System for forecasting renewable energy generation
Systems and methods for forecasting renewable energy generation using holistic weather and system analysis are provided. Derate factors of energy sources can be considered, along with regional weather variability, site specific weather, and a cross-view of the sky from ground based and/or geo-stationary satellite imaging. The forecast can include short-term forecasting and long-term forecasting.
1. A system for forecasting renewable energy generation, the system comprising:
a renewable energy source;
at least one first sensor on the renewable energy source;
a processor; and
a non-transitory machine-readable medium in operable communication with the processor and having instructions stored thereon that, when executed by the processor, perform the following steps:
receiving energy data on current energy generation from the at least one first sensor on the renewable energy source;
receiving weather parameters of the local weather from second sensors;
receiving image data of the sky from at least one imaging camera;
estimating future energy generation based on the energy data and the weather parameters;
estimating cloud cover based on the image data to derive a cloud shading profile;
performing a univariate regression on the weather parameters and the cloud shading profile to derive input parameters;
performing at least one parametric regression on the input parameters and the energy data and deriving a forecast of renewable energy generation of the renewable energy source; and
providing the forecast of renewable energy generation to a power system having the renewable energy source such that the power system adjusts amounts of power obtained from the renewable energy source and another energy source in operable communication with the power system, thereby optimizing use of energy generated by the renewable energy source.
2. The system according to claim 1 , the forecast of renewable energy generation comprising a 15-minute ahead prediction.
3. The system according to claim 1 , the forecast of renewable energy generation comprising a 1-hour ahead prediction.
4. The system according to claim 1 , the forecast of renewable energy generation comprising a 7-day ahead prediction.
5. The system according to claim 1 , the renewable energy generation being photovoltaic (PV) energy generation.
6. The system according to claim 1 , further comprising the at least one first sensor and the second sensors.
7. The system according to claim 1 , the weather parameters comprising wind speed, wind direction ambient temperature, precipitation, atmosphere turbidity, and atmosphere translucency.
8. The system according to claim 1 , the instructions when executed by the processor further receiving the image data from a geo-satellite feed.
9. The system according to claim 1 , the estimating ofthe cloud cover based on the image data to derive the cloud shading profile comprising using a convolutional-time-dependent neural network to derive the cloud shading profile.
10. The system according to claim 1 , the instructions when executed by the processor further receiving aggregation data and using the aggregation data when deriving the forecast of renewable energy generation.
11. A method for forecasting renewable energy generation, the method comprising:
receiving, by a processor, energy data on current energy generation from at least one first sensor on a renewable energy source;
receiving, by the processor, weather parameters of the local weather from second sensors;
receiving, by the processor, image data of the sky from at least one imaging camera;
estimating, by the processor, future energy generation based on the energy data and the weather parameters;
estimating, by the processor, cloud cover based on the image data to derive a cloud shading profile;
performing, by the processor, a univariate regression on the weather parameters and the cloud shading profile to derive input parameters;
performing, by the processor, at least one parametric regression on the input parameters and the energy data and deriving a forecast of renewable energy generation of the renewable energy source; and
providing the forecast of renewable energy generation to a power system having the renewable energy source such that the power system adjusts amounts of power obtained from the renewable energy source and another energy source in operable communication with the power system, thereby optimizing use of energy generated by the renewable energy source.
12. The method according to claim 11 , the forecast of renewable energy generation comprising a 15-minute ahead prediction.
13. The method according to claim 11 , the forecast of renewable energy generation comprising a 1-hour ahead prediction.
14. The method according to claim 11 , the forecast of renewable energy generation comprising a 7-day ahead prediction.
15. The method according to claim 11 , the renewable energy generation being photovoltaic (PV) energy generation.
16. The method according to claim 11 , the weather parameters comprising wind speed, wind direction ambient temperature, precipitation, atmosphere turbidity, and atmosphere translucency.
17. The method according to claim 11 , further comprising receiving the image data from a geo-satellite feed.
18. The method according to claim 11 , the estimating of the cloud cover based on the image data to derive the cloud shading profile comprising using a convolutional-time-dependent neural network to derive the cloud shading profile.
19. The method according to claim 11 , further comprising receiving aggregation data and using the aggregation data when deriving the forecast of renewable energy generation.
20. A system for forecasting renewable energy generation, the system comprising:
a renewable energy source;
at least one first sensor on the renewable energy source;
a plurality of second sensors;
a processor; and
a non-transitory machine-readable medium in operable communication with the processor, the at least one first sensor, and the plurality of second sensors, the machine-readable medium having instructions stored thereon that, when executed by the processor, perform the following steps:
receiving energy data on current energy generation from the at least one first sensor on the renewable energy source;
receiving weather parameters of the local weather from the plurality of second sensors;
receiving image data of the sky from at least one imaging camera and a geo-satellite feed;
receiving aggregation data from the at least one first sensor;
estimating future energy generation based on the energy data and the weather parameters;
estimating cloud cover based on the image data to derive a cloud shading profile;
performing a univariate regression on the weather parameters and the cloud shading profile to derive input parameters;
performing at least one parametric regression on the input parameters and the energy data and deriving a forecast of renewable energy generation of the renewable energy source; and
providing the forecast of renewable energy generation to a power system having the renewable energy source such that the power system adjusts amounts of power obtained from the renewable energy source and another energy source in operable communication with the power system, thereby optimizing use of energy generated by the renewable energy source,
the forecast of renewable energy generation comprising a 15-minute ahead prediction, a 1-hour ahead prediction, and a 7-day ahead prediction,
the renewable energy generation being photovoltaic (PV) energy generation,
the weather parameters comprising wind speed, wind direction ambient temperature, precipitation, atmosphere turbidity, and atmosphere translucency, and
the estimating of the cloud cover based on the image data to derive the cloud shading profile comprising using a convolutional-time-dependent neural network to derive the cloud shading profile,
the aggregation data being used when the forecast of renewable energy generation is derived.