Efficient use of renewable energy sources with machine learning

Solar power systems could be a key tool for energy production for the present and future generations. Solar energy is environmentally friendly and provides electricity to places where it is difficult to build conventional infrastructure. Photovoltaic (PV) cells become cheaper each year. Solar energy is cheaper than ever.

However, it has two huge obstacles: energy is produced only during the daytime and the amount of energy produced is highly dependent on the weather. Machine learning algorithms combined with weather data have the potential to overcome these barriers, which results with more efficient use of renewable energy sources.

In this article, you will learn about predicting time series depending on external (weather) conditions. I will show you how to improve your predictions using the domain knowledge of the target variable. We will go quickly through collecting data about energy production from the solar farm through its producers API. Next, we will analyze gathered data and select features for time-series forecasting. Finally, we will train and test several predictive models and identify the best, most suitable for the described case.

Read More:
https://netlabe.com/how-to-predict-solar-energy-production-887ce31ec9d1