Abstract: A framework to handle monitoring and automatic fault manifestation in cloud networks. Multiple techniques correlate the logs of different cloud services or generate independent capsules for each component, VM, storage, or transaction. In a first exemplary technique, an authentication token is provided by an authentication service for logs during a period of an event. In a second exemplary technique, a unique instance ID for multiple distinct processes may be created in a data model of notification logs or service logs.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system receives data at an edge node of a network that also includes regional nodes and central nodes. The processing system also determines a latency criterion associated with an application for processing the data; the application corresponds to an application programming interface. The method also includes processing the data in accordance with the application, monitoring a latency associated with the processing, and determining whether the latency meets the latency criterion. The processing system dynamically assigns data processing resources so that the latency meets the latency criterion; the resources include computation, network and storage resources of the edge node, a central node, and a regional node in communication with the edge node and the central node. Other embodiments are disclosed.

Abstract: A framework to handle monitoring and automatic fault manifestation in cloud networks. Multiple techniques correlate the logs of different cloud services or generate independent capsules for each component, VM, storage, or transaction. In a first exemplary technique, an authentication token is provided by an authentication service for logs during a period of an event. In a second exemplary technique, a unique instance ID for multiple distinct processes may be created in a data model of notification logs or service logs.

Abstract: Assignment of network addresses and estimations of flow sizes associated with network nodes can be enhanced. Assignment management component (AMC) partitions a set of network addresses into subsets of network addresses associated with respective classes. For respective virtual machines (VMs), an estimator component estimates a flow size associated with a VM based on parameters associated with the VM. AMC classifies VMs based on threshold flow-size values and respective estimated flow sizes of VMs, and assigns VMs to respective sub-groups of VMs associated with respective subsets of network addresses based on respective classifications of VMs. AMC assigns an available network address of a subset of network addresses associated with a class to a VM of a sub-group associated with that class. Estimated flow sizes and performance metrics also are utilized to make determinations regarding VM placement, traffic management, load balancing, resource allocation, and orchestration in cloud networks.

Abstract: In some examples, a method can include receiving, at a network monitor, discrete side information from a first server at a first rack regarding a data flow between the first server and a second server at a rack other than the first rack. The discrete side information can, for example, include an indicator determined by the first server that indicates whether the data flow satisfies a reference criteria. The method can further include performing, with the network monitor, a network inference process partly based on the received discrete side information.

Abstract: Concepts and technologies for providing virtualized network monitoring as a service are provided. In an embodiment, a method can include providing, by a processor of a computer system within a service host network, a network monitoring portal to a user equipment associated with a private network. The method also can include receiving, from the user equipment via the network monitoring portal, access credentials that enable access to the private network. The method can include receiving a selection of a plurality of network monitoring service modules for monitoring the private network, and instantiating a plurality of virtual network monitoring probes that each correspond to at least one of the plurality of network monitoring service modules selected. The method can include injecting the plurality of virtual network monitoring probes within the private network, where the virtual network monitoring probes are activated in response to being injected within the private network.

Abstract: Assignment of network addresses and estimations of flow sizes associated with network nodes can be enhanced. Assignment management component (AMC) partitions a set of network addresses into subsets of network addresses associated with respective classes. For respective virtual machines (VMs), an estimator component estimates a flow size associated with a VM based on parameters associated with the VM. AMC classifies VMs based on threshold flow-size values and respective estimated flow sizes of VMs, and assigns VMs to respective sub-groups of VMs associated with respective subsets of network addresses based on respective classifications of VMs. AMC assigns an available network address of a subset of network addresses associated with a class to a VM of a sub-group associated with that class. Estimated flow sizes and performance metrics also are utilized to make determinations regarding VM placement, traffic management, load balancing, resource allocation, and orchestration in cloud networks.

Abstract: A processing system having at least one processor may obtain, from at least one probe packet, path measurements among pairs of host devices of a plurality of host devices in a packet network comprising a plurality of links, and compose a plurality of linear equations, each linear equation relating one of the path measurements between a respective pair of host devices to at least one link performance indicator for a corresponding one or more of the links in the packet network between the respective pair of host devices. The processing system may then determine a plurality of link performance indicators for the plurality of links via a solution to the plurality of linear equations, the plurality of link performance indicators including the at least one link performance indicators of each of the linear equations, and generate a report comprising at least one of the plurality of link performance indicators.

