System and method for predictive foliage impingement and wildfire management using generative adversarial network
An exemplary system and method are disclosed for identifying anomalies relating to distribution power line disturbances and faults indicative of foliage impingement and potential equipment failure. The exemplary system and method employ neural network-based models such as generative adversarial networks models that can continuously monitor for electrical-signal anomalies to locate faults, predict power outages and safety hazards, thereby reducing the likelihood of wildfires. The exemplary system and method can beneficially learn and update its neural network models in a continuous and unsupervised manner using a live stream of sensor inputs.
1. A method to predict foliage impingement by detecting an anomalous event, the method comprising:
providing a first classifier of a first trained neural network of a first generative adversarial-based network (GAN-based network), wherein the first GAN-based network is continuously configured using (i) a first power line data set acquired by a first sensor equipment operatively placed at a low voltage-side at a first location of a utility power distribution circuit and (ii) first imputed data generated by a first generator of the first GAN-based network, wherein the first imputed data imitates data associated with an abnormal power line event;
providing a second classifier of a second trained neural network of a second GAN-based network, wherein the second GAN-based network is continuously configured using (i) a second power line data set comprising voltage, current, and/or power factor acquired by a second sensor equipment operatively placed at a low voltage-side at a second location of the utility power distribution circuit and (ii) second imputed data generated by a second generator of the second GAN-based network, wherein the second imputed data imitates data associated with an abnormal power line event;
determining, by a global GAN-based network based on a first signature received from the first GAN-based network and a second signature received from the second GAN-based network, a predicted output indicative of a presence of the anomalous event; and
outputting, by one or more processors, via a fault detection location operator using the predicted output, a location indicator indicating a distance to a foliage impingement along the utility power distribution circuit from either the first sensor equipment or the second sensor equipment;
wherein the location indicator is used to estimate foliage impingement at a location in the utility power distribution circuit.
2. The method of claim 1 further comprising:
estimating, by the one or more processors, on an ongoing basis, via a global GAN-based network, the location indicator using the predicted output.
3. The method of claim 1 , further comprising:
identifying the foliage impingement at the location in the utility power distribution circuit by triangulating the location using the first signature and the second signature, wherein the triangulation is constrained to a physical layout or map of the utility power distribution circuit.
4. The method of claim 1 , wherein the location indicator is used to prioritize maintenance, direct maintenance crew to the location for servicing, and guide foliage management.
5. The method of claim 1 , further comprising:
obtaining, by one or more processors of the first sensor equipment, on a continuous ongoing basis, power line data comprising voltage, current, and/or power factor from sensors of the first sensor equipment; and
retraining, by the one or more processors, on an ongoing basis, via reinforcement learning operations, the first GAN-based network using the power line data.
6. The method of claim 1 , wherein the first classifier of the first trained neural network of the first GAN-based network is trained from 3-phase electrical data.
7. The method of claim 1 , wherein the first classifier of the first trained neural network of the first GAN-based network is trained from 3-phase electrical data evaluated through an encapsulation network, wherein an output of the encapsulation network is provided as input to the first GAN-based network.
8. The method of claim 1 , wherein the first classifier of the first trained neural network of the first GAN-based network is trained from 3-phase electrical data evaluated through a state-space module that frames the 3-phase electrical data in three-dimensional data space.
9. The method of claim 8 , wherein the state-space module is configured to perform a fractional calculus operation using the 3-phase electrical data to generate additional inputs for the first GAN-based network.
10. The method of claim 5 , further comprising:
transmitting, by the one or more processors, the power line data to a storage area network (SAN) when the anomalous event is detected by the first classifier.
11. The method of claim 1 , wherein the first classifier of the first trained neural network can classify abnormal power line events that are correlated and prioritized with foliage interaction and/or fire risk.
12. The method of claim 1 , wherein the first classifier of the first trained neural network can detect foliage signatures type, locations of voltage, faults, drops, or surges/spikes on a secondary transformer in the utility power distribution circuit.
