The American-Made Solar Forecasting Prize is designed to better enable solar industry stakeholders with state-of-the-art solar forecasting capabilities. Sponsored by the U.S. Department of Energy Solar Energy Technologies Office, this prize aims to increase the use of the Solar Forecast Arbiter, an open platform developed by the University of Arizona, to allow for the transparent, rigorous, and consistent analysis and evaluation of solar forecasts.
Increasing Awareness of State-of-the-Art Solar Forecasting
Probabilistic forecasts are being recognized as a critical tool for cost-effective reserve allocation and unit scheduling. Considering a future with high-penetration weather-bound renewable energy generation is becoming increasingly important. But today, deployment and integration of these forecasts into energy management systems has not been widely adopted.
Additionally, independent system operators agree that solar forecasting is an important part of system operations, and forecasting becomes even more important as the fraction of variable weather-dependent generation increases.
The Solar Forecasting Prize aims to address this by:
Increasing stakeholder awareness of the state of the art in solar forecasting.
Incentivizing the participation of a broad range of competitors from the solar forecasting industry and research and development space.
Growing industry knowledge of the Solar Forecast Arbiter (SFA) platform and its potential.
Promoting the adoption of uniform and transparent metrics and specifications for solar forecasts using SFA (or similar platforms) by forecast end-users.
Identifying algorithms that perform better than a baseline probabilistic forecast.
Earn Cash Prizes for Successful Solar Forecasting
Up to five teams will win $50,000 each in cash prizes for showcasing the best performing algorithm and the strongest commercialization plan.
Five runner-up teams will also have the chance to earn $25,000 in cash prizes.
What Is the Solar Forecast Arbiter?
The Solar Forecast Arbiter (SFA) is an open forecasting platform developed by the University of Arizona. It allows for the transparent, rigorous, and consistent analysis and evaluation of solar forecasts by end-users.
In case you missed it, we recently announced a new prize you might be interested in: the Net Load Forecasting Prize! Learn about this $600,000 competition and how you can get involved at an informational webinar on Feb. 20.
The American-Made Net Load Forecasting Prize is designed to incentivize innovators to develop probabilistic tools that predict amounts of net load a day in advance of the forecast and promote the adoption of probabilistic forecasts and evaluation tools for those forecasts.
Competing teams are challenged to create a forecasting model that can predict the net load of four specified locations over 28 days. The teams with the most accurate model at the end will receive cash prizes.
This prize is an updated version of last year’s Solar Forecasting Prize. Whether or not you participated in the prize, we invite you to join the Net Load Forecasting Prize for your shot at $200,000. Follow the competition on HeroX to receive updates and register your team by March 27.
Join the upcoming informational webinar to hear first-hand from prize administrators about eligibility, deadlines, and submission requirements, then get your questions answered at a live Q&A session! Register now for the informational webinar on Feb. 20 at 3 p.m. ET. We hope to see you there.
The leading transmission and distribution event, DISTRIBUTECH International®️, is coming up—and the American-Made team will be there! Join us in San Diego Feb. 7–9 for unparalleled education and networking opportunities and the chance to talk with American-Made prize administrators. Come find us at EPRI booth #5216! We’d love to hear from Solar Forecasting Prize competitors and followers about their experience with the prize.
Attendees of DISTRIBUTECH will be able to choose from 13 expert-led education tracks and visit the packed trade show floor, feature more than 400 solution providers and experts steeped in the technologies used to move electricity from the power plant through the transmission and distribution systems to the meter and inside the home or business.
Register today and use promo code DTPART4 to save 20%! We hope to see you there!
The $1.1-million Digitizing Utilities Prize—sponsored by U.S. Department of Energy’s Office of Electricity—invites experts in data analytics and software development to transform digital systems in the energy sector through data processing, quality assurance, storage, and deletion.
In Phase 1, competitors will work directly alongside utility partners to propose a solution that improves how the energy industry manages, stores, and processes large data sets. Up to nine winners of Phase 1 will receive a cash prize of $75,000.
