Solar Radiation Forecasting: A Systematic Meta-Review of Current Methods and Emerging Trends

Energies, Journal Year: 2024, Volume and Issue: 17(13), P. 3156 - 3156

Published: June 26, 2024

Effective solar forecasting has become a critical topic in the scholarly literature recent years due to rapid growth of photovoltaic energy production worldwide and inherent variability this source energy. The need optimise systems, ensure power continuity, balance supply demand is driving continuous development methods approaches based on meteorological data or plant characteristics. This article presents results meta-review literature, including current state knowledge methodological discussion. It comprehensive set methods, evaluates classifications, proposes new synthetic typology. emphasises increasing role artificial intelligence (AI) machine learning (ML) techniques improving forecast accuracy, alongside traditional statistical physical models. explores challenges hybrid ensemble models, which combine multiple enhance performance. paper addresses emerging trends research, such as integration big advanced computational tools. Additionally, from perspective, outlines rigorous approach research procedure, scientific associated with conducting bibliometric highlights best practices principles. article’s relevance consists providing up-to-date forecasting, along insights trends, future directions, anticipating implications for theory practice.

Language: Английский

---

Integrated Planning and Operation Dispatching of Source–Grid–Load–Storage in a New Power System: A Coupled Socio–Cyber–Physical Perspective

Energies, Journal Year: 2024, Volume and Issue: 17(12), P. 3013 - 3013

Published: June 19, 2024

The coupling between modern electric power physical and cyber systems is deepening. An increasing number of users are gradually participating in operation control, engaging bidirectional interactions with the grid. evolving new system transforming into a highly intelligent socio–cyber–physical system, featuring increasingly intricate expansive architectures. Demands for stable becoming more specific rigorous. confronts significant challenges areas like planning, dispatching, operational maintenance. Hence, this paper aims to comprehensively explore potential synergies among various components from multiple viewpoints. It analyzes numerous core elements key technologies fully unlock efficiency coupling. Our objective establish solid theoretical foundation practical strategies precise implementation integrated planning dispatching source–grid–load–storage systems. Based on this, first delves concepts source, grid, load, storage, exploring developments emerging changes each domain within context. Secondly, it summarizes pivotal such as data acquisition, collaborative security measures, while presenting reasonable prospects their future advancement. Finally, extensively discusses immense value applications concept This includes its assistance regards large-scale engineering projects extreme disaster management, facilitating green energy development desertification regions, promoting construction zero-carbon parks.

Language: Английский

---

A Review of State-of-the-art and Short-Term Forecasting Models for Solar PV Power Generation

Published: May 23, 2023

Accurately predicting the power of solar generation can greatly reduce impact randomness and volatility on stability grid system, which is beneficial for balanced operation optimized dispatch reduces operating costs. Solar PV depends weather conditions, are prone to large fluctuations under different conditions. Its characterized by randomness, intermittency. Recently, demand further investigation effective use uncertainty short-term prediction has been getting increasing attention in many application renewable energy sources. In order improve predictive accuracy output develop a precise model, authors worked algorithms system. Moreover, since forecasting one important aspects optimizing control systems electricity markets, this review focuses models generation, be verified daily planning smart addition, methods reviewed literature classified according input data source used accurate models, case studies examples proposed analyzed detail. The contributions, advantages disadvantages probabilistic compared. Finally, future proposed.

Language: Английский

---

Revolutionizing Solar PV Forecasting with Machine Learning Techniques

Published: March 21, 2025

Language: Английский

---

Advancements and Challenges in Photovoltaic Power Forecasting: A Comprehensive Review

Energies, Journal Year: 2025, Volume and Issue: 18(8), P. 2108 - 2108

Published: April 19, 2025

The fast growth of photovoltaic (PV) power generation requires dependable forecasting methods to support efficient integration solar energy into systems. This study conducts an up-to-date, systematized analysis different models and used for prediction. It begins with a new taxonomy, classifying PV according the time horizon, architecture, selection criteria matched certain application areas. An overview most popular heterogeneous techniques, including physical models, statistical methodologies, machine learning algorithms, hybrid approaches, is provided; their respective advantages disadvantages are put perspective based on tasks. paper also explores advanced model optimization methodologies; achieving hyperparameter tuning; feature selection, use evolutionary swarm intelligence which have shown promise in enhancing accuracy efficiency models. review includes detailed examination performance metrics frameworks, as well consequences weather conditions affecting renewable operational economic implications performance. highlights recent advancements field, deep architectures, incorporation diverse data sources, development real-time on-demand solutions. Finally, this identifies key challenges future research directions, emphasizing need improved adaptability, quality, computational large-scale By providing holistic critical assessment landscape, aims serve valuable resource researchers, practitioners, decision makers working towards sustainable reliable deployment worldwide.

