Next Article in Journal
Mechanical Harvesting of Camelina: Work Productivity, Costs and Seed Loss Evaluation
Previous Article in Journal
Predictive Trajectory Control with Online MTPA Calculation and Minimization of the Inner Torque Ripple for Permanent-Magnet Synchronous Machines
Previous Article in Special Issue
Short-Term Load Forecasting for Spanish Insular Electric Systems
Open AccessArticle

A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series

1
Department of Statistics, Universidad Carlos III de Madrid, 126-28903 Getafe, Spain
2
Instituto Flores de Lemus, Calle Madrid 126, 28903 Getafe, Spain
3
UC3M-Santander Big Data Institute (IBiDat), Avda. de la Universidad 30, 28911 Leganés, Spain
*
Author to whom correspondence should be addressed.
Energies 2020, 13(20), 5328; https://doi.org/10.3390/en13205328
Received: 10 July 2020 / Revised: 30 September 2020 / Accepted: 1 October 2020 / Published: 13 October 2020
Most electricity systems worldwide are deploying advanced metering infrastructures to collect relevant operational data. In particular, smart meters allow tracking electricity load consumption at a very disaggregated level and at high frequency rates. This data opens the possibility of developing new forecasting models with a potential positive impact on electricity systems. We present a general methodology that can process and forecast many smart-meter time series. Instead of using traditional and univariate approaches, we develop a single but complex recurrent neural-network model with long short-term memory that can capture individual consumption patterns and consumptions from different households. The resulting model can accurately predict future loads (short-term) of individual consumers, even if these were not included in the original training set. This entails a great potential for large-scale applications as once the single network is trained, accurate individual forecast for new consumers can be obtained at almost no computational cost. The proposed model is tested under a large set of numerical experiments by using a real-world dataset with thousands of disaggregated electricity consumption time series. Furthermore, we explore how geo-demographic segmentation of consumers may impact the forecasting accuracy of the model. View Full-Text
Keywords: load forecasting; disaggregated time series; neural networks; smart meters load forecasting; disaggregated time series; neural networks; smart meters
Show Figures

Figure 1

MDPI and ACS Style

Alonso, A.M.; Nogales, F.J.; Ruiz, C. A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series. Energies 2020, 13, 5328. https://doi.org/10.3390/en13205328

AMA Style

Alonso AM, Nogales FJ, Ruiz C. A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series. Energies. 2020; 13(20):5328. https://doi.org/10.3390/en13205328

Chicago/Turabian Style

Alonso, Andrés M.; Nogales, Francisco J.; Ruiz, Carlos. 2020. "A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series" Energies 13, no. 20: 5328. https://doi.org/10.3390/en13205328

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop