Ultra-short-term power forecast method for the wind farm based on feature selection and temporal convolution network

Zha, Wenting; Liu, Jie; Li, Yalong; Liang, Yingyu

doi:10.1016/j.isatra.2022.01.024

Cited by 36 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The alignment of results between these studies provides further validation and strengthens the reliability of the feature selection approach [37,38]. By comparing the results of this article with other relevant studies, it becomes evident that selecting the most important parameters is a crucial step in energy forecasting [39]. The consistent findings across different studies emphasize the importance of considering these influential factors to optimize the prediction accuracy and enhance decision-making in energy management [39].…”

Section: Discussionsupporting

confidence: 60%

“…By comparing the results of this article with other relevant studies, it becomes evident that selecting the most important parameters is a crucial step in energy forecasting [39]. The consistent findings across different studies emphasize the importance of considering these influential factors to optimize the prediction accuracy and enhance decision‐making in energy management [39]. Thus, the findings of this article contribute to the existing body of knowledge by demonstrating the effectiveness of feature selection methods in identifying the key parameters for energy production prediction.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Geographic information system‐based prediction of solar power plant production using deep neural networks

Mokarram

Aghaei

Mokarram

et al. 2023

IET Renewable Power Gen

View full text Add to dashboard Cite

The study aims to predict solar energy generation to ensure the successful operation of solar power plants. This objective is crucial in light of the increasing energy demand, global warming concerns, and greenhouse gas emissions. To achieve this, the study employs multiple linear regression and feature selection techniques to calculate energy generation. Additionally, long short‐term memory (LSTM) is used to predict energy generation levels based on climate conditions. Furthermore, the spatial distribution of energy generation is analyzed using inverse distance weighting. The results of the study reveal that temperature, solar radiation, relative humidity, wind speed, wind direction, and vapor pressure deficit are the most significant parameters for predicting energy generation. The LSTM method proves to be highly accurate in predicting fluctuating energy generation patterns. Notably, the southern regions of the study area exhibit a greater potential for energy generation compared to the northern regions. Approximately 30% of the region generates over 1400 kWh, with the southern areas, characterized by hot and dry climates, producing around 1500 kWh, while the northern regions, with cold and humid climates, generate approximately 1100 kWh.

show abstract

Section: Discussionsupporting

confidence: 60%

Section: Discussionmentioning

confidence: 99%

Geographic information system‐based prediction of solar power plant production using deep neural networks

Mokarram

Aghaei

Mokarram

et al. 2023

IET Renewable Power Gen

View full text Add to dashboard Cite

show abstract

“…Bai S et al (2018) proposed a new network called temporal convolutional network (TCN), which has the advantages of both CNN and RNN, and experiments show that TCN outperforms the LSTM model in prediction accuracy (Lara-Benítez P et al 2020). And fortunately, some studies have demonstrated that TCN with unique structures outperforms LSTM networks when dealing with long-step time series, indicating that TCN can effectively utilize convolutional methods to extract the features in complex time series, which makes it suitable for forecasting ultra-short-term wind speed prediction (Zha W et al 2022). In addition to using TCN to extract features from complex wind speed sequences, the sequence decomposition method has also been proved to be an effective means.…”

Section: Introductionmentioning

confidence: 99%

Short-term prediction for wind power based on temporal convolutional network

2020

View full text Add to dashboard Cite

“…In this study, an Extreme gradient boosting (XGBoost) [42,43] model is also established and trained to complete the feature selection [44]. XGBoost constructs multiple decision tree models through iterative iterations to continuously optimize the prediction objective.…”

Section: Data Feature Selectionmentioning

confidence: 99%

Evaluation of Energy Utilization Efficiency and Optimal Energy Matching Model of EAF Steelmaking Based on Association Rule Mining

Yang,

Li,

et al. 2024

Metals

View full text Add to dashboard Cite

In the iron and steel industry, evaluating the energy utilization efficiency (EUE) and determining the optimal energy matching mode play an important role in addressing increasing energy depletion and environmental problems. Electric Arc Furnace (EAF) steelmaking is a typical short crude steel production route, which is characterized by an energy-intensive fast smelting rhythm and diversified raw charge structure. In this paper, the energy model of the EAF steelmaking process is established to conduct an energy analysis and EUE evaluation. An association rule mining (ARM) strategy for guiding the EAF production process based on data cleaning, feature selection, and an association rule (AR) algorithm was proposed, and the effectiveness of this strategy was verified. The unsupervised algorithm Auto-Encoder (AE) was adopted to detect and eliminate abnormal data, complete data cleaning, and ensure data quality and accuracy. The AE model performs best when the number of nodes in the hidden layer is 18. The feature selection determines 10 factors such as the hot metal (HM) ratio and HM temperature as important data features to simplify the model structure. According to different ratios and temperatures of the HM, combined with k-means clustering and an AR algorithm, the optimal operation process for the EUE in the EAF steelmaking under different smelting modes is proposed. The results indicated that under the conditions of a low HM ratio and low HM temperature, the EUE is best when the power consumption in the second stage ranges between 4853 kWh and 7520 kWh, the oxygen consumption in the second stage ranges between 1816 m3 and 1961 m3, and the natural gas consumption ranges between 156 m3 and 196 m3. Conversely, under the conditions of a high HM ratio and high HM temperature, the EUE tends to decrease, and the EUE is best when the furnace wall oxygen consumption ranges between 4732 m3 and 5670 m3, and the oxygen consumption in the second stage ranges between 1561 m3 and 1871 m3. By comparison, under different smelting modes, the smelting scheme obtained by the ARM has an obvious effect on the improvement of the EUE. With a high EUE, the improvement of the A2B1 smelting mode is the most obvious, from 24.7% to 53%. This study is expected to provide technical ideas for energy conservation and emission reduction in the EAF steelmaking process in the future.

show abstract

Ultra-short-term power forecast method for the wind farm based on feature selection and temporal convolution network

Cited by 36 publications

References 17 publications

Geographic information system‐based prediction of solar power plant production using deep neural networks

Geographic information system‐based prediction of solar power plant production using deep neural networks

Short-term prediction for wind power based on temporal convolutional network

Evaluation of Energy Utilization Efficiency and Optimal Energy Matching Model of EAF Steelmaking Based on Association Rule Mining

Contact Info

Product

Resources

About