Extreme Learning Machines for Solar Photovoltaic Power Predictions DOI Creative Commons
Sameer Al‐Dahidi, Osama Ayadi,

Jehad Adeeb

et al.

Energies, Journal Year: 2018, Volume and Issue: 11(10), P. 2725 - 2725

Published: Oct. 11, 2018

The unpredictability of intermittent renewable energy (RE) sources (solar and wind) constitutes reliability challenges for utilities whose goal is to match electricity supply consumer demands across centralized grid networks. Thus, balancing the variable increasing power inputs from plants with becomes a fundamental issue transmission system operators. As result, forecasting techniques have obtained paramount importance. This work aims at exploiting simplicity, fast computational good generalization capability Extreme Learning Machines (ELMs) in providing accurate 24 h-ahead solar photovoltaic (PV) production predictions. ELM architecture firstly optimized, e.g., terms number hidden neurons, historical radiations ambient temperatures (embedding dimension) required training model, then it used online predict PV productions. investigated model applied real case study 264 kWp installed on roof Faculty Engineering Applied Science Private University (ASU), Amman, Jordan. Results showed predictions that are slightly more negligible efforts compared Back Propagation Artificial Neural Network (BP-ANN) which currently adopted by owners prediction task.

Language: Английский

A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization DOI
Razin Ahmed, Victor Sreeram, Yateendra Mishra

et al.

Renewable and Sustainable Energy Reviews, Journal Year: 2020, Volume and Issue: 124, P. 109792 - 109792

Published: March 2, 2020

Language: Английский

Citations

851
Forecasting: theory and practice DOI Creative Commons
Fotios Petropoulos, Daniele Apiletti,

Vassilios Assimakopoulos

et al.

International Journal of Forecasting, Journal Year: 2022, Volume and Issue: 38(3), P. 705 - 871

Published: Jan. 20, 2022

Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds future is both exciting challenging, with individuals organisations seeking to minimise risks maximise utilities. large number forecasting applications calls for a diverse set methods tackle real-life challenges. This article provides non-systematic review theory practice forecasting. We provide an overview wide range theoretical, state-of-the-art models, methods, principles, approaches prepare, produce, organise, evaluate forecasts. then demonstrate how such theoretical concepts are applied in variety contexts. do not claim this exhaustive list applications. However, we wish our encyclopedic presentation will offer point reference rich work undertaken over last decades, some key insights practice. Given its nature, intended mode reading non-linear. cross-references allow readers navigate through various topics. complement covered by lists free or open-source software implementations publicly-available databases.

Language: Английский

Citations

560
Short-Term Photovoltaic Power Forecasting Based on Long Short Term Memory Neural Network and Attention Mechanism DOI Creative Commons
Hangxia Zhou, Yujin Zhang,

Lingfan Yang

et al.

IEEE Access, Journal Year: 2019, Volume and Issue: 7, P. 78063 - 78074

Published: Jan. 1, 2019

Photovoltaic power generation forecasting is an important topic in the field of sustainable system design, energy conversion management, and smart grid construction. Difficulties arise while generated PV usually unstable due to variability solar irradiance, temperature, other meteorological factors. In this paper, a hybrid ensemble deep learning framework proposed forecast short-term photovoltaic time series manner. Two LSTM neural networks are employed working on temperature outputs forecasting, respectively. The results flattened combined with fully connected layer enhance accuracy. Moreover, we adopted attention mechanism for two adaptively focus input features that more significant forecasting. Comprehensive experiments conducted recently collected real-world datasets. Three error metrics were compare produced by model state-of-art methods, including persistent model, auto-regressive integrated moving average exogenous variable (ARIMAX), multi-layer perceptron (MLP), traditional all four seasons various horizons show effectiveness robustness method.

Language: Английский

Citations

335
Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression DOI
Mahdi Sharifzadeh,

Alexandra Sikinioti-Lock,

Nilay Shah

et al.

Renewable and Sustainable Energy Reviews, Journal Year: 2019, Volume and Issue: 108, P. 513 - 538

Published: April 10, 2019

Language: Английский

Citations

297
Taxonomy research of artificial intelligence for deterministic solar power forecasting DOI
Huaizhi Wang, Yangyang Liu, Bin Zhou

et al.

Energy Conversion and Management, Journal Year: 2020, Volume and Issue: 214, P. 112909 - 112909

Published: May 1, 2020

Language: Английский

Citations

266
Advanced Methods for Photovoltaic Output Power Forecasting: A Review DOI Creative Commons
A. Mellit, Alessandro Pavan, Emanuèle Ogliari

et al.

