Abstract
Nuclear power is an indispensable part of modern energy systems. To operate the nuclear power plants safely and reliably, it is crucial to greatly develop the predictive maintenance of nuclear infrastructure with the support of various smart sensors and big data analytics. To this end, this paper proposes a novel collaborative edge computing-enabled solution for predictive maintenance in nuclear power plants, from which a key problem of efficiently allocating some edge computing tasks is formulated. Specifically, considering huge amounts of industrial data are continuously generated during plant operations, we first present a three-layer predictive maintenance computing framework for nuclear power plants. Subsequently, to timely process these data in some distributed and heterogeneous industrial computing nodes, a complicated scheduling optimization model with some interdependent computational tasks is established. To lower the size of model, we also introduce some reduction strategies. Finally, an actual predictive maintenance scenario in nuclear power plant is chosen and some algorithms are taken for comparisons.
