Abstract:

Aiming at the “double-high” characteristics of new-type power systems with high penetration of renewable energy and high proportion of connected power electronic equipment,as well as the regulation difficulties caused by the volatility and intermittency of new energy generation and large-scale access of electric vehicles,a load regulation optimization method considering the characteristics of new-type power systems is proposed.Accurate day-ahead forecasting of new energy generation is realized via back propagation (BP) neural network,and forecasting of conventional station-area power loads is completed by time-series neural network.A calculation model for electric vehicle charging demand is constructed to estimate the charging demand of electric vehicles in the station area.Finally,combined with the temporal characteristics of new energy generation and conventional loads,an optimization strategy for user-side load regulation is designed.Accurate matching between electric vehicle charging schedules,the peak output of new energy generation and the valley value of conventional loads is achieved,and technical support is provided for the stable operation of new-type power systems and the realization of the “dual carbon” goals.

Key words: new-type power system, load regulation, new energy consumption, electric vehicles, neural network prediction, peak-valley difference optimization