Stefan Niessen, Head of Technology Field Sustainable Energy & Infrastructure at Siemens Technology – AI in Energy, EV Grid Integration, Emerging Tech, Sustainability Advancements, Efficiency Optimization

In this interview, we feature Stefan Niessen, Head of Technology Field Sustainable Energy & Infrastructure at Siemens Technology, as he sheds light on the intersection between academic research and industrial innovation in the realm of sustainable energy and infrastructure. With extensive experience in leading technological advancements, Mr. Niessen shares insights into the challenges and opportunities in integrating emerging technologies into existing energy grids. This interview is part of AI Time Journal’s AI for Energy Initiative.

In your dual role, how do you balance the demands of leading technological advancements in sustainable energy with the theoretical and educational aspects of your professorship?

We have three degrees of maturity in which we address these various topics. One is pure university research as a professor where I can work on topics where converting into a product is five years or longer away. Then we have publicly funded projects in which I may participate either as a professor or as a Siemens employee with my team, allowing us to co-create with other universities, customers, and competitors on pre-development topics. This co-creation mode is great because any new technology can only work if deployed by an ecosystem of partners. The third degree is internal Siemens projects where my team does actual product development work for business units, guiding a promising technology from the initial university stages to an actual product stage where it can be effectively deployed in real life.

Can you discuss a specific project or innovation under your leadership at Siemens that exemplifies the integration of AI into sustainable energy systems?

One example is the multimodal energy storage and flexibility idea I mentioned, which requires smart interaction between grid operators, grid users, and renewable electricity injectors to synchronize consumption with generation. The grid operator needs to estimate how loaded the grid is, which requires AI for forecasting future demand for heat, cooling, traction, and electricity prices and renewable generation. Data cleaning and quality assurance is another AI element, as whenever you measure data, issues arise that need detecting and correcting. Grid state estimation, processing data from different sources for an overview of the grid’s operating state, is the last element.

What emerging technologies or methods in energy trading do you believe hold the most promise for enhancing sustainability globally?

I have sympathy for energy trading, being part of the team that established the European Energy Exchange. Still, we are not yet using the full potential further down the voltage levels where smart, internet-connected devices like charging stations, heat pumps, batteries, and PV inverters exist but are not yet actively trading, though they could. To answer your question, I believe automated local energy trading within grid boundaries is a key emerging technology. We cannot rely that grid capacity will always be fully available, so smart injection is needed. We have field-tested how this can work in projects like pebbles in southern Germany and with the Viennese city utility.

Considering your work in mobility, what are the biggest challenges and opportunities for integrating electric vehicles into existing energy grids?

The biggest challenge is low voltage grid capacity, as these grids were not designed to connect many charging stations. Typically buried underground in Europe, rapidly increasing capacity is difficult compared to the US where you can add another line on poles. This means we must buy time by making the grid interaction increasingly smart to synchronize charging with local PV generation and minimize grid load. Further variables like heat pumps, stationary batteries, industrial processes, and buildings providing flexibility as thermal energy storage can contribute.

With your multimodal focus, how do you approach optimizing these systems for efficiency and sustainability without compromising reliability and accessibility?

I would argue it actually helps, as decarbonized systems automatically mean more decentralized structures with inherent redundancy benefiting reliability. In Germany, there are over 2 million decentralized electricity generators, mostly rooftop PV. Those multimodal couplings bring flexibility through inherent storage functionality, as any consumer able to delay consumption provides flexibility, improving reliability.

Could you elaborate on any recent conversion component advancements significantly impacting energy infrastructure sustainability?

No single technology solves the energy problem, but heat pumps can now provide higher temperatures up to 150°C or more at industrial scale, allowing use of waste heat sources. When gas prices spiked, many industrial sites invested in heat pumps to utilize previously wasted lower temperatures. Advancements in battery materials like sodium-ion instead of lithium, using abundant sodium, could also be a breakthrough even if energy density is lower. This mature technology already has cars manufactured in series in China. I still expect more battery surprises in the next two years as it remains a highly active research field.

How have lifecycle assessments influenced sustainable project design and development at Siemens?

We do extensive lifecycle assessments, aiming for all our products to have environmental product declarations by 2026, going beyond regulatory requirements. My team develops the methodology to increasingly automatically generate lifecycle assessments for hardware products, for software and service offerings.

In transitioning cities and regions to sustainable energy, how critical is AI’s role in forecasting, planning and managing these complex systems?

Currently, it’s not critical, but in the future AI can help rapidly find plausible assumptions when developing decarbonization roadmaps for cities or regions. You need assumptions on future consumption profiles for infrastructure that doesn’t exist yet, and AI can contribute plausible assumptions.

Lastly, reflecting on your career, what advice would you give young engineers and researchers aspiring to significantly impact sustainable energy and infrastructure?

I would advise young engineers to strive to truly understand fundamentals, as the laws of physics don’t change. At some point, resilience might become as important as sustainability. The multimodal, sector-coupled energy systems benefiting decarbonization are also advantageous for security of supply, so these topics are converging. Engineers also tend to forget understanding costs and developing a genuine interest in business models is extremely helpful.

About The Author

Scroll to Top
Share via
Copy link
Powered by Social Snap