Details
Original language | English |
---|---|
Title of host publication | Highlights in Practical Applications of Agents, Multi-Agent Systems, and Social Good. The PAAMS Collection |
Subtitle of host publication | International Workshops of PAAMS 2021, Salamanca, Spain, October 6–9, 2021, Proceedings |
Editors | Fernando De La Prieta, Alia El Bolock, Dalila Durães, João Carneiro, Fernando Lopes, Vicente Julian |
Place of Publication | Cham |
Pages | 191-202 |
Number of pages | 12 |
ISBN (electronic) | 978-3-030-85710-3 |
Publication status | Published - 27 Sept 2021 |
Event | 19th International Conference on Practical Applications of Agents and Multi-Agent Systems - Duration: 6 Oct 2021 → 8 Oct 2021 https://www.paams.net/ |
Publication series
Name | Communications in Computer and Information Science |
---|---|
Volume | 1472 CCIS |
ISSN (Print) | 1865-0929 |
ISSN (electronic) | 1865-0937 |
Abstract
In future energy systems, decentralized control will require delegation of liabilities to small energy resources. Distributed energy scheduling constitutes a complex multi-level optimization task regarding the underlying high-dimensional, multi-modal and nonlinear problem structure. The multi-level issue as well as the requirement for model independent algorithm design are substantially supported by appropriate machine learning flexibility models. Generating training sets by digital twins works well for single energy units. Combining training sets from individually modeled energy units, on the other hand, results in folded distributions with unfavorable properties for training. Nevertheless, this happens to be a quite frequent use case, e.g. when an ensemble of distributed energy resources wants to harness the joint flexibility for some control task. A fully decentralized agent-based algorithm is proposed that samples from distributed twins maximizing coverage of flexibility and simultaneously minimizing the discrepancy of the sample by using Ripley’s K measure. Applicability and effectiveness are demonstrated by several simulations using established models for energy unit simulation.
Keywords
- Discrepancy, MAS, Phase space sampling, Scheduling
ASJC Scopus subject areas
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Highlights in Practical Applications of Agents, Multi-Agent Systems, and Social Good. The PAAMS Collection: International Workshops of PAAMS 2021, Salamanca, Spain, October 6–9, 2021, Proceedings. ed. / Fernando De La Prieta; Alia El Bolock; Dalila Durães; João Carneiro; Fernando Lopes; Vicente Julian. Cham, 2021. p. 191-202 (Communications in Computer and Information Science; Vol. 1472 CCIS).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Agent-Based Phase Space Sampling of Ensembles using Ripley’s K for Homogeneity
AU - Bremer, Jörg
AU - Gerster, Johannes
AU - Brückner, Birk
AU - Sarstedt, Marcel
AU - Lehnhoff, Sebastian
N1 - Funding Information: This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) ? 359921210.
PY - 2021/9/27
Y1 - 2021/9/27
N2 - In future energy systems, decentralized control will require delegation of liabilities to small energy resources. Distributed energy scheduling constitutes a complex multi-level optimization task regarding the underlying high-dimensional, multi-modal and nonlinear problem structure. The multi-level issue as well as the requirement for model independent algorithm design are substantially supported by appropriate machine learning flexibility models. Generating training sets by digital twins works well for single energy units. Combining training sets from individually modeled energy units, on the other hand, results in folded distributions with unfavorable properties for training. Nevertheless, this happens to be a quite frequent use case, e.g. when an ensemble of distributed energy resources wants to harness the joint flexibility for some control task. A fully decentralized agent-based algorithm is proposed that samples from distributed twins maximizing coverage of flexibility and simultaneously minimizing the discrepancy of the sample by using Ripley’s K measure. Applicability and effectiveness are demonstrated by several simulations using established models for energy unit simulation.
AB - In future energy systems, decentralized control will require delegation of liabilities to small energy resources. Distributed energy scheduling constitutes a complex multi-level optimization task regarding the underlying high-dimensional, multi-modal and nonlinear problem structure. The multi-level issue as well as the requirement for model independent algorithm design are substantially supported by appropriate machine learning flexibility models. Generating training sets by digital twins works well for single energy units. Combining training sets from individually modeled energy units, on the other hand, results in folded distributions with unfavorable properties for training. Nevertheless, this happens to be a quite frequent use case, e.g. when an ensemble of distributed energy resources wants to harness the joint flexibility for some control task. A fully decentralized agent-based algorithm is proposed that samples from distributed twins maximizing coverage of flexibility and simultaneously minimizing the discrepancy of the sample by using Ripley’s K measure. Applicability and effectiveness are demonstrated by several simulations using established models for energy unit simulation.
KW - Discrepancy
KW - MAS
KW - Phase space sampling
KW - Scheduling
UR - http://www.scopus.com/inward/record.url?scp=85116476286&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-85710-3_16
DO - 10.1007/978-3-030-85710-3_16
M3 - Conference contribution
SN - 978-3-030-85709-7
T3 - Communications in Computer and Information Science
SP - 191
EP - 202
BT - Highlights in Practical Applications of Agents, Multi-Agent Systems, and Social Good. The PAAMS Collection
A2 - De La Prieta, Fernando
A2 - El Bolock, Alia
A2 - Durães, Dalila
A2 - Carneiro, João
A2 - Lopes, Fernando
A2 - Julian, Vicente
CY - Cham
T2 - 19th International Conference on Practical Applications of Agents and Multi-Agent Systems
Y2 - 6 October 2021 through 8 October 2021
ER -