Internet of things-enabled solar photovoltaic health monitoring and advising related thereto
Methods, systems, and computer program products are provided herein in connection with IoT-enabled solar PV health monitoring and advising related thereto. A computer-implemented method includes obtaining current-voltage samples corresponding to solar photovoltaic modules by triggering switch circuitry between (i) an inverter attributed to the solar photovoltaic modules and (ii) a current-voltage tracer; detecting one or more anomalies in the obtained current-voltage samples by applying machine learning techniques to the obtained current-voltage samples; automatically performing a root cause analysis on the detected anomalies by (i) converting the obtained current-voltage samples to sequential data, (ii) applying a sequence classifier to the sequential data, and (iii) identifying a pre-determined anomaly class comparable to the sequential data based on the application of the sequence classifier; and automatically generating and outputting a suggestion for remedial action based on the identified pre-determined anomaly class.
1. A computer-implemented method, the method comprising steps of:
obtaining current-voltage samples corresponding to one or more particular solar photovoltaic modules from among plurality of photovoltaic modules by triggering Internet of Things-based switch circuitry between (i) an inverter attributed to the one or more particular solar photovoltaic modules and (ii) a current-voltage tracer, wherein said triggering comprises triggering the switch circuitry in response to under-performance of one or more expected parameters associated with the one or more solar photovoltaic modules;
detecting one or more anomalies in the obtained current-voltage samples by applying one or more machine learning techniques to the obtained current-voltage samples;
automatically performing a root cause analysis on the one or more detected anomalies by (i) converting the obtained current-voltage samples to sequential data, (ii) applying a sequence classifier to the sequential data, and (iii) identifying at least one pre-determined anomaly class comparable to the sequential data based on the application of the sequence classifier to the sequential data, wherein performing the root cause analysis further comprises determining the number of solar photovoltaic modules affected by the one or more detected anomalies; and
automatically generating and outputting a suggestion for one or more remedial actions based on the at least one identified pre-determined anomaly class;
wherein the steps are carried out by at least one computing device.
2. The computer-implemented method of claim 1 , wherein the plurality of solar photovoltaic modules comprises one or more solar photovoltaic cells.
3. The computer-implemented method of claim 1 , wherein the plurality of solar photovoltaic modules comprises one or more solar photovoltaic panels.
4. The computer-implemented method of claim 1 , wherein the plurality of solar photovoltaic modules comprises one or more Internet of Things-enabled solar photovoltaic modules.
5. The computer-implemented method of claim 1 , wherein said triggering comprises triggering the switch circuitry on a periodic basis.
6. The computer-implemented method of claim 1 , wherein said triggering the switch circuitry comprises (i) temporarily disconnecting the inverter from the one or more particular solar photovoltaic modules and (ii) temporarily connecting the one or more particular solar photovoltaic modules to the current-voltage tracer.
7. The computer-implemented method of claim 1 , wherein the sequence classifier comprises a long short-term memory- (LSTM-) based sequence classifier.
8. The computer-implemented method of claim 1 , wherein the at least one pre-determined anomaly class comprises at least one of shading, dust, droppings, pollution, module aging, soldering failure, and hardware-related issue.
9. A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:
obtain current-voltage samples corresponding to one or more particular solar photovoltaic modules from among plurality of photovoltaic modules by triggering Internet of Things-based switch circuitry between (i) an inverter attributed to the one or more particular solar photovoltaic modules and (ii) a current-voltage tracer, wherein said triggering comprises triggering the switch circuitry in response to under-performance of one or more expected parameters associated with the one or more solar photovoltaic modules;
detect one or more anomalies in the obtained current-voltage samples by applying one or more machine learning techniques to the obtained current-voltage samples;
automatically perform a root cause analysis on the one or more detected anomalies by (i) converting the obtained current-voltage samples to sequential data, (ii) applying a sequence classifier to the sequential data, and (iii) identifying at least one pre-determined anomaly class comparable to the sequential data based on the application of the sequence classifier to the sequential data, wherein performing the root cause analysis further comprises determining the number of solar photovoltaic modules affected by the one or more detected anomalies; and
automatically generate and output a suggestion for one or more remedial actions based on the at least one identified pre-determined anomaly class.
10. The computer program product of claim 9 , wherein said triggering comprises triggering the switch circuitry on a periodic basis.
11. The computer program product of claim 9 , wherein the plurality of solar photovoltaic modules comprises one or more Internet of Things-enabled solar photovoltaic modules.
12. The computer program product of claim 9 , wherein said triggering the switch circuitry comprises (i) temporarily disconnecting the inverter from the one or more particular solar photovoltaic modules and (ii) temporarily connecting the one or more particular solar photovoltaic modules to the current-voltage tracer.
13. The computer program product of claim 9 , wherein the sequence classifier comprises a long short-term memory- (LSTM-) based sequence classifier.
14. The computer program product of claim 9 , wherein the at least one pre-determined anomaly class comprises at least one of shading, dust, droppings, pollution, module aging, soldering failure, and hardware-related issue.
15. A system comprising:
a memory; and
at least one processor operably coupled to the memory and configured for:
obtaining current-voltage samples corresponding to one or more particular solar photovoltaic modules from among plurality of photovoltaic modules by triggering Internet of Things-based switch circuitry between (i) an inverter attributed to the one or more particular solar photovoltaic modules and (ii) a current-voltage tracer, wherein said triggering comprises triggering the switch circuitry in response to under-performance of one or more expected parameters associated with the one or more solar photovoltaic modules;
detecting one or more anomalies in the obtained current-voltage samples by applying one or more machine learning techniques to the obtained current-voltage samples;
automatically performing a root cause analysis on the one or more detected anomalies by (i) converting the obtained current-voltage samples to sequential data, (ii) applying a sequence classifier to the sequential data, and (iii) identifying at least one pre-determined anomaly class comparable to the sequential data based on the application of the sequence classifier to the sequential data, wherein performing the root cause analysis further comprises determining the number of solar photovoltaic modules affected by the one or more detected anomalies; and
automatically generating and outputting a suggestion for one or more remedial actions based on the at least one identified pre-determined anomaly class.
16. A computer-implemented method, the method comprising steps of:
obtaining current-voltage samples corresponding to one or more particular solar photovoltaic modules from among a plurality of photovoltaic modules by triggering Internet of Things-based switch circuitry between (i) an inverter attributed to the one or more solar photovoltaic modules and (ii) a current-voltage tracer, wherein said triggering comprises triggering the switch circuitry in response to under-performance of one or more expected parameters associated with the one or more solar photovoltaic modules;
detecting one or more anomalies in the obtained current-voltage samples by applying one or more machine learning techniques to the obtained current-voltage samples;
automatically performing a root cause analysis on the one or more detected anomalies by (i) extracting one or more features from the obtained current-voltage samples, (ii) applying a feature-based classifier to the one or more extracted features, and (iii) identifying at least one pre-determined anomaly class comparable to the obtained current-voltage samples based on the application of the feature-based classifier to the one or more extracted features, wherein performing the root cause analysis further comprises determining the number of solar photovoltaic modules affected by the one or more detected anomalies; and
automatically generating and outputting a suggestion for one or more remedial actions based on the at least one identified pre-determined anomaly class;
wherein the steps are carried out by at least one computing device.
17. The computer-implemented method of claim 16 , wherein the feature-based classifier comprises one or more support vector machines.
18. The computer-implemented method of claim 16 , wherein the feature-based classifier comprises one or more random forests.
19. The computer-implemented method of claim 16 , wherein said triggering comprises triggering the switch circuitry on a periodic basis.