Abstract: Novel tools and techniques are provided for implementing a telemetry hub, and, more particularly, to methods, systems, and apparatuses for implementing a telemetry hub that obtains sensor data from a plurality of sources and that determines one or more first actions to take in response to receiving the first sensor data. In operation, a telemetry hub might receive first sensor data from one or more sensors. The telemetry hub may determine whether the first sensor data can be trusted and whether the first sensor data is valid. Based on a determination that the first sensor data can be trusted and is valid, the telemetry hub might analyze the first sensor data to determine one or more first actions to take. The telemetry hub might then implement the one or more first actions based at least in part on the analysis of the first sensor data.

Abstract: Novel tools and techniques are provided for implementing Inference as a Service. In various embodiments, a computing system may receive a request to perform an AI/ML task on first data, the request including desired parameters, in some cases, without information regarding any of specific hardware, specific hardware type, specific location, or specific network for providing network services for performing the requested AI/ML task. The computing system may identify edge compute nodes within a network based on the desired parameters and/or unused processing capacity of each node. The computing system may identify AI/ML pipelines capable of performing the AI/ML task, the pipelines including neural networks utilizing pre-trained AI/ML models. The computing system may cause the identified nodes to run the identified pipelines to perform the AI/ML task.

Abstract: The present technology relates to improving computing services in a distributed network of remote computing resources, such as edge nodes in an edge compute network. In an aspect, the technology relates to a method that includes aggregating historical request data for a plurality of requests, wherein the aggregated historical request data a time of the request, a location of a device from which the request originated, and/or a type of service being requested. The method also incudes training a machine learning model based on the aggregated historical request data; generating, from the trained machine learning model, a prediction for a type of service to be request; identifying an edge node, from a plurality of edge nodes, based on a physical location of the edge node; and based on predicted service, allocating computing resources for the computing service on the identified edge node.

Abstract: Novel tools and techniques are provided for implementing data and source validation for equipment output data and/or for equipment failure predict. In various embodiments, in response to receiving a first request for first data that is output by first equipment, a computing system might retrieve and analyze the first data to determine whether the first data can be trusted. If so, the computing system might send the first data to the requesting device. If not, the computing system might send a second request for identifying a blockchain containing a block containing a copy of the first data. In response to the blockchain system identifying such a blockchain, the computing system might receive the identified blockchain; might abstract the block containing the copy of the first data from the identified blockchain; might abstract the first data from the block; and might send the first data to the requesting device.

Abstract: Novel tools and techniques are provided for implementing network experience shifting, and, in particular embodiments, using either a roaming or portable hypervisor associated with a user or a local hypervisor unassociated with the user. In some embodiments, a network node in a first network might receive, via a first network access device in a second network, a request from a user device to establish roaming network access, and might authenticate a user associated with the user device, the user being unassociated with the first network access device. Based on a determination that the user is authorized to access data, content, profiles, and/or software applications that are accessible via a second network access device, the network node might establish a secure private connection through a hypervisor or container communicatively coupled to the first network access device to provide the user with access to her data, content, profiles, and/or software applications.

Abstract: Novel tools and techniques are provided for implementing block-level, bit-mapped binary data access for parallel processing. In various embodiments, a computing system may cause a plurality of compute nodes to perform one or more tasks (e.g., artificial intelligence (“AI”) and/or machine learning (“ML”) tasks) on portions of decompressed data, after causing some, but not all, of the compute nodes to decompress the entire compressed data. In some cases, the computing system may cause each compute node to decompress portions of the compressed data. Once the data has been decompressed and/or bit-mapped, each compute node may be caused to perform at least one task (e.g., AI/ML task) on its assigned portion of the decompressed data. Different portions of the same decompressed data may be processed with the same (AI/ML) algorithm, or the same portions of the same decompressed data may be processed with a different (AI/ML) algorithm, or a combination thereof.

Abstract: Implementations include providing security services to workloads deployed across various types of network environments, such as public networks, private networks, hybrid networks, customer premise network environments, and the like, by redirecting traffic intended for the service device through a security environment of the first network. After application of the security features to the incoming traffic, the “clean” traffic may be transmitted to the service device instantiated on the separate network via a tunnel. Redirection of incoming traffic to the security-providing first network may include correlating a network address of the service device to a reserved network address of a block of reserved addresses and updating a Domain Name Server (DNS) or other address resolving system with the reserved address. The return transmission tunnel may be established between the security environment and the network address of the service device.

