Deep Learning Assisted Online Multi-Step Demand Forecasting of Fused Magnesia Smelting Processes

This paper proposes a multi-step ahead power demand model for fused magnesia smelting processes (FMSP) which combines a linear model and an unknown nonlinear term to predict the electricity demand and its variation tendency for the next 5 steps. The linear model is identified by the multi-output fas...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 4th International Conference on Industrial Artificial Intelligence (IAI) s. 1 - 8
Hlavní autori: Li, Mingyu, Zhang, Jingwen, Chai, Tianyou
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 24.08.2022
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract This paper proposes a multi-step ahead power demand model for fused magnesia smelting processes (FMSP) which combines a linear model and an unknown nonlinear term to predict the electricity demand and its variation tendency for the next 5 steps. The linear model is identified by the multi-output fast recursive algorithm (MFRA) while the unknown nonlinear term is fitted with a long-short term memory (LSTM) model. The hyperparameters in the LSTM are estimated by the Bayesian optimization (BO) algorithm. Since the sampling period of the power is only 7 seconds, and we have to predict the next 5 steps electricity demand and its tendency within one sampling period, we therefore update parameters of the linear model by the MFRA while parameters of the dense layer of the LSTM are updated by the gradient descent algorithm within the online multi-step demand forecasting framework. The experimental results using the real-time data of a FMSP confirm the effectiveness of the proposed algorithm, achieving up to 52% error reduction in 5-step ahead demand forecasting when compared with other approaches.
AbstractList This paper proposes a multi-step ahead power demand model for fused magnesia smelting processes (FMSP) which combines a linear model and an unknown nonlinear term to predict the electricity demand and its variation tendency for the next 5 steps. The linear model is identified by the multi-output fast recursive algorithm (MFRA) while the unknown nonlinear term is fitted with a long-short term memory (LSTM) model. The hyperparameters in the LSTM are estimated by the Bayesian optimization (BO) algorithm. Since the sampling period of the power is only 7 seconds, and we have to predict the next 5 steps electricity demand and its tendency within one sampling period, we therefore update parameters of the linear model by the MFRA while parameters of the dense layer of the LSTM are updated by the gradient descent algorithm within the online multi-step demand forecasting framework. The experimental results using the real-time data of a FMSP confirm the effectiveness of the proposed algorithm, achieving up to 52% error reduction in 5-step ahead demand forecasting when compared with other approaches.
Author Chai, Tianyou
Li, Mingyu
Zhang, Jingwen
Author_xml – sequence: 1
  givenname: Mingyu
  surname: Li
  fullname: Li, Mingyu
  email: 2010718@stu.neu.edu.cn
  organization: Northeastern University,State Key Laboratory of Synthetical Automation for Process Industries,Sheyang,China
– sequence: 2
  givenname: Jingwen
  surname: Zhang
  fullname: Zhang, Jingwen
  email: 1610277@stu.neu.edu.cn
  organization: Northeastern University,State Key Laboratory of Synthetical Automation for Process Industries,Sheyang,China
– sequence: 3
  givenname: Tianyou
  surname: Chai
