Abstract: A network device organizes packets into various queues, in which the packets await processing. Queue management logic tracks how long certain packet(s), such as a designated marker packet, remain in a queue. Based thereon, the logic produces a measure of delay for the queue, referred to herein as the “queue delay.” Based on a comparison of the current queue delay to one or more thresholds, various associated delay-based actions may be performed, such as tagging and/or dropping packets departing from the queue, or preventing addition enqueues to the queue. In an embodiment, a queue may be expired based on the queue delay, and all packets dropped. In other embodiments, when a packet is dropped prior to enqueue into an assigned queue, copies of some or all of the packets already within the queue at the time the packet was dropped may be forwarded to a visibility component for analysis.

Abstract: A switch architecture includes an ingress module, ingress fabric interface module, and a switch fabric. The switch fabric communicates with egress fabric interface modules and egress modules. The architecture implements multiple layers of congestion management. The congestion management may include fast acting link level flow control and more slowly acting end-to-end flow control. The switch architecture simultaneously provides high scalability, with low latency and low frame loss.

Abstract: This disclosure relates generally to health monitoring of systems, and more particularly to monitor health of a system for fault signature identification. The system estimates Health Index (HI) of the system as time series data. By analyzing data corresponding to the estimated HI, the system identifies one or more time windows in which majority of the estimated HI values are low as a low HI window, and one or more time windows in which majority of the estimated HI values are high as a high HI window. Upon identifying a low HI window, which indicates an abnormal behavior of the system being monitored, based on a local Bayesian Network generated for the system being monitored, an Explainability Index (EI) for each sensor is generated, wherein the EI quantifies contribution of the sensor to the low HI. Further, associated component(s) is identified as contributing to abnormal/faulty behavior of the system.

Abstract: A network device organizes packets into various queues, in which the packets await processing. Queue management logic tracks how long certain packet(s), such as a designated marker packet, remain in a queue. Based thereon, the logic produces a measure of delay for the queue, referred to herein as the “queue delay.” Based on a comparison of the current queue delay to one or more thresholds, various associated delay-based actions may be performed, such as tagging and/or dropping packets departing from the queue, or preventing addition enqueues to the queue. In an embodiment, a queue may be expired based on the queue delay, and all packets dropped. In other embodiments, when a packet is dropped prior to enqueue into an assigned queue, copies of some or all of the packets already within the queue at the time the packet was dropped may be forwarded to a visibility component for analysis.

Abstract: Users have to assign labels to a ticket to route to right domain expert for resolving issue(s). In practice, labels are large and organized in form of a tree. Lack in clarity in problem description has resulted in inconsistent and incorrect labeling of data, making it hard for one to learn/interpret. Embodiments of the present disclosure provide systems and methods that identify relevant queries to obtain user response, for identification of right category and ticket logging there. This is achieved by implementing attention based sequence to sequence (seq2seq) hierarchical classification model to assign the hierarchical categories to tickets, followed by a slot filling model to enable identifying/deciding right set of queries, if the top-k model predictions are not consistent. Further, training data for slot filling model is automatically generated based on attention weight in the hierarchical classification model.

Abstract: Advanced analytics refers to theories, technologies, tools, and processes that enable an in-depth understanding and discovery of actionable insights in big data, wherein conventional systems and methods may be prone to errors leading to inaccuracies.

Abstract: A method of and system for correlating data from among a disparate group of data sources and providing the correlated data to data consumers via API's and direct transmission of the data are disclosed. Once the validity of the data is verified, the data is translated from a format specific to the data source into a format that is usable by various other data repositories. Thereafter, the data may be provided to data consumers.

Abstract: Certain hash-based operations in network devices and other devices, such as mapping and/or lookup operations, are improved by manipulating a hash key prior to executing a hash function on the hash key and/or by manipulating outputs of a hash function. A device may be configured to manipulate hash keys and/or outputs using manipulation logic based on one or more predefined manipulation values. A similar hash-based operation may be performed by multiple devices within a network of computing devices. Different devices may utilize different predefined manipulation values for their respective implementations of the manipulation logic. For instance, each device may assign itself a random mask value for key transformation logic as part of an initialization process when the device powers up and/or each time the device reboots. In an embodiment, described techniques may increase the entropy of hashing function outputs in certain contexts, thereby increasing the effectiveness of certain hashing functions.

