Abstract: A system for managing clouds of edge devices as an Infrastructure as a Service clouds includes an application server, a location based situational awareness subsystem and a cloud management subsystem. The cloud management subsystem includes a first API through which the application server makes request to the location based situational awareness subsystem and a conductor that searches for the optimal deployment of cloud resources that meet a set of constraints. A second API for managing and deploying applications on a selected set of the plurality of network connected devices. The system also includes a compute node that can interact with the selected set of the plurality of network connected devices to launch and manage containers on the selected set of the plurality of network connected devices.

Abstract: The concepts and technologies disclosed herein are directed to a policy-driven homing service system that can receive, from a master service orchestrator, a demand specifying a service component to be used to provide, at least in part, a service. The system can receive, from a policy system, a homing constraint. The system can determine, for the demand, an initial set of all potential candidates. The system can apply the homing constraint to each potential candidate in the initial set of all potential candidates. The system can determine a resultant set of potential solutions that satisfy the homing constraint. The system can determine a best solution from the resultant set of potential solutions. The system can send the best solution to the master service orchestrator, which instantiates the demand based upon the best solution.

Abstract: A method includes, for components of an application, identifying a plurality of groups including a first group and a second group, The method also includes nesting the first group into the second group to create a nested group, based at least on a level of the first group not exceeding a level of the second group. The method includes deploying the application by placing the components of the nested group within a network in accordance with a restriction of the nested group. The components include at least one virtual machine.

Abstract: Cloud-based orchestration may be leveraged to create flexible storage solutions that use continuous adaptation to tailor themselves to their target application workloads that made provide efficiencies in performance, cost, or scalability over conventional designs.

Abstract: Concepts and technologies are disclosed herein for creating cross-service chains of virtual network functions in a wide area network. A controller can receive a chain request from a requestor. The chain request can specify functionality that is to be included in a service chain. The functionality can include a first function and a second function. The controller can compute a route associated with the service chain. The route can specify a first site that hosts a first service that provides the first function and a second site that hosts a second service that provides the second function. A first virtual network function can be located at the first site and a second virtual network function can be located at the second site. The controller can configure edge devices and forwarding devices to various entities at the two sites to enable the cross-service virtual network function chain.

Abstract: Systems and methods are disclosed for creating and managing hybrid clouds including both standard compute nodes and edge devices. Edge devices can be enrolled in a hybrid cloud by deploying a lightweight container to the edge device.

Abstract: A system for managing clouds of edge devices as an Infrastructure as a Service clouds includes an application server, a location based situational awareness subsystem and a cloud management subsystem. The cloud management subsystem includes a first API through which the application server makes request to the location based situational awareness subsystem and a conductor that searches for the optimal deployment of cloud resources that meet a set of constraints. A second API for managing and deploying applications on a selected set of the plurality of network connected devices. The system also includes a compute node that can interact with the selected set of the plurality of network connected devices to launch and manage containers on the selected set of the plurality of network connected devices.

Abstract: Virtual redundancy for active-standby cloud applications is disclosed herein. A virtual machine (“VM”) placement scheduling system is disclosed herein. The system can compute, for each standby VM of a plurality of available standby VMs, a minimum required placement overlap delta to meet an entitlement assurance rate (“EAR”) threshold. The system can compute a minimum number of available VM slots for activating each standby VM to meet the EAR threshold. For each standby VM of a given application, the system can filter out any server of a plurality of servers that does not meet criteria. If a given server meets the criteria, the system can add the given server to a candidate list; sort, in descending order, the candidate list by the minimum required placement overlap delta and the number of available virtual machine slots; and select, from the candidate list of servers, a candidate server from atop the candidate list.

Abstract: Concepts and technologies are disclosed herein for a topology aware load balancing engine. A processor that executes a load balancing engine can receive a request for a load balancing plan for an application. The processor can obtain network topology data that describes elements of a data center and links associated with the elements. The processor can obtain an application flow graph associated with the application and create a load balancing plan to use in balancing traffic associated with the application. The processor can create the load balancing plan to use in balancing traffic associated with the application and distribute commands to the data center to balance traffic over the links.

Abstract: An eNodeB or other cell access point device can receive demand data from mobile devices served by the cell. The demand data can represent an estimate of demand over a future period for network resources (e.g., bandwidth). The cell can aggregate this demand data and determine price data for the time period or for various intervals of the time period, then transmit the price data to the mobile devices. The price data can operate as a collaborative approach to scheduling traffic. For example, data (e.g., delay tolerant data) can be shifted (e.g., delayed for a few seconds) based on an examination of the price data in conjunction a determined priority of the data. Such can be applicable to data traffic not traditionally thought of as delay tolerant such as streaming video or web browsing, and can be accomplished without negatively impacting the quality of service or experience of the client.

Abstract: Concepts and technologies are disclosed herein for creating cross-service chains of virtual network functions in a wide area network. A controller can receive a chain request from a requestor. The chain request can specify functionality that is to be included in a service chain. The functionality can include a first function and a second function. The controller can compute a route associated with the service chain. The route can specify a first site that hosts a first service that provides the first function and a second site that hosts a second service that provides the second function. A first virtual network function can be located at the first site and a second virtual network function can be located at the second site. The controller can configure edge devices and forwarding devices to various entities at the two sites to enable the cross-service virtual network function chain.

