Forecasting Building Electric Consumption Patterns Through Statistical Methods

Serrano-Guerrero, Xavier; Siavichay, Luis Fernando; Clairand, Jean-Michel; Escrivá-Escrivá, Guillermo

doi:10.1007/978-3-030-32033-1_16

Cited by 5 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, the authors have proposed a specific method to obtain patterns and detect anomalies in the electricity demand. K-means [34,35] a,c Image processing technology [36] Classification and outlier detection b,c Canonical variate analysis [25] K-means and support vector machines [21] Outlier Detection b Statistics and hierarchical clustering [24] Symbolic aggregate approximation process [26] a,b C-means based on fuzzy clustering [20] a,c Support vector machines and k-means [27] LSTM neural networks and statistics [28] [12,13] a,e Support vector regression [14] d,e Simple linear regression, multiple linear regression, and ARIMA [37] b Data mining, unsupervised data clustering and bayesian network prediction [15] Energy Management a,b Hierarchical clustering [16] a Event-triggered-based distributed algorithm [38] a,e Formulation of a multiple knapsack problem and solve it through dynamic programming [39] b…”

Section: Related Workmentioning

confidence: 99%

A Time-Series Treatment Method to Obtain Electrical Consumption Patterns for Anomalies Detection Improvement in Electrical Consumption Profiles

et al. 2020

Self Cite

View full text Add to dashboard Cite

Electricity consumption patterns reveal energy demand behaviors and enable strategY implementation to increase efficiency using monitoring systems. However, incorrect patterns can be obtained when the time-series components of electricity demand are not considered. Hence, this research proposes a new method for handling time-series components that significantly improves the ability to obtain patterns and detect anomalies in electrical consumption profiles. Patterns are found using the proposed method and two widespread methods for handling the time-series components, in order to compare the results. Through this study, the conditions that electricity demand data must meet for making the time-series analysis useful are established. Finally, one year of real electricity consumption is analyzed for two different cases to evaluate the effect of time-series treatment in the detection of anomalies. The proposed method differentiates between periods of high or low energy demand, identifying contextual anomalies. The results indicate that it is possible to reduce time and effort involved in data analysis, and improve the reliability of monitoring systems, without adding complex procedures.

show abstract

Section: Related Workmentioning

confidence: 99%

A Time-Series Treatment Method to Obtain Electrical Consumption Patterns for Anomalies Detection Improvement in Electrical Consumption Profiles

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…e applications of artificial neural networks (ANN) for short-term load power prediction have evolved [1][2][3][4], and new proposals have been proposed over time, such as statistical methods [5][6][7], support vector machines [8][9][10], and decision trees [11,12]. ese traditional techniques could be utilized with heterogeneous and incomplete databases and straightforward interpretation for a simple dataset.…”

Section: Introductionmentioning

confidence: 99%

“…ese traditional techniques could be utilized with heterogeneous and incomplete databases and straightforward interpretation for a simple dataset. e statistical methods could be applied in simple applications but achieved a poor prediction due to the multiple seasonality of electricity load [6]. e support vector machine (SVM) could obtain the global solutions as conventional ANN, but it typically suffers the overfitting problems and quickly falls into local minima solution [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Three-Phase Load Prediction-Based Hybrid Convolution Neural Network Combined Bidirectional Long Short-Term Memory in Solar Power Plant

Lee

Thanh

Yeh

et al. 2022

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

e economic renewable energy generations have been rapidly developed because of the sharp reduction in the costs of solar panels. It is imperative to forecast the three-phase load power for more effective energy planning and optimization in a smart solar microgrid installed on a building in the Linyuan District, Taiwan. To alleviate this problem, this article proposes a convolution neural network bidirectional long short-term memory (CNN-Bi-LSTM) to accurately predict the short-term three-phase load power in building the energy management system in the smart solar microgrid with the collected data from advanced metering infrastructure (AMI), which have not been investigated before. e three-phase load-predicting methodology is developed using weather parameters and different collected data from AMI. e project evaluates the performance of the CNN-Bi-LSTM model by utilizing hyper-parameter optimization to attain the optimum parameters. e prediction models are trained based on hourly historical input features, selected based on the Pearson correlation coefficient. e performances' optimal structure CNN-Bi-LSTM are validated and compared with the bidirectional LSTM (Bi-LSTM), LSTM, the Gated Recurrent Unit (GRU), and the recurrent neural network (RNN) models. e obtained optimized structure of CNN-Bi-LSTM demonstrates the effectiveness of the proposed models in the short-term prediction of three-phase load power in a smart solar microgrid for building with a maximum enhancement of 68.36% and 8.81% average MSE, and 30.26% and 36.36% average MAE during the testing and validating operations.

show abstract

“…An innovative approach to forecasting energy consumption was applied in [39], where the combined Bootstrap aggregation methods (Bagging) were used. In turn, in [40] energy consumption projections for two real university buildings from Ecuador and Spain were built. Smoothing methods, simple and multiple regressions and ARIMA models were used.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Electricity Consumption in Poland Using Prediction Models and Neural Networks

et al. 2021

View full text Add to dashboard Cite

The challenges of the modern world require transformations in the energy market towards the possible reduction of consumption and greater use of renewable sources. The conducted research of consumers of this market confirms that the behaviour in the field of increased use of renewable energy is burdened with cognitive errors and motivational factors, which makes it difficult to conduct quantitative research. Electricity demand forecasting can be modelled using selected quantitative methods. In this way, not so much the behaviour, but the result of the consumer’s behaviour is predicted. The research presented in the article has been divided into two parts. The aim of the first one is to study the prospects of a greater share of renewable sources in obtaining energy in Poland, based on the attitudes and opinions of consumers on the retail energy market, legal regulations and the energy balance. The aim of the second part is to build forecasts of daily, weekly, monthly and quarterly electricity consumption in Poland, including the prediction of the RES share, using selected machine and deep learning methods. The analyses used the time series of daily electricity consumption in Poland from 2015–2021; the ENTSO-E data was obtained from the cire.pl website. Depending on the adopted forecast horizon, the forecasting method with the lowest MAPE error was exponential smoothing, SARIMA and NNETAR. An evolution of energy consumers’ attitudes towards pro-ecological and pro-social sensitivity and understanding of the importance of RES for the economy was also observed.

show abstract

Forecasting Building Electric Consumption Patterns Through Statistical Methods

Cited by 5 publications

References 21 publications

A Time-Series Treatment Method to Obtain Electrical Consumption Patterns for Anomalies Detection Improvement in Electrical Consumption Profiles

A Time-Series Treatment Method to Obtain Electrical Consumption Patterns for Anomalies Detection Improvement in Electrical Consumption Profiles

Three-Phase Load Prediction-Based Hybrid Convolution Neural Network Combined Bidirectional Long Short-Term Memory in Solar Power Plant

Analysis of Electricity Consumption in Poland Using Prediction Models and Neural Networks

Contact Info

Product

Resources

About