Abstract: A service tool utilizes a machine learning approach to generate predictions for Quality-of-Service (QoS) parameters at one or more locations within a wireless network. A hybrid machine learning model includes a physics-based model that models wireless signal propagation of the wireless assets in view of detected geospatial features in a region around the wireless assets, and includes a data driven model learned from historical measured operational data associated with the wireless network. A user interface enables a user to enter a location of interest and configure various settings associated with generating the QoS predictions. Prediction results may be presented in a map overlay. The user interface may furthermore be used to resolve issues of subscribed wireless service of existing customers or present recommendations for subscribing to a wireless service based on the QoS predictions, and may directly facilitate enrollment of new customers.

Abstract: Acoustic characterization and mapping of flow from a perforation zone of a well. As a wireline probe containing acoustic sensors moves through the well, the acoustic sensors record acoustic pressure measurements of flow for each perforation in the well casing. The acoustic data is recorded and compiled into a three-dimensional flow model showing flow of hydrocarbons within and/or out of perforation tunnels. The three-dimensional flow models generated can be combined with historical data to form four-dimensional models illustrating flow over time, and both the three and four-dimensional models can be used to determine effectiveness of perforation charges as well as future flow from the well.

Abstract: Pressure-inducing devices and pressure transducers can be used to detect and quantify liquid pools in hydrocarbon fluid pipelines. Pressure fluctuations can be detected by a pressure transducer, where the pressure fluctuations are the response of a pressure-inducing device outputting a pressure signal in a pipe carrying hydrocarbons. Variation in a pipe diameter caused by pooling or deposition can be estimated using an inverse model. The pooling or depositions can be classified by applying a machine-learning model to the pressure fluctuations. The variation in pipe diameter can be converted to an equivalent liquid volume for pooling locations. A pooling or deposition location and volume can be output and used for determining an action on the pipe to remove the pooling or deposition.

Abstract: A host computer inventory system within a provider network detects patterns of launch requests on an individual user account basis. For a customer that cyclically submits similar launch requests, the inventory system may allocate slots in specific host computers consistent with the detected launch pattern so that future attempts to launch the virtual machines will be honored using the pre-allocated hosts.

Abstract: The subject technology relates to synthetic aperture to image leaks and sound sources. Other methods and systems are also disclosed. The subject technology includes drilling a wellbore penetrating a subterranean formation. The subject technology includes logging the wellbore using the stationary acoustic sensor and the moving acoustic sensor of the logging tool to obtain logged measurements, and obtaining an actual acoustic signal associated with a leak source in the wellbore using logged measurement data. The subject technology also includes determining a synthetic acoustic signal indicating an estimated leak source in the wellbore, and determining a correlation between the synthetic acoustic signal and the actual acoustic signal. The subject technology also includes generating a probability map from the determined correlation, in which the probability map indicates a likelihood of the leak source being located at a given location in the wellbore based on the probability map.

Abstract: A method is provided for non-intrusively determining cross-sectional variation of a fluidic channel. The method includes creating a pressure pulse in a fluidic channel using a hammer to strike an external surface of a fluidic channel. The method also includes sensing, by one or more sensors, reflections of the pressure pulse; and obtaining, from the one or more sensors, a measured pressure profile based on the sensed reflections of the pressure pulse. A forward model of cross-sectional variation of the fluidic channel is generated based on a baseline simulation. Using the forward model, a simulated pressure profile is generated. Using the measured pressure profile and the simulated pressure profile, an error is determined. When the error is outside a predetermined threshold, the forward model is updated based on the error. An estimate of cross-sectional variation of the fluidic channel based on the forward model is displayed.

Abstract: A method for detecting an irregularity within a fluidic channel, the method including inducing a pressure pulse within a fluidic channel, the pressure pulse resulting in a pressure fluctuation; detecting the pressure fluctuation at a predetermined location within the fluidic channel; determining a measured pressure profile based on the detected pressure fluctuation; providing a baseline pressure profile relating to a pressure within an unaltered fluidic channel; applying an algorithm to the baseline pressure profile and the measured pressure profile; and outputting an irregularity location and an irregularity effect based on the algorithm.

Abstract: Dynamic pressure wave propagation can be used in pipelines to provide information about the available, unobstructed diameter and any partial or complete blockages in the pipeline. Based on this information, a system can automatically determine optimal times to launch pipeline inspection gauges for cleaning or other purposes. A pipeline inspection gauge is sometimes referred to as a pig. Certain aspects and features include a system that can launch pigs as needed automatically by activating an automatic multiple pig launcher at appropriate times.

Abstract: Dynamic pressure wave propagation can be used in pipelines to provide information about the available, unobstructed diameter and any partial or complete blockages in the pipeline. Based on this information, a system can automatically determine optimal times to launch pipeline inspection gauges for cleaning or other purposes. A pipeline inspection gauge is sometimes referred to as a pig. Certain aspects and features include a system that can launch pigs as needed automatically by activating an automatic multiple pig launcher at appropriate times.

Abstract: The subject technology relates to a process by which data from two downhole loggers (e.g., acoustic transducers), one at each end of a pipeline, can be used to improve the resolution of a pressure pulse system, even for slow valve operating times. For example, the process of the subject technology uses data from two transducers (e.g., acoustic transducers), instead of one transducer typically employed in traditional approaches, thereby leading to increased resolution of the deposit location and thickness. By improving the deposition estimation resolution, locating smaller deposits in a pipeline more accurately can be realized. The improved resolution in deposition estimation computations supports better decision making by providing more detailed measurement and quantification data for use in resolution of deposition buildup.

