Solar Energy forecasting
Results Links at the last.
This Repository Contains:-
Solar Energy Forecast Using Machine Learning
Ridge Regression Model
sklearn Regression Model
Keras Neural Network Model
Abstract
The field of solar and photovoltaic (PV) forecasting is rapidly evolving. The electricity system in India faces several challenges as the energy demand is expected to grow significantly within the next decades while the domestic energy resources in terms of fossil fuels are limited. Hence it becomes important to get more dependent upon Renewable Energy to meet the future requirements. This project report provides state of the art of this dynamic research area, focusing on solar and PV forecast of next dates with given weather data. Diverse resources are used to generate solar and PV forecasts, ranging from measured weather and PV system data to satellite and sky imagery observations of clouds which form the basis of modern weather forecasting.
Electric utility companies need accurate forecasts of energy production in order to have the right balance of renewable and fossil fuels available. Errors in the forecast could lead to large expenses for the utility from excess fuel consumption or emergency purchases of electricity from neighboring utilities. Power forecasts typically are derived from numerical weather prediction models, but statistical and machine learning techniques are increasingly being used in conjunction with the numerical models to produce more accurate forecasts.
Major aspects of Solar Forecasting
Forecasting methods can be broadly characterized as physical or statistical. The physical approach
uses solar and PV models to generate PV forecasts, whereas the statistical approach relies primarily
on past data to “train” models, with little or no reliance on solar and PV models.
The selection of input variables and prediction horizon affects the accuracy of developed prediction model. In this project we have included the following factors:-
• 3-hrs accumulated precipitation on the surface
• Downward long-wave radiative flux average at the surface.
• Downward short-wave radiative flux average at the surface.
• Air Pressure at mean sea level
• Precipitable water over the entire depth of atmosphere.
• Specific humidity at 2m above ground.
• Total Cloud Cover
• Total Column integrated condensate.
• Maximum temperature over past 3 hours.
• Minimum temperature over past 3 hours.
• Current Temperature 2 mt above ground
• Current Temperature at the surface
• Upward long wave radiation at the surface
• Upward long wave radiation at the top of the atmosphere
• Upward short wave radiation at the surface
Types-
- Very Short Term Forecasting (from a few seconds to minutes)- It can be used for PV and storage control and electricity market clearing. In smart grid environment, very short term forecasting of solar power becomes more important than before.
- Short Term Forecasting (upto 48-72 hrs ahead)- Such forecasts are important for different decision making problems involved in the Electricity market and power system operation, including economic dispatch, unit commitment, economic dispatch etc.
- Mid Term (upto 1 week ahead)- Mid Term forecasting would be useful for e.g. maintenance, scheduling of PV power plants, conventional power plants, transformers and transmission lines.
- Long Term (upto months to year)- Long term prediction for long term solar energy assessment and PV plant planning.
Results
Actual Values
Predicted Values
Comparison
Error Rates For different Hyper Parameters