Forecasting and Comparative Application of PV System Electricity Generation for Sprinkler Irrigation Machines Based on Multiple Models DOI Creative Commons

Bohan Li,

Kenan Liu, Yaohui Cai

и другие.

Agronomy, Год журнала: 2024, Номер 14(11), С. 2696 - 2696

Опубликована: Ноя. 15, 2024

Currently, photovoltaic (PV) resources have been widely applied in the agricultural sector. However, due to unreasonable configuration of multi-energy collaboration, issues such as unstable power supply and high investment costs still persist. Therefore, this study proposes a solution reasonably determine area capacity PV panels for irrigation machines, addressing fluctuations generation solar sprinkler systems under different regional meteorological conditions. The aim is more accurately predict (PVPG) optimize system, ensuring reliability while reducing costs. This paper first establishes PVPG prediction model based on four forecasting models conducts comparative analysis identify optimal model. Next, annual, seasonal, term scale are developed further studied conjunction with model, using evaluation metrics assess compare models. Finally, mathematical established combination solved system machines. results indicate that among models, SARIMAX performs best, R2 index reached 0.948, which was 19.4% higher than others, MAE 10% lower others. exhibited highest accuracy three time RMSE 4.8% 1.1% After optimizing machine scale, it verified can ensure both manage energy overflow effectively.

Язык: Английский

A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster DOI Creative Commons
Tong Yang, Minan Tang, Hanting Li

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 6, 2025

Abstract Short-term day-ahead photovoltaic power prediction is of great significance for system dispatch plan formulation. In this work, to improve the accuracy prediction, a TCN-Wpsformer (temporal convolutional network-window probability sparse Transformer) model based on combining data restoration and FCM (fuzzy C means) cluster proposed. The time code dataset obtained after clustering was spliced with location code. A temporal neural network introduced extract segment features incorporate self-attention mechanism. short-term outputted by window Transformer in multiple steps. Compared original model, uses It captures long-term dependencies while filtering out relatively high importance computation, which improves reduces computational cost. computing reduced 68.83% R squared improved 5.3% compared Transformer. comparison made through 11 models, above 99% different volume station data. proves that stability cross scene generalisation ability well. Meanwhile, it can also provide more accurate confidence intervals basis point has certain application value.

Язык: Английский

Процитировано

0
Photovoltaic power forecasting: Using wavelet threshold denoising combined with VMD DOI
Lin Liu, Jianqiu Zhang, Shibei Xue

и другие.

Renewable Energy, Год журнала: 2025, Номер unknown, С. 123152 - 123152

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Sky Images based Photovoltaic Power Forecasting: A Novel Approach with Optimized VMD and Vision Mamba DOI Creative Commons
Chenhao Cai,

Leyao Zhang,

Jianguo Zhou

и другие.

Results in Engineering, Год журнала: 2024, Номер unknown, С. 103022 - 103022

Опубликована: Окт. 1, 2024

Язык: Английский

Процитировано

3
Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning DOI Creative Commons
Liang Yuan,

Xiangting Wang,

Yao Sun

и другие.

International Journal of Electrical Power & Energy Systems, Год журнала: 2024, Номер 164, С. 110389 - 110389

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

3
Multi 2D-CNN-based model for short-term PV power forecast embedded with Laplacian Attention DOI Creative Commons

Tuyen Nguyen‐Duc,

Hieu Do-Dinh,

Goro Fujita

и другие.

Energy Reports, Год журнала: 2024, Номер 12, С. 2086 - 2096

Опубликована: Авг. 14, 2024

Amid the bloom of Renewable energy (RE) integrated into grid, an accurate Photovoltaic(PV) power forecast is considered to be a crucial task in maintaining reliability and stability systems since this technology strongly depends on various external factors, causing fluctuation output power. However, poor quality input data, which very common practical circumstances owing low-cost measurement data acquisition devices, poses enormous challenge for predictive model deeply extract spatial temporal correlation data. This study proposes Multi Two-Dimensional Convolutional Neural Network (2D-CNN) short-term PV embedded with Laplacian Attention mechanism. By viewing sequences 2D form, map constructed, interconnected feature among variables can captured by convolution operation. Moreover, multiple CNN layers working parallel architecture, different representations hidden inside detected, enabling proposed bring out promising performance across time-step without modifying its initial parameters. In order reduce decay impact irrelevant existing mechanism employed. The matrix dynamically modified during training process produce attention matrix, represents between variables. Therefore, able focus informative features ignore negative ones. experiments conducted two datasets opposite characteristics provide deep insights strength over baseline model, demonstrates efficiency especially when dealing bearing tough characteristics.

