Abstract: Techniques are described for a centralized, neutral system for Internet of Things (IoT) device activation and automatic onboarding on an end-to-end basis, and for establishing secure communication between IoT devices and the IoT platforms. For example, a method includes receiving an activation request message from an IoT device to activate the IoT device on an IoT core network of a plurality of IoT core networks, wherein the plurality of IoT core networks and a plurality of IoT edge devices are co-located within the co-location facilities, and wherein the plurality of IoT edge devices are connected to one or more IoT platforms; authenticating the IoT device for connection to the IoT core network; and in response to authenticating the IoT device, provisioning a connection between the IoT core network and the plurality of IoT edge devices to provide the IoT device access to the one or more IoT platforms.

Abstract: In general, this disclosure describes techniques for hierarchical management of co-location facility assets and permissions. For example, techniques are described for managing permissions for sub-customer access to reseller assets of a co-location facility, where the sub-customers are customers of the reseller. The techniques as described herein may, as a result, enable customers that become resellers to assign assets of the cloud exchange and manage sub-customer permissions to those assigned assets, including sub-customer orderings and/or access of assets associated with one or more geographically distinct co-location facilities and port-level assets.

Abstract: In general, techniques are described for overriding a programmed set-point of an air moving component of a cooling unit, in order to control an extent of a refrigeration load on an air cooling component of the cooling unit. In one example, an air cooling unit that is configured to be coupled to an electrical bus of a data center includes an air cooling component, an air moving component that is configured to supply air to the air cooling component at a volumetric flow rate according to a fan speed set-point of the air moving component, and a unit controller that is configured to adjust the fan speed set-point of the air moving component to limit power draw by the air cooling unit from the electrical bus to within a bounded range of values that is defined in part by a power draw set-point of the air cooling unit.

Abstract: In some examples, a customer churn risk engine is configured to query at least one of co-location data indicating co-location facility usage by a particular co-location facility customer and telemetry data indicating interconnections established between the particular co-location facility customer and at least one additional co-location facility customer within at least one co-location facility operated by a co-location facility provider. The customer churn risk engine is further configured to generate, based at least in part on at least one of the co-location data and the telemetry data, a churn risk score for the particular co-location facility customer. The customer churn risk engine is configured to output the churn risk score for the particular co-location facility customer.

Abstract: In some examples, a computing device comprises at least one computer processor; and a memory comprising instructions that when executed by the at least one computer processor cause the at least one computer processor to: receive feature usage data indicating respective usages of a plurality of network device features configured for the network device; receive resource utilization data indicating resource utilization of the network device resource by each of the network device features at different usages; determine, based on the features usage data and the resource utilization data, respective resource utilizations of the network device resource by the plurality of network device features; combine the respective resource utilizations of the network device resource to determine a total network device resource utilization for the network device resource; and output an indication of the total network device resource utilization for the network device resource.

Abstract: A power supply system includes a plurality of UPSs configured to provide output power to one or more loads using AC power drawn from a supply bus and energy stored at respective energy modules of the plurality of UPSs. Each UPS of the plurality of UPSs comprises a corresponding frequency sensor configured to generate an indication of a frequency of the AC power at the supply bus. The plurality of UPSs comprises a first UPS configured to draw the AC power from the supply bus when the indication of the frequency output by the corresponding frequency sensor for the first UPS satisfies a first frequency priority threshold and a second UPS configured to draw the AC power from the supply bus when the indication of the frequency output by the corresponding frequency sensor for the second UPS satisfies a second frequency priority threshold.

Abstract: In some examples, a method includes obtaining, by a data center infrastructure monitoring (DCIM) agent executing on a computing device deployed by a data center provider within a first data center of a plurality of geographically-distributed data centers, an infrastructure asset data object comprising infrastructure asset data for a physical infrastructure asset of a second data center of the plurality of geographically-distributed data centers; translating, by the DCIM agent using an asset mapping table, the infrastructure asset data object to formatted infrastructure asset data, wherein the asset mapping table maps one or more properties of infrastructure asset data objects to management protocol objects or control protocol objects for one of a management protocol or control protocol; and sending, by the DCIM agent to customer equipment co-located within the first data center, the formatted infrastructure asset data in a communication that conforms to one of the management protocol or control protocol.

Abstract: In general, this disclosure describes a programmable network platform for dynamically programming a cloud exchange to provide a layer three (L3) routing instance as a service to customers of the cloud exchange. In one example, a cloud exchange comprises an L3 network located within a data center and configured with an L3 routing instance for an enterprise; and for the L3 routing instance, respective first and second attachment circuits for first and second cloud service provider networks co-located within the data center, wherein the L3 routing instance stores a route to a subnet of the second cloud service provider network to cause the L3 routing instance to forward packets, received from the first cloud service provider network via the first attachment circuit, to the second cloud service provider network via the second attachment circuit.

Abstract: A data center infrastructure monitoring system and method that includes a plurality of geographically distributed data centers, each data center comprising a plurality of physical infrastructure assets. A data center gateway system communicatively coupled to one or more data centers of the plurality of data centers is configured to receive a request from a customer of a data center of the plurality of data centers to display a real-time power path that shows a current flow of power through a plurality of assets of the data center, determine a subset of the plurality of assets of the data center that provide power to equipment of the customer of the data center, and output, for display, a graphical depiction of the real-time power path between the subset of the plurality of assets of the data center that provide power to equipment of the customer in the data center.

