Dynamic Feature Selection for Solar Irradiance Forecasting Based on Deep Reinforcement Learning

Cheng Lyu, Sara Eftekharnejad, Sagnik Basumallik, Chongfang Xu

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


A large volume of data is typically needed to achieve an accurate solar generation prediction. However, not all types of data are consistently available. Various research efforts have addressed this challenge by developing methods that identify the most relevant features for predicting solar generation. However, the optimal features vary with different weather patterns, making it impossible to select a fixed set of optimal features for all weather patterns. This study develops a new framework to accurately predict solar irradiance using dynamically changing optimal features. The developed model first incorporates feature extraction with clustering techniques to identify representative weather data from a dataset. Next, using deep reinforcement learning (DRL), a new feature selection method is developed to yield the minimum features required to accurately forecast solar irradiance from representative data. Benefiting from the model-free nature of DRL, the developed method is adaptive to various weather conditions, and dynamically alters the selected features. Case studies using real-world data have shown that the developed model significantly reduces the volume of data required for accurate irradiance forecasting for different weather patterns.

Original languageEnglish (US)
Pages (from-to)533-543
Number of pages11
JournalIEEE Transactions on Industry Applications
Issue number1
StatePublished - Jan 1 2023
Externally publishedYes


  • Data analytics
  • data clustering
  • deep reinforcement learning
  • feature extraction
  • solar generation forecast

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering


Dive into the research topics of 'Dynamic Feature Selection for Solar Irradiance Forecasting Based on Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this