Citation: Zhu, W.; Chen, T.; Hou, B.;
Bian, C.; Yu, A.; Chen, L.; Tang, M.;
Zhu, Y. Classification of
Ground-Based Cloud Images by
Improved Combined Convolutional
Network. Appl. Sci. 2022, 12, 1570.
https://doi.org/10.3390/
app12031570
Academic Editor: Luis
Hernández-Callejo
Received: 1 December 2021
Accepted: 29 January 2022
Published: 1 February 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Classification of Ground-Based Cloud Images by Improved
Combined Convolutional Network
Wen Zhu, Tianliang Chen , Beiping Hou *, Chen Bian, Aihua Yu, Lingchao Chen, Ming Tang and Yuzhen Zhu
School of Automation and Electrical Engineering, Zhejiang University of Science and Technology,
Hangzhou 310023, China; joywenzhu@zust.edu.cn (W.Z.); 222007855005@zust.edu.cn (T.C.);
221901852094@zust.edu.cn (C.B.); yuaihua@zust.edu.cn (A.Y.); 222007855004@zust.edu.cn (L.C.);
222007855035@zust.edu.cn (M.T.); 1200309030@zust.edu.cn (Y.Z.)
* Correspondence: bphou@zust.edu.cn
Abstract:
Changes in clouds can affect the outpower of photovoltaics (PVs). Ground-based cloud
images classification is an important prerequisite for PV power prediction. Due to the intra-class
difference and inter-class similarity of cloud images, the classical convolutional network is obviously
insufficient in distinguishing ability. In this paper, a classification method of ground-based cloud
images by improved combined convolutional network is proposed. To solve the problem of sub-
network overfitting caused by redundancy of pixel information, overlap pooling kernel is used
to enhance the elimination effect of information redundancy in the pooling layer. A new channel
attention module, ECA-WS (Efficient Channel Attention–Weight Sharing), is introduced to improve
the network’s ability to express channel information. The decision fusion algorithm is employed to
fuse the outputs of sub-networks with multi-scales. According to the number of cloud images in each
category, different weights are applied to the fusion results, which solves the problem of network
scale limitation and dataset imbalance. Experiments are carried out on the open MGCD dataset and
the self-built NRELCD dataset. The results show that the proposed model has significantly improved
the classification accuracy compared with the classical network and the latest algorithms.
Keywords:
convolutional neural network; classification of ground-based cloud images; combined
convolutional network; overlap pooling; attention mechanism
1. Introduction
Affected by short-term weather changes, the output power of PV power generation
is easily fluctuated [
1
,
2
]. At present, the forecasting of PV power becomes an important
method to reduce the impact of power fluctuations. Through power forecasting, the power
sector can reasonably dispatch PV resources and reduce the impact of power fluctuations on
grid-connected PVs. Dissipation and aggregation of cloud clusters in a short period of time
are important factors that cause fluctuations in output power. Besides, solar irradiance is
affected directly by the different types of clouds [
3
]. Different types of clouds have different
characteristics, such as thickness, height, and sky coverage, which affect the magnitude of
solar radiation received by the ground. Therefore, classification of clouds is crucial for PV
power prediction.
There are various forms of clouds belonging to the same category, and different cate-
gories of clouds are also a transitional relationship, so they have greater similarity, which
brings great challenges to the classification of clouds. In the early days, machine learning
based classifiers were often used to classify cloud images. For example,
Heinle et al. [4]
used the K-nearest neighbors to classify the cloud by extracting the spectral and texture fea-
tures of the cloud image. Kazantzidis et al. [
5
] introduced cloud classification by counting
the color and texture features of cloud images, and at the same time considered multi-modal
information as the input of the improved K-nearest neighbors classifier. Zhao et al. [
6
]
Appl. Sci. 2022, 12, 1570. https://doi.org/10.3390/app12031570 https://www.mdpi.com/journal/applsci
