Abstract: Techniques for a machine learning event-driven radio resource management (ED-RRM) module which provides analysis of interference events in a network system are described. The network system reacts to the detection of interference in a network system and uses multiple input parameters to determine a type of device creating the interference, a predicted duration of the interference, and an ED-RRM decision on whether to activate the radio resource management (RRM) processes to alter the network transmission or block the RRM processes to conserve system resources for the network system.

Abstract: In one embodiment, a device in a network monitors a plurality of traffic flows in the network. The device extracts a plurality of features from the monitored plurality of traffic flows. The device generates a context model by using deep learning and reinforcement learning on the plurality of features extracted from the monitored traffic flows. The device applies the context model to a particular traffic flow associated with a client, to determine a context for the particular traffic flow. The device personalizes data sent to the client from a remote source based on the determined context.

Abstract: In one embodiment, a method is performed at a node in a multi-site enterprise fabric. The method includes obtaining map entries from a fabric control plane of the multi-site enterprise fabric, where the map entries are associated with identifiers of endpoints in external networks, site and virtual network identifiers of sites in the multi-site enterprise fabric, location identifiers of border nodes, and characteristics of the border nodes. The method further includes receiving a request from a source to connect to an external endpoint. After deriving an external endpoint identifier and source parameters, the method additionally includes establishing at least one connection between the source and the external endpoint via border node(s) that are selected from the map entries based at least in part on the source parameters, the external endpoint identifier, and characteristics of the border node(s) with their site and virtual network identifier(s) along the at least one connection.

Abstract: A method is provided in one example embodiment and may include receiving load information for a plurality of cells of a Radio Access Network (RAN); determining, for each of a plurality of user equipment (UE) in each cell, identification information for each UE and an Access Point Name (APN) to which each UE is connected; identifying, from a plurality of policy servers, each policy server that serves each APN to which each UE in each cell of the plurality of cells is connected; and sending, to each of a particular policy server, congestion information comprising: an identity for each cell having UE that are connected to each APN served by the particular policy server; the corresponding congestion level for each of the cells; and a per-cell UE list identifying each of a plurality of UE connected to each of APNs served by the particular policy server.

Abstract: In various embodiments, a device classification service forms a device cluster by applying clustering to attributes of endpoint devices observed in one or more networks. The device classification service applies an initial device classification rule to the endpoint devices in the device cluster, based on one or more of the endpoint devices in the device cluster matching the initial device classification rule. The device classification service computes metrics for the initial device classification rule that quantify how well the attributes of the endpoint devices in the device cluster match the initial device classification rule. The device classification service decides, based on the metrics, whether to associate the initial device classification rule with the device cluster or generate a new device classification rule based on the device cluster.

Abstract: Embodiments herein describe a fiber array unit (FAU) configured to optically couple a photonic chip with a plurality of optical fibers. Epoxy can be used to bond the FAU to the photonic chip. However, curing the epoxy between the FAU and the photonic chip is difficult. As such, the FAU can include one or more optical windows etched into or completely through a non-transparent layer that overlap the epoxy disposed on the photonic chip. UV radiation can be emitted through the optical windows to cure the underlying epoxy. In one example, the windows can also be used for dispensing epoxy. In addition to the optical windows, the FAU can include alignment protrusions (e.g., frustums) which mate or interlock with respective alignment receivers in the photonic chip. Doing so may facilitate passive alignment of the optical fibers in the FAU to an optical interface in the photonic chip.

Abstract: A method is provided for handling a voice call in a heterogeneous network environment by a wireless device. The method includes sending a registration request to a network node in a Next Generation (5G) network. The wireless device has an existing voice call on a different network in the heterogeneous network environment. The method further includes receiving a registration acceptance from the network node in the 5G network. The registration acceptance indicates that IMS voice services are supported, but existing voice calls are not supported. The method further includes determining to stop an attempt to move the existing voice call to the 5G network.

Abstract: In various embodiments, a collaboration endpoint transmits an ultrasonic signal into an area. The collaboration endpoint receives a reflected signal that comprises the ultrasonic signal reflected off an object located in the area. The collaboration endpoint detects, based on the reflected signal, the object as being a potential user. The collaboration endpoint determines, based on the reflected signal, a distance from the collaboration endpoint to the potential user. The collaboration endpoint initiates, based on the distance from the collaboration endpoint to the potential user, a wake-up sequence of the collaboration endpoint to exit a standby mode.

Abstract: In one embodiment, a wireless access point is disclosed comprising a housing that defines a compartment and a plurality of apertures configured to receive a plurality of fasteners; a gasket located along a perimeter of the compartment; an access cover for the compartment that defines a plurality of corresponding apertures (that align substantially with the plurality of apertures of the housing); and a hinge coupled to the housing and to the access cover. The hinge includes a first arm affixed to an interior portion of the compartment and extended substantially along a first axis; a second arm connected to the first arm at a first pivot point; a third arm connected to the second arm at a second pivot point; and a fourth arm affixed to an interior portion of the access cover and connected to the third arm at a third pivot point.

Abstract: Presented herein are systems, and methods thereof, that is configured to enter a maintenance mode to isolate itself from its neighbor and to gracefully cause neighbor devices to isolate themselves from the system, as to cause minimal or “zero” service disruption with its neighbors. The system broadcasts a maintenance-related message, via a standard transport layer, over routing protocols, to counter parts protocols at the neighbor device and waits for an acknowledgement message from the neighbor network devices. The broadcast and acknowledgement, through standard transport layer messaging, ensures that traffic generated by such protocols at the neighbor devices, regardless of manufacturer, are redirected before the system fully enters into the maintenance mode.

