Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending

TL;DR

This paper introduces an hourly-similarity based multi-model machine learning approach for 1-hour-ahead solar irradiance forecasting, significantly improving accuracy by leveraging diurnal patterns and hourly data distinctions.

Contribution

The paper develops a novel hourly-similarity based multi-model framework that enhances solar forecasting accuracy over traditional all-in-one models.

Findings

HS-based method outperforms non-HS method by 10.94% in NMAE

HS-based method outperforms non-HS method by 7.74% in NRMSE

Validated with one-year NREL solar data

Abstract

With the increasing penetration of solar power into power systems, forecasting becomes critical in power system operations. In this paper, an hourly-similarity (HS) based method is developed for 1-hour-ahead (1HA) global horizontal irradiance (GHI) forecasting. This developed method utilizes diurnal patterns, statistical distinctions between different hours, and hourly similarities in solar data to improve the forecasting accuracy. The HS-based method is built by training multiple two-layer multi-model forecasting framework (MMFF) models independently with the same-hour subsets. The final optimal model is a combination of MMFF models with the best-performed blending algorithm at every hour. At the forecasting stage, the most suitable model is selected to perform the forecasting subtask of a certain hour. The HS-based method is validated by 1-year data with six solar features collected by the National Renewable Energy Laboratory (NREL). Results show that the HS-based method outperforms the non-HS (all-in-one) method significantly with the same MMFF architecture, wherein the optimal HS- based method outperforms the best all-in-one method by 10.94% and 7.74% based on the normalized mean absolute error and normalized root mean square error, respectively.