Embodiments of the invention are directed to techniques for detecting anomalous values in data streams using forecasting models. In some embodiments, a computer can receive a value of a data stream comprising a plurality of data values, where the received value corresponds to a time interval and previously received values each correspond to a previous time interval. Models can be selected based on the time interval, where each of the models has a different periodicity. For each of the selected models, the computer may generate a score by generating a prediction value based on the model and generating the score based on the prediction value and the received value. A final score can then be generated based on the scores. Next, a score threshold can be generated. If the final score exceeds the score threshold, the computer may generate a notification that indicates that the data value is an anomaly.

A system and method for detecting a communication status includes generating, at an originating virtual tunnel end point (VTEP), a network virtualization using generic routing encapsulation (NVGRE) data packet in accordance with NVGRE protocols. A bidirectional forwarding detection (BFD) data packet is encapsulated in the NVGRE data packet to provide an NVGRE BFD data packet. The NVGRE BFD data packet is transmitted to a terminating VTEP to establish a BFD session over an NVGRE tunnel. A communication status of the NVGRE tunnel is determined for the BFD session based on a reply BFD data packet received from the terminating VTEP in accordance with a receiving time interval.

A method, system and computer program product for data lifecycle management is provided. A method for managing metrics from a monitored system comprises: identifying a fault from the monitored system; identifying from the monitored system, one or more metrics are that are directly related to the fault and one or more metrics that are indirectly related to the fault by virtue of being directly or indirectly related to the one or more directly related metrics; identifying a lifespan condition associated with the fault; adding or changing a lifespan for each of the directly and indirectly related metrics based on the identified lifespan condition; and removing metrics from the storage if their associated lifespans are over.

Novel tools and techniques are provided for implementing error detection in a network, and, more particularly, to methods, systems, and apparatuses for implementing error and/or fault detection in a network and/or media stream and providing options to address the error and/or fault in the network and/or media stream. In various embodiments, a computer might detect an error in a first network and send a notification indicating that the error has occurred. The notification might contain one or more options to address the error in the first network. The computer, a user device, a service provider device, or a content provider device might receive and display the notification containing the one or more options. The computer, the user device, the service provider device, or the content provider device might then select at least one of the one or more options to address the error in the first network.

A method and technique for data lifecycle management includes storing in a memory from a monitored system one or more metrics. A fault from the monitored system is identified and a first metric from the one or more metrics as being related to the fault is identified. A lifespan is assigned to the first metric, and the first metric is removed from the memory if the lifespan is over.

Systems and methods for tracking resources used by triggers such as alarms and timers that are used by mobile applications to schedule tasks and intelligently manipulating the timing of the triggers to optimize usage of resources such as, but not limited to: network, battery, CPU and/or memory are disclosed. In one embodiment, an intelligent alarm manipulator and resource tracker tracks triggers from multiple applications on a mobile device and corresponding use of resources resulting from the triggers on a mobile device. The intelligent alarm manipulator and resource tracker further determines correlations between the triggers and the corresponding use of the resources on the mobile device and manipulates, based on the correlations, timing or frequency of some or all of the triggers to optimize the use of the resources on the mobile device.

Described are systems and methods of monitoring network health and traffic. Monitoring network health and traffic can include sending a request to a compute instance to trigger a response from the compute instance, monitoring, via a network virtualization device, communications from a virtual network interface card (VNIC) associated with the compute instance, storing information indicative of a last received packet by the VNIC, monitoring the stored information indicative of the last received packet to determine a health status of the compute instance associated with the VNIC, updating a table configured to track received responses from the compute instance, and notifying a downstream user of the health status of the compute instance.

A method performed by a node in a telecommunications network for managing faults includes obtaining predictions of faults in the telecommunications network and time intervals in which the faults are predicted to occur. The method then includes determining possible actions that could be performed to address the predicted faults and associated resource usages to perform the possible actions, and selecting actions to perform, from the possible actions, in order to address the predicted faults, based on the predicted time intervals and the determined resource usages.

A method for providing data relating to at least one user device to a data analysis entity. The method includes: collecting, for a plurality of events having impacted on at least one state of the user device in the network, data relating to the at least one impacted state; and supplying, to the data analysis entity, for at least one such state of the user device, at least one statistic obtained for this state by aggregating data relating to this state collected during the collecting step and a part of the data corresponding to an integer X greater than or equal to 1 of events among the most recent events of the plurality of events.

Disclosed are a method and device for providing network analytics information in a wireless communication network. A method for providing network analytics information by means of a network data collection and analytics function (NWDAF) entity in a wireless communication network may comprise the steps of: receiving, from a consumer network function (NF), a request message including information indicating a request time interval related to analytics information; in response to the request message, transmitting, to the consumer NF, a response message including information notifying that real-time analytics information can be provided; and transmitting, to the consumer NF, the analytics information corresponding to the request message within the request time interval.