This product is a zip file that contains files that consist of PowerPoint slides synchronized with the audio-recording of the speaker, PDF files of the slides, and audio only (mp3 format) as noted.
High-fidelity building load forecasting model is critical for advanced GEB control. Data-driven load forecasting modeling, especially those that use machine learning methods, receives great interest recently due to its cost-effectiveness and scalability. This two seminar series provides an overview (Seminar I) of the current development, limitations, gaps and future trend of the application of machine learning in GEB load forecasting. Seminar I also discusses a general framework and strategies to defy data bias issues. Several case studies (Seminar II) using various machine learning methods are presented to demonstrate the effectiveness and performance of machine learning enabled load forecasting.
- 1. Machine Learning in Building Load Forecasting
Liang Zhang, Ph.D., Associate Member, National Renewable National Laboratory, Golden, CO
- 2. Development of Generalized Machine Learning Approach for Forecasting Electricity, Zone Temperature and Zone
Srinivas Katipamula, Ph.D., Fellow ASHRAE, Pacific Northwest National Laboratory, Richland, WA
- 3. Active Learning Strategy for High Fidelity Short-Term Data-Driven Building Energy Forecasting
Jin Wen, Ph.D., Member, Drexel University, Philadelphia, PA
Citation: ASHRAE 2020 Virtual Seminar
- Units of Measure:
- File Size:
- 1 file , 88 MB
- Product Code(s):