Abstract: One example includes a power generator protection system. The system includes a circuit breaker configured, when triggered, to provide an open circuit in a power line configured to conduct a current between a power grid point-of-interconnect (POI) and a power generator system. The system also includes a programmable controller configured to monitor the current and to generate a dynamic current threshold based on the current. The programmable controller can further be configured to compare the current with the dynamic current threshold and to trigger the circuit breaker based on a difference of the current relative to the dynamic current threshold to set an arc flash incident energy level of the power generator system at or below a predetermined safety level.

Abstract: Large-scale unmanned monitoring devices, such as unmanned aerial vehicles (UAV), drones or rovers capable of operating within environmental conditions not suitable for human personnel and lesser capable monitoring devices may inspect system components within an area of interest (AOI) such an electric power distribution system including generation, transmission, and distribution elements for autonomous detection of damage to the components. The large-scale unmanned monitoring devices may inspect the system components while the environmental conditions are occurring. Work orders for repairing the damage are autonomously generated and resources identified within the work orders are autonomously provisioned.

Abstract: Systems and methods to label images for inclusion into a machine learning image recognition training data set. A coded labeling definition is defined. A set of digital images is collected that includes images of different types of piece of equipment. A digital image is presented that includes an image of a particular piece of equipment. A received numeric code corresponding to the particular piece of equipment within the present image is received. The received numeric code is associated with the present image and the present image is stored in association with the received numeric code into a machine learning image recognition data set. A machine learning image recognition is trained based on the machine learning image recognition data set to automatically associate unlabeled images with the respective numeric code that corresponds to the particular piece of equipment in the unlabeled image.

Abstract: A system and method that enable analysis and visualization of disparate data to provide actionable insight regarding a smart meter network are disclosed. In some implementations, smart meter grid dashboard functionality may provide an improved and integrated data view and enable dynamic investigations and actions based on smart meter analytics. A method of aggregating and displaying data relevant to operations of an AMI network may provide actionable insight into operation of the network, predict failures, and recommend remedial actions.

Abstract: A power distribution system adapted for high current fault management during a fault event utilizes reclosing switches configured for a quick-slow-quick reclosing sequence in which the reclosing switch initially responds to the fault condition by tripping open, and then after a delay recloses for a first duration of time (slow) prior to tripping open. After another delay, the reclosing switch recloses for a second duration of time (quick) that is less than the first duration of time prior to tripping open for an indefinite interval. When installed in new segments or retrofitted in place of a fuse, reclosing switches configured with quick-slow-quick reclose timing allows for reduction of downstream customer outages, reduced I2T exposure for elements upstream of a fault event and a reduction in the duration of voltage sags experienced by customers during fault events while allowing for improved fault management configurations of the power distribution system.

Abstract: A service ticket control can close an open service ticket for a field service visit to resolve a power outage experienced at a given customer premises. The open service ticket can be closed in response to usage data from a given smart meter at the customer premises indicating that the customer premises is consuming power above a predetermined threshold level. The service ticket control closes the open service ticket prior to a service crew assigned the service ticket arriving at the given customer premises.

Abstract: A system and method is disclosed for using AMI smart meter messaging types and data mining decision trees to determine if local equipment failure is present. The system and method may be used to predict impending failure based upon smart meter message behaviors and to create proactive investigation tickets. The predictions models may be generated from a database of smart meter messaging and customer outage reports. The system and method can be applied to detect failures of higher level device equipment and may be incorporated into customer service processes. The system and method may also be used to determine customer owned equipment failures for referral to electricians.

Abstract: One example includes a power relay system. The system includes a circuit breaker configured, when triggered, to provide an open circuit in a power line configured to conduct a current between a power grid point-of-interconnect (POI) and a power generator system. The system also includes a power controller configured to monitor the current and to generate a dynamic current threshold based on the current, the power controller being further configured to compare the current with the dynamic current threshold and to trigger the circuit breaker based on a difference of the current relative to the dynamic current threshold to set an arc flash incident energy level of the power generator system to less than or equal to a predetermined safety level.

Abstract: Systems and methods to manage a crowd sourced observation program. A plurality of participant cameras are determined where each participant camera is within a threshold distance of a geographic location for observation. An accepting participant camera is selected. Based on selecting the accepting participant camera, a cancellation of the offer is sent to each participant in the plurality of participants other than the accepting participant. Based on selecting the accepting participant camera, the accepting participant camera is instructed to go to the geographic location for image capture. The image capture is received.

Abstract: Systems and methods for deterring avian species from approaching a sensitive area. A determination is made that a bird is approaching a sensitive area. A predefined flight path is selected from a plurality of predefined flight paths based on the determination that the bird is approaching the sensitive area. Each of the predefined flight paths of the plurality of predefined flight paths is configured to avoid objects within the sensitive area. An unmanned aerial vehicle is instructed to traverse the predefined flight path that has been selected.

