Experiments and Comparison of Digital Twinning of Photovoltaic Panels by Machine Learning Models and a Cyber-Physical Model in Modelica

被引：20

作者：

Delussu, Federico ^{[1
]}

Manzione, Davide ^{[3
]}

Meo, Rosa ^{[1
]}

Ottino, Gabriele ^{[3
]}

Asare, Mark ^{[2
]}

机构：

[1] Univ Torino, Dipartimento Informat, I-10124 Turin, Italy

[2] Univ Torino, Dipartimento Matemat, I-10124 Turin, Italy

[3] DOFWARE Srl, I-10099 Turin, Italy

来源：

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS | 2022年 / 18卷 / 06期

关键词：

Object oriented modeling; Predictive models; Mathematical model; Data models; Production; Integrated circuit modeling; Computational modeling; Anomaly detection; cyber-physical system; energy prediction; energy production; long short term memory (LSTM); Modelica; photovoltaic (PV) panels; PV MODULE; PREDICTION;

D O I：

10.1109/TII.2021.3108688

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We present two approaches for digital twinning in the context of the forecast of power production by photovoltaic panels. We employ two digital models that are complementary: the first one is a cyber-physical system, simulating the physical properties of a photovoltaic panel, built by the open- source object-oriented modeling language Modelica. The second model is data-driven, obtained by the application of machine learning techniques on the data collected in an installation of the equipment. Both approaches make use of data from the weather forecast of each day. We compare the results of the two approaches. Finally, we integrate them in more sophisticated hybrid systems that get the benefits of both.

引用

页码：4018 / 4028

页数：11

共 38 条

[1]

Altché F, 2017, IEEE INT C INTELL TR

[2]

Altshuller D., 2017, P 12 INT MOD C PRAG, P477

[3]

[Anonymous], 2002, P MOD

[4] LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT [J].

BENGIO, Y ;

SIMARD, P ;

FRASCONI, P .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :157-166

[5]

Box G. E. P., 2016, TIME SERIES ANAL FOR, V5th

[6]

Brkic J., 2019, P INT MOD C REG GERM, P16

[7]

Chollet F., 2018, Keras: Thepython deep learning library, pascl

[8]

Chung Junyoung, 2014, EMPIRICAL EVALUATION

[9] On the analytical approach for modeling photovoltaic systems behavior [J].

Cubas, Javier ;

Pindado, Santiago ;

Victoria, Marta .

JOURNAL OF POWER SOURCES, 2014, 247 :467-474

[10]

El-Shimi Ahmed., 2012, Proceedings of the 2012 USENIX conference on Annual Technical Conference, USENIX ATC'12, P26

← 1 2 3 4 →