top of page
  • Jacob Bourne

Bridging Energy Supply-Demand Gap Could Lower Carbon Emissions

The modern expectation for continuous on-demand energy supply means that power companies have to operate with a surplus. There are periods of the day or year when demand spikes in any given community, followed by lengthy intervals of low energy usage. However, to prepare for the peak periods, companies over-dimension energy supplies, which results in higher carbon emissions.

A study conducted by researchers at Gwangju Institute of Science and Technology found that artificial intelligence can effectively estimate demand response potential in improving power consumption and reduce society’s carbon footprint.

So-called demand response (DR) programs incentivize electric grid users to lower their consumption during peak hours; however, the effectiveness of DR hadn’t been fully verified before the study. The GIST team proposes an AI-based approach to estimate DR potential per household based on real-world user behavior to ease grid stress and help curb climate change.

[Like what you read in The Carbonic? Help support climate journalism]

“Our results show that big data-based analysis can be used to convert information about household energy demand into large-scale integrated resources,” said Prof. Jinho Kim, who headed the study. “We believe this technology can be further expanded to improve the efficiency and coupling of other sectors, including water, heat, gas, and electric vehicles sectors.”

To meet periods of surges in energy demand, power stations use an excessive number of generators in preparation for peak periods. This creates an ongoing inefficiency in operations and more carbon dioxide emissions. Additionally, while more sustainable, distributed energy resources such as rooftop solar panels can exacerbate the mismatch between supply and demand.

Implementing DR programs allows consumers to be informed about shifts in energy pricing between peak vs. off-peak hours, thus incentivizing people to consume a more significant share of energy during lower-demand hours when prices are lower. Such advance planning can also integrate distributed energy resource management to help lessen the burden on the grid.

The GIST scientists developed an AI approach that analyzes and extracts grid user behavior to establish energy consumption per household. The data-driven framework estimates an optimal DR management plan for each household based on user behavior, appliances and predictions about the energy generated from solar panels. The researchers also calculated the potential contributions of DR programs in reducing CO2 emissions and the costs of managing coal-powered generators.

“In our simulations, we considered and quantified the level of user discomfort related to the dynamics of home appliances in each household and then used it to estimate the optimal DR potential,” explained Kim.

Overall, this study showcases how consumers and grid operators can leverage AI to improve electricity consumption patterns for both a smaller carbon footprint and energy cost savings for consumers.


Drop a line to for newsletter subscriptions, tips, questions or comments.

bottom of page