  fullname: Chai, Tianyou
  email: tychai@mail.neu.edu.cn
  organization: Northeastern University,State Key Laboratory of Synthetical Automation for Process Industries,Sheyang,China
BookMark eNotz99KwzAYBfAIeuGmTyBCXqA1f5qkuSyb1ULHhOn1_Jp-HYE2HU134ds73a7Oxflx4CzIbRgDEvLMWco5sy9VUSllcpYKJkRqrdHKmBuy4FqrTHHB5D35XiMeaY0wBR8OtIjRxxlbug29D0g3p372yW4-mzUOEFpajhM6iPOfHjtanuJZb-AQMHqguwH7_-pjGh3GiPGB3HXQR3y85pJ8la-fq_ek3r5Vq6JOPOf5nJiMOdVA3sqGW1CNE6oTOXJhO6c1QiZb1GAAnQEjLTcsB21zZxsmrWCNXJKny65HxP1x8gNMP_vrafkL6KlSPA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/IAI55780.2022.9976577
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1665451203
9781665451208
EndPage 8
ExternalDocumentID 9976577
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i118t-740c5ba8d3b19a5bc25f28e129fc66ea43de6a7aec7a7391708a698c9b03920b3
IEDL.DBID RIE
IngestDate Thu Jan 18 11:14:18 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-740c5ba8d3b19a5bc25f28e129fc66ea43de6a7aec7a7391708a698c9b03920b3
PageCount 8
ParticipantIDs ieee_primary_9976577
PublicationCentury 2000
PublicationDate 2022-Aug.-24
PublicationDateYYYYMMDD 2022-08-24
PublicationDate_xml – month: 08
  year: 2022
  text: 2022-Aug.-24
  day: 24
PublicationDecade 2020
PublicationTitle 2022 4th International Conference on Industrial Artificial Intelligence (IAI)
PublicationTitleAbbrev IAI
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8117477
Snippet This paper proposes a multi-step ahead power demand model for fused magnesia smelting processes (FMSP) which combines a linear model and an unknown nonlinear...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Bayesian optimization
Deep learning
Demand forecasting
Long-short term memory
Multi-output fast recursive algorithm
Online multi-step ahead demand forecasting
Power demand
Prediction algorithms
Predictive models
Real-time systems
Smelting
Title Deep Learning Assisted Online Multi-Step Demand Forecasting of Fused Magnesia Smelting Processes
URI https://ieeexplore.ieee.org/document/9976577
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5t8eBJpRXf5ODRbbO7eR7FWuzBUlCht5pMpqVgt6Xb-vtNtosiePEWkiGBmZAvk8w3Q8htCgH0UmaTXENwUCSmiTEoE_DgtZOAXLiq2IQajfRkYsYNcvfNhUHEKvgMu7FZ_eX7FeziU1nPBOwUSjVJUym552rVpJyUmd7wfijC_mPB6cuybi37q2hKhRmDo_-tdkw6P-Q7Ov6GlRPSwKJN3vuIa1onQ53ToNRoHk_3mUJpRaNNYsQW7ePSFp7GkptgyxjUTFczOtiVQfrZzsPJtrD0ZYkf1VDNE8CyQ94Gj68PT0ldHCFZBJ9gmyjOQDirfe5SY4WDTMwyjQG-ZyAlWp57lFZZBGVVHpwypq00Goxj4UrEXH5KWsWqwDNCM-W9Qsk4cMFzAOe08RLDDMw4weGctKN2put9_otprZiLv7svyWE0QHx3zfgVaW03O7wmB_C5XZSbm8poXyHRm5I
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEG0QTfSkBozf9uDRhe5ut90ejUogAiERE27YTgdCIgthwd9vu2wwJl68NW3TTWaavk533jxC7kNwoBcyHcQpuABFYBgohSIACzY1ApAnphCbkP1-OhqpQYU87LgwiFgkn2HDN4t_-XYBG_9U1lQOOxMp98i-V84q2VolLSdkqtl57CRuBzIX9kVRo5z9SzalQI3W8f--d0LqP_Q7OtgByympYFYjH8-IS1qWQ51SZ1bvIEu3tUJpQaQNfM4Wfca5ziz1opugc5_WTBcT2trkbnZPT93ZNtP0bY6fxVDJFMC8Tt5bL8OndlDKIwQzFxWsA8kZJEanNjah0omBKJlEKToAn4AQqHlsUWipEaSWsQvLWKqFSkEZ5i5FzMRnpJotMjwnNJLWShSMA094DGBMqqxAtwJTJuFwQWreOuPltgLGuDTM5d_dd-SwPex1x91O__WKHHln-FfYiF-T6nq1wRtyAF_rWb66LRz4DWnvnts
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2022+4th+International+Conference+on+Industrial+Artificial+Intelligence+%28IAI%29&rft.atitle=Deep+Learning+Assisted+Online+Multi-Step+Demand+Forecasting+of+Fused+Magnesia+Smelting+Processes&rft.au=Li%2C+Mingyu&rft.au=Zhang%2C+Jingwen&rft.au=Chai%2C+Tianyou&rft.date=2022-08-24&rft.pub=IEEE&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FIAI55780.2022.9976577&rft.externalDocID=9976577