Practice analysis of collaborative security application of power big data

Published: Jan. 15, 2025

Through data preprocessing, fusion and collaborative analysis, as well security protection technologies, the quality in smart grids have been improved. Specific approaches include power demand side management, energy analysis of existing methods. The research results indicate that technology methods big are great significance for improving efficiency system, achieving comprehensive monitoring, prediction, optimization.

Language: Английский

---

Master-slave game-based optimal scheduling strategy for integrated energy systems with carbon capture considerations

Energy Reports, Journal Year: 2024, Volume and Issue: 13, P. 780 - 788

Published: Dec. 26, 2024

Language: Английский

---

High-precision concentration detection of CO₂ in flue gas based on BO-LSTM and variational mode decomposition

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 35(9), P. 095202 - 095202

Published: June 3, 2024

Abstract In order to improve the detection accuracy of CO 2 and other gases in flue gas emitted from thermal power plants, a concentration model based on tunable semiconductor laser absorption spectroscopy was proposed. First, variational mode decomposition used filter harmonic signal after removing outliers reduce influence noise results. Suitable lines characteristics were then selected according properties correlation theory. Finally, inversion completed using long short-term memory networks, Bayesian optimization algorithm introduced optimize hyperparameters network. The experimental results showed that R RMSE test set 0.998 84 0.116 08, respectively, range 1%–12%. addition, Allan analysis variance revealed maximum measurement error only 0.005 619% when integration time 38 s. Compared traditional schemes, stability are significantly improved, which provides feasible scheme for plants.

Language: Английский

---

Exploring LSTM-based Attention Mechanisms with PSO and Grid Search under Different Normalization Techniques for Energy demands Time Series Forecasting

Knowledge Engineering and Data Science, Journal Year: 2024, Volume and Issue: 7(1), P. 1 - 1

Published: April 16, 2024

Advanced analytical approaches are required to accurately forecast the energy sector's rising complexity and volume of time series data. This research aims demand utilizing sophisticated Long Short-Term Memory (LSTM) configurations with Attention mechanisms (Att), Grid search, Particle Swarm Optimization (PSO). In addition, study also examines influence Min-Max Z-Score normalization in preprocessing stage on accuracy performances baselines proposed models. PSO Search techniques used select best hyperparameters for LSTM models, while attention mechanism selects important input LSTM. The compares performance (LSTM, Grid-search-LSTM, PSO-LSTM) proposes models (Att-LSTM, Att-Grid-search-LSTM, Att-PSO-LSTM) based MAPE, RMSE, R2 metrics into two scenarios normalization: Min-Max, Z-Score. results show that all have better than those model is shown Att-PSO-LSTM MAPE 3.1135, RMSE 0.0551, 0.9233, followed by Att-LSTM, PSO-LSTM, These findings emphasize effectiveness improving predictions methods performance. study's novel approach provides valuable insights forecasting demands.

Language: Английский

---

Transfer-learning enabled adaptive framework for load forecasting under concept-drift challenges in smart-grids across different-generation-modalities

Energy Reports, Journal Year: 2024, Volume and Issue: 12, P. 3519 - 3532

Published: Sept. 24, 2024

Language: Английский

---

Research on Ultra-short-term combination forecasting algorithm of power load based on machine learning

Journal of Physics Conference Series, Journal Year: 2024, Volume and Issue: 2846(1), P. 012046 - 012046

Published: Sept. 1, 2024

Abstract Power load forecasting is of great significance to the power grid marketing department. To obtain accurate results, a minute-by-minute method for electricity based on multi-stage proposed (TPE-WXL) by combining non-linear and time-series attributes. Firstly, historical series specific areas in city are pre-processed. Then, order accurately predicted XGBoost LightGBM applied extract attributes from build hybrid model. Moreover, TPE introduced enhance hyperparameters model series. Finally, dataset region used as an example conduct experimental analysis. Experimental results revealed that can forecast trend load, is, R 2 =0.981, RMSE =2.643.

Language: Английский

---