A Distributed Machine Learning Approach for the Secondary Voltage Control of an Islanded Micro-Grid
| aut.relation.conference | 2016 IEEE Innovative Smart Grid Technologies - Asia (ISGT-Asia) | en_NZ |
| aut.researcher | Lie, Tek | |
| dc.contributor.author | Al Karim, M | en_NZ |
| dc.contributor.author | Currie, J | en_NZ |
| dc.contributor.author | Lie, T | en_NZ |
| dc.date.accessioned | 2017-02-19T23:56:08Z | |
| dc.date.available | 2017-02-19T23:56:08Z | |
| dc.date.copyright | 2016-12-26 | en_NZ |
| dc.date.issued | 2016-12-26 | en_NZ |
| dc.description.abstract | Balancing the active and the reactive power in a stand-alone micro-grid is a critical task. A micro-grid without energy storage capability is even more vulnerable to stability issues. This paper investigates a distributed secondary control to maintain the rated voltage in a stand-alone micro-grid. Here multiple machine learning algorithms have been implemented to provide the secondary control where a primary control scheme is insufficient to maintain a stable voltage after a sudden change in the load. The performance of the secondary control is monitored by a centralized system and in most of the cases it does not interfere. Based on different contingencies the proposed method would suggest different machine learning algorithms which are previously trained with similar data. The contingencies are based on an imbalance either in the active or in the reactive power in the system. It is considered that the distributed generators such as the wind and solar plants as well as the residential loads have some degree of randomness. The secondary control is invoked only in the events when primary droop control is insufficient to address the stability issue and maintain a desired voltage in the system. | |
| dc.identifier.citation | 2016 IEEE Innovative Smart Grid Technologies - Asia (ISGT-Asia), Melbourne, VIC, 2016, pp. 611-616. doi: 10.1109/ISGT-Asia.2016.7796454 | |
| dc.identifier.doi | 10.1109/ISGT-Asia.2016.7796454 | en_NZ |
| dc.identifier.issn | 2378-8542 | en_NZ |
| dc.identifier.uri | https://hdl.handle.net/10292/10332 | |
| dc.publisher | IEEE | |
| dc.relation.uri | https://doi.org/10.1109/ISGT-Asia.2016.7796454 | |
| dc.rights | Copyright © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
| dc.rights.accessrights | OpenAccess | en_NZ |
| dc.subject | Solar energy; Neural network; Automatic generation; Control; Load forecasting; Distributed generation; Wind energy | |
| dc.title | A Distributed Machine Learning Approach for the Secondary Voltage Control of an Islanded Micro-Grid | en_NZ |
| dc.type | Conference Contribution | |
| pubs.elements-id | 219268 | |
| pubs.organisational-data | /AUT | |
| pubs.organisational-data | /AUT/Design & Creative Technologies | |
| pubs.organisational-data | /AUT/Design & Creative Technologies/Engineering, Computer & Mathematical Sciences |