Abstract: The present subject matter discloses system and method for executing prescriptive analytics. Simulation is performed from an input data (xinput) and simulation parameters (?) to generate simulating data (D). Further, forecast data may be predicted by processing the simulating data (D) using predictive model (M). Further, prescriptive value (x?) may be determined based on the forecast data by using optimization model. The prescriptive value (x?) may be determined such that an objective function associated with the optimization model is optimized, whereby the optimization of the objective function indicates business objective being achieved. Further, the steps of simulating, predicting and determining may be iteratively performed until the objective function is not further optimized, satisfying predefined condition.

Abstract: Techniques for improved handling of queues of data units are described, such as queues of buffered data units of differing types and/or sources within a switch or other network device. When the size of a queue surpasses the state entry threshold for a certain state, the queue is said to be in the certain state. While in the certain state, data units assigned to the queue may be handled differently in some respect, such as being marked or being dropped without further processing. The queue remains in this certain state until its size falls below the state release threshold for the state. The state release threshold is adjusted over time in, for example, a random or pseudo-random manner. Among other aspects, in some embodiments, this adjustment of the state release threshold addresses fairness issues that may arise with respect to the treatment of different types or sources of data units.

Abstract: A method and system for interpreting a dataset is described herein. The method include computing a rule set pertaining to the dataset, followed by generating a rule cover pertinent to a subset of the rule set. Further, a plurality of distances between the plurality of rule pairs in the rule cover is calculated and a distance matrix based on the calculated plurality of distances is generated. Consequently, the overlapping rules within the rule cover are clustered using the distance matrix and a representative rule from each cluster is selected. Further, at least one exception for each representative rule is determined and the dataset is interpreted using the representative rules and the at least one exception. Thereby, the method provides succinct results in terms of rules and exceptions along with multiple interpretations of the same set of transactions from the dataset, thereby providing a holistic view about the dataset.

Abstract: The efficiency of the network device is improved by sharing a packet processor across two or more control paths. Data unit sources send the first portion of each data unit that passes through the sources to the shared packet processor via their respective control paths. The packet processor generates control information for each of the data units, and sends the control information to a merger component that corresponds to the source of the data unit. The merger component merges the control information with a payload portion of the data unit that the data unit source sent along a separate data path. To better facilitate the sharing of the packet processor, the control paths may converge at an adaptive distributor, which uses a policy-based mechanism to select which data unit portion to forward to the packet processor in a given time slot. The policy may change based on various demand measures.

Abstract: Approaches, techniques, and mechanisms are disclosed for assigning paths to network packets. The path assignment techniques utilize path state information and/or other criteria to determine whether to route a packet along a primary candidate path selected for the packet, or one or more alternative candidate paths selected for the packet. According to an embodiment, network traffic is at least partially balanced by redistributing only a portion of the traffic that would have been assigned to a given primary path. Move-eligibility criteria are applied to traffic to determine whether a given packet is eligible for reassignment from a primary path to an alternative path. The move-eligibility criteria determine which portion of the network traffic to move and which portion to allow to proceed as normal. In an embodiment, the criteria and functions used to determine whether a packet is redistributable are adjusted over time based on path state information.

Abstract: Approaches, techniques, and mechanisms are disclosed for improving the efficiency with which data units are handled within a device, such as a networking device. Received data units, or portions thereof, are temporarily stored within one or more memories of a merging component, while the merging component waits to receive control information for the data units. Once received, the merging component merges the control information with the associated data units. The merging component dispatches the merged data units, or portions thereof, to an interconnect component, which forwards the merged data units to destinations indicated by the control information. The device is configured to intelligently schedule the dispatching of merged data units to the interconnect component. To this end, the device includes a scheduler configured to select which merged data units to dispatch at which times based on a variety of factors described herein.

