Automated Deep CNN-LSTM Architecture Design for Solar Irradiance Forecasting

Jalali, Seyed Mohammad Jafar; Ahmadian, Sajad; Kavousi‐Fard, Abdollah; Khosravi, Abbas; Nahavandi, Saeid

doi:10.1109/tsmc.2021.3093519

Cited by 95 publications

(25 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results demonstrate the effectiveness of the proposed approach based on DL compared with current methods (such as CNN, LSTM, and ANN). In [53], the authors presented a hybrid deep convolutional CNN-LSTM technique to predict horizontal irradiance. Dataset was collected from three solar stations in the east of the United States.…”

Section: B Energy Forecastingmentioning

confidence: 99%

A Survey on Deep Learning Role in Distribution Automation System: A New Collaborative Learning-to-Learning (L2L) Concept

et al. 2022

Self Cite

View full text Add to dashboard Cite

This paper focuses on a powerful and comprehensive overview of Deep Learning (DL) techniques on Distribution Automation System (DAS) applications to provide a complete viewpoint of modern power systems. DAS is a crucial approach to increasing the reliability, quality, and management of distribution networks. Due to the importance of development and sustainable security of DAS, the use of DL data-driven technology has grown significantly. DL techniques have blossomed rapidly, and have been widely applied in several fields of distribution systems. DL techniques are suitable for dynamic, decision-making, and uncertain environments such as DAS. This survey has provided a comprehensive review of the existing research into DL techniques on DAS applications, including fault detection and classification, load and energy forecasting, demand response, energy market forecasting, cyber security, network reconfiguration, and voltage control. Comparative results based on evaluation criteria are also addressed in this manuscript. According to the discussion and results of studies, the use and development of hybrid methods of DL with other methods to enhance and optimize the configuration of the techniques are highlighted. In all matters, hybrid structures accomplish better than single methods as hybrid approaches hold the benefit of several methods to construct a precise performance. Due to this, a new smart technique called Learning-to-learning (L2L) based DL is proposed that can enhance and improve the efficiency, reliability, and security of DAS. The proposed model follows several stages that link different DL algorithms to solve modern power system problems. To show the effectiveness and merit of the L2L based on the proposed framework, it has been tested on a modified reconfigurable IEEE 32 test system. This method has been implemented on several DAS applications that the results prove the decline of mean square errors by approximately 12% compared to conventional LSTM and GRU methods in terms of prediction fields.

show abstract

Section: B Energy Forecastingmentioning

confidence: 99%

A Survey on Deep Learning Role in Distribution Automation System: A New Collaborative Learning-to-Learning (L2L) Concept

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The clarity index is defined as the ratio between the values of the spherical radiation at ground level 𝐺 on the horizontal surface and the 𝐺𝐻𝑆𝐼 of extraterrestrial spherical radiation [39]. The clarity index consists of the difference between the mean value of the daily maximum temperatures (𝑇 𝑚𝑎𝑥 ) and the mean value of the daily minimum temperatures (𝑇 𝑚𝑖𝑛 ) and can be estimated using Equation (16).…”

Section: F Prediction Of Global Horizontal Irradiance Datamentioning

confidence: 99%

“…Analyzing global horizontal irradiance (GHSI) data based on important weather parameters such as air temperature, relative humidity, and wind speed will be an interesting approach for using photovoltaic solar plants [14,15]. Accordingly, it is necessary to examine the effects and correlation of temperature on GHSI and to put forward energy management plans accordingly [16,17]. Therefore, making long-term predictions in GHSI and other climate data is a challenging task.…”

Section: Introductionmentioning

confidence: 99%

LSTM-CNN Tabanlı Derin Öğrenme Tekniği Kullanılarak Küresel Yatay Güneş Radyasyonu ile Hava Durumu Parametrelerinin Tahmini ve Analizi

Yalçın

Herdem

2022

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

Predicting global horizontal solar irradiance (GHSI) as well as important climate parameters plays an important role in energy management and resource planning of photovoltaic panels. To further benefit from solar energy, it is necessary to obtain information regarding future values by frequently analyzing and predicting such time series parameter data. Hence, predicting long-term solar irradiance data is a challenging task. For these purposes, in this work, a hybrid method, with modeling of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) deep neural networks, is proposed to ensure the most accurate prediction of such data. The GHSI as well as temperature, relative humidity, and wind speed data obtained in the Jordan valley are used in the forecasting methodology. In the CNN block of the proposed deep architecture, the input parameters are passed through the convolution, pooling, and flattening layers, and the outputs are forwarded to the LSTM data input. With this method, it is aimed to make more effective and accurate estimations. The proposed method has been compared according to Root Mean Square Error (RMSE), Mean Absolute Deviation Error (MADE), and Mean Absolute Percentage Error (MAPE) error performance criteria in order to reveal the difference from other methods. The proposed method produces superior results compared to other algorithms, especially in GHSI estimation.

show abstract

“…However, evolutionary algorithms mainly suffer from low convergence speed and tapping into local optima. Moreover, making a balance between the exploration and exploitation phases of these algorithms plays a critical role in enhancing their ability of search process ( Ahmadian, Jalali, Raziani et al, 2021 , Jalali et al, 2022 , Jalali, Ahmadian, Khodayar et al, 2021 , Jalali, Ahmadian, Khosravi et al, 2021 , Jalali, Hedjam et al, 2020 , Jalali, Khodayar et al, 2021 , Jalali, Khosravi, Kebria et al, 2019 , Qazani et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%