Carbon-neutral city: how AI can reduce electricity costs by more than 18%

Creating sustainable urban environments requires reliable sources of renewable energy. AI can provide solutions by efficiently managing the electricity grid in extreme weather conditions.

Carbon neutrality is the key to addressing climate change, but making cities carbon-free is a challenging task. Urban electrification aims to reduce the use of fossil fuels and introduce renewable energy sources, such as building-integrated solar technology. However, energy supply stability has been difficult to achieve.

Renewable energy creates more instability in supply because of changing weather, which can lead to mismatches in electricity demand across buildings. Sudden cold or extreme heat waves can dramatically spike energy demand while reducing energy production.

Such events threaten the stability of the urban power grid and could result in widespread blackouts. Traditional power production could use fossil fuels to meet this demand, but that solution is out of the question for electrified cities.

AI makes electricity cheaper

A research team from the Renewable Energy System Laboratory and the Energy ICT Research Department at the Korea Institute of Energy Research has developed an AI algorithm that can manage the power grid to ensure the stability of the energy supply.

Once they applied it to a real-life community, they saw impressive results – an 18% reduction in electricity costs and significantly improved power grid stability.

The algorithm also helped to achieve an energy self-sufficiency rate of 38%, meaning the building could meet 38% of its electricity demand through its own power generation. It also had a self-consumption rate of 58%, which refers to the percentage of electricity produced by the building used on-site rather than sent to the power grid.

The annual energy consumption used in the demonstration was 107 megawatt-hours (MWh), which is seven times higher than simulation-based studies showed before. This greatly increases the system's potential for real-world application in urban environments."By applying this system to various urban environments in the future, we can improve energy efficiency and enhance grid stability, ultimately making a significant contribution to achieving carbon neutrality," said the lead research author Dr. Gwangwoo Han.

How did AI do it?

To achieve these results, the research team first used an AI model to analyze the patterns of renewable energy – both how it is produced and consumed. The model considered variables such as weather, human behavior patterns, and the size and operational status of renewable energy facilities.

Through this analysis, researchers discovered high-impact events, such as extreme weather conditions, that were affecting power grids and their operational costs.

Based on the gathered data, scientists built an algorithm that could respond to unexpected events and optimize energy sharing between buildings to manage peak energy demand.