Two researchers have found a way to use artificial intelligence to predict college campus energy use with an accuracy of within 1%.
According to Environment+Energy Leader, two University of Missouri College of Engineering researchers used a collection of AI tools and data to predict campus energy usage. Sanjeev Khanna and Saad Alsamraee use hourly data going back six years from the Combined Heat and Power Plant. They found that campus-wide energy consumption barely dropped during the COVID-19 pandemic, a trend that's difficult to explain.
Before now, autoregressive integrated moving average (ARIMA) forecasting models were used to assess and predict campus energy use. However, those models can only handle basic trends and cannot account for all real-world data.
Khanna and Alsamraee used an array of machine learning tools, including Decision Trees, Support Vector Regression, Random Forest, K-Nearest Neighbors, and XGBoost. In an impressive feat, XGBoost reduced prediction errors by 46%, outshining the other machine learning tools.
The new technology allows university campuses to better budget and plan for energy use. It can help them cut costs by understanding the factors that influence these predictions the most.
In this case, the researchers found that outside temperature played a large role in energy consumption, something the traditional forecasting models didn't consider. XGBoost can also account for energy use during particular times of the day, which was also affected by the outside temperature.
Even when 10% of the data was taken away from the model, it was still able to assess a multitude of factors and make an accurate prediction. The innovation can reshape how universities plan their energy and help mitigate climate change, creating a cooler, cleaner future.
This technology isn't just useful for college campuses. It can help other facilities, like sports complexes, hospitals, and government buildings, better predict and manage their energy use. This can save people money and help reduce pollution created by energy consumption.
According to E+EL, Khanna, a professor of mechanical engineering and director of the Midwest Industrial Assessment Center, said: "By knowing when there are going to be peaks and valleys and how much energy will be needed, even on an hour-by-hour basis, we can ultimately help power plants better plan ahead so they can be as efficient as possible with energy use. This research can help universities and industries reduce carbon emissions and save money."
XGBoost is already an operational AI tool, so with enough data, the predictive model can be used to help with energy budgeting and pollution reduction right away.
TCD Picks » Upway Spotlight
💡Upway makes it easy to find discounts of up to 60% on premium e-bike brands
|
Do you think our power grid needs to be upgraded? Click your choice to see results and speak your mind. |
Definitely 👍 
Join our free newsletter for weekly updates on the latest innovations improving our lives and shaping our future, and don't miss this cool list of easy ways to help yourself while helping the planet.
Cool Picks
