Energy Consumption Load Forecasting Using a Level-Based Random Forest Classifier

Chen, Yu-Tung; Piedad, Eduardo Jr; Kuo, Cheng‐Chien

doi:10.3390/sym11080956

Cited by 19 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed approach consists of converting the dataset values into levels during the pre-processing phase, instead of the post-processing phase, allowing the direct prediction of the desired levels using simpler classifier models without undergoing regression. Using a 12-month dataset of a large hypermarket, consisting in hourly energy consumption and temperature, as well, as 10-time cross-validation, it was concluded that the proposed approach performs better for all tests done, which were of 3, 5, and 7 levels, then the conventional way, however, the performance of the conventional classifier was also concluded to be able to approach the proposed method in terms of classification accuracy at the expense of computation time (Chen et al, 2019).…”

Section: Related Workmentioning

confidence: 95%

“…Chen, Piedad Jr., and Kuo, in 2019, also used a Random Forest for energy consumption load forecasting (Chen et al, 2019). In this approach, the authors propose the use of a level-based methodology, contrary to the conventional value-based methodology approach, that works by training the model with the pre-processed dataset values and then converting the results into consumer-preferred levels (e.g., low, average, high).…”

Section: Related Workmentioning

confidence: 99%

“…One drawback associated with Decision Tree Classifiers is their high variance, due to the significant change a tree can suffer from a small variance in the training data, therefore, the Random Forest methodology was invented, so that tree classification could be more stable (Azar et al, 2014). The use of this technique for energy consumption reduction is also not new, as seen in (Ahmad et al, 2017), where it is used for the prediction of a hotel's HVAC energy consumption, and (Chen et al, 2019), where it is used for energy load consumption forecasting of a large hypermarket.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Climatization and luminosity optimization of buildings using genetic algorithm, random forest, and regression models

et al. 2021

View full text Add to dashboard Cite

With the rise in popularity of artificial intelligence, coupled with the growing concern over the environment, there has been a surge in the use of intelligent energy management systems. Additionally, as more buildings transition into the smart grid and, consequently, more energy and environmental data is gathered, there has been a significant increase in the number of data-driven approaches for building management systems. This paper proposes a methodology that aims to optimize the climatization and luminosity inside a building, using a genetic algorithm, a random forest, and two polynomial models. The proposed methodology enables the real-time management of the building taking into account the user needs and preferences. Air conditioner units and light systems are optimized to minimize energy costs, while also improving the air quality and considering the users’ temperature and luminosity preferences. This paper shows the results achieved, by the proposed solution, in an office building case study. The promising results demonstrate the possibility of minimizing energy costs while maximizing the users’ comfort.

show abstract

Section: Related Workmentioning

confidence: 95%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Climatization and luminosity optimization of buildings using genetic algorithm, random forest, and regression models

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For example, in [8], [31]- [34] the authors used datasets of eighteen months to two years duration for developing forecasting models. Data of one year was used in [6], [35]- [37] while three years data was used in [38]. In this study, a time series data of hourly electricity consumption of Muzaffarabad city in kilowatt-hour (KWh), across the time period from 1 st January 2014 to 31 st December 2015 (two years) is used.…”

Section: Datasetsmentioning

confidence: 99%

Machine Learning Based Cost Effective Electricity Load Forecasting Model Using Correlated Meteorological Parameters

et al. 2020

View full text Add to dashboard Cite

Electricity, a fundamental commodity, must be generated as per required utilization which cannot be stored at large scales. The production cost heavily depends upon the source such as hydroelectric power plants, petroleum products, nuclear and wind energy. Besides overproduction and underproduction, electricity demand is driven by metrological parameters, economic and industrial activities. Therefore, the region specific accurate electric load forecasting can help to effectively manage, plan, and schedule appropriate low cost electricity generation units to decrease per unit cost and provision of on time energy for maximum financial benefits. Machine learning (ML) offers different supervised learning algorithms including multiple linear regression, support vector regressors with different kernels, k-nearest neighbors, Random Forest and AdaBoost to forecast the time series data, but the performance of these algorithms is data dependent. It is vitally important to consider correlated metrological parameters of the specific region for accurate prediction of electricity load demand using ML based forecasting models to minimize the price per unit. In this study, an algorithm is proposed to select least cost electric load forecasting model (lcELFM) using correlated meteorological parameters. We developed least cost forecasting models by minimizing root mean squared error, mean absolute error, and mean absolute percentage error. For simulations, the recorded electricity demand data is taken from a substation of water and power development authority Muzaffarabad city from 1 st January 2014 to 31 st December 2015. The meteorological time series data are obtained from the substation of Pakistan meteorological department for the same period and same region. Empirical results demonstrate the robustness of the proposed algorithm to select lcELFM. Moreover, SVR (Radial) based electric load forecasting model proves to be the robust model when built using correlated features (temperature and dew point) for the said region and in turn can save up to PKR 0.313 million daily.INDEX TERMS Electricity load demand, electricity load forecasting, least cost forecasting model, machine learning, meteorological parameters.

show abstract

“…Chen et al reported "Energy Consumption Load Forecasting Using a Level-Based Random Forest Classifier" [19]. In this study, a conventional method of level prediction with a pattern recognition approach was performed by first predicting the actual numerical values using typical pattern-based regression models, and then classifying them into pattern levels (e.g., low, average, and high).…”

Section: Lan Et Al Reported "Symmetric Modeling Of Communication Effectiveness and Satisfactionmentioning

confidence: 99%

Selected Papers from IIKII 2019 Conferences in Symmetry

Meen

Tijus

2020

Symmetry

View full text Add to dashboard Cite

The International Institute of Knowledge Innovation and Invention (IIKII) is an institute that promotes the exchange of innovations and inventions, and establishes a communication platform for international innovations and researches. In 2019, IIKII cooperated with the Institute of Electrical and Electronics Engineers (IEEE) Tainan Section Sensors Council to hold IEEE conferences such as IEEE ICIASE 2019, IEEE ECBIOS 2019, IEEE ICKII 2019, ICUSA-GAME 2019, and IEEE ECICE 2019. This Special Issue entitled “Selected Papers from IIKII 2019 conferences” aims to select excellent papers from IIKII 2019 conferences, including symmetry in physics, chemistry, biology, mathematics, and computer science, etc. It selected 21 excellent papers from 750 papers presented in IIKII 2019 conferences on the topic of symmetry. The main goals of this Special Issue are to encourage scientists to publish their experimental and theoretical results in as much detail as possible, and to discover new scientific knowledge relevant to the topic of symmetry.

show abstract

Energy Consumption Load Forecasting Using a Level-Based Random Forest Classifier

Cited by 19 publications

References 23 publications

Climatization and luminosity optimization of buildings using genetic algorithm, random forest, and regression models

Climatization and luminosity optimization of buildings using genetic algorithm, random forest, and regression models

Machine Learning Based Cost Effective Electricity Load Forecasting Model Using Correlated Meteorological Parameters

Selected Papers from IIKII 2019 Conferences in Symmetry

Contact Info

Product

Resources

About