https://www.mdu.se/

mdu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A rule-based energy management strategy for a low-temperature solar/wind-driven heating system optimized by the machine learning-assisted grey wolf approach
KTH University, Stockholm, Sweden.
Mälardalen University, School of Business, Society and Engineering, Future Energy Center.
2023 (English)In: Energy Conversion and Management, ISSN 0196-8904, E-ISSN 1879-2227, Vol. 277, article id 116590Article in journal (Refereed) Published
Abstract [en]

This work presents an innovative, practical, and cost-effective solution for advancing state-of-the-art intelligent building energy systems and aiding the intended worldwide green transition with maximum renewable integration. The vanadium chloride cycle, electrolyzer unit, and Alkaline fuel cell are powered by the sun's and wind's energy to produce/store/use hydrogen. A rule-based control scheme is designed to provide a sophisticated interplay between the demand/supply sides, components, and local energy networks to reduce peak capacity, lower emissions, and save energy costs. TRNSYS is used to analyze and compare the techno-economic-environmental indicators of the conventional system and the suggested smart model for a multi-family building in Sweden. A grey wolf method is built in MATLAB with the help of machine learning to determine the optimum operating state with the maximum accuracy and the least amount of computational time. The results reveal that the suggested smart model considerably saves energy and money compared to the conventional system in Sweden while lowering CO2 emissions. According to the optimization results, the grey wolf optimizer and machine learning techniques enable greater total efficiency of 13 %, higher CO2 mitigation of 8 %, a larger cost saving of 38 %, and a reduced levelized energy cost of 41 $/MWh. The scatter distribution of important design parameters shows that altering the fuel cell current and electrode area considerably impacts the system's performance from all angles. The bidirectional connection of the proposed smart system with the heating and electrical networks through the rule-based controller demonstrates that it can supply the building's energy requirements for more than 300 days of the year. Eventually, the major contribution of the vanadium chloride cycle in the summer and the electrolyzer in the winter to the creation of hydrogen highlights the significance of renewable hybridization in reducing the dependence of buildings on energy networks.

Place, publisher, year, edition, pages
2023. Vol. 277, article id 116590
Keywords [en]
Fuel cell, Hydrogen storage, Low-temperature heating, Machine learning, Multi-objective optimization, Smart energy system, Solar energy
National Category
Energy Systems
Identifiers
URN: urn:nbn:se:mdh:diva-61457DOI: 10.1016/j.enconman.2022.116590ISI: 000919111700001Scopus ID: 2-s2.0-85145275738OAI: oai:DiVA.org:mdh-61457DiVA, id: diva2:1725615
Funder
Swedish Energy AgencyAvailable from: 2023-01-11 Created: 2023-01-11 Last updated: 2023-02-15Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Sadrizadeh, Sasan

Search in DiVA

By author/editor
Sadrizadeh, Sasan
By organisation
Future Energy Center
In the same journal
Energy Conversion and Management
Energy Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 66 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf