Currents: AI & Energy Insights - May 2024

Welcome back to Currents, a monthly column from Reimagine Energy dedicated to the latest news at the intersection of AI & Energy. Every last Sunday of the month I’m sending out an expert-curated summary of the most relevant updates from the sector. The focus is on major industry news, published scientific articles, a recap of the month’s posts from Reimagine Energy, and a dedicated job board.

1. Industry news

1. Electricity Maps has raised €5 million in a financing round led by climate funds Transition and Revent. The funding is aimed at helping them scale up, hire more staff, and enhance their app and API to provide more detailed mapping of global electricity grids. Electricity Maps provides granular historical, real-time, and forecasted data for carbon emissions in over 230 regions globally.
   
   What I’m thinking: I’m glad to see Electricity Maps grow as they are providing a key service that many AI startups and companies in the energy field can build upon. Their data is essential for AI systems to understand the real-time and forecasted state of the electricity grid and make informed decisions about when and where to consume electricity.
   
   Read the full press release here.

2. IKEA introduced the Energy Insights feature in its smart home app, initially piloted in Sweden. The tool offers real-time monitoring of household energy consumption, helping users identify power-hungry devices and compare usage with similar households. The consumption analysis is also matched with real-time data of the price of electricity, to help users run their energy-intensive appliances more efficiently. You can find the official article here.
   
   What I’m thinking: It’s increasingly important to expose customers to their consumption and pricing data, especially as we experience increasingly frequent negative electricity prices. As we move towards a future with more heat pumps, solar panels, and EV chargers, consumers will need to make numerous decisions about how and when to use energy at home. Until now, companies have not invested significantly in this kind of product, as there’s traditionally been limited value to be extracted from the residential sector. However, as part of a broader program from IKEA, integrating energy insights into the smart home ecosystem makes a lot of sense. I believe that more and more similar products will start to appear on the market.

Source: Ikea

3. U.S. regulators approved new rules that will enable faster construction of new transmission lines and better long-term planning. Grid operators will now be required to plan 20 years into the future, considering factors such as changes in energy sources, state renewable energy mandates, and risks from extreme weather. Read more in this paid article and official news release.
   
   What I’m thinking: For years, experts have highlighted the electricity transmission infrastructure as a key concern, recognizing it as one of the primary bottlenecks limiting the growth of renewable energy. This new regulation targets critical aspect of grid modernization and will likely increase demand for AI-driven tools that can optimize grid operations and assist in the long-term planning process. Europe, facing similar challenges, will likely need to adopt comparable measures soon.

4. The OpenEAC Alliance was launched. The OpenEAC Alliance is an industry group dedicated to ensuring quality, consistency, and transparency in the measurement and verification of distributed energy resources (DERs). Its key objective is to overcome structural barriers that have hindered the proper valuation of DERs’ climate benefits by establishing transparent and consistent industry standards for their measurement and reporting.
   
   What I’m thinking: If you know me, you’ll know that I strongly believe that accurate and trustworthy measurement and verification can unlock billions of investments in energy efficiency and clean energy technologies. I participated in the kickoff meeting this month, and it was refreshing and empowering to see so many like-minded professionals. I’m looking forward to the next meetings and getting to know the other members of the Alliance better. You can find a recording of the event and instructions to get involved at the following link:

The OpenEAC Alliance Kicks Off!

2. Scientific publications

It’s hard to keep track of everything that is released in the academic sector, but I always try to reserve some time to look at the most interesting publications of the month. Two articles from academia caught my attention in May:

1. Detailed operational building data for six office rooms in Denmark: Occupancy, indoor environment, heating, ventilation, lighting and room control monitoring with sub-hourly temporal resolution. by Simon Pommerencke Melgaard et al.
   This publication is actually from a couple months back, but I only came across it now. The article presents a comprehensive dataset collected from six office rooms at Aalborg University in Denmark. The dataset includes occupancy, indoor environmental quality, heating, ventilation, lighting, and room control data. It also features high temporal resolution and nearly year-long span, capturing different seasons and operational conditions.The full dataset is available here.

   
   What I’m thinking: Ground-truth occupancy data with high granularity is precious and extremely hard to come by. The dataset could be used to build a predictive model to estimate building occupancy based on CO2 and temperature sensor values. While the coverage of only six rooms may limit generalizability, the five-minute measurement resolution can offer a pretty detailed view of occupancy and environmental conditions.

2. SWOAM: Swarm optimized agents for energy management in grid-interactive connected buildings by Chia E. Tungom et al.
   The paper introduces a novel framework that combines swarm intelligence and online k-means clustering to optimize energy management in grid-interactive buildings. The collaborative approach enhances scalability and adaptability, making it particularly suitable for optimizing energy usage across multiple buildings, providing stability and rapid adaptability to changing conditions.
   
   What I’m thinking: Reinforcement Learning applications, which seemed to be the technology that would finally enable grid-interactive buildings, have shown to struggle with scalability and adaptability. It’s interesting to look now at a potential scalable alternative which seemingly shows stability and rapid adaptability to changing conditions. While having a network of buildings intelligently synchronize and interact with the grid in an optimized way might sound like science fiction to some, I find this to be one of the most promising and fascinating areas of research right now. Solving this extremely complex problem will be a key breakthrough in the energy transition.

3. Reimagine Energy publications

The two articles published this month featured part 2 and 3 of our Python tutorial on how to build counterfactual energy models to estimate energy efficiency savings:

Code Tutorial: Building a Counterfactual Energy Model for Savings Verification - Part 2

Code Tutorial: Building a Counterfactual Energy Model for Savings Verification - Part 3

4. AI in Energy job board

This space is dedicated to job posts in the sector that caught my attention during the last month. I have no affiliation with any of them, I’m just looking to help readers connect with relevant jobs in the market.

1. Data Scientist Internship at ABB

2. Data Scientist - Metereology at Dexter Energy

3. Data Science Leader at Infogrid

4. Doctoral student in integrated geospatial planning of energy access at KTH

Conclusion

With so much going on in the sector it’s not easy to follow everything. If you’re aware of anything that seems relevant and should be included in Currents (job posts, scientific articles, relevant industry events, etc.) please answer to this email or reach out to me on LinkedIn and I’ll be happy to consider them for inclusion!