In the modern scenario of smart-grids, the concept of virtual power plant (VPP) is undoubtedly a cornerstone for the smooth integration of renewable energy sources into existing energy systems with a high penetration level. A VPP is the aggregation of decentralized medium-scale power sources, including photovoltaic and wind power plants, combined heat and power units, as well as demand-responsive loads and storage systems, with a twofold objective. On one hand, VPP relieves the stability and dispatchability problems on the external smart grid since it can be operated on an individual basis, appearing as a single system on the whole. On the other hand, VPP improves flexibility coming from all the networked units and enable traders to enhance forecasting and trading programs of renewable energies. This paper proposes a novel distributed decentralized prediction method for the management of VPPs. The novelty of the proposed technique is to effectively combine the concepts of neural networks and machine learning with a distributed architecture that is suitable for the aggregation purposes of the VPP.

A neural network based prediction system of distributed generation for the management of microgrids / Rosato, Antonello; Panella, Massimo; Araneo, Rodolfo; Andreotti, Amedeo. - In: IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS. - ISSN 0093-9994. - 55:6(2019), pp. 7092-7102. [10.1109/TIA.2019.2916758]

A neural network based prediction system of distributed generation for the management of microgrids

Rosato, Antonello;Panella, Massimo;Araneo, Rodolfo
;
2019

Abstract

In the modern scenario of smart-grids, the concept of virtual power plant (VPP) is undoubtedly a cornerstone for the smooth integration of renewable energy sources into existing energy systems with a high penetration level. A VPP is the aggregation of decentralized medium-scale power sources, including photovoltaic and wind power plants, combined heat and power units, as well as demand-responsive loads and storage systems, with a twofold objective. On one hand, VPP relieves the stability and dispatchability problems on the external smart grid since it can be operated on an individual basis, appearing as a single system on the whole. On the other hand, VPP improves flexibility coming from all the networked units and enable traders to enhance forecasting and trading programs of renewable energies. This paper proposes a novel distributed decentralized prediction method for the management of VPPs. The novelty of the proposed technique is to effectively combine the concepts of neural networks and machine learning with a distributed architecture that is suitable for the aggregation purposes of the VPP.
2019
distributed generation (DG); distributed methods; neural networks; photovoltaic (PV) plants; virtual power plants (VPPs)
01 Pubblicazione su rivista::01a Articolo in rivista
A neural network based prediction system of distributed generation for the management of microgrids / Rosato, Antonello; Panella, Massimo; Araneo, Rodolfo; Andreotti, Amedeo. - In: IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS. - ISSN 0093-9994. - 55:6(2019), pp. 7092-7102. [10.1109/TIA.2019.2916758]
File allegati a questo prodotto
File Dimensione Formato  
Rosato_A Neural_2019.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.74 MB
Formato Adobe PDF
1.74 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1310759
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 49
  • ???jsp.display-item.citation.isi??? 41
social impact