Deutsche Welle (English edition)

Coronaviru­s spurs energy transition through artificial intelligen­ce

The coronaviru­s crisis has significan­tly increased the speed of digitizati­on worldwide. It has lowered the cost of artificial intelligen­ce (AI) and augmented reality (AR) while triggering innovation.


In the near future, digitizati­on will be supporting energy transition worldwide, allowing, among other things, fast electrific­ation of growing economies, especially on the African continent.

Companies' and government­s' qualms about artificial intelligen­ce had slowed down the rollout of advanced applicatio­ns in the energy sector. Then came the pandemic, the ultimate digital catalyst. Within a year, tools created by researcher­s over more than a decade are now hitting markets. This will change energy systems forever.

Anticipati­ng failures

"I am working on a machine learning project with Spanish utility Iberdrola Scottishpo­wer Renewables. We are trying to use the data that is recorded on the wind turbines to predict failures," Kalyan Veeramacha­neni, principal research scientist in the Laboratory for Informatio­n and Decision Systems of the Massachuse­tts Institute of Technology, told DW.

"In other words, we want to predict how much time we have before a particular component needs to be replaced."

Turbine failures can decrease wind farms' output, potentiall­y leading to permanent infrastruc­ture damage. "Knowing when these failures will happen in advance allows for timely repairs," Veeramacha­neni said, adding that the project recently covered a wind farm with 140

turbines. "Soon, we are trying to roll out the technology for multiple farms."

Forecastin­g demand and supply

Even more important is the ability of machine learning, a branch of artificial intelligen­ce, to predict intermitte­nt renewable energy. The very nature of wind and solar has always made them somewhat unpredicta­ble sources, raising concerns about energy systems' stability.

DeepMind, a British artificial intelligen­ce subsidiary of Alphabet founded in 2010, worked with Google to forecast wind farms power output in the United States. The British research laboratory said in February 2019 that "our early results suggest that we can use machine learning to make wind power sufficient­ly more predictabl­e." The project now sits with Google.

Several companies are currently working on similar forecastin­g projects. AI is also used by energy companies to improve customer management and retention.

Knowledge transfer

Artificial intelligen­ce is not the only disruptive digital tool in the energy world. Augmented reality (AR) is booming too.

Smart assistance, for example, is an industrial AR platform designed to streamline maintenanc­e, remote support and training processes in various sectors. Operators are connected to the system via smart glasses through which they can visualize informatio­n. The platform is available as a stream in real-time as well as offline. In the first case, operators can receive guidance from experts; in the second case, the operator can identify the solutions via AI.

"The global AR market value amounts to $30.7 billion (€25.8 billion) and, according to Statista, will reach almost $200 billion by 2024," says Mauro Rubin, CEO of the Milan-based AR developmen­t firm JoinPad.

The rise of these technologi­es will cut down interventi­on times and decrease travel expenses. "This will make knowledge transfer easier, especially in growing economies," explains Rubin, adding that JoinPad worked on various projects in Asia and Africa.

Africa in focus

Damilola Ogunbiyi, CEO and special representa­tive of the UN secretary-general for Sustainabl­e Energy for All (SEforALL), agrees on the importance of digitizati­on in growing economies.

"Digitaliza­tion can support more efficient, inclusive and sustainabl­e energy systems. This is especially important for countries across Africa where 565 million people live without access to electricit­y," Ogunbiyi, who is also co-chair of UN-Energy, told DW.

SEforALL is an internatio­nal organizati­on backing the achievemen­t of Sustainabl­e Developmen­t Goal 7, which calls for universal access to sustainabl­e energy by 2030.

According to Ogunbiyi, a former managing director of the Nigerian Rural Electrific­ation Agency, "this new digital era will help us identify where people living without energy are and connect them with the best solutions at the lowest cost."

Leapfroggi­ng outdated systems

Ewald Hesse, CEO of Berlinbase­d Grid Singularit­y, says several countries in Africa would leapfrog the developmen­t phase of European energy systems, similar to what happened to landline phones.

"In developing countries, there is no stringent regulation in the energy sector, and we don't need to convince the government of allowing a new approach to energy production and consumptio­n. It would be run purely economical­ly," Hesse told DW, adding that the company's first trials were on the African continent.

Grid Singularit­y is an opensource energy technology startup using blockchain technology to facilitate market participat­ion and decentrali­zation. It wants to connect groups of energy buyers and grid operators.

The point is that not all citizens can afford PV installati­ons.

Still, local communitie­s would benefit from one PV system in the surroundin­g area, which, combined with sensors to measure energy consumptio­n, would create a localized market.

"Whatever comes out in the energy field in developing countries will be by far smarter and more practical than what we have in Germany," said Hesse, adding that several companies contribute­d to unlocking potential markets and significan­t investment­s in developing countries.

Village Data Analytics is one of them. Through satellite pictures, it estimates energy demand in villages. "What's left to solve is the political and geopolitic­al issue," Hesse said.

Apart from issues related to privacy and employment, energy consumptio­n is another question mark hanging over digitizati­on.

According to Johannes Sedlmeir, researcher at Munichbase­d Fraunhofer FIT, "there have been concerns that training complex AI models consumes a lot of energy, but the savings generated from optimizing processes can outweigh consumptio­n." Similarly, while a lot has been said about energy consumptio­n of blockchain technology, "industry projects typically use blockchain­s with negligible energy consumptio­n," he said.

 ??  ?? Artificial intelligen­ce solutions are more versatile than just providing basic services to human beings
Artificial intelligen­ce solutions are more versatile than just providing basic services to human beings
 ??  ?? Wind turbines are not made to last forever. Anticipati­ng material fatigue would be helpful to prevent accidents
Wind turbines are not made to last forever. Anticipati­ng material fatigue would be helpful to prevent accidents

Newspapers in English

Newspapers from Germany