Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Foresee the Future: Using Machine Learning, Climate, and Site Characteristics to Predict PV Solar Plant Generation

Technical Report ·
DOI:https://doi.org/10.2172/1592882· OSTI ID:1592882
 [1];  [2]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  2. Trimark Associates, Inc., Folsom, CA (United States)

Accurately predicting power generation for PV sites is critical for prioritizing relevant operations & maintenance activities, thereby extending the lifetime of a system and increasing the amount of revenue generated. Machine learning techniques can help us in this regard by providing more accurate predictions of PV power production, such that the forecasts take into account not only a site's system design characteristics, but also important weather and climate information. This type of research is important because we can leverage the vast amounts of SCADA data we collect to build more effective, accurate models that can help improve our performance management.

Research Organization:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Solar Energy Technologies Office (EE-4S)
DOE Contract Number:
AC04-94AL85000; NA0003525
OSTI ID:
1592882
Report Number(s):
SAND--2019-15241R; 682084
Country of Publication:
United States
Language:
English

Similar Records

Predicting Solar Plant Generation with Machine Learning Techniques
Technical Report · Mon Feb 10 23:00:00 EST 2020 · OSTI ID:1598939

Evaluating the Accuracy of Machine Learning Forecasts
Technical Report · Sun Sep 01 00:00:00 EDT 2024 · OSTI ID:3011529

A TCN-Based Hybrid Forecasting Framework for Hours-Ahead Utility-Scale PV Forecasting
Journal Article · Sun Jan 15 23:00:00 EST 2023 · IEEE Transactions on Smart Grid · OSTI ID:2329476