Systems and methods of the present invention for maintaining network data distribution are provided. Network data may be distributed in such as manner as to allow a network session to weather interrupted communications between host and clients without significant loss of data. Embodiments of the present invention provide for one or more clients to serve as backup host(s) for the network session. When the other clients transmit data to the host, they may also transmit the data to one or more backup hosts if there are any indications of interrupted communication.

An indication to determine a device to host at least one shared content found on a first device is received. The first device is connected to a network. The network includes two or more devices. To each device of the two or more devices connected to the network, a request to host the at least one shared content found on the first device is transmitted. Responsive to transmitting the request, a response to host from at least one device of the two or more devices connected to the network is received. An optimal device of the at least one device to host the at least one shared content is determined. The at least one shared content is transmitted to the optimal device.

Example embodiments relate to a method of, and device for facilitating, resilient peer-to-peer application message routing. The method comprises storing a network routing table comprising destination addresses of applications hosted on peer nodes of a network, and providing the peer nodes with a copy of the routing table via which routing table an application message from any one of the peer nodes is routed to a destination address designating a destination application hosted by a destination peer node. Further, the method comprises providing, when the destination application hosted by the destination peer node is inactivated, all peer nodes with a copy of an updated routing table taking into account the inactivation of said application, wherein a further application message addressed from any one of the peer nodes to the destination address associated with the inactivated application is routed via the updated routing table, to an alternative destination application having the same destination address as the inactivated application.

A system and method are provided of minimizing network bandwidth used from an external network by client peers in a local network. The method can include the operation of organizing a plurality of clients each having media streamlets and a client parent in a structure within the local network. Mapping information propagates through the structure. The mapping information represents local streamlet locations as stored by the plurality of clients. Another operation is retrieving a local streamlet from a client identified in the mapping information as having the local streamlet for the requesting client.

A method scalably authorizes requests. A request to authorize access to a resource is received. A plurality of policies controlling the request is identified. The plurality of policies are concurrently processed. A decision for a policy is received. The decision is of a plurality of decisions corresponding to the plurality of policies. The policy is of the plurality of policies. The decision is determined using a machine learning model and the request. An aggregate decision is generated from the plurality of decisions. A token to access the resource is transmitted in response to the aggregate decision.

The predictive overlay network architecture of the present invention improves the performance of applications distributing digital content among nodes of an underlying network such as the Internet by establishing and reconfiguring overlay network topologies over which associated content items are distributed. The present invention addresses not only frequently changing network congestion, but also interdependencies among nodes and links of prospective overlay network topologies. The present invention provides a prediction engine that monitors metrics and predicts the relay capacity of individual nodes and links (as well as demand of destination nodes) over time to reflect the extent to which the relaying of content among the nodes of an overlay network will be impacted by (current or future) underlying network congestion. The present invention further provides a topology selector that addresses node and link interdependencies while redistributing excess capacity to determine an overlay network topology that satisfies application-specific performance criteria.

A service provider may apply customer-selected or customer-defined auto-scaling policies to a cluster of resources (e.g., virtualized computing resource instances or storage resource instances in a MapReduce cluster). Different policies may be applied to different subsets of cluster resources (e.g., different instance groups containing nodes of different types or having different roles). Each policy may define an expression to be evaluated during execution of a distributed application, a scaling action to take if the expression evaluates true, and an amount by which capacity should be increased or decreased. The expression may be dependent on metrics emitted by the application, cluster, or resource instances by default, metrics defined by the client and emitted by the application, or metrics created through aggregation. Metric collection, aggregation and rules evaluation may be performed by a separate service or by cluster components. An API may support auto-scaling policy definition.

The present invention faces the issue of supporting edge cloud in an NG network. There is thus provided an edge cloud broker (ECB) and a method carried out by the ECB for selecting edge cloud resources of a mobile edge computing (MEC) network, the edge cloud resources usable by a UE accessing the NG network. This method comprises: obtaining, from a first network node of the NG network, a UE's location; obtaining, from a second network node of the NG network, an identifier of an edge cloud application that the UE requests; obtaining, from a third network node of the MEC network, a location of each one or more edge cloud resources available to execute the edge cloud application; and selecting, based on at least the UE's location and the location of each one or more edge cloud resources, an applicable edge cloud resource to execute the edge cloud application for the UE.

An example operation may include a system, comprising one or more of receiving a virtual network function component instance (VNFCI) status notification resumption message with an active state when a peer VNFCI operational state is active, retrieving a timestamp of a VNFCI state change to an active state from an element VNFCI state database, retrieving a timestamp of a peer VNFCI state change to active from an element VNFCI state database, sending one or more of: a request to a virtual network function manager (VNFM) to determine if the VNFCI network is isolating while an operating state was active, and a request to the VNFM to determine if the peer VNFCI network is isolating while an operating state was active, sending a state change request with standby state to the peer VNFCI when the VNFCI is not network isolated and the peer VNFCI is network isolated, and a VNFM response is received regarding the VNFCI, a timeout response from the VNFM, and a VNFM response is received regarding the peer VNFCI, and sending a state change request with standby to the VNFCI with one or more of: the VNFCI network isolate and peer VNFCI is not network isolated, and the VNFCI is network isolated or the peer VNFCI is not network isolated, and the VNFCI is not network isolated and the peer VNFCI is network isolated and the VNFCI is in preferred standby.

Techniques are provided for user-based data tiering. In an example, a computer maintains a first-in-first-out queue that logs a finite set of users that have most-recently modified a file. This queue can be maintained in an extended attribute of an Mode that corresponds to a file. A computer can also maintain a policy that defines how to perform storage tiering on a file based on which users have accessed the file. When a tiering operation is performed, the files specified by a corresponding tiering policy can be evaluated for which users have recently accessed them. When a user specified by the tiering policy has recently modified a file, the file can be placed in tiering queue for tiering.