Microgrid Energy Management System with Embedded Deep Learning Forecaster and Combined Optimizer

Vishnu Suresh; Przemyslaw Janik; Josep M. Guerrero; Zbigniew Leonowicz; Tomasz Sikorski

doi:10.1109/ACCESS.2020.3036131

Microgrid Energy Management System with Embedded Deep Learning Forecaster and Combined Optimizer

Vishnu Suresh^*, Przemyslaw Janik, Josep M. Guerrero, Zbigniew Leonowicz, Tomasz Sikorski

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › Research › peer-review

32 Citations (Scopus)

75 Downloads (Pure)

Abstract

This paper presents an energy management system for the microgrid present at Wroclaw University of Science and Technology. It has three components: a forecasting system, an optimizer and an optimized electrical vehicle charging station as a separate load for the system. The forecasting system is based on a deep learning model utilizing a Long Short-Term Memory (LSTM) - Autoencoder based architecture. The study provides a statistical analysis of its performance over several runs and addresses reliability and running time issues thereby building a case for its adoption. A MIDACO - MATPOWER combined optimization algorithm has been used as the optimization algorithm for energy management which intends to harness the speed of MATPOWER and the search capabilities of Mixed Integer Distributed Ant Colony Optimization (MIDACO) in finding an appropriate global minimum solution. The objective of the system is to minimize the import of power from the main grid resulting in improved self-sufficiency. Finally, an optimized electrical vehicle charging station model to maximize the renewable energy utilization within the facility is incorporated into the same.

Original language	English
Article number	9249013
Journal	IEEE Access
Volume	8
Pages (from-to)	202225-202239
Number of pages	15
ISSN	2169-3536
DOIs	https://doi.org/10.1109/ACCESS.2020.3036131
Publication status	Published - 2020

Bibliographical note

Funding Information:
This work was supported in part by the Chair of Electrical Engineering Fundamentals under Grant K38W05D02, and in part by the Wroclaw University of Technology, Wroclaw, Poland, and Erasmus + under Grant 2018-1-PL-01-KA103-048415. The work of Josep M. Guerrero was supported by the VILLUM FONDEN through the VILLUM Investigator, Center for Research on Microgrids (CROM), under Grant 25920.

Publisher Copyright:
© 2013 IEEE.

Keywords

deep learning
electrical vehicle charging stations
LSTM - autoencoders
meta-heuristic optimization
Microgrid energy management
MIDACO
solar PV output forecasting

Access to Document

10.1109/ACCESS.2020.3036131Licence: CC BY 4.0

Open Access articleFinal published version, 6.68 MBLicence: CC BY 4.0

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@article{a1121506245843d880b0ab2be1ac645b,

title = "Microgrid Energy Management System with Embedded Deep Learning Forecaster and Combined Optimizer",

abstract = "This paper presents an energy management system for the microgrid present at Wroclaw University of Science and Technology. It has three components: a forecasting system, an optimizer and an optimized electrical vehicle charging station as a separate load for the system. The forecasting system is based on a deep learning model utilizing a Long Short-Term Memory (LSTM) - Autoencoder based architecture. The study provides a statistical analysis of its performance over several runs and addresses reliability and running time issues thereby building a case for its adoption. A MIDACO - MATPOWER combined optimization algorithm has been used as the optimization algorithm for energy management which intends to harness the speed of MATPOWER and the search capabilities of Mixed Integer Distributed Ant Colony Optimization (MIDACO) in finding an appropriate global minimum solution. The objective of the system is to minimize the import of power from the main grid resulting in improved self-sufficiency. Finally, an optimized electrical vehicle charging station model to maximize the renewable energy utilization within the facility is incorporated into the same.",

keywords = "deep learning, electrical vehicle charging stations, LSTM - autoencoders, meta-heuristic optimization, Microgrid energy management, MIDACO, solar PV output forecasting",

author = "Vishnu Suresh and Przemyslaw Janik and Guerrero, {Josep M.} and Zbigniew Leonowicz and Tomasz Sikorski",