Abstract: A framework to handle monitoring and automatic fault manifestation in cloud networks. Multiple techniques correlate the logs of different cloud services or generate independent capsules for each component, VM, storage, or transaction. In a first exemplary technique, an authentication token is provided by an authentication service for logs during a period of an event. In a second exemplary technique, a unique instance ID for multiple distinct processes may be created in a data model of notification logs or service logs.

Abstract: A method for solving an under-determined inverse problem or network inference/tomography problem in per-flow size, delay, loss and throughput inference in a computer network, through a system is presented. The method includes the following steps, which are not necessarily in order. First, establishing the computer network having a plurality of nodes wherein the per-flow size, the delay, the loss and the throughput inference are unknown. An original observation or routing matrix determines how flows are appeared on the links and construct the measurements. Next, performing a learning phase to obtain an optimal observation matrix or pseudo-optimal observation matrix. After that, performing a computer controller adaptive measurement and inference phase to estimate the set of unknowns using the measurement quantities, and a function of one of the set consisting of: the optimal observation matrix, the original observation matrix, or both.

Abstract: Concepts and technologies for providing virtualized network monitoring as a service are provided. In an embodiment, a method can include providing, by a processor of a computer system within a service host network, a network monitoring portal to a user equipment associated with a private network. The method also can include receiving, from the user equipment via the network monitoring portal, access credentials that enable access to the private network. The method can include receiving a selection of a plurality of network monitoring service modules for monitoring the private network, and instantiating a plurality of virtual network monitoring probes that each correspond to at least one of the plurality of network monitoring service modules selected. The method can include injecting the plurality of virtual network monitoring probes within the private network, where the virtual network monitoring probes are activated in response to being injected within the private network.

Abstract: Assignment of network addresses and estimations of flow sizes associated with network nodes can be enhanced. Assignment management component (AMC) partitions a set of network addresses into subsets of network addresses associated with respective classes. For respective virtual machines (VMs), an estimator component estimates a flow size associated with a VM based on parameters associated with the VM. AMC classifies VMs based on threshold flow-size values and respective estimated flow sizes of VMs, and assigns VMs to respective sub-groups of VMs associated with respective subsets of network addresses based on respective classifications of VMs. AMC assigns an available network address of a subset of network addresses associated with a class to a VM of a sub-group associated with that class. Estimated flow sizes and performance metrics also are utilized to make determinations regarding VM placement, traffic management, load balancing, resource allocation, and orchestration in cloud networks.

Abstract: In some examples, a method can include receiving, at a network monitor, discrete side information from a first server at a first rack regarding a data flow between the first server and a second server at a rack other than the first rack. The discrete side information can, for example, include an indicator determined by the first server that indicates whether the data flow satisfies a reference criteria. The method can further include performing, with the network monitor, a network inference process partly based on the received discrete side information.

Abstract: A method for solving an under-determined inverse problem or network inference/tomography problem in per-flow size, delay, loss and throughput inference in a computer network, through a system is presented. The method includes the following steps, which are not necessarily in order. First, establishing the computer network having a plurality of nodes wherein the per-flow size, the delay, the loss and the throughput inference are unknown. An original observation or routing matrix determines how flows are appeared on the links and construct the measurements. Next, performing a learning phase to obtain an optimal observation matrix or pseudo-optimal observation matrix. After that, performing a computer controller adaptive measurement and inference phase to estimate the set of unknowns using the measurement quantities, and a function of one of the set consisting of: the optimal observation matrix, the original observation matrix, or both.

Abstract: There is provided a computer-implemented method of solving an under-determined problem. The method includes partitioning the under-determined problem into a plurality of sub-problems of reduced order. The method also includes receiving a plurality of local solutions to the plurality of sub-problems. Additionally, the method includes fusing the local solutions to generate a global solution to the under-determined problem.