13. The method of claim 1 , wherein the first classifier of the first trained neural network is further configured to output a second output associated with at least one equipment failure, line sag, and transformer failure in the utility power distribution circuit.
14. The method of claim 1 , wherein the first power line data set and the second sensor equipment are further used to determine and/or monitor power flow efficiency in the utility power distribution circuit.
15. The method of claim 5 , wherein the first power line data set and the second sensor equipment are further used to determine and/or monitor power factors across multiple phases at the first sensor equipment and/or the second sensor equipment.
16. A system, comprising:
one or more processors; and
a memory operatively coupled to the one or more processors, the memory having instructions stored thereon, wherein execution of the instructions by the one or more processors cause the one or more processors to:
provide a first classifier of a first trained neural network of a first GAN-based network, wherein the first GAN-based network is continuously configured using (i) a first power line data set acquired by a first sensor equipment operatively placed at a low voltage-side at a first location of a utility power distribution circuit and (ii) first imputed data generated by a first generator of the first GAN-based network, wherein the first imputed data imitates data associated with an abnormal power line event;
provide a second classifier of a second trained neural network of a second GAN-based network, wherein the second GAN-based network is continuously configured using (i) a second power line data set comprising voltage, current, and/or power factor acquired by a second sensor equipment operatively placed at a low voltage-side at a second location of the utility power distribution circuit and (ii) second imputed data generated by a second generator of the second GAN-based network, wherein the second imputed data imitates data associated with an abnormal power line event;
determine, using on a global GAN-based network, based on a first signature received from the first GAN-based network and a second signature received from the second GAN-based network, a predicted output indicative of a presence of an anomalous event; and
output, via a fault detection location operator using the predicted output, a location indicator indicating a distance to a foliage impingement along the utility power distribution circuit from either the first sensor equipment or the second sensor equipment;
wherein the location indicator is used to predict foliage impingement at the location in the utility power distribution circuit.
17. The system of claim 16 , wherein execution of the instructions by the one or more processors causes the one or more processors to:
estimate, on an ongoing basis, via a global GAN-based network, the location indicator using the predicted output.
18. The system of claim 16 , wherein execution of the instructions by the one or more processors cause the one or more processors to:
identify the foliage impingement at the location in the utility power distribution circuit by triangulating the location using the first signature and the second signature, wherein the triangulation is constrained to a physical layout or map of the utility power distribution circuit.
19. A non-transitory computer-readable medium having instructions stored thereon, wherein execution of the instructions by one or more processors of a remote-server or cloud-based analytical engine cause the one or more processors to:
provide a first classifier of a first trained neural network of a first GAN-based network, wherein the first GAN-based network is continuously configured using (i) a first power line data set acquired by a first sensor equipment operatively placed at a low voltage-side at a first location of a utility power distribution circuit and (ii) first imputed data generated by a first generator of the first GAN-based network, wherein the first imputed data imitates data associated with an abnormal power line event;
provide a second classifier of a second trained neural network of a second GAN-based network, wherein the second GAN-based network is continuously configured using (i) a second power line data set comprising voltage, current, and/or power factor acquired by a second sensor equipment operatively placed at a low voltage-side at a second location of the utility power distribution circuit and (ii) second imputed data generated by a second generator of the second GAN-based network, wherein the second imputed data imitates data associated with an abnormal power line event;
determine, using a global GAN-based network, based on a first signature received from the first GAN-based network and a second signature received from the second GAN-based network, a predicted output indicative of a presence of an anomalous event; and
output, via a fault detection location operator using the predicted output, a location indicator indicating a distance to a foliage impingement along the utility power distribution circuit from either the first sensor equipment or the second sensor equipment;
wherein the location indicator is used to predict foliage impingement at the location in the utility power distribution circuit.
20. The non-transitory computer-readable medium of claim 19 , wherein execution of the instructions by the one or more processors causes the one or more processors to:
estimate, on an ongoing basis, via a global GAN-based network, the location indicator using the predicted output.