Abstract: Concepts and technologies are disclosed herein for a distributed stateful load balancer. A first load balancer can store a first portion of a distributed hash table including data over a first range of hash keys. The first load balancer can be in communication with a second load balancer that stores a second portion of the distributed hash table including data over a second range of hash keys. The first load balancer can receive a packet, where a hash value calculated for the packet does not fall in the first range of hash keys. The first load balancer can identify, based on the hash value, that the second load balancer stores data that identifies a path associated with the packet and query the second load balancer to identify the path. The first load balancer can receive the data and forward, along the path, the packet to a network element.

Abstract: Virtual redundancy for active-standby cloud applications is disclosed herein. A virtual machine (“VM”) placement scheduling system is disclosed herein. The system can compute, for each standby VM of a plurality of available standby VMs, a minimum required placement overlap delta to meet an entitlement assurance rate (“EAR”) threshold. The system can compute a minimum number of available VM slots for activating each standby VM to meet the EAR threshold. For each standby VM of a given application, the system can filter out any server of a plurality of servers that does not meet criteria. If a given server meets the criteria, the system can add the given server to a candidate list; sort, in descending order, the candidate list by the minimum required placement overlap delta and the number of available virtual machine slots; and select, from the candidate list of servers, a candidate server from atop the candidate list.

Abstract: An eNodeB or other cell access point device can receive demand data from mobile devices served by the cell. The demand data can represent an estimate of demand over a future period for network resources (e.g., bandwidth). The cell can aggregate this demand data and determine price data for the time period or for various intervals of the time period, then transmit the price data to the mobile devices. The price data can operate as a collaborative approach to scheduling traffic. For example, data (e.g., delay tolerant data) can be shifted (e.g., delayed for a few seconds) based on an examination of the price data in conjunction a determined priority of the data. Such can be applicable to data traffic not traditionally thought of as delay tolerant such as streaming video or web browsing, and can be accomplished without negatively impacting the quality of service or experience of the client.

Abstract: Concepts and technologies are disclosed herein for a topology aware load balancing engine. A processor that executes a load balancing engine can receive a request for a load balancing plan for an application. The processor can obtain network topology data that describes elements of a data center and links associated with the elements. The processor can obtain an application flow graph associated with the application and create a load balancing plan to use in balancing traffic associated with the application. The processor can create the load balancing plan to use in balancing traffic associated with the application and distribute commands to the data center to balance traffic over the links.

Abstract: Concepts and technologies are disclosed herein for an application deployment engine. A processor that executes an application deployment engine can receive an application request. The processor can obtain network topology data that indicates availability of resources of a data center, an application template associated with the application, and a running time during which an application placement plan is to be identified out of a large number of placement scenarios within the running time. The application template can describe an application flow path associated with the application. The processor can identify the application placement plan, where the application placement plan can include an optimal placement of the application at the data center, before a given running time expires by pruning the large search space. The processor can generate a command to effect deployment of the application in accordance with the application placement plan.

Abstract: Example mobile devices disclosed herein include a camera, memory including computer-executable instructions, and a processor to execute the instructions to at least associate a location of the mobile device with picture data obtained with the camera. The processor is also to assign a first data tag to the picture data when the location of the mobile device corresponds to a first area, the first data tag to identify a first security level for the picture data, or assign a second data tag to the picture data when the location of the mobile device does not correspond to the first area, the second data tag to identify a second security level for the picture data. The processor is further to determine whether to permit an application to access the picture data based on whether the first data tag or the second data tag is assigned to the picture data.

Abstract: Concepts and technologies are disclosed herein for creating cross-service chains of virtual network functions in a wide area network. A controller can receive a chain request from a requestor. The chain request can specify functionality that is to be included in a service chain. The functionality can include a first function and a second function. The controller can compute a route associated with the service chain. The route can specify a first site that hosts a first service that provides the first function and a second site that hosts a second service that provides the second function. A first virtual network function can be located at the first site and a second virtual network function can be located at the second site. The controller can configure edge devices and forwarding devices to various entities at the two sites to enable the cross-service virtual network function chain.

Abstract: Concepts and technologies are disclosed herein for providing streaming video from mobile computing nodes. A request for streaming video captured by a mobile computing node can be received at a computer including a processor that executes a controller. The request can include a parameter associated with the streaming video. The computer can initiate transmission of an inquiry message to two or more mobile computing nodes and receive inquiry message responses from the mobile computing nodes that include the mobile computing node. The inquiry message responses can indicate that the mobile computing nodes can satisfy the parameter. The computer can create a list of the mobile computing nodes that can satisfy the parameter and provide the list to the requestor. The computer can receive a selection of the mobile computing node, and initiate delivery of a video stream to the requestor.

Abstract: Concepts and technologies are disclosed herein for an application deployment engine. A processor that executes an application deployment engine can receive an application request. The processor can obtain network topology data that indicates availability of resources of a data center, an application template associated with the application, and a running time during which an application placement plan is to be identified out of a large number of placement scenarios within the running time. The application template can describe an application flow path associated with the application. The processor can identify the application placement plan, where the application placement plan can include an optimal placement of the application at the data center, before a given running time expires by pruning the large search space. The processor can generate a command to effect deployment of the application in accordance with the application placement plan.