Exploratory Data Analysis of India's Weather And Its Impact On Renewable Energy

Motivation Behind Choosing Weather Data

Weather Monitoring Station (WMS) is one of the most crucial instruments installed in Solar PV Power plants. A weather monitoring station can be immensely helpful in monitoring the efficiency and performance of any solar power plant. The data from the WMS can be used to get many insights about the plant operation and possible avenues to increase the plant output.

 The key factor affecting the PV system's performance is the solar radiation data. But along with solar radiation data, the weather parameters like ambient temperature, relative humidity, wind speed, wind direction, atmospheric pressure, and rain are the other important factors affecting the performance. 
Weather data and weather prediction can help in scheduling maintenance and repairs. Doing maintenance and repairs at the wrong time could prove to be a costly affair.

Wind velocity is important from the plant safety perspective. The heavy wind loads at a site may cause damage to the PV modules. With accurate wind speed and direction data, a user can take the necessary steps to prevent damages and loss. While wind speed largely determines the amount of electricity generated by a wind turbine. Higher wind speeds generate more power because stronger winds allow the blades to rotate faster. Faster rotation translates to more mechanical power and more electrical power from the generator. 
So it is of utmost importance to analyze the weather data and get to know the climate facts in different states and cities for the installation, and maintenance of power plants.

What is Exploratory Data Analysis

Exploratory Data Analysis (EDA) is the process of exploring, investigating and gathering insights from data using statistical measures and visualizations. The objective of EDA is to develop and understanding of data, by uncovering trends, relationships and patterns.

EDA is both a science and an art. On the one hand it requires the knowledge of statistics, visualization techniques and data analysis tools like Numpy, Pandas, Seaborn etc. On the other hand, it requires asking interesting questions to guide the investigation and interpreting numbers & figures to generate useful insights.

In this project, I have selected an Indian weather dataset from kaggle to explore and analyze the sites which are more efficient for solar as well as wind power installations. We'll use the the python libraries pandas, matplotlib, seaborn, plotly and folium to do exploratory data analysis on the weather dataset.

Here's the outline of the steps we'll follow:

1. Downloading a dataset from an online source
2. Data preparation and cleaning with Pandas
3. Open-ended exploratory analysis and visualization
4. Asking and answering interesting questions
5. Summarizing inferences and drawing conclusions

By the end of the project we'll get an idea on Indian weather and also have some preferable sites for solar as well as wind power installations.

How to run the code

The easiest way to start executing the code is to click the Run button at the top of this page and select Run on Binder. You can also select "Run on Colab" or "Run on Kaggle", but you'll need to create an account on Google Colab or Kaggle to use these platforms. You can make changes and save your own version of the notebook to Jovian by executing the following cells.

Since the selected dataset contains 5+ million rows of data, I have selected "Gogle Colab" to execute the code for faster response.

When you are commiting the notebook to Jovian for the first time in "Colab" it will ask for API key which will be found in your Jovian account getstarted section.