Weather Forecasting for Renewable Energy System: A Review

Archives of Computational Methods in Engineering, Journal Year: 2022, Volume and Issue: 29(5), P. 2875 - 2891

Published: Jan. 26, 2022

Language: Английский

---

Time-series analysis with smoothed Convolutional Neural Network

Journal Of Big Data, Journal Year: 2022, Volume and Issue: 9(1)

Published: April 26, 2022

CNN originates from image processing and is not commonly known as a forecasting technique in time-series analysis which depends on the quality of input data. One methods to improve by smoothing This study introduces novel hybrid exponential using called Smoothed-CNN (S-CNN). The method combining tactics outperforms majority individual solutions forecasting. S-CNN was compared with original other such Multilayer Perceptron (MLP) Long Short-Term Memory (LSTM). dataset year daily website visitors. Since there are no special rules for number hidden layers, Lucas used. results show that better than MLP LSTM, best MSE 0.012147693 76 layers at 80%:20% data composition.

Language: Английский

---

Trends and gaps in photovoltaic power forecasting with machine learning

Energy Reports, Journal Year: 2022, Volume and Issue: 9, P. 447 - 471

Published: Dec. 10, 2022

The share of solar energy in the electricity mix increases year after year. Knowing production photovoltaic (PV) power at each instant time is crucial for its integration into grid. However, due to meteorological phenomena, PV output can be uncertain and continuously varying, which complicates yield prediction. In recent years, machine learning (ML) techniques have entered world forecasting help increase accuracy predictions. Researchers seen great potential this approach, creating a vast literature on topic. This paper intends identify most popular approaches gaps discipline. To do so, representative part consisting 100 publications classified based different aspects such as ML family, location systems, number systems considered, features, etc. Via classification, main trends highlighted while offering advice researchers interested

Language: Английский

---

Deep learning for renewable energy forecasting: A taxonomy, and systematic literature review

Journal of Cleaner Production, Journal Year: 2022, Volume and Issue: 384, P. 135414 - 135414

Published: Dec. 15, 2022

Language: Английский

---

Application of Deep Learning to the Prediction of Solar Irradiance through Missing Data

International Journal of Photoenergy, Journal Year: 2023, Volume and Issue: 2023, P. 1 - 17

Published: Sept. 22, 2023

The task of predicting solar irradiance is critical in the development renewable energy sources. This research aimed at photovoltaic plant’s or power and serving as a standard for grid stability. In practical situations, missing data can drastically diminish prediction precision. Meanwhile, it tough to pick an appropriate imputation approach before modeling because not knowing distribution datasets. Furthermore, all datasets benefit equally from using same technique. suggests utilizing recurrent neural network (RNN) equipped with adaptive module (ANIM) estimate direct when some missing. Without imputed information, typical projects’ imminent 4-hour depends on gaps antique climatic irradiation records. projected model evaluated widely available information by simulating each input series. performance assessed alternative techniques under range rates parameters. outcomes prove that suggested methods perform better than competing strategies measured various criteria. Moreover, combine methodology attentive mechanism invent excels low-light conditions.

Language: Английский

---

A review: state estimation based on hybrid models of Kalman filter and neural network

Systems Science & Control Engineering, Journal Year: 2023, Volume and Issue: 11(1)

Published: Feb. 9, 2023

In this paper, hybrid models of Kalman filter and neural network for state estimation are reviewed their corresponding academic achievements, the creation which is a noteworthy development in estimation. This paper aims to provide summary research progress on such emphasize functions advantages. First all, concept feature paid attention about filter, its transmutative modes taken into consideration. Then several popular algorithms introduced brief. Subsequently, results analysed discussed comprehensively. Not only can be adopted succession, but also mixed structure. The divided two types, equations or parameters state–space model trained by updated filter. It proved that outperform than single accuracy generalization. Last not least, effectiveness established nonlinear systems verified.

Language: Английский

---

A comprehensive analysis of the emerging modern trends in research on photovoltaic systems and desalination in the era of artificial intelligence and machine learning

Heliyon, Journal Year: 2024, Volume and Issue: 10(3), P. e25407 - e25407

Published: Feb. 1, 2024

Integration of photovoltaic (PV) systems, desalination technologies, and Artificial Intelligence (AI) combined with Machine Learning (ML) has introduced a new era remarkable research innovation. This review article thoroughly examines the recent advancements in field, focusing on interplay between PV systems water within framework AI ML applications, along it analyses current to identify significant patterns, obstacles, prospects this interdisciplinary field. Furthermore, incorporation methods improving performance systems. includes raising their efficiency, implementing predictive maintenance strategies, enabling real-time monitoring. It also explores transformative influence intelligent algorithms techniques, specifically addressing concerns pertaining energy usage, scalability, environmental sustainability. provides thorough analysis literature, identifying areas where is lacking suggesting potential future avenues for investigation. These have resulted increased decreased expenses, improved sustainability system. By utilizing artificial intelligence freshwater productivity can increase by 10 % efficiency. offers informative perspectives researchers, engineers, policymakers involved renewable technology. sheds light latest desalination, which are facilitated ML. The aims guide towards more sustainable technologically advanced future.

Language: Английский

---

Hybrid deep learning models for time series forecasting of solar power

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(16), P. 9095 - 9112

Published: Feb. 22, 2024

Abstract Forecasting solar power production accurately is critical for effectively planning and managing renewable energy systems. This paper introduces investigates novel hybrid deep learning models forecasting using time series data. The research analyzes the efficacy of various capturing complex patterns present in In this study, all possible combinations convolutional neural network (CNN), long short-term memory (LSTM), transformer (TF) are experimented. These also compared with single CNN, LSTM TF respect to different kinds optimizers. Three evaluation metrics employed performance analysis. Results show that CNN–LSTM–TF model outperforms other models, a mean absolute error (MAE) 0.551% when Nadam optimizer. However, TF–LSTM has relatively low performance, an MAE 16.17%, highlighting difficulties making reliable predictions power. result provides valuable insights optimizing systems, significance selecting appropriate optimizers accurate forecasting. first such comprehensive work presented involves networks

Language: Английский

---

Artificial Neural Networks for Photovoltaic Power Forecasting: A Review of Five Promising Models

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 90461 - 90485

Published: Jan. 1, 2024

Solar energy is largely dependent on weather conditions, resulting in unpredictable, fluctuating, and unstable photovoltaic (PV) power outputs. Thus, accurate PV forecasts are increasingly crucial for managing controlling integrated systems. Over the years, advanced artificial neural network (ANN) models have been proposed to increase accuracy of various geographical regions. Hence, this paper provides a state-of-the-art review five most popular ANN forecasting. These include multilayer perceptron (MLP), recurrent (RNN), long short-term memory (LSTM), gated unit (GRU), convolutional (CNN). First, internal structure operation these studied. It then followed by brief discussion main factors affecting their forecasting accuracy, including horizons, meteorological evaluation metrics. Next, an in-depth separate analysis standalone hybrid provided. has determined that bidirectional GRU LSTM offer greater whether used as model or configuration. Furthermore, upgraded metaheuristic algorithms demonstrated exceptional performance when applied models. Finally, study discusses limitations shortcomings may influence practical implementation

Language: Английский

---

Deep learning for time series forecasting: a survey

International Journal of Machine Learning and Cybernetics, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 8, 2025

Language: Английский

---