Deep Bi-Directional LSTM Networks for Device Workload Forecasting

Dymitr Ruta, Ling Cen, Quang Hieu Vu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

Deep convolutional neural networks revolutionized the area of automated objects detection from images. Can the same be achieved in the domain of time series forecasting? Can one build a universal deep network that once trained on the past would be able to deliver accurate predictions reaching deep into the future for any even most diverse time series? This work is a first step in an attempt to address such a challenge in the context of a FEDCSIS'2020 Competition dedicated to network device workload prediction based on their historical time series data. We have developed and pre-trained a universal 3-layer bi-directional Long-Short-Term-Memory (LSTM) regression network that reported the most accurate hourly predictions of the weekly workload time series from the thousands of different network devices with diverse shape and seasonality profiles. We will also show how intuitive human-led post-processing of the raw LSTM predictions could easily destroy the generalization abilities of such prediction model.

Original languageBritish English
Title of host publicationProceedings of the 2020 Federated Conference on Computer Science and Information Systems, FedCSIS 2020
EditorsMaria Ganzha, Leszek Maciaszek, Leszek Maciaszek, Marcin Paprzycki
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages115-118
Number of pages4
ISBN (Electronic)9788395541674
DOIs
StatePublished - Sep 2020
Event15th Federated Conference on Computer Science and Information Systems, FedCSIS 2020 - Virtual, Sofia, Bulgaria
Duration: 6 Sep 20209 Sep 2020

Publication series

NameProceedings of the 2020 Federated Conference on Computer Science and Information Systems, FedCSIS 2020

Conference

Conference15th Federated Conference on Computer Science and Information Systems, FedCSIS 2020
Country/TerritoryBulgaria
CityVirtual, Sofia
Period6/09/209/09/20

Keywords

  • ensemble averaging
  • Long Short-Term Memory (LSTM)
  • time series
  • Workload prediction

Fingerprint

Dive into the research topics of 'Deep Bi-Directional LSTM Networks for Device Workload Forecasting'. Together they form a unique fingerprint.

Cite this