Research on Photovoltaic Power Prediction Method for Power Grid Safety DOI

Mingkang Guo,

Wenxuan Ji,

Bingling Gu

et al.

2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE), Journal Year: 2023, Volume and Issue: unknown, P. 296 - 299

Published: April 14, 2023

When integrating large-scale photovoltaic systems with the power grid, variability and intermittency of may potentially endanger secure stable operation system as well its scheduling management. So a new prediction method using logistic chaotic mapping (LCM) improving atomic search optimization algorithm (ASO) to optimize back propagation neural network (LCM-ASO-BPNN) is proposed solve this problem. The ASO used defect that BPNN likely be trapped in local optimum, initial population optimized by introducing mapping, subsequently, model's predictive accuracy greatly enhanced. experimental results demonstrate significant improvement model when compared traditional model.

Language: Английский

Research on time-series based and similarity search based methods for PV power prediction DOI
Meng Jiang, Kun Ding, Xiang Chen

et al.

Energy Conversion and Management, Journal Year: 2024, Volume and Issue: 308, P. 118391 - 118391

Published: April 9, 2024

Language: Английский

Citations

10
Short-Term Photovoltaic Power Forecasting Based on the VMD-IDBO-DHKELM Model DOI Creative Commons
Shengli Wang, Xiaolong Guo, Tian-Le Sun

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(2), P. 403 - 403

Published: Jan. 17, 2025

A short-term photovoltaic power forecasting method is proposed, integrating variational mode decomposition (VMD), an improved dung beetle algorithm (IDBO), and a deep hybrid kernel extreme learning machine (DHKELM). First, the weather factors less relevant to (PV) generation are filtered using Spearman correlation coefficient. Historical data then clustered into three categories—sunny, cloudy, rainy days—using K-means algorithm. Next, original PV decomposed through VMD. DHKELM-based combined prediction model developed for each component of decomposition, tailored different types. The model’s hyperparameters optimized IDBO. final forecast determined by combining outcomes individual component. Validation performed actual from plant in Australia station Kashgar, China demonstrates. Numerical evaluation results show that proposed improves Mean Absolute Error (MAE) 3.84% Root-Mean-Squared (RMSE) 3.38%, confirming its accuracy.

Language: Английский

Citations

0
V2G Scheduling of Electric Vehicles Considering Wind Power Consumption DOI Creative Commons
Bingjie Shang, Nina Dai, Li Cai

et al.

World Electric Vehicle Journal, Journal Year: 2023, Volume and Issue: 14(9), P. 236 - 236

Published: Aug. 28, 2023

The wind power (WP) has strong random volatility and is not coordinated with the load in time space, resulting serious abandonment. Based on this, an orderly charging discharging strategy for electric vehicles (EVs) considering WP consumption proposed this paper. uses vehicle-to-grid (V2G) technology to establish maximum of region, minimizes peak–valley difference grid maximizes electricity sales efficiency company mountainous city. dynamic prices are set according predicted values true output, improved adaptive particle swarm optimization (APSO) CVX toolbox used solve problems. When user responsiveness 30%, 60% 100%, 72.1%, 81.04% 92.69%, respectively. Meanwhile, peak shaving valley filling realized, benefit guaranteed.

Language: Английский

Citations

6
Photovoltaic power generation prediction and optimization configuration model based on GPR and improved PSO algorithm DOI Creative Commons
Zhennan Zhang,

Zhenliang Duan,

Lingwei Zhang

et al.

EAI Endorsed Transactions on Energy Web, Journal Year: 2024, Volume and Issue: 11

Published: Feb. 20, 2024

As the growing demand for energy as well strengthening of environmental awareness, photovoltaic power generation, a clean and renewable source, has gradually attracted people's attention attention. To facilitate dispatching planning system, this study uses historical data meteorological to build generation prediction configuration optimization model on ground Gaussian process regression improved particle swarm algorithm. The simulation results show that curve is closest real curve, stable not easily disturbed by noise data. Root-mean-square deviation average absolute proportional error are small, disparity in predicted value true small; integration multi factor accuracy data, effect good. Particle algorithm could continuously enhance search optimal solution, Rate convergence fast. Pareto solution can provide different solutions suitable optimization. Reasonable effectively reduce active line loss voltage deviation, with maximum reduction values reaching 132kW 0.028, respectively. research design predictive models optimized promote formation smart grids.

Language: Английский

Citations

1
Research on Modulation Signal Denoising Method Based on Improved Variational Mode Decomposition DOI Open Access

Canyu Mo,

Qianqiang Lin,

Yuanduo Niu

et al.

Journal of Electronic Research and Application, Journal Year: 2024, Volume and Issue: 8(1), P. 7 - 15

Published: Jan. 18, 2024

In order to further analyze the micro-motion modulation signals generated by rotating components and extractmicro-motion features, a signal denoising algorithm based on improved variational mode decomposition (VMD)is proposed. To improve time-frequency performance, this method decomposes data into narrowband signalsand analyzes internal energy frequency variations within signal. Genetic algorithms are used adaptivelyoptimize number bandwidth control parameters in process of VMD. This approach aims obtain theoptimal parameter combination perform The optimalmode quadratic penalty factor for VMD determined. Based optimal values numberand factor, original is decomposed using VMD, resulting intrinsicmode function (IMF) components. effective modes then reconstructed with denoised modes, achieving signaldenoising. Through experimental verification, proposed demonstrates modulationsignals. simulation validation, achieves highest signal-to-noise ratio (SNR) exhibits bestperformance.

Language: Английский

Citations

1
Short-term photovoltaic power prediction based on coyote algorithm optimized long-short-term memory network DOI

Jinjin Mai,

Xiaohong Zhang

Published: Jan. 19, 2024

Language: Английский

Citations

0
A PV Prediction Model Based on Sparrow Search Optimization with Variational Mode Decomposition and Gated Recurrent Unit Neural Network DOI

Yi-Lin Zhao,

Youqiang Wang,

Xiaoming Li

et al.

Lecture notes in electrical engineering, Journal Year: 2024, Volume and Issue: unknown, P. 591 - 597

Published: Jan. 1, 2024

Language: Английский

Citations

0
Research on Photovoltaic Power Prediction Method for Power Grid Safety DOI

Mingkang Guo,

Wenxuan Ji,

Bingling Gu

et al.

2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE), Journal Year: 2023, Volume and Issue: unknown, P. 296 - 299

Published: April 14, 2023

When integrating large-scale photovoltaic systems with the power grid, variability and intermittency of may potentially endanger secure stable operation system as well its scheduling management. So a new prediction method using logistic chaotic mapping (LCM) improving atomic search optimization algorithm (ASO) to optimize back propagation neural network (LCM-ASO-BPNN) is proposed solve this problem. The ASO used defect that BPNN likely be trapped in local optimum, initial population optimized by introducing mapping, subsequently, model's predictive accuracy greatly enhanced. experimental results demonstrate significant improvement model when compared traditional model.

Language: Английский

Citations

0