Publication: A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series
Loading...
Identifiers
Publication date
2020-10-02
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
MDPI
Impact
Export
Abstract
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.
Description
This article belongs to the Special Issue Forecasting in Electricity Markets with Big Data and Artificial Intelligence.
Keywords
Disaggregated time series, Load forecasting, Neural networks, Smart meters
Bibliographic citation
Alonso, A. M., Nogales, F. J. & Ruiz, C. (2020). A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series. Energies, 13(20), 5328.