A new ensemble reinforcement learning strategy for solar irradiance forecasting using deep optimized convolutional neural network models

Author Identifier

Syed Mohammad Shamsul Islam

https://orcid.org/0000-0002-3200-2903

Document Type

Conference Proceeding

Publication Title

2021 International Conference on Smart Energy Systems and Technologies (SEST)

Publisher

IEEE

School

School of Science

RAS ID

36653

Comments

Jalali, S. M. J., Khodayar, M., Ahmadian, S., Shafie-khah, M., Khosravi, A., Islam, S. M. S., . . . Catalão, J. P. S. (2021, September). A new ensemble reinforcement learning strategy for solar irradiance forecasting using deep optimized convolutional neural network models [Paper presentation]. 2021 International Conference on Smart Energy Systems and Technologies (SEST), Vaasa, Finland. https://doi.org/10.1109/SEST50973.2021.9543462

Abstract

Solar irradiance forecasting is a major priority for the power transmission systems in order to generate and incorporate the performance of massive photovoltaic plants efficiently. As such, prior forecasting techniques that use classical modelling and single deep learning models that undertake feature extraction procedures manually were unable to meet the output demands in specific situations with dynamic variability. Therefore, in this study, we propose an efficient novel hybrid solar irradiance forecasting based on three steps. In step I, we employ a powerful variable input selection strategy named as partial mutual information (PMI) to calculate the linear and non-linear correlations of the original solar irradiance data. In step II, unlike the traditional deep learning models designing their architectures manually, we utilize several deep convolutional neural network (CNN) models optimized by a novel modified whale optimization algorithm in order to compute the forecasting results of the solar irradiance datasets. Finally in step III, we deploy a deep Q-learning reinforcement learning strategy for selecting the best subsets of the combined deep optimized CNN models. Through analysing the forecasting results over two USA solar irradiance stations, it can be inferred that the proposed optimized deep RL-ensemble framework (ODERLEN) outperforms other powerful benchmarked algorithms in different time-step horizons.

DOI

10.1109/SEST50973.2021.9543462

Access Rights

subscription content

Link to Full Text

Share

 
COinS