note = "Funding Information: This work was supported in part by the Chair of Electrical Engineering Fundamentals under Grant K38W05D02, and in part by the Wroclaw University of Technology, Wroclaw, Poland, and Erasmus + under Grant 2018-1-PL-01-KA103-048415. The work of Josep M. Guerrero was supported by the VILLUM FONDEN through the VILLUM Investigator, Center for Research on Microgrids (CROM), under Grant 25920. Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2020",

doi = "10.1109/ACCESS.2020.3036131",

language = "English",

volume = "8",

pages = "202225--202239",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "IEEE",

}

TY - JOUR

T1 - Microgrid Energy Management System with Embedded Deep Learning Forecaster and Combined Optimizer

AU - Suresh, Vishnu

AU - Janik, Przemyslaw

AU - Guerrero, Josep M.

AU - Leonowicz, Zbigniew

AU - Sikorski, Tomasz

N1 - Funding Information: This work was supported in part by the Chair of Electrical Engineering Fundamentals under Grant K38W05D02, and in part by the Wroclaw University of Technology, Wroclaw, Poland, and Erasmus + under Grant 2018-1-PL-01-KA103-048415. The work of Josep M. Guerrero was supported by the VILLUM FONDEN through the VILLUM Investigator, Center for Research on Microgrids (CROM), under Grant 25920. Publisher Copyright: © 2013 IEEE.

PY - 2020

Y1 - 2020

N2 - This paper presents an energy management system for the microgrid present at Wroclaw University of Science and Technology. It has three components: a forecasting system, an optimizer and an optimized electrical vehicle charging station as a separate load for the system. The forecasting system is based on a deep learning model utilizing a Long Short-Term Memory (LSTM) - Autoencoder based architecture. The study provides a statistical analysis of its performance over several runs and addresses reliability and running time issues thereby building a case for its adoption. A MIDACO - MATPOWER combined optimization algorithm has been used as the optimization algorithm for energy management which intends to harness the speed of MATPOWER and the search capabilities of Mixed Integer Distributed Ant Colony Optimization (MIDACO) in finding an appropriate global minimum solution. The objective of the system is to minimize the import of power from the main grid resulting in improved self-sufficiency. Finally, an optimized electrical vehicle charging station model to maximize the renewable energy utilization within the facility is incorporated into the same.

AB - This paper presents an energy management system for the microgrid present at Wroclaw University of Science and Technology. It has three components: a forecasting system, an optimizer and an optimized electrical vehicle charging station as a separate load for the system. The forecasting system is based on a deep learning model utilizing a Long Short-Term Memory (LSTM) - Autoencoder based architecture. The study provides a statistical analysis of its performance over several runs and addresses reliability and running time issues thereby building a case for its adoption. A MIDACO - MATPOWER combined optimization algorithm has been used as the optimization algorithm for energy management which intends to harness the speed of MATPOWER and the search capabilities of Mixed Integer Distributed Ant Colony Optimization (MIDACO) in finding an appropriate global minimum solution. The objective of the system is to minimize the import of power from the main grid resulting in improved self-sufficiency. Finally, an optimized electrical vehicle charging station model to maximize the renewable energy utilization within the facility is incorporated into the same.

KW - deep learning

KW - electrical vehicle charging stations

KW - LSTM - autoencoders

KW - meta-heuristic optimization

KW - Microgrid energy management

KW - MIDACO

KW - solar PV output forecasting

UR - http://www.scopus.com/inward/record.url?scp=85096235025&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2020.3036131

DO - 10.1109/ACCESS.2020.3036131

M3 - Journal article

AN - SCOPUS:85096235025

SN - 2169-3536

VL - 8

SP - 202225

EP - 202239

JO - IEEE Access

JF - IEEE Access

M1 - 9249013

ER -

Microgrid Energy Management System with Embedded Deep Learning Forecaster and Combined Optimizer

Abstract

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this