Abstract: Provided is a method and system for optimizing utilization and performance of one or more unlicensed bands in a network (Wi-Fi and Citizens Broadband Radio Service (CBRS)) through a client device application that communicates with a central node deployed on a cloud platform. The method and system collects Radio Frequency (RF) measurements from a plurality of client devices and from a plurality of nearby point of attachments (PoAs) and transmits the collected RF measurements to the cloud platform. An optimal transmission channel/network in the one or more unlicensed bands is then calculated for one or more nearby PoAs using an Artificial Intelligence (AI) module based on the RF measurements, which utilizes a Dynamic Frequency Selection (DFS), an Automated Frequency Coordinator (AFC) and a Spectrum Access System (SAS) to select the optimal transmission channel/network based on the data-rate result received from the DFS, AFC and SAS.

Abstract: The invention generally relates to a method and system for utilizing an Artificial Intelligence (AI)-based technology for tracking human mobility patterns and contact points, via a Software Development Kit (SDK) integrated into client device applications. The SDK performs contact tracing by recording past and current signal data/measurements of Wi-Fi access points encountered by a client device and stores these measurements in a local memory of the client device. The SDK further analyses the recorded past and current signal data/measurements of the Wi-Fi access points using an AI module to derive mobility patterns of user of the client device. The AI module of the SDK then identifies other client devices that the client device may have encountered based on analyzing the mobility patterns of the user of the client device and the recorded past and current signal data/measurements and via performing Wi-Fi network sniffing.

Abstract: Provided is a method and system for a network-assisted Quality of Experience (QoE)-based smart and proactive video streaming framework to be deployed at Multi-access Edge Computing (MEC) servers. Quality of Experience (QoE) levels for a plurality of video sessions streamed from a cloud server to computing devices through a central edge server are estimated based on one or more metrics associated with the plurality of video sessions. Additionally, channel status of one or more neighboring edge servers proximate to the central edge server is determined. The QoE levels of the plurality of video sessions are then maximized based on the estimating, by employing a local optimization, a global optimization and a combination of both the local optimization and the global optimization based on the one or more metrics and the channel status determined for the one or more neighboring edge servers.

Abstract: Provided is a method and system for optimizing utilization and performance of a Wi-Fi network for one or more subscriber client devices through a Wi-Fi console application by monitoring an RF environment of the Wi-Fi network to detect interference to a subscriber client device from one or more neighboring client devices that include non-subscriber client devices and other subscriber client devices and allocating a spectrum/channel for the subscriber client device to access the Wi-Fi network using an AI model based on the interference detected, throughput requirements of applications running on the subscriber client device and importance/priority of an activity on the subscriber client device. The AI model constructs a relational aggregated graph and decompose the relational aggregated graph into dynamic clusters. A heuristic deep-learning method is applied to analyze the dynamic clusters to reduce a computation time for recommendation of a suitable spectrum/channel for accessing the Wi-Fi network.

Abstract: The invention provides a method and system for automatically managing a plurality of Wi-Fi access points using a network management cloud. In order to manage the plurality of Wi-Fi access points, a connection is established between one or more Wi-Fi access points and a client device using the network management cloud. The network management cloud, then, receives and analyzes information from the client device related to controlling one or more Wi-Fi access points. Thereafter, the network management cloud determines one or more operation settings for the one or more Wi-Fi access points based on the analyzed information. The one or more operation settings of the one or more Wi-Fi access points are then configured using the network management cloud. Thus, the one or more Wi-Fi access points are configured by the client device through the network management cloud.

Abstract: The invention provides a method and system for managing a plurality of Wi-Fi access points using a cloud based adaptive software defined network (A-SDN). In order to manage the plurality of Wi-Fi access points, measurement data corresponding to a plurality of network variables are collected from one or more Wi-Fi access points and one or more client devices using a cloud based network application. Once the measurement data are collected, one or more optimal settings of one or more decision variables are derived for the one or more Wi-Fi access points using one or more network variables from the plurality of network variables. The one or more optimal settings are derived by formulation of optimization problems through heuristic solutions and a machine learning based optimization using the one or more network variables.

Abstract: The invention provides a method and system for establishing a connection between a client device of a plurality of client devices and a Wi-Fi access point of a plurality of Wi-Fi access points using a cloud platform. In an embodiment, the cloud platform identifies one or more target Wi-Fi access points and transmits an SSID-password tuple associated with the client device to the one or more target Wi-Fi access points. The one or more target Wi-Fi access points, then, broadcast an SSID of the client device and upon detecting the broadcast, the client device selects a target Wi-Fi access point and transmits a message with a pre-stored SSID-password tuple to the target Wi-Fi access point. Thereafter, the target Wi-Fi access point authorizes the client device to access the target Wi-Fi access point based on a comparison of the pre-stored SSID-password tuple and the SSID-password tuple received from the cloud platform.

