Aerospace firm Airbus has completed two 18-day stratospheric flights of its solar-powered aircraft, called Zephyr, 76,100 feet above the Earth. Zephyr's solar powered test flights in the stratosphere – the second layer of the Earth's atmosphere – set a new world record for altitude this summer, Airbus says. The firm now wants to deploy the'high altitude pseudo-satellite' (HAPS) for surveillance and beaming broadband down to remote areas that don't have internet. Zephyr, an UAV with two small propellers, is powered exclusively by the Sun, thanks to solar panels lining its whole 82-foot wingspan. It's typically hand-launched by four to five ground crew, fast-walking or jogging into a light wind, but it features on-board software for remote navigation.

A new white paper published by the World Economic Forum explains in detail the immense of potential of Artificial Intelligence in the energy transition. The scenario it describes is exciting, but a lot of work needs to be done. Last month saw the publication of a white paper by the World Economic Forum, in collaboration with BloombergNEF ("New Energy Finance") and Deutsche Agenzie-Agenture (dena): "Harnessing Artificial Intelligence to Accelerate the Energy Transition." As a global leader in renewable energy, the Enel Group was also involved, and Giuseppe Amoroso, Head of Digital Strategy and Governance in Enel, was a member of the Paper's editorial team. The White Paper explains that "The global energy system is currently undergoing a massive transformation, and in the decades ahead, it will continue to become more decentralized, digitalized and decarbonized."

The uncertainty of the energy generated by photovoltaic systems incurs an additional cost for a guaranteed, reliable supply of energy (i.e., energy storage). This investigation aims to decrease the additional cost by introducing probabilistic multi-task intra-hour solar forecasting (feasible in real time applications) to increase the penetration of photovoltaic systems in power grids. The direction of moving clouds is estimated in consecutive sequences of sky images by extracting features of cloud dynamics with the objective of forecasting the global solar irradiance that reaches photovoltaic systems. The sky images are acquired using a low-cost infrared sky imager mounted on a solar tracker. The solar forecasting algorithm is based on kernel learning methods, and uses the clear sky index as predictor and features extracted from clouds as feature vectors. The proposed solar forecasting algorithm achieved 16.45\% forecasting skill 8 minutes ahead with a resolution of 15 seconds. In contrast, previous work reached 15.4\% forecasting skill with the resolution of 1 minute. Therefore, this solar forecasting algorithm increases the performances with respect to the state-of-the-art, providing grid operators with the capability of managing the inherent uncertainties of power grids with a high penetration of photovoltaic systems.

Enterprises and labs performing computationally expensive data science applications sooner or later face the problem of scale but unconnected infrastructure. For this up-scaling process, an IT service provider can be hired or in-house personnel can attempt to implement a software stack. The first option can be quite expensive if it is just about connecting several machines. For the latter option often experience is missing with the data science staff in order to navigate through the software jungle. In this technical report, we illustrate the decision process towards an on-premises infrastructure, our implemented system architecture, and the transformation of the software stack towards a scaleable GPU cluster system.

Strategy Development has followed a set path since the last century where a predetermined, rectilinear, and inflexible approach defined the process. In the 21st century, however, business leaders are devising Strategy by evolving it into a probabilistic, repeated, and multifaceted process. An approach that can both endure and adapt to the growing pace of Change and Disruption that is manifesting itself in all industries. Using gaming, AI, unremitting execution, and adjustment, with numerous scenarios to deliberate on, leaders create "Flywheels" that successfully tackle the not so deterministic world where the future is highly uncertain. Flywheel is a concept originally used in the power industry to explain an origin of stabilization, energy storage, and momentum.

We're now more than two decades out from the initial announcement of the National Nanotechnology Initiative (NNI), a federal program from President Bill Clinton founded in 2000 to support nanotechnology research and development in universities, government agencies and industry laboratories across the United States. It was a significant financial bet on a field that was better known among the general public for science fiction than scientific achievement. Today it's clear that the NNI did more than influence the direction of research in the U.S. It catalyzed a worldwide effort and spurred an explosion of creativity in the scientific community. And we're reaping the rewards not just in medicine, but also clean energy, environmental remediation and beyond. Before the NNI, there were people who thought nanotechnology was a gimmick. I began my research career in chemistry, but it seemed to me that nanotechnology was a once-in-a-lifetime opportunity: the opening of a new field that crossed scientific disciplines.

False data injection attacks (FDIAs) represent a major class of attacks that aim to break the integrity of measurements by injecting false data into the smart metering devices in power grids. To the best of authors' knowledge, no study has attempted to design a detector that automatically models the underlying graph topology and spatially correlated measurement data of the smart grids to better detect cyber attacks. The contributions of this paper to detect and mitigate FDIAs are twofold. First, we present a generic, localized, and stealth (unobservable) attack generation methodology and publicly accessible datasets for researchers to develop and test their algorithms. Second, we propose a Graph Neural Network (GNN) based, scalable and real-time detector of FDIAs that efficiently combines model-driven and data-driven approaches by incorporating the inherent physical connections of modern AC power grids and exploiting the spatial correlations of the measurement. It is experimentally verified by comparing the proposed GNN based detector with the currently available FDIA detectors in the literature that our algorithm outperforms the best available solutions by 3.14%, 4.25%, and 4.41% in F1 score for standard IEEE testbeds with 14, 118, and 300 buses, respectively.

A robot avatar that mimics the motions of a human controller could take the place of workers in several dangerous jobs, such as tree trimming and construction, by the end of 2022. The challenge: If a tree branch gets too close to a power line, it can cause electrical outages or, even worse, dangerous fires (as Californians know all too well). To avoid this, utility companies have to regularly trim trees near their lines. But it's dangerous work, as workers are dozens of feet above the ground, using sharp power tools to trim trees while power lives are still active -- this puts them at risk of falls, cuts, and electrocution, all at once. By some estimates, tree trimming is one of the most dangerous jobs in the country.

From 2012 to 2018, for instance, the computational cost of advanced AI applications that use deep-learning models increased by 300,000 times, causing a significant rise in electric power consumption and resource utilization. The emerging green AI, or environmentally friendly AI, on the other hand, addresses the issue by minimizing ML's computational demand and reducing its carbon footprint.

Companies who have some success with their initial AI projects are seeking ways to accelerate adoption to deliver more value to the business. One researcher has defined an AI Adoption Maturity Model that presents a roadmap for accelerating AI adoption. The first stage of the six-step AI adoption maturity model is the digitization of work, turning work in the physical world into digital processes that can be tracked and recorded as data, suggests Dr. Michael Wu, chief AI strategist for PROS Holdings, providing AI-based software as a service for pricing optimization, with a focus on the airline industry. "This stage is all about getting the data, which is the raw material for AI," stated Wu, in an account from ZDNet. "If you are on the digital transformation bandwagon, good for you. You are already in Stage 1 of this maturity curve."