Abstract: Techniques for deploying, monitoring, and modifying network topologies operating across multi-domain environments using formal models and weighting factors assigned to computing elements in the network topologies. The weighting factors restrict or allow the movement of various computing elements and/or element groupings to prevent undesirable disruptions or outages in the network topologies. Generally, the weighting factors may be determined based on an amount of disruption experienced in the network topologies if the corresponding computing element or grouping was migrated. As the amount of disruption caused by modifying a particular computing element increases, the weighting factor represents a greater measure of resistivity for migrating the computing element. In this way, topology deployment systems may allow, or disallow, the modification of particular computing elements based on weighting factors.

Abstract: Systems and methods herein can convert downstream group addressed packets to unicast packets and send them to Workgroup Bridges (WGBs) by Downlink (DL) Multiple-User (MU) Orthogonal Frequency Division Multiple Access (OFDMA) (DL-MU-OFDMA). A Wireless Controller (WLC)/Access Point (AP) can extend current Inter-Access Point Protocol (IAPP) messages for broadcast and deploy Internet Group Management Protocol (IGMP) processing for multicast messages. The APs can maintain WGB entries for each group address. When there is a downstream broadcast packet received at the AP, the AP can search the entries in the domain and can build a 4-address unicast packet for each WGB, then transmit those converted packets in parallel by DL-OFDMA. After receiving those converted packets over the air, the WGB simply rebuilds 802.3 packets and forwards the 802.3 packets to the corresponding VLAN domain.

Abstract: Aspects herein generally relate to a system and/or a method for enforcing synchronization of WiFi users interacting with a common hierarchical multi-element VR/AR scene. The aspects can use Orthogonal Frequency Division Multiple Access (OFDMA) and trigger frames to synchronize parallel updates to different scene elements. Deep Packet Inspection (DPI) can be used to analyze standard VR/AR streaming formats to identify those VR scene elements that are to be synchronized. The result is a more immersive AR/VR experience for the users, who receive the same scene elements at the same time.

Abstract: Access Point (AP) placement using Fine Time Measurement (FTM) may be provided. First, a plurality of Time-of-Flight (ToF) values between a first service end point and a second service end point may be determined. Each one of the plurality of ToF values may be derived from packets transmitted via different beamforming vector patterns at the first service end point and the second service end point. Then a minimum ToF value of the plurality of ToF values may be determined. Next, a distance between the first service end point and the second service end point may be determined based on the minimum ToF value.

Abstract: Inter-protocol interference reduction for hidden nodes may be provided. A first service end point may determine that an inter-protocol interference is present on a channel. Next, an initial packet failure count value on the channel may be determined. A transmit (Tx) power for selected packets may then be increased until a subsequent packet failure count value on the channel is less than the initial packet failure count value.

Abstract: In one embodiment, a device obtains one or more fabric port (F-port) counters and one or more extender port (E-port) counters in a storage area network (SAN). The device inputs the obtained F-port and E-port counters to a machine learning-based prediction model. The device uses the prediction model to predict a slow drain condition in the SAN, based on the counters input to the model. The device initiates a corrective measure in the SAN, based on the predicted slow drain condition.

Abstract: Methods and network devices are disclosed for multicast traffic steering in a communications network. In one embodiment, a method includes receiving, at a node in a network, a multicast message comprising an incoming message bit array and a tree identifier value. The embodiment further includes selecting a bit indexed forwarding table stored at the node and corresponding to the tree identifier value, accessing within the selected forwarding table an entry corresponding to an intended destination node for the message, and forwarding, to a neighboring node identified in the accessed entry, a copy of the message comprising a forwarded message bit array in place of the incoming message bit array. An embodiment of a network device includes one or more network interfaces and a processor adapted to perform steps of the method.

Abstract: In one embodiment, an operating system on a computer device interfaces with a graph database that has data nodes interconnected by relationship edges. The operating system generates database instructions that specify a database operation for a target node in the graph database and a node traversal list through the graph database to reach the target node. By then transmitting the database instruction to the graph database, the graph database (e.g., a database management operating system) traverses the specified node traversal list through the graph database to the target node, and performs the database operation on the target node.

Abstract: In one embodiment, a process on a computer for dynamic application component auditing is disclosed, the process includes automatically identifying, by an agent, all application components in an application. The process includes determining, by the agent, manifest information for the identified application components. The process includes accessing, by the agent, an alias file to convert the determined manifest information to align with corresponding information in a vulnerability database. The process includes using a Web service to query the vulnerability database to search for a match with the converted manifest information. The process includes responsive to the query, creating an audit report of the application components.

Abstract: The embodiments herein use a factorization based technique for determining filter coefficients for a subset of the subcarriers in a wireless frequency band. Once the filter coefficients for the subset of the subcarriers are calculated, the network device uses these filter coefficients to identify the filter coefficients in a neighboring subcarrier. To do so, the network device uses pseudo-inverse iteration to convert the already calculated filter coefficients into filter coefficients for a neighboring subcarrier. The network device can repeat this process for the next set of neighboring subcarriers until all the filter coefficients have been calculated.