Abstract: The disclosed technology is directed towards automatically detecting failure states and the cause of the failure. For a network, the technology collects status messages from equipment and customers into batches as they occur. The technology groups and aggregates messages, then transforms the aggregations to the frequency domain. Anomalies induce detectable changes in the particle distribution of a trained particle filter, from which an anomalous spectrogram is generated. The status messages of each device are iteratively removed from the larger set of messages, resulting in reduced subsets that are each aggregated, transformed into a modified spectrogram and compared against the anomalous spectrogram to obtain a distance score. The distance score for each device is used to rank the devices with respect to being the cause of the failure.

Abstract: A method performed by a processing system including at least one processor includes defining a proposal for a proposed machine learning model, identifying an existing machine learning model, where the existing machine learning model shares a similarity with the proposed machine learning model, evaluating a fitness of the existing machine learning model for reuse in building the proposed machine learning model, building a new machine learning model that is consistent with the proposal for the proposed machine learning model by reusing a portion of the existing machine learning model, and monitoring a performance of the new machine learning model in a deployment environment.

Abstract: A method performed by a processing system including at least one processor includes monitoring interactions of a human user with a platform for building machine learning models, where the human user is using the platform to build a new machine learning model, detecting, within the interactions, an event that triggers a suggestion feature, performing a search of a data source for existing data from existing machine learning models which can be reused to build the new machine learning model, using information about the event, presenting a suggestion to the human user to reuse a portion of the existing data discovered in the search in the new machine learning model, receiving a user feedback in response to the suggestion, and generating an updated suggestion in response to the user feedback.

Abstract: Facilitating striated random restart during routing of resources using a heuristic approach is provided herein. Operations of a system can include, separating objects of a group of objects into a first grouping and a second grouping, assigning first objects of the first grouping and second objects of the second grouping to respective resource elements, resulting in a first classification. A search space is enabled and includes, at respective iterations of a group of iterations, selecting a defined priority level, removing third objects of the second grouping that do not satisfy the defined priority level from the first classification, and assigning the third objects to the respective resource elements, resulting in a second classification. The first objects and the second objects, other than the third objects, remain assigned according to the first classification. According to an implementation, the schedule search reduces a search space of the group of objects.

Abstract: Methods, systems, and apparatuses may provide for receiving an indication of a set of sites in a geographical area, wherein the set of sites comprises a plurality of spare distribution sites; receiving an indication of a respective physical routing distance of each site of the geographical area; and determining a centrality value for each respective site of the plurality of candidate distribution sites of the geographic area, wherein the centrality value is based on the respective physical routing distance of each site of the geographical area.

Abstract: The disclosed technology is directed towards automatically detecting failure states and the cause of the failure. For a network, the technology collects status messages from equipment and customers into batches as they occur. The technology groups and aggregates messages, then transforms the aggregations to the frequency domain. Anomalies induce detectable changes in the particle distribution of a trained particle filter, from which an anomalous spectrogram is generated. The status messages of each device are iteratively removed from the larger set of messages, resulting in reduced subsets that are each aggregated, transformed into a modified spectrogram and compared against the anomalous spectrogram to obtain a distance score. The distance score for each device is used to rank the devices with respect to being the cause of the failure.

Abstract: Facilitating localization of faults in core, edge, and access networks is provided herein. Operations of a system can include establishing a restoration of a group of communication paths of a network infrastructure that includes network nodes between a root network node and a leaf network node. A fault is determined to exist in the group of communication paths between the root network node and the leaf network node. The operations also can include determining that a defined network node of the network nodes is a source of the fault based on respective positions of user equipment experiencing the fault relative to the defined network node. Further, the operations can include removing the fault based on controlling a functionality of the defined network node.

Abstract: Devices, non-transitory computer-readable media and methods for providing a haptic signal based upon a detection of an object are disclosed. For example, the processor of a device may transmit a first ultrasonic signal via an ultrasonic emitter and detect an object based upon a receiving of a reflected signal via an ultrasonic detector, where the reflected signal comprises a reflection of the first ultrasonic signal from the object. The processor may further monitor for a second ultrasonic signal via the ultrasonic detector. The device may be associated with a user, and the second ultrasonic signal may be associated with a teammate of the user. The processor may also select whether to provide an instruction to a haptic actuator when the object is detected, based upon whether the second ultrasonic signal is received via the ultrasonic detector.

Abstract: A processing system including at least one processor may collect a first set of time series features relating to requests for a content item at a content distribution node in a communication network, generate a first prediction model based upon the first set of time series features to predict levels of demand for the content item at the content distribution node at future time periods, identify, via the first prediction model, a first time period of the future time periods when a predicted level of demand for the content item exceeds a threshold level of demand, identify a second time period of the future time periods when a predicted level of utilization of the communication network is below a threshold level of utilization, the second time period being prior to the first time period, and transfer the content item to the content distribution node in the second time period.

Abstract: Architectures and techniques are presented that improve or optimize (e.g., within a factor of optimal) spare equipment allocation. Efficient spare equipment allocation is capable of satisfying many orthogonal or even conflicting goals such as reducing the cost of purchase and storage of the spare equipment while simultaneously seeking to reduce downtime due to failed equipment resulting from too sparse coverage by the spare equipment. A sparing procedure can identify depot nodes that are indicative of depot locations where a spare device is to be stored.

