A Comparative Study of Predictive Approaches for Load Forecasting in Smart Buildings

Hadri, Soubhi; NaitMalek, Y.; Najib, Mehdi; Bakhouya, Mohamed; Fakhri, Yadolah; Elaroussi, Mohammed

doi:10.1016/j.procs.2019.09.458

Cited by 40 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The random forest (RF) ensemble technique combines independent learners to improve the overall model forecasting ability. The research presented in Reference [30] took advantage of this principle to forecast the day-ahead hourly consumption in office buildings. They used many ensemble algorithms, with RF being one of them, including environmental variables such as temperature and humidity and lagged load records to improve the results.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Due to its recent development, XGB is not a matured STLF method [16]. Nevertheless, researchers are starting to use it, showing outstanding performances against traditional methods [29,30].…”

Section: Modelingmentioning

confidence: 99%

“…Load weekly lags, load weekly moving average (LMA), and weekly moving standard deviation features were newly calculated features that helped capture the most recent load changes [30], keeping the hourly granularity. These were calculated from the immediately preceding week until the fourth week, adding 12 more features to the current dataset.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Short-Term Electricity Load Forecasting with Machine Learning

Madrid

António

2021

Information

View full text Add to dashboard Cite

An accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydrothermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This research proposes a set of machine learning (ML) models to improve the accuracy of 168 h forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Short-Term Electricity Load Forecasting with Machine Learning

Madrid

António

2021

Information

View full text Add to dashboard Cite

show abstract

“…A comparative study of load forecasting approaches using three different methods for occupancy prediction and context-driven control of a smart building's appliances was reported by S. Hadri et.al. (2019) [4]. The proposed methods were ARIMA and SARIMA, which were based on statistical method, while XGBoost and Random Forest (RF) are based on machine learning method and LSTM is based on deep learning method.…”

Section: Hung Nguyen Et Al (2017)mentioning

confidence: 99%

A Survey on Electric Power Consumption Prediction Techniques

Barua¹,

Goswami²

2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

“…According to [11] doing traffic flow forecasting for one day using the Gradient Boosting Decision Tree (GBDT) method is very effective with a MAPE error rate of 0.097%. XGBoost also produces the best forecast and fast execution times than several other methods such as ARIMA, SARIMA, and Random Forest in load forecasting [12].…”

Section: Introductionmentioning

confidence: 96%

Estimation of Gourami Supplies Using Gradient Boosting Decision Tree Method of XGBoost

Sukarsa¹,

Pinata²,

Rusjayanthi³

et al. 2021

TEM Journal

View full text Add to dashboard Cite

The need for food supplies are very crucial in a food business, therefore it is necessary to estimate the right supplies to maximize profit. One of the methods to determine these is by looking for patterns and forecasting transaction data. The purpose of this research is to estimate the gourami supplies using transaction data to forecast using the gradient boosting decision tree method from XGBoost. The transaction data used comes from Restaurant X with a time period from 2016 to 2019. A measurement error rate of the model is achieved by using MAE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error). This study tried five XGBoost models with different features such as lag, rolling window, mean encoding, and mix. The results of this study indicate that the mixed feature model produces an accuracy of 97.54% with an MAE of 0.63 and a MAPE of 2.64%.

show abstract

A Comparative Study of Predictive Approaches for Load Forecasting in Smart Buildings

Cited by 40 publications

References 22 publications

Short-Term Electricity Load Forecasting with Machine Learning

Short-Term Electricity Load Forecasting with Machine Learning

A Survey on Electric Power Consumption Prediction Techniques

Estimation of Gourami Supplies Using Gradient Boosting Decision Tree Method of XGBoost

Contact Info

Product

Resources

About