Applied Sciences, Journal Year: 2020, Volume and Issue: 10(2), P. 487 - 487

Published: Jan. 9, 2020

Forecasting is a crucial task for successfully integrating photovoltaic (PV) output power into the grid. The design of accurate forecasters remains challenging issue, particularly multistep-ahead prediction. Accurate PV forecasting critical in number applications, such as micro-grids (MGs), energy optimization and management, integrated smart buildings, electrical vehicle chartering. Over last decade, vast literature has been produced on this topic, investigating numerical probabilistic methods, physical models, artificial intelligence (AI) techniques. This paper aims at providing complete review recent applications AI techniques; we will focus machine learning (ML), deep (DL), hybrid these branches are becoming increasingly attractive. Special attention be paid to development application DL, well future trends topic.

Language: Английский

Citations

251
Artificial Intelligence Based MPPT Techniques for Solar Power System: A review DOI Open Access
Kah Yung Yap, Charles R. Sarimuthu,

Joanne Mun-Yee Lim

et al.

Journal of Modern Power Systems and Clean Energy, Journal Year: 2020, Volume and Issue: 8(6), P. 1043 - 1059

Published: Jan. 1, 2020

In the last decade, artificial intelligence (AI) techniques have been extensively used for maximum power point tracking (MPPT) in solar system. This is because conventional MPPT are incapable of global (GMPP) under partial shading condition (PSC). The output curve versus voltage a panel has only one GMPP and multiple local points (MPPs). integration AI crucial to guarantee while increasing overall efficiency performance MPPT. selection AI-based complicated each technique its own merits demerits. general, all exhibit fast convergence speed, less steady-state oscillation high efficiency, compared with techniques. However, computationally intensive costly realize. Overall, hybrid favorable terms balance between complexity, it combines advantages this paper, detailed comparison classification 6 major made based on review MATLAB/Simulink simulation results. merits, open issues technical implementations evaluated. We intend provide new insights into choice optimal

Language: Английский

Citations

229
A Survey of Machine Learning Models in Renewable Energy Predictions DOI Creative Commons
Jung-Pin Lai, Yu-Ming Chang,

Chieh-Huang Chen

et al.

Applied Sciences, Journal Year: 2020, Volume and Issue: 10(17), P. 5975 - 5975

Published: Aug. 28, 2020

The use of renewable energy to reduce the effects climate change and global warming has become an increasing trend. In order improve prediction ability energy, various techniques have been developed. aims this review are illustrated as follows. First, survey attempts provide a analysis machine-learning models in renewable-energy predictions. Secondly, study depicts procedures, including data pre-processing techniques, parameter selection algorithms, performance measurements, used for Thirdly, sources values mean absolute percentage error, coefficient determination were conducted. Finally, some possible potential opportunities future work provided at end survey.

Language: Английский

Citations

155
Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information DOI

Zhen Hao,

Dongxiao Niu, Keke Wang

et al.

Energy, Journal Year: 2021, Volume and Issue: 231, P. 120908 - 120908

Published: May 10, 2021

Language: Английский

Citations

145
A novel long term solar photovoltaic power forecasting approach using LSTM with Nadam optimizer: A case study of India DOI Creative Commons
Jatin Sharma, Sameer Soni, Priyanka Paliwal

et al.

Energy Science & Engineering, Journal Year: 2022, Volume and Issue: 10(8), P. 2909 - 2929

Published: May 11, 2022

Abstract Solar photovoltaic (PV) power is emerging as one of the most viable renewable energy sources. The recent enhancements in integration sources into grid create a dire need for reliable solar forecasting techniques. In this paper, new long‐term PV approach using long short‐term memory (LSTM) model with Nadam optimizer presented. LSTM performs better time‐series data it persists information more time steps. experimental models are realized on 250.25 kW installed capacity system located at MANIT Bhopal, Madhya Pradesh, India. proposed compared two and eight neural network different optimizers. obtained results present significant improvement accuracy 30.56% over autoregressive integrated moving average, 47.48% seasonal 1.35%, 1.43%, 3.51%, 4.88%, 11.84%, 50.69%, 58.29% RMSprop, Adam, Adamax, SGD, Adagrad, Adadelta, Ftrl optimizer, respectively. prove that methodology conclusive can be employed enhanced planning management.

Language: Английский

Citations

77