Abstract: Novel tools and techniques are provided for implementing intent-based orchestration using network parsimony trees. In various embodiments, in response to receiving a request for network services that comprises desired characteristics and performance parameters for the requested network services without information regarding specific hardware, hardware type, location, or network, a computing system might generate a request-based parsimony tree based on the desired characteristics and performance parameters. The computing system might access, from a datastore, a plurality of network-based parsimony trees that are each generated based on measured network metrics, might compare the request-based parsimony tree with each of one or more network-based parsimony trees to determine a fitness score for each network-based parsimony tree, and might identify a best-fit network-based parsimony tree based on the fitness scores.

Abstract: The present technology relates to improving computing services in a distributed network of remote computing resources, such as edge nodes in an edge compute network. In an aspect, the technology relates to a system that includes a plurality of edge nodes and a beacon. The system performs operations that may include collecting traffic data from the beacon over a period of time, wherein the traffic data includes at least an amount of devices sending probe requests to the beacon; comparing the amount of devices to a predetermined threshold for traffic data; and based on the comparison of the amount of devices to the predetermined threshold for traffic data, generating a recommendation for installation of a new edge node in addition to the plurality of edge nodes.

Abstract: Novel tools and techniques might provide for implementing application, service, and/or content access control. Based at least in part on a consumer's choice of applications, services, content, and/or content providers-particular in exchange for a subsidy on content and/or network access fees provided to the consumer by chosen content providers-, a computing system may determine whether access to applications, services, and/or content not associated with the chosen content providers (“other content”) should be allowed or restricted. If restricted, the computing system might utilize various network access techniques and/or technologies to block the consumer's access to the other content, to allow access to the other content on a charge per access basis, or to allow access to the other content at reduced network access speeds. In some embodiments, an access provider (e.g., an Internet service provider, etc.) might perform both determination and implementation of content access and restriction.

Abstract: Implementations include providing security services to workloads deployed across various types of network environments, such as public networks, private networks, hybrid networks, customer premise network environments, and the like, by redirecting traffic intended for the service device through a security environment of the first network. After application of the security features to the incoming traffic, the “clean” traffic may be transmitted to the service device instantiated on the separate network via a tunnel. Redirection of incoming traffic to the security-providing first network may include correlating a network address of the service device to a reserved network address of a block of reserved addresses and updating a Domain Name Server (DNS) or other address resolving system with the reserved address. The return transmission tunnel may be established between the security environment and the network address of the service device.

Abstract: Novel tools and techniques are provided for implementing intent-based orchestration using network parsimony trees. In various embodiments, in response to receiving a request for network services that comprises desired characteristics and performance parameters for the requested network services without information regarding specific hardware, hardware type, location, or network, a computing system might generate a request-based parsimony tree based on the desired characteristics and performance parameters. The computing system might access, from a datastore, a plurality of network-based parsimony trees that are each generated based on measured network metrics, might compare the request-based parsimony tree with each of one or more network-based parsimony trees to determine a fitness score for each network-based parsimony tree, and might identify a best-fit network-based parsimony tree based on the fitness scores.

Abstract: Novel tools and techniques might provide for implementing application, service, and/or content access control. Based at least in part on a consumer's choice of applications, services, content, and/or content providers—particular in exchange for a subsidy on content and/or network access fees provided to the consumer by chosen content providers—, a computing system may determine whether access to applications, services, and/or content not associated with the chosen content providers (“other content”) should be allowed or restricted. If restricted, the computing system might utilize various network access techniques and/or technologies to block the consumer's access to the other content, to allow access to the other content on a charge per access basis, or to allow access to the other content at reduced network access speeds. In some embodiments, an access provider (e.g., an Internet service provider, etc.) might perform both determination and implementation of content access and restriction.

