The Aussie sun, supercharging superchargers and solar sheep

Hi all. In this week's digest we see how Australia is mixing solar panel detection and cloud cover detection to predict solar output, using AI to save EV batteries, keeping the grid alive amidst extreme weather events and how geospatial analysis can minimise risk and generate opportunities.

How much solar?: In the past week, solar has eclipsed coal as the lead source of electricity generation in Australia. Using satellite imagery, Solstice AI has identified solar panels on rooftops, including the direction they're facing so they can determine if they will get morning or afternoon sun. Combining this with real-time cloud cover identification they can create accurate forecasts of distributed solar output for suburbs and perhaps even whole regions and states. Using these forecasts, operators can manage scheduling of energy storage which once more community and household batteries are installed on low voltage networks, many of the issues surrounding the unpredictability of rooftop solar fleets can actually be managed locally by integrating forecasts with energy management software and AI technologies, rather than needing to call to centralised generators. [PV-Magazine-Australia]

Super-fast AI charging: One of the drawbacks of electric vehicles is the time it takes to recharge. While fast charging is available, it can also damage EV batteries in the long run. Researchers from Idaho National Laboratory are using machine learning to reduce charging times to 10 minutes or less without damaging the battery. ML will creating unique charging protocols based on the type of battery being charged - balancing quick charge without damaging the battery. "We've significantly increased the amount of energy that can go into a battery cell in a short amount of time," says Eric Dufek from Idaho National Laboratory's Energy Storage & Electric Transportation Department. "Currently, we're seeing batteries charge to over 90 percent in 10 minutes without lithium plating or cathode cracking." [InterestingEngineering]

Keeping the grid alive: As heatwaves sweep the globe, aging electrical grids are struggling to handle the energy demand, particularly in areas with large amounts of air conditioning. To avoid grid failures, power plant managers can take advantage of AI platforms with the capability to predict energy demand levels days in advance. Forecasting when best to perform maintenance, enact upgrades or charge or drain batteries can be crucial. AI platforms can revolutionize grid management with intelligent time horizon analyses and accurate energy consumption predictions, which will play crucial roles in increasing grid resiliency as scorching temperatures become more frequent. AI can also change the face of the energy industry by helping power plants successfully maximize the amount of solar and wind power into their operations. [TDWorld]

Driving clean energy: Northwestern University and Toyota Research Institute have joined forces to find materials to drive clean energy transition by using AI to design and synthesize next-generation materials to help reduce carbon emissions. They have developed the world's first nanomaterial "data factory", where AI searches different materials' genomes, and mixes them together to discover new applications, such as new catalysts to make fuel cell vehicles more efficient. TRI and Northwestern believe this method of materials discovery will have wide-ranging applications in the future.?[Northwestern]

The Data Crystal Ball: The intermittency of renewable energy continues to hold back full scale move away from fossil fuels, however the move to green technology is happening. But the move to low-carbon energy does create a number of challenges, particularly in regard to how grid operators manage the supply and demand of electricity. In some countries, the markets themselves are becoming more complicated and moving from prices changing every 30 minutes to every five. There are more than 400 variables, which can affect how a typical gas power plant can perform – including maintenance, fuel costs and the weather.?Energy Exemplar’s Plexos acts as “crystal ball for energy markets”. [Forbes]

Geospatial the way: As wildfires rage with seemingly increased frequency and ferocity, and floodwaters rise due to torrential rains in one region while drought dries lakes in another, geospatial data can be a critical aid in the preparation for disasters caused by climate change. Geospatial data is location intelligence, or the relationship between an event and the place where it occurs. By tracking changes in a single location over time, those analysing the data can see whether a location that once seemed safe from floods might now be vulnerable, or a location that once received enough rainfall to protect it from drought is now drier and more susceptible to fires. For a long time, in order to collect data, utility companies had to walk their power lines or drive their power lines to look at the vegetation next to the lines. Previously, looking at the vegetation once a year was probably fine. Now, conditions are changing rapidly, so the ability to use data collected from satellites and lidar enables them to look at all this on a much more frequent basis. [TechTarget]

TSO's Digital Strategy: With extreme weather events occurring more and more frequently, transmission operators are having to focus on day-to-day priorities. However, Paul Frey, chief operating officer at Sharper Shape, highlights the increasing importance of a digitised data strategy (DDS) for transmission and distribution (T&D) utilities. An underdeveloped DDS can expose a utility to a risk of life and death. To be clear, utilities are not responsible for the weather, but they are responsible for the state of their assets. Vegetation management is crucial as 6 of California's 20 most destructive wildfires since 2015 were caused by powerlines. a data-lead method involves strict prioritization of vegetation management hotspots based on previously harvested datapoints such as proximity to vegetation, species of tree, and proximity to residential property, for example. Smart use of data can transform daily operations by forming the basis for any number of next-gen approaches, such as living digital twins and drone-based automated inspection regimes. This in turn can create savings for the bottom line through new efficiencies. [Smart-Energy]

Intelligent workflows in oil & gas: Intelligent automation (IA) refers to the integration of robotics with multiple components from different emerging technologies.?Silos and data sets are seen as the main barriers within organisations and across the energy industry at large, which has led to such initiatives as the?Open AI Energy Initiative (OAI), a first-of-its-kind open ecosystem of AI solutions involving Shell, C3 AI, Baker Hughes and Microsoft. The OAI allows oil, cement and mining companies (amongst others) to commercialise their predictive maintenance applications. “The nearest analogue to what we’re trying to do with the OAI is to create an Apple App Store for the process industry” [Technology Magazine]

Solar sheep: Not an AI story but still a nice one. Denver-based?Guzman Energy almost didn’t get approval for a solar farm, but when the wholesale power provider agreed to add irrigation to support 1,000 sheep and possibly host beehives, it then gained unanimous approval. Sheep and solar panels paired together are a win-win because the solar panels provide shade and shelter for the sheep, and the sheep keep the grass trimmed, so the solar farm owners don’t have to maintain the grass. Also, the sheep get to eat for free. [Electrek]

Not much on the AI + energy podcasts this week - however this one is great look at offshore wind, something that will become more and more prominent in Ireland over the coming decades.

Offshore Wind in the US: Although offshore wind has been booming for decades in Europe, it has gotten a slow start in the US. But that’s about to change. From a single 30 MW offshore wind farm today, offshore wind capacity in the US is expected to reach 1 GW in just two years, and grow by a factor of 40 over the next two decades to 30 GW under a new target set by the US Government. [Energy Transition Show]

Thanks, Kev

All views my own - may not reflect views of my employer