Language: Английский

---

Refining Long Short-Term Memory Neural Network Input Parameters for Enhanced Solar Power Forecasting

Energies, Journal Year: 2024, Volume and Issue: 17(16), P. 4174 - 4174

Published: Aug. 22, 2024

This article presents a research approach to enhancing the quality of short-term power output forecasting models for photovoltaic plants using Long Short-Term Memory (LSTM) recurrent neural network. Typically, time-related indicators are used as inputs PV generators. However, this study proposes replacing with clear sky solar irradiance at specific location plant. feature represents maximum potential radiation that can be received particular on Earth. The Ineichen/Perez model is then employed calculate irradiance. To evaluate effectiveness approach, incorporating new input was trained and results were compared those obtained from previously published models. show reduction in Mean Absolute Percentage Error (MAPE) 3.491% 2.766%, indicating 24% improvement. Additionally, Root Square (RMSE) decreased by approximately 0.991 MW, resulting 45% These demonstrate an effective solution accuracy while reducing number variables.

Language: Английский

---

Global Horizontal Irradiance in Brazil: A Comparative Study of Reanalysis Datasets with Ground-Based Data

Energies, Journal Year: 2024, Volume and Issue: 17(20), P. 5063 - 5063

Published: Oct. 11, 2024

Renewable energy sources are increasing globally, mainly due to efforts achieve net zero emissions. In Brazil, solar photovoltaic electricity generation has grown substantially in recent years, with the installed capacity rising from 2455 MW 2018 47,033 August 2024. However, intermittency of increases challenges forecasting generation, making it more difficult for decision-makers plan flexible and efficient distribution systems. addition, forecast power support grid expansion, is essential have adequate data sources, but measured climate Brazil limited does not cover entire country. To address this problem, study evaluates global horizontal irradiance (GHI) four reanalysis datasets—MERRA-2, ERA5, ERA5-Land, CFSv2—at 35 locations across Brazil. The GHI time series was compared ground-based measurements assess its ability represent hourly Results indicate that MERRA-2 performed best 90% studied, considering root mean squared error. These findings will help advance by offering an alternative regions observational through use datasets.

Language: Английский

---

Estimation of Solar Irradiance Using a Neural Network Based on the Combination of Sky Camera Images and Meteorological Data

Energies, Journal Year: 2024, Volume and Issue: 17(2), P. 438 - 438

Published: Jan. 16, 2024

In recent years, with the growing proliferation of photovoltaics (PV), accurate nowcasting PV power has emerged as a challenge. Global horizontal irradiance (GHI), which is key factor influencing power, known to be highly variable it determined by short-term meteorological phenomena, particularly cloud movement. Deep learning and computer vision techniques applied all-sky imagery are demonstrated methods, they encode crucial information about sky’s state. While these methods utilize deep neural network models, such Convolutional Neural Networks (CNN), attain high levels accuracy, training image-based models demands significant computational resources. this work, we present computationally economical estimation technique, based on model. We both data, however, state encoded feature vector extracted using traditional image processing methods. introduce six features utilizing detailed knowledge physical significantly decreasing amount input data model complexity. investigate accuracy global diffuse radiation for different combinations parameters. The evaluated two years measurements from an on-site camera adjacent station. Our findings demonstrate that provides comparable CNN-based yet at lower cost.

Language: Английский

---

Photovoltaic Power Prediction Based on Irradiation Interval Distribution and Transformer-LSTM

Energies, Journal Year: 2024, Volume and Issue: 17(12), P. 2969 - 2969

Published: June 17, 2024

Accurate photovoltaic power prediction is of great significance to the stable operation electric system with renewable energy as main body. In view different influence mechanisms meteorological factors on generation in irradiation intervals and that data-driven algorithm has problem regression mean, this article, a method based interval distribution Transformer-long short-term memory (IID-Transformer-LSTM) proposed. Firstly, calculated boxplot. Secondly, distributed data each input into Transformer-LSTM model for training. The self-attention mechanism Transformer applied coding layer focus more important information, LSTM decoding further capture potential change relationship data. Finally, sunny data, cloudy rainy are selected test sets case analysis. Through experimental verification, proposed article certain improvement accuracy compared traditional methods under weather conditions. local extrema large fluctuations, clearly improved.

Language: Английский

---

An Ensemble Approach for Intra-Hour Forecasting of Solar Resource

Energies, Journal Year: 2023, Volume and Issue: 16(18), P. 6608 - 6608

Published: Sept. 14, 2023

Solar resource forecasting is an essential step towards smart management of power grids. This study aims to increase the performance intra-hour forecasts. For this, a novel ensemble model, combining statistical extrapolation time-series measurements with models based on machine learning and all-sky imagery, proposed. conducted high-quality data high-resolution sky images recorded Platform West University Timisoara, Romania. Atmospheric factors that contribute improving or reducing quality forecasts are discussed. Generally, gain small skill score across all forecast horizons (5 30 min). The machine-learning-based methods perform best at smaller (less than 15 min), while all-sky-imagery-based model performs larger horizons. Overall, for between 10 min, weighted frozen coefficients achieves 20%.

Language: Английский

---