کنفرانس بین المللی فناوری و مدیریت انرژی

صفحه اصلی / هشتمین کنفرانس بین المللی فناوری و مدیریت انرژی

Photovoltaic Power Forecasting With an Ensemble Multi-Input Deep Learning Approach

نویسندگان :

Fariba Dehghan¹ Mohsen Parsa Moghaddam² Maryam Imani³

1- دانشگاه تربیت مدرس 2- دانشگاه تربیت مدرس 3- دانشگاه تربیت مدرس

کلمات کلیدی :

Bidirectional long short-term memory networks،Convolution neural networks،Deep learning،PV power forecasting

چکیده :

The inherent intermittency of solar power due to meteorological factors presents a significant challenge in integrating them into grids on large scales. An accurate Photovoltaic (PV) power generation forecasting effectively supports achieving optimal planning and operational stability of power systems. Motivated by satisfactory performance of deep learning methods in the energy sector, an ensemble multi-input deep learning method combining three-dimensional convolution (Conv3D) networks and bidirectional long short-term memory (BiLSTM) networks is proposed in this study. First, one-dimensional (vector) PV power production and atmosphere parameters series are rearranged into a bi-dimensional matrix (2D image) and stacked in the third dimension (3D image) to preserve dependency between the input data. Then, the Conv3D network is utilized to extract non-linear spatial features of the 3D image. Finally, the BiLSTM network is implemented to learn the long-term dependencies of the extracted spatial features. The proposed method is utilized for one-day, three-day, five-day, and seven-day ahead PV power forecasting with one-hour intervals for Tennent operators, Germany dataset. Experimental results show reduced prediction error compared to two-dimensional Convolution (Conv2D), Conv3D, long short-term memory (LSTM), BiLSTM, Conv-LSTM, and ConvLSTM networks.

لیست مقالات

لیست مقالات بایگانی شده

بررسی پتانسیل کاهش مصرف انرژی الکتریکی در صنایع فولاد و آهن کشور

مرتضی مهرگو - وهاب مکاری زاده

Optimizing energy of carbon dioxide absorption in distilled water using ultrasonic system through response surface methodology

Abolfazl Shokri - Arash Kamran-Pirzaman

Employing Machine Learning Algorithms to Identify False Data Injection in Smart Grid

Mohsen Tajdinian - Mostafa Mohammadpourfard - Ali Goodarzi

Using a Multi-Functional Inverter to Connect the Distributed Generation Source to the Network with Purpose of Reducing Harmonic and Network Imbalance

Mehdi Forouzanfar - Narges S. Ghiasi - Mohammad Babaei - Mehrdad Bagheri Sanjareh - Seyyed Mohammad Sadegh Ghiasi

A high gain non-isolated DC-DC converter based on coupled-inductor with low voltage stress on switches for renewable energy applications

Meysam Abdi - Ali Nadermohammadi - Pouneh Aghakhanlou - Kazem Zare - Seyed Hossein Hosseini

Feature Selection in Phishing Attack Detection Using Bee Algorithm and Logistic Regression Method

Nazila Razzaghi-Asl - Jafar Tanha - Soodabeh Imanzadeh - Negin Samadi - Sahar Hassanzadeh Mostafaei - Sayyad Nojavan

مدیریت سطح قابلیت اطمینان مشترکین بزرگ موجود در شبکه انتقال به کمک روشی مبتنی بر بازار برق

بهرام بالازاده - بهزاد فریدونی - یونس فرهمند - ابراهیم آقائی

A Comparative Analysis of High-Rise Building Shapes and Orientations on the Performance and Energy Generation of Building Integrated Photovoltaic Systems in Tehran

Shahrzad Zeynali - Mohammad Nazififard - Javad Divandari

ارزیابی فنی و اقتصادی جایگزینی کولرهای گازی فرسوده در کشور (مطالعه موردی استان خوزستان)

مصطفی قاسمی - علی خندانی - نیلوفر نیکزاد - رحیم زینالی

طراحی بهینه ریزشبکه مستقل از شبکه شامل منابع تولید توان تجدید پذیر و ذخیره کننده انرژی با درنظر گرفتن قابلیت اطمینان

حمید حسن زاده فرد - یونس فرهمند گل تپه - بهرام بالازاده - ابراهیم آقایی - بهرام رمضانی

بیشتر