Abstract: A method is provided for non-intrusively determining cross-sectional variation of a fluidic channel. The method includes creating a pressure pulse in a fluidic channel using a hammer to strike an external surface of a fluidic channel. The method also includes sensing, by one or more sensors, reflections of the pressure pulse; and obtaining, from the one or more sensors, a measured pressure profile based on the sensed reflections of the pressure pulse. A forward model of cross-sectional variation of the fluidic channel is generated based on a baseline simulation. Using the forward model, a simulated pressure profile is generated. Using the measured pressure profile and the simulated pressure profile, an error is determined. When the error is outside a predetermined threshold, the forward model is updated based on the error. An estimate of cross-sectional variation of the fluidic channel based on the forward model is displayed.

Abstract: Dynamic pressure wave propagation can be used in pipelines to provide information about the available, unobstructed diameter and any partial or complete blockages in the pipeline. Certain aspects and features can be used to locate a pipeline inspection gauge (pig) that may be deployed in the pipeline, since in terms of a pressure profile, the pig is no different than any other type of pipeline blockage. Regular pulsing of the pipeline with a pressure wave can further be used to track a blockage over time. A valve or any other suitable device such as an air gun can be used to generate the pressure wave. A time series analysis can be carried out to determine and track the location of the blockage.

Abstract: A passive array of acoustic sensors capture acoustic signals produced by sand movement. The array tool is deployed downhole where it passively listens for acoustic energy generated by sand movement in the well. Once acoustic signals are acquired, model-based frameworks are used to extract single and multiple sensor features from the acoustic signals. The extracted features are used as signatures to detect or classify the production of sand.

Abstract: The subject technology relates to a process by which data from two downhole loggers (e.g., acoustic transducers), one at each end of a pipeline, can be used to improve the resolution of a pressure pulse system, even for slow valve operating times. For example, the process of the subject technology uses data from two transducers (e.g., acoustic transducers), instead of one transducer typically employed in traditional approaches, thereby leading to increased resolution of the deposit location and thickness. By improving the deposition estimation resolution, locating smaller deposits in a pipeline more accurately can be realized. The improved resolution in deposition estimation computations supports better decision making by providing more detailed measurement and quantification data for use in resolution of deposition buildup.

Abstract: Various embodiments include methods and apparatus structured to investigate a structure of multiple strings of pipe in a wellbore and material around the pipes in the wellbore. An array of acoustic receivers can be used to monitor sound energy from the structure and material within and around the structure. The received sound energy can be segregated and coherent signal processing of the received sound energy can be conducted with respect to location. A bond map of the structure and regions around the multiple strings of pipe can be derived from the coherent signal processing. Additional apparatus, systems, and methods can be implemented in a variety of applications.

Abstract: The subject technology relates to estimation of flow rates using acoustics in a subterranean borehole and/or formation. Other methods, systems, and computer-readable media are also disclosed. The subject technology includes drilling a wellbore penetrating a subterranean formation. The subject technology includes logging the wellbore using an acoustic sensing tool to obtain logged measurements, and obtaining acoustic pressure data associated with a leak source in the wellbore using the logged measurements. The subject technology also includes determining a flow rate (volumetric for fluid-based or mass for gas-based) of the leak source from the acoustic pressure data, and determining an area of the leak source from the determined flow rate. The subject technology also includes generating and providing, for display, a representation of the leak source using the flow rate and the area of the leak source.

Abstract: Methods and apparatus for reconfiguring hosts in provider network environments in which hosts are evaluated to determine if steps of a full rebuild can be skipped. The hosts may implement slots of different types for virtual machines (VMs). Upon detecting that slots of a particular type are needed, a host that implements slots of another type may be selected for reconfiguration. The host may be evaluated to determine if one or more steps of a full rebuild can be skipped. The host may then be reconfigured to implement slots of the target type according to results of the evaluation. In at least some reconfigurations, at least one step of a full rebuild procedure is not performed for the respective host. Results of previous reconfigurations may be fed back into the evaluation process and used as one of the criteria for determining if steps can be skipped.

Abstract: A method is provided for non-intrusively determining cross-sectional variation of a fluidic channel. The method includes obtaining, from one or more sensors, a measured pressure profile based on at least one pressure pulse induced in a fluidic channel. A forward model of cross-sectional variation of the fluidic channel is generated. Using the forward model, a simulated pressure profile is generated. Using the measured pressure profile and the simulated pressure profile, an error is determined. When the error is outside a predetermined threshold, the forward model is updated based on the error.

Abstract: A method for detecting an irregularity within a fluidic channel, the method including inducing a pressure pulse within a fluidic channel, the pressure pulse resulting in a pressure fluctuation; detecting the pressure fluctuation at a predetermined location within the fluidic channel; determining a measured pressure profile based on the detected pressure fluctuation; providing a baseline pressure profile relating to a pressure within an unaltered fluidic channel; applying an algorithm to the baseline pressure profile and the measured pressure profile; and outputting an irregularity location and an irregularity effect based on the algorithm.

Abstract: A method is provided for non-intrusively determining deposits in a fluidic channel. The method includes obtaining ,from one or more sensors, a measured pressure profile based on at least one pressure pulse induced in a fluidic channel; generating a forward model of deposits in the fluidic channel; and generating, using the forward model, a simulated pressure profile. An error is calculated using the measured pressure profile and the simulated pressure profile, and when the error is outside a predetermined threshold, the forward model is updated. The updated forward model is adjusted based on the error.