Forecasting solar power generation using real-time power data, weather data, and complexity-based similarity factors
US9857778B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 7, 2016 |
| Grant date | Jan 2, 2018 |
| Priority date | — |
| Expiry date | Oct 7, 2036 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY02A90/10
- WIPO fieldMeasurement
- WIPO sectorInstruments
Abstract
Embodiments are directed to a computer-implemented method, computer system, and computer program product of forecasting power generation. The method includes analyzing a set of historical power generation data. Thereafter a set of clusters is determined wherein each cluster of the set of clusters represents power generated during the time period. Then receiving actual power generation data for a portion of the time period. Thereafter, determining which cluster of the set of clusters contains historical power generation data that is most similar to the actual power generation data. Then forecasting power generation for a remainder of the time period, using the historical power generation data of the cluster.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.