The Comparison of Machine-Learning Methods XGBoost and LightGBM to Predict Energy Development

Nemeth, Martin; Borkin, Dmitrii; Michalconok, German

doi:10.1007/978-3-030-31362-3_21

Cited by 12 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LightGBM [18] also belongs to the gradient tree boosting models, in which a decision tree is split in leaf-wise with the best fit, thus reducing the loss with better accuracy. Similarly, XGBoost and LightGBM models have been used to predict the thermal power energy development [19] and later showed less Mean Absolute Percentage Error (MAPE%) on their dataset.…”

Section: Related Workmentioning

confidence: 99%

A Long Short-Term Memory (LSTM) Network for Hourly Estimation of PM2.5 Concentration in Two Cities of South Korea

et al. 2020

View full text Add to dashboard Cite

Air pollution not only damages the environment but also leads to various illnesses such as respiratory tract and cardiovascular diseases. Nowadays, estimating air pollutants concentration is becoming very important so that people can prepare themselves for the hazardous impact of air pollution beforehand. Various deterministic models have been used to forecast air pollution. In this study, along with various pollutants and meteorological parameters, we also use the concentration of the pollutants predicted by the community multiscale air quality (CMAQ) model which are strongly related to PM 2.5 concentration. After combining these parameters, we implement various machine learning models to predict the hourly forecast of PM 2.5 concentration in two big cities of South Korea and compare their results. It has been shown that Long Short Term Memory network outperforms other well-known gradient tree boosting models, recurrent, and convolutional neural networks.

show abstract

Section: Related Workmentioning

confidence: 99%

A Long Short-Term Memory (LSTM) Network for Hourly Estimation of PM2.5 Concentration in Two Cities of South Korea

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This combination leads to nonlinearity. It is confirmed that neural networks have ability to solve nonlinearity, and their implementation is successfully proven in many cases and described in many publications [5][6][7].…”

Section: Introductionmentioning

confidence: 72%

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

et al. 2021

View full text Add to dashboard Cite

Short-Term Load Prediction (STLP) is an important part of energy planning. STLP is based on the analysis of historical data such as outdoor temperature, heat load, heat consumer configuration, and the seasons. This research aims to forecast heat consumption during the winter heating season. By preprocessing and analyzing the data, we can determine the patterns in the data. The results of the data analysis make it possible to form learning algorithms for an artificial neural network (ANN). The biggest disadvantage of an ANN is the lack of precise guidelines for architectural design. Another disadvantage is the presence of false information in the analyzed training data. False information is the result of errors in measuring, collecting, and transferring data. Usually, trial error techniques are used to determine the number of hidden nodes. To compare prediction accuracy, several models have been proposed, including a conventional ANN and a wavelet ANN. In this research, the influence of different learning algorithms was also examined. The main differences were the training time and number of epochs. To improve the quality of the raw data and remove false information, the research uses the technology of normalizing raw data. The basis of normalization was the technology of the Z-score of the data and determination of the energy‒entropy ratio. The purpose of this research was to compare the accuracy of various data processing and neural network training algorithms suitable for use in data-driven (black box) modeling. For this research, we used a software application created in the MATLAB environment. The app uses wavelet transforms to compare different heat demand prediction methods. The use of several wavelet transforms for various wavelet functions in the research allowed us to determine the best algorithm and method for predicting heat production. The results of the research show the need to normalize the raw data using wavelet transforms. The sequence of steps involves following milestones: normalization of initial data, wavelet analysis employing quantitative criteria (energy, entropy, and energy‒entropy ratio), optimization of ANN training with information energy–entropy ratio, ANN training with different training algorithms, and evaluation of obtained outputs using statistical methods. The developed application can serve as a control tool for dispatchers during planning.

show abstract

“…Besides, RF model might underestimated/overestimated the extremely values of ambient benzene (Xue et al, 2019), which could be neutralized by the XGBoost algorithm through the boosting method (Li et al, 2020). For XGBoost algorithm, excessive leaf nodes often showed low splitting gain, while the LightGBM model could make up this defect (Nemeth et al, 2019). Overall, the combination of these decision tree models could overcome these weaknesses of these individual models and enhance the robustness of the final model.…”

Section: The Model Fitting and Validationmentioning

confidence: 99%

Global impact of COVID-19 lockdown on surface concentration and health risk of atmospheric benzene

Ling

Cui²,

Li³

2023

Preprint

View full text Add to dashboard Cite

Abstract. To curb the spread of COVID-19 pandemic, many countries around the world imposed an unprecedented lockdown producing reductions in pollutant emissions. Unfortunately, the lockdown-driven global ambient benzene changes still remained unknown. The ensemble machine-learning model coupled with the chemical transport models (CTMs) was applied to estimate global high-resolution ambient benzene levels. Afterwards, the XGBoost algorithm was employed to decouple the contributions of meteorology and emission reduction to ambient benzene. The change ratio (Pdew) of deweathered benzene concentration from pre-lockdown to lockdown period was in the order of India (−23.6 %) > Europe (−21.9 %) > United States (−16.2 %) > China (−15.6 %). The detrended change (P*) of deweathered benzene level (change ratio in 2020 – change ratio in 2019) followed the order of India (P* = −16.2 %) > Europe (P* = −13.9 %) > China (P* = −13.3 %) > United States (P* = −6.00 %). Substantial decreases of atmospheric benzene levels saved sufficient health benefits. The global average lifetime carcinogenic risks (LCR) and hazard index (HI) decreased from 4.89 × 10−7 and 5.90 × 10−3 and 4.51 × 10−7 and 5.40 × 10−3, respectively.

show abstract

The Comparison of Machine-Learning Methods XGBoost and LightGBM to Predict Energy Development

Cited by 12 publications

References 8 publications

A Long Short-Term Memory (LSTM) Network for Hourly Estimation of PM2.5 Concentration in Two Cities of South Korea

A Long Short-Term Memory (LSTM) Network for Hourly Estimation of PM2.5 Concentration in Two Cities of South Korea

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

Global impact of COVID-19 lockdown on surface concentration and health risk of atmospheric benzene

Contact Info

Product

Resources

About