Future smart grids are expected to be equipped with a multitude of distributed and connected devices, able to measure, manage and control the state of the grid. In this view, the presence of distributed devices, with spare computational capabilities, allows the development of Distributed Machine Learning (ML) algorithms, aiming at performing the analyses and optimizations needed to ensure the correct grid operation. This work aims to present a new Decentralized Genetic Algorithm (DGA) approach able to perform, form a global perspective, the optimization of the network operation, showing resilience to malfunctioning and cyber-attacks to the distributed Internet of Things (IoT) devices. This result has been achieved by implementing an immutable, certified and decentralized blockchain based master ledger, which serves as the coordinating node among all the distributed computing devices. The proposed methodology has been tested considering an optimal scheduling problem in a local MV network, with high penetration of Distributed Renewable Generation and Controllable Loads.

Smart Grid Optimization with Blockchain Based Decentralized Genetic Algorithm

Mureddu, Mario
Conceptualization
;
Ghiani, Emilio
Writing – Review & Editing
;
Pilo, Fabrizio
Supervision
2020-01-01

Abstract

Future smart grids are expected to be equipped with a multitude of distributed and connected devices, able to measure, manage and control the state of the grid. In this view, the presence of distributed devices, with spare computational capabilities, allows the development of Distributed Machine Learning (ML) algorithms, aiming at performing the analyses and optimizations needed to ensure the correct grid operation. This work aims to present a new Decentralized Genetic Algorithm (DGA) approach able to perform, form a global perspective, the optimization of the network operation, showing resilience to malfunctioning and cyber-attacks to the distributed Internet of Things (IoT) devices. This result has been achieved by implementing an immutable, certified and decentralized blockchain based master ledger, which serves as the coordinating node among all the distributed computing devices. The proposed methodology has been tested considering an optimal scheduling problem in a local MV network, with high penetration of Distributed Renewable Generation and Controllable Loads.
2020
978-1-7281-5508-1
Decentralized Machine Learning, Genetic Algorithms, Smart Grid Optimization, Internet of Things, Blockchain
File in questo prodotto:
File Dimensione Formato  
PES_GM_2020 Mureddu Ghiani Pilo.pdf

Solo gestori archivio

Tipologia: versione editoriale
Dimensione 498.78 kB
Formato Adobe PDF
498.78 kB 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/11584/303849
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 6
social impact