In addition, mark your calendars for Wednesday, November 15 at 12 p.m. MT. Register now to learn more about the prize timeline and deliverables. A recording of the webinar will be available after the event.
If you’re interested in transforming digital systems in the energy sector, we encourage you to compete in the Digitizing Utilities Prize. The deadline to enter is Thursday, January 26, 2023. Good luck!
Congratulations to the Solar Forecasting Prize winners and runners-up, announced by the Tassos Golnas, Solar Forecasting Prize Lead in the Solar Energy Technologies Office, during the CMU Energy Week Virtual Networking Mixer!
The five winners and two runners-up were selected based on their performance in the forecast evaluation period as well as the quality of their commercialization plans, which proposed innovative solutions for deployment. Each winner was awarded $50,000 in cash prizes, while runners-up earned $25,000 each.
Please join us in congratulating the following winners and runners-up:
Solar Forecasting Prize Winners
Leaptran - San Antonio, TX Integrated Solar Forecasting Solutions This team used crowd-sourced weather data and algorithms, leveraging site-specific data fusion, to achieve intra-day and days-ahead solar forecasting. This model offered a >50% improvement of days-ahead, intra-hour, and intra-day solar forecasting accuracy by integrating asset-level data.
Nimbus AI -Honolulu, Hawaii Fast Solar Forecasting with Machine Learning This team developed a fast and inexpensive system for geographically flexible, hyper-local day-ahead probabilistic solar forecasting. The team combined historical ground- andsatellite-based instrument data with physics-based numerical weather prediction (NWP) techniques to produce probabilistic forecasts.
Northview Weather - Danville, VT Determining Who Wins the Cumulus vs. Stratus Battle This team developed a solar forecasting method that uses a mesoscale weather forecast model to produce a dynamically based spread of probabilistic solar power forecast information. Probabilistic information is also tuned blending statistical information and machine learning of historic sky cover observations.
UM (University of Michigan) CLaSP - Ann Arbor, MI A Novel Hybrid Approach for Solar Forecasting This team developed a hybrid solar forecasting method using ground horizontal irradiance based on a recursive neural network (RNN), trained with past observations and a weather-regime-dependent empirical bias correction scheme. The team based this scheme on the RNN output and the multi-day weather forecast made from NWP.
WenYuan Tang -Apex, North Carolina A Hybrid Approach to Probabilistic Forecasting This team developed a simple (low-data-cost and low-computational-cost) yet effective solar forecasting method that includes learning from many base models, as well as physical and statistical models, to provide a comprehensive tool for both forecasting and grid optimization. This team provided a simple yet effective model that is easy to interpret, train, validate, and deploy, thus overcoming the barriers of experimentation and adoption by utilities and other end users.
Solar Forecasting Prize Runners-up:
Matt Motoki - Aiea, Hawaii RadianceIQ This team developed an advanced machine learning technique for probabilistic forecasting that utilizes custom deep neural networks to directly minimize the Continuous Ranked Probability Score (CRPS) loss with no post-processing calibration needed. This method allowed for greater accuracy and its lightweight architecture allows it to run faster than NWP ensembles and other machine learning approaches.
Syracuse University Team - Syracuse, NY Weather Adaptive Probabilistic Solar Forecast This team developed a weather-adaptive probabilistic day-ahead solar forecast methodology that leverages innovations in machine learning and statistics. This model could adapt to different weather patterns for an accurate forecast under varying weather conditions.
Congratulations to these teams for their outstanding work in the Solar Forecasting Prize!
The event kicks off at 3:30 p.m. ET with a free networking session for energy industry stakeholders. The mixer is open to anyone looking to forge connections with top innovators, organizations, students, and entrepreneurs in the energy industry. Whether or not you are a Solar Forecasting Prize competitor, you’re invited to join this networking event.
The event will wrap up with the announcement of the Solar Forecasting Prize winners and runners-up. RSVP now for the Virtual Networking Mixer!
