EV charging load temporal-spatial distribution prediction method based on real-time traffic and temperature

Abstract

The invention relates to an EV charging load temporal-spatial distribution prediction method based on real-time traffic and temperature, and belongs to the field of intelligent power grids. The method comprises the steps that S1, various electric vehicles are classified, and the space transferring and charging characteristics of the electric vehicles are analyzed; S2, an urban traffic network is subjected to abstract simulation by utilizing the trip chain theory and a graph theory method; S3, time-space shift models of the electric vehicles are built through Monte-Carlo simulation and a random shortest circuit method based on the Markovian decision; S4, a temperature and traffic energy consumption model is established according to actual test data of the electric vehicles. The method has universality, is suitable for regional distribution network analysis, can conveniently and effectively calculate the temporal-spatial distribution situation in an urban area and can predict charging load changes when the traffic condition and the temperature condition change, and prediction results provide a basis for research of charging station planning, load scheduling and the like.

Description

technical field [0001] The invention belongs to the field of smart grids, and relates to a method for predicting the temporal and spatial distribution of EV charging loads in consideration of real-time traffic and temperature. Background technique [0002] With the adjustment of the world's energy structure and the development of automobile industry technology, electric vehicles (EV) are the main development direction of new energy vehicles. The integration of large-scale electric vehicles will have a non-negligible impact on the planning and operation of the power system, including the increase in load, the increase in the difficulty of optimal control of power grid operation, the impact on power quality, and new requirements for distribution network planning. The basis for solving the above problems is to effectively predict the spatio-temporal distribution of charging load, so there is an urgent need to establish an accurate and effective load forecasting model. [0003]...

AI Technical Summary

Problems solved by technology

However, the above studies are mostly based on functional plots for spatial division, which cannot meet the accuracy requirements of analyzing spatial distribution for power grid planning and operation.

Existing literature proposes a method for predicting the spatio-temporal distribution of charging load based on the traffic travel matrix and cloud model. The different travel and charging modes of similar electric vehicles also ignore the impact of environmental factors on load forecasting

Images