Abstract: A brief case sized battery pack for powering large power tools for use in portable applications. Large cordless power tools, such as torque guns, are often used to fasten very large nuts on wind turbines. AC power for charging may not be available depending on the location within the wind turbine. The portable rechargeable battery pack has several battery elements, each element able to power the cordless power tool. Using a selectable switch, a user manually selects the battery element to power the cordless power tool. The manually operable switch electrically connects to enable one of the first battery elements to be electrically coupled to the at least one DC output electrical connector while the DC output of a battery charger simultaneously charges all the battery elements. In one example, the DC output connector provides at least four positive DC leads all at different voltages plus ground.

Abstract: Unmanned monitoring devices, such as unmanned aerial vehicles (UAV), drones or rovers may survey an area of interest (AOI) such an electric power distribution system including generation, transmission, and distribution elements to automatically determine components in the AOI to be monitored. Types, placements locations, and pathways taken by other unmanned monitoring devices to facilitate the monitoring of the components of the AOI are also automatically determined.

Abstract: Systems and methods to combine line fault location probabilities. A first and second location probability distribution are received for a location of an line fault along an electrical line based upon at least electrical current measurements reported by a first electrical current monitor at a first location and at least a second electrical current measurements reported by a second electrical current monitor at a second location. The second electrical current measurements being made within a time interval of the first electrical current measurements. A composite location probability distribution is determined for the location of the line fault along the electrical line based on an algorithm processing the first location probability distribution and the second location probability distribution. The composite location probability distribution is provided.

Abstract: Systems and methods to combine line fault location probabilities. A first and second location probability distribution are received for a location of an line fault along an electrical line based upon at least electrical current measurements reported by a first electrical current monitor at a first location and at least a second electrical current measurements reported by a second electrical current monitor at a second location. The second electrical current measurements being made within a time interval of the first electrical current measurements. A composite location probability distribution is determined for the location of the line fault along the electrical line based on an algorithm processing the first location probability distribution and the second location probability distribution. The composite location probability distribution is provided.

Abstract: Systems and methods to detect Automatic Lateral Switch operations. Power down reports indicating power went down at a subset of reporting power meters during a time duration is received, at a monitoring facility. The plurality of reporting power meters receive power from a lateral power feed receiving power through an Automatic Lateral Switch. A respective power restore report indicating power is restored at the respective reporting power meter is received within a recovery time duration after receiving each respective power down report. Based on receiving the respective power restore report within the recovery time duration, an occurrence of an Automatic Lateral Switch operation which includes operating contacts providing power to the lateral power feed by the contacts opening and remaining reclosed is determined. Based on determining the Automatic Lateral Switch operation, an indication of the Automatic Lateral Switch operation is stored into a database system.

Abstract: An energy management system receives voltage and current data from each of a plurality of fault indicators. Each fault indicator is positioned on a powerline of a power distribution system immediately upstream of a respective one of a plurality of disconnect switches. The energy management system also determines a status of each disconnect switch based on the voltage and current from the plurality of fault indicators.

Abstract: Systems and methods to provide composite fault maps. A first event report is received from a system indicating a first set of location probability distributions of a first event. A second event report is received from a second system that is a different type than the first system indicating a second set of location probability distributions of a second event that is different from the first event. Based upon data in the received reports, the first event is determined to be associated with the second event. A composite fault map is determined that includes composite location likelihood values for the first event and the second event, the composite fault map being determined based on assembling the first set of location probability distributions and the second set of location probability distributions. The the composite fault map is provided to a different process.

Abstract: An outage estimator that generates outage data characterizing a power state for a number of premises serviced by a power grid, the number of premises comprising a first set of the premises and a second set of the premises different from the first set of the premises. The generating includes executing a first stage analysis that estimates the power state for the first set of the premises associated with a set of transformers coupled to a first feeder in the power grid in response to detecting an event message from a smart meter associated with the first set of the premises. The generating also includes executing a second stage analysis that estimates the power state for a second set of premises associated with a set of laterals coupled to a second feeder in the power grid in response to detecting that no event messages have been provided from smart meters associated with the second set of the premises within a predetermined amount of time.

Abstract: Systems and methods to determine events that are associated with one another. Reports of a first, second, and third events are received. Based upon data associated with the first and second event, a determination is made that the first event is associated with the second event. Based upon data associated with the first event and the third event, a determination is made that the first event is not associated with the third event. A presentation is created indicating that the first and second events are related to the second event and that the first and third events are not related. The presentation is presented to a different process.