Smart Grid Optimization with Blockchain Based Decentralized Genetic Algorithm

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.