Abstract: Devices, non-transitory computer-readable media and methods for providing a haptic signal based upon a detection of an object are disclosed. For example, the processor of a device may transmit a first ultrasonic signal via an ultrasonic emitter and detect an object based upon a receiving of a reflected signal via an ultrasonic detector, where the reflected signal comprises a reflection of the first ultrasonic signal from the object. The processor may further monitor for a second ultrasonic signal via the ultrasonic detector. The device may be associated with a user, and the second ultrasonic signal may be associated with a teammate of the user. The processor may also select whether to provide an instruction to a haptic actuator when the object is detected, based upon whether the second ultrasonic signal is received via the ultrasonic detector.

Abstract: A processing system including at least one processor may collect a first set of time series features relating to requests for a content item at a content distribution node in a communication network, generate a first prediction model based upon the first set of time series features to predict levels of demand for the content item at the content distribution node at future time periods, identify, via the first prediction model, a first time period of the future time periods when a predicted level of demand for the content item exceeds a threshold level of demand, identify a second time period of the future time periods when a predicted level of utilization of the communication network is below a threshold level of utilization, the second time period being prior to the first time period, and transfer the content item to the content distribution node in the second time period.

Abstract: A method for generating a multi-layer predictive model includes collecting historical observable data from one or more pieces of equipment of a same type, wherein the historical observable data is collected at different hierarchical levels of the one or more pieces of equipment; collecting operational state indications of the pieces of equipment corresponding to the collected historical observable data; generating, from the collected historical observable data, a set of operational state models, wherein each operational state model corresponds to one of the different hierarchical levels; and generating, from outputs of the set of operational state models, a top-level operational model for the piece of equipment. The top-level operational model is operable to determine maintenance and replacement timing for the piece of equipment.

Abstract: A method for generating a multi-layer predictive model includes collecting historical observable data from one or more pieces of equipment of a same type, wherein the historical observable data is collected at different hierarchical levels of the one or more pieces of equipment; collecting operational state indications of the pieces of equipment corresponding to the collected historical observable data; generating, from the collected historical observable data, a set of operational state models, wherein each operational state model corresponds to one of the different hierarchical levels; and generating, from outputs of the set of operational state models, a top-level operational model for the piece of equipment. The top-level operational model is operable to determine maintenance and replacement timing for the piece of equipment.

Abstract: A processing system including at least one processor may collect a first set of time series features relating to requests for a content item at a content distribution node in a communication network, generate a first prediction model based upon the first set of time series features to predict levels of demand for the content item at the content distribution node at future time periods, identify, via the first prediction model, a first time period of the future time periods when a predicted level of demand for the content item exceeds a threshold level of demand, identify a second time period of the future time periods when a predicted level of utilization of the communication network is below a threshold level of utilization, the second time period being prior to the first time period, and transfer the content item to the content distribution node in the second time period.

Abstract: A processing system may obtain historical job feature, network plant feature, and calendar feature data associated with customer premises installation jobs of a telecommunication network which include a dispatch of a customer premises technician. A plurality of the customer premises installation jobs may further include a dispatch of a network-based technician.

Abstract: A processing system including at least one processor may collect a first set of time series features relating to requests for a content item at a content distribution node in a communication network, generate a first prediction model based upon the first set of time series features to predict levels of demand for the content item at the content distribution node at future time periods, identify, via the first prediction model, a first time period of the future time periods when a predicted level of demand for the content item exceeds a threshold level of demand, identify a second time period of the future time periods when a predicted level of utilization of the communication network is below a threshold level of utilization, the second time period being prior to the first time period, and transfer the content item to the content distribution node in the second time period.

Abstract: A processing system may obtain a loan graph including a travel cost for network technicians between adjacent work centers of a telecommunication network, each network technician assigned to a work center, and obtain work quantities for each work center for a day, at least a first work center having excess work for network technicians assigned to the first work center. The processing system may select, in accordance with an objective function, moves by a first subset of network technicians comprising moves to adjacent work centers from the work centers to which the first subset is assigned, select in accordance with the objective function, moves by a second subset of network technicians comprising moves to adjacent work centers from work centers to which the second subset is assigned, and generate a work plan for the day for the network technicians in accordance with the moves.

Abstract: A processing system including at least one processor may collect a first set of time series features relating to requests for a content item at a content distribution node in a communication network, generate a first prediction model based upon the first set of time series features to predict levels of demand for the content item at the content distribution node at future time periods, identify, via the first prediction model, a first time period of the future time periods when a predicted level of demand for the content item exceeds a threshold level of demand, identify a second time period of the future time periods when a predicted level of utilization of the communication network is below a threshold level of utilization, the second time period being prior to the first time period, and transfer the content item to the content distribution node in the second time period.

Abstract: A method for generating a multi-layer predictive model includes collecting historical observable data from one or more pieces of equipment of a same type, wherein the historical observable data is collected at different hierarchical levels of the one or more pieces of equipment; collecting operational state indications of the pieces of equipment corresponding to the collected historical observable data; generating, from the collected historical observable data, a set of operational state models, wherein each operational state model corresponds to one of the different hierarchical levels; and generating, from outputs of the set of operational state models, a top-level operational model for the piece of equipment. The top-level operational model is operable to determine maintenance and replacement timing for the piece of equipment.