Genetic Algorithm Based Optimized Feature Engineering and Hybrid Machine Learning for Effective Energy Consumption Prediction

Byun, Yung-Cheol

doi:10.1109/access.2020.3034101

Cited by 38 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their results, based on a performance index that combines coefficient of determination (R 2 ), RMSE, and MAPE (Mean Absolute Percentage Error), indicate that the random forest performance was 14-25% and 5-5.5% better than RT and SVR, respectively [11]. In 2020, Khan et al proposed hybrid machine learning methods [12][13][14] to forecast the energy demand. They developed a hybrid algorithm based on three machine learning techniques, i.e., random forest, extreme gradient boosting, and categorical boosting for energy demand forecasting.…”

Section: Previous Workmentioning

confidence: 99%

Medium-Term Regional Electricity Load Forecasting through Machine Learning and Deep Learning

Shirzadi

Nizami

Khazen

et al. 2021

Designs

View full text Add to dashboard Cite

Due to severe climate change impact on electricity consumption, as well as new trends in smart grids (such as the use of renewable resources and the advent of prosumers and energy commons), medium-term and long-term electricity load forecasting has become a crucial need. Such forecasts are necessary to support the plans and decisions related to the capacity evaluation of centralized and decentralized power generation systems, demand response strategies, and controlling the operation. To address this problem, the main objective of this study is to develop and compare precise district level models for predicting the electrical load demand based on machine learning techniques including support vector machine (SVM) and Random Forest (RF), and deep learning methods such as non-linear auto-regressive exogenous (NARX) neural network and recurrent neural networks (Long Short-Term Memory—LSTM). A dataset including nine years of historical load demand for Bruce County, Ontario, Canada, fused with the climatic information (temperature and wind speed) are used to train the models after completing the preprocessing and cleaning stages. The results show that by employing deep learning, the model could predict the load demand more accurately than SVM and RF, with an R-Squared of about 0.93–0.96 and Mean Absolute Percentage Error (MAPE) of about 4–10%. The model can be used not only by the municipalities as well as utility companies and power distributors in the management and expansion of electricity grids; but also by the households to make decisions on the adoption of home- and district-scale renewable energy technologies.

show abstract

Section: Previous Workmentioning

confidence: 99%

Medium-Term Regional Electricity Load Forecasting through Machine Learning and Deep Learning

Shirzadi

Nizami

Khazen

et al. 2021

Designs

View full text Add to dashboard Cite

show abstract

“…On the other hand, considering the benefits and drawbacks of ML and DL algorithms, various studies were employed either a hybrid method or an ensemble method to execute more reliable and accurate forecasting outcomes [20][21][22][23]. The incorporation of an artificial neural network (ANN), a BPNN, a generalized regression neural network (GRNN), an Elman neural network, and a genetic algorithm optimized backpropagation neural network (GABPNN) was proposed for half-hourly electrical power prediction by Xiao et al [24].…”

Section: Related Workmentioning

confidence: 99%

Hybrid Ensemble Deep Learning-Based Approach for Time Series Energy Prediction

Phyo

Byun

2021

Symmetry

Self Cite

View full text Add to dashboard Cite

The energy manufacturers are required to produce an accurate amount of energy by meeting the energy requirements at the end-user side. Consequently, energy prediction becomes an essential role in the electric industrial zone. In this paper, we propose the hybrid ensemble deep learning model, which combines multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and hybrid CNN-LSTM to improve the forecasting performance. These DL architectures are more popular and better than other machine learning (ML) models for time series electrical load prediction. Therefore, hourly-based energy data are collected from Jeju Island, South Korea, and applied for forecasting. We considered external features associated with meteorological conditions affecting energy. Two-year training and one-year testing data are preprocessed and arranged to reform the times series, which are then trained in each DL model. The forecasting results of the proposed ensemble model are evaluated by using mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Error metrics are compared with DL stand-alone models such as MLP, CNN, LSTM, and CNN-LSTM. Our ensemble model provides better performance than other forecasting models, providing minimum MAPE at 0.75%, and was proven to be inherently symmetric for forecasting time-series energy and demand data, which is of utmost concern to the power system sector.

show abstract

“…In conclusion, the sensitivity analysis method can be used to screen the updating parameters from the numerous parameters of the MGDM, thereby providing a foundation for the subsequent model updating. To improve the calculation efficiency, the KRG surrogate model was combined with the genetic algorithm [27]- [29] to determine parameter values that minimize the error between the simulation and experimental results within the value range of the updating parameters to improve the accuracy of the MGDM.…”

Section: B Updating Parameter Screening Based On Sobol Sensitivity Anmentioning

confidence: 99%

An Improved Dynamic Model Updating Method for Multistage Gearbox Based on Surrogate Model and Sensitivity Analysis

Qin

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Model updating can improve the accuracy of the multistage gearbox dynamic model (MGDM). However, owing to the time-consuming calculations and numerous parameters of the MGDM, previous updating methods are not suitable for updating the MGDM. To solve the above problems, an improved dynamic model updating method that is suitable for updating the MGDM is proposed in this paper. Compared with previous methods, this updating method presents two improvements: (1) In the iterative calculation process, the surrogate model is used to replace the time-consuming MGDM, thereby solving the problem of low computational efficiency; (2) before the updating calculation, Sobol sensitivity analysis is performed to screen out updating parameters from numerous parameters. This study shows that the accuracy of the updated MGDM improved by 18.52% compared with the initial model, thereby enabling a more accurate prediction of the dynamic characteristics of the actual system. This proves the effectiveness of the improved updating method.INDEX TERMS Gear, gearbox, dynamic model, updating method, sensitivity analysis, surrogate model.

show abstract

Genetic Algorithm Based Optimized Feature Engineering and Hybrid Machine Learning for Effective Energy Consumption Prediction

Cited by 38 publications

References 40 publications

Medium-Term Regional Electricity Load Forecasting through Machine Learning and Deep Learning

Medium-Term Regional Electricity Load Forecasting through Machine Learning and Deep Learning

Hybrid Ensemble Deep Learning-Based Approach for Time Series Energy Prediction

An Improved Dynamic Model Updating Method for Multistage Gearbox Based on Surrogate Model and Sensitivity Analysis

Contact Info

Product

Resources

About