ON WITH THE WIND
Pollution from fossil fuel combustion is a global problem. This pollution is responsible for 1 in 8 global deaths, according to the WHO. A cleaner energy source such as wind power will save lives.
​
One obstacle to the use of wind power is the inaccuracy of predictions of turbine power output. Inaccurate predictions force utilities to use backup plants. This wastes energy. Inaccurate predictions can cause utilities to waste money because backup plants are expensive to maintain.
​
I used machine learning to improve the accuracy of turbine power output predictions. Machine learning is a type of artificial intelligence that teaches the computer to learn from existing data and predict outcomes for future data.
​
For my project, I innovated HAWC -- Hybrid Algorithms for Wind-power Computation. HAWC teaches the computer to act as an artificial brain by using neural networks to sort and classify data.
​
HAWC can reduce the need for wasteful backup plants, thereby making wind power more feasible and reducing pollution.
​
​
HOW IT WORKS
The HAWC software ensemble consists of the following algorithms: linear regression, polynomial regression, a 2-layer neural network, and a 3-layer neural network.
​
First, I coded linear regression and polynomial regression in the programming language MATLAB. Linear regression uses a linear function to make a prediction, generating a line that fits the data.
​
Polynomial regression uses a polynomial function to create a curved line. Each point represents a prediction, so an accurate fit represents an accurate prediction.
​
Part of the challenge of coding a neural network is structuring it so it is both accurate and efficient. One needs to determine how many nodes, or artificial neurons, to use, and how many layers, or connection-making steps to use.
To address these challenges, I coded a 3-layer neural network that has not previously been applied to wind power prediction.
​
Pollution kills 7 million people per year -- that’s 13 people every minute. In the time it may have taken you to read this, pollution killed 65 people. The clock is ticking for us to find a solution to this crisis. My results suggest that HAWC could help reduce pollution and save lives by enabling the growth of wind power.