Charging and discharging optimization scheduling method based on nonlinear quantile interval prediction

Abstract

The invention relates to a charge and discharge optimization scheduling method based on nonlinear quantile interval prediction, which comprises the following steps of: 1) constructing a nonlinear quantile regression prediction model, and predicting to obtain an interval prediction result of access time and departure time of an electric vehicle; 2) improving the prediction precision of the prediction model through a Stacking fusion framework, integrating a plurality of nonlinear prediction functions to select an optimal prediction result, and converting the optimal prediction result into interval prediction based on quantiles; 3) considering various distributed power supplies and refined battery operation related constraints to construct a robust economic dispatching model; and 4) solving the robust economic dispatching model by adopting a C&CG method, and obtaining dispatching statistical information, including the charging and discharging power and the charge state of the electric vehicle, the wind power photovoltaic output condition and the park electricity purchasing power. Compared with the prior art, the method has the advantages of rapidness, reliability, high feasibility, wide application range and the like.

Description

technical field [0001] The invention relates to the field of optimal scheduling of electric vehicles, in particular to a charging and discharging optimal scheduling method for electric vehicles based on nonlinear quantile interval prediction. Background technique [0002] Due to the uncertainty of electric vehicle (EV) charging and discharging demand, its grid connection time has the characteristics of randomness, intermittent and time fluctuation, which will bring difficulties to the optimal scheduling of the park. [0003] When optimal scheduling is carried out in the park, it is difficult to know the time of EV access and departure, and day-ahead prediction is required. Most of the existing technical literature is based on a specific probability distribution function to predict the time interval of EV access and departure. However, for electric vehicles in small charging stations, due to the limited number of samples, it is difficult to effectively calculate the probabili...

AI Technical Summary

Problems solved by technology

Most of the existing technology has fixed operating constraints on the battery structure, does not dynamically analyze the battery operating boundary, and does not solve the problem of frequent charging and discharging conversion of electric vehicles

Images