Breaking News

Coronavirus spurs energy transition through artificial intelligence – DW (English)

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.” Wind turbines are not made to last forever. Anticipating material fatigue would be helpful to prevent accidents 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 says, 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. “From March 2020, JoinPad increased Smart assistance sales by 980% compared with the previous year,” Mauro Rubin, CEO of the Milan-based AR development firm, told DW. Through the use of AR, direct replacement is possible in the worldwide production network of German carmaker Daimler Smart assistance 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 $198.17 billion dollars by 2024,” says Rubin. 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 Berlin-based 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 open-source 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 told DW. Apart from issues related to privacy and employment, energy consumption is another question mark hanging over digitization. According to Johannes Sedlmeir, researcher at Munich-based 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.”