Abstract: Nodes within a network are configured to adapt to changing path states, due to congestion, node failures, and/or other factors. A node may selectively convey path information and/or other state information to another node by annotating the information into packets it receives from the other node. A node may selectively reflect these annotated packets back to the other node, or other nodes that subsequently receive these annotated packets may reflect them. A weighted cost multipathing selection technique is improved by dynamically adjusting weights of paths in response to feedback indicating the current state of the network topology, such as collected through these reflected packets. In an embodiment, certain packets that would have been dropped may instead be transformed into “special visibility” packets that may be stored and/or sent for analysis. In an embodiment, insight into the performance of a network device is enhanced through the use of programmable visibility engines.

Abstract: Methods and apparatus for transmit buffers for network devices. One apparatus includes a packing unit, a buffer manager and a plurality of aggregated port buffers, each coupled to receive output from the packing unit. The packing unit is configured to receive packet data as input segments of a first size; generate storage units of a second size; and write each storage unit to a particular aggregated port buffer identified by the buffer manager. The buffer manager is configured to: select a particular aggregated port buffer for each storage unit, and send information to the buffer manager about the selected particular aggregated port buffer; monitor availability of storage space in the aggregated port buffers; control reception of input segments based on storage space availability; and manage transmission of the storage units from the aggregated port buffers to one or more external destinations as output segments of a third size.

Abstract: Conversational systems are required to be capable of handling more sophisticated interactions than providing factual answers only. Such interactions are handled by resolving abstract anaphoric references in conversational systems which includes antecedent fact references and posterior fact references. The present disclosure resolves abstract anaphoric references in conversational systems using hierarchically stacked neural networks. In the present disclosure, a deep hierarchical maxpool network based model is used to obtain a representation of each utterance received from users and a representation of one or more generated sequences of utterances. The obtained representations are further used to identify contextual dependencies with in the one or more generated sequences which helps in resolving abstract anaphoric references in conversational systems.

Abstract: Efficient garbage collection techniques for network packets and other units of data are described. Constituent portions of a data unit are stored in buffer entries spread out across multiple distinct banks. Linking data is generated and stored on a per-bank basis. The linking data defines, for each bank in which data for the data unit is stored, a chain of all entries in that bank that store data for the data unit. When the data unit is dropped or otherwise disposed of, a chain's head entry address may be placed in a garbage collection list for the corresponding bank. A garbage collector uses the linking data to gradually follow the chain of entries for the given bank, and frees each entry in the chain along the way. Optionally, certain addresses in the chain, including each chain's tail address, are immediately freed for the corresponding bank, without waiting to follow the chain.

Abstract: Prefix entries are efficiently stored at a networking device for performance of a longest prefix match against the stored entries. A prefix entry generally refers to a data entry which maps a particular prefix to one or more actions to be performed by a networking device with respect to network packets or other data structures associated with a network packet that matches the particular prefix. In the context of a router networking device handling a data packet, the one or more actions may include, for example, forwarding a received network packet to a particular “next hop” networking device in order to progress the network packet towards its final destination, applying firewall rule(s), manipulating the packet, and so forth. To reduce a total amount of space occupied by a prefix tree in storage, each of the nodes of a prefix tree may be configured to store only an incremental portion of a prefix relative to its parent node.

Abstract: Described techniques enable resource accounting and tracking in high access rate systems using low cost memories. A first set of counters is maintained in relatively lower cost memory. The first counters generally indicate the amount of resources used for each object in a set of objects, but on a potentially delayed basis. A second set of counters of smaller size is stored in a relatively higher cost memory that supports high arrival and departure rates for accurate accounting. Each second counter indicates the amount of resources assigned (or unassigned) to an object since the object's first counter was last updated, and is incremented or decremented whenever this amount changes. A background process is configured to update individual first counters from the corresponding second counters on a recurring basis. The exact times at which a given first counter is updated may vary in accordance with a variety of approaches.