Toggle light / dark theme

Dr. Valentin Robu, Associate Professor and Academic PI of the project, says that this work was part of the NCEWS (Network Constraints Early Warning System project), a collaboration between Heriot-Watt and Scottish Power Energy Networks, part funded by InnovateUK, the United Kingdom’s applied research and innovation agency. The project’s results greatly exceeded our expectations, and it illustrates how advanced AI techniques (in this case deep learning neural networks) can address important practical challenges emerging in modern energy systems.


Power networks worldwide are faced with increasing challenges. The fast rollout of distributed renewable generation (such as rooftop solar panels or community wind turbines) can lead to considerable unpredictability. The previously used fit-and-forget mode of operating power networks is no longer adequate, and a more active management is required. Moreover, new types of demand (such as from the rollout EV charging) can also be source of unpredictability, especially if concentrated in particular areas of the distribution grid.

Network operators are required to keep power and voltage within safe operating limits at all connection points in the , as out of bounds fluctuations can damage expensive equipment and connected devices. Hence, having good estimates of which area of the network could be at risk and require interventions (such as strengthening the network, or extra storage to smoothen fluctuations) is increasingly a key requirement.

Privacy-sensitive machine learning

Smart meter data analysis holds great promise for identifying at risk areas in distribution networks. Yet, using smart meter data can present significant practical constraints. In many countries and regions, the rollout of smart meters does not provide full coverage, as installation is voluntary and many customers may reject installing a smart meter at their home. Moreover, even places where there is a successful smart meter roll-out, privacy restrictions must be taken into account and, in practice, regulators considerably constrain what private data from smart meters network operators have access to.

What was that again about wind and solar power being unreliable? Some energy pundits are still tossing that old ball around, but meanwhile savvy investors are plowing billions into new energy storage facilities that spit out clean kilowatts on demand. Like they say, money talks, and in a fitting twist the latest example comes from the Golden State, California.

Massive New Energy Storage Facility For The Golden State

California has plenty of both wind and solar, and it also has an ambitious renewable energy goal, which makes it the perfect spot to launch ambitious clean power projects such as massive new energy storage facilities.

Over the last few decades, various forms of solar power stations have been proposed from around the world but they remained theoretical because of major technical challenges.

At Bishan, Chinese researchers would first need to prove that wireless power transfer worked over a long distance.


Civilian and military researchers will look at applications for the technology amid concerns about radiation and the potential for beams misfired from space.

Heat flows naturally through the TEG because its cold side is kept at room temperature, while its hot side, which is in thermal contact with the cell, is at a high temperature. The Seebeck effect, which is the direct conversion of temperature differences between two semiconductor materials into electric voltage, generates this difference which then translates into additional electrical power.

The scientists decided not to use a spectrum splitting technology, which is generally utilized in these applications, to direct different parts of the solar spectrum towards either the PV or the TEG unit. “It is more convenient, in terms of final efficiency gains, to keep the solar cell at the same temperature of the TEG hot side, instead of keeping the cell cold but losing much of the recoverable heat,” the academics explained, noting that a wide-gap solar cell based on perovskite was chosen for the device, due to its lower sensitivity to high temperatures. “Temperature-sensitive materials, such as silicon, lose too much efficiency to make the hybridization convenient,” they further explained.

German researchers developed a lattice arrangement of three different layers of ferroelectric crystals that created a powerful photovoltaic effect.


Combining ultra-thin layers of different materials can raise the photovoltaic effect of solar cells by a factor of 1,000 according to researchers at Martin Luther University Halle-Wittenberg (MLU) in Germany.

Their findings, published in the journal “Science Advances,” described a lattice arrangement of three different layers of ferroelectric crystals (in this case, of barium titanate, strontium titanate, and calcium titanate) that created a powerful solar energy producing effect.

Ferroelectric means that the material has spatially separated positive and negative charges. The charge separation leads to an asymmetric structure that enables electricity to be generated from light.

Circa 2016


Scientists and engineers since the 1940s have been toying with the idea of building self-replicating machines, or von Neumann machines, named for John von Neumann. With recent advances in 3D printing (including in zero gravity) and machine learning AI, it seems like self-replicating machines are much more feasible today. In the 21st century, a tantalizing possibility for this technology has emerged: sending a space probe out to a different star system, having it mine resources to make a copy of itself, and then launching that one to yet another star system, and on and on and on.

As a wild new episode of PBS’s YouTube series Space Time suggests, if we could send a von Neumann probe to another star system—likely Alpha Centauri, the closest to us at about 4.4 light years away—then that autonomous spaceship could land on a rocky planet, asteroid, or moon and start building a factory. (Of course, it’d probably need a nuclear fusion drive, something we still need to develop.)

That factory of autonomous machines could then construct solar panels, strip mine the world for resources, extract fuels from planetary atmospheres, build smaller probes to explore the system, and eventually build a copy of the entire von Neumann spacecraft to send off to a new star system and repeat the process. It has even been suggested that such self-replicating machines could build a Dyson sphere to harness energy from a star or terraform a planet for the eventual arrival of humans.

Farmers reap double benefits with solar power in fields Solar panels generate electricity in the fields, helping both farmers and climate protection. DW visits a German solar farm — and looks at other places this combination is paying off. How widely can agrovoltaics spread? Fabian Karthaus grew u…

Wind farms certainly allow for the production of clean energy. Although they are 100% renewable, they still have problems. They have high costs, disfigure the landscape, produce noise pollution, and above all, have a heavy impact on fauna, and in particular on birds.

The Spanish startup Vortex Bladeless has developed a bladeless turbine that can revolutionize wind energy, especially at the household level, and become the alternative to solar panels. The design of the Spanish firm has already received the approval of Norway’s state energy company, Equinor.

The new turbine, which has also been called the “Skybrator” due to its phallic shape, is capable of harnessing energy from winds without the sweeping white blades everyone associates with wind power. It generates wind energy thanks to vibration and without generating the environmental and visual impact on the fauna of the large wind farms.

It’s the stuff of science fiction: Solar panels in space that beam power directly to Earth equipping the planet with clean renewable and affordable energy. Yet, it could soon be reality.

Caltech has just received $100 million in funding for their Space Solar Power Project (SSPP). The project is described by Caltech as: “Collecting solar power in space and transmitting the energy wirelessly to Earth through microwaves enables terrestrial power availability unaffected by weather or time of day. Solar power could be continuously available anywhere on earth.”

“This ambitious project is a transformative approach to large-scale solar energy harvesting for the Earth that overcomes this intermittency and the need for energy storage,” said SSPP researcher Harry Atwater in the Caltech press release on the matter.