Abstract: Novel tools and techniques are provided for implementing network experience shifting, and, in particular embodiments, using either a roaming or portable hypervisor associated with a user or a local hypervisor unassociated with the user. In some embodiments, a network node in a first network might receive, via a first network access device in a second network, a request from a user device to establish roaming network access, and might authenticate a user associated with the user device, the user being unassociated with the first network access device. Based on a determination that the user is authorized to access data, content, profiles, and/or software applications that are accessible via a second network access device, the network node might establish a secure private connection through a hypervisor or container communicatively coupled to the first network access device to provide the user with access to her data, content, profiles, and/or software applications.

Abstract: The present technology relates to improving computing services in a distributed network of remote computing resources, such as edge nodes in an edge compute network. In an aspect, the technology relates to a method that includes aggregating historical request data for a plurality of requests, wherein the aggregated historical request data a time of the request, a location of a device from which the request originated, and/or a type of service being requested. The method also incudes training a machine learning model based on the aggregated historical request data; generating, from the trained machine learning model, a prediction for a type of service to be request; identifying an edge node, from a plurality of edge nodes, based on a physical location of the edge node; and based on predicted service, allocating computing resources for the computing service on the identified edge node.

Abstract: Novel tools and techniques are provided for implementing data and source validation for equipment output data and/or for equipment failure predict. In various embodiments, in response to receiving a first request for first data that is output by first equipment, a computing system might retrieve and analyze the first data to determine whether the first data can be trusted. If so, the computing system might send the first data to the requesting device. If not, the computing system might send a second request for identifying a blockchain containing a block containing a copy of the first data. In response to the blockchain system identifying such a blockchain, the computing system might receive the identified blockchain; might abstract the block containing the copy of the first data from the identified blockchain; might abstract the first data from the block; and might send the first data to the requesting device.

Abstract: Novel tools and techniques are provided for implementing intent-based orchestration using network parsimony trees. In various embodiments, in response to receiving a request for network services that comprises desired characteristics and performance parameters for the requested network services without information regarding specific hardware, hardware type, location, or network, a computing system might generate a request-based parsimony tree based on the desired characteristics and performance parameters. The computing system might access, from a datastore, a plurality of network-based parsimony trees that are each generated based on measured network metrics, might compare the request-based parsimony tree with each of one or more network-based parsimony trees to determine a fitness score for each network-based parsimony tree, and might identify a best-fit network-based parsimony tree based on the fitness scores.

Abstract: Novel tools and techniques are provided for implementing network experience shifting, and, in particular embodiments, using either a roaming or portable hypervisor associated with a user or a local hypervisor unassociated with the user. In some embodiments, a network node in a first network might receive, via a first network access device in a second network, a request from a user device to establish roaming network access, and might authenticate a user associated with the user device, the user being unassociated with the first network access device. Based on a determination that the user is authorized to access data, content, profiles, and/or software applications that are accessible via a second network access device, the network node might establish a secure private connection through a hypervisor or container communicatively coupled to the first network access device to provide the user with access to her data, content, profiles, and/or software applications.

Abstract: Novel tools and techniques are provided for remotely configuring and orchestrating multifunctional cloud devices located on customer premises, in some cases, using a smart cloud adaptive device. In some embodiments, the smart cloud adaptive device, which might have one or more wireless programmable radios configured to communicate with a network termination device, might communicate with a cloud configuration server over a network via the one or more wireless programmable radios (and, in some embodiments, through the network termination device). The smart cloud adaptive device might transmit device identification information associated with a customer and/or service codes indicative of services to be provided to the customer. The smart cloud adaptive device might receive one or more configuration files from the cloud configuration server based on the service codes, and enable functionality among a plurality of functionalities to provision the services, based on the one or more configuration files.

Abstract: The present technology relates to improving computing services in a distributed network of remote computing resources, such as edge nodes in an edge compute network. In an aspect, the technology relates to a method that includes aggregating historical request data for a plurality of requests, wherein the aggregated historical request data a time of the request, a location of a device from which the request originated, and/or a type of service being requested. The method also incudes training a machine learning model based on the aggregated historical request data; generating, from the trained machine learning model, a prediction for a type of service to be request; identifying an edge node, from a plurality of edge nodes, based on a physical location of the edge node; and based on predicted service, allocating computing resources for the computing service on the identified edge node.