Accurate solar power forecasting is crucial to integrate photovoltaic plants into the electric grid, schedule and secure the power grid safety. This problem becomes more demanding for those newly installed solar plants which lack sufficient data. Current research predominantly relies on historical solar power data or numerical weather prediction in a single-modality format, ignoring the complementary information provided in different modalities. In this paper, we propose a multi-modality fusion framework to integrate historical power data, numerical weather prediction, and satellite images, significantly improving forecast performance. We introduce a vector quantized framework that aligns modalities with varying information densities, striking a balance between integrating sufficient information and averting model overfitting. Our framework demonstrates strong zero-shot forecasting capability, which is especially useful for those newly installed plants. Moreover, we collect and release a multi-modal solar power (MMSP) dataset from real-world plants to further promote the research of multi-modal solar forecasting algorithms. Our extensive experiments show that our model not only operates with robustness but also boosts accuracy in both zero-shot forecasting and scenarios rich with training data, surpassing leading models. We have incorporated it into our eForecaster platform and deployed it for more than 300 solar plants with a capacity of over 15GW.

China is planning to build miles-wide'megastructures' in orbit, including solar power plants, tourism complexes, gas stations and even asteroid mining facilities. The National Natural Science Foundation of China (NSFC) announced a new five-year plan, directing researchers to develop technologies and techniques. The structures will require lightweight materials to allow larger objects to get into orbit with existing rockets. Researchers will also need to adopt technology to allow for in-orbit assembly and control. The Chinese government said there is an'urgent need' for megaprojects in space that would require ultra-large spacecraft to keep them in orbit.

At the edge of a plot of muddy farmland, a few miles down the road from the University of California at Davis, an engineer takes a few quick steps across crop rows and lets go of a three-foot drone. Within seconds, the device – which weighs less than 2lbs and carries a powerful camera – ascends hundreds of feet into the cold, clear, blue sky and begins to snap detailed photos of the ground far below, including a long row of large solar panels mounted on steel poles. This flight is just a test, demonstrated by Kingsley Chen, the drone fleet coordinator for SunPower at the solar company's research and development center, which is under construction and about a two-hour drive northeast of the San Francisco Bay Area. The drone will enable SunPower to survey a wide region and help design a solar power farm that can fit more solar panels on a piece of land, more quickly and for lower costs than it previously could. The test highlights a growing use of the latest computing technologies – drones, robots, software, sensors and networks – by US companies to design, build and operate solar farms.

Koichiro Otaki started taking aerial pictures of photovoltaic power stations in April 2015. At first, it was an innocent desire to capture their sheer scale and aesthetic value that motivated him, he says. Solar parks, mostly in rural, desolate areas, were also among the few places where he could practice flying a drone without having to worry about hitting people or tall structures, he says. Weather permitting, the 38-year-old freelance photographer would toss a compact drone into his backpack and venture out to the suburbs of Tokyo or up north to the Tohoku region by motorcycle, snapping away at solar panels neatly lined up along river banks, mountain slopes and even abandoned golf courses. "I was simply captivated by their geometric beauty," Otaki said of the panels.

Crescent Dunes looks and sounds a bit like an invention lifted from a science fiction novel. Deep in the Nevada desert more than 10,000 mirrors--each the size of a highway billboard--neatly encircle a giant 640-foot tower. It looks like it might be used to communicate with aliens in deep space. But the engineers and financiers behind the facility, located in the desert about halfway between Las Vegas and Reno, say the power plant's promise is anything but fiction. The solar power facility built and operated by the company SolarReserve can power 75,000 homes.