Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks

Serrano-Guerrero, Xavier; Prieto-Galarza, Ricardo; Huilcatanda, Esteban; Cabrera-Zeas, Juan; Escrivá-Escrivá, Guillermo

doi:10.1109/ropec.2017.8261630

Cited by 9 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Over time, scholars have developed new proposals for forecasting electricity demand [12][13][14][15]. Actually, artificial intelligence (AI) techniques are preferred over others.…”

Section: Related Workmentioning

confidence: 99%

“…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%

See 1 more Smart Citation

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

“…Over time, scholars have developed new proposals for forecasting electricity demand [12][13][14][15]. Actually, artificial intelligence (AI) techniques are preferred over others.…”

Section: Related Workmentioning

confidence: 99%

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

“…The typical profiles of each cluster represent the usual demand of the installation, that is, a consumption pattern. Consumption patterns are useful in several areas, such as forecasting and predicting demand [25], energy management, efficiency policies implementation and energy intelligence, improving the supply of tariffs, etc.…”

Section: Obtaining Patternsmentioning

confidence: 99%

Characterization and Classification of Daily Electricity Consumption Profiles: Shape Factors and k-Means Clustering Technique

et al. 2018

View full text Add to dashboard Cite

This paper exposes a method to classify the electric consumption profiles of different types of consumers, based on patterns given. The direct characteristics method is used in this paper, this method is also known as shape factors deduction (SFs) to easily define consumption profiles by using the load patterns resulting from measurements in the time domain, considering weekdays and time ranges. After the characterization of load profiles, k-means clustering technique is applied to SFs. The SFs are segmented in such a way that, in each group similar SFs are gathered. The characterization and classification of electric profiles has important applications, such as the application of specific tariffs according the consumer type, determination of optimal location of generation resources in electrical distribution systems, detection of anomalies in transmission and distribution of electricity or classify geographical areas according to electricity consumption and perform an optimum balance of feeders in electrical substations.

show abstract

“…A lo largo del tiempo los investigadores han desarrollado nuevas propuestas para la predicción de la demanda de electricidad [13], [81]- [83], siendo las técnicas de inteligencia artificial las preferidas actualmente. Sin embargo, su aplicación acarrea ciertas dificultades, como por ejemplo las debilidades del tipo a, b, d y e identificadas previamente.…”

Section: Influencia Del Tratamiento De La Demanda De Electricidad Comunclassified

“…La revisión del estado del arte acerca de la predicción del consumo de electricidad realizada en el Capítulo 2, así como la experiencia adquirida por el propio autor en [108] indica que la demanda de electricidad puede asociarse a diferentes variables, tales como: la temperatura, precipitación, hora del día, mes, año, laboralidad, etc. Sin embargo, su utilización en sistemas de monitorización y vigilancia puede resultar poco práctica debido a su complejidad, elevado gasto computacional y el requerimiento de predicciones de las otras variables consideradas, lo cual también eleva la incertidumbre.…”

Section: Aplicación De La Metodología Saicc En La Predicción De La Deunclassified

Caracterización de la demanda de energía mediante patrones estocásticos en las Redes Eléctricas Inteligentes

Guerrero¹,

Xavier²

View full text Add to dashboard Cite

The energy demand is increasing considerably every year worldwide. Moreover, the electrification of different sectors has caused the growth of electricity demand at an even higher rate. Thus, the electricity grids have technologically evolved in several aspects, one of them is the availability of demand data at different points and levels of the grid, such as in transmission and distribution systems, and large and small consumers. The data provided by the new smart grids are essential baseline information for the management and planning of electricity systems.

show abstract

Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks

Cited by 9 publications

References 7 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

Characterization and Classification of Daily Electricity Consumption Profiles: Shape Factors and k-Means Clustering Technique

Caracterización de la demanda de energía mediante patrones estocásticos en las Redes Eléctricas Inteligentes

Contact Info

Product

Resources

About