Charging space-time prediction method of mixed isomorphic and heterogeneous depth map neural network

Abstract

The invention provides a charging space-time prediction method of a hybrid isomorphic and heterogeneous depth map neural network. The method comprises a deep neural network module, a multi-step adaptive dynamic programming module, a graphic neural network module and a hybrid isomorphic and heterogeneous module. The deep neural network module realizes a function from automatic language translation to image recognition, and models high-complexity data through multi-layer nonlinear transformation; the multi-step self-adaptive dynamic programming module comprises a self-adaptive dynamic programming method and a self-adaptive multi-step correction method and is used for solving the problem of optimization control of a large-scale complex nonlinear system; the graph neural network module constructs an electric vehicle charging space-time prediction model; the hybrid isomorphic and heterogeneous module comprises an isomorphic network and a heterogeneous network, and is used for processing the same type and different types of information; the method can effectively solve the problem that the charging load of the electric vehicle has randomness in time and space and is difficult to predict.

Description

technical field [0001] The invention belongs to the technical field of electric vehicles, and relates to a method for predicting charging time and space based on an artificial intelligence method, which is applicable to the distribution of charging piles for electric vehicles. Background technique [0002] Nowadays, problems such as energy shortage, climate warming and environmental pollution are becoming more and more serious. Motor vehicle exhaust pollution is one of the main sources of air pollution. Many countries and regions have formulated a timetable for banning the sale of fuel vehicles. For example, in March 2019, China's Hainan Province issued the "Development Plan for Clean Energy Vehicles in Hainan Province", which was the first in China to propose that the sale of fuel vehicles in the province be banned in 2030. Driven by policies and markets, the scale of electric vehicles and the demand for charging will usher in a new round of growth, and the connection of l...

AI Technical Summary

Problems solved by technology

The hybrid isomorphic and heterogeneous deep graph neural network charging spatiotemporal prediction method can be applied to complex road conditions and the distribution of charging piles with a large flow of people

The difference between this method and the traditional space-time prediction method of electric vehicle load based on dynamic traffic flow: (1) the multi-step adaptive dynamic programming can solve the real-time control problem that the traditional dynamic programming is not suitable for complex nonlinear systems; (2) the hybrid The charging space-time prediction method of isomorphic and heterogeneous deep graph neural network is not only a simple prediction of charging space-time, but also introduces graph neural network, which improves the accuracy of the method

Images