English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Most electricity systems worldwide are deploying advanced meteringinfrastructures to collect relevant operational data. In particular, smartmeters allow tracking electricity load consumption at a very disaggregatedlevel and at high frequency rates. This data opens the possibility ofdeveloping new forecasting models with a potential positive impact inelectricity systems. We present a general methodology that is able to processand forecast a large number of smart meter time series. Instead of usingtraditional and univariate approaches, we develop a single but complexrecurrent neural-network model with long short-term memory that can captureindividual consumption patterns and also consumptions from differenthouseholds. The resulting model can accurately predict future loads(short-term) of individual consumers, even if these were not included in theoriginal training set. This entails a great potential for large scaleapplications as once the single network is trained, accurate individualforecast for new consumers can be obtained at almost no computational cost. Theproposed model is tested under a large set of numerical experiments by using areal-world dataset with thousands of disaggregated electricity consumption timeseries. Furthermore, we explore how geo-demographic segmentation of consumersmay impact the forecasting accuracy of the model.

A Single Scalable LSTM Model for Short-Term Forecasting of Disaggregated Electricity Loads