Artificial intelligence will improve energy efficiency

Real-life example: Gustavsberg (Sweden)

Since spring 2022, AI technology has been used in two large residential buildings in Gustavsberg (Sweden). Two residential buildings with 119 rental apartments built in 2018 and enjoying AI-optimized heating. One of the main demands was that the comfort of tenants should be at least at the same level as it was before. Buildings are related to district heating, but this has nothing to do with the implementation of AI: most heating technologies can be combined with AI.

“The fact is that the interior temperature is now more uniform and the comfort is higher thanks to the ventilation and heating controlled by artificial intelligence,” says Michael Skogqvist, property manager at Polstjärnan, the building’s owner.

Michael continued: “By taking into account various factors such as solar radiation and weather forecasts, the system can go one step further and predict how much heat different parts of the building need to maintain the right temperature with the lowest possible heat input.” Skogqvist.

Energy consumption decreased by 30 percent

The building heating system is constantly linked to the artificial intelligence software, and the combination of sensors and controls means that the system is constantly learning how to heat the buildings with the lowest possible energy use. Through the introduction of this technology, energy consumption in buildings in Gustavsburg has so far been reduced by approximately 20 percent. Combined with other measures, the total energy savings amounted to about 30 percent.

The potential for using AI to improve energy extends to many energy areas. Other examples are complex energy networks that need to be increasingly flexible. The shift to fossil-free power generation brings with it more weather-dependent sources such as wind and solar, and large batteries can be used to maintain frequency in grids. Artificial intelligence is crucial to so-called smart grids, which can predict which energy sources will be needed, when, and then control energy supplies as needed.

Another example is energy-intensive mobile phone networks, which are used very differently depending on where people are, how many calls they make, and how much they use the Internet. Japan’s first AI-driven mobile network has cut power consumption by up to half in areas with relatively low data traffic and by up to 20 percent per unit of transmission, according to telecommunications company Nokia and Japanese mobile operator KDDI, which has more than 60 million user network.

Coming soon to a building near you

But can AI technology help reduce your home’s energy consumption? According to Michael Skogqvist, this is likely. “I think all buildings can benefit from this energy optimization technology. The oldest building we plan to optimize with AI dates back to 1905, and I think it’s only a matter of time before we install this in all our buildings.”