Abstract: Devices, systems, methods, and processes for tackling the problem of sticky clients in wireless networks using machine learning processes are described herein. Thresholds related to data rates and/or Received Signal Strength Indicators (RSSI), for Access Points (APs) in a network are identified. These thresholds are configured to dynamically adjust, either based on the time of day or real-time roaming patterns, with the aim of mitigating sticky clients and enhancing overall network performance. Advanced machine learning techniques such as Graph Neural Networks are implemented within the domain of deep learning to significantly alleviate sticky client concerns and promote seamless connectivity for all users.

Abstract: The present disclosure provides techniques for APs to evaluate status updates received from STAs for adaptive AID management. An AP establishes a wireless communications link with a station, generates a list of N AIDs, each of the N AIDs to be used in a corresponding epoch of N epochs associated with an EDP group, transmits to the station in a protected wireless frame, information indicating the list of N AIDs for the station, receives from the station a response frame to the protected wireless frame, where the response frame includes a status code indicating whether the station successfully stored at least a portion of the list of N AIDs, and maintains the wireless communications link with the station based at least in part on the timing information for randomized MAC address rotation for the EDP group, and including using each AID in the list of N AIDs during corresponding epochs.

Abstract: A system and method for using 802.11v action report messages to enhance roaming. In one embodiment, a method includes transmitting, to a station, a transition management message that identifies a recommended access point for roaming for the station, receiving, from the station, an action report in response to the transition management message, where the action report indicates feedback to the recommended access point identified in the transition management message, and determining a roaming recommendation based on the action report.

Abstract: In one embodiment, a device obtains telemetry data indicative of a plurality of different types of events that occurred in a network. The device computes event counts for each of the plurality of different types of events within each of a sequence of predefined timespans based on the telemetry data and generates timeseries for each of the plurality of different types of events using the event counts. The device provides display data that causes a user interface to display a selected two or more of the timeseries concurrently.

Abstract: The present disclosure provides techniques for device authorization using a per-device identifier. A network device authenticates a client device using simultaneous authentication of equals (SAE) with a shared passphrase. After completing association, the network device sends a first message to the client device, comprising an access point (AP)-generated random value to the client device. The network device receives a second message from the client device, comprising a station (STA)-generated random value and an authorization identifier. The network device decrypts the authorization identifier using a session key. In response to determining that the authorization identifier matches an entry in the authorization database, the network device sends a third message confirming authorization of the client device as a trusted entity. The network device receives a fourth message confirming completion of a security key exchange.

Abstract: In one embodiment, a method can receive transmission metadata associated with a plurality of devices within an Internet of Things (IoT) network. The method can use a transmission sensing component (TSC) to measure transmission energy cost for each of the plurality of devices over a time period using the transmission metadata. The method can use a central compute engine (CCE) and the transmission energy cost for each of the plurality of devices to determine a plurality of transmission features associated with the plurality of devices having a transmission energy cost that is minimized. The method can use a transmission scheduling engine (TSE) and the plurality of transmission features to generate a transmission mode schedule to reduce a transmission energy cost for the plurality of devices within the IoT network. The method can adjust a transmission mode associated with the plurality of devices based on the transmission mode schedule.

Abstract: In one implementation, a device may obtain performance metrics from vantage points distributed across a computing network. The device may map the performance metrics to a corresponding application based on a network address associated with the performance metrics. The device may establish a performance metric baseline for the corresponding application based on the performance metrics that are mapped to the corresponding application. The device may identify an anomaly in a performance metric mapped to the corresponding application based on a comparison to the performance metric baseline.

Abstract: In one implementation, a device obtains traceroute results for a forward path from a first endpoint in a network to a second endpoint in the network that indicates a plurality of intermediate nodes along the forward path. The device causes the second endpoint to perform traceroute testing with respect to the plurality of intermediate nodes, to obtain traceroute results for a reverse path between the second endpoint and the first endpoint that includes the plurality of intermediate nodes. The device computes a delay metric associated with a particular intermediate node among the plurality of intermediate nodes, based on the traceroute results for the forward path and the traceroute results for the reverse path. The device provides the delay metric for presentation via a user interface.

Abstract: In one implementation, a device generates a routing graph using path trace data, wherein nodes of the routing graph represent different entities in one or more computer networks. The device computes importance metrics for the nodes in the routing graph based on their traffic loads. The device generates an insight regarding the one or more computer networks based on the importance metrics for the nodes. The device provides the insight to a user interface for presentation to a user.

Abstract: In one embodiment, a device detects a performance anomaly in a network based on a plurality of time series of network metrics collected from the network. The device determines a loss of visibility in the network based on results from probing the network. The device identifies a particular location in the network as a root cause of the performance anomaly based on the loss of visibility. The device provides, to a user interface, an indication of the particular location being the root cause of the performance anomaly.

Abstract: The present disclosure provides techniques for TID obfuscation. A network device generates a first transformation matrix comprising a plurality of rows and a plurality of columns, each row corresponding to a real traffic identifier (TID) value, and each column corresponding to an epoch identifier within a sequence of epochs. The network device populates each entry of the first transformation matrix with an over-the-air-TID (OTA-TID) value, where each OTA-TID value is mapped from a respective TID and a respective epoch identifier. The network device transmits the first transformation matrix to a station (STA).

