Reviewed by Danielle Ellis, B.Sc.Sep 23 2024
An international group of researchers from the Renewable Energy System Laboratory and the Energy ICT Research Department at the Korea Institute of Energy Research developed key technologies to implement “Urban Electrification” utilizing artificial intelligence. The research was published in the journal Sustainable Cities and Society.
Researchers group photo (from left to right Dr. Jong-Kyu Kim, Dr. Min-Hwi Kim, Dr. Gwangwoo Han, Student Researcher Dong Eun Jung, Dr. Young-Sub An, and Dr. Hong-Jin Joo). Image Credit: Korea Institute of Energy Research
Urban electrification seeks to change urban energy systems by reducing the use of fossil fuels and introducing renewable energy sources, such as solar technology, into buildings. This idea is being pushed as a crucial tactic in the US and Europe for reaching carbon neutrality and developing sustainable urban settings, even though it is comparatively unknown in the Republic of Korea.
Fossil fuels can readily be used to modify the energy supply in classic urban models to fulfill power demand. However, in electrified cities, a strong reliance on renewable energy causes more weather-related fluctuations in the energy supply. This leads to imbalances in the amount of electricity consumed by different buildings and complicates the power grid's ability to operate steadily.
Specifically, abrupt cold snaps and intense heat waves are examples of Low-Probability High-Impact Events (LPHI) that can sharply raise energy demand while limiting energy production. These occurrences seriously threaten the stability of the urban electrical infrastructure and could result in widespread blackouts.
To address concerns with power grid stability, the research team created an energy management algorithm based on AI analysis and integrated it into a system. When compared to traditional approaches, the new system's demonstration revealed an 18% reduction in electricity expenses.
Using artificial intelligence (AI), the research team first examined patterns of energy use by building types and patterns of renewable energy output. They also uncovered the intricate relationships between the electricity grid and several complicated factors, including weather, human behavior, and the size and state of operation of renewable energy installations.
They found, notably, that Low-Probability High-Impact Events, which happen on average only 1.7 days annually (or around 0.5% of the time), significantly affect the power grid's overall stability and operating expenses.
An algorithm and a system are constructed using content analysis. The algorithm efficiently controls peak demand and peak energy production while optimizing energy sharing among buildings. The system responds to Low-Probability High-Impact Events in addition to preserving daily energy balance. This feature guarantees the stability of the power grid even under dire circumstances.
When implemented in a community-scale real-world context that replicated urban electrification, the designed system achieved an energy self-sufficiency rate of 38% and a self-consumption rate of 58%.
Compared to buildings without the system, which had a 30% self-consumption rate and a 20% self-sufficiency rate, this is a major increase. Additionally, this application significantly increased the reliability of the power system and reduced electricity expenditures by 18%.
In particular, the demonstration's annual energy usage of 107 MWh was seven times higher than studies based on simulations carried out by eminent international organizations. This greatly expands the system's potential for use in actual urban settings.
The results of this study demonstrate that AI can enhance the efficiency of urban electrification and address power grid stability issues, while also highlighting the importance of managing Low-Probability High-Impact Events, 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.
Dr. Gwangwoo Han, Study Lead Author and Researcher, ICT Research Department, Korea Institute of Energy Research
The study was conducted as part of the Korea Institute of Energy Research’s (KIER) R&D projects.
Journal Reference:
Han, G., et al. (2024) Analysis of grid flexibility in 100% electrified urban energy community: A year-long empirical study. Sustainable Cities and Society. doi.org/10.1016/j.scs.2024.105648.