- Numerical prediction
- Probability prediction
Predictive technologies using weather simulations
Accurately predict electric power demand and renewable energy generation volumes.
- Highly accurate predictions achieved by combining independently operating weather prediction systems and machine learning
- Used in predictive services for electric power companies to support stable power supply and power market transactions.
Applications
- Electric power demand predictions in Kanto and other regions
- Solar power generation predictions
- Public transportation demand predictions
- Predictions for other indexes impacted by weather
Benchmarks, strengths, and track record
- First Prize in Tokyo Electric Power Company Holdings, Inc.’s “First Electricity Load Forecasting Technology Contest”
- Grand Prize in the “PV in HOKKAIDO Contest on Technology for Predicting Solar Energy Production” held jointly by Tokyo Electric Power Company Holdings and Hokkaido Electric Power Co.,Ltd.
Inquiries
Please include the title “Toshiba AI Technology Catalog: Predictive technologies used in weather simulations” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.
References:
- Shin Hiromasa et.al.; “Highly accurate electric power demand prediction using weather prediction data and machine learning”, Toshiba Review; Vol. 74, No. 5, 2019.
- “Developed a highly accurate solar power generation volume prediction technology using Toshiba’s original AI” (in Japanese)
- “Developed a highly accurate electric power demand prediction system using AI” (in Japanese)