AI helps to alleviate the strain on the facility grid – without affecting people’s energy consumption

My colleagues and I even have developed a synthetic intelligence system that helps buildings shift their energy use to times when the facility grid is cleaner.

I’m an engineer who researches and develops intelligent buildingsMy lab has developed Merlin, which learns how people use energy of their homes and adapt energy controls reminiscent of thermostats to their needs while minimizing impact on the grid. The system can learn from a bunch of buildings and occupants and could be deployed in buildings with different control and energy use patterns.

We named it Merlin, after King Arthur's legendary wizard, to reflect the magical nature of the system: it robotically collects data on how people use energy of their homes and detects opportunities to charge and discharge home battery storage, so you usually have power for every thing you would like. So your air con is all the time available, but at the identical time the grid is relieved – for instance during peak demand within the afternoon.

When demand exceeds available generation, utilities typically ask customers to regulate their thermostats and otherwise reduce their loads. If that's not enough, blackouts are possible. That's where Merlin is available in. By managing energy use in homes more intelligently, Merlin helps balance energy supplies and make power grids more stable and reliable. Merlin manages the grid's use of the house's battery while maintaining the house's normal energy use.

Why it will be important

To combat climate change, society must move to using only non-fossil energy sources reminiscent of solar, wind and nuclear power to generate electricity. All household appliances or end-use devices – heating, cooking, drying clothes – must even be electrified. The same shift is happening in cars, where we’re moving from vehicles with combustion engines to battery-powered electric vehicles. However, most renewable energy sources usually are not controllable, meaning that energy suppliers cannot simply switch them on when needed.

This requires a fundamental shift from a centralized energy system, through which one power plant generates all of the electricity needed, to a more decentralized or distributed system. In decentralized systems, electricity is generated at the perimeters of the grid – for instance, in homes with solar panels – and houses and office buildings can store energy in batteries.

Private households and office buildings are also actively trying to cut back or shift their loads to cut back demands on the grid. This means fewer power outages and fewer energy wastage. In addition, more efficient energy use helps reduce greenhouse gas emissions.

a wall-mounted box with wires coming out the bottom
Battery storage is a key element in linking smart homes with smart grid management.
Jens Büttner/picture alliance via Getty Images

What other research is being carried out

Researchers are working on various ways to make buildings smarter and higher manage their energy consumption. In fact, the U.S. Department of Energy has created a national plan to Development of such network-interactive, efficient buildings to triple the energy efficiency and energy demand flexibility of buildings by 2030. In 2021, the Department funded 10 public-private partnership projects together with his Connected Communities Program to develop and test technologies for network-interactive buildings.

The International Energy Agency supports a lot of programs through which researchers are working to Software applications for smarter constructing operations, Energy-flexible buildings and more recently Network-integrated control of buildings.

All these programs and developments give attention to advanced control systems and promote the adoption of intelligent technologies to optimize energy consumption, just like Merlin.

What happens next?

The next step is to check systems like Merlin in additional communities under real-world conditions and learn how well they work in several locations and conditions. It's essential that we collect feedback on user experiences and incorporate this into our next prototypes to make sure the adoption of AI systems to administer household energy use. Our goal is to make these systems easy to make use of and reasonably priced so that everybody can profit from smarter, greener homes.

The goal is for each neighborhood to have households sharing energy like a team, ensuring there may be all the time enough power for everybody and as little power as possible is used from the grid.

image credit : theconversation.com