An Ensemble Feature Selection Method for Short-Term Electrical Load Forecasting

Chen, Junxingxu; Li, Ting; Zou, Yanhui; Wang, Guorui; Ye, Huisheng; Lv, Fengyi

doi:10.1109/ei247390.2019.9062042

Cited by 12 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is necessary to construct a forecasting model by collecting and analyzing multiple input variables. Final input variables for distribution line peak load forecasting should be selected, and a forecasting model should be presented by comparing the performance of forecasting models according to the combination of input variables through correlation analysis of input variables and output variables such as Pearson correlation, Spearman correlation, and mutual information analysis [17][18][19][20][21][22]. Figure 4 shows the input variable selection process for constructing a machine learning model.…”

Section: Input Variable Selection Processmentioning

confidence: 99%

“…The mutual information is called interdependence information and is an indicator that can determine the correlation between two data sets in addition to the linear correlation. The Pearson correlation coefficient, which is often used in correlation analysis, analyzes linear correlations, and the Spearman correlation coefficient has a high correlation even in the case of non-linear monotonic functions by analyzing the linear correlation of rank [17][18][19][20][21][22]. Figures 6 and 7 show the results of analyzing the correlation coefficients of 46 input variables, representing that the first row or column shows the correlation between the month peak and other input variables.…”

Section: Input and Output Correlation Analysismentioning

confidence: 99%

See 1 more Smart Citation

A Study on Load Forecasting of Distribution Line Based on Ensemble Learning for Mid- to Long-Term Distribution Planning

et al. 2022

View full text Add to dashboard Cite

The complexity and uncertainty of the distribution system are increasing as the connection of distributed power sources using solar or wind energy is rapidly increasing, and digital loads are expanding. As these complexity and uncertainty keep increasing the investment cost for distribution facilities, optimal distribution planning becomes a matter of greater focus. This paper analyzed the existing mid-to-long-term load forecasting method for KEPCO’s distribution planning and proposed a mid- to long-term load forecasting method based on ensemble learning. After selecting optimal input variables required for the load forecasting model through correlation analysis, individual forecasting models were selected, which enabled the derivation of the optimal combination of ensemble load forecast models. This paper additionally offered an improved load forecasting model that considers the characteristics of each distribution line for enhancing the mid- to long-term distribution line load forecasting process for distribution planning. The study verified the performance of the proposed method by comparing forecasting values with actual values.

show abstract

Section: Input Variable Selection Processmentioning

confidence: 99%

Section: Input and Output Correlation Analysismentioning

confidence: 99%

A Study on Load Forecasting of Distribution Line Based on Ensemble Learning for Mid- to Long-Term Distribution Planning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In typical engineering applications of machine learning, feature selection methods can be roughly classified into filtering, wrapping, and embedding methods. Feature dimension reduction methods include the principal component and linear discriminant analyses [5,[10][11][12][13]. Although the machine learning feature engineering method has its general advantages in application, the interpretability of the finally formed load features is not clear and sufficiently intuitive.…”

Section: Introductionmentioning

confidence: 99%

“…Fig.11Optimal setting of hidden layer neurons Fig.11shows that the optimal interval for trial based on an empirical equation is[11,20]. To avoid the contingency of a single test, 10 rounds of calculation were conducted for the number of neurons in each hidden layer, and the mean square error of repeated test training data samples was calculated.…”

mentioning

confidence: 99%

Short-term load forecasting method based on fuzzy optimization combined model of load feature recognition

Xie,

Lin,

Xie

2024

Preprint

View full text Add to dashboard Cite

With the continuous development of smart grid construction and the gradual improvement of power market operation mechanisms, the importance of power load forecasting is continually increasing. In this study, a short-term load prediction method based on the fuzzy optimization combined model of load feature recognition was designed to address the problems of weak generalization ability and poor prediction accuracy of the conventional feedforward neural network prediction model. First, the Douglas–Peucker algorithm and fuzzy optimization theory of load feature recognition was analyzed, and the combined prediction model was constructed. Second, data analysis and pre-processing were performed based on the actual historical load data of a certain area and the corresponding meteorological and calendar rule information data. Finally, a practical example was used to test and analyze the short-term load forecasting effect of the fuzzy optimization combined model. The calculation results proved that the presented fuzzy optimization combined model of load feature recognition outperformed the conventional model in terms of computational efficiency and specific performance; therefore, the proposed model supports further development of actual power load prediction.

show abstract

“…A wrapper method considers different feature subsets and then evaluates the goodness of them using classification or prediction accuracy. This results in good performance but costs more computational resource [23]. Moreover, to get the best subset, we need evaluate all possible subsets of features, which is not feasible for high-dimensional datasets.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems

Xue¹,

Chang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

A major limitation of fuzzy or neuro-fuzzy systems is their failure to deal with high-dimensional datasets. This happens primarily due to the use of T-norm, particularly, product or minimum (or a softer version of it). Thus, there are hardly any work dealing with datasets with dimensions more than hundred or so. Here, we propose a neuro-fuzzy framework that can handle datasets with dimensions even more than 7000! In this context, we propose an adaptive softmin (Ada-softmin) which effectively overcomes the drawbacks of "numeric underflow" and "fake minimum" that arise for existing fuzzy systems while dealing with high-dimensional problems. We call it an Adaptive Takagi-Sugeno-Kang (AdaTSK) fuzzy system. We then equip the AdaTSK system to perform feature selection and rule extraction in an integrated manner. In this context, a novel gate function is introduced and embedded only in the consequent parts, which can determine the useful features and rules, in two successive phases of learning. Unlike conventional fuzzy rule bases, we design an enhanced fuzzy rule base (En-FRB), which maintains adequate rules but does not grow the number of rules exponentially with dimension that typically happens for fuzzy neural networks. The integrated Feature Selection and Rule Extraction AdaTSK (FSRE-AdaTSK) system consists of three sequential phases: (i) feature selection, (ii) rule extraction, and (iii) fine tuning. The effectiveness of the FSRE-AdaTSK is demonstrated on 19 datasets of which five are in more than 2000 dimension including two with dimension greater than 7000. This may be the first time fuzzy systems are realized for classification involving more than 7000 input features.

show abstract

An Ensemble Feature Selection Method for Short-Term Electrical Load Forecasting

Cited by 12 publications

References 11 publications

A Study on Load Forecasting of Distribution Line Based on Ensemble Learning for Mid- to Long-Term Distribution Planning

A Study on Load Forecasting of Distribution Line Based on Ensemble Learning for Mid- to Long-Term Distribution Planning

Short-term load forecasting method based on fuzzy optimization combined model of load feature recognition

An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems

Contact Info

Product

Resources

About