in a swarm learning context, where nodes of a blockchain network that contribute data to training a machine learning model using their own local data can be rewarded. In order to conduct such data monetization in a fair and accurate manner, the systems and methods rely on various phases in which Merkle trees are used and corresponding Merkle roots are registered in a blockchain ledger. Moreover, any claims for a reward are challenged by peer nodes before the reward is distributed.

Abstract: A system for facilitating enhanced virtual channel switching in a node of a distributed computing environment is provided. During operation, the system can allocate flow control credits for a first virtual channel to an upstream node in the distributed computing environment. The system can receive, via a message path comprising the upstream node, a message on the first virtual channel based on the allocated flow control credits. The system can then store the message in a queue associated with an input port and determine whether the message is a candidate for changing the first virtual channel at the node based on a mapping rule associated with the input port. If the message is a candidate, the system can associate the message with a second virtual channel indicated in the mapping rule in the queue. Subsequently, the system can send the message from the queue on the second virtual channel.

Abstract: Example implementations relate to changing a status of a device responsive to detecting an anomaly. A traffic pattern of a device may be monitored across a network. It may be determined that the monitored traffic pattern deviates from an expected traffic pattern of the group of devices by a threshold. Responsive to determining that the devices deviates from the expected traffic pattern, packet data transmitted by the device may be inspected. It may be determined that the inspected packet data transmitted by the device is anomalous. The status of the device may be changed responsive to determining that the packet data transmitted by the device is anomalous.

Abstract: Examples of techniques for dynamically controlling data bursts are described. In an example, an access point (AP) monitors a link quality between the AP and a client device associated with the AP. The AP determines a channel occupancy of a channel in which the AP is configured to operate. In response to determining that the channel occupancy is less than a channel busy threshold, the AP modifies a burst duration for traffic flow between the AP and the client device based on the link quality. The AP communicates with the client device using the channel for the modified burst duration.

Abstract: Examples described herein provide multi-band directional scanning. Examples may include receiving, by a first radio of a first network device operating at a first frequency band below the millimeter-wave (mmWave), a probe request from a second network device indicating a protocol and a particular sector receiving direction of the second network device, and in response to the protocol indicated by the probe request, transmitting, by a second radio of the first network device operating at a second frequency band within the mmWave, a probe response in each of one or more sector transmitting directions, wherein the second network device receives one or more probe responses in the particular sector receiving direction.

Abstract: In some examples, a system receives a first collection of tokens relating to characteristics of workloads for a computing system. The system encodes the first collection of tokens, the encoding including computing weights representing relationships among tokens of the first collection of tokens, and generating a representation of the first collection of tokens based on the weights. The system determines, based on the representation, a correlation between the first collection of tokens and a second collection of tokens relating to elapsed times in executing the workloads.

Abstract: An optical connector assembly (OCA) includes a connector housing to maintain alignment between optical components housed within the OCA and photoelectric converters on an optoelectronic substrate (OES) assembly. The optical components include a ferrule and an optical cable. The ferrule is optically coupled to the optical cable. The OCA includes a ferrule holder to hold the ferrule within the OCA, and a spring located between the connector housing and the ferrule holder. The spring is to apply a separating force between the ferrule holder and the connector housing. The OCA includes a gasket coupled to the connector housing. The coupling of the connector housing to a socket compresses the gasket to provide a seal between the connector housing and the socket.

Abstract: A system and a method of classifying data and providing an accuracy of classification are described. The method includes determining values of statistical features associated with data packets present in a data stream. The values of statistical features are provided to a data model for producing a classification output including the data packets classified into one or more categories. While producing the classification output, the data model extracts heuristics for each of the values of statistical features, compares the heuristics with one or more conditional checks defined at each node within the data model, and determines a cumulative score based on results of the comparing. The cumulative score is determined by aggregating a score assigned to successful clearance of each conditional check. The cumulative score indicates an accuracy of the classification output.

Abstract: Examples relate to adjusting a switching frequency of a voltage regulator to operate the voltage regulator at a predetermined power efficiency. Examples described herein include receiving load information corresponding to a component that receives regulated power from the voltage regulator, determining, from a repository, a predetermined value of the switching frequency of the voltage regulator based on the load information to attain the predetermined power efficiency of the voltage regulator and adjusting the switching frequency of the voltage regulator to the predetermined value of the switching frequency to operate the voltage regulator at the predetermined power efficiency.

Abstract: Systems and methods are provided for employing analog content addressable memory (aCAMs) to achieve low latency complex distribution sampling. For example, an aCAM core circuit can include an aCAM array. Amplitudes of a probability distribution function are mapped to a width of one or more aCAM cells in each row of the aCAM array. The aCAM core circuit can also include a resistive random access memory (RRAM) storing lookup information, such as information used for processing a model. By randomly selecting columns to search of the aCAM array, the mapped probability distribution function is sampled in a manner that has low latency. The aCAM core circuit can accelerate the sampling step in methods relying on sampling from arbitrary probability distributions, such as particle filter techniques. A hardware architecture for an aCAM Particle Filter that utilizes the aCAM core circuit as a central structure is also described.

Abstract: Systems and methods for improving the performance and stability of bonding radios are provided. One method includes receiving a packet from a client device. Next, the method includes determining whether the received packet is an expected next packet and transmitting the received packet to a next destination if the received packet is the expected next packet. In an event the received packet is not the expected next packet, transmitting the received packet to a queue, setting a timer to wait for the expected next packet, and transmitting a message to the sender of the received packet requesting that the expected next packet be sent.

Abstract: Examples of renewal of security certificates of supplicant devices are described. In an example, a request to authenticate a supplicant device based on a security certificate is received by an authenticator device and from a supplicant device. The request comprises information relating to the security certificate which is expired. A login history of the supplicant device and presence of a valid account associated with the supplicant device in a directory database is determined. An authentication successful message is sent to the supplicant device based on the login history and presence of the valid account in the directory database. The supplicant device is redirected to a captive web portal for authentication of the supplicant device based on the login credential. In response to a successful authentication of the supplicant device in the captive web portal, a renewed security certificate for the supplicant device is provided.

Abstract: Examples include service authentication for a principal. A request to access a first service of a plurality of services of a network may be received from a principal by an identity intermediary. An identifier of the first service may be stored at the identity intermediary, and an unsigned credential of the principal and a principal identifier may be transferred from the identity intermediary to a credential provider. The principal identifier and the credential signed by the credential provider may be received, and the signed credential may be transmitted to the first service for authentication.

Abstract: A network interface controller (NIC) capable of performing message passing interface (MPI) list matching is provided. The NIC can include a host interface, a network interface, and a hardware list-processing engine (LPE). The host interface can couple the NIC to a host device. The network interface can couple the NIC to a network. During operation, the LPE can receive a match request and perform MPI list matching based on the received match request.