LASSO-Based Single Index Model for Solar Power Generation Forecasting
| Autor: | Ningkai Tang, Shiwen Mao, Yu Wang, Mark Nelms |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Scheme (programming language)
Mathematical optimization Computer science business.industry Single-index model Anomaly (natural sciences) 020208 electrical & electronic engineering 02 engineering and technology 01 natural sciences Renewable energy 010104 statistics & probability Lasso (statistics) 0202 electrical engineering electronic engineering information engineering Renewable power generation Power grid 0101 mathematics business computer Solar power computer.programming_language |
| Zdroj: | GLOBECOM |
| DOI: | 10.1109/glocom.2017.8255070 |
| Popis: | Despite the high promises of renewable energy, it brings great challenges to the existing power grid due to its nature of intermittent and uncontrollable generation. In order to fully harvest its potential, accurate forecasting of renewable power generation is indispensable for effective power management. In this paper, we propose a LASSO- based forecasting model and algorithm for solar power generation forecasting. We compare the proposed scheme with two representative schemes with a real world dataset. We find that the LASSO-based algorithm achieves a considerably higher accuracy comparing to the existing methods, using fewer training data and being robust to anomaly data points in the training data. Its variable selection capability also offers a trade-off between complexity and accuracy, which all make it a highly competitive solution to forecasting of solar power generation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|