Big Tech's appetite for energy is just about visible from the east coast of Scotland. Some 12 miles out to sea sits a wind farm, where each of the 60 giant turbines has blades roughly the length of an American football field. The utility companies behind the Moray West project had promised the site would be capable of generating enough electricity to power 1.3 million homes once completed. That was before Amazon stepped in. In January, Amazon announced it had struck a deal to claim more than half the site's 880 megawatts of output, part of its ongoing attempt to slake its unquenchable thirst for power.

As future energy systems become more decentralised due to the integration of renewable energy resources and storage technologies, several autonomous energy management and peer-to-peer trading mechanisms have been recently proposed for the operation of energy hub networks based on optimization and game theory. However, most of these strategies have been tested either only in simulated environments or small prosumer units as opposed to larger energy hubs. This simulation reality gap has hindered large-scale implementation and practical application of these method. In this paper, we aim to experimentally validate the performance of a novel multi-horizon distributed model predictive controller for an energy hub network by implementing the controller on a complete network of hubs comprising of a real energy hub inter-faced with multiple virtual hubs. The experiments are done using two different network topologies and the controller shows promising results in both setups.

Electricity grids have become an essential part of daily life, even if they are often not noticed in everyday life. We usually only become particularly aware of this dependence by the time the electricity grid is no longer available. However, significant changes, such as the transition to renewable energy (photovoltaic, wind turbines, etc.) and an increasing number of energy consumers with complex load profiles (electric vehicles, home battery systems, etc.), pose new challenges for the electricity grid. To address these challenges, we propose two first-of-its-kind datasets based on measurements in a broadband powerline communications (PLC) infrastructure. Both datasets FiN-1 and FiN-2, were collected during real practical use in a part of the German low-voltage grid that supplies around 4.4 million people and show more than 13 billion datapoints collected by more than 5100 sensors. In addition, we present different use cases in asset management, grid state visualization, forecasting, predictive maintenance, and novelty detection to highlight the benefits of these types of data. For these applications, we particularly highlight the use of novel machine learning architectures to extract rich information from real-world data that cannot be captured using traditional approaches. By publishing the first large-scale real-world dataset, we aim to shed light on the previously largely unrecognized potential of PLC data and emphasize machine-learning-based research in low-voltage distribution networks by presenting a variety of different use cases.

Alphabet's Google Cloud empowers organisations to digitally transform themselves into smarter businesses. Its diverse solutions include cloud computing, data analytics, and the latest artificial intelligence (AI) and machine learning tools. Last week, many of the platform's latest advances were shared at Next '22, Google Cloud's annual developer and tech conference about digital transformation in the cloud. We've partnered with Google Cloud over the last few years to apply our AI research for making a positive impact on core solutions used by their customers. Here, we introduce a few of these projects, including optimising document understanding, enhancing the value of wind energy, and offering easier use of AlphaFold.

The energy grid is a complex network of hard and soft infrastructure that delivers electricity from producers to consumers. Producing the electricity that powers our homes and businesses involves dozens of steps, including generation, transmission, distribution, and consumption. Luckily, most people in the United States don't have to think about this process. They simply pay the electricity bill each month and the lights come on. The electricity grid in the United States has remained relatively stagnant for decades.

BRUSSELS – (Thomson Reuters Foundation) – As climate change intensifies the devastation from storms, wildfires and droughts, artificial intelligence (AI) and digital tools are increasingly being seen as a way to predict and limit its impacts. Governments, tech firms and investors are showing growing interest in machine-based learning systems that use algorithms to identify patterns in data sets and make predictions, recommendations or decisions in real or virtual settings. In June, the Rise Fund, an impact investing arm of private equity firm TPG, invested $100 million in a data and AI-driven "nowcasting" system devised by Kentucky-based startup Climavision to predict weather patterns with granular accuracy. And an intergovernmental roadmap on AI's role in fighting global warming is due to launch at November's COP26 climate summit in Scotland. But AI can also be highly energy-intensive and environmentally damaging, say critics who warn that the tech could be a costly distraction from more effective ways of tackling climate change.

Earlier this month, under its "The Future of Everything" vertical, The Wall Street Journal reported how AI is improving the power grid. The Journal says artificial intelligence is "the key to keeping the lights on." The article explains how power companies are "turning to AI, drones, and sensors to curtail outages, save money, and help operate an increasingly complex electricity grid." Further, by doing so, they cut the recovery time from hurricane-related outages nearly in half in just a little over a decade. But these improvements are just the beginning of how artificial intelligence will manage the electricity grid of the future.

The carbon footprint of algorithms must be measured and transparently reported so computer scientists can take an honest and active role in environmental sustainability. In this paper, we take analyses usually applied at the industrial level and make them accessible for individual computer science researchers with an easy-to-use Python package. Localizing to the energy mixture of the electrical power grid, we make the conversion from energy usage to CO2 emissions, in addition to contextualizing these results with more human-understandable benchmarks such as automobile miles driven. We also include comparisons with energy mixtures employed in electrical grids around the world. We propose including these automatically-generated Energy Usage Reports as part of standard algorithmic accountability practices, and demonstrate the use of these reports as part of model-choice in a machine learning context.

LAUNCESTON, Australia (Reuters) - One of humankind's most enduring weaknesses is to assume that the way things are presently will somehow persist into the future, and that current trends are inexorable. This thinking is behind the often repeated view that renewable energy sources such as wind and solar cannot replace thermal electricity generation such as coal and natural gas. Presently, it is correct that the most significant weakness of these renewables is that they are intermittent, meaning they don't generate close to their installed capacity and cause instability in electricity grids. While storage through batteries or pumped hydro is often touted as a solution to the drawbacks of wind and solar, there are other emerging technologies that may well make renewables more effective. One of those is harnessing artificial intelligence (AI) to improve the efficiency of wind and solar by using machine learning programmes to enhance predictability of generation and grid stability.

Existing power grids were designed to transmit electricity over relatively short distances, however, increasingly grids are required to supply major cities from remote offshore wind farms at the same time as integrating local generation. With generators feeding variable amounts of energy from renewable sources into the grid at all voltage levels, it is more difficult to balance supply and demand, and the risks of overloads and fluctuations increase. By 2020 it is estimated that there will be over 50 billion smart devices connected to the internet, creating vast quantities of data which can be harnessed to develop smart systems for managing electricity systems, both at a local and national level to reduce the costs of balancing the electricity system. Relying on traditional linear mathematical models to manage these processes is not feasible, since both the manpower required to encode the models and the computing power to process them would be extremely large. A more real-time approach is required.