Advanced Methods for Photovoltaic Output Power Forecasting: A Review

Applied Sciences, Год журнала: 2020, Номер 10(2), С. 487 - 487

Опубликована: Янв. 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.

Язык: Английский

---

Day-Ahead Photovoltaic Forecasting: A Comparison of the Most Effective Techniques

Energies, Год журнала: 2019, Номер 12(9), С. 1621 - 1621

Опубликована: Апрель 29, 2019

We compare the 24-hour ahead forecasting performance of two methods commonly used for prediction power output photovoltaic systems. Both are based on Artificial Neural Networks (ANN), which have been trained same dataset, thus enabling a much-needed homogeneous comparison currently lacking in available literature. The dataset consists an hourly series simultaneous climatic and PV system parameters covering entire year, has clustered to distinguish sunny from cloudy days separately train ANN. One method feeds only while other is hybrid as it relies upon daily weather forecast. For days, first shows very good stable performance, with almost constant Normalized Mean Absolute Error, NMAE%, all cases (1% < NMAE% 2%); even better (NMAE% 1%) considered this analysis, but overall less > 2% up 5.3% cases). both typically drops; rather that does not use forecasts, varies significantly analysis.

Язык: Английский

---

Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning

International Journal of Electrical Power & Energy Systems, Год журнала: 2019, Номер 118, С. 105790 - 105790

Опубликована: Дек. 31, 2019

Язык: Английский

---

A review on modeling of solar photovoltaic systems using artificial neural networks, fuzzy logic, genetic algorithm and hybrid models

International Journal of Energy Research, Год журнала: 2020, Номер 45(1), С. 6 - 35

Опубликована: Июнь 25, 2020

Язык: Английский

---

Day-ahead hourly photovoltaic power forecasting using attention-based CNN-LSTM neural network embedded with multiple relevant and target variables prediction pattern

Energy, Год журнала: 2021, Номер 232, С. 120996 - 120996

Опубликована: Май 20, 2021

Язык: Английский

---

Sustainability perspectives- a review for solar photovoltaic trends and growth opportunities

Journal of Cleaner Production, Год журнала: 2019, Номер 227, С. 589 - 612

Опубликована: Апрель 12, 2019

Язык: Английский

---

Long short term memory–convolutional neural network based deep hybrid approach for solar irradiance forecasting

Applied Energy, Год журнала: 2021, Номер 295, С. 117061 - 117061

Опубликована: Май 6, 2021

Язык: Английский

---

A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power

Energies, Год журнала: 2020, Номер 13(24), С. 6623 - 6623

Опубликована: Дек. 15, 2020

Presently, deep learning models are an alternative solution for predicting solar energy because of their accuracy. The present study reviews handling time-series data to predict irradiance and photovoltaic (PV) power. We selected three standalone one hybrid model the discussion, namely, recurrent neural network (RNN), long short-term memory (LSTM), gated unit (GRU), convolutional network-LSTM (CNN–LSTM). were compared based on accuracy, input data, forecasting horizon, type season weather, training time. performance analysis shows that these have strengths limitations in different conditions. Generally, models, LSTM best regarding root-mean-square error evaluation metric (RMSE). On other hand, (CNN–LSTM) outperforms although it requires longer most significant finding is interest more suitable PV power than conventional machine models. Additionally, we recommend using relative RMSE as representative facilitate accuracy comparison between studies.

Язык: Английский

---

Artificial Intelligence for Smart Renewable Energy Sector in Europe—Smart Energy Infrastructures for Next Generation Smart Cities

IEEE Access, Год журнала: 2020, Номер 8, С. 77364 - 77377

Опубликована: Янв. 1, 2020

One of the most challenging areas Future Smart Cities Research is Energy domain. Critical issues related to optimization, provision smart customizable networks and sophisticated computational techniques methods enabled by artificial intelligence machine learning need further investigation. The renewable energy (RE) a powerful resource for future global development in context climate change resources depletion. Artificial (AI) implies new rules organizing activities order respond these requirements. It necessary improve design infrastructure, deployment production RE face multiple challenges that will affect sector’s growth resilience.. In this research work we exploit recent developments on AI adoption sector European Union (EU). respect, analysed (i) efficiency transformation processes within chain from Gross Inland Consumption Final Consumption, (ii) its implications structure source (solar, wind, biomass etc.), (iii) labour productivity compared economy as whole correlation with investments level, (iv) implication towards Research. main contribution framework understanding Europe. Another bold discussion directions.

Язык: Английский

---

A review of very short-term wind and solar power forecasting

Renewable and Sustainable Energy Reviews, Год журнала: 2021, Номер 153, С. 111758 - 111758

Опубликована: Окт. 25, 2021

Язык: Английский

---