Abstract: The invention provides a method and system for tracking a position of one or more Wi-Fi devices of a plurality of Wi-Fi devices. For tracking the position of the one or more Wi-Fi devices, a Triggering Router triggers the one or more Wi-Fi devices to transmit one of a broadcast probe and a directed probe through broadcasting hidden SSID networks and common SSIDs that increase a probing tendency of the one or more Wi-Fi devices. The plurality of Wi-Fi sniffers, then, collect measurement data associated with the one or more Wi-Fi devices in response to detecting the broadcast probe transmission and the directed probe transmission. Thereafter, the position of the one or more Wi-Fi devices is estimated using an adaptive machine learning model based on an indoor model whose parameters are tuned based on radio frequency (RF) measurements from the plurality of Wi-Fi devices and the measurement data.

Abstract: The invention provides a method and system for establishing a connection between a client device of a plurality of client devices and a Wi-Fi access point of a plurality of Wi-Fi access points using a cloud platform. One or more cellular devices and one or more non-Subscriber Identity Module (non-SIM) devices of a user are registered at the cloud platform. The one or more non-SIM devices are then associated to the one or more cellular devices. Further, each Wi-Fi access point of the plurality of Wi-Fi access points is also registered at the cloud platform. A location of the client device is identified and one or more Wi-Fi access points that are closest to the client device is identified. The one or more Wi-Fi access points then authorize the client device to access the one or more Wi-Fi access points based on the information provided by the cloud platform.

Abstract: The invention provides a method and system for establishing a connection between a client device of a plurality of client devices and a Wi-Fi access point of a plurality of Wi-Fi access points using a cloud platform. To start with, the plurality of client devices and the plurality of Wi-Fi access points are registered with the cloud platform. Subsequently, the client device transmits a network demand request to one or more target Wi-Fi access points. The one or more target Wi-Fi access points receive account details containing pre-registered credentials associated with the client device from the cloud platform. Upon receiving the account details, the one or more target Wi-Fi access points authorize the client device and broadcast a personalized SSID. The client device uses the personalized SSID to access a Wi-Fi access point of the one or more target Wi-Fi access points using the pre-registered credentials.

Abstract: The invention provides a method and system for managing a plurality of Wi-Fi access points using a cloud based adaptive software defined network (A-SDN). The measurement data corresponding to a plurality of network variables are collected from one or more Wi-Fi access points and one or more client devices. Once the measurement data are collected, optimal operating channels and optimal transmit power for the one or more Wi-Fi access points are derived based on one or more network variables, backhaul limits corresponding to the one or more Wi-Fi access points and a download behavior of the one or more client devices using a real-time optimization. The real-time optimization includes deriving the optimal settings through heuristic solutions of an optimization problem formulated as a Mixed Integer Nonlinear Programming (MINLP) and a machine learning based optimization.

Abstract: The invention provides a method and system for assigning one or more optimal wireless channels to a Wi-Fi access point of a plurality of Wi-Fi access points using a cloud-based orchestrator through a software defined network (SDN). To start with, RF measurements are collected from a plurality of client devices in the cloud using a RF measurement module. The RF measurements include received signal strength indicator (RSSI) measured by the plurality of client devices and a transmission channel from connected or nearby Wi-Fi access points. The one or more optimal wireless channels for the Wi-Fi access point are then derived by solving a complex optimization problem. This process employs an artificial intelligence (AI) module integrated with a global continuous optimization algorithm. The AI module utilizes the collected RF measurements and a plurality of measured variables for determining the one or more optimal wireless channels for the Wi-Fi access point using the optimization formulation.

Abstract: The invention provides a method and system for routing delay-tolerant communication messages to a destination device. The method and system creates an ad-hoc communication network for transmitting and/or receiving a delay-tolerant communication message by clustering a plurality of devices to form a social community. The delay-tolerant communication message received from a device connected to an ad-hoc hotspot is transmitted to the destination device using one or more moving subscribers/nodes. The method and system selects the one or more moving subscribers/nodes using a deep learning algorithm based on an MRC feature of the one or more moving subscribers/nodes, and transmits the delay-tolerant communication message from a device in the social community to the selected one or more moving subscribers/nodes.