Abstract: In some examples, a method includes acquiring status information of at least one resource of a data center, estimating, based on the status information, whether load on a power supply will exceed a threshold value at a time subsequent a time of the estimating, and in response to estimating that load on the power supply will exceed the threshold value at the time subsequent the time of the estimating, transmitting a command signal to a server rack that is coupled to the power supply to configure equipment of the server rack to operate at a reduced power supply level that is reduced from a power supply level at the time of the estimating and that is based on a service level agreement associated with the server rack.

Abstract: Techniques for enforcing a common signaling latency between components positioned throughout a data center in order to realize latency equalization even though interconnects between components positioned throughout the data center do not by comparison necessarily exhibit a same total physical length.

Abstract: This disclosure describes techniques for securely, efficiently, and/or effectively providing cryptographic operations and key management services. Systems in accordance with one or more aspects of the present disclosure may provide secure management of cryptographic keys as service to a plurality of data center users or customers that contract for services provided by a data center. In one example, this disclosure describes a data center comprising a plurality of cloud service provider ports, a plurality of customer ports, network infrastructure coupling the plurality of cloud service provider ports to the plurality of customer ports, and a computing system including at least one hardware security module.

Abstract: In some examples, a method includes receiving, by a data center infrastructure monitoring system, a registration request that indicates a method of a subscription application programming interface and specifies one or more event subjects of events describing a system operation of a data center; storing, by the data center infrastructure monitoring system to a data-topic map, respective mappings for the one or more event subjects to a topic of a cloud-based publication platform; monitoring, by a data center infrastructure monitoring system, a plurality of physical infrastructure assets that enable system operation within the data center to obtain an event that describes one of the event subjects; and publishing, by the data center infrastructure monitoring system, the event to the topic.

Abstract: In some examples, a system includes a plurality of posts and a plurality of cage panels, wherein each of the cage panels is removably coupled to one or more of the plurality of posts, wherein a nominal width of each of the cage panels is congruent based on a modulus, wherein an actual width of each of the cage panels is equal to a difference between the nominal width of the cage panel and the width of one of the plurality of posts, and wherein any combination of a subset of the plurality of cage panels coupled in a common orientation to a subset of the plurality of posts has a combined width, between respective centers of end posts of the subset of the plurality of posts, that is congruent based on the modulus.

Abstract: In one example, a cloud-based services exchange comprises a plurality of interconnection assets configured to connect a customer of the cloud-based services exchange to one or more cloud service providers, the plurality of interconnection assets including a virtual circuit by which the customer accesses a cloud service from the one or more cloud service providers; and an orchestration engine configured to modify the plurality of interconnection assets.

Abstract: This disclosure describes, in some examples, techniques for improving, adjusting, and/or optimizing the infrastructure of a network. This disclosure also describes techniques for monitoring a network using a ping utility integrated into the monitoring platform described herein at the application service level. This disclosure further describes techniques for monitoring database performance through data collected by, for example, database scripts that capture the response time for queries.

Abstract: In general, techniques are described for dynamically programming a cloud-based service exchange to enable connections from an enterprise buyer in one metropolitan area to connect to a cloud exchange in another metropolitan area. For example, a network data center includes a programmable network platform to receive an indication of a network service provider (NSP) configured to transport traffic to a customer in a second metropolitan area; provision a virtual circuit from a customer-facing port of a cloud-based services exchange point of the second metropolitan area to the NSP; receive a service request that specifies one or more cloud services provided by one or more cloud service provider networks of the first metropolitan area operated by the respective cloud service providers; and configure access to the one or more cloud services provided by one or more cloud service provider networks via the virtual circuit.

Abstract: A method includes receiving, by an asset privacy system, an input video feed that includes images of one or more assets located within a data center, identifying, by the asset privacy system, one or more corresponding assets for the images of the one or more assets, determining, by the asset privacy system, an asset of the one or more assets a customer is not authorized to view, and generating, from the input video feed, by the asset privacy system based at least on the determining, an output video feed that does not include images of the asset the customer is not authorized to view and that does include images of at least one other asset of the one or more assets.

Abstract: A data center infrastructure monitoring system and method that includes a plurality of geographically distributed data centers, each having a plurality of physical infrastructure assets. A data center gateway system is communicatively coupled to one or more data centers of plurality of data centers and configured to receive data for configuring an alert specifying one or more data center assets to monitor for a primary alert event, an event type for the primary alert event, and a conditional trigger event upon which providing an alert notification for the primary alert event will be conditioned, store the data for configuring the alert, monitor, based on the stored data, the one or more infrastructure assets for the conditional trigger event and the primary alert event, and in response to detecting both the conditional trigger event and the primary alert event associated with the configured alert, providing the alert notification.

Abstract: In one example, a method includes receiving, by a computing system, first data defining an alarm associated with an infrastructure asset, the alarm having an alarm condition that causes a notification to be output indicating the alarm condition is met, and receiving, by the computing system, second data defining a one-time trigger condition for the alarm. The method also includes, in response to determining that the alarm condition is met and the one-time trigger condition for the alarm has not been met at least once, suppressing, by the computing system, output of notifications for the alarm, and in response to determining that the alarm condition is met and the one-time trigger condition for the alarm has been met at least once, outputting, by the computing device and for display, the notification indicating the alarm condition is met.