Biomimetic power: the AI “brain” that keeps renewable power grids stable

summary: As the world replaces fossil fuel power plants with solar and wind power, power grids are becoming more “intermittent” and difficult to control. Researchers have developed a solution inspired by the human brain.

Khan used artificial neural networks (ANNs) to create a “biomimetic” controller that can predict and adapt to unpredictable spikes and dips in renewable energy in real time. This AI-driven approach not only outperforms traditional methods, but also allows the grid to operate with fewer physical sensors, making the infrastructure cheaper and more reliable.

important facts

Stability challenges: Renewable energy sources use inverters that don’t have the “natural inertia” of heavy rotating turbines in traditional plants, making them more susceptible to grid crashes.
Brain-inspired control: Khan’s AI controller learns from thousands of scenarios to proactively “predict” grid instability and adjust voltages and currents in milliseconds.
Hardware and software: AI is so accurate that it can replace physical hardware. In testing, the system gave the same results as: 1 sensor Instead of the traditional two, it reduces costs and potential points of mechanical failure.
“Black box” hurdles: Although the AI performed flawlessly in real-time testing, researchers admit that it could explain: how Getting AI to make decisions remains a challenge and a common hurdle when integrating AI into critical infrastructure.
A carbon neutral future: This research is a key component of “microgrids,” which will allow communities to safely integrate higher rates of wind and solar power without risking power outages.

sauce: vasa university

As traditional power plants are replaced by intermittent sources such as solar and wind, maintaining grid stability has become a complex engineering challenge.

Hussein Khan’s PhD thesis from the University of Vaasa in Finland presents an advanced AI-based control strategy to ensure the reliability and resilience of local power grids.

This shows a node-based brain and a wind turbine. — This biomimetic approach allows power systems to learn and adapt to the unpredictability of nature. Credit: Neuroscience News

The power system is undergoing a major transformation as fossil fuel-based power generation is gradually replaced by inverter-based renewable energy. This change introduces inherent uncertainties and low inertia that significantly complicate grid operation and voltage stability in AC and DC microgrids.

Hussein Khan tackles these challenges in his doctoral thesis in electrical engineering. By using artificial neural networks (ANN), Khan has developed a controller that can predict and compensate for changes in the grid in real time, outperforming traditional control methods.

– ANN is inspired by the human brain, which processes information through interconnected neurons. This biomimetic approach allows the system to learn from different scenarios and adapt to the unpredictability of solar and wind power generation, Kahn said.

Cost-effective solution with sensor optimization

Traditional systems rely on multiple physical sensors to monitor voltage, current, and other parameters, increasing cost and increasing the number of potential points of failure. Khan’s AI-driven approach demonstrates that sophisticated software can compensate for fewer hardware components.

– By effectively training the neural network, the system can provide the same reliable results with just one sensor instead of two. This results in fewer physical parts that can fail, leading to cost optimization and improved overall reliability, Kahn said.

While AI-based control improves efficiency and reduces hardware requirements, introducing intelligent controllers into critical infrastructure also brings new considerations.

– The main concern is that AI behaves like a black box. You can see the inputs and outputs, but it doesn’t always fully explain what’s happening under the hood. Still, the controller performed very well in our tests and was rigorously validated in real time, Khan said.

Khan’s research supports the broader goal of creating a carbon-neutral energy system in the coming decades. AI-based control could enable power grids to integrate more renewable energy in the future by improving stability and reducing hardware requirements.

Answers to key questions:

Q: Why does the renewable energy grid need an “AI brain”?

answer: Traditional grids are like giant, heavy flywheels that are difficult to stop once they spin. Solar and wind power are like “light” electricity. Flashes instantly. The AI brain acts as a super-fast stabilizer, making thousands of tweaks every second to keep the lights from flickering as clouds pass over the solar power plant.

Q: How will I save money on my electricity bill?

answer: Sensors and hardware are expensive to buy, and even more expensive to repair if they break. By using “virtual sensors” (software) to do the work of physical hardware, utilities can reduce the cost of building and maintaining local microgrids, which is ultimately passed on to consumers.

Q: Can we trust AI in the power grid if it is a “black box”?

answer: This is a big debate in electrical engineering. Kahn’s research used Rigorous real-time verification The next step in this field is “Explainable AI” (XAI), as we cannot always “see” the logic of AI to prove that it works. For now, the performance gains are so high that they outweigh transparency concerns in a controlled microgrid environment.