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

Energies, Journal Year: 2023, Volume and Issue: 16(14), P. 5436 - 5436

Published: July 17, 2023

Accurately predicting the power produced during solar generation can greatly reduce impact of randomness and volatility on stability grid system, which is beneficial for its balanced operation optimized dispatch reduces operating costs. Solar PV depends weather conditions, such as temperature, relative humidity, rainfall (precipitation), global radiation, wind speed, etc., it prone to large fluctuations under different conditions. Its characterized by randomness, volatility, intermittency. Recently, demand further investigation into uncertainty short-term prediction effective use in many applications renewable energy sources has increased. In order improve predictive accuracy output develop a precise model, authors used algorithms system. Moreover, since forecasting an important aspect optimizing control systems electricity markets, this review focuses models generation, be verified daily planning smart addition, methods identified reviewed literature are classified according input data source, case studies examples proposed analyzed detail. The contributions, advantages, disadvantages probabilistic compared. Finally, future proposed.

Language: Английский

---

A Novel Deep Learning-Based Data Analysis Model for Solar Photovoltaic Power Generation and Electrical Consumption Forecasting in the Smart Power Grid

Applied Computational Intelligence and Soft Computing, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

With the installation of solar panels around world and permanent fluctuation climatic factors, it is, therefore, important to provide necessary energy in electrical network order satisfy demand at all times for smart grid applications. This study first presents a comprehensive comparative review existing deep learning methods used applications such as photovoltaic (PV) generation forecasting power consumption forecasting. In this work, is long term will consider meter data socioeconomic demographic data. Photovoltaic short by considering irradiance, temperature, humidity. Moreover, we have proposed novel hybrid method based on multilayer perceptron (MLP), short‐term memory (LSTM), genetic algorithm (GA). We then simulated climate electricity dataset city Douala. Electrical are collected from meters installed consumers Climate management center The results obtained show outperformance optimized both PV its superiority compared basic support vector machine (SVM), MLP, recurrent neural (RNN), random forest (RFA).

Language: Английский

---

Solar photovoltaic generation and electrical demand forecasting using multi-objective deep learning model for smart grid systems

Cogent Engineering, Journal Year: 2024, Volume and Issue: 11(1)

Published: April 20, 2024

The growing of the photovoltaic (PV) panel's installation in world and intermittent nature climate conditions highlights importance power forecasting for smart grid integration. This work aims to study implement existing Deep Learning (DL) methods used PV electrical load forecasting. We then developed a novel hybrid model made Feed-Forward Neural Network (FFNN), Long Short Term Memory (LSTM) Multi-Objective Particle Swarm Optimization (MOPSO). In this work, is long-term will consider meter data, socio-economic demographic data. generation by considering climatic data such as solar irradiance, temperature humidity. Moreover, we implemented these deep learning on two datasets, first one consumption collected from meters installed at consumers Douala. second management center performances models are evaluated using different error metrics Root Mean Square Error (RMSE) Absolute (MAE) regression (R). proposed gives RMSE, MAE R 1.15, 0.75 0.999 respectively. results obtained show that effective both prediction outperforms other FFNN, Recurrent (RNN), Decision Tree (DT), Gated Unit (GRU) eXtreme Gradient Boosting (XGBoost).

Language: Английский

---

A photovoltaic power ultra short-term prediction method integrating Hungarian clustering and PSO algorithm

Energy Informatics, Journal Year: 2025, Volume and Issue: 8(1)

Published: Jan. 8, 2025

In response to the problem of low prediction accuracy in ultra short-term photovoltaic power, this study combines Hungarian clustering analysis and particle swarm optimization variational mode decomposition algorithm construct a power forecasting model, analyze data depth improve accuracy. The experiment outcomes show that performs well integrating single results effectively improves atypical classification. addition, ensemble model shows significant improvement compared other models on Calinski-Harabasz index, reduces overlap between clusters Davies-Bouldin improving overall quality clustering. Under different weather conditions, convergence speed multiverse support vector machine, algorithms each have their own advantages, but better. has high stability predicting errors, with average absolute error relative lower than BP RBF models. maximum are reduced, indicating effectiveness predictive advantage proposed power.

Language: Английский

---

Exploring the landscape of deep learning for solar photovoltaic power output forecasting: A review

Renewable energy focus, Journal Year: 2025, Volume and Issue: unknown, P. 100682 - 100682

Published: Jan. 1, 2025

Language: Английский

---

Forecasting techniques for power systems with renewables

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 381 - 412

Published: Jan. 1, 2025

Language: Английский

---

Multi-objective collaborative operation optimization of park-level integrated energy system clusters considering green power forecasting and trading

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135055 - 135055

Published: Feb. 1, 2025

Language: Английский

---

BROWN BEAR OPTIMIZED RANDOM FOREST MODEL FOR SHORT TERM SOLAR POWER FORECASTING

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104583 - 104583

Published: March 1, 2025

Language: Английский

---

Deep learning approaches for robust prediction of large-scale renewable energy generation: A comprehensive comparative study from a national context

Intelligent Data Analysis, Journal Year: 2025, Volume and Issue: unknown

Published: March 19, 2025

Precise forecasting of renewable energy generation is crucial for ensuring grid stability and enhancing the efficiency management systems. This research develops rigorously evaluates a range deep learning models—such as Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Units (GRUs), Bidirectional LSTM (BiLSTM) architectures—for predicting solar, wind, total production at national scale. These models are systematically benchmarked against traditional machine approaches gradient boosting methods to determine their predictive capabilities. The findings demonstrate that incorporating memory mechanisms consistently surpass conventional methods, with BiLSTM standing out most precise dependable model. Furthermore, study investigates fully connected artificial neural networks (ANNs) ConvLSTM2D models, reinforcing advantages memory-based architectures in modeling temporal relationships. By introducing robust framework large-scale forecasting, this represents considerable leap forward compared techniques. results highlight transformative potential improving accuracy, thereby facilitating more effective planning smooth integration into power grids.

Language: Английский

---

Model for Forecasting the Volume of Electricity Consumption Using the «Random Forest» Algorithm

Èlektronnoe modelirovanie, Journal Year: 2025, Volume and Issue: 47(2), P. 48 - 66

Published: April 7, 2025

The article presents the peculiarities of applying Random Forest (RF) algorithm for short-term forecasting electricity consumption by consumers served a supplier company. As result processing historical data using RF algorithm, model was developed that takes into account time, meteorological, and calendar features. Identification mo-del’s hyperparameters made it possible to achieve high accuracy in forecast calculations. results experimental calculations demonstrate effectiveness model, particu-lar, possibility finding its key qualifying parameters. features applica-tion decision-making system company regarding management en-ergy resources minimization imbalance volumes market are shown.

Language: Английский

---