Abstract: In one implementation, a device obtains node information regarding a plurality of nodes in a computer network. The device identifies a topology of the computer network. The device determines an optimal agent deployment plan for probing agents in the computer network based on the node information and the topology of the computer network. The device causes probing agents to be deployed to a selected set of nodes from the plurality of nodes in accordance with the optimal agent deployment plan.

Abstract: Techniques and apparatus for supporting seamless roaming for enhanced privacy wireless stations are described. An example technique performed by a wireless station includes obtaining, while associated with a first access point (AP) in a first basic service set (BSS) and associated with a first enhanced data privacy (EDP) group supported by the first AP, information associated with one or more EDP groups supported by a second AP in a second BSS. Upon roaming from the first AP in the first BSS to the second AP in the second BSS, a second EDP group of the one or more EDP groups is joined, based at least in part on the information.

Abstract: Described herein are devices, systems, methods, and processes for managing roaming actions in a wireless network. The embodiments utilize a machine learning model to generate roaming recommendations based on a plurality of roaming-related metrics. The metrics include data about the current network conditions, the station's previous roaming experiences, and the capabilities of potential roaming target candidates. The roaming recommendations can be provided to a station by an access point (AP). The station can then attempt to perform a roaming action based on the recommendations. After the attempt, the station transmits a roaming feedback to the AP, which includes data about the success or failure of the roaming action and any additional relevant data. In case the station rejects the roaming recommendations, the station may also provide a feedback indicating the rejection. The feedback is utilized to update the machine learning model, thereby improving the accuracy of future roaming recommendations.

Abstract: Aspects of this disclosure provide a method including establishing a wireless communications link between an access point and a wireless station. Establishing the wireless communications link comprises assigning the wireless station to an Enhanced Data Privacy (EDP) group that is associated with timing information for rotating wireless frame anonymization parameters at epoch transitions. The method further includes determining a privacy-enhanced association identifier (peAID) having a size greater than a size of an AID field that is used in one or more types of wireless frames on the wireless communications link. The method further includes generating an over-the-air AID (otaAID) to be used in the one or more types of wireless frames. Generating the otaAID comprises applying at least the peAID to a hash function. The method further includes transmitting, from the access point, a first wireless frame having the otaAID in the AID field.

Abstract: A system and method are provided for tracking the quality of telemetry data in a wireless network, and to provide profiling of the telemetry to prevent erroneous radio resource management (RRM) computations. Statistical profiles are generated from the telemetry data that includes both computation data, which is used in RRM computations, and other network data. A data-quality score is generated based on the other data and statistical profiles of the computation data. The data-quality score represents whether the telemetry data is of sufficient quality to be used in RRM computations. The data-quality score can be based, at least in part, on detecting changes in the statistical profiles relative to a baseline statistical profile of the telemetry data and using the second network data to assess a likelihood that the detected changes arise from a degradation in a quality of the first network data.

Abstract: A system and method for using 802.11v action report messages to enhance roaming. In one embodiment, a method includes transmitting, to a station, a transition management message that identifies a recommended access point for roaming for the station, receiving, from the station, an action report in response to the transition management message, where the action report indicates feedback to the recommended access point identified in the transition management message, and determining a roaming recommendation based on the action report.

Abstract: Techniques for classification of wireless signals are disclosed. These techniques include receiving data describing radio frequency characteristics of a wireless network transmission environment and presenting the data for display on a graphical user interface (GUI) associated with a network device in the wireless network. The techniques further include receiving input from the GUI identifying one or more portions of the data, and training a machine learning (ML) model to classify an interferer in the wireless network transmission environment based on the identified one or more portions of the data.

Abstract: In one embodiment, a method can receive transmission metadata associated with a plurality of devices within an Internet of Things (IoT) network. The method can use a transmission sensing component (TSC) to measure transmission energy cost for each of the plurality of devices over a time period using the transmission metadata. The method can use a central compute engine (CCE) and the transmission energy cost for each of the plurality of devices to determine a plurality of transmission features associated with the plurality of devices having a transmission energy cost that is minimized. The method can use a transmission scheduling engine (TSE) and the plurality of transmission features to generate a transmission mode schedule to reduce a transmission energy cost for the plurality of devices within the IoT network. The method can adjust a transmission mode associated with the plurality of devices based on the transmission mode schedule.

Abstract: The present disclosure provides techniques for physical layer (PHY) parameter recommendation for improved link quality. An access point (AP) receives a recommendation request frame from a station (STA), the recommendation request frame comprising at least one of: one or more physical layer (PHY) parameters of the STA, a link margin of the STA, or one or more acceptable link degradation limits of the STA. The AP determines, based on the recommendation request frame, a recommended range for at least one of the PHY parameters, the recommended range being determined to maintain link performance within the acceptable link degradation limits. The AP transmits a recommendation response frame to the STA, the recommendation response frame comprising the recommended range, where the STA adjusts at least one PHY parameter based on the recommended range.