Cost Savings Estimation for Solar Energy Consumption Using Machine Learning

With the surging requirement for green energy in today's world, renewable energy has been in high demand in the market. Unlike fossil fuels, which will eventually run out, the sun has more than enough energy to supply the world's energy needs. The carbon footprint of solar panels is nearly 20 times lower than the carbon output of electricity sources that are coal-powered. Solar energy's variability and our capacity to transform it into electricity efficiently and economically are its only drawbacks as a renewable energy source. Estimating the amount of electricity generated and the cost saved by installing a solar panel at a particular location can be a beneficial tool for consumers. This study aims to develop models based on time series forecasting to predict hourly and monthly solar radiation values for various locations in India using a Seasonal Autoregressive Integrated Moving Average model, which gives a highly accurate forecasting model. These predicted values of solar radiation are used to check whether solar energy can replace non-renewable sources of energy and be utilized with sufficient efficiency for the given location. Cost savings estimation takes the user’s current average monthly electricity bill value and power consumption rate. This information is used to calculate the rating of the solar panel needed and is tallied with the average cost of solar energy per unit for that location. A user can potentially get an estimate of the cost saved by shifting to solar energy, which could save over 70% of their current electricity bills. The result shown is in terms of how much a user can save economically and the breakeven period.