Methods, devices, and systems for distributed monitoring based adaptive diagnosis of power anomalies in a power network
Methods, devices and systems for detecting an anomaly in a power network are described. A method for detecting an anomaly in a power network includes determining a baseline power usage in the power network, receiving data indicative of an active power usage in the power network, detecting an anomaly based on a difference between the baseline power usage and the active power usage, isolating a fault for an element in the power network, responsive to detecting the anomaly, and transmitting fault isolation information indicating the fault to a user device. Related devices and systems may perform operations of the method described herein.
1. A method for detecting an anomaly in a power network, the method comprising: determining a baseline power usage in the power network; receiving data indicative of an active power usage in the power network; detecting an anomaly based on a difference between the baseline power usage and the active power usage; isolating a fault for an element in the power network, responsive to detecting the anomaly; transmitting fault isolation information indicating the fault to a user device; determining a feedback based on the anomaly; and modifying the baseline power usage based on the feedback, wherein the element is at a lower level hierarchy of the power network than the anomaly,
wherein isolating the fault comprises: identifying, with a main anomaly detection circuit, a main anomaly in a first element of a main meter hierarchy of the power network comprising a plurality of first elements; searching, with a lower anomaly detection circuit, for a lower anomaly in a plurality of second elements of the lower level hierarchy that is lower than the main meter hierarchy, wherein the plurality of second elements are associated with the first element; and identifying, with the lower anomaly detection circuit, a second element of the plurality of second elements associated with the lower anomaly,
wherein determining the feedback based on the anomaly comprises: generating data related to the active power usage and the anomaly; and triggering generation of the feedback based on the data related to the active power usage and the anomaly.
2. The method of claim 1 , wherein the lower anomaly comprises a first lower anomaly, and wherein the lower level hierarchy comprises a first lower level hierarchy, the method further comprising: searching for a second lower anomaly in a plurality of third elements of a second lower level hierarchy, wherein the plurality of third elements are associated with the second element; and identifying a third element of the plurality of third elements associated with the second lower anomaly, wherein the second lower level hierarchy is at a lower level in the power network than the first lower level hierarchy.
3. The method of claim 1 , wherein the detecting the anomaly comprises: identifying an outlier in the active power usage, responsive to the active power usage being outside of a predetermined range of the baseline power usage; and determining that the outlier comprises the anomaly in the power network.
4. The method of claim 1 , wherein determining the feedback based on the anomaly comprises: providing information related to the anomaly to a user of the power network; receiving an input from the user; and determining the feedback based on the input from the user.
5. The method of claim 1 , wherein determining the feedback based on the anomaly comprises: monitoring the active power usage over a time period; determining a shift in properties of the active power usage over the time period; and determining the feedback based on the shift in properties of the active power usage over the time period.
6. The method of claim 1 , wherein the element comprises a building, a section, a machine, or a component.
7. The method of claim 1 , further comprising: determining an anomaly type and/or severity of the anomaly, wherein the anomaly type is associated with a repair action taken, responsive to the isolating the fault, and wherein the severity of the anomaly is obtained from a database comprising historical power usage data of the power network.
8. The method of claim 1 , wherein the detecting the anomaly based on the difference between the baseline power usage and the active power usage comprises: predicting expected power usage in a future time period based on historical power usage data; generating an uncertainty bound for the expected power usage that was predicted; and detecting the anomaly, responsive to the active power usage being outside of the uncertainty bound.
9. The method of claim 8 , wherein the active power usage comprises a first active power usage in a first time period, the method further comprising: determining a second active power usage in a second time period that is after the first time period; and modifying the baseline power usage, responsive to both the first active power usage and the second active power usage being outside of the uncertainty bound.
10. The method of claim 8 , wherein the expected power usage is predicted based on determining a temporal pattern in the historical power usage data.
11. The method of claim 1 , further comprising: determining if the fault is related to a previous anomaly that was reported; and reporting the fault when the fault is not related to the previous anomaly that was reported.