Язык: Английский

Процитировано

2
Ultra-short-term Single-step Photovoltaic Power Prediction based on VMD-Attention-BiLSTM Combined Model DOI
Haisheng Yu,

Shenhui Song

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Сен. 20, 2024

Abstract Research on photovoltaic systems (PV) power prediction contributes to optimizing configurations, responding promptly emergencies, reducing costs, and maintaining long-term system stability. This study proposes a VMD-Attention-BiLSTM model for predicting ultra-short-term further enhance performance. Firstly, VMD decomposes historical data into multiple sub-sequences with different frequencies, treating each sub-sequence as separate input variable expansion. Secondly, the Attention mechanism calculates correlation coefficients between variables assigns corresponding weights based magnitude of output variable. Finally, BiLSTM adopts dual-layer LSTM structure more accurately extract features. Experimental results show that compared various advanced deep learning methods, MAE combined improves by at least 29%.

Язык: Английский

Процитировано

1
Explainable AI and optimized solar power generation forecasting model based on environmental conditions DOI Creative Commons
Rizk M. Rizk‐Allah,

Lobna M. Abouelmagd,

Ashraf Darwish

и другие.

PLoS ONE, Год журнала: 2024, Номер 19(10), С. e0308002 - e0308002

Опубликована: Окт. 2, 2024

This paper proposes a model called X-LSTM-EO, which integrates explainable artificial intelligence (XAI), long short-term memory (LSTM), and equilibrium optimizer (EO) to reliably forecast solar power generation. The LSTM component forecasts generation rates based on environmental conditions, while the EO optimizes model’s hyper-parameters through training. XAI-based Local Interpretable Model-independent Explanation (LIME) is adapted identify critical factors that influence accuracy of in smart systems. effectiveness proposed X-LSTM-EO evaluated use five metrics; R-squared (R 2 ), root mean square error (RMSE), coefficient variation (COV), absolute (MAE), efficiency (EC). gains values 0.99, 0.46, 0.35, 0.229, 0.95, for R , RMSE, COV, MAE, EC respectively. results this improve performance original conventional LSTM, where improvement rate is; 148%, 21%, 27%, 20%, 134% compared with other machine learning algorithm such as Decision tree (DT), Linear regression (LR) Gradient Boosting. It was shown worked better than DT LR when were compared. Additionally, PSO employed instead validate outcomes, further demonstrated efficacy optimizer. experimental simulations demonstrate can accurately estimate PV response abrupt changes patterns. Moreover, might assist optimizing operations photovoltaic units. implemented utilizing TensorFlow Keras within Google Collab environment.

Язык: Английский

Процитировано

1
Improving short-term photovoltaic power forecasting with an evolving neural network incorporating time-varying filtering based on empirical mode decomposition DOI
Mokhtar Ghodbane, Naima El-Amarty, Boussad Boumeddane

и другие.

Energy Conversion and Management, Год журнала: 2024, Номер 323, С. 119261 - 119261

Опубликована: Ноя. 14, 2024

Язык: Английский

Процитировано

1
Microgrid economic dispatch using Information-Enhanced Deep Reinforcement Learning with consideration of control periods DOI
Wenzhao Liu,

Z. Mao

Electric Power Systems Research, Год журнала: 2024, Номер 239, С. 111244 - 111244

Опубликована: Ноя. 21, 2024

Язык: Английский

Процитировано

1
Predictive Modeling of Photovoltaic Energy Yield Using an ARIMA Approach DOI Creative Commons
Fatima Sapundzhi,

Aleksandar Chikalov,

Slavi Georgiev

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(23), С. 11192 - 11192

Опубликована: Ноя. 30, 2024

This paper presents a method for predicting the energy yield of photovoltaic (PV) system based on ARIMA algorithm. We analyze two key time series: specific and total PV system. Two models are developed each one selected by authors determined SPSS. Model performance is evaluated through fit statistics, providing comprehensive assessment model accuracy. The residuals’ ACF PACF examined to ensure adequacy, confidence intervals calculated residuals validate models. A monthly forecast then generated both series, complete with intervals, demonstrate models’ predictive capabilities. results highlight effectiveness in forecasting yields, offering valuable insights optimizing planning. study contributes field renewable demonstrating applicability systems.

Язык: Английский

Процитировано

1