System and method for distributed, secure, power grid data collection, consensual voting analysis, and situational awareness and anomaly detection
A system and method for data collection and aggregation using a distributed network of communications enabled sensors connected to another primary network to achieve a secondary out-of-band monitoring perspective, for example, in power grids. The data collection system includes an aggregation and processing server configured to collect data from a variety of sensors adjacent to the monitored network each sensor includes secondary power such that it can continue data transmission even during power grid outages. The data collection system includes a method for secure real-time data ingest, machine learning enabled analysis, risk assessment, and anomaly detection on a broad geographic scale irrespective of isolated network boundaries.
1. A method, comprising:
receiving, via a communications network from a plurality of network nodes of the communications network, a first set of data indicating a metric associated with a power grid, the communications network configured to provide a communication service to end devices at locations serviced by the power grid, wherein the plurality of network nodes use the power grid as a primary source of power;
determining a normalized range for the metric associated with the power grid based at least in part on the first set of data;
receiving, via the communications network from the plurality of network nodes of the communications network, a second set of data indicating the metric associated with the power grid; and
generating a third set of data indicating a relationship between the second set of data and the normalized range for the metric;
identifying a fourth set of data comprising an ordering, for each of the plurality of network nodes, of a set of quantized values according to values determined from the second set of data corresponding to the each of the plurality of network nodes; and
determining a consensus value from the ordered sets of quantized values associated with the plurality of network nodes, wherein the third set of data comprises the consensus value.
2. The method of claim 1 , wherein the values determined from the second set of data comprise differences between the second set of data and the normalized range for the metric.
3. The method of claim 1 , wherein determining the consensus value comprises:
weighting one or more of the quantized values of the ordered set of quantized values for one or more of the plurality of network nodes based at least in part on a function of respective values of the second set of data for the one or more of the plurality of network nodes, a function of a difference between the ordered set of quantized values for a previous determination of the consensus value and the previously determined consensus value, an amount of traffic communicated via the one or more of the plurality of network nodes, a connectivity metric for the one or more of the plurality of network nodes, a relative network impact of unavailability of the one or more of the plurality of network nodes, or a combination thereof.
4. The method of claim 1 , wherein identifying the fourth set of data comprises:
identifying the set of quantized values for the metric associated with the power grid; and
ordering the set of quantized values for each of the plurality of network nodes according to the values of the third set of data to generate the fourth set of data.
5. The method of claim 1 , wherein the second set of data received from the plurality of network nodes comprises the fourth set of data.
6. The method of claim 1 , further comprising:
triggering an alert based at least in part on determining that the consensus value satisfies a threshold.
7. The method of claim 1 , further comprising:
identifying a fifth set of data comprising an ordering, for each of a second plurality of network nodes, of a second set of quantized values according to values determined from the second set of data corresponding to the each of the plurality of network nodes; and
determining a second consensus value from the ordered second sets of quantized values associated with the second plurality of network nodes, wherein the third set of data is based at least in part on a comparison of the consensus value and the second consensus value.
8. The method of claim 1 , wherein the metric associated with the power grid is a first metric associated with the power grid, the method further comprising:
receiving, via the communications network from the plurality of network nodes of the communications network, a fourth set of data indicating a second metric associated with the power grid different than the first metric associated with the power grid; and
ranking the second set of data and the fourth set of data based at least in part on a magnitude of a difference between respective values of the second set of data and the fourth set of data and respective normalized ranges of the first metric and the second metric, wherein the third set of data is based at least in part on the ranking.
9. The method of claim 8 , wherein:
generating the third set of data comprises accumulating the rankings of the second set of data and the fourth set of data.
10. The method of claim 9 , wherein:
generating the third set of data comprises weighting the rankings of the second set of data and the fourth set of data.
11. The method of claim 10 , wherein the weighting is based at least in part on a function of respective values of the rankings of the second set of data and the fourth set of data, a function of a difference between the second set of data and the fourth set of data and normalized ranges for the first metric and the second metric, an amount of traffic communicated via respective network nodes of the plurality of network nodes, a connectivity metric for respective network nodes the plurality of network nodes, a relative network impact of unavailability of respective network nodes of the plurality of network nodes, or a combination thereof.
12. A method, comprising:
receiving, via a communications network from a plurality of network nodes of the communications network, a first set of data indicating a metric associated with a power grid, the communications network configured to provide a communication service to end devices at locations serviced by the power grid, wherein the plurality of network nodes use the power grid as a primary source of power;
determining a normalized range for the metric associated with the power grid based at least in part on the first set of data;
receiving, via the communications network from the plurality of network nodes of the communications network, a second set of data indicating the metric associated with the power grid; and
generating a third set of data indicating a relationship between the second set of data and the normalized range for the metric;
receiving a request for the third set of data associated with a geographical region comprising a subset of the plurality of network nodes from a third party;
determining the third set of data for the geographical region based at least in part on the second set of data for the subset of the plurality of network nodes; and
communicating the third set of data for the geographical region to the third party.
13. The method of claim 12 , wherein determining the third set of data for the geographical region comprises:
determining the third set of data based at least in part on the second set of data for the subset of the plurality of network nodes and at least one network node of the plurality of network nodes not within the subset of the plurality of network nodes.
14. The method of claim 13 , wherein determining the third set of data for the geographical region comprises:
weighting values determined from the second set of data for the subset of the plurality of network nodes and the at least one network node based at least in part on locations of the subset of the plurality of network nodes and the at least one network node relative to the geographical region.