In this paper, the modelling and fault monitoring methods of virtual power plants are investigated. Aiming at the risks faced by the virtual power plant, a virtual power plant dynamic model based on BPNN is proposed, which uses neural networks to establish the relationship between the uncertainty factors and the technical parameters of the virtual power plant, and adjusts the technical parameters of the virtual power plant in real time according to the size of the uncertainty factors. The technical parameters of the virtual power plant are optimised to obtain the parameters that maintain the optimal performance of the virtual power plant. At the same time, in order to be able to comprehensively monitor the failure of the virtual power plant, play a role in early warning, starting from the real-time database of the equipment, the data from a variety of sources to the equipment as the centre of the fusion. Multiple state parameters of the equipment are tracked in real time and displayed in the form of trend graphs, which completes the analysis of the parameters of the fault characteristics in the database and achieves a nonlinear mapping from characteristics and signs to the cause of the fault and the type of fault. Based on the BPNN dynamic model, the SMAPE is 6.51%, and after using the model constructed in this paper to monitor the virtual power plant, the failure rate of the virtual power plant decreases month by month, and the failure rate is much smaller than that before the model is used. It verifies the good performance of the method of this paper, and also shows that the method of this paper has a broad application prospect in the field of fault monitoring and warning of virtual power plant.
1970-2025 CP (Manitoba, Canada) unless otherwise stated.