Connection topology optimization in photovoltaic arrays using neural networks

Vivek Sivaraman Narayanaswamy, Raja Ayyanar, Andreas Spanias, Cihan Tepedelenlioglu, Devarajan Srinivasan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A cyber-physical system (CPS) approach for optimizing the output power of photovoltaic (PV) energy systems is proposed. In particular, a novel connection topology reconfiguration strategy for PV arrays to maximize power output under partial shading conditions using neural networks is put forth. Depending upon an irradiance/shading profile of the panels, topologies, namely series parallel (SP), total cross tied (TCT) or bridge link (BL) produce different maximum power points (MPP). The connection topology of the PV array that provides the maximum power output is chosen using a multi-layer perceptron. The simulation results show that empirically an output power increase of 12% can be achieved through reconfiguration. The method proposed can be implemented in any CPS PV system with switching capabilities and is simple to implement.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages167-172
Number of pages6
ISBN (Electronic)9781538685006
DOIs
StatePublished - May 1 2019
Event2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019 - Taipei, Taiwan, Province of China
Duration: May 6 2019May 9 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019

Conference

Conference2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019
CountryTaiwan, Province of China
CityTaipei
Period5/6/195/9/19

Fingerprint

Shape optimization
Topology
Neural networks
Multilayer neural networks
Cyber Physical System
Reconfiguration

Keywords

  • CPS
  • IoT energy systems
  • machine learning
  • neural networks
  • partial shading
  • Photovoltaic Array (PV)

ASJC Scopus subject areas

  • Hardware and Architecture
  • Industrial and Manufacturing Engineering
  • Information Systems and Management
  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality

Cite this

Narayanaswamy, V. S., Ayyanar, R., Spanias, A., Tepedelenlioglu, C., & Srinivasan, D. (2019). Connection topology optimization in photovoltaic arrays using neural networks. In Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019 (pp. 167-172). [8780242] (Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPHYS.2019.8780242

Connection topology optimization in photovoltaic arrays using neural networks. / Narayanaswamy, Vivek Sivaraman; Ayyanar, Raja; Spanias, Andreas; Tepedelenlioglu, Cihan; Srinivasan, Devarajan.

Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 167-172 8780242 (Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Narayanaswamy, VS, Ayyanar, R, Spanias, A, Tepedelenlioglu, C & Srinivasan, D 2019, Connection topology optimization in photovoltaic arrays using neural networks. in Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019., 8780242, Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 167-172, 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019, Taipei, Taiwan, Province of China, 5/6/19. https://doi.org/10.1109/ICPHYS.2019.8780242
Narayanaswamy VS, Ayyanar R, Spanias A, Tepedelenlioglu C, Srinivasan D. Connection topology optimization in photovoltaic arrays using neural networks. In Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 167-172. 8780242. (Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019). https://doi.org/10.1109/ICPHYS.2019.8780242
Narayanaswamy, Vivek Sivaraman ; Ayyanar, Raja ; Spanias, Andreas ; Tepedelenlioglu, Cihan ; Srinivasan, Devarajan. / Connection topology optimization in photovoltaic arrays using neural networks. Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 167-172 (Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019).
@inproceedings{e18b626466744dbba87343c2c6d7adb3,
title = "Connection topology optimization in photovoltaic arrays using neural networks",
abstract = "A cyber-physical system (CPS) approach for optimizing the output power of photovoltaic (PV) energy systems is proposed. In particular, a novel connection topology reconfiguration strategy for PV arrays to maximize power output under partial shading conditions using neural networks is put forth. Depending upon an irradiance/shading profile of the panels, topologies, namely series parallel (SP), total cross tied (TCT) or bridge link (BL) produce different maximum power points (MPP). The connection topology of the PV array that provides the maximum power output is chosen using a multi-layer perceptron. The simulation results show that empirically an output power increase of 12{\%} can be achieved through reconfiguration. The method proposed can be implemented in any CPS PV system with switching capabilities and is simple to implement.",
keywords = "CPS, IoT energy systems, machine learning, neural networks, partial shading, Photovoltaic Array (PV)",
author = "Narayanaswamy, {Vivek Sivaraman} and Raja Ayyanar and Andreas Spanias and Cihan Tepedelenlioglu and Devarajan Srinivasan",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICPHYS.2019.8780242",
language = "English (US)",
series = "Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "167--172",
booktitle = "Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019",

}

TY - GEN

T1 - Connection topology optimization in photovoltaic arrays using neural networks

AU - Narayanaswamy, Vivek Sivaraman

AU - Ayyanar, Raja

AU - Spanias, Andreas

AU - Tepedelenlioglu, Cihan

AU - Srinivasan, Devarajan

PY - 2019/5/1

Y1 - 2019/5/1

N2 - A cyber-physical system (CPS) approach for optimizing the output power of photovoltaic (PV) energy systems is proposed. In particular, a novel connection topology reconfiguration strategy for PV arrays to maximize power output under partial shading conditions using neural networks is put forth. Depending upon an irradiance/shading profile of the panels, topologies, namely series parallel (SP), total cross tied (TCT) or bridge link (BL) produce different maximum power points (MPP). The connection topology of the PV array that provides the maximum power output is chosen using a multi-layer perceptron. The simulation results show that empirically an output power increase of 12% can be achieved through reconfiguration. The method proposed can be implemented in any CPS PV system with switching capabilities and is simple to implement.

AB - A cyber-physical system (CPS) approach for optimizing the output power of photovoltaic (PV) energy systems is proposed. In particular, a novel connection topology reconfiguration strategy for PV arrays to maximize power output under partial shading conditions using neural networks is put forth. Depending upon an irradiance/shading profile of the panels, topologies, namely series parallel (SP), total cross tied (TCT) or bridge link (BL) produce different maximum power points (MPP). The connection topology of the PV array that provides the maximum power output is chosen using a multi-layer perceptron. The simulation results show that empirically an output power increase of 12% can be achieved through reconfiguration. The method proposed can be implemented in any CPS PV system with switching capabilities and is simple to implement.

KW - CPS

KW - IoT energy systems

KW - machine learning

KW - neural networks

KW - partial shading

KW - Photovoltaic Array (PV)

UR - http://www.scopus.com/inward/record.url?scp=85070899353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070899353&partnerID=8YFLogxK

U2 - 10.1109/ICPHYS.2019.8780242

DO - 10.1109/ICPHYS.2019.8780242

M3 - Conference contribution

T3 - Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019

SP - 167

EP - 172

BT - Proceedings - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -