Announcement of winners of the 2nd Solar Power Generation Prediction AI Competition, which uses AI prediction technology to solve solar power generation issues

Announcement of winners of the 2nd Solar Power Generation Prediction AI Competition, which uses AI prediction technology to solve solar power generation issues ​ Smart Energy Co., Ltd. Press release: November 7, 2024 Announcement of winners of the 2nd Solar Power Generation Prediction AI Competition, which uses AI prediction technology to solve solar power generation issues Smart Energy Co., Ltd. (Headquarters: Minato-ku, Tokyo, Representative Director: Takuya Okushi, hereinafter referred to as Smart Energy) is co-hosting the “2nd Solar Photovoltaic Solar System” with Makoto Iida from ClimCORE, the University of Tokyo, and in cooperation with Weathernews Co., Ltd. The award ceremony for the Power Generation Prediction AI Competition was held on November 6th (Wednesday), and the winners were announced.
https://prcdn.freetls.fastly.net/release_image/6241/28/6241-28-8f8f94e13fa5ed9012fb7d2d043d07b1-2500×1667.jpg

What is the solar power generation prediction AI competition? This competition not only promotes the improvement of AI prediction technology and the utilization of advanced weather data, but also recognizes unique technologies, ideas, and their accuracy that solve the problems of solar power generation, which is said to be a naturally variable power source. Participants will create an AI model that predicts this year’s power generation amount based on the past two years’ power generation data and weather data from the solar power plants owned by Smart Energy, and compete for prediction accuracy. In the first round last year, the only evaluation criteria was the accuracy of the predictions, but this year we have established the following two divisions to evaluate the reproducibility of the AI ​​model as well. ■ Open category :Department that submits predicted values ​​and source code. In addition to prediction accuracy, validation of the AI ​​model is also scored. ■ Close department : Departments that are scored only based on predicted values. This applies to those who are unable to submit source code due to certain circumstances. In addition, we have made other changes from the previous competition, such as shortening the competition period and holding the competition in September, when the weather is more prone to change in order to require highly accurate predictions, based on the requests of previous participants. Tournament HP:
https://www.solar-forecast.jp/ Background Traditionally, solar power plants were mainly mega solar power plants installed on vast tracts of land, but due to a lack of suitable land, the trend is for low-voltage power generation equipment that can be installed on the roofs of buildings to increase in the future. As the number of low-voltage power generation facilities distributed across the country increases, it will become difficult to estimate and predict the amount of power generated, and the stable supply of solar power generation will become more complicated. Smart Energy, which has the top domestic market share (*) in the operation and maintenance of solar power plants, has collaborated with Mr. Makoto Iida, Project Associate Professor at the Research Center for Advanced Science and Technology, The University of Tokyo, and Weathernews Co., Ltd., in order to further stabilize the introduction of solar power. With our cooperation, we held this competition, which aims to develop solar power generation prediction technology using AI, as a continuation from last year (*Source: PVeye August 2023 issue of “Major O&M Companies” ranking). Scene from the award ceremony
https://prcdn.freetls.fastly.net/release_image/6241/28/6241-28-0346818a6780d0a3dfb24b7127b2468b-2500×1667.jpg
https://prcdn.freetls.fastly.net/release_image/6241/28/6241-28-6f031dbe4e8346dc7655dc2aa684c3c3-2500×1667.jpg “2nd Solar Power Generation Prediction AI Competition” screening results [Description of each award] ■Top award: The team with the smallest prediction error for the amount of power generated during the period will receive the award. Judgment is made based on the sum of prediction errors for the three target power plants. Open division: Prize money of 500,000 yen / Close division: Prize money of 50,000 yen ■Top award for each power plant: During the period, the award will be given to the team with the smallest prediction error for any of the three target power plants. Open category: Prize money 150,000 yen / Close category: Souvenir gift ■Special Jury Award: A review committee will evaluate the data processing techniques and select one team from all participating teams. *There are no duplicate awards for each award [List of award winners] Award Team name Company name Open Division Top Award Yuzoi v2 Okiden Global Systems Co., Ltd. Open Division Top Prize for Each Power Plant Kasumigaura Kamitsuchida Power Plant Division MAICS Mitsubishi Electric Corporation Open Division Top Prize for Each Power Plant Shioya Sanuki Power Plant Category TeamD Mitsubishi Electric Corporation Close Category Top Award Alone Osaka Gas Co., Ltd. Closed Division Top Prize for Each Power Plant Shioya Sanuki Power Plant Category shiojima1 Osaka Gas Co., Ltd. Special Jury Award Monzo NTT Data CCS Corporation Smart Energy Co., Ltd. Company Profile Established in 2007. We are a group of professionals who aim to realize a decarbonized society through business, with the mission of “Connecting a Beautiful Earth.” We provide solutions to solve global environmental problems through renewable energy operation and maintenance (O&M), new power business support, asset management business, renewable energy citizen fund formation business,
environmental consulting business, etc. HP:
https://www.smart-energy.jp/