Multi-task short-term reactive and active load forecasting method based on attention-LSTM model

Qin, Jian; Zhang, Yi; Fan, Shixiong; Hu, Xiaonan; Huang, Yongqiang; Lu, Zexin; Liu, Yan

doi:10.1016/j.ijepes.2021.107517

Cited by 54 publications

(26 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed MACL model was compared with the corresponding single-task attention-CLSTM model for both subtasks. former was trained in multi-task mode, while the latter was trained on a single subtask [51]. Because of the multi-task learning, MACL can extract complementary features of hydrogen ion concentration and ferrous ion concentration, and exploit the potential dynamic correlation between them to improve prediction accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, the original data was normalized so that the pre-processed data was limited to the range [0,1]. The formulas are as follows [51]:…”

Section: Data Preprocessingmentioning

confidence: 99%

“…Firstly, the outliers in the data were removed by data cleaning, while the missing values were filled by linear interpolation. Secondly, different features often have different dimensions, which will affect the results of data analysis and reduce the prediction accuracy of the model [51]. Therefore, the original data was normalized so that the pre-processed data was limited to the range [0,1].…”

Section: Data Preprocessingmentioning

confidence: 99%

See 2 more Smart Citations

A multi-task prediction method for acid concentration based on attention-CLSTM

Zhu

Liu

Cao

et al. 2022

Preprint

View full text Add to dashboard Cite

The accurate measurement of acid concentration, including hydrogen chloride (HCl) and ferrous chloride concentrations (FeCl2), is a critical part of ensuring the quality of strip steel pickling. In this study, a multi-task attention convolutional long short-term memory (MACL) neural network model was proposed to predict hydrogen ion and ferrous ion concentrations simultaneously. Firstly, in order to extract significant information from the input sequence, an attention mechanism was added to the model to calculate the correlation between the input features and the acid concentration at each time step. Next, multi-task learning explores the connections between the two tasks and exploits hidden constraints to improve prediction accuracy. Finally, deep features were extracted through convolutional long short-term memory (CLSTM) neural network, and the acid concentration was predicted. The proposed MACL model was compared with other popular prediction models. The experimental results show that proposed MACL model generally outperforms other models, indicating that proposed model has excellent predictive performance and effectiveness.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Therefore, the original data was normalized so that the pre-processed data was limited to the range [0,1]. The formulas are as follows [51]:…”

Section: Data Preprocessingmentioning

confidence: 99%

Section: Data Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

A multi-task prediction method for acid concentration based on attention-CLSTM

Zhu

Liu

Cao

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Recurrent neural networks (RNN) will have the problem of long-term dependence during the training process. Therefore, long short-term memory (LSTM) [70][71][72] is born to solve the problem of long-term dependence, and LSTM is deliberately designed to avoid the problem of long-term dependence. In practice, remembering long-term information is the default behavior of LSTM, not a capability that can be acquired at a high cost.…”

Section: Bidirectional Long Short-term Memorymentioning

confidence: 99%

Short‐term natural gas consumption prediction based on wavelet transform and bidirectional long short‐term memory optimized by Bayesian network

Liu²,

Qiao

2022

Energy Science & Engineering

View full text Add to dashboard Cite

In the energy structure, natural gas is an important clean energy, and its consumption forecast is of great significance for energy policy formulation, pipeline network planning design, and peak shaving capacity determination. In the field of forecasting, wavelet transform (WT) is widely used to process time series, especially natural gas consumption. However, in the application of the WT, the wavelet's orders and levels are randomly fixed. To solve this problem, this study proposes a hybrid model, which is based on bidirectional long short‐term memory (BiLSTM). In addition, Bayesian networks are used to optimize the hyperparameters of BiLSTM. And the different wavelets' orders and levels are utilized to deal with the daily natural gas consumption (DNLGSCN). When each level of Coiflets wavelets' four and five orders are used to process the DNLGSCN, the fifth level of Coiflets wavelets' four and five orders have the highest prediction accuracy, respectively, which is 0.3318 and 0.1773, taking U1 as an example. Using Symflets wavelet to decompose the DNLGSCN also gives the same result. Compared with the decomposition method (e.g., ensemble empirical mode decomposition), the prediction performance of the above four wavelet decomposition methods is better. The main conclusions are that decomposing the DNLGSCN with the fifth level of Coiflets wavelet's five orders has the best prediction performance.

show abstract

“…Effective feature selection can eliminate redundant or irrelevant features, reduce the features and running time, the complexity and over fitting, and improve the prediction accuracy and generalization ability. Generally, historical load, electricity price and weather factors such as temperature and humidity are the common input variables [7][8][9][10][11][12] . If all of them are used as input variables directly, it is likely to result in high input dimensions and more redundant information, which will further affect the prediction accuracy of the load.…”

Section: Introductionmentioning

confidence: 99%

Day-ahead load forecasting based on Spearman-MultiTaskLasso-MLP

Wang

Wang²,

Zhang³

2022

International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2022)

View full text Add to dashboard Cite

Short term load forecasting is an important guarantee to ensure the smooth operation of power system, but there are many factors affecting it, which makes it difficult to predict it whit high-precision in the future. In order to improve the accuracy of load forecasting, a day ahead load forecasting model based on Spearman correlation coefficient, MultiTaskLasso and Multilayer Perceptron (MLP) is proposed in this paper. Firstly, Spearman correlation coefficient is used to select the leading steps in order to eliminate the low influencing factors related to load; Secondly, MultiTaskLasso is applied for feature extraction to extract the optimal feature set effectively that can best express the load fluctuation from different influencing factors with different candidate input variables; Finally, MLP is applied to predict the load with 48 lagging steps in the next 24 hours. Model comparison and verification results show that, the predict accuracy has increased by at least 24.38% and 25.32% respectively when the selection of the leading steps and the extraction of the optimal feature set have completed, and the prediction accuracy of Spearman-MultiTaskLasso-MLP is improved by at least 39.42%. The effect of the leading steps selection and feature extraction is obvious, and the prediction accuracy of each comparative model is improved significantly. The results of this study can provide a reference for the selection of leading steps and feature extraction for similar studies.

show abstract

Multi-task short-term reactive and active load forecasting method based on attention-LSTM model

Cited by 54 publications

References 35 publications

A multi-task prediction method for acid concentration based on attention-CLSTM

A multi-task prediction method for acid concentration based on attention-CLSTM

Short‐term natural gas consumption prediction based on wavelet transform and bidirectional long short‐term memory optimized by Bayesian network

Day-ahead load forecasting based on Spearman-MultiTaskLasso